Corrected header file documentation comment.

src/render/SDL_d3dmath.c

@@ -0,0 +1,136 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../SDL_internal.h"
+
+#if (SDL_VIDEO_RENDER_D3D || SDL_VIDEO_RENDER_D3D11) && !SDL_RENDER_DISABLED
+#include "SDL_stdinc.h"
+
+#include "SDL_d3dmath.h"
+
+/* Direct3D matrix math functions */
+
+Float4X4 MatrixIdentity()
+{
+    Float4X4 m;
+    SDL_zero(m);
+    m._11 = 1.0f;
+    m._22 = 1.0f;
+    m._33 = 1.0f;
+    m._44 = 1.0f;
+    return m;
+}
+
+Float4X4 MatrixMultiply(Float4X4 M1, Float4X4 M2)
+{
+    Float4X4 m;
+    m._11 = M1._11 * M2._11 + M1._12 * M2._21 + M1._13 * M2._31 + M1._14 * M2._41;
+    m._12 = M1._11 * M2._12 + M1._12 * M2._22 + M1._13 * M2._32 + M1._14 * M2._42;
+    m._13 = M1._11 * M2._13 + M1._12 * M2._23 + M1._13 * M2._33 + M1._14 * M2._43;
+    m._14 = M1._11 * M2._14 + M1._12 * M2._24 + M1._13 * M2._34 + M1._14 * M2._44;
+    m._21 = M1._21 * M2._11 + M1._22 * M2._21 + M1._23 * M2._31 + M1._24 * M2._41;
+    m._22 = M1._21 * M2._12 + M1._22 * M2._22 + M1._23 * M2._32 + M1._24 * M2._42;
+    m._23 = M1._21 * M2._13 + M1._22 * M2._23 + M1._23 * M2._33 + M1._24 * M2._43;
+    m._24 = M1._21 * M2._14 + M1._22 * M2._24 + M1._23 * M2._34 + M1._24 * M2._44;
+    m._31 = M1._31 * M2._11 + M1._32 * M2._21 + M1._33 * M2._31 + M1._34 * M2._41;
+    m._32 = M1._31 * M2._12 + M1._32 * M2._22 + M1._33 * M2._32 + M1._34 * M2._42;
+    m._33 = M1._31 * M2._13 + M1._32 * M2._23 + M1._33 * M2._33 + M1._34 * M2._43;
+    m._34 = M1._31 * M2._14 + M1._32 * M2._24 + M1._33 * M2._34 + M1._34 * M2._44;
+    m._41 = M1._41 * M2._11 + M1._42 * M2._21 + M1._43 * M2._31 + M1._44 * M2._41;
+    m._42 = M1._41 * M2._12 + M1._42 * M2._22 + M1._43 * M2._32 + M1._44 * M2._42;
+    m._43 = M1._41 * M2._13 + M1._42 * M2._23 + M1._43 * M2._33 + M1._44 * M2._43;
+    m._44 = M1._41 * M2._14 + M1._42 * M2._24 + M1._43 * M2._34 + M1._44 * M2._44;
+    return m;
+}
+
+Float4X4 MatrixScaling(float x, float y, float z)
+{
+    Float4X4 m;
+    SDL_zero(m);
+    m._11 = x;
+    m._22 = y;
+    m._33 = z;
+    m._44 = 1.0f;
+    return m;
+}
+
+Float4X4 MatrixTranslation(float x, float y, float z)
+{
+    Float4X4 m;
+    SDL_zero(m);
+    m._11 = 1.0f;
+    m._22 = 1.0f;
+    m._33 = 1.0f;
+    m._44 = 1.0f;
+    m._41 = x;
+    m._42 = y;
+    m._43 = z;
+    return m;
+}
+
+Float4X4 MatrixRotationX(float r)
+{
+    float sinR = SDL_sinf(r);
+    float cosR = SDL_cosf(r);
+    Float4X4 m;
+    SDL_zero(m);
+    m._11 = 1.0f;
+    m._22 = cosR;
+    m._23 = sinR;
+    m._32 = -sinR;
+    m._33 = cosR;
+    m._44 = 1.0f;
+    return m;
+}
+
+Float4X4 MatrixRotationY(float r)
+{
+    float sinR = SDL_sinf(r);
+    float cosR = SDL_cosf(r);
+    Float4X4 m;
+    SDL_zero(m);
+    m._11 = cosR;
+    m._13 = -sinR;
+    m._22 = 1.0f;
+    m._31 = sinR;
+    m._33 = cosR;
+    m._44 = 1.0f;
+    return m;
+}
+
+Float4X4 MatrixRotationZ(float r)
+{
+    float sinR = SDL_sinf(r);
+    float cosR = SDL_cosf(r);
+    Float4X4 m;
+    SDL_zero(m);
+    m._11 = cosR;
+    m._12 = sinR;
+    m._21 = -sinR;
+    m._22 = cosR;
+    m._33 = 1.0f;
+    m._44 = 1.0f;
+    return m;
+
+}
+
+#endif /* (SDL_VIDEO_RENDER_D3D || SDL_VIDEO_RENDER_D3D11) && !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/SDL_d3dmath.h

@@ -0,0 +1,72 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../SDL_internal.h"
+
+#if (SDL_VIDEO_RENDER_D3D || SDL_VIDEO_RENDER_D3D11) && !SDL_RENDER_DISABLED
+
+/* Direct3D matrix math functions */
+
+typedef struct
+{
+    float x;
+    float y;
+} Float2;
+
+typedef struct
+{
+    float x;
+    float y;
+    float z;
+} Float3;
+
+typedef struct
+{
+    float x;
+    float y;
+    float z;
+    float w;
+} Float4;
+
+typedef struct
+{
+    union {
+        struct {
+            float _11, _12, _13, _14;
+            float _21, _22, _23, _24;
+            float _31, _32, _33, _34;
+            float _41, _42, _43, _44;
+        };
+        float m[4][4];
+    };
+} Float4X4;
+
+
+Float4X4 MatrixIdentity();
+Float4X4 MatrixMultiply(Float4X4 M1, Float4X4 M2);
+Float4X4 MatrixScaling(float x, float y, float z);
+Float4X4 MatrixTranslation(float x, float y, float z);
+Float4X4 MatrixRotationX(float r);
+Float4X4 MatrixRotationY(float r);
+Float4X4 MatrixRotationZ(float r);
+
+#endif /* (SDL_VIDEO_RENDER_D3D || SDL_VIDEO_RENDER_D3D11) && !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/SDL_sysrender.h

@@ -0,0 +1,202 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../SDL_internal.h"
+
+#ifndef _SDL_sysrender_h
+#define _SDL_sysrender_h
+
+#include "SDL_render.h"
+#include "SDL_events.h"
+#include "SDL_yuv_sw_c.h"
+
+/* The SDL 2D rendering system */
+
+typedef struct SDL_RenderDriver SDL_RenderDriver;
+
+typedef struct
+{
+    float x;
+    float y;
+} SDL_FPoint;
+
+typedef struct
+{
+    float x;
+    float y;
+    float w;
+    float h;
+} SDL_FRect;
+
+/* Define the SDL texture structure */
+struct SDL_Texture
+{
+    const void *magic;
+    Uint32 format;              /**< The pixel format of the texture */
+    int access;                 /**< SDL_TextureAccess */
+    int w;                      /**< The width of the texture */
+    int h;                      /**< The height of the texture */
+    int modMode;                /**< The texture modulation mode */
+    SDL_BlendMode blendMode;    /**< The texture blend mode */
+    Uint8 r, g, b, a;           /**< Texture modulation values */
+
+    SDL_Renderer *renderer;
+
+    /* Support for formats not supported directly by the renderer */
+    SDL_Texture *native;
+    SDL_SW_YUVTexture *yuv;
+    void *pixels;
+    int pitch;
+    SDL_Rect locked_rect;
+
+    void *driverdata;           /**< Driver specific texture representation */
+
+    SDL_Texture *prev;
+    SDL_Texture *next;
+};
+
+/* Define the SDL renderer structure */
+struct SDL_Renderer
+{
+    const void *magic;
+
+    void (*WindowEvent) (SDL_Renderer * renderer, const SDL_WindowEvent *event);
+    int (*GetOutputSize) (SDL_Renderer * renderer, int *w, int *h);
+    int (*CreateTexture) (SDL_Renderer * renderer, SDL_Texture * texture);
+    int (*SetTextureColorMod) (SDL_Renderer * renderer,
+                               SDL_Texture * texture);
+    int (*SetTextureAlphaMod) (SDL_Renderer * renderer,
+                               SDL_Texture * texture);
+    int (*SetTextureBlendMode) (SDL_Renderer * renderer,
+                                SDL_Texture * texture);
+    int (*UpdateTexture) (SDL_Renderer * renderer, SDL_Texture * texture,
+                          const SDL_Rect * rect, const void *pixels,
+                          int pitch);
+    int (*UpdateTextureYUV) (SDL_Renderer * renderer, SDL_Texture * texture,
+                            const SDL_Rect * rect,
+                            const Uint8 *Yplane, int Ypitch,
+                            const Uint8 *Uplane, int Upitch,
+                            const Uint8 *Vplane, int Vpitch);
+    int (*LockTexture) (SDL_Renderer * renderer, SDL_Texture * texture,
+                        const SDL_Rect * rect, void **pixels, int *pitch);
+    void (*UnlockTexture) (SDL_Renderer * renderer, SDL_Texture * texture);
+    int (*SetRenderTarget) (SDL_Renderer * renderer, SDL_Texture * texture);
+    int (*UpdateViewport) (SDL_Renderer * renderer);
+    int (*UpdateClipRect) (SDL_Renderer * renderer);
+    int (*RenderClear) (SDL_Renderer * renderer);
+    int (*RenderDrawPoints) (SDL_Renderer * renderer, const SDL_FPoint * points,
+                             int count);
+    int (*RenderDrawLines) (SDL_Renderer * renderer, const SDL_FPoint * points,
+                            int count);
+    int (*RenderFillRects) (SDL_Renderer * renderer, const SDL_FRect * rects,
+                            int count);
+    int (*RenderCopy) (SDL_Renderer * renderer, SDL_Texture * texture,
+                       const SDL_Rect * srcrect, const SDL_FRect * dstrect);
+    int (*RenderCopyEx) (SDL_Renderer * renderer, SDL_Texture * texture,
+                       const SDL_Rect * srcquad, const SDL_FRect * dstrect,
+                       const double angle, const SDL_FPoint *center, const SDL_RendererFlip flip);
+    int (*RenderReadPixels) (SDL_Renderer * renderer, const SDL_Rect * rect,
+                             Uint32 format, void * pixels, int pitch);
+    void (*RenderPresent) (SDL_Renderer * renderer);
+    void (*DestroyTexture) (SDL_Renderer * renderer, SDL_Texture * texture);
+
+    void (*DestroyRenderer) (SDL_Renderer * renderer);
+
+    int (*GL_BindTexture) (SDL_Renderer * renderer, SDL_Texture *texture, float *texw, float *texh);
+    int (*GL_UnbindTexture) (SDL_Renderer * renderer, SDL_Texture *texture);
+
+    /* The current renderer info */
+    SDL_RendererInfo info;
+
+    /* The window associated with the renderer */
+    SDL_Window *window;
+    SDL_bool hidden;
+
+    /* The logical resolution for rendering */
+    int logical_w;
+    int logical_h;
+    int logical_w_backup;
+    int logical_h_backup;
+
+    /* The drawable area within the window */
+    SDL_Rect viewport;
+    SDL_Rect viewport_backup;
+
+    /* The clip rectangle within the window */
+    SDL_Rect clip_rect;
+    SDL_Rect clip_rect_backup;
+
+    /* Wether or not the clipping rectangle is used. */
+    SDL_bool clipping_enabled;
+    SDL_bool clipping_enabled_backup;
+
+    /* The render output coordinate scale */
+    SDL_FPoint scale;
+    SDL_FPoint scale_backup;
+
+    /* The list of textures */
+    SDL_Texture *textures;
+    SDL_Texture *target;
+
+    Uint8 r, g, b, a;                   /**< Color for drawing operations values */
+    SDL_BlendMode blendMode;            /**< The drawing blend mode */
+
+    void *driverdata;
+};
+
+/* Define the SDL render driver structure */
+struct SDL_RenderDriver
+{
+    SDL_Renderer *(*CreateRenderer) (SDL_Window * window, Uint32 flags);
+
+    /* Info about the renderer capabilities */
+    SDL_RendererInfo info;
+};
+
+#if !SDL_RENDER_DISABLED
+
+#if SDL_VIDEO_RENDER_D3D
+extern SDL_RenderDriver D3D_RenderDriver;
+#endif
+#if SDL_VIDEO_RENDER_D3D11
+extern SDL_RenderDriver D3D11_RenderDriver;
+#endif
+#if SDL_VIDEO_RENDER_OGL
+extern SDL_RenderDriver GL_RenderDriver;
+#endif
+#if SDL_VIDEO_RENDER_OGL_ES2
+extern SDL_RenderDriver GLES2_RenderDriver;
+#endif
+#if SDL_VIDEO_RENDER_OGL_ES
+extern SDL_RenderDriver GLES_RenderDriver;
+#endif
+#if SDL_VIDEO_RENDER_DIRECTFB
+extern SDL_RenderDriver DirectFB_RenderDriver;
+#endif
+#if SDL_VIDEO_RENDER_PSP
+extern SDL_RenderDriver PSP_RenderDriver;
+#endif
+extern SDL_RenderDriver SW_RenderDriver;
+
+#endif /* !SDL_RENDER_DISABLED */
+
+#endif /* _SDL_sysrender_h */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/SDL_yuv_mmx.c

@@ -0,0 +1,431 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../SDL_internal.h"
+
+#if (__GNUC__ > 2) && defined(__i386__) && __OPTIMIZE__ && SDL_ASSEMBLY_ROUTINES
+
+#include "SDL_stdinc.h"
+
+#include "mmx.h"
+
+/* *INDENT-OFF* */
+
+static mmx_t MMX_0080w    = { .ud = {0x00800080, 0x00800080} };
+static mmx_t MMX_00FFw    = { .ud = {0x00ff00ff, 0x00ff00ff} };
+static mmx_t MMX_FF00w    = { .ud = {0xff00ff00, 0xff00ff00} };
+
+static mmx_t MMX_Ycoeff   = { .uw = {0x004a, 0x004a, 0x004a, 0x004a} };
+
+static mmx_t MMX_UbluRGB  = { .uw = {0x0072, 0x0072, 0x0072, 0x0072} };
+static mmx_t MMX_VredRGB  = { .uw = {0x0059, 0x0059, 0x0059, 0x0059} };
+static mmx_t MMX_UgrnRGB  = { .uw = {0xffea, 0xffea, 0xffea, 0xffea} };
+static mmx_t MMX_VgrnRGB  = { .uw = {0xffd2, 0xffd2, 0xffd2, 0xffd2} };
+
+static mmx_t MMX_Ublu5x5  = { .uw = {0x0081, 0x0081, 0x0081, 0x0081} };
+static mmx_t MMX_Vred5x5  = { .uw = {0x0066, 0x0066, 0x0066, 0x0066} };
+static mmx_t MMX_Ugrn565  = { .uw = {0xffe8, 0xffe8, 0xffe8, 0xffe8} };
+static mmx_t MMX_Vgrn565  = { .uw = {0xffcd, 0xffcd, 0xffcd, 0xffcd} };
+
+static mmx_t MMX_red565   = { .uw = {0xf800, 0xf800, 0xf800, 0xf800} };
+static mmx_t MMX_grn565   = { .uw = {0x07e0, 0x07e0, 0x07e0, 0x07e0} };
+
+/**
+   This MMX assembler is my first assembler/MMX program ever.
+   Thus it maybe buggy.
+   Send patches to:
+   mvogt@rhrk.uni-kl.de
+
+   After it worked fine I have "obfuscated" the code a bit to have
+   more parallism in the MMX units. This means I moved
+   initilisation around and delayed other instruction.
+   Performance measurement did not show that this brought any advantage
+   but in theory it _should_ be faster this way.
+
+   The overall performanve gain to the C based dither was 30%-40%.
+   The MMX routine calculates 256bit=8RGB values in each cycle
+   (4 for row1 & 4 for row2)
+
+   The red/green/blue.. coefficents are taken from the mpeg_play
+   player. They look nice, but I dont know if you can have
+   better values, to avoid integer rounding errors.
+
+
+   IMPORTANT:
+   ==========
+
+   It is a requirement that the cr/cb/lum are 8 byte aligned and
+   the out are 16byte aligned or you will/may get segfaults
+
+*/
+
+void ColorRGBDitherYV12MMX1X( int *colortab, Uint32 *rgb_2_pix,
+                              unsigned char *lum, unsigned char *cr,
+                              unsigned char *cb, unsigned char *out,
+                              int rows, int cols, int mod )
+{
+    Uint32 *row1;
+    Uint32 *row2;
+
+    unsigned char* y = lum +cols*rows;    /* Pointer to the end */
+    int x = 0;
+    row1 = (Uint32 *)out;                 /* 32 bit target */
+    row2 = (Uint32 *)out+cols+mod;        /* start of second row */
+    mod = (mod+cols+mod)*4;               /* increment for row1 in byte */
+
+    __asm__ __volatile__ (
+        /* tap dance to workaround the inability to use %%ebx at will... */
+        /*  move one thing to the stack... */
+        "pushl $0\n"  /* save a slot on the stack. */
+        "pushl %%ebx\n"  /* save %%ebx. */
+        "movl %0, %%ebx\n"  /* put the thing in ebx. */
+        "movl %%ebx,4(%%esp)\n"  /* put the thing in the stack slot. */
+        "popl %%ebx\n"  /* get back %%ebx (the PIC register). */
+
+        ".align 8\n"
+        "1:\n"
+
+        /* create Cr (result in mm1) */
+        "pushl %%ebx\n"
+        "movl 4(%%esp),%%ebx\n"
+        "movd (%%ebx),%%mm1\n"   /*         0  0  0  0  v3 v2 v1 v0 */
+        "popl %%ebx\n"
+        "pxor %%mm7,%%mm7\n"      /*         00 00 00 00 00 00 00 00 */
+        "movd (%2), %%mm2\n"           /*    0  0  0  0 l3 l2 l1 l0 */
+        "punpcklbw %%mm7,%%mm1\n" /*         0  v3 0  v2 00 v1 00 v0 */
+        "punpckldq %%mm1,%%mm1\n" /*         00 v1 00 v0 00 v1 00 v0 */
+        "psubw %9,%%mm1\n"        /* mm1-128:r1 r1 r0 r0 r1 r1 r0 r0 */
+
+        /* create Cr_g (result in mm0) */
+        "movq %%mm1,%%mm0\n"           /* r1 r1 r0 r0 r1 r1 r0 r0 */
+        "pmullw %10,%%mm0\n"           /* red*-46dec=0.7136*64 */
+        "pmullw %11,%%mm1\n"           /* red*89dec=1.4013*64 */
+        "psraw  $6, %%mm0\n"           /* red=red/64 */
+        "psraw  $6, %%mm1\n"           /* red=red/64 */
+
+        /* create L1 L2 (result in mm2,mm4) */
+        /* L2=lum+cols */
+        "movq (%2,%4),%%mm3\n"         /*    0  0  0  0 L3 L2 L1 L0 */
+        "punpckldq %%mm3,%%mm2\n"      /*   L3 L2 L1 L0 l3 l2 l1 l0 */
+        "movq %%mm2,%%mm4\n"           /*   L3 L2 L1 L0 l3 l2 l1 l0 */
+        "pand %12,%%mm2\n"             /*   L3 0  L1  0 l3  0 l1  0 */
+        "pand %13,%%mm4\n"             /*   0  L2  0 L0  0 l2  0 l0 */
+        "psrlw $8,%%mm2\n"             /*   0  L3  0 L1  0 l3  0 l1 */
+
+        /* create R (result in mm6) */
+        "movq %%mm2,%%mm5\n"           /*   0 L3  0 L1  0 l3  0 l1 */
+        "movq %%mm4,%%mm6\n"           /*   0 L2  0 L0  0 l2  0 l0 */
+        "paddsw  %%mm1, %%mm5\n"       /* lum1+red:x R3 x R1 x r3 x r1 */
+        "paddsw  %%mm1, %%mm6\n"       /* lum1+red:x R2 x R0 x r2 x r0 */
+        "packuswb %%mm5,%%mm5\n"       /*  R3 R1 r3 r1 R3 R1 r3 r1 */
+        "packuswb %%mm6,%%mm6\n"       /*  R2 R0 r2 r0 R2 R0 r2 r0 */
+        "pxor %%mm7,%%mm7\n"      /*         00 00 00 00 00 00 00 00 */
+        "punpcklbw %%mm5,%%mm6\n"      /*  R3 R2 R1 R0 r3 r2 r1 r0 */
+
+        /* create Cb (result in mm1) */
+        "movd (%1), %%mm1\n"      /*         0  0  0  0  u3 u2 u1 u0 */
+        "punpcklbw %%mm7,%%mm1\n" /*         0  u3 0  u2 00 u1 00 u0 */
+        "punpckldq %%mm1,%%mm1\n" /*         00 u1 00 u0 00 u1 00 u0 */
+        "psubw %9,%%mm1\n"        /* mm1-128:u1 u1 u0 u0 u1 u1 u0 u0 */
+
+        /* create Cb_g (result in mm5) */
+        "movq %%mm1,%%mm5\n"            /* u1 u1 u0 u0 u1 u1 u0 u0 */
+        "pmullw %14,%%mm5\n"            /* blue*-109dec=1.7129*64 */
+        "pmullw %15,%%mm1\n"            /* blue*114dec=1.78125*64 */
+        "psraw  $6, %%mm5\n"            /* blue=red/64 */
+        "psraw  $6, %%mm1\n"            /* blue=blue/64 */
+
+        /* create G (result in mm7) */
+        "movq %%mm2,%%mm3\n"      /*   0  L3  0 L1  0 l3  0 l1 */
+        "movq %%mm4,%%mm7\n"      /*   0  L2  0 L0  0 l2  0 l1 */
+        "paddsw  %%mm5, %%mm3\n"  /* lum1+Cb_g:x G3t x G1t x g3t x g1t */
+        "paddsw  %%mm5, %%mm7\n"  /* lum1+Cb_g:x G2t x G0t x g2t x g0t */
+        "paddsw  %%mm0, %%mm3\n"  /* lum1+Cr_g:x G3  x G1  x g3  x g1 */
+        "paddsw  %%mm0, %%mm7\n"  /* lum1+blue:x G2  x G0  x g2  x g0 */
+        "packuswb %%mm3,%%mm3\n"  /* G3 G1 g3 g1 G3 G1 g3 g1 */
+        "packuswb %%mm7,%%mm7\n"  /* G2 G0 g2 g0 G2 G0 g2 g0 */
+        "punpcklbw %%mm3,%%mm7\n" /* G3 G2 G1 G0 g3 g2 g1 g0 */
+
+        /* create B (result in mm5) */
+        "movq %%mm2,%%mm3\n"         /*   0  L3  0 L1  0 l3  0 l1 */
+        "movq %%mm4,%%mm5\n"         /*   0  L2  0 L0  0 l2  0 l1 */
+        "paddsw  %%mm1, %%mm3\n"     /* lum1+blue:x B3 x B1 x b3 x b1 */
+        "paddsw  %%mm1, %%mm5\n"     /* lum1+blue:x B2 x B0 x b2 x b0 */
+        "packuswb %%mm3,%%mm3\n"     /* B3 B1 b3 b1 B3 B1 b3 b1 */
+        "packuswb %%mm5,%%mm5\n"     /* B2 B0 b2 b0 B2 B0 b2 b0 */
+        "punpcklbw %%mm3,%%mm5\n"    /* B3 B2 B1 B0 b3 b2 b1 b0 */
+
+        /* fill destination row1 (needed are mm6=Rr,mm7=Gg,mm5=Bb) */
+
+        "pxor %%mm2,%%mm2\n"           /*  0  0  0  0  0  0  0  0 */
+        "pxor %%mm4,%%mm4\n"           /*  0  0  0  0  0  0  0  0 */
+        "movq %%mm6,%%mm1\n"           /* R3 R2 R1 R0 r3 r2 r1 r0 */
+        "movq %%mm5,%%mm3\n"           /* B3 B2 B1 B0 b3 b2 b1 b0 */
+
+        /* process lower lum */
+        "punpcklbw %%mm4,%%mm1\n"      /*  0 r3  0 r2  0 r1  0 r0 */
+        "punpcklbw %%mm4,%%mm3\n"      /*  0 b3  0 b2  0 b1  0 b0 */
+        "movq %%mm1,%%mm2\n"           /*  0 r3  0 r2  0 r1  0 r0 */
+        "movq %%mm3,%%mm0\n"           /*  0 b3  0 b2  0 b1  0 b0 */
+        "punpcklwd %%mm1,%%mm3\n"      /*  0 r1  0 b1  0 r0  0 b0 */
+        "punpckhwd %%mm2,%%mm0\n"      /*  0 r3  0 b3  0 r2  0 b2 */
+
+        "pxor %%mm2,%%mm2\n"           /*  0  0  0  0  0  0  0  0 */
+        "movq %%mm7,%%mm1\n"           /* G3 G2 G1 G0 g3 g2 g1 g0 */
+        "punpcklbw %%mm1,%%mm2\n"      /* g3  0 g2  0 g1  0 g0  0 */
+        "punpcklwd %%mm4,%%mm2\n"      /*  0  0 g1  0  0  0 g0  0 */
+        "por %%mm3, %%mm2\n"          /*  0 r1 g1 b1  0 r0 g0 b0 */
+        "movq %%mm2,(%3)\n"          /* wrote out ! row1 */
+
+        "pxor %%mm2,%%mm2\n"           /*  0  0  0  0  0  0  0  0 */
+        "punpcklbw %%mm1,%%mm4\n"      /* g3  0 g2  0 g1  0 g0  0 */
+        "punpckhwd %%mm2,%%mm4\n"      /*  0  0 g3  0  0  0 g2  0 */
+        "por %%mm0, %%mm4\n"          /*  0 r3 g3 b3  0 r2 g2 b2 */
+        "movq %%mm4,8(%3)\n"         /* wrote out ! row1 */
+
+        /* fill destination row2 (needed are mm6=Rr,mm7=Gg,mm5=Bb) */
+        /* this can be done "destructive" */
+        "pxor %%mm2,%%mm2\n"           /*  0  0  0  0  0  0  0  0 */
+        "punpckhbw %%mm2,%%mm6\n"      /*  0 R3  0 R2  0 R1  0 R0 */
+        "punpckhbw %%mm1,%%mm5\n"      /* G3 B3 G2 B2 G1 B1 G0 B0 */
+        "movq %%mm5,%%mm1\n"           /* G3 B3 G2 B2 G1 B1 G0 B0 */
+        "punpcklwd %%mm6,%%mm1\n"      /*  0 R1 G1 B1  0 R0 G0 B0 */
+        "movq %%mm1,(%5)\n"          /* wrote out ! row2 */
+        "punpckhwd %%mm6,%%mm5\n"      /*  0 R3 G3 B3  0 R2 G2 B2 */
+        "movq %%mm5,8(%5)\n"         /* wrote out ! row2 */
+
+        "addl $4,%2\n"            /* lum+4 */
+        "leal 16(%3),%3\n"        /* row1+16 */
+        "leal 16(%5),%5\n"        /* row2+16 */
+        "addl $2,(%%esp)\n"        /* cr+2 */
+        "addl $2,%1\n"           /* cb+2 */
+
+        "addl $4,%6\n"            /* x+4 */
+        "cmpl %4,%6\n"
+
+        "jl 1b\n"
+        "addl %4,%2\n" /* lum += cols */
+        "addl %8,%3\n" /* row1+= mod */
+        "addl %8,%5\n" /* row2+= mod */
+        "movl $0,%6\n" /* x=0 */
+        "cmpl %7,%2\n"
+        "jl 1b\n"
+
+        "addl $4,%%esp\n"  /* get rid of the stack slot we reserved. */
+        "emms\n"  /* reset MMX registers. */
+        :
+        : "m" (cr), "r"(cb),"r"(lum),
+          "r"(row1),"r"(cols),"r"(row2),"m"(x),"m"(y),"m"(mod),
+          "m"(MMX_0080w),"m"(MMX_VgrnRGB),"m"(MMX_VredRGB),
+          "m"(MMX_FF00w),"m"(MMX_00FFw),"m"(MMX_UgrnRGB),
+          "m"(MMX_UbluRGB)
+    );
+}
+
+void Color565DitherYV12MMX1X( int *colortab, Uint32 *rgb_2_pix,
+                             unsigned char *lum, unsigned char *cr,
+                             unsigned char *cb, unsigned char *out,
+                             int rows, int cols, int mod )
+{
+    Uint16 *row1;
+    Uint16 *row2;
+
+    unsigned char* y = lum +cols*rows;    /* Pointer to the end */
+    int x = 0;
+    row1 = (Uint16 *)out;                 /* 16 bit target */
+    row2 = (Uint16 *)out+cols+mod;        /* start of second row  */
+    mod = (mod+cols+mod)*2;               /* increment for row1 in byte */
+
+    __asm__ __volatile__(
+        /* tap dance to workaround the inability to use %%ebx at will... */
+        /*  move one thing to the stack... */
+        "pushl $0\n"  /* save a slot on the stack. */
+        "pushl %%ebx\n"  /* save %%ebx. */
+        "movl %0, %%ebx\n"  /* put the thing in ebx. */
+        "movl %%ebx, 4(%%esp)\n"  /* put the thing in the stack slot. */
+        "popl %%ebx\n"  /* get back %%ebx (the PIC register). */
+
+        ".align 8\n"
+        "1:\n"
+
+        "movd           (%1),                   %%mm0\n" /* 4 Cb         0  0  0  0 u3 u2 u1 u0 */
+        "pxor           %%mm7,                  %%mm7\n"
+        "pushl %%ebx\n"
+        "movl 4(%%esp), %%ebx\n"
+        "movd (%%ebx), %%mm1\n"   /* 4 Cr                0  0  0  0 v3 v2 v1 v0 */
+        "popl %%ebx\n"
+
+        "punpcklbw      %%mm7,                  %%mm0\n" /* 4 W cb   0 u3  0 u2  0 u1  0 u0 */
+        "punpcklbw      %%mm7,                  %%mm1\n" /* 4 W cr   0 v3  0 v2  0 v1  0 v0 */
+        "psubw          %9,                     %%mm0\n"
+        "psubw          %9,                     %%mm1\n"
+        "movq           %%mm0,                  %%mm2\n" /* Cb                   0 u3  0 u2  0 u1  0 u0 */
+        "movq           %%mm1,                  %%mm3\n" /* Cr */
+        "pmullw         %10,                    %%mm2\n" /* Cb2green 0 R3  0 R2  0 R1  0 R0 */
+        "movq           (%2),                   %%mm6\n" /* L1      l7 L6 L5 L4 L3 L2 L1 L0 */
+        "pmullw         %11,                    %%mm0\n" /* Cb2blue */
+        "pand           %12,                    %%mm6\n" /* L1      00 L6 00 L4 00 L2 00 L0 */
+        "pmullw         %13,                    %%mm3\n" /* Cr2green */
+        "movq           (%2),                   %%mm7\n" /* L2 */
+        "pmullw         %14,                    %%mm1\n" /* Cr2red */
+        "psrlw          $8,                     %%mm7\n"        /* L2           00 L7 00 L5 00 L3 00 L1 */
+        "pmullw         %15,                    %%mm6\n" /* lum1 */
+        "paddw          %%mm3,                  %%mm2\n" /* Cb2green + Cr2green == green */
+        "pmullw         %15,                    %%mm7\n" /* lum2 */
+
+        "movq           %%mm6,                  %%mm4\n" /* lum1 */
+        "paddw          %%mm0,                  %%mm6\n" /* lum1 +blue 00 B6 00 B4 00 B2 00 B0 */
+        "movq           %%mm4,                  %%mm5\n" /* lum1 */
+        "paddw          %%mm1,                  %%mm4\n" /* lum1 +red  00 R6 00 R4 00 R2 00 R0 */
+        "paddw          %%mm2,                  %%mm5\n" /* lum1 +green 00 G6 00 G4 00 G2 00 G0 */
+        "psraw          $6,                     %%mm4\n" /* R1 0 .. 64 */
+        "movq           %%mm7,                  %%mm3\n" /* lum2                       00 L7 00 L5 00 L3 00 L1 */
+        "psraw          $6,                     %%mm5\n" /* G1  - .. + */
+        "paddw          %%mm0,                  %%mm7\n" /* Lum2 +blue 00 B7 00 B5 00 B3 00 B1 */
+        "psraw          $6,                     %%mm6\n" /* B1         0 .. 64 */
+        "packuswb       %%mm4,                  %%mm4\n" /* R1 R1 */
+        "packuswb       %%mm5,                  %%mm5\n" /* G1 G1 */
+        "packuswb       %%mm6,                  %%mm6\n" /* B1 B1 */
+        "punpcklbw      %%mm4,                  %%mm4\n"
+        "punpcklbw      %%mm5,                  %%mm5\n"
+
+        "pand           %16,                    %%mm4\n"
+        "psllw          $3,                     %%mm5\n" /* GREEN       1 */
+        "punpcklbw      %%mm6,                  %%mm6\n"
+        "pand           %17,                    %%mm5\n"
+        "pand           %16,                    %%mm6\n"
+        "por            %%mm5,                  %%mm4\n" /* */
+        "psrlw          $11,                    %%mm6\n" /* BLUE        1 */
+        "movq           %%mm3,                  %%mm5\n" /* lum2 */
+        "paddw          %%mm1,                  %%mm3\n" /* lum2 +red      00 R7 00 R5 00 R3 00 R1 */
+        "paddw          %%mm2,                  %%mm5\n" /* lum2 +green 00 G7 00 G5 00 G3 00 G1 */
+        "psraw          $6,                     %%mm3\n" /* R2 */
+        "por            %%mm6,                  %%mm4\n" /* MM4 */
+        "psraw          $6,                     %%mm5\n" /* G2 */
+        "movq           (%2, %4),               %%mm6\n" /* L3 load lum2 */
+        "psraw          $6,                     %%mm7\n"
+        "packuswb       %%mm3,                  %%mm3\n"
+        "packuswb       %%mm5,                  %%mm5\n"
+        "packuswb       %%mm7,                  %%mm7\n"
+        "pand           %12,                    %%mm6\n" /* L3 */
+        "punpcklbw      %%mm3,                  %%mm3\n"
+        "punpcklbw      %%mm5,                  %%mm5\n"
+        "pmullw         %15,                    %%mm6\n" /* lum3 */
+        "punpcklbw      %%mm7,                  %%mm7\n"
+        "psllw          $3,                     %%mm5\n" /* GREEN 2 */
+        "pand           %16,                    %%mm7\n"
+        "pand           %16,                    %%mm3\n"
+        "psrlw          $11,                    %%mm7\n" /* BLUE  2 */
+        "pand           %17,                    %%mm5\n"
+        "por            %%mm7,                  %%mm3\n"
+        "movq           (%2,%4),                %%mm7\n" /* L4 load lum2 */
+        "por            %%mm5,                  %%mm3\n"
+        "psrlw          $8,                     %%mm7\n" /* L4 */
+        "movq           %%mm4,                  %%mm5\n"
+        "punpcklwd      %%mm3,                  %%mm4\n"
+        "pmullw         %15,                    %%mm7\n" /* lum4 */
+        "punpckhwd      %%mm3,                  %%mm5\n"
+
+        "movq           %%mm4,                  (%3)\n"  /* write row1 */
+        "movq           %%mm5,                  8(%3)\n" /* write row1 */
+
+        "movq           %%mm6,                  %%mm4\n" /* Lum3 */
+        "paddw          %%mm0,                  %%mm6\n" /* Lum3 +blue */
+
+        "movq           %%mm4,                  %%mm5\n" /* Lum3 */
+        "paddw          %%mm1,                  %%mm4\n" /* Lum3 +red */
+        "paddw          %%mm2,                  %%mm5\n" /* Lum3 +green */
+        "psraw          $6,                     %%mm4\n"
+        "movq           %%mm7,                  %%mm3\n" /* Lum4 */
+        "psraw          $6,                     %%mm5\n"
+        "paddw          %%mm0,                  %%mm7\n" /* Lum4 +blue */
+        "psraw          $6,                     %%mm6\n" /* Lum3 +blue */
+        "movq           %%mm3,                  %%mm0\n" /* Lum4 */
+        "packuswb       %%mm4,                  %%mm4\n"
+        "paddw          %%mm1,                  %%mm3\n" /* Lum4 +red */
+        "packuswb       %%mm5,                  %%mm5\n"
+        "paddw          %%mm2,                  %%mm0\n" /* Lum4 +green */
+        "packuswb       %%mm6,                  %%mm6\n"
+        "punpcklbw      %%mm4,                  %%mm4\n"
+        "punpcklbw      %%mm5,                  %%mm5\n"
+        "punpcklbw      %%mm6,                  %%mm6\n"
+        "psllw          $3,                     %%mm5\n" /* GREEN 3 */
+        "pand           %16,                    %%mm4\n"
+        "psraw          $6,                     %%mm3\n" /* psr 6 */
+        "psraw          $6,                     %%mm0\n"
+        "pand           %16,                    %%mm6\n" /* BLUE */
+        "pand           %17,                    %%mm5\n"
+        "psrlw          $11,                    %%mm6\n" /* BLUE  3 */
+        "por            %%mm5,                  %%mm4\n"
+        "psraw          $6,                     %%mm7\n"
+        "por            %%mm6,                  %%mm4\n"
+        "packuswb       %%mm3,                  %%mm3\n"
+        "packuswb       %%mm0,                  %%mm0\n"
+        "packuswb       %%mm7,                  %%mm7\n"
+        "punpcklbw      %%mm3,                  %%mm3\n"
+        "punpcklbw      %%mm0,                  %%mm0\n"
+        "punpcklbw      %%mm7,                  %%mm7\n"
+        "pand           %16,                    %%mm3\n"
+        "pand           %16,                    %%mm7\n" /* BLUE */
+        "psllw          $3,                     %%mm0\n" /* GREEN 4 */
+        "psrlw          $11,                    %%mm7\n"
+        "pand           %17,                    %%mm0\n"
+        "por            %%mm7,                  %%mm3\n"
+        "por            %%mm0,                  %%mm3\n"
+
+        "movq           %%mm4,                  %%mm5\n"
+
+        "punpcklwd      %%mm3,                  %%mm4\n"
+        "punpckhwd      %%mm3,                  %%mm5\n"
+
+        "movq           %%mm4,                  (%5)\n"
+        "movq           %%mm5,                  8(%5)\n"
+
+        "addl           $8,                     %6\n"
+        "addl           $8,                     %2\n"
+        "addl           $4,                     (%%esp)\n"
+        "addl           $4,                     %1\n"
+        "cmpl           %4,                     %6\n"
+        "leal           16(%3),                 %3\n"
+        "leal           16(%5),%5\n" /* row2+16 */
+
+        "jl             1b\n"
+        "addl           %4,     %2\n" /* lum += cols */
+        "addl           %8,     %3\n" /* row1+= mod */
+        "addl           %8,     %5\n" /* row2+= mod */
+        "movl           $0,     %6\n" /* x=0 */
+        "cmpl           %7,     %2\n"
+        "jl             1b\n"
+        "addl $4, %%esp\n"  /* get rid of the stack slot we reserved. */
+        "emms\n"
+        :
+        : "m" (cr), "r"(cb),"r"(lum),
+          "r"(row1),"r"(cols),"r"(row2),"m"(x),"m"(y),"m"(mod),
+          "m"(MMX_0080w),"m"(MMX_Ugrn565),"m"(MMX_Ublu5x5),
+          "m"(MMX_00FFw),"m"(MMX_Vgrn565),"m"(MMX_Vred5x5),
+          "m"(MMX_Ycoeff),"m"(MMX_red565),"m"(MMX_grn565)
+    );
+}
+
+/* *INDENT-ON* */
+
+#endif /* GCC3 i386 inline assembly */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/SDL_yuv_sw_c.h

@@ -0,0 +1,72 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../SDL_internal.h"
+
+#include "SDL_video.h"
+
+/* This is the software implementation of the YUV texture support */
+
+struct SDL_SW_YUVTexture
+{
+    Uint32 format;
+    Uint32 target_format;
+    int w, h;
+    Uint8 *pixels;
+    int *colortab;
+    Uint32 *rgb_2_pix;
+    void (*Display1X) (int *colortab, Uint32 * rgb_2_pix,
+                       unsigned char *lum, unsigned char *cr,
+                       unsigned char *cb, unsigned char *out,
+                       int rows, int cols, int mod);
+    void (*Display2X) (int *colortab, Uint32 * rgb_2_pix,
+                       unsigned char *lum, unsigned char *cr,
+                       unsigned char *cb, unsigned char *out,
+                       int rows, int cols, int mod);
+
+    /* These are just so we don't have to allocate them separately */
+    Uint16 pitches[3];
+    Uint8 *planes[3];
+
+    /* This is a temporary surface in case we have to stretch copy */
+    SDL_Surface *stretch;
+    SDL_Surface *display;
+};
+
+typedef struct SDL_SW_YUVTexture SDL_SW_YUVTexture;
+
+SDL_SW_YUVTexture *SDL_SW_CreateYUVTexture(Uint32 format, int w, int h);
+int SDL_SW_QueryYUVTexturePixels(SDL_SW_YUVTexture * swdata, void **pixels,
+                                 int *pitch);
+int SDL_SW_UpdateYUVTexture(SDL_SW_YUVTexture * swdata, const SDL_Rect * rect,
+                            const void *pixels, int pitch);
+int SDL_SW_UpdateYUVTexturePlanar(SDL_SW_YUVTexture * swdata, const SDL_Rect * rect,
+                                  const Uint8 *Yplane, int Ypitch,
+                                  const Uint8 *Uplane, int Upitch,
+                                  const Uint8 *Vplane, int Vpitch);
+int SDL_SW_LockYUVTexture(SDL_SW_YUVTexture * swdata, const SDL_Rect * rect,
+                          void **pixels, int *pitch);
+void SDL_SW_UnlockYUVTexture(SDL_SW_YUVTexture * swdata);
+int SDL_SW_CopyYUVToRGB(SDL_SW_YUVTexture * swdata, const SDL_Rect * srcrect,
+                        Uint32 target_format, int w, int h, void *pixels,
+                        int pitch);
+void SDL_SW_DestroyYUVTexture(SDL_SW_YUVTexture * swdata);
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/direct3d11/SDL_render_winrt.cpp

@@ -0,0 +1,116 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#if SDL_VIDEO_RENDER_D3D11 && !SDL_RENDER_DISABLED
+
+#include "SDL_syswm.h"
+#include "../../video/winrt/SDL_winrtvideo_cpp.h"
+extern "C" {
+#include "../SDL_sysrender.h"
+}
+
+#include <windows.ui.core.h>
+#include <windows.graphics.display.h>
+
+#if WINAPI_FAMILY == WINAPI_FAMILY_APP
+#include <windows.ui.xaml.media.dxinterop.h>
+#endif
+
+using namespace Windows::UI::Core;
+using namespace Windows::Graphics::Display;
+
+#include <DXGI.h>
+
+#include "SDL_render_winrt.h"
+
+
+extern "C" void *
+D3D11_GetCoreWindowFromSDLRenderer(SDL_Renderer * renderer)
+{
+    SDL_Window * sdlWindow = renderer->window;
+    if ( ! renderer->window ) {
+        return NULL;
+    }
+
+    SDL_SysWMinfo sdlWindowInfo;
+    SDL_VERSION(&sdlWindowInfo.version);
+    if ( ! SDL_GetWindowWMInfo(sdlWindow, &sdlWindowInfo) ) {
+        return NULL;
+    }
+
+    if (sdlWindowInfo.subsystem != SDL_SYSWM_WINRT) {
+        return NULL;
+    }
+
+    if (!sdlWindowInfo.info.winrt.window) {
+        return NULL;
+    }
+
+    ABI::Windows::UI::Core::ICoreWindow *coreWindow = NULL;
+    if (FAILED(sdlWindowInfo.info.winrt.window->QueryInterface(&coreWindow))) {
+        return NULL;
+    }
+
+    IUnknown *coreWindowAsIUnknown = NULL;
+    coreWindow->QueryInterface(&coreWindowAsIUnknown);
+    coreWindow->Release();
+
+    return coreWindowAsIUnknown;
+}
+
+extern "C" DXGI_MODE_ROTATION
+D3D11_GetCurrentRotation()
+{
+    const DisplayOrientations currentOrientation = WINRT_DISPLAY_PROPERTY(CurrentOrientation);
+
+    switch (currentOrientation) {
+
+#if WINAPI_FAMILY == WINAPI_FAMILY_PHONE_APP
+    /* Windows Phone rotations */
+    case DisplayOrientations::Landscape:
+        return DXGI_MODE_ROTATION_ROTATE90;
+    case DisplayOrientations::Portrait:
+        return DXGI_MODE_ROTATION_IDENTITY;
+    case DisplayOrientations::LandscapeFlipped:
+        return DXGI_MODE_ROTATION_ROTATE270;
+    case DisplayOrientations::PortraitFlipped:
+        return DXGI_MODE_ROTATION_ROTATE180;
+#else
+    /* Non-Windows-Phone rotations (ex: Windows 8, Windows RT) */
+    case DisplayOrientations::Landscape:
+        return DXGI_MODE_ROTATION_IDENTITY;
+    case DisplayOrientations::Portrait:
+        return DXGI_MODE_ROTATION_ROTATE270;
+    case DisplayOrientations::LandscapeFlipped:
+        return DXGI_MODE_ROTATION_ROTATE180;
+    case DisplayOrientations::PortraitFlipped:
+        return DXGI_MODE_ROTATION_ROTATE90;
+#endif /* WINAPI_FAMILY == WINAPI_FAMILY_PHONE_APP */
+    }
+
+    return DXGI_MODE_ROTATION_IDENTITY;
+}
+
+
+#endif /* SDL_VIDEO_RENDER_D3D11 && !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/direct3d11/SDL_render_winrt.h

@@ -0,0 +1,40 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#if SDL_VIDEO_RENDER_D3D11 && !SDL_RENDER_DISABLED
+
+#include "SDL_render.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+void * D3D11_GetCoreWindowFromSDLRenderer(SDL_Renderer * renderer);
+DXGI_MODE_ROTATION D3D11_GetCurrentRotation();
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* SDL_VIDEO_RENDER_D3D11 && !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/mmx.h

@@ -0,0 +1,642 @@
+/*	mmx.h
+
+	MultiMedia eXtensions GCC interface library for IA32.
+
+	To use this library, simply include this header file
+	and compile with GCC.  You MUST have inlining enabled
+	in order for mmx_ok() to work; this can be done by
+	simply using -O on the GCC command line.
+
+	Compiling with -DMMX_TRACE will cause detailed trace
+	output to be sent to stderr for each mmx operation.
+	This adds lots of code, and obviously slows execution to
+	a crawl, but can be very useful for debugging.
+
+	THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY
+	EXPRESS OR IMPLIED WARRANTIES, INCLUDING, WITHOUT
+	LIMITATION, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+	AND FITNESS FOR ANY PARTICULAR PURPOSE.
+
+	1997-99 by H. Dietz and R. Fisher
+
+ Notes:
+	It appears that the latest gas has the pand problem fixed, therefore
+	  I'll undefine BROKEN_PAND by default.
+*/
+
+#ifndef _MMX_H
+#define _MMX_H
+
+
+/*	Warning:  at this writing, the version of GAS packaged
+	with most Linux distributions does not handle the
+	parallel AND operation mnemonic correctly.  If the
+	symbol BROKEN_PAND is defined, a slower alternative
+	coding will be used.  If execution of mmxtest results
+	in an illegal instruction fault, define this symbol.
+*/
+#undef	BROKEN_PAND
+
+
+/*	The type of an value that fits in an MMX register
+	(note that long long constant values MUST be suffixed
+	 by LL and unsigned long long values by ULL, lest
+	 they be truncated by the compiler)
+*/
+typedef union
+{
+    long long q;                /* Quadword (64-bit) value */
+    unsigned long long uq;      /* Unsigned Quadword */
+    int d[2];                   /* 2 Doubleword (32-bit) values */
+    unsigned int ud[2];         /* 2 Unsigned Doubleword */
+    short w[4];                 /* 4 Word (16-bit) values */
+    unsigned short uw[4];       /* 4 Unsigned Word */
+    char b[8];                  /* 8 Byte (8-bit) values */
+    unsigned char ub[8];        /* 8 Unsigned Byte */
+    float s[2];                 /* Single-precision (32-bit) value */
+} __attribute__ ((aligned(8))) mmx_t;   /* On an 8-byte (64-bit) boundary */
+
+
+#if 0
+/*	Function to test if multimedia instructions are supported...
+*/
+inline extern int
+mm_support(void)
+{
+    /* Returns 1 if MMX instructions are supported,
+       3 if Cyrix MMX and Extended MMX instructions are supported
+       5 if AMD MMX and 3DNow! instructions are supported
+       0 if hardware does not support any of these
+     */
+    register int rval = 0;
+
+    __asm__ __volatile__(
+                            /* See if CPUID instruction is supported ... */
+                            /* ... Get copies of EFLAGS into eax and ecx */
+                            "pushf\n\t"
+                            "popl %%eax\n\t" "movl %%eax, %%ecx\n\t"
+                            /* ... Toggle the ID bit in one copy and store */
+                            /*     to the EFLAGS reg */
+                            "xorl $0x200000, %%eax\n\t"
+                            "push %%eax\n\t" "popf\n\t"
+                            /* ... Get the (hopefully modified) EFLAGS */
+                            "pushf\n\t" "popl %%eax\n\t"
+                            /* ... Compare and test result */
+                            "xorl %%eax, %%ecx\n\t" "testl $0x200000, %%ecx\n\t" "jz NotSupported1\n\t" /* CPUID not supported */
+                            /* Get standard CPUID information, and
+                               go to a specific vendor section */
+                            "movl $0, %%eax\n\t" "cpuid\n\t"
+                            /* Check for Intel */
+                            "cmpl $0x756e6547, %%ebx\n\t"
+                            "jne TryAMD\n\t"
+                            "cmpl $0x49656e69, %%edx\n\t"
+                            "jne TryAMD\n\t"
+                            "cmpl $0x6c65746e, %%ecx\n"
+                            "jne TryAMD\n\t" "jmp Intel\n\t"
+                            /* Check for AMD */
+                            "\nTryAMD:\n\t"
+                            "cmpl $0x68747541, %%ebx\n\t"
+                            "jne TryCyrix\n\t"
+                            "cmpl $0x69746e65, %%edx\n\t"
+                            "jne TryCyrix\n\t"
+                            "cmpl $0x444d4163, %%ecx\n"
+                            "jne TryCyrix\n\t" "jmp AMD\n\t"
+                            /* Check for Cyrix */
+                            "\nTryCyrix:\n\t"
+                            "cmpl $0x69727943, %%ebx\n\t"
+                            "jne NotSupported2\n\t"
+                            "cmpl $0x736e4978, %%edx\n\t"
+                            "jne NotSupported3\n\t"
+                            "cmpl $0x64616574, %%ecx\n\t"
+                            "jne NotSupported4\n\t"
+                            /* Drop through to Cyrix... */
+                            /* Cyrix Section */
+                            /* See if extended CPUID level 80000001 is supported */
+                            /* The value of CPUID/80000001 for the 6x86MX is undefined
+                               according to the Cyrix CPU Detection Guide (Preliminary
+                               Rev. 1.01 table 1), so we'll check the value of eax for
+                               CPUID/0 to see if standard CPUID level 2 is supported.
+                               According to the table, the only CPU which supports level
+                               2 is also the only one which supports extended CPUID levels.
+                             */
+                            "cmpl $0x2, %%eax\n\t" "jne MMXtest\n\t"    /* Use standard CPUID instead */
+                            /* Extended CPUID supported (in theory), so get extended
+                               features */
+                            "movl $0x80000001, %%eax\n\t" "cpuid\n\t" "testl $0x00800000, %%eax\n\t"    /* Test for MMX */
+                            "jz NotSupported5\n\t"      /* MMX not supported */
+                            "testl $0x01000000, %%eax\n\t"      /* Test for Ext'd MMX */
+                            "jnz EMMXSupported\n\t" "movl $1, %0:\n\n\t"        /* MMX Supported */
+                            "jmp Return\n\n" "EMMXSupported:\n\t" "movl $3, %0:\n\n\t"  /* EMMX and MMX Supported */
+                            "jmp Return\n\t"
+                            /* AMD Section */
+                            "AMD:\n\t"
+                            /* See if extended CPUID is supported */
+                            "movl $0x80000000, %%eax\n\t" "cpuid\n\t" "cmpl $0x80000000, %%eax\n\t" "jl MMXtest\n\t"    /* Use standard CPUID instead */
+                            /* Extended CPUID supported, so get extended features */
+                            "movl $0x80000001, %%eax\n\t" "cpuid\n\t" "testl $0x00800000, %%edx\n\t"    /* Test for MMX */
+                            "jz NotSupported6\n\t"      /* MMX not supported */
+                            "testl $0x80000000, %%edx\n\t"      /* Test for 3DNow! */
+                            "jnz ThreeDNowSupported\n\t" "movl $1, %0:\n\n\t"   /* MMX Supported */
+                            "jmp Return\n\n" "ThreeDNowSupported:\n\t" "movl $5, %0:\n\n\t"     /* 3DNow! and MMX Supported */
+                            "jmp Return\n\t"
+                            /* Intel Section */
+                            "Intel:\n\t"
+                            /* Check for MMX */
+                            "MMXtest:\n\t" "movl $1, %%eax\n\t" "cpuid\n\t" "testl $0x00800000, %%edx\n\t"      /* Test for MMX */
+                            "jz NotSupported7\n\t"      /* MMX Not supported */
+                            "movl $1, %0:\n\n\t"        /* MMX Supported */
+                            "jmp Return\n\t"
+                            /* Nothing supported */
+                            "\nNotSupported1:\n\t" "#movl $101, %0:\n\n\t" "\nNotSupported2:\n\t" "#movl $102, %0:\n\n\t" "\nNotSupported3:\n\t" "#movl $103, %0:\n\n\t" "\nNotSupported4:\n\t" "#movl $104, %0:\n\n\t" "\nNotSupported5:\n\t" "#movl $105, %0:\n\n\t" "\nNotSupported6:\n\t" "#movl $106, %0:\n\n\t" "\nNotSupported7:\n\t" "#movl $107, %0:\n\n\t" "movl $0, %0:\n\n\t" "Return:\n\t":"=a"(rval):     /* no input */
+                            :"eax", "ebx", "ecx", "edx");
+
+    /* Return */
+    return (rval);
+}
+
+/*	Function to test if mmx instructions are supported...
+*/
+inline extern int
+mmx_ok(void)
+{
+    /* Returns 1 if MMX instructions are supported, 0 otherwise */
+    return (mm_support() & 0x1);
+}
+#endif
+
+/*	Helper functions for the instruction macros that follow...
+	(note that memory-to-register, m2r, instructions are nearly
+	 as efficient as register-to-register, r2r, instructions;
+	 however, memory-to-memory instructions are really simulated
+	 as a convenience, and are only 1/3 as efficient)
+*/
+#ifdef	MMX_TRACE
+
+/*	Include the stuff for printing a trace to stderr...
+*/
+
+#define	mmx_i2r(op, imm, reg) \
+	{ \
+		mmx_t mmx_trace; \
+		mmx_trace.uq = (imm); \
+		printf(#op "_i2r(" #imm "=0x%08x%08x, ", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+		__asm__ __volatile__ ("movq %%" #reg ", %0" \
+				      : "=X" (mmx_trace) \
+				      : /* nothing */ ); \
+		printf(#reg "=0x%08x%08x) => ", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+		__asm__ __volatile__ (#op " %0, %%" #reg \
+				      : /* nothing */ \
+				      : "X" (imm)); \
+		__asm__ __volatile__ ("movq %%" #reg ", %0" \
+				      : "=X" (mmx_trace) \
+				      : /* nothing */ ); \
+		printf(#reg "=0x%08x%08x\n", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+	}
+
+#define	mmx_m2r(op, mem, reg) \
+	{ \
+		mmx_t mmx_trace; \
+		mmx_trace = (mem); \
+		printf(#op "_m2r(" #mem "=0x%08x%08x, ", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+		__asm__ __volatile__ ("movq %%" #reg ", %0" \
+				      : "=X" (mmx_trace) \
+				      : /* nothing */ ); \
+		printf(#reg "=0x%08x%08x) => ", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+		__asm__ __volatile__ (#op " %0, %%" #reg \
+				      : /* nothing */ \
+				      : "X" (mem)); \
+		__asm__ __volatile__ ("movq %%" #reg ", %0" \
+				      : "=X" (mmx_trace) \
+				      : /* nothing */ ); \
+		printf(#reg "=0x%08x%08x\n", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+	}
+
+#define	mmx_r2m(op, reg, mem) \
+	{ \
+		mmx_t mmx_trace; \
+		__asm__ __volatile__ ("movq %%" #reg ", %0" \
+				      : "=X" (mmx_trace) \
+				      : /* nothing */ ); \
+		printf(#op "_r2m(" #reg "=0x%08x%08x, ", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+		mmx_trace = (mem); \
+		printf(#mem "=0x%08x%08x) => ", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+		__asm__ __volatile__ (#op " %%" #reg ", %0" \
+				      : "=X" (mem) \
+				      : /* nothing */ ); \
+		mmx_trace = (mem); \
+		printf(#mem "=0x%08x%08x\n", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+	}
+
+#define	mmx_r2r(op, regs, regd) \
+	{ \
+		mmx_t mmx_trace; \
+		__asm__ __volatile__ ("movq %%" #regs ", %0" \
+				      : "=X" (mmx_trace) \
+				      : /* nothing */ ); \
+		printf(#op "_r2r(" #regs "=0x%08x%08x, ", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+		__asm__ __volatile__ ("movq %%" #regd ", %0" \
+				      : "=X" (mmx_trace) \
+				      : /* nothing */ ); \
+		printf(#regd "=0x%08x%08x) => ", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+		__asm__ __volatile__ (#op " %" #regs ", %" #regd); \
+		__asm__ __volatile__ ("movq %%" #regd ", %0" \
+				      : "=X" (mmx_trace) \
+				      : /* nothing */ ); \
+		printf(#regd "=0x%08x%08x\n", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+	}
+
+#define	mmx_m2m(op, mems, memd) \
+	{ \
+		mmx_t mmx_trace; \
+		mmx_trace = (mems); \
+		printf(#op "_m2m(" #mems "=0x%08x%08x, ", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+		mmx_trace = (memd); \
+		printf(#memd "=0x%08x%08x) => ", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+		__asm__ __volatile__ ("movq %0, %%mm0\n\t" \
+				      #op " %1, %%mm0\n\t" \
+				      "movq %%mm0, %0" \
+				      : "=X" (memd) \
+				      : "X" (mems)); \
+		mmx_trace = (memd); \
+		printf(#memd "=0x%08x%08x\n", \
+			mmx_trace.d[1], mmx_trace.d[0]); \
+	}
+
+#else
+
+/*	These macros are a lot simpler without the tracing...
+*/
+
+#define	mmx_i2r(op, imm, reg) \
+	__asm__ __volatile__ (#op " %0, %%" #reg \
+			      : /* nothing */ \
+			      : "X" (imm) )
+
+#define	mmx_m2r(op, mem, reg) \
+	__asm__ __volatile__ (#op " %0, %%" #reg \
+			      : /* nothing */ \
+			      : "m" (mem))
+
+#define	mmx_r2m(op, reg, mem) \
+	__asm__ __volatile__ (#op " %%" #reg ", %0" \
+			      : "=m" (mem) \
+			      : /* nothing */ )
+
+#define	mmx_r2r(op, regs, regd) \
+	__asm__ __volatile__ (#op " %" #regs ", %" #regd)
+
+#define	mmx_m2m(op, mems, memd) \
+	__asm__ __volatile__ ("movq %0, %%mm0\n\t" \
+			      #op " %1, %%mm0\n\t" \
+			      "movq %%mm0, %0" \
+			      : "=X" (memd) \
+			      : "X" (mems))
+
+#endif
+
+
+/*	1x64 MOVe Quadword
+	(this is both a load and a store...
+	 in fact, it is the only way to store)
+*/
+#define	movq_m2r(var, reg)	mmx_m2r(movq, var, reg)
+#define	movq_r2m(reg, var)	mmx_r2m(movq, reg, var)
+#define	movq_r2r(regs, regd)	mmx_r2r(movq, regs, regd)
+#define	movq(vars, vard) \
+	__asm__ __volatile__ ("movq %1, %%mm0\n\t" \
+			      "movq %%mm0, %0" \
+			      : "=X" (vard) \
+			      : "X" (vars))
+
+
+/*	1x32 MOVe Doubleword
+	(like movq, this is both load and store...
+	 but is most useful for moving things between
+	 mmx registers and ordinary registers)
+*/
+#define	movd_m2r(var, reg)	mmx_m2r(movd, var, reg)
+#define	movd_r2m(reg, var)	mmx_r2m(movd, reg, var)
+#define	movd_r2r(regs, regd)	mmx_r2r(movd, regs, regd)
+#define	movd(vars, vard) \
+	__asm__ __volatile__ ("movd %1, %%mm0\n\t" \
+			      "movd %%mm0, %0" \
+			      : "=X" (vard) \
+			      : "X" (vars))
+
+
+/*	2x32, 4x16, and 8x8 Parallel ADDs
+*/
+#define	paddd_m2r(var, reg)	mmx_m2r(paddd, var, reg)
+#define	paddd_r2r(regs, regd)	mmx_r2r(paddd, regs, regd)
+#define	paddd(vars, vard)	mmx_m2m(paddd, vars, vard)
+
+#define	paddw_m2r(var, reg)	mmx_m2r(paddw, var, reg)
+#define	paddw_r2r(regs, regd)	mmx_r2r(paddw, regs, regd)
+#define	paddw(vars, vard)	mmx_m2m(paddw, vars, vard)
+
+#define	paddb_m2r(var, reg)	mmx_m2r(paddb, var, reg)
+#define	paddb_r2r(regs, regd)	mmx_r2r(paddb, regs, regd)
+#define	paddb(vars, vard)	mmx_m2m(paddb, vars, vard)
+
+
+/*	4x16 and 8x8 Parallel ADDs using Saturation arithmetic
+*/
+#define	paddsw_m2r(var, reg)	mmx_m2r(paddsw, var, reg)
+#define	paddsw_r2r(regs, regd)	mmx_r2r(paddsw, regs, regd)
+#define	paddsw(vars, vard)	mmx_m2m(paddsw, vars, vard)
+
+#define	paddsb_m2r(var, reg)	mmx_m2r(paddsb, var, reg)
+#define	paddsb_r2r(regs, regd)	mmx_r2r(paddsb, regs, regd)
+#define	paddsb(vars, vard)	mmx_m2m(paddsb, vars, vard)
+
+
+/*	4x16 and 8x8 Parallel ADDs using Unsigned Saturation arithmetic
+*/
+#define	paddusw_m2r(var, reg)	mmx_m2r(paddusw, var, reg)
+#define	paddusw_r2r(regs, regd)	mmx_r2r(paddusw, regs, regd)
+#define	paddusw(vars, vard)	mmx_m2m(paddusw, vars, vard)
+
+#define	paddusb_m2r(var, reg)	mmx_m2r(paddusb, var, reg)
+#define	paddusb_r2r(regs, regd)	mmx_r2r(paddusb, regs, regd)
+#define	paddusb(vars, vard)	mmx_m2m(paddusb, vars, vard)
+
+
+/*	2x32, 4x16, and 8x8 Parallel SUBs
+*/
+#define	psubd_m2r(var, reg)	mmx_m2r(psubd, var, reg)
+#define	psubd_r2r(regs, regd)	mmx_r2r(psubd, regs, regd)
+#define	psubd(vars, vard)	mmx_m2m(psubd, vars, vard)
+
+#define	psubw_m2r(var, reg)	mmx_m2r(psubw, var, reg)
+#define	psubw_r2r(regs, regd)	mmx_r2r(psubw, regs, regd)
+#define	psubw(vars, vard)	mmx_m2m(psubw, vars, vard)
+
+#define	psubb_m2r(var, reg)	mmx_m2r(psubb, var, reg)
+#define	psubb_r2r(regs, regd)	mmx_r2r(psubb, regs, regd)
+#define	psubb(vars, vard)	mmx_m2m(psubb, vars, vard)
+
+
+/*	4x16 and 8x8 Parallel SUBs using Saturation arithmetic
+*/
+#define	psubsw_m2r(var, reg)	mmx_m2r(psubsw, var, reg)
+#define	psubsw_r2r(regs, regd)	mmx_r2r(psubsw, regs, regd)
+#define	psubsw(vars, vard)	mmx_m2m(psubsw, vars, vard)
+
+#define	psubsb_m2r(var, reg)	mmx_m2r(psubsb, var, reg)
+#define	psubsb_r2r(regs, regd)	mmx_r2r(psubsb, regs, regd)
+#define	psubsb(vars, vard)	mmx_m2m(psubsb, vars, vard)
+
+
+/*	4x16 and 8x8 Parallel SUBs using Unsigned Saturation arithmetic
+*/
+#define	psubusw_m2r(var, reg)	mmx_m2r(psubusw, var, reg)
+#define	psubusw_r2r(regs, regd)	mmx_r2r(psubusw, regs, regd)
+#define	psubusw(vars, vard)	mmx_m2m(psubusw, vars, vard)
+
+#define	psubusb_m2r(var, reg)	mmx_m2r(psubusb, var, reg)
+#define	psubusb_r2r(regs, regd)	mmx_r2r(psubusb, regs, regd)
+#define	psubusb(vars, vard)	mmx_m2m(psubusb, vars, vard)
+
+
+/*	4x16 Parallel MULs giving Low 4x16 portions of results
+*/
+#define	pmullw_m2r(var, reg)	mmx_m2r(pmullw, var, reg)
+#define	pmullw_r2r(regs, regd)	mmx_r2r(pmullw, regs, regd)
+#define	pmullw(vars, vard)	mmx_m2m(pmullw, vars, vard)
+
+
+/*	4x16 Parallel MULs giving High 4x16 portions of results
+*/
+#define	pmulhw_m2r(var, reg)	mmx_m2r(pmulhw, var, reg)
+#define	pmulhw_r2r(regs, regd)	mmx_r2r(pmulhw, regs, regd)
+#define	pmulhw(vars, vard)	mmx_m2m(pmulhw, vars, vard)
+
+
+/*	4x16->2x32 Parallel Mul-ADD
+	(muls like pmullw, then adds adjacent 16-bit fields
+	 in the multiply result to make the final 2x32 result)
+*/
+#define	pmaddwd_m2r(var, reg)	mmx_m2r(pmaddwd, var, reg)
+#define	pmaddwd_r2r(regs, regd)	mmx_r2r(pmaddwd, regs, regd)
+#define	pmaddwd(vars, vard)	mmx_m2m(pmaddwd, vars, vard)
+
+
+/*	1x64 bitwise AND
+*/
+#ifdef	BROKEN_PAND
+#define	pand_m2r(var, reg) \
+	{ \
+		mmx_m2r(pandn, (mmx_t) -1LL, reg); \
+		mmx_m2r(pandn, var, reg); \
+	}
+#define	pand_r2r(regs, regd) \
+	{ \
+		mmx_m2r(pandn, (mmx_t) -1LL, regd); \
+		mmx_r2r(pandn, regs, regd) \
+	}
+#define	pand(vars, vard) \
+	{ \
+		movq_m2r(vard, mm0); \
+		mmx_m2r(pandn, (mmx_t) -1LL, mm0); \
+		mmx_m2r(pandn, vars, mm0); \
+		movq_r2m(mm0, vard); \
+	}
+#else
+#define	pand_m2r(var, reg)	mmx_m2r(pand, var, reg)
+#define	pand_r2r(regs, regd)	mmx_r2r(pand, regs, regd)
+#define	pand(vars, vard)	mmx_m2m(pand, vars, vard)
+#endif
+
+
+/*	1x64 bitwise AND with Not the destination
+*/
+#define	pandn_m2r(var, reg)	mmx_m2r(pandn, var, reg)
+#define	pandn_r2r(regs, regd)	mmx_r2r(pandn, regs, regd)
+#define	pandn(vars, vard)	mmx_m2m(pandn, vars, vard)
+
+
+/*	1x64 bitwise OR
+*/
+#define	por_m2r(var, reg)	mmx_m2r(por, var, reg)
+#define	por_r2r(regs, regd)	mmx_r2r(por, regs, regd)
+#define	por(vars, vard)	mmx_m2m(por, vars, vard)
+
+
+/*	1x64 bitwise eXclusive OR
+*/
+#define	pxor_m2r(var, reg)	mmx_m2r(pxor, var, reg)
+#define	pxor_r2r(regs, regd)	mmx_r2r(pxor, regs, regd)
+#define	pxor(vars, vard)	mmx_m2m(pxor, vars, vard)
+
+
+/*	2x32, 4x16, and 8x8 Parallel CoMPare for EQuality
+	(resulting fields are either 0 or -1)
+*/
+#define	pcmpeqd_m2r(var, reg)	mmx_m2r(pcmpeqd, var, reg)
+#define	pcmpeqd_r2r(regs, regd)	mmx_r2r(pcmpeqd, regs, regd)
+#define	pcmpeqd(vars, vard)	mmx_m2m(pcmpeqd, vars, vard)
+
+#define	pcmpeqw_m2r(var, reg)	mmx_m2r(pcmpeqw, var, reg)
+#define	pcmpeqw_r2r(regs, regd)	mmx_r2r(pcmpeqw, regs, regd)
+#define	pcmpeqw(vars, vard)	mmx_m2m(pcmpeqw, vars, vard)
+
+#define	pcmpeqb_m2r(var, reg)	mmx_m2r(pcmpeqb, var, reg)
+#define	pcmpeqb_r2r(regs, regd)	mmx_r2r(pcmpeqb, regs, regd)
+#define	pcmpeqb(vars, vard)	mmx_m2m(pcmpeqb, vars, vard)
+
+
+/*	2x32, 4x16, and 8x8 Parallel CoMPare for Greater Than
+	(resulting fields are either 0 or -1)
+*/
+#define	pcmpgtd_m2r(var, reg)	mmx_m2r(pcmpgtd, var, reg)
+#define	pcmpgtd_r2r(regs, regd)	mmx_r2r(pcmpgtd, regs, regd)
+#define	pcmpgtd(vars, vard)	mmx_m2m(pcmpgtd, vars, vard)
+
+#define	pcmpgtw_m2r(var, reg)	mmx_m2r(pcmpgtw, var, reg)
+#define	pcmpgtw_r2r(regs, regd)	mmx_r2r(pcmpgtw, regs, regd)
+#define	pcmpgtw(vars, vard)	mmx_m2m(pcmpgtw, vars, vard)
+
+#define	pcmpgtb_m2r(var, reg)	mmx_m2r(pcmpgtb, var, reg)
+#define	pcmpgtb_r2r(regs, regd)	mmx_r2r(pcmpgtb, regs, regd)
+#define	pcmpgtb(vars, vard)	mmx_m2m(pcmpgtb, vars, vard)
+
+
+/*	1x64, 2x32, and 4x16 Parallel Shift Left Logical
+*/
+#define	psllq_i2r(imm, reg)	mmx_i2r(psllq, imm, reg)
+#define	psllq_m2r(var, reg)	mmx_m2r(psllq, var, reg)
+#define	psllq_r2r(regs, regd)	mmx_r2r(psllq, regs, regd)
+#define	psllq(vars, vard)	mmx_m2m(psllq, vars, vard)
+
+#define	pslld_i2r(imm, reg)	mmx_i2r(pslld, imm, reg)
+#define	pslld_m2r(var, reg)	mmx_m2r(pslld, var, reg)
+#define	pslld_r2r(regs, regd)	mmx_r2r(pslld, regs, regd)
+#define	pslld(vars, vard)	mmx_m2m(pslld, vars, vard)
+
+#define	psllw_i2r(imm, reg)	mmx_i2r(psllw, imm, reg)
+#define	psllw_m2r(var, reg)	mmx_m2r(psllw, var, reg)
+#define	psllw_r2r(regs, regd)	mmx_r2r(psllw, regs, regd)
+#define	psllw(vars, vard)	mmx_m2m(psllw, vars, vard)
+
+
+/*	1x64, 2x32, and 4x16 Parallel Shift Right Logical
+*/
+#define	psrlq_i2r(imm, reg)	mmx_i2r(psrlq, imm, reg)
+#define	psrlq_m2r(var, reg)	mmx_m2r(psrlq, var, reg)
+#define	psrlq_r2r(regs, regd)	mmx_r2r(psrlq, regs, regd)
+#define	psrlq(vars, vard)	mmx_m2m(psrlq, vars, vard)
+
+#define	psrld_i2r(imm, reg)	mmx_i2r(psrld, imm, reg)
+#define	psrld_m2r(var, reg)	mmx_m2r(psrld, var, reg)
+#define	psrld_r2r(regs, regd)	mmx_r2r(psrld, regs, regd)
+#define	psrld(vars, vard)	mmx_m2m(psrld, vars, vard)
+
+#define	psrlw_i2r(imm, reg)	mmx_i2r(psrlw, imm, reg)
+#define	psrlw_m2r(var, reg)	mmx_m2r(psrlw, var, reg)
+#define	psrlw_r2r(regs, regd)	mmx_r2r(psrlw, regs, regd)
+#define	psrlw(vars, vard)	mmx_m2m(psrlw, vars, vard)
+
+
+/*	2x32 and 4x16 Parallel Shift Right Arithmetic
+*/
+#define	psrad_i2r(imm, reg)	mmx_i2r(psrad, imm, reg)
+#define	psrad_m2r(var, reg)	mmx_m2r(psrad, var, reg)
+#define	psrad_r2r(regs, regd)	mmx_r2r(psrad, regs, regd)
+#define	psrad(vars, vard)	mmx_m2m(psrad, vars, vard)
+
+#define	psraw_i2r(imm, reg)	mmx_i2r(psraw, imm, reg)
+#define	psraw_m2r(var, reg)	mmx_m2r(psraw, var, reg)
+#define	psraw_r2r(regs, regd)	mmx_r2r(psraw, regs, regd)
+#define	psraw(vars, vard)	mmx_m2m(psraw, vars, vard)
+
+
+/*	2x32->4x16 and 4x16->8x8 PACK and Signed Saturate
+	(packs source and dest fields into dest in that order)
+*/
+#define	packssdw_m2r(var, reg)	mmx_m2r(packssdw, var, reg)
+#define	packssdw_r2r(regs, regd) mmx_r2r(packssdw, regs, regd)
+#define	packssdw(vars, vard)	mmx_m2m(packssdw, vars, vard)
+
+#define	packsswb_m2r(var, reg)	mmx_m2r(packsswb, var, reg)
+#define	packsswb_r2r(regs, regd) mmx_r2r(packsswb, regs, regd)
+#define	packsswb(vars, vard)	mmx_m2m(packsswb, vars, vard)
+
+
+/*	4x16->8x8 PACK and Unsigned Saturate
+	(packs source and dest fields into dest in that order)
+*/
+#define	packuswb_m2r(var, reg)	mmx_m2r(packuswb, var, reg)
+#define	packuswb_r2r(regs, regd) mmx_r2r(packuswb, regs, regd)
+#define	packuswb(vars, vard)	mmx_m2m(packuswb, vars, vard)
+
+
+/*	2x32->1x64, 4x16->2x32, and 8x8->4x16 UNPaCK Low
+	(interleaves low half of dest with low half of source
+	 as padding in each result field)
+*/
+#define	punpckldq_m2r(var, reg)	mmx_m2r(punpckldq, var, reg)
+#define	punpckldq_r2r(regs, regd) mmx_r2r(punpckldq, regs, regd)
+#define	punpckldq(vars, vard)	mmx_m2m(punpckldq, vars, vard)
+
+#define	punpcklwd_m2r(var, reg)	mmx_m2r(punpcklwd, var, reg)
+#define	punpcklwd_r2r(regs, regd) mmx_r2r(punpcklwd, regs, regd)
+#define	punpcklwd(vars, vard)	mmx_m2m(punpcklwd, vars, vard)
+
+#define	punpcklbw_m2r(var, reg)	mmx_m2r(punpcklbw, var, reg)
+#define	punpcklbw_r2r(regs, regd) mmx_r2r(punpcklbw, regs, regd)
+#define	punpcklbw(vars, vard)	mmx_m2m(punpcklbw, vars, vard)
+
+
+/*	2x32->1x64, 4x16->2x32, and 8x8->4x16 UNPaCK High
+	(interleaves high half of dest with high half of source
+	 as padding in each result field)
+*/
+#define	punpckhdq_m2r(var, reg)	mmx_m2r(punpckhdq, var, reg)
+#define	punpckhdq_r2r(regs, regd) mmx_r2r(punpckhdq, regs, regd)
+#define	punpckhdq(vars, vard)	mmx_m2m(punpckhdq, vars, vard)
+
+#define	punpckhwd_m2r(var, reg)	mmx_m2r(punpckhwd, var, reg)
+#define	punpckhwd_r2r(regs, regd) mmx_r2r(punpckhwd, regs, regd)
+#define	punpckhwd(vars, vard)	mmx_m2m(punpckhwd, vars, vard)
+
+#define	punpckhbw_m2r(var, reg)	mmx_m2r(punpckhbw, var, reg)
+#define	punpckhbw_r2r(regs, regd) mmx_r2r(punpckhbw, regs, regd)
+#define	punpckhbw(vars, vard)	mmx_m2m(punpckhbw, vars, vard)
+
+
+/*	Empty MMx State
+	(used to clean-up when going from mmx to float use
+	 of the registers that are shared by both; note that
+	 there is no float-to-mmx operation needed, because
+	 only the float tag word info is corruptible)
+*/
+#ifdef	MMX_TRACE
+
+#define	emms() \
+	{ \
+		printf("emms()\n"); \
+		__asm__ __volatile__ ("emms"); \
+	}
+
+#else
+
+#define	emms()			__asm__ __volatile__ ("emms")
+
+#endif
+
+#endif
+/* vi: set ts=4 sw=4 expandtab: */

src/render/opengl/SDL_glfuncs.h

@@ -0,0 +1,477 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+
+/* list of OpenGL functions sorted alphabetically
+   If you need to use a GL function from the SDL video subsystem,
+   change its entry from SDL_PROC_UNUSED to SDL_PROC and rebuild.
+*/
+#define SDL_PROC_UNUSED(ret,func,params)
+
+SDL_PROC_UNUSED(void, glAccum, (GLenum, GLfloat))
+SDL_PROC_UNUSED(void, glAlphaFunc, (GLenum, GLclampf))
+SDL_PROC_UNUSED(GLboolean, glAreTexturesResident,
+                (GLsizei, const GLuint *, GLboolean *))
+SDL_PROC_UNUSED(void, glArrayElement, (GLint))
+SDL_PROC(void, glBegin, (GLenum))
+SDL_PROC(void, glBindTexture, (GLenum, GLuint))
+SDL_PROC_UNUSED(void, glBitmap,
+                (GLsizei, GLsizei, GLfloat, GLfloat, GLfloat, GLfloat,
+                 const GLubyte *))
+SDL_PROC(void, glBlendFunc, (GLenum, GLenum))
+SDL_PROC(void, glBlendFuncSeparate, (GLenum, GLenum, GLenum, GLenum))
+SDL_PROC_UNUSED(void, glCallList, (GLuint))
+SDL_PROC_UNUSED(void, glCallLists, (GLsizei, GLenum, const GLvoid *))
+SDL_PROC(void, glClear, (GLbitfield))
+SDL_PROC_UNUSED(void, glClearAccum, (GLfloat, GLfloat, GLfloat, GLfloat))
+SDL_PROC(void, glClearColor, (GLclampf, GLclampf, GLclampf, GLclampf))
+SDL_PROC_UNUSED(void, glClearDepth, (GLclampd))
+SDL_PROC_UNUSED(void, glClearIndex, (GLfloat))
+SDL_PROC_UNUSED(void, glClearStencil, (GLint))
+SDL_PROC_UNUSED(void, glClipPlane, (GLenum, const GLdouble *))
+SDL_PROC_UNUSED(void, glColor3b, (GLbyte, GLbyte, GLbyte))
+SDL_PROC_UNUSED(void, glColor3bv, (const GLbyte *))
+SDL_PROC_UNUSED(void, glColor3d, (GLdouble, GLdouble, GLdouble))
+SDL_PROC_UNUSED(void, glColor3dv, (const GLdouble *))
+SDL_PROC_UNUSED(void, glColor3f, (GLfloat, GLfloat, GLfloat))
+SDL_PROC(void, glColor3fv, (const GLfloat *))
+SDL_PROC_UNUSED(void, glColor3i, (GLint, GLint, GLint))
+SDL_PROC_UNUSED(void, glColor3iv, (const GLint *))
+SDL_PROC_UNUSED(void, glColor3s, (GLshort, GLshort, GLshort))
+SDL_PROC_UNUSED(void, glColor3sv, (const GLshort *))
+SDL_PROC_UNUSED(void, glColor3ub, (GLubyte, GLubyte, GLubyte))
+SDL_PROC_UNUSED(void, glColor3ubv, (const GLubyte *))
+SDL_PROC_UNUSED(void, glColor3ui, (GLuint, GLuint, GLuint))
+SDL_PROC_UNUSED(void, glColor3uiv, (const GLuint *))
+SDL_PROC_UNUSED(void, glColor3us, (GLushort, GLushort, GLushort))
+SDL_PROC_UNUSED(void, glColor3usv, (const GLushort *))
+SDL_PROC_UNUSED(void, glColor4b, (GLbyte, GLbyte, GLbyte, GLbyte))
+SDL_PROC_UNUSED(void, glColor4bv, (const GLbyte *))
+SDL_PROC_UNUSED(void, glColor4d, (GLdouble, GLdouble, GLdouble, GLdouble))
+SDL_PROC_UNUSED(void, glColor4dv, (const GLdouble *))
+SDL_PROC(void, glColor4f, (GLfloat, GLfloat, GLfloat, GLfloat))
+SDL_PROC_UNUSED(void, glColor4fv, (const GLfloat *))
+SDL_PROC_UNUSED(void, glColor4i, (GLint, GLint, GLint, GLint))
+SDL_PROC_UNUSED(void, glColor4iv, (const GLint *))
+SDL_PROC_UNUSED(void, glColor4s, (GLshort, GLshort, GLshort, GLshort))
+SDL_PROC_UNUSED(void, glColor4sv, (const GLshort *))
+SDL_PROC_UNUSED(void, glColor4ub,
+                (GLubyte red, GLubyte green, GLubyte blue, GLubyte alpha))
+SDL_PROC_UNUSED(void, glColor4ubv, (const GLubyte * v))
+SDL_PROC_UNUSED(void, glColor4ui,
+                (GLuint red, GLuint green, GLuint blue, GLuint alpha))
+SDL_PROC_UNUSED(void, glColor4uiv, (const GLuint * v))
+SDL_PROC_UNUSED(void, glColor4us,
+                (GLushort red, GLushort green, GLushort blue, GLushort alpha))
+SDL_PROC_UNUSED(void, glColor4usv, (const GLushort * v))
+SDL_PROC_UNUSED(void, glColorMask,
+                (GLboolean red, GLboolean green, GLboolean blue,
+                 GLboolean alpha))
+SDL_PROC_UNUSED(void, glColorMaterial, (GLenum face, GLenum mode))
+SDL_PROC_UNUSED(void, glColorPointer,
+                (GLint size, GLenum type, GLsizei stride,
+                 const GLvoid * pointer))
+SDL_PROC_UNUSED(void, glCopyPixels,
+                (GLint x, GLint y, GLsizei width, GLsizei height,
+                 GLenum type))
+SDL_PROC_UNUSED(void, glCopyTexImage1D,
+                (GLenum target, GLint level, GLenum internalFormat, GLint x,
+                 GLint y, GLsizei width, GLint border))
+SDL_PROC_UNUSED(void, glCopyTexImage2D,
+                (GLenum target, GLint level, GLenum internalFormat, GLint x,
+                 GLint y, GLsizei width, GLsizei height, GLint border))
+SDL_PROC_UNUSED(void, glCopyTexSubImage1D,
+                (GLenum target, GLint level, GLint xoffset, GLint x, GLint y,
+                 GLsizei width))
+SDL_PROC_UNUSED(void, glCopyTexSubImage2D,
+                (GLenum target, GLint level, GLint xoffset, GLint yoffset,
+                 GLint x, GLint y, GLsizei width, GLsizei height))
+SDL_PROC_UNUSED(void, glCullFace, (GLenum mode))
+SDL_PROC_UNUSED(void, glDeleteLists, (GLuint list, GLsizei range))
+SDL_PROC(void, glDeleteTextures, (GLsizei n, const GLuint * textures))
+SDL_PROC(void, glDepthFunc, (GLenum func))
+SDL_PROC_UNUSED(void, glDepthMask, (GLboolean flag))
+SDL_PROC_UNUSED(void, glDepthRange, (GLclampd zNear, GLclampd zFar))
+SDL_PROC(void, glDisable, (GLenum cap))
+SDL_PROC_UNUSED(void, glDisableClientState, (GLenum array))
+SDL_PROC_UNUSED(void, glDrawArrays, (GLenum mode, GLint first, GLsizei count))
+SDL_PROC_UNUSED(void, glDrawBuffer, (GLenum mode))
+SDL_PROC_UNUSED(void, glDrawElements,
+                (GLenum mode, GLsizei count, GLenum type,
+                 const GLvoid * indices))
+SDL_PROC(void, glDrawPixels,
+         (GLsizei width, GLsizei height, GLenum format, GLenum type,
+          const GLvoid * pixels))
+SDL_PROC_UNUSED(void, glEdgeFlag, (GLboolean flag))
+SDL_PROC_UNUSED(void, glEdgeFlagPointer,
+                (GLsizei stride, const GLvoid * pointer))
+SDL_PROC_UNUSED(void, glEdgeFlagv, (const GLboolean * flag))
+SDL_PROC(void, glEnable, (GLenum cap))
+SDL_PROC_UNUSED(void, glEnableClientState, (GLenum array))
+SDL_PROC(void, glEnd, (void))
+SDL_PROC_UNUSED(void, glEndList, (void))
+SDL_PROC_UNUSED(void, glEvalCoord1d, (GLdouble u))
+SDL_PROC_UNUSED(void, glEvalCoord1dv, (const GLdouble * u))
+SDL_PROC_UNUSED(void, glEvalCoord1f, (GLfloat u))
+SDL_PROC_UNUSED(void, glEvalCoord1fv, (const GLfloat * u))
+SDL_PROC_UNUSED(void, glEvalCoord2d, (GLdouble u, GLdouble v))
+SDL_PROC_UNUSED(void, glEvalCoord2dv, (const GLdouble * u))
+SDL_PROC_UNUSED(void, glEvalCoord2f, (GLfloat u, GLfloat v))
+SDL_PROC_UNUSED(void, glEvalCoord2fv, (const GLfloat * u))
+SDL_PROC_UNUSED(void, glEvalMesh1, (GLenum mode, GLint i1, GLint i2))
+SDL_PROC_UNUSED(void, glEvalMesh2,
+                (GLenum mode, GLint i1, GLint i2, GLint j1, GLint j2))
+SDL_PROC_UNUSED(void, glEvalPoint1, (GLint i))
+SDL_PROC_UNUSED(void, glEvalPoint2, (GLint i, GLint j))
+SDL_PROC_UNUSED(void, glFeedbackBuffer,
+                (GLsizei size, GLenum type, GLfloat * buffer))
+SDL_PROC_UNUSED(void, glFinish, (void))
+SDL_PROC_UNUSED(void, glFlush, (void))
+SDL_PROC_UNUSED(void, glFogf, (GLenum pname, GLfloat param))
+SDL_PROC_UNUSED(void, glFogfv, (GLenum pname, const GLfloat * params))
+SDL_PROC_UNUSED(void, glFogi, (GLenum pname, GLint param))
+SDL_PROC_UNUSED(void, glFogiv, (GLenum pname, const GLint * params))
+SDL_PROC_UNUSED(void, glFrontFace, (GLenum mode))
+SDL_PROC_UNUSED(void, glFrustum,
+                (GLdouble left, GLdouble right, GLdouble bottom,
+                 GLdouble top, GLdouble zNear, GLdouble zFar))
+SDL_PROC_UNUSED(GLuint, glGenLists, (GLsizei range))
+SDL_PROC(void, glGenTextures, (GLsizei n, GLuint * textures))
+SDL_PROC_UNUSED(void, glGetBooleanv, (GLenum pname, GLboolean * params))
+SDL_PROC_UNUSED(void, glGetClipPlane, (GLenum plane, GLdouble * equation))
+SDL_PROC_UNUSED(void, glGetDoublev, (GLenum pname, GLdouble * params))
+SDL_PROC(GLenum, glGetError, (void))
+SDL_PROC_UNUSED(void, glGetFloatv, (GLenum pname, GLfloat * params))
+SDL_PROC(void, glGetIntegerv, (GLenum pname, GLint * params))
+SDL_PROC_UNUSED(void, glGetLightfv,
+                (GLenum light, GLenum pname, GLfloat * params))
+SDL_PROC_UNUSED(void, glGetLightiv,
+                (GLenum light, GLenum pname, GLint * params))
+SDL_PROC_UNUSED(void, glGetMapdv, (GLenum target, GLenum query, GLdouble * v))
+SDL_PROC_UNUSED(void, glGetMapfv, (GLenum target, GLenum query, GLfloat * v))
+SDL_PROC_UNUSED(void, glGetMapiv, (GLenum target, GLenum query, GLint * v))
+SDL_PROC_UNUSED(void, glGetMaterialfv,
+                (GLenum face, GLenum pname, GLfloat * params))
+SDL_PROC_UNUSED(void, glGetMaterialiv,
+                (GLenum face, GLenum pname, GLint * params))
+SDL_PROC_UNUSED(void, glGetPixelMapfv, (GLenum map, GLfloat * values))
+SDL_PROC_UNUSED(void, glGetPixelMapuiv, (GLenum map, GLuint * values))
+SDL_PROC_UNUSED(void, glGetPixelMapusv, (GLenum map, GLushort * values))
+SDL_PROC(void, glGetPointerv, (GLenum pname, GLvoid * *params))
+SDL_PROC_UNUSED(void, glGetPolygonStipple, (GLubyte * mask))
+SDL_PROC(const GLubyte *, glGetString, (GLenum name))
+SDL_PROC_UNUSED(void, glGetTexEnvfv,
+                (GLenum target, GLenum pname, GLfloat * params))
+SDL_PROC_UNUSED(void, glGetTexEnviv,
+                (GLenum target, GLenum pname, GLint * params))
+SDL_PROC_UNUSED(void, glGetTexGendv,
+                (GLenum coord, GLenum pname, GLdouble * params))
+SDL_PROC_UNUSED(void, glGetTexGenfv,
+                (GLenum coord, GLenum pname, GLfloat * params))
+SDL_PROC_UNUSED(void, glGetTexGeniv,
+                (GLenum coord, GLenum pname, GLint * params))
+SDL_PROC_UNUSED(void, glGetTexImage,
+                (GLenum target, GLint level, GLenum format, GLenum type,
+                 GLvoid * pixels))
+SDL_PROC_UNUSED(void, glGetTexLevelParameterfv,
+                (GLenum target, GLint level, GLenum pname, GLfloat * params))
+SDL_PROC_UNUSED(void, glGetTexLevelParameteriv,
+                (GLenum target, GLint level, GLenum pname, GLint * params))
+SDL_PROC_UNUSED(void, glGetTexParameterfv,
+                (GLenum target, GLenum pname, GLfloat * params))
+SDL_PROC_UNUSED(void, glGetTexParameteriv,
+                (GLenum target, GLenum pname, GLint * params))
+SDL_PROC_UNUSED(void, glHint, (GLenum target, GLenum mode))
+SDL_PROC_UNUSED(void, glIndexMask, (GLuint mask))
+SDL_PROC_UNUSED(void, glIndexPointer,
+                (GLenum type, GLsizei stride, const GLvoid * pointer))
+SDL_PROC_UNUSED(void, glIndexd, (GLdouble c))
+SDL_PROC_UNUSED(void, glIndexdv, (const GLdouble * c))
+SDL_PROC_UNUSED(void, glIndexf, (GLfloat c))
+SDL_PROC_UNUSED(void, glIndexfv, (const GLfloat * c))
+SDL_PROC_UNUSED(void, glIndexi, (GLint c))
+SDL_PROC_UNUSED(void, glIndexiv, (const GLint * c))
+SDL_PROC_UNUSED(void, glIndexs, (GLshort c))
+SDL_PROC_UNUSED(void, glIndexsv, (const GLshort * c))
+SDL_PROC_UNUSED(void, glIndexub, (GLubyte c))
+SDL_PROC_UNUSED(void, glIndexubv, (const GLubyte * c))
+SDL_PROC_UNUSED(void, glInitNames, (void))
+SDL_PROC_UNUSED(void, glInterleavedArrays,
+                (GLenum format, GLsizei stride, const GLvoid * pointer))
+SDL_PROC_UNUSED(GLboolean, glIsEnabled, (GLenum cap))
+SDL_PROC_UNUSED(GLboolean, glIsList, (GLuint list))
+SDL_PROC_UNUSED(GLboolean, glIsTexture, (GLuint texture))
+SDL_PROC_UNUSED(void, glLightModelf, (GLenum pname, GLfloat param))
+SDL_PROC_UNUSED(void, glLightModelfv, (GLenum pname, const GLfloat * params))
+SDL_PROC_UNUSED(void, glLightModeli, (GLenum pname, GLint param))
+SDL_PROC_UNUSED(void, glLightModeliv, (GLenum pname, const GLint * params))
+SDL_PROC_UNUSED(void, glLightf, (GLenum light, GLenum pname, GLfloat param))
+SDL_PROC_UNUSED(void, glLightfv,
+                (GLenum light, GLenum pname, const GLfloat * params))
+SDL_PROC_UNUSED(void, glLighti, (GLenum light, GLenum pname, GLint param))
+SDL_PROC_UNUSED(void, glLightiv,
+                (GLenum light, GLenum pname, const GLint * params))
+SDL_PROC_UNUSED(void, glLineStipple, (GLint factor, GLushort pattern))
+SDL_PROC(void, glLineWidth, (GLfloat width))
+SDL_PROC_UNUSED(void, glListBase, (GLuint base))
+SDL_PROC(void, glLoadIdentity, (void))
+SDL_PROC_UNUSED(void, glLoadMatrixd, (const GLdouble * m))
+SDL_PROC_UNUSED(void, glLoadMatrixf, (const GLfloat * m))
+SDL_PROC_UNUSED(void, glLoadName, (GLuint name))
+SDL_PROC_UNUSED(void, glLogicOp, (GLenum opcode))
+SDL_PROC_UNUSED(void, glMap1d,
+                (GLenum target, GLdouble u1, GLdouble u2, GLint stride,
+                 GLint order, const GLdouble * points))
+SDL_PROC_UNUSED(void, glMap1f,
+                (GLenum target, GLfloat u1, GLfloat u2, GLint stride,
+                 GLint order, const GLfloat * points))
+SDL_PROC_UNUSED(void, glMap2d,
+                (GLenum target, GLdouble u1, GLdouble u2, GLint ustride,
+                 GLint uorder, GLdouble v1, GLdouble v2, GLint vstride,
+                 GLint vorder, const GLdouble * points))
+SDL_PROC_UNUSED(void, glMap2f,
+                (GLenum target, GLfloat u1, GLfloat u2, GLint ustride,
+                 GLint uorder, GLfloat v1, GLfloat v2, GLint vstride,
+                 GLint vorder, const GLfloat * points))
+SDL_PROC_UNUSED(void, glMapGrid1d, (GLint un, GLdouble u1, GLdouble u2))
+SDL_PROC_UNUSED(void, glMapGrid1f, (GLint un, GLfloat u1, GLfloat u2))
+SDL_PROC_UNUSED(void, glMapGrid2d,
+                (GLint un, GLdouble u1, GLdouble u2, GLint vn, GLdouble v1,
+                 GLdouble v2))
+SDL_PROC_UNUSED(void, glMapGrid2f,
+                (GLint un, GLfloat u1, GLfloat u2, GLint vn, GLfloat v1,
+                 GLfloat v2))
+SDL_PROC_UNUSED(void, glMaterialf, (GLenum face, GLenum pname, GLfloat param))
+SDL_PROC_UNUSED(void, glMaterialfv,
+                (GLenum face, GLenum pname, const GLfloat * params))
+SDL_PROC_UNUSED(void, glMateriali, (GLenum face, GLenum pname, GLint param))
+SDL_PROC_UNUSED(void, glMaterialiv,
+                (GLenum face, GLenum pname, const GLint * params))
+SDL_PROC(void, glMatrixMode, (GLenum mode))
+SDL_PROC_UNUSED(void, glMultMatrixd, (const GLdouble * m))
+SDL_PROC_UNUSED(void, glMultMatrixf, (const GLfloat * m))
+SDL_PROC_UNUSED(void, glNewList, (GLuint list, GLenum mode))
+SDL_PROC_UNUSED(void, glNormal3b, (GLbyte nx, GLbyte ny, GLbyte nz))
+SDL_PROC_UNUSED(void, glNormal3bv, (const GLbyte * v))
+SDL_PROC_UNUSED(void, glNormal3d, (GLdouble nx, GLdouble ny, GLdouble nz))
+SDL_PROC_UNUSED(void, glNormal3dv, (const GLdouble * v))
+SDL_PROC_UNUSED(void, glNormal3f, (GLfloat nx, GLfloat ny, GLfloat nz))
+SDL_PROC_UNUSED(void, glNormal3fv, (const GLfloat * v))
+SDL_PROC_UNUSED(void, glNormal3i, (GLint nx, GLint ny, GLint nz))
+SDL_PROC_UNUSED(void, glNormal3iv, (const GLint * v))
+SDL_PROC_UNUSED(void, glNormal3s, (GLshort nx, GLshort ny, GLshort nz))
+SDL_PROC_UNUSED(void, glNormal3sv, (const GLshort * v))
+SDL_PROC_UNUSED(void, glNormalPointer,
+                (GLenum type, GLsizei stride, const GLvoid * pointer))
+SDL_PROC(void, glOrtho,
+         (GLdouble left, GLdouble right, GLdouble bottom, GLdouble top,
+          GLdouble zNear, GLdouble zFar))
+SDL_PROC_UNUSED(void, glPassThrough, (GLfloat token))
+SDL_PROC_UNUSED(void, glPixelMapfv,
+                (GLenum map, GLsizei mapsize, const GLfloat * values))
+SDL_PROC_UNUSED(void, glPixelMapuiv,
+                (GLenum map, GLsizei mapsize, const GLuint * values))
+SDL_PROC_UNUSED(void, glPixelMapusv,
+                (GLenum map, GLsizei mapsize, const GLushort * values))
+SDL_PROC_UNUSED(void, glPixelStoref, (GLenum pname, GLfloat param))
+SDL_PROC(void, glPixelStorei, (GLenum pname, GLint param))
+SDL_PROC_UNUSED(void, glPixelTransferf, (GLenum pname, GLfloat param))
+SDL_PROC_UNUSED(void, glPixelTransferi, (GLenum pname, GLint param))
+SDL_PROC_UNUSED(void, glPixelZoom, (GLfloat xfactor, GLfloat yfactor))
+SDL_PROC(void, glPointSize, (GLfloat size))
+SDL_PROC_UNUSED(void, glPolygonMode, (GLenum face, GLenum mode))
+SDL_PROC_UNUSED(void, glPolygonOffset, (GLfloat factor, GLfloat units))
+SDL_PROC_UNUSED(void, glPolygonStipple, (const GLubyte * mask))
+SDL_PROC_UNUSED(void, glPopAttrib, (void))
+SDL_PROC_UNUSED(void, glPopClientAttrib, (void))
+SDL_PROC(void, glPopMatrix, (void))
+SDL_PROC_UNUSED(void, glPopName, (void))
+SDL_PROC_UNUSED(void, glPrioritizeTextures,
+                (GLsizei n, const GLuint * textures,
+                 const GLclampf * priorities))
+SDL_PROC_UNUSED(void, glPushAttrib, (GLbitfield mask))
+SDL_PROC_UNUSED(void, glPushClientAttrib, (GLbitfield mask))
+SDL_PROC(void, glPushMatrix, (void))
+SDL_PROC_UNUSED(void, glPushName, (GLuint name))
+SDL_PROC_UNUSED(void, glRasterPos2d, (GLdouble x, GLdouble y))
+SDL_PROC_UNUSED(void, glRasterPos2dv, (const GLdouble * v))
+SDL_PROC_UNUSED(void, glRasterPos2f, (GLfloat x, GLfloat y))
+SDL_PROC_UNUSED(void, glRasterPos2fv, (const GLfloat * v))
+SDL_PROC(void, glRasterPos2i, (GLint x, GLint y))
+SDL_PROC_UNUSED(void, glRasterPos2iv, (const GLint * v))
+SDL_PROC_UNUSED(void, glRasterPos2s, (GLshort x, GLshort y))
+SDL_PROC_UNUSED(void, glRasterPos2sv, (const GLshort * v))
+SDL_PROC_UNUSED(void, glRasterPos3d, (GLdouble x, GLdouble y, GLdouble z))
+SDL_PROC_UNUSED(void, glRasterPos3dv, (const GLdouble * v))
+SDL_PROC_UNUSED(void, glRasterPos3f, (GLfloat x, GLfloat y, GLfloat z))
+SDL_PROC_UNUSED(void, glRasterPos3fv, (const GLfloat * v))
+SDL_PROC_UNUSED(void, glRasterPos3i, (GLint x, GLint y, GLint z))
+SDL_PROC_UNUSED(void, glRasterPos3iv, (const GLint * v))
+SDL_PROC_UNUSED(void, glRasterPos3s, (GLshort x, GLshort y, GLshort z))
+SDL_PROC_UNUSED(void, glRasterPos3sv, (const GLshort * v))
+SDL_PROC_UNUSED(void, glRasterPos4d,
+                (GLdouble x, GLdouble y, GLdouble z, GLdouble w))
+SDL_PROC_UNUSED(void, glRasterPos4dv, (const GLdouble * v))
+SDL_PROC_UNUSED(void, glRasterPos4f,
+                (GLfloat x, GLfloat y, GLfloat z, GLfloat w))
+SDL_PROC_UNUSED(void, glRasterPos4fv, (const GLfloat * v))
+SDL_PROC_UNUSED(void, glRasterPos4i, (GLint x, GLint y, GLint z, GLint w))
+SDL_PROC_UNUSED(void, glRasterPos4iv, (const GLint * v))
+SDL_PROC_UNUSED(void, glRasterPos4s,
+                (GLshort x, GLshort y, GLshort z, GLshort w))
+SDL_PROC_UNUSED(void, glRasterPos4sv, (const GLshort * v))
+SDL_PROC(void, glReadBuffer, (GLenum mode))
+SDL_PROC(void, glReadPixels,
+         (GLint x, GLint y, GLsizei width, GLsizei height,
+          GLenum format, GLenum type, GLvoid * pixels))
+SDL_PROC_UNUSED(void, glRectd,
+                (GLdouble x1, GLdouble y1, GLdouble x2, GLdouble y2))
+SDL_PROC_UNUSED(void, glRectdv, (const GLdouble * v1, const GLdouble * v2))
+SDL_PROC(void, glRectf,
+                (GLfloat x1, GLfloat y1, GLfloat x2, GLfloat y2))
+SDL_PROC_UNUSED(void, glRectfv, (const GLfloat * v1, const GLfloat * v2))
+SDL_PROC_UNUSED(void, glRecti, (GLint x1, GLint y1, GLint x2, GLint y2))
+SDL_PROC_UNUSED(void, glRectiv, (const GLint * v1, const GLint * v2))
+SDL_PROC_UNUSED(void, glRects,
+                (GLshort x1, GLshort y1, GLshort x2, GLshort y2))
+SDL_PROC_UNUSED(void, glRectsv, (const GLshort * v1, const GLshort * v2))
+SDL_PROC_UNUSED(GLint, glRenderMode, (GLenum mode))
+SDL_PROC(void, glRotated,
+                (GLdouble angle, GLdouble x, GLdouble y, GLdouble z))
+SDL_PROC(void, glRotatef,
+                (GLfloat angle, GLfloat x, GLfloat y, GLfloat z))
+SDL_PROC_UNUSED(void, glScaled, (GLdouble x, GLdouble y, GLdouble z))
+SDL_PROC_UNUSED(void, glScalef, (GLfloat x, GLfloat y, GLfloat z))
+SDL_PROC(void, glScissor, (GLint x, GLint y, GLsizei width, GLsizei height))
+SDL_PROC_UNUSED(void, glSelectBuffer, (GLsizei size, GLuint * buffer))
+SDL_PROC(void, glShadeModel, (GLenum mode))
+SDL_PROC_UNUSED(void, glStencilFunc, (GLenum func, GLint ref, GLuint mask))
+SDL_PROC_UNUSED(void, glStencilMask, (GLuint mask))
+SDL_PROC_UNUSED(void, glStencilOp, (GLenum fail, GLenum zfail, GLenum zpass))
+SDL_PROC_UNUSED(void, glTexCoord1d, (GLdouble s))
+SDL_PROC_UNUSED(void, glTexCoord1dv, (const GLdouble * v))
+SDL_PROC_UNUSED(void, glTexCoord1f, (GLfloat s))
+SDL_PROC_UNUSED(void, glTexCoord1fv, (const GLfloat * v))
+SDL_PROC_UNUSED(void, glTexCoord1i, (GLint s))
+SDL_PROC_UNUSED(void, glTexCoord1iv, (const GLint * v))
+SDL_PROC_UNUSED(void, glTexCoord1s, (GLshort s))
+SDL_PROC_UNUSED(void, glTexCoord1sv, (const GLshort * v))
+SDL_PROC_UNUSED(void, glTexCoord2d, (GLdouble s, GLdouble t))
+SDL_PROC_UNUSED(void, glTexCoord2dv, (const GLdouble * v))
+SDL_PROC(void, glTexCoord2f, (GLfloat s, GLfloat t))
+SDL_PROC_UNUSED(void, glTexCoord2fv, (const GLfloat * v))
+SDL_PROC_UNUSED(void, glTexCoord2i, (GLint s, GLint t))
+SDL_PROC_UNUSED(void, glTexCoord2iv, (const GLint * v))
+SDL_PROC_UNUSED(void, glTexCoord2s, (GLshort s, GLshort t))
+SDL_PROC_UNUSED(void, glTexCoord2sv, (const GLshort * v))
+SDL_PROC_UNUSED(void, glTexCoord3d, (GLdouble s, GLdouble t, GLdouble r))
+SDL_PROC_UNUSED(void, glTexCoord3dv, (const GLdouble * v))
+SDL_PROC_UNUSED(void, glTexCoord3f, (GLfloat s, GLfloat t, GLfloat r))
+SDL_PROC_UNUSED(void, glTexCoord3fv, (const GLfloat * v))
+SDL_PROC_UNUSED(void, glTexCoord3i, (GLint s, GLint t, GLint r))
+SDL_PROC_UNUSED(void, glTexCoord3iv, (const GLint * v))
+SDL_PROC_UNUSED(void, glTexCoord3s, (GLshort s, GLshort t, GLshort r))
+SDL_PROC_UNUSED(void, glTexCoord3sv, (const GLshort * v))
+SDL_PROC_UNUSED(void, glTexCoord4d,
+                (GLdouble s, GLdouble t, GLdouble r, GLdouble q))
+SDL_PROC_UNUSED(void, glTexCoord4dv, (const GLdouble * v))
+SDL_PROC_UNUSED(void, glTexCoord4f,
+                (GLfloat s, GLfloat t, GLfloat r, GLfloat q))
+SDL_PROC_UNUSED(void, glTexCoord4fv, (const GLfloat * v))
+SDL_PROC_UNUSED(void, glTexCoord4i, (GLint s, GLint t, GLint r, GLint q))
+SDL_PROC_UNUSED(void, glTexCoord4iv, (const GLint * v))
+SDL_PROC_UNUSED(void, glTexCoord4s,
+                (GLshort s, GLshort t, GLshort r, GLshort q))
+SDL_PROC_UNUSED(void, glTexCoord4sv, (const GLshort * v))
+SDL_PROC_UNUSED(void, glTexCoordPointer,
+                (GLint size, GLenum type, GLsizei stride,
+                 const GLvoid * pointer))
+SDL_PROC(void, glTexEnvf, (GLenum target, GLenum pname, GLfloat param))
+SDL_PROC_UNUSED(void, glTexEnvfv,
+                (GLenum target, GLenum pname, const GLfloat * params))
+SDL_PROC_UNUSED(void, glTexEnvi, (GLenum target, GLenum pname, GLint param))
+SDL_PROC_UNUSED(void, glTexEnviv,
+                (GLenum target, GLenum pname, const GLint * params))
+SDL_PROC_UNUSED(void, glTexGend, (GLenum coord, GLenum pname, GLdouble param))
+SDL_PROC_UNUSED(void, glTexGendv,
+                (GLenum coord, GLenum pname, const GLdouble * params))
+SDL_PROC_UNUSED(void, glTexGenf, (GLenum coord, GLenum pname, GLfloat param))
+SDL_PROC_UNUSED(void, glTexGenfv,
+                (GLenum coord, GLenum pname, const GLfloat * params))
+SDL_PROC_UNUSED(void, glTexGeni, (GLenum coord, GLenum pname, GLint param))
+SDL_PROC_UNUSED(void, glTexGeniv,
+                (GLenum coord, GLenum pname, const GLint * params))
+SDL_PROC_UNUSED(void, glTexImage1D,
+                (GLenum target, GLint level, GLint internalformat,
+                 GLsizei width, GLint border, GLenum format, GLenum type,
+                 const GLvoid * pixels))
+SDL_PROC(void, glTexImage2D,
+         (GLenum target, GLint level, GLint internalformat, GLsizei width,
+          GLsizei height, GLint border, GLenum format, GLenum type,
+          const GLvoid * pixels))
+SDL_PROC_UNUSED(void, glTexParameterf,
+                (GLenum target, GLenum pname, GLfloat param))
+SDL_PROC_UNUSED(void, glTexParameterfv,
+                (GLenum target, GLenum pname, const GLfloat * params))
+SDL_PROC(void, glTexParameteri, (GLenum target, GLenum pname, GLint param))
+SDL_PROC_UNUSED(void, glTexParameteriv,
+                (GLenum target, GLenum pname, const GLint * params))
+SDL_PROC_UNUSED(void, glTexSubImage1D,
+                (GLenum target, GLint level, GLint xoffset, GLsizei width,
+                 GLenum format, GLenum type, const GLvoid * pixels))
+SDL_PROC(void, glTexSubImage2D,
+         (GLenum target, GLint level, GLint xoffset, GLint yoffset,
+          GLsizei width, GLsizei height, GLenum format, GLenum type,
+          const GLvoid * pixels))
+SDL_PROC_UNUSED(void, glTranslated, (GLdouble x, GLdouble y, GLdouble z))
+SDL_PROC(void, glTranslatef, (GLfloat x, GLfloat y, GLfloat z))
+SDL_PROC_UNUSED(void, glVertex2d, (GLdouble x, GLdouble y))
+SDL_PROC_UNUSED(void, glVertex2dv, (const GLdouble * v))
+SDL_PROC(void, glVertex2f, (GLfloat x, GLfloat y))
+SDL_PROC_UNUSED(void, glVertex2fv, (const GLfloat * v))
+SDL_PROC_UNUSED(void, glVertex2i, (GLint x, GLint y))
+SDL_PROC_UNUSED(void, glVertex2iv, (const GLint * v))
+SDL_PROC_UNUSED(void, glVertex2s, (GLshort x, GLshort y))
+SDL_PROC_UNUSED(void, glVertex2sv, (const GLshort * v))
+SDL_PROC_UNUSED(void, glVertex3d, (GLdouble x, GLdouble y, GLdouble z))
+SDL_PROC_UNUSED(void, glVertex3dv, (const GLdouble * v))
+SDL_PROC_UNUSED(void, glVertex3f, (GLfloat x, GLfloat y, GLfloat z))
+SDL_PROC(void, glVertex3fv, (const GLfloat * v))
+SDL_PROC_UNUSED(void, glVertex3i, (GLint x, GLint y, GLint z))
+SDL_PROC_UNUSED(void, glVertex3iv, (const GLint * v))
+SDL_PROC_UNUSED(void, glVertex3s, (GLshort x, GLshort y, GLshort z))
+SDL_PROC_UNUSED(void, glVertex3sv, (const GLshort * v))
+SDL_PROC_UNUSED(void, glVertex4d,
+                (GLdouble x, GLdouble y, GLdouble z, GLdouble w))
+SDL_PROC_UNUSED(void, glVertex4dv, (const GLdouble * v))
+SDL_PROC_UNUSED(void, glVertex4f,
+                (GLfloat x, GLfloat y, GLfloat z, GLfloat w))
+SDL_PROC_UNUSED(void, glVertex4fv, (const GLfloat * v))
+SDL_PROC_UNUSED(void, glVertex4i, (GLint x, GLint y, GLint z, GLint w))
+SDL_PROC_UNUSED(void, glVertex4iv, (const GLint * v))
+SDL_PROC_UNUSED(void, glVertex4s,
+                (GLshort x, GLshort y, GLshort z, GLshort w))
+SDL_PROC_UNUSED(void, glVertex4sv, (const GLshort * v))
+SDL_PROC_UNUSED(void, glVertexPointer,
+                (GLint size, GLenum type, GLsizei stride,
+                 const GLvoid * pointer))
+SDL_PROC(void, glViewport, (GLint x, GLint y, GLsizei width, GLsizei height))
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/opengl/SDL_shaders_gl.c

@@ -0,0 +1,463 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#if SDL_VIDEO_RENDER_OGL && !SDL_RENDER_DISABLED
+
+#include "SDL_stdinc.h"
+#include "SDL_log.h"
+#include "SDL_opengl.h"
+#include "SDL_video.h"
+#include "SDL_shaders_gl.h"
+
+/* OpenGL shader implementation */
+
+/* #define DEBUG_SHADERS */
+
+typedef struct
+{
+    GLhandleARB program;
+    GLhandleARB vert_shader;
+    GLhandleARB frag_shader;
+} GL_ShaderData;
+
+struct GL_ShaderContext
+{
+    GLenum (*glGetError)(void);
+
+    PFNGLATTACHOBJECTARBPROC glAttachObjectARB;
+    PFNGLCOMPILESHADERARBPROC glCompileShaderARB;
+    PFNGLCREATEPROGRAMOBJECTARBPROC glCreateProgramObjectARB;
+    PFNGLCREATESHADEROBJECTARBPROC glCreateShaderObjectARB;
+    PFNGLDELETEOBJECTARBPROC glDeleteObjectARB;
+    PFNGLGETINFOLOGARBPROC glGetInfoLogARB;
+    PFNGLGETOBJECTPARAMETERIVARBPROC glGetObjectParameterivARB;
+    PFNGLGETUNIFORMLOCATIONARBPROC glGetUniformLocationARB;
+    PFNGLLINKPROGRAMARBPROC glLinkProgramARB;
+    PFNGLSHADERSOURCEARBPROC glShaderSourceARB;
+    PFNGLUNIFORM1IARBPROC glUniform1iARB;
+    PFNGLUNIFORM1FARBPROC glUniform1fARB;
+    PFNGLUSEPROGRAMOBJECTARBPROC glUseProgramObjectARB;
+
+    SDL_bool GL_ARB_texture_rectangle_supported;
+
+    GL_ShaderData shaders[NUM_SHADERS];
+};
+
+/*
+ * NOTE: Always use sampler2D, etc here. We'll #define them to the
+ *  texture_rectangle versions if we choose to use that extension.
+ */
+static const char *shader_source[NUM_SHADERS][2] =
+{
+    /* SHADER_NONE */
+    { NULL, NULL },
+
+    /* SHADER_SOLID */
+    {
+        /* vertex shader */
+"varying vec4 v_color;\n"
+"\n"
+"void main()\n"
+"{\n"
+"    gl_Position = gl_ModelViewProjectionMatrix * gl_Vertex;\n"
+"    v_color = gl_Color;\n"
+"}",
+        /* fragment shader */
+"varying vec4 v_color;\n"
+"\n"
+"void main()\n"
+"{\n"
+"    gl_FragColor = v_color;\n"
+"}"
+    },
+
+    /* SHADER_RGB */
+    {
+        /* vertex shader */
+"varying vec4 v_color;\n"
+"varying vec2 v_texCoord;\n"
+"\n"
+"void main()\n"
+"{\n"
+"    gl_Position = gl_ModelViewProjectionMatrix * gl_Vertex;\n"
+"    v_color = gl_Color;\n"
+"    v_texCoord = vec2(gl_MultiTexCoord0);\n"
+"}",
+        /* fragment shader */
+"varying vec4 v_color;\n"
+"varying vec2 v_texCoord;\n"
+"uniform sampler2D tex0;\n"
+"\n"
+"void main()\n"
+"{\n"
+"    gl_FragColor = texture2D(tex0, v_texCoord) * v_color;\n"
+"}"
+    },
+
+    /* SHADER_YUV */
+    {
+        /* vertex shader */
+"varying vec4 v_color;\n"
+"varying vec2 v_texCoord;\n"
+"\n"
+"void main()\n"
+"{\n"
+"    gl_Position = gl_ModelViewProjectionMatrix * gl_Vertex;\n"
+"    v_color = gl_Color;\n"
+"    v_texCoord = vec2(gl_MultiTexCoord0);\n"
+"}",
+        /* fragment shader */
+"varying vec4 v_color;\n"
+"varying vec2 v_texCoord;\n"
+"uniform sampler2D tex0; // Y \n"
+"uniform sampler2D tex1; // U \n"
+"uniform sampler2D tex2; // V \n"
+"\n"
+"// YUV offset \n"
+"const vec3 offset = vec3(-0.0627451017, -0.501960814, -0.501960814);\n"
+"\n"
+"// RGB coefficients \n"
+"const vec3 Rcoeff = vec3(1.164,  0.000,  1.596);\n"
+"const vec3 Gcoeff = vec3(1.164, -0.391, -0.813);\n"
+"const vec3 Bcoeff = vec3(1.164,  2.018,  0.000);\n"
+"\n"
+"void main()\n"
+"{\n"
+"    vec2 tcoord;\n"
+"    vec3 yuv, rgb;\n"
+"\n"
+"    // Get the Y value \n"
+"    tcoord = v_texCoord;\n"
+"    yuv.x = texture2D(tex0, tcoord).r;\n"
+"\n"
+"    // Get the U and V values \n"
+"    tcoord *= UVCoordScale;\n"
+"    yuv.y = texture2D(tex1, tcoord).r;\n"
+"    yuv.z = texture2D(tex2, tcoord).r;\n"
+"\n"
+"    // Do the color transform \n"
+"    yuv += offset;\n"
+"    rgb.r = dot(yuv, Rcoeff);\n"
+"    rgb.g = dot(yuv, Gcoeff);\n"
+"    rgb.b = dot(yuv, Bcoeff);\n"
+"\n"
+"    // That was easy. :) \n"
+"    gl_FragColor = vec4(rgb, 1.0) * v_color;\n"
+"}"
+    },
+
+    /* SHADER_NV12 */
+    {
+        /* vertex shader */
+"varying vec4 v_color;\n"
+"varying vec2 v_texCoord;\n"
+"\n"
+"void main()\n"
+"{\n"
+"    gl_Position = gl_ModelViewProjectionMatrix * gl_Vertex;\n"
+"    v_color = gl_Color;\n"
+"    v_texCoord = vec2(gl_MultiTexCoord0);\n"
+"}",
+        /* fragment shader */
+"varying vec4 v_color;\n"
+"varying vec2 v_texCoord;\n"
+"uniform sampler2D tex0; // Y \n"
+"uniform sampler2D tex1; // U/V \n"
+"\n"
+"// YUV offset \n"
+"const vec3 offset = vec3(-0.0627451017, -0.501960814, -0.501960814);\n"
+"\n"
+"// RGB coefficients \n"
+"const vec3 Rcoeff = vec3(1.164,  0.000,  1.596);\n"
+"const vec3 Gcoeff = vec3(1.164, -0.391, -0.813);\n"
+"const vec3 Bcoeff = vec3(1.164,  2.018,  0.000);\n"
+"\n"
+"void main()\n"
+"{\n"
+"    vec2 tcoord;\n"
+"    vec3 yuv, rgb;\n"
+"\n"
+"    // Get the Y value \n"
+"    tcoord = v_texCoord;\n"
+"    yuv.x = texture2D(tex0, tcoord).r;\n"
+"\n"
+"    // Get the U and V values \n"
+"    tcoord *= UVCoordScale;\n"
+"    yuv.yz = texture2D(tex1, tcoord).ra;\n"
+"\n"
+"    // Do the color transform \n"
+"    yuv += offset;\n"
+"    rgb.r = dot(yuv, Rcoeff);\n"
+"    rgb.g = dot(yuv, Gcoeff);\n"
+"    rgb.b = dot(yuv, Bcoeff);\n"
+"\n"
+"    // That was easy. :) \n"
+"    gl_FragColor = vec4(rgb, 1.0) * v_color;\n"
+"}"
+    },
+
+    /* SHADER_NV21 */
+    {
+        /* vertex shader */
+"varying vec4 v_color;\n"
+"varying vec2 v_texCoord;\n"
+"\n"
+"void main()\n"
+"{\n"
+"    gl_Position = gl_ModelViewProjectionMatrix * gl_Vertex;\n"
+"    v_color = gl_Color;\n"
+"    v_texCoord = vec2(gl_MultiTexCoord0);\n"
+"}",
+        /* fragment shader */
+"varying vec4 v_color;\n"
+"varying vec2 v_texCoord;\n"
+"uniform sampler2D tex0; // Y \n"
+"uniform sampler2D tex1; // U/V \n"
+"\n"
+"// YUV offset \n"
+"const vec3 offset = vec3(-0.0627451017, -0.501960814, -0.501960814);\n"
+"\n"
+"// RGB coefficients \n"
+"const vec3 Rcoeff = vec3(1.164,  0.000,  1.596);\n"
+"const vec3 Gcoeff = vec3(1.164, -0.391, -0.813);\n"
+"const vec3 Bcoeff = vec3(1.164,  2.018,  0.000);\n"
+"\n"
+"void main()\n"
+"{\n"
+"    vec2 tcoord;\n"
+"    vec3 yuv, rgb;\n"
+"\n"
+"    // Get the Y value \n"
+"    tcoord = v_texCoord;\n"
+"    yuv.x = texture2D(tex0, tcoord).r;\n"
+"\n"
+"    // Get the U and V values \n"
+"    tcoord *= UVCoordScale;\n"
+"    yuv.yz = texture2D(tex1, tcoord).ar;\n"
+"\n"
+"    // Do the color transform \n"
+"    yuv += offset;\n"
+"    rgb.r = dot(yuv, Rcoeff);\n"
+"    rgb.g = dot(yuv, Gcoeff);\n"
+"    rgb.b = dot(yuv, Bcoeff);\n"
+"\n"
+"    // That was easy. :) \n"
+"    gl_FragColor = vec4(rgb, 1.0) * v_color;\n"
+"}"
+    },
+};
+
+static SDL_bool
+CompileShader(GL_ShaderContext *ctx, GLhandleARB shader, const char *defines, const char *source)
+{
+    GLint status;
+    const char *sources[2];
+
+    sources[0] = defines;
+    sources[1] = source;
+
+    ctx->glShaderSourceARB(shader, SDL_arraysize(sources), sources, NULL);
+    ctx->glCompileShaderARB(shader);
+    ctx->glGetObjectParameterivARB(shader, GL_OBJECT_COMPILE_STATUS_ARB, &status);
+    if (status == 0) {
+        GLint length;
+        char *info;
+
+        ctx->glGetObjectParameterivARB(shader, GL_OBJECT_INFO_LOG_LENGTH_ARB, &length);
+        info = SDL_stack_alloc(char, length+1);
+        ctx->glGetInfoLogARB(shader, length, NULL, info);
+        SDL_LogError(SDL_LOG_CATEGORY_RENDER,
+            "Failed to compile shader:\n%s%s\n%s", defines, source, info);
+#ifdef DEBUG_SHADERS
+        fprintf(stderr,
+            "Failed to compile shader:\n%s%s\n%s", defines, source, info);
+#endif
+        SDL_stack_free(info);
+
+        return SDL_FALSE;
+    } else {
+        return SDL_TRUE;
+    }
+}
+
+static SDL_bool
+CompileShaderProgram(GL_ShaderContext *ctx, int index, GL_ShaderData *data)
+{
+    const int num_tmus_bound = 4;
+    const char *vert_defines = "";
+    const char *frag_defines = "";
+    int i;
+    GLint location;
+
+    if (index == SHADER_NONE) {
+        return SDL_TRUE;
+    }
+
+    ctx->glGetError();
+
+    /* Make sure we use the correct sampler type for our texture type */
+    if (ctx->GL_ARB_texture_rectangle_supported) {
+        frag_defines =
+"#define sampler2D sampler2DRect\n"
+"#define texture2D texture2DRect\n"
+"#define UVCoordScale 0.5\n";
+    } else {
+        frag_defines = 
+"#define UVCoordScale 1.0\n";
+    }
+
+    /* Create one program object to rule them all */
+    data->program = ctx->glCreateProgramObjectARB();
+
+    /* Create the vertex shader */
+    data->vert_shader = ctx->glCreateShaderObjectARB(GL_VERTEX_SHADER_ARB);
+    if (!CompileShader(ctx, data->vert_shader, vert_defines, shader_source[index][0])) {
+        return SDL_FALSE;
+    }
+
+    /* Create the fragment shader */
+    data->frag_shader = ctx->glCreateShaderObjectARB(GL_FRAGMENT_SHADER_ARB);
+    if (!CompileShader(ctx, data->frag_shader, frag_defines, shader_source[index][1])) {
+        return SDL_FALSE;
+    }
+
+    /* ... and in the darkness bind them */
+    ctx->glAttachObjectARB(data->program, data->vert_shader);
+    ctx->glAttachObjectARB(data->program, data->frag_shader);
+    ctx->glLinkProgramARB(data->program);
+
+    /* Set up some uniform variables */
+    ctx->glUseProgramObjectARB(data->program);
+    for (i = 0; i < num_tmus_bound; ++i) {
+        char tex_name[10];
+        SDL_snprintf(tex_name, SDL_arraysize(tex_name), "tex%d", i);
+        location = ctx->glGetUniformLocationARB(data->program, tex_name);
+        if (location >= 0) {
+            ctx->glUniform1iARB(location, i);
+        }
+    }
+    ctx->glUseProgramObjectARB(0);
+
+    return (ctx->glGetError() == GL_NO_ERROR);
+}
+
+static void
+DestroyShaderProgram(GL_ShaderContext *ctx, GL_ShaderData *data)
+{
+    ctx->glDeleteObjectARB(data->vert_shader);
+    ctx->glDeleteObjectARB(data->frag_shader);
+    ctx->glDeleteObjectARB(data->program);
+}
+
+GL_ShaderContext *
+GL_CreateShaderContext()
+{
+    GL_ShaderContext *ctx;
+    SDL_bool shaders_supported;
+    int i;
+
+    ctx = (GL_ShaderContext *)SDL_calloc(1, sizeof(*ctx));
+    if (!ctx) {
+        return NULL;
+    }
+
+    if (!SDL_GL_ExtensionSupported("GL_ARB_texture_non_power_of_two") &&
+        (SDL_GL_ExtensionSupported("GL_ARB_texture_rectangle") ||
+         SDL_GL_ExtensionSupported("GL_EXT_texture_rectangle"))) {
+        ctx->GL_ARB_texture_rectangle_supported = SDL_TRUE;
+    }
+
+    /* Check for shader support */
+    shaders_supported = SDL_FALSE;
+    if (SDL_GL_ExtensionSupported("GL_ARB_shader_objects") &&
+        SDL_GL_ExtensionSupported("GL_ARB_shading_language_100") &&
+        SDL_GL_ExtensionSupported("GL_ARB_vertex_shader") &&
+        SDL_GL_ExtensionSupported("GL_ARB_fragment_shader")) {
+        ctx->glGetError = (GLenum (*)(void)) SDL_GL_GetProcAddress("glGetError");
+        ctx->glAttachObjectARB = (PFNGLATTACHOBJECTARBPROC) SDL_GL_GetProcAddress("glAttachObjectARB");
+        ctx->glCompileShaderARB = (PFNGLCOMPILESHADERARBPROC) SDL_GL_GetProcAddress("glCompileShaderARB");
+        ctx->glCreateProgramObjectARB = (PFNGLCREATEPROGRAMOBJECTARBPROC) SDL_GL_GetProcAddress("glCreateProgramObjectARB");
+        ctx->glCreateShaderObjectARB = (PFNGLCREATESHADEROBJECTARBPROC) SDL_GL_GetProcAddress("glCreateShaderObjectARB");
+        ctx->glDeleteObjectARB = (PFNGLDELETEOBJECTARBPROC) SDL_GL_GetProcAddress("glDeleteObjectARB");
+        ctx->glGetInfoLogARB = (PFNGLGETINFOLOGARBPROC) SDL_GL_GetProcAddress("glGetInfoLogARB");
+        ctx->glGetObjectParameterivARB = (PFNGLGETOBJECTPARAMETERIVARBPROC) SDL_GL_GetProcAddress("glGetObjectParameterivARB");
+        ctx->glGetUniformLocationARB = (PFNGLGETUNIFORMLOCATIONARBPROC) SDL_GL_GetProcAddress("glGetUniformLocationARB");
+        ctx->glLinkProgramARB = (PFNGLLINKPROGRAMARBPROC) SDL_GL_GetProcAddress("glLinkProgramARB");
+        ctx->glShaderSourceARB = (PFNGLSHADERSOURCEARBPROC) SDL_GL_GetProcAddress("glShaderSourceARB");
+        ctx->glUniform1iARB = (PFNGLUNIFORM1IARBPROC) SDL_GL_GetProcAddress("glUniform1iARB");
+        ctx->glUniform1fARB = (PFNGLUNIFORM1FARBPROC) SDL_GL_GetProcAddress("glUniform1fARB");
+        ctx->glUseProgramObjectARB = (PFNGLUSEPROGRAMOBJECTARBPROC) SDL_GL_GetProcAddress("glUseProgramObjectARB");
+        if (ctx->glGetError &&
+            ctx->glAttachObjectARB &&
+            ctx->glCompileShaderARB &&
+            ctx->glCreateProgramObjectARB &&
+            ctx->glCreateShaderObjectARB &&
+            ctx->glDeleteObjectARB &&
+            ctx->glGetInfoLogARB &&
+            ctx->glGetObjectParameterivARB &&
+            ctx->glGetUniformLocationARB &&
+            ctx->glLinkProgramARB &&
+            ctx->glShaderSourceARB &&
+            ctx->glUniform1iARB &&
+            ctx->glUniform1fARB &&
+            ctx->glUseProgramObjectARB) {
+            shaders_supported = SDL_TRUE;
+        }
+    }
+
+    if (!shaders_supported) {
+        SDL_free(ctx);
+        return NULL;
+    }
+
+    /* Compile all the shaders */
+    for (i = 0; i < NUM_SHADERS; ++i) {
+        if (!CompileShaderProgram(ctx, i, &ctx->shaders[i])) {
+            GL_DestroyShaderContext(ctx);
+            return NULL;
+        }
+    }
+
+    /* We're done! */
+    return ctx;
+}
+
+void
+GL_SelectShader(GL_ShaderContext *ctx, GL_Shader shader)
+{
+    ctx->glUseProgramObjectARB(ctx->shaders[shader].program);
+}
+
+void
+GL_DestroyShaderContext(GL_ShaderContext *ctx)
+{
+    int i;
+
+    for (i = 0; i < NUM_SHADERS; ++i) {
+        DestroyShaderProgram(ctx, &ctx->shaders[i]);
+    }
+    SDL_free(ctx);
+}
+
+#endif /* SDL_VIDEO_RENDER_OGL && !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/opengl/SDL_shaders_gl.h

@@ -0,0 +1,41 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+/* OpenGL shader implementation */
+
+typedef enum {
+    SHADER_NONE,
+    SHADER_SOLID,
+    SHADER_RGB,
+    SHADER_YUV,
+    SHADER_NV12,
+    SHADER_NV21,
+    NUM_SHADERS
+} GL_Shader;
+
+typedef struct GL_ShaderContext GL_ShaderContext;
+
+extern GL_ShaderContext * GL_CreateShaderContext();
+extern void GL_SelectShader(GL_ShaderContext *ctx, GL_Shader shader);
+extern void GL_DestroyShaderContext(GL_ShaderContext *ctx);
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/opengles/SDL_glesfuncs.h

@@ -0,0 +1,63 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+
+SDL_PROC(void, glBindTexture, (GLenum, GLuint))
+SDL_PROC(void, glBlendFunc, (GLenum, GLenum))
+SDL_PROC_OES(void, glBlendFuncSeparateOES, (GLenum, GLenum, GLenum, GLenum))
+SDL_PROC(void, glClear, (GLbitfield))
+SDL_PROC(void, glClearColor, (GLclampf, GLclampf, GLclampf, GLclampf))
+SDL_PROC(void, glColor4f, (GLfloat, GLfloat, GLfloat, GLfloat))
+SDL_PROC(void, glDeleteTextures, (GLsizei, const GLuint *))
+SDL_PROC(void, glDisable, (GLenum))
+SDL_PROC(void, glDisableClientState, (GLenum array))
+SDL_PROC(void, glDrawArrays, (GLenum, GLint, GLsizei))
+SDL_PROC_OES(void, glDrawTexfOES, (GLfloat, GLfloat, GLfloat, GLfloat, GLfloat))
+SDL_PROC(void, glEnable, (GLenum))
+SDL_PROC(void, glEnableClientState, (GLenum))
+SDL_PROC(void, glFinish, (void))
+SDL_PROC_OES(void, glGenFramebuffersOES, (GLsizei, GLuint *))
+SDL_PROC(void, glGenTextures, (GLsizei, GLuint *))
+SDL_PROC(GLenum, glGetError, (void))
+SDL_PROC(void, glGetIntegerv, (GLenum, GLint *))
+SDL_PROC(void, glLoadIdentity, (void))
+SDL_PROC(void, glMatrixMode, (GLenum))
+SDL_PROC(void, glOrthof, (GLfloat, GLfloat, GLfloat, GLfloat, GLfloat, GLfloat))
+SDL_PROC(void, glPixelStorei, (GLenum, GLint))
+SDL_PROC(void, glReadPixels, (GLint, GLint, GLsizei, GLsizei, GLenum, GLenum, GLvoid*))
+SDL_PROC(void, glScissor, (GLint, GLint, GLsizei, GLsizei))
+SDL_PROC(void, glTexCoordPointer, (GLint, GLenum, GLsizei, const GLvoid *))
+SDL_PROC(void, glTexEnvf, (GLenum, GLenum, GLfloat))
+SDL_PROC(void, glTexImage2D, (GLenum, GLint, GLint, GLsizei, GLsizei, GLint, GLenum, GLenum, const GLvoid *))
+SDL_PROC(void, glTexParameteri, (GLenum, GLenum, GLint))
+SDL_PROC(void, glTexParameteriv, (GLenum, GLenum, const GLint *))
+SDL_PROC(void, glTexSubImage2D, (GLenum, GLint, GLint, GLint, GLsizei, GLsizei, GLenum, GLenum, const GLvoid *))
+SDL_PROC(void, glVertexPointer, (GLint, GLenum, GLsizei, const GLvoid *))
+SDL_PROC(void, glViewport, (GLint, GLint, GLsizei, GLsizei))
+SDL_PROC_OES(void, glBindFramebufferOES, (GLenum, GLuint))
+SDL_PROC_OES(void, glFramebufferTexture2DOES, (GLenum, GLenum, GLenum, GLuint, GLint))
+SDL_PROC_OES(GLenum, glCheckFramebufferStatusOES, (GLenum))
+SDL_PROC(void, glPushMatrix, (void))
+SDL_PROC(void, glTranslatef, (GLfloat, GLfloat, GLfloat))
+SDL_PROC(void, glRotatef, (GLfloat, GLfloat, GLfloat, GLfloat))
+SDL_PROC(void, glPopMatrix, (void))
+SDL_PROC_OES(void, glDeleteFramebuffersOES, (GLsizei, const GLuint*))
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/opengles2/SDL_gles2funcs.h

@@ -0,0 +1,71 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+
+SDL_PROC(void, glActiveTexture, (GLenum))
+SDL_PROC(void, glAttachShader, (GLuint, GLuint))
+SDL_PROC(void, glBindAttribLocation, (GLuint, GLuint, const char *))
+SDL_PROC(void, glBindTexture, (GLenum, GLuint))
+SDL_PROC(void, glBlendFuncSeparate, (GLenum, GLenum, GLenum, GLenum))
+SDL_PROC(void, glClear, (GLbitfield))
+SDL_PROC(void, glClearColor, (GLclampf, GLclampf, GLclampf, GLclampf))
+SDL_PROC(void, glCompileShader, (GLuint))
+SDL_PROC(GLuint, glCreateProgram, (void))
+SDL_PROC(GLuint, glCreateShader, (GLenum))
+SDL_PROC(void, glDeleteProgram, (GLuint))
+SDL_PROC(void, glDeleteShader, (GLuint))
+SDL_PROC(void, glDeleteTextures, (GLsizei, const GLuint *))
+SDL_PROC(void, glDisable, (GLenum))
+SDL_PROC(void, glDisableVertexAttribArray, (GLuint))
+SDL_PROC(void, glDrawArrays, (GLenum, GLint, GLsizei))
+SDL_PROC(void, glEnable, (GLenum))
+SDL_PROC(void, glEnableVertexAttribArray, (GLuint))
+SDL_PROC(void, glFinish, (void))
+SDL_PROC(void, glGenFramebuffers, (GLsizei, GLuint *))
+SDL_PROC(void, glGenTextures, (GLsizei, GLuint *))
+SDL_PROC(void, glGetBooleanv, (GLenum, GLboolean *))
+SDL_PROC(const GLubyte *, glGetString, (GLenum))
+SDL_PROC(GLenum, glGetError, (void))
+SDL_PROC(void, glGetIntegerv, (GLenum, GLint *))
+SDL_PROC(void, glGetProgramiv, (GLuint, GLenum, GLint *))
+SDL_PROC(void, glGetShaderInfoLog, (GLuint, GLsizei, GLsizei *, char *))
+SDL_PROC(void, glGetShaderiv, (GLuint, GLenum, GLint *))
+SDL_PROC(GLint, glGetUniformLocation, (GLuint, const char *))
+SDL_PROC(void, glLinkProgram, (GLuint))
+SDL_PROC(void, glPixelStorei, (GLenum, GLint))
+SDL_PROC(void, glReadPixels, (GLint, GLint, GLsizei, GLsizei, GLenum, GLenum, GLvoid*))
+SDL_PROC(void, glScissor, (GLint, GLint, GLsizei, GLsizei))
+SDL_PROC(void, glShaderBinary, (GLsizei, const GLuint *, GLenum, const void *, GLsizei))
+SDL_PROC(void, glShaderSource, (GLuint, GLsizei, const GLchar* const*, const GLint *))
+SDL_PROC(void, glTexImage2D, (GLenum, GLint, GLint, GLsizei, GLsizei, GLint, GLenum, GLenum, const void *))
+SDL_PROC(void, glTexParameteri, (GLenum, GLenum, GLint))
+SDL_PROC(void, glTexSubImage2D, (GLenum, GLint, GLint, GLint, GLsizei, GLsizei, GLenum, GLenum, const GLvoid *))
+SDL_PROC(void, glUniform1i, (GLint, GLint))
+SDL_PROC(void, glUniform4f, (GLint, GLfloat, GLfloat, GLfloat, GLfloat))
+SDL_PROC(void, glUniformMatrix4fv, (GLint, GLsizei, GLboolean, const GLfloat *))
+SDL_PROC(void, glUseProgram, (GLuint))
+SDL_PROC(void, glVertexAttribPointer, (GLuint, GLint, GLenum, GLboolean, GLsizei, const void *))
+SDL_PROC(void, glViewport, (GLint, GLint, GLsizei, GLsizei))
+SDL_PROC(void, glBindFramebuffer, (GLenum, GLuint))
+SDL_PROC(void, glFramebufferTexture2D, (GLenum, GLenum, GLenum, GLuint, GLint))
+SDL_PROC(GLenum, glCheckFramebufferStatus, (GLenum))
+SDL_PROC(void, glDeleteFramebuffers, (GLsizei, const GLuint *))
+SDL_PROC(GLint, glGetAttribLocation, (GLuint, const GLchar *))
+SDL_PROC(void, glGetProgramInfoLog, (GLuint, GLsizei, GLsizei*, GLchar*))

src/render/opengles2/SDL_shaders_gles2.c

@@ -0,0 +1,912 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#if SDL_VIDEO_RENDER_OGL_ES2 && !SDL_RENDER_DISABLED
+
+#include "SDL_video.h"
+#include "SDL_opengles2.h"
+#include "SDL_shaders_gles2.h"
+#include "SDL_stdinc.h"
+
+/*************************************************************************************************
+ * Vertex/fragment shader source                                                                 *
+ *************************************************************************************************/
+
+static const Uint8 GLES2_VertexSrc_Default_[] = " \
+    uniform mat4 u_projection; \
+    attribute vec2 a_position; \
+    attribute vec2 a_texCoord; \
+    attribute float a_angle; \
+    attribute vec2 a_center; \
+    varying vec2 v_texCoord; \
+    \
+    void main() \
+    { \
+        float angle = radians(a_angle); \
+        float c = cos(angle); \
+        float s = sin(angle); \
+        mat2 rotationMatrix = mat2(c, -s, s, c); \
+        vec2 position = rotationMatrix * (a_position - a_center) + a_center; \
+        v_texCoord = a_texCoord; \
+        gl_Position = u_projection * vec4(position, 0.0, 1.0);\
+        gl_PointSize = 1.0; \
+    } \
+";
+
+static const Uint8 GLES2_FragmentSrc_SolidSrc_[] = " \
+    precision mediump float; \
+    uniform vec4 u_color; \
+    \
+    void main() \
+    { \
+        gl_FragColor = u_color; \
+    } \
+";
+
+static const Uint8 GLES2_FragmentSrc_TextureABGRSrc_[] = " \
+    precision mediump float; \
+    uniform sampler2D u_texture; \
+    uniform vec4 u_modulation; \
+    varying vec2 v_texCoord; \
+    \
+    void main() \
+    { \
+        gl_FragColor = texture2D(u_texture, v_texCoord); \
+        gl_FragColor *= u_modulation; \
+    } \
+";
+
+/* ARGB to ABGR conversion */
+static const Uint8 GLES2_FragmentSrc_TextureARGBSrc_[] = " \
+    precision mediump float; \
+    uniform sampler2D u_texture; \
+    uniform vec4 u_modulation; \
+    varying vec2 v_texCoord; \
+    \
+    void main() \
+    { \
+        vec4 abgr = texture2D(u_texture, v_texCoord); \
+        gl_FragColor = abgr; \
+        gl_FragColor.r = abgr.b; \
+        gl_FragColor.b = abgr.r; \
+        gl_FragColor *= u_modulation; \
+    } \
+";
+
+/* RGB to ABGR conversion */
+static const Uint8 GLES2_FragmentSrc_TextureRGBSrc_[] = " \
+    precision mediump float; \
+    uniform sampler2D u_texture; \
+    uniform vec4 u_modulation; \
+    varying vec2 v_texCoord; \
+    \
+    void main() \
+    { \
+        vec4 abgr = texture2D(u_texture, v_texCoord); \
+        gl_FragColor = abgr; \
+        gl_FragColor.r = abgr.b; \
+        gl_FragColor.b = abgr.r; \
+        gl_FragColor.a = 1.0; \
+        gl_FragColor *= u_modulation; \
+    } \
+";
+
+/* BGR to ABGR conversion */
+static const Uint8 GLES2_FragmentSrc_TextureBGRSrc_[] = " \
+    precision mediump float; \
+    uniform sampler2D u_texture; \
+    uniform vec4 u_modulation; \
+    varying vec2 v_texCoord; \
+    \
+    void main() \
+    { \
+        vec4 abgr = texture2D(u_texture, v_texCoord); \
+        gl_FragColor = abgr; \
+        gl_FragColor.a = 1.0; \
+        gl_FragColor *= u_modulation; \
+    } \
+";
+
+/* YUV to ABGR conversion */
+static const Uint8 GLES2_FragmentSrc_TextureYUVSrc_[] = " \
+    precision mediump float; \
+    uniform sampler2D u_texture; \
+    uniform sampler2D u_texture_u; \
+    uniform sampler2D u_texture_v; \
+    uniform vec4 u_modulation; \
+    varying vec2 v_texCoord; \
+    \
+    void main() \
+    { \
+        mediump vec3 yuv; \
+        lowp vec3 rgb; \
+        yuv.x = texture2D(u_texture,   v_texCoord).r; \
+        yuv.y = texture2D(u_texture_u, v_texCoord).r - 0.5; \
+        yuv.z = texture2D(u_texture_v, v_texCoord).r - 0.5; \
+        rgb = mat3( 1,        1,       1, \
+                    0,       -0.39465, 2.03211, \
+                    1.13983, -0.58060, 0) * yuv; \
+        gl_FragColor = vec4(rgb, 1); \
+        gl_FragColor *= u_modulation; \
+    } \
+";
+
+/* NV12 to ABGR conversion */
+static const Uint8 GLES2_FragmentSrc_TextureNV12Src_[] = " \
+    precision mediump float; \
+    uniform sampler2D u_texture; \
+    uniform sampler2D u_texture_u; \
+    uniform vec4 u_modulation; \
+    varying vec2 v_texCoord; \
+    \
+    void main() \
+    { \
+        mediump vec3 yuv; \
+        lowp vec3 rgb; \
+        yuv.x = texture2D(u_texture,   v_texCoord).r; \
+        yuv.yz = texture2D(u_texture_u, v_texCoord).ra - 0.5; \
+        rgb = mat3( 1,        1,       1, \
+                    0,       -0.39465, 2.03211, \
+                    1.13983, -0.58060, 0) * yuv; \
+        gl_FragColor = vec4(rgb, 1); \
+        gl_FragColor *= u_modulation; \
+    } \
+";
+
+/* NV21 to ABGR conversion */
+static const Uint8 GLES2_FragmentSrc_TextureNV21Src_[] = " \
+    precision mediump float; \
+    uniform sampler2D u_texture; \
+    uniform sampler2D u_texture_u; \
+    uniform vec4 u_modulation; \
+    varying vec2 v_texCoord; \
+    \
+    void main() \
+    { \
+        mediump vec3 yuv; \
+        lowp vec3 rgb; \
+        yuv.x = texture2D(u_texture,   v_texCoord).r; \
+        yuv.yz = texture2D(u_texture_u, v_texCoord).ar - 0.5; \
+        rgb = mat3( 1,        1,       1, \
+                    0,       -0.39465, 2.03211, \
+                    1.13983, -0.58060, 0) * yuv; \
+        gl_FragColor = vec4(rgb, 1); \
+        gl_FragColor *= u_modulation; \
+    } \
+";
+
+static const GLES2_ShaderInstance GLES2_VertexSrc_Default = {
+    GL_VERTEX_SHADER,
+    GLES2_SOURCE_SHADER,
+    sizeof(GLES2_VertexSrc_Default_),
+    GLES2_VertexSrc_Default_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentSrc_SolidSrc = {
+    GL_FRAGMENT_SHADER,
+    GLES2_SOURCE_SHADER,
+    sizeof(GLES2_FragmentSrc_SolidSrc_),
+    GLES2_FragmentSrc_SolidSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentSrc_TextureABGRSrc = {
+    GL_FRAGMENT_SHADER,
+    GLES2_SOURCE_SHADER,
+    sizeof(GLES2_FragmentSrc_TextureABGRSrc_),
+    GLES2_FragmentSrc_TextureABGRSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentSrc_TextureARGBSrc = {
+    GL_FRAGMENT_SHADER,
+    GLES2_SOURCE_SHADER,
+    sizeof(GLES2_FragmentSrc_TextureARGBSrc_),
+    GLES2_FragmentSrc_TextureARGBSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentSrc_TextureRGBSrc = {
+    GL_FRAGMENT_SHADER,
+    GLES2_SOURCE_SHADER,
+    sizeof(GLES2_FragmentSrc_TextureRGBSrc_),
+    GLES2_FragmentSrc_TextureRGBSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentSrc_TextureBGRSrc = {
+    GL_FRAGMENT_SHADER,
+    GLES2_SOURCE_SHADER,
+    sizeof(GLES2_FragmentSrc_TextureBGRSrc_),
+    GLES2_FragmentSrc_TextureBGRSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentSrc_TextureYUVSrc = {
+    GL_FRAGMENT_SHADER,
+    GLES2_SOURCE_SHADER,
+    sizeof(GLES2_FragmentSrc_TextureYUVSrc_),
+    GLES2_FragmentSrc_TextureYUVSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentSrc_TextureNV12Src = {
+    GL_FRAGMENT_SHADER,
+    GLES2_SOURCE_SHADER,
+    sizeof(GLES2_FragmentSrc_TextureNV12Src_),
+    GLES2_FragmentSrc_TextureNV12Src_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentSrc_TextureNV21Src = {
+    GL_FRAGMENT_SHADER,
+    GLES2_SOURCE_SHADER,
+    sizeof(GLES2_FragmentSrc_TextureNV21Src_),
+    GLES2_FragmentSrc_TextureNV21Src_
+};
+
+
+/*************************************************************************************************
+ * Vertex/fragment shader binaries (NVIDIA Tegra 1/2)                                            *
+ *************************************************************************************************/
+
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+
+#define GL_NVIDIA_PLATFORM_BINARY_NV 0x890B
+
+static const Uint8 GLES2_VertexTegra_Default_[] = {
+    243, 193, 1, 142, 31, 109, 131, 38, 6, 0, 1, 0, 5, 0, 0, 0, 17, 0, 0, 0, 1, 0, 0, 0, 73, 0,
+    0, 0, 46, 0, 0, 0, 48, 0, 0, 0, 2, 0, 0, 0, 85, 0, 0, 0, 2, 0, 0, 0, 24, 0, 0, 0, 3, 0, 0, 0,
+    91, 0, 0, 0, 1, 0, 0, 0, 16, 0, 0, 0, 5, 0, 0, 0, 95, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 95, 0, 0, 0, 1, 0, 0, 0, 28, 0, 0, 0,
+    13, 0, 0, 0, 102, 0, 0, 0, 2, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 16, 0, 0, 0, 104, 0, 0, 0, 1, 0, 0, 0, 32, 0, 0, 0, 17, 0, 0, 0, 112, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 18, 0, 0, 0, 112, 0, 0, 0, 80, 0, 0, 0, 80, 0, 0, 0, 19, 0, 0, 0, 132, 0,
+    0, 0, 104, 0, 0, 0, 104, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 109, 97, 110, 70, 73, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 97,
+    95, 112, 111, 115, 105, 116, 105, 111, 110, 0, 97, 95, 116, 101, 120, 67, 111, 111, 114, 100,
+    0, 118, 95, 116, 101, 120, 67, 111, 111, 114, 100, 0, 117, 95, 112, 114, 111, 106, 101, 99,
+    116, 105, 111, 110, 0, 0, 0, 0, 0, 0, 0, 82, 139, 0, 0, 0, 0, 0, 0, 11, 0, 0, 0, 80, 139, 0,
+    0, 1, 0, 0, 0, 22, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 33, 0, 0, 0, 92, 139, 0, 0,
+    1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 240, 0, 0, 0, 0, 0, 0, 1, 0,
+    0, 0, 64, 0, 0, 0, 80, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 193, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 128, 63, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 66, 24, 0, 6, 34, 108, 28,
+    0, 0, 42, 16, 128, 0, 195, 192, 6, 129, 252, 255, 65, 96, 108, 28, 0, 0, 0, 0, 0, 1, 195, 192,
+    6, 1, 252, 255, 33, 96, 108, 156, 31, 64, 8, 1, 64, 0, 131, 192, 6, 1, 156, 159, 65, 96, 108,
+    28, 0, 0, 85, 32, 0, 1, 195, 192, 6, 1, 252, 255, 33, 96, 108, 156, 31, 64, 0, 64, 64, 0, 131,
+    192, 134, 1, 152, 31, 65, 96, 108, 156, 31, 64, 127, 48, 0, 1, 195, 192, 6, 129, 129, 255, 33,
+    96
+};
+
+static const Uint8 GLES2_FragmentTegra_None_SolidSrc_[] = {
+    155, 191, 159, 1, 47, 109, 131, 38, 6, 0, 1, 0, 5, 0, 0, 0, 17, 0, 0, 0, 1, 0, 0, 0, 73, 0,
+    0, 0, 8, 0, 0, 0, 8, 0, 0, 0, 2, 0, 0, 0, 75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 0, 0, 0, 75,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 6, 0, 0, 0, 75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0,
+    75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 75, 0, 0, 0, 1, 0, 0, 0, 28, 0, 0, 0, 13, 0,
+    0, 0, 82, 0, 0, 0, 2, 0, 0, 0, 8, 0, 0, 0, 14, 0, 0, 0, 84, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    22, 0, 0, 0, 84, 0, 0, 0, 8, 0, 0, 0, 32, 0, 0, 0, 23, 0, 0, 0, 92, 0, 0, 0, 1, 0, 0, 0, 4,
+    0, 0, 0, 15, 0, 0, 0, 93, 0, 0, 0, 1, 0, 0, 0, 80, 0, 0, 0, 17, 0, 0, 0, 113, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 18, 0, 0, 0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 19, 0, 0, 0, 113, 0, 0,
+    0, 108, 0, 0, 0, 108, 0, 0, 0, 20, 0, 0, 0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21, 0, 0,
+    0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 109, 97, 110, 70, 73, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 117, 95, 99, 111, 108, 111, 114, 0, 0, 0, 0, 0, 82, 139, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 48, 0, 0, 0, 0, 0, 0, 0, 0, 0, 241, 0, 0, 0, 240, 0, 0,
+    0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 0, 0,
+    0, 0, 0, 1, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 21, 32, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 20, 0, 0, 0, 16, 0, 0, 0, 16, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 65, 82, 50, 48, 45, 66, 73, 78, 1,
+    0, 0, 0, 1, 0, 0, 0, 1, 0, 65, 37, 0, 0, 0, 0, 1, 0, 0, 21, 0, 0, 0, 0, 1, 0, 1, 38, 0, 0, 0,
+    0, 1, 0, 1, 39, 0, 0, 0, 0, 1, 0, 1, 40, 1, 0, 0, 0, 8, 0, 4, 40, 0, 40, 0, 0, 0, 242, 65, 63,
+    192, 200, 0, 0, 0, 242, 65, 63, 128, 168, 0, 0, 0, 242, 65, 63, 64, 72, 0, 0, 0, 242, 65, 63,
+    1, 0, 6, 40, 0, 0, 0, 0, 1, 0, 1, 41, 5, 0, 2, 0
+};
+
+static const Uint8 GLES2_FragmentTegra_Alpha_SolidSrc_[] = {
+    169, 153, 195, 28, 47, 109, 131, 38, 6, 0, 1, 0, 5, 0, 0, 0, 17, 0, 0, 0, 1, 0, 0, 0, 73, 0,
+    0, 0, 8, 0, 0, 0, 8, 0, 0, 0, 2, 0, 0, 0, 75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 0, 0, 0, 75,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 6, 0, 0, 0, 75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0,
+    75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 75, 0, 0, 0, 1, 0, 0, 0, 28, 0, 0, 0, 13, 0,
+    0, 0, 82, 0, 0, 0, 2, 0, 0, 0, 8, 0, 0, 0, 14, 0, 0, 0, 84, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    22, 0, 0, 0, 84, 0, 0, 0, 8, 0, 0, 0, 32, 0, 0, 0, 23, 0, 0, 0, 92, 0, 0, 0, 1, 0, 0, 0, 4,
+    0, 0, 0, 15, 0, 0, 0, 93, 0, 0, 0, 1, 0, 0, 0, 80, 0, 0, 0, 17, 0, 0, 0, 113, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 18, 0, 0, 0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 19, 0, 0, 0, 113, 0, 0,
+    0, 220, 0, 0, 0, 220, 0, 0, 0, 20, 0, 0, 0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21, 0, 0,
+    0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 109, 97, 110, 70, 73, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 117, 95, 99, 111, 108, 111, 114, 0, 0, 0, 0, 0, 82, 139, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 48, 0, 0, 0, 0, 0, 0, 118, 118, 17, 241, 0, 0, 0, 240, 0,
+    0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 0,
+    0, 0, 0, 0, 1, 0, 0, 0, 7, 0, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 3, 0, 0, 0, 21, 32, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 20, 0, 0, 0, 16, 0, 0, 0, 16, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 65, 82, 50, 48, 45, 66, 73, 78,
+    1, 0, 0, 0, 3, 0, 0, 0, 3, 0, 65, 37, 8, 0, 129, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 21, 0,
+    0, 0, 0, 3, 0, 1, 38, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 1, 39, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 3, 0, 1, 40, 1, 0, 0, 0, 5, 0, 0, 0, 9, 0, 0, 0, 24, 0, 4, 40, 232, 231, 15,
+    0, 0, 242, 65, 62, 194, 72, 1, 0, 0, 250, 65, 63, 194, 40, 1, 0, 0, 250, 65, 63, 192, 168, 1,
+    0, 0, 242, 1, 64, 192, 168, 1, 0, 0, 242, 1, 68, 168, 32, 0, 0, 0, 50, 64, 0, 192, 168, 15,
+    0, 0, 242, 1, 66, 168, 64, 0, 16, 0, 242, 65, 1, 232, 231, 15, 0, 0, 242, 65, 62, 168, 160,
+    0, 0, 0, 50, 64, 2, 104, 192, 0, 0, 36, 48, 66, 4, 232, 231, 15, 0, 0, 242, 65, 62, 3, 0, 6,
+    40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 1, 41, 0, 0, 0, 0, 0, 0, 0, 0, 5, 0, 2, 0
+};
+
+static const Uint8 GLES2_FragmentTegra_Additive_SolidSrc_[] = {
+    59, 71, 42, 17, 47, 109, 131, 38, 6, 0, 1, 0, 5, 0, 0, 0, 17, 0, 0, 0, 1, 0, 0, 0, 73, 0, 0,
+    0, 8, 0, 0, 0, 8, 0, 0, 0, 2, 0, 0, 0, 75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 0, 0, 0, 75,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 6, 0, 0, 0, 75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0,
+    75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 75, 0, 0, 0, 1, 0, 0, 0, 28, 0, 0, 0, 13, 0,
+    0, 0, 82, 0, 0, 0, 2, 0, 0, 0, 8, 0, 0, 0, 14, 0, 0, 0, 84, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    22, 0, 0, 0, 84, 0, 0, 0, 8, 0, 0, 0, 32, 0, 0, 0, 23, 0, 0, 0, 92, 0, 0, 0, 1, 0, 0, 0, 4,
+    0, 0, 0, 15, 0, 0, 0, 93, 0, 0, 0, 1, 0, 0, 0, 80, 0, 0, 0, 17, 0, 0, 0, 113, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 18, 0, 0, 0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 19, 0, 0, 0, 113, 0, 0,
+    0, 108, 0, 0, 0, 108, 0, 0, 0, 20, 0, 0, 0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21, 0, 0,
+    0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 109, 97, 110, 70, 73, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 117, 95, 99, 111, 108, 111, 114, 0, 0, 0, 0, 0, 82, 139, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 48, 0, 0, 0, 0, 0, 0, 22, 22, 17, 241, 0, 0, 0, 240, 0,
+    0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 0,
+    0, 0, 0, 0, 1, 0, 0, 0, 7, 0, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 21, 32, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 20, 0, 0, 0, 16, 0, 0, 0, 16, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 65, 82, 50, 48, 45, 66, 73, 78,
+    1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 65, 37, 8, 0, 129, 0, 1, 0, 0, 21, 0, 0, 0, 0, 1, 0, 1, 38, 0,
+    0, 0, 0, 1, 0, 1, 39, 0, 0, 0, 0, 1, 0, 1, 40, 1, 0, 0, 0, 8, 0, 4, 40, 192, 200, 0, 0, 0, 26,
+    0, 70, 192, 40, 0, 0, 0, 2, 0, 64, 192, 72, 0, 0, 0, 10, 0, 66, 192, 168, 0, 0, 0, 18, 0, 68,
+    1, 0, 6, 40, 0, 0, 0, 0, 1, 0, 1, 41, 5, 0, 2, 0
+};
+
+static const Uint8 GLES2_FragmentTegra_Modulated_SolidSrc_[] = {
+    37, 191, 49, 17, 47, 109, 131, 38, 6, 0, 1, 0, 5, 0, 0, 0, 17, 0, 0, 0, 1, 0, 0, 0, 73, 0, 0,
+    0, 8, 0, 0, 0, 8, 0, 0, 0, 2, 0, 0, 0, 75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 0, 0, 0, 75,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 6, 0, 0, 0, 75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0,
+    75, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 75, 0, 0, 0, 1, 0, 0, 0, 28, 0, 0, 0, 13, 0,
+    0, 0, 82, 0, 0, 0, 2, 0, 0, 0, 8, 0, 0, 0, 14, 0, 0, 0, 84, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    22, 0, 0, 0, 84, 0, 0, 0, 8, 0, 0, 0, 32, 0, 0, 0, 23, 0, 0, 0, 92, 0, 0, 0, 1, 0, 0, 0, 4,
+    0, 0, 0, 15, 0, 0, 0, 93, 0, 0, 0, 1, 0, 0, 0, 80, 0, 0, 0, 17, 0, 0, 0, 113, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 18, 0, 0, 0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 19, 0, 0, 0, 113, 0, 0,
+    0, 108, 0, 0, 0, 108, 0, 0, 0, 20, 0, 0, 0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21, 0, 0,
+    0, 113, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 109, 97, 110, 70, 73, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 117, 95, 99, 111, 108, 111, 114, 0, 0, 0, 0, 0, 82, 139, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 48, 0, 0, 0, 0, 0, 0, 32, 32, 17, 241, 0, 0, 0, 240, 0,
+    0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 0,
+    0, 0, 0, 0, 1, 0, 0, 0, 7, 0, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 21, 32, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 20, 0, 0, 0, 16, 0, 0, 0, 16, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 65, 82, 50, 48, 45, 66, 73, 78,
+    1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 65, 37, 8, 0, 129, 0, 1, 0, 0, 21, 0, 0, 0, 0, 1, 0, 1, 38, 0,
+    0, 0, 0, 1, 0, 1, 39, 0, 0, 0, 0, 1, 0, 1, 40, 1, 0, 0, 0, 8, 0, 4, 40, 104, 192, 0, 0, 0, 242,
+    1, 70, 8, 32, 0, 0, 0, 242, 1, 64, 40, 64, 0, 0, 0, 242, 1, 66, 72, 160, 0, 0, 0, 242, 1, 68,
+    1, 0, 6, 40, 0, 0, 0, 0, 1, 0, 1, 41, 5, 0, 2, 0
+};
+
+static const Uint8 GLES2_FragmentTegra_None_TextureSrc_[] = {
+    220, 217, 41, 211, 47, 109, 131, 38, 6, 0, 1, 0, 5, 0, 0, 0, 17, 0, 0, 0, 1, 0, 0, 0, 73, 0,
+    0, 0, 34, 0, 0, 0, 36, 0, 0, 0, 2, 0, 0, 0, 82, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 0, 0, 0,
+    82, 0, 0, 0, 1, 0, 0, 0, 20, 0, 0, 0, 6, 0, 0, 0, 87, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0,
+    0, 0, 87, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 87, 0, 0, 0, 2, 0, 0, 0, 56, 0, 0, 0,
+    13, 0, 0, 0, 101, 0, 0, 0, 4, 0, 0, 0, 16, 0, 0, 0, 14, 0, 0, 0, 105, 0, 0, 0, 1, 0, 0, 0, 4,
+    0, 0, 0, 22, 0, 0, 0, 106, 0, 0, 0, 8, 0, 0, 0, 32, 0, 0, 0, 23, 0, 0, 0, 114, 0, 0, 0, 1, 0,
+    0, 0, 4, 0, 0, 0, 15, 0, 0, 0, 115, 0, 0, 0, 1, 0, 0, 0, 80, 0, 0, 0, 17, 0, 0, 0, 135, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 18, 0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 19, 0, 0, 0, 135,
+    0, 0, 0, 120, 0, 0, 0, 120, 0, 0, 0, 20, 0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21,
+    0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 109, 97, 110, 70, 73, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 118, 95, 116, 101, 120, 67, 111, 111, 114, 100, 0, 117, 95, 109, 111, 100, 117, 108,
+    97, 116, 105, 111, 110, 0, 117, 95, 116, 101, 120, 116, 117, 114, 101, 0, 0, 0, 0, 0, 0, 0,
+    2, 0, 0, 0, 0, 0, 0, 0, 220, 0, 0, 0, 0, 0, 0, 0, 11, 0, 0, 0, 82, 139, 0, 0, 1, 0, 0, 0, 1,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 0, 0, 94, 139, 0, 0, 1, 0, 0, 0, 1, 0, 0,
+    0, 2, 0, 0, 0, 16, 0, 0, 0, 0, 0, 0, 0, 5, 48, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 1, 0, 0, 0, 241, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240,
+    0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 1, 0,
+    0, 0, 1, 0, 0, 0, 21, 32, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 0, 0, 16, 0, 0, 0, 16, 0, 0,
+    0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 65, 82, 50, 48, 45, 66, 73, 78, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 65, 37, 0, 0, 0, 0, 1, 0,
+    0, 21, 0, 0, 0, 0, 1, 0, 1, 38, 1, 0, 0, 0, 2, 0, 4, 38, 186, 81, 78, 16, 2, 1, 0, 0, 1, 0,
+    1, 39, 0, 4, 0, 0, 1, 0, 1, 40, 1, 0, 0, 0, 8, 0, 4, 40, 104, 192, 0, 0, 0, 242, 1, 70, 8, 32,
+    0, 0, 0, 242, 1, 64, 40, 64, 0, 0, 0, 242, 1, 66, 72, 160, 0, 0, 0, 242, 1, 68, 1, 0, 6, 40,
+    0, 0, 0, 0, 1, 0, 1, 41, 5, 0, 2, 0
+};
+
+static const Uint8 GLES2_FragmentTegra_Alpha_TextureSrc_[] = {
+    71, 202, 114, 229, 47, 109, 131, 38, 6, 0, 1, 0, 5, 0, 0, 0, 17, 0, 0, 0, 1, 0, 0, 0, 73, 0,
+    0, 0, 34, 0, 0, 0, 36, 0, 0, 0, 2, 0, 0, 0, 82, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 0, 0, 0,
+    82, 0, 0, 0, 1, 0, 0, 0, 20, 0, 0, 0, 6, 0, 0, 0, 87, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0,
+    0, 0, 87, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 87, 0, 0, 0, 2, 0, 0, 0, 56, 0, 0, 0,
+    13, 0, 0, 0, 101, 0, 0, 0, 4, 0, 0, 0, 16, 0, 0, 0, 14, 0, 0, 0, 105, 0, 0, 0, 1, 0, 0, 0, 4,
+    0, 0, 0, 22, 0, 0, 0, 106, 0, 0, 0, 8, 0, 0, 0, 32, 0, 0, 0, 23, 0, 0, 0, 114, 0, 0, 0, 1, 0,
+    0, 0, 4, 0, 0, 0, 15, 0, 0, 0, 115, 0, 0, 0, 1, 0, 0, 0, 80, 0, 0, 0, 17, 0, 0, 0, 135, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 18, 0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 19, 0, 0, 0, 135,
+    0, 0, 0, 176, 0, 0, 0, 176, 0, 0, 0, 20, 0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21,
+    0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 109, 97, 110, 70, 73, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 118, 95, 116, 101, 120, 67, 111, 111, 114, 100, 0, 117, 95, 109, 111, 100, 117, 108,
+    97, 116, 105, 111, 110, 0, 117, 95, 116, 101, 120, 116, 117, 114, 101, 0, 0, 0, 0, 0, 0, 0,
+    2, 0, 0, 0, 0, 0, 0, 0, 220, 0, 0, 0, 0, 0, 0, 0, 11, 0, 0, 0, 82, 139, 0, 0, 1, 0, 0, 0, 1,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 0, 0, 94, 139, 0, 0, 1, 0, 0, 0, 1, 0, 0,
+    0, 2, 0, 0, 0, 16, 0, 0, 0, 0, 0, 0, 0, 5, 48, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 1, 118, 118, 17, 241, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0,
+    240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 7, 0, 0, 0, 2, 0, 0, 0,
+    1, 0, 0, 0, 2, 0, 0, 0, 21, 32, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 0, 0, 16, 0, 0, 0, 16,
+    0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 65, 82, 50, 48, 45, 66, 73, 78, 1, 0, 0, 0, 2, 0, 0, 0, 2, 0, 65, 37, 0, 0, 0, 0,
+    8, 0, 129, 0, 1, 0, 0, 21, 0, 0, 0, 0, 2, 0, 1, 38, 1, 0, 0, 0, 0, 0, 0, 0, 2, 0, 4, 38, 186,
+    81, 78, 16, 2, 1, 0, 0, 2, 0, 1, 39, 0, 4, 0, 0, 0, 0, 0, 0, 2, 0, 1, 40, 1, 0, 0, 0, 5, 0,
+    0, 0, 16, 0, 4, 40, 40, 160, 1, 0, 0, 242, 1, 66, 8, 192, 1, 0, 0, 242, 1, 64, 104, 32, 1, 0,
+    0, 242, 1, 70, 72, 64, 1, 0, 0, 242, 1, 68, 154, 192, 0, 0, 37, 34, 64, 3, 8, 32, 0, 0, 5, 58,
+    208, 4, 40, 64, 0, 0, 5, 50, 208, 4, 72, 160, 0, 0, 37, 42, 208, 4, 2, 0, 6, 40, 0, 0, 0, 0,
+    0, 0, 0, 0, 2, 0, 1, 41, 0, 0, 0, 0, 5, 0, 2, 0
+};
+
+static const Uint8 GLES2_FragmentTegra_Additive_TextureSrc_[] = {
+    161, 234, 193, 234, 47, 109, 131, 38, 6, 0, 1, 0, 5, 0, 0, 0, 17, 0, 0, 0, 1, 0, 0, 0, 73, 0,
+    0, 0, 34, 0, 0, 0, 36, 0, 0, 0, 2, 0, 0, 0, 82, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 0, 0, 0,
+    82, 0, 0, 0, 1, 0, 0, 0, 20, 0, 0, 0, 6, 0, 0, 0, 87, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0,
+    0, 0, 87, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 87, 0, 0, 0, 2, 0, 0, 0, 56, 0, 0, 0,
+    13, 0, 0, 0, 101, 0, 0, 0, 4, 0, 0, 0, 16, 0, 0, 0, 14, 0, 0, 0, 105, 0, 0, 0, 1, 0, 0, 0, 4,
+    0, 0, 0, 22, 0, 0, 0, 106, 0, 0, 0, 8, 0, 0, 0, 32, 0, 0, 0, 23, 0, 0, 0, 114, 0, 0, 0, 1, 0,
+    0, 0, 4, 0, 0, 0, 15, 0, 0, 0, 115, 0, 0, 0, 1, 0, 0, 0, 80, 0, 0, 0, 17, 0, 0, 0, 135, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 18, 0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 19, 0, 0, 0, 135,
+    0, 0, 0, 176, 0, 0, 0, 176, 0, 0, 0, 20, 0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21,
+    0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 109, 97, 110, 70, 73, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 118, 95, 116, 101, 120, 67, 111, 111, 114, 100, 0, 117, 95, 109, 111, 100, 117, 108,
+    97, 116, 105, 111, 110, 0, 117, 95, 116, 101, 120, 116, 117, 114, 101, 0, 0, 0, 0, 0, 0, 0,
+    2, 0, 0, 0, 0, 0, 0, 0, 220, 0, 0, 0, 0, 0, 0, 0, 11, 0, 0, 0, 82, 139, 0, 0, 1, 0, 0, 0, 1,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 0, 0, 94, 139, 0, 0, 1, 0, 0, 0, 1, 0, 0,
+    0, 2, 0, 0, 0, 16, 0, 0, 0, 0, 0, 0, 0, 5, 48, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 1, 22, 22, 17, 241, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240,
+    0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 7, 0, 0, 0, 2, 0, 0, 0, 1, 0,
+    0, 0, 2, 0, 0, 0, 21, 32, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 0, 0, 16, 0, 0, 0, 16, 0, 0,
+    0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 65, 82, 50, 48, 45, 66, 73, 78, 1, 0, 0, 0, 2, 0, 0, 0, 2, 0, 65, 37, 0, 0, 0, 0, 8, 0,
+    129, 0, 1, 0, 0, 21, 0, 0, 0, 0, 2, 0, 1, 38, 1, 0, 0, 0, 0, 0, 0, 0, 2, 0, 4, 38, 186, 81,
+    78, 16, 2, 1, 0, 0, 2, 0, 1, 39, 0, 4, 0, 0, 0, 0, 0, 0, 2, 0, 1, 40, 1, 0, 0, 0, 5, 0, 0, 0,
+    16, 0, 4, 40, 40, 160, 1, 0, 0, 242, 1, 66, 104, 32, 1, 0, 0, 242, 1, 70, 8, 192, 1, 0, 0, 242,
+    1, 64, 72, 64, 1, 0, 0, 242, 1, 68, 136, 192, 0, 0, 0, 26, 64, 4, 136, 32, 0, 0, 0, 2, 64, 7,
+    136, 64, 0, 0, 0, 10, 64, 6, 136, 160, 0, 0, 0, 18, 64, 5, 2, 0, 6, 40, 0, 0, 0, 0, 0, 0, 0,
+    0, 2, 0, 1, 41, 0, 0, 0, 0, 5, 0, 2, 0
+};
+
+static const Uint8 GLES2_FragmentTegra_Modulated_TextureSrc_[] = {
+    75, 132, 201, 227, 47, 109, 131, 38, 6, 0, 1, 0, 5, 0, 0, 0, 17, 0, 0, 0, 1, 0, 0, 0, 73, 0,
+    0, 0, 34, 0, 0, 0, 36, 0, 0, 0, 2, 0, 0, 0, 82, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 0, 0, 0,
+    82, 0, 0, 0, 1, 0, 0, 0, 20, 0, 0, 0, 6, 0, 0, 0, 87, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0,
+    0, 0, 87, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 87, 0, 0, 0, 2, 0, 0, 0, 56, 0, 0, 0,
+    13, 0, 0, 0, 101, 0, 0, 0, 4, 0, 0, 0, 16, 0, 0, 0, 14, 0, 0, 0, 105, 0, 0, 0, 1, 0, 0, 0, 4,
+    0, 0, 0, 22, 0, 0, 0, 106, 0, 0, 0, 8, 0, 0, 0, 32, 0, 0, 0, 23, 0, 0, 0, 114, 0, 0, 0, 1, 0,
+    0, 0, 4, 0, 0, 0, 15, 0, 0, 0, 115, 0, 0, 0, 1, 0, 0, 0, 80, 0, 0, 0, 17, 0, 0, 0, 135, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 18, 0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 19, 0, 0, 0, 135,
+    0, 0, 0, 176, 0, 0, 0, 176, 0, 0, 0, 20, 0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21,
+    0, 0, 0, 135, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 109, 97, 110, 70, 73, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 118, 95, 116, 101, 120, 67, 111, 111, 114, 100, 0, 117, 95, 109, 111, 100, 117, 108,
+    97, 116, 105, 111, 110, 0, 117, 95, 116, 101, 120, 116, 117, 114, 101, 0, 0, 0, 0, 0, 0, 0,
+    2, 0, 0, 0, 0, 0, 0, 0, 220, 0, 0, 0, 0, 0, 0, 0, 11, 0, 0, 0, 82, 139, 0, 0, 1, 0, 0, 0, 1,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 0, 0, 94, 139, 0, 0, 1, 0, 0, 0, 1, 0, 0,
+    0, 2, 0, 0, 0, 16, 0, 0, 0, 0, 0, 0, 0, 5, 48, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 1, 32, 32, 17, 241, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 240,
+    0, 0, 0, 240, 0, 0, 0, 240, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 7, 0, 0, 0, 2, 0, 0, 0, 1, 0,
+    0, 0, 2, 0, 0, 0, 21, 32, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 0, 0, 16, 0, 0, 0, 16, 0, 0,
+    0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 65, 82, 50, 48, 45, 66, 73, 78, 1, 0, 0, 0, 2, 0, 0, 0, 2, 0, 65, 37, 0, 0, 0, 0, 8, 0,
+    129, 0, 1, 0, 0, 21, 0, 0, 0, 0, 2, 0, 1, 38, 1, 0, 0, 0, 0, 0, 0, 0, 2, 0, 4, 38, 186, 81,
+    78, 16, 2, 1, 0, 0, 2, 0, 1, 39, 0, 4, 0, 0, 0, 0, 0, 0, 2, 0, 1, 40, 1, 0, 0, 0, 5, 0, 0, 0,
+    16, 0, 4, 40, 40, 160, 1, 0, 0, 242, 1, 66, 8, 192, 1, 0, 0, 242, 1, 64, 104, 32, 1, 0, 0, 242,
+    1, 70, 72, 64, 1, 0, 0, 242, 1, 68, 104, 192, 0, 0, 0, 242, 65, 4, 232, 32, 0, 0, 0, 242, 65,
+    0, 40, 64, 0, 0, 0, 242, 65, 6, 72, 160, 0, 0, 0, 242, 65, 5, 2, 0, 6, 40, 0, 0, 0, 0, 0, 0,
+    0, 0, 2, 0, 1, 41, 0, 0, 0, 0, 5, 0, 2, 0
+};
+
+static const GLES2_ShaderInstance GLES2_VertexTegra_Default = {
+    GL_VERTEX_SHADER,
+    GL_NVIDIA_PLATFORM_BINARY_NV,
+    sizeof(GLES2_VertexTegra_Default_),
+    GLES2_VertexTegra_Default_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentTegra_None_SolidSrc = {
+    GL_FRAGMENT_SHADER,
+    GL_NVIDIA_PLATFORM_BINARY_NV,
+    sizeof(GLES2_FragmentTegra_None_SolidSrc_),
+    GLES2_FragmentTegra_None_SolidSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentTegra_Alpha_SolidSrc = {
+    GL_FRAGMENT_SHADER,
+    GL_NVIDIA_PLATFORM_BINARY_NV,
+    sizeof(GLES2_FragmentTegra_Alpha_SolidSrc_),
+    GLES2_FragmentTegra_Alpha_SolidSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentTegra_Additive_SolidSrc = {
+    GL_FRAGMENT_SHADER,
+    GL_NVIDIA_PLATFORM_BINARY_NV,
+    sizeof(GLES2_FragmentTegra_Additive_SolidSrc_),
+    GLES2_FragmentTegra_Additive_SolidSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentTegra_Modulated_SolidSrc = {
+    GL_FRAGMENT_SHADER,
+    GL_NVIDIA_PLATFORM_BINARY_NV,
+    sizeof(GLES2_FragmentTegra_Modulated_SolidSrc_),
+    GLES2_FragmentTegra_Modulated_SolidSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentTegra_None_TextureSrc = {
+    GL_FRAGMENT_SHADER,
+    GL_NVIDIA_PLATFORM_BINARY_NV,
+    sizeof(GLES2_FragmentTegra_None_TextureSrc_),
+    GLES2_FragmentTegra_None_TextureSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentTegra_Alpha_TextureSrc = {
+    GL_FRAGMENT_SHADER,
+    GL_NVIDIA_PLATFORM_BINARY_NV,
+    sizeof(GLES2_FragmentTegra_Alpha_TextureSrc_),
+    GLES2_FragmentTegra_Alpha_TextureSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentTegra_Additive_TextureSrc = {
+    GL_FRAGMENT_SHADER,
+    GL_NVIDIA_PLATFORM_BINARY_NV,
+    sizeof(GLES2_FragmentTegra_Additive_TextureSrc_),
+    GLES2_FragmentTegra_Additive_TextureSrc_
+};
+
+static const GLES2_ShaderInstance GLES2_FragmentTegra_Modulated_TextureSrc = {
+    GL_FRAGMENT_SHADER,
+    GL_NVIDIA_PLATFORM_BINARY_NV,
+    sizeof(GLES2_FragmentTegra_Modulated_TextureSrc_),
+    GLES2_FragmentTegra_Modulated_TextureSrc_
+};
+
+#endif /* GLES2_INCLUDE_NVIDIA_SHADERS */
+
+/*************************************************************************************************
+ * Vertex/fragment shader definitions                                                            *
+ *************************************************************************************************/
+
+static GLES2_Shader GLES2_VertexShader_Default = {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+    2,
+#else
+    1,
+#endif
+    {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+        &GLES2_VertexTegra_Default,
+#endif
+        &GLES2_VertexSrc_Default
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_None_SolidSrc = {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+    2,
+#else
+    1,
+#endif
+    {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+        &GLES2_FragmentTegra_None_SolidSrc,
+#endif
+        &GLES2_FragmentSrc_SolidSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Alpha_SolidSrc = {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+    2,
+#else
+    1,
+#endif
+    {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+        &GLES2_FragmentTegra_Alpha_SolidSrc,
+#endif
+        &GLES2_FragmentSrc_SolidSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Additive_SolidSrc = {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+    2,
+#else
+    1,
+#endif
+    {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+        &GLES2_FragmentTegra_Additive_SolidSrc,
+#endif
+        &GLES2_FragmentSrc_SolidSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Modulated_SolidSrc = {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+    2,
+#else
+    1,
+#endif
+    {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+        &GLES2_FragmentTegra_Modulated_SolidSrc,
+#endif
+        &GLES2_FragmentSrc_SolidSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_None_TextureABGRSrc = {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+    2,
+#else
+    1,
+#endif
+    {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+        &GLES2_FragmentTegra_None_TextureSrc,
+#endif
+        &GLES2_FragmentSrc_TextureABGRSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Alpha_TextureABGRSrc = {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+    2,
+#else
+    1,
+#endif
+    {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+        &GLES2_FragmentTegra_Alpha_TextureSrc,
+#endif
+        &GLES2_FragmentSrc_TextureABGRSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Additive_TextureABGRSrc = {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+    2,
+#else
+    1,
+#endif
+    {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+        &GLES2_FragmentTegra_Additive_TextureSrc,
+#endif
+        &GLES2_FragmentSrc_TextureABGRSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Modulated_TextureABGRSrc = {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+    2,
+#else
+    1,
+#endif
+    {
+#if GLES2_INCLUDE_NVIDIA_SHADERS
+        &GLES2_FragmentTegra_Modulated_TextureSrc,
+#endif
+        &GLES2_FragmentSrc_TextureABGRSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_None_TextureARGBSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureARGBSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Alpha_TextureARGBSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureARGBSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Additive_TextureARGBSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureARGBSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Modulated_TextureARGBSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureARGBSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_None_TextureRGBSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureRGBSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Alpha_TextureRGBSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureRGBSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Additive_TextureRGBSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureRGBSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Modulated_TextureRGBSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureRGBSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_None_TextureBGRSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureBGRSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Alpha_TextureBGRSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureBGRSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Additive_TextureBGRSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureBGRSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_Modulated_TextureBGRSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureBGRSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_TextureYUVSrc = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureYUVSrc
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_TextureNV12Src = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureNV12Src
+    }
+};
+
+static GLES2_Shader GLES2_FragmentShader_TextureNV21Src = {
+    1,
+    {
+        &GLES2_FragmentSrc_TextureNV21Src
+    }
+};
+
+
+/*************************************************************************************************
+ * Shader selector                                                                               *
+ *************************************************************************************************/
+
+const GLES2_Shader *GLES2_GetShader(GLES2_ShaderType type, SDL_BlendMode blendMode)
+{
+    switch (type)
+    {
+    case GLES2_SHADER_VERTEX_DEFAULT:
+        return &GLES2_VertexShader_Default;
+    case GLES2_SHADER_FRAGMENT_SOLID_SRC:
+    switch (blendMode)
+    {
+    case SDL_BLENDMODE_NONE:
+        return &GLES2_FragmentShader_None_SolidSrc;
+    case SDL_BLENDMODE_BLEND:
+        return &GLES2_FragmentShader_Alpha_SolidSrc;
+    case SDL_BLENDMODE_ADD:
+        return &GLES2_FragmentShader_Additive_SolidSrc;
+    case SDL_BLENDMODE_MOD:
+        return &GLES2_FragmentShader_Modulated_SolidSrc;
+    default:
+        return NULL;
+    }
+    case GLES2_SHADER_FRAGMENT_TEXTURE_ABGR_SRC:
+        switch (blendMode)
+    {
+        case SDL_BLENDMODE_NONE:
+            return &GLES2_FragmentShader_None_TextureABGRSrc;
+        case SDL_BLENDMODE_BLEND:
+            return &GLES2_FragmentShader_Alpha_TextureABGRSrc;
+        case SDL_BLENDMODE_ADD:
+            return &GLES2_FragmentShader_Additive_TextureABGRSrc;
+        case SDL_BLENDMODE_MOD:
+            return &GLES2_FragmentShader_Modulated_TextureABGRSrc;
+        default:
+            return NULL;
+    }
+    case GLES2_SHADER_FRAGMENT_TEXTURE_ARGB_SRC:
+        switch (blendMode)
+    {
+        case SDL_BLENDMODE_NONE:
+            return &GLES2_FragmentShader_None_TextureARGBSrc;
+        case SDL_BLENDMODE_BLEND:
+            return &GLES2_FragmentShader_Alpha_TextureARGBSrc;
+        case SDL_BLENDMODE_ADD:
+            return &GLES2_FragmentShader_Additive_TextureARGBSrc;
+        case SDL_BLENDMODE_MOD:
+            return &GLES2_FragmentShader_Modulated_TextureARGBSrc;
+        default:
+            return NULL;
+    }
+
+    case GLES2_SHADER_FRAGMENT_TEXTURE_RGB_SRC:
+        switch (blendMode)
+    {
+        case SDL_BLENDMODE_NONE:
+            return &GLES2_FragmentShader_None_TextureRGBSrc;
+        case SDL_BLENDMODE_BLEND:
+            return &GLES2_FragmentShader_Alpha_TextureRGBSrc;
+        case SDL_BLENDMODE_ADD:
+            return &GLES2_FragmentShader_Additive_TextureRGBSrc;
+        case SDL_BLENDMODE_MOD:
+            return &GLES2_FragmentShader_Modulated_TextureRGBSrc;
+        default:
+            return NULL;
+    }
+
+    case GLES2_SHADER_FRAGMENT_TEXTURE_BGR_SRC:
+        switch (blendMode)
+    {
+        case SDL_BLENDMODE_NONE:
+            return &GLES2_FragmentShader_None_TextureBGRSrc;
+        case SDL_BLENDMODE_BLEND:
+            return &GLES2_FragmentShader_Alpha_TextureBGRSrc;
+        case SDL_BLENDMODE_ADD:
+            return &GLES2_FragmentShader_Additive_TextureBGRSrc;
+        case SDL_BLENDMODE_MOD:
+            return &GLES2_FragmentShader_Modulated_TextureBGRSrc;
+        default:
+            return NULL;
+    }
+    
+    case GLES2_SHADER_FRAGMENT_TEXTURE_YUV_SRC:
+    {
+        return &GLES2_FragmentShader_TextureYUVSrc;
+    }
+
+    case GLES2_SHADER_FRAGMENT_TEXTURE_NV12_SRC:
+    {
+        return &GLES2_FragmentShader_TextureNV12Src;
+    }
+
+    case GLES2_SHADER_FRAGMENT_TEXTURE_NV21_SRC:
+    {
+        return &GLES2_FragmentShader_TextureNV21Src;
+    }
+
+    default:
+        return NULL;
+    }
+}
+
+#endif /* SDL_VIDEO_RENDER_OGL_ES2 && !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/opengles2/SDL_shaders_gles2.h

@@ -0,0 +1,63 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#if SDL_VIDEO_RENDER_OGL_ES2
+
+#ifndef SDL_shaderdata_h_
+#define SDL_shaderdata_h_
+
+typedef struct GLES2_ShaderInstance
+{
+    GLenum type;
+    GLenum format;
+    int length;
+    const void *data;
+} GLES2_ShaderInstance;
+
+typedef struct GLES2_Shader
+{
+    int instance_count;
+    const GLES2_ShaderInstance *instances[4];
+} GLES2_Shader;
+
+typedef enum
+{
+    GLES2_SHADER_VERTEX_DEFAULT,
+    GLES2_SHADER_FRAGMENT_SOLID_SRC,
+    GLES2_SHADER_FRAGMENT_TEXTURE_ABGR_SRC,
+    GLES2_SHADER_FRAGMENT_TEXTURE_ARGB_SRC,
+    GLES2_SHADER_FRAGMENT_TEXTURE_BGR_SRC,
+    GLES2_SHADER_FRAGMENT_TEXTURE_RGB_SRC,
+    GLES2_SHADER_FRAGMENT_TEXTURE_YUV_SRC,
+    GLES2_SHADER_FRAGMENT_TEXTURE_NV12_SRC,
+    GLES2_SHADER_FRAGMENT_TEXTURE_NV21_SRC
+} GLES2_ShaderType;
+
+#define GLES2_SOURCE_SHADER (GLenum)-1
+
+const GLES2_Shader *GLES2_GetShader(GLES2_ShaderType type, SDL_BlendMode blendMode);
+
+#endif /* SDL_shaderdata_h_ */
+
+#endif /* SDL_VIDEO_RENDER_OGL_ES2 */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_blendfillrect.c

@@ -0,0 +1,336 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#if !SDL_RENDER_DISABLED
+
+#include "SDL_draw.h"
+#include "SDL_blendfillrect.h"
+
+
+static int
+SDL_BlendFillRect_RGB555(SDL_Surface * dst, const SDL_Rect * rect,
+                         SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    unsigned inva = 0xff - a;
+
+    switch (blendMode) {
+    case SDL_BLENDMODE_BLEND:
+        FILLRECT(Uint16, DRAW_SETPIXEL_BLEND_RGB555);
+        break;
+    case SDL_BLENDMODE_ADD:
+        FILLRECT(Uint16, DRAW_SETPIXEL_ADD_RGB555);
+        break;
+    case SDL_BLENDMODE_MOD:
+        FILLRECT(Uint16, DRAW_SETPIXEL_MOD_RGB555);
+        break;
+    default:
+        FILLRECT(Uint16, DRAW_SETPIXEL_RGB555);
+        break;
+    }
+    return 0;
+}
+
+static int
+SDL_BlendFillRect_RGB565(SDL_Surface * dst, const SDL_Rect * rect,
+                         SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    unsigned inva = 0xff - a;
+
+    switch (blendMode) {
+    case SDL_BLENDMODE_BLEND:
+        FILLRECT(Uint16, DRAW_SETPIXEL_BLEND_RGB565);
+        break;
+    case SDL_BLENDMODE_ADD:
+        FILLRECT(Uint16, DRAW_SETPIXEL_ADD_RGB565);
+        break;
+    case SDL_BLENDMODE_MOD:
+        FILLRECT(Uint16, DRAW_SETPIXEL_MOD_RGB565);
+        break;
+    default:
+        FILLRECT(Uint16, DRAW_SETPIXEL_RGB565);
+        break;
+    }
+    return 0;
+}
+
+static int
+SDL_BlendFillRect_RGB888(SDL_Surface * dst, const SDL_Rect * rect,
+                         SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    unsigned inva = 0xff - a;
+
+    switch (blendMode) {
+    case SDL_BLENDMODE_BLEND:
+        FILLRECT(Uint32, DRAW_SETPIXEL_BLEND_RGB888);
+        break;
+    case SDL_BLENDMODE_ADD:
+        FILLRECT(Uint32, DRAW_SETPIXEL_ADD_RGB888);
+        break;
+    case SDL_BLENDMODE_MOD:
+        FILLRECT(Uint32, DRAW_SETPIXEL_MOD_RGB888);
+        break;
+    default:
+        FILLRECT(Uint32, DRAW_SETPIXEL_RGB888);
+        break;
+    }
+    return 0;
+}
+
+static int
+SDL_BlendFillRect_ARGB8888(SDL_Surface * dst, const SDL_Rect * rect,
+                           SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    unsigned inva = 0xff - a;
+
+    switch (blendMode) {
+    case SDL_BLENDMODE_BLEND:
+        FILLRECT(Uint32, DRAW_SETPIXEL_BLEND_ARGB8888);
+        break;
+    case SDL_BLENDMODE_ADD:
+        FILLRECT(Uint32, DRAW_SETPIXEL_ADD_ARGB8888);
+        break;
+    case SDL_BLENDMODE_MOD:
+        FILLRECT(Uint32, DRAW_SETPIXEL_MOD_ARGB8888);
+        break;
+    default:
+        FILLRECT(Uint32, DRAW_SETPIXEL_ARGB8888);
+        break;
+    }
+    return 0;
+}
+
+static int
+SDL_BlendFillRect_RGB(SDL_Surface * dst, const SDL_Rect * rect,
+                      SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    SDL_PixelFormat *fmt = dst->format;
+    unsigned inva = 0xff - a;
+
+    switch (fmt->BytesPerPixel) {
+    case 2:
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            FILLRECT(Uint16, DRAW_SETPIXEL_BLEND_RGB);
+            break;
+        case SDL_BLENDMODE_ADD:
+            FILLRECT(Uint16, DRAW_SETPIXEL_ADD_RGB);
+            break;
+        case SDL_BLENDMODE_MOD:
+            FILLRECT(Uint16, DRAW_SETPIXEL_MOD_RGB);
+            break;
+        default:
+            FILLRECT(Uint16, DRAW_SETPIXEL_RGB);
+            break;
+        }
+        return 0;
+    case 4:
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            FILLRECT(Uint32, DRAW_SETPIXEL_BLEND_RGB);
+            break;
+        case SDL_BLENDMODE_ADD:
+            FILLRECT(Uint32, DRAW_SETPIXEL_ADD_RGB);
+            break;
+        case SDL_BLENDMODE_MOD:
+            FILLRECT(Uint32, DRAW_SETPIXEL_MOD_RGB);
+            break;
+        default:
+            FILLRECT(Uint32, DRAW_SETPIXEL_RGB);
+            break;
+        }
+        return 0;
+    default:
+        return SDL_Unsupported();
+    }
+}
+
+static int
+SDL_BlendFillRect_RGBA(SDL_Surface * dst, const SDL_Rect * rect,
+                       SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    SDL_PixelFormat *fmt = dst->format;
+    unsigned inva = 0xff - a;
+
+    switch (fmt->BytesPerPixel) {
+    case 4:
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            FILLRECT(Uint32, DRAW_SETPIXEL_BLEND_RGBA);
+            break;
+        case SDL_BLENDMODE_ADD:
+            FILLRECT(Uint32, DRAW_SETPIXEL_ADD_RGBA);
+            break;
+        case SDL_BLENDMODE_MOD:
+            FILLRECT(Uint32, DRAW_SETPIXEL_MOD_RGBA);
+            break;
+        default:
+            FILLRECT(Uint32, DRAW_SETPIXEL_RGBA);
+            break;
+        }
+        return 0;
+    default:
+        return SDL_Unsupported();
+    }
+}
+
+int
+SDL_BlendFillRect(SDL_Surface * dst, const SDL_Rect * rect,
+                  SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    SDL_Rect clipped;
+
+    if (!dst) {
+        return SDL_SetError("Passed NULL destination surface");
+    }
+
+    /* This function doesn't work on surfaces < 8 bpp */
+    if (dst->format->BitsPerPixel < 8) {
+        return SDL_SetError("SDL_BlendFillRect(): Unsupported surface format");
+    }
+
+    /* If 'rect' == NULL, then fill the whole surface */
+    if (rect) {
+        /* Perform clipping */
+        if (!SDL_IntersectRect(rect, &dst->clip_rect, &clipped)) {
+            return 0;
+        }
+        rect = &clipped;
+    } else {
+        rect = &dst->clip_rect;
+    }
+
+    if (blendMode == SDL_BLENDMODE_BLEND || blendMode == SDL_BLENDMODE_ADD) {
+        r = DRAW_MUL(r, a);
+        g = DRAW_MUL(g, a);
+        b = DRAW_MUL(b, a);
+    }
+
+    switch (dst->format->BitsPerPixel) {
+    case 15:
+        switch (dst->format->Rmask) {
+        case 0x7C00:
+            return SDL_BlendFillRect_RGB555(dst, rect, blendMode, r, g, b, a);
+        }
+        break;
+    case 16:
+        switch (dst->format->Rmask) {
+        case 0xF800:
+            return SDL_BlendFillRect_RGB565(dst, rect, blendMode, r, g, b, a);
+        }
+        break;
+    case 32:
+        switch (dst->format->Rmask) {
+        case 0x00FF0000:
+            if (!dst->format->Amask) {
+                return SDL_BlendFillRect_RGB888(dst, rect, blendMode, r, g, b, a);
+            } else {
+                return SDL_BlendFillRect_ARGB8888(dst, rect, blendMode, r, g, b, a);
+            }
+            break;
+        }
+        break;
+    default:
+        break;
+    }
+
+    if (!dst->format->Amask) {
+        return SDL_BlendFillRect_RGB(dst, rect, blendMode, r, g, b, a);
+    } else {
+        return SDL_BlendFillRect_RGBA(dst, rect, blendMode, r, g, b, a);
+    }
+}
+
+int
+SDL_BlendFillRects(SDL_Surface * dst, const SDL_Rect * rects, int count,
+                   SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    SDL_Rect rect;
+    int i;
+    int (*func)(SDL_Surface * dst, const SDL_Rect * rect,
+                SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a) = NULL;
+    int status = 0;
+
+    if (!dst) {
+        return SDL_SetError("Passed NULL destination surface");
+    }
+
+    /* This function doesn't work on surfaces < 8 bpp */
+    if (dst->format->BitsPerPixel < 8) {
+        return SDL_SetError("SDL_BlendFillRects(): Unsupported surface format");
+    }
+
+    if (blendMode == SDL_BLENDMODE_BLEND || blendMode == SDL_BLENDMODE_ADD) {
+        r = DRAW_MUL(r, a);
+        g = DRAW_MUL(g, a);
+        b = DRAW_MUL(b, a);
+    }
+
+    /* FIXME: Does this function pointer slow things down significantly? */
+    switch (dst->format->BitsPerPixel) {
+    case 15:
+        switch (dst->format->Rmask) {
+        case 0x7C00:
+            func = SDL_BlendFillRect_RGB555;
+        }
+        break;
+    case 16:
+        switch (dst->format->Rmask) {
+        case 0xF800:
+            func = SDL_BlendFillRect_RGB565;
+        }
+        break;
+    case 32:
+        switch (dst->format->Rmask) {
+        case 0x00FF0000:
+            if (!dst->format->Amask) {
+                func = SDL_BlendFillRect_RGB888;
+            } else {
+                func = SDL_BlendFillRect_ARGB8888;
+            }
+            break;
+        }
+        break;
+    default:
+        break;
+    }
+
+    if (!func) {
+        if (!dst->format->Amask) {
+            func = SDL_BlendFillRect_RGB;
+        } else {
+            func = SDL_BlendFillRect_RGBA;
+        }
+    }
+
+    for (i = 0; i < count; ++i) {
+        /* Perform clipping */
+        if (!SDL_IntersectRect(&rects[i], &dst->clip_rect, &rect)) {
+            continue;
+        }
+        status = func(dst, &rect, blendMode, r, g, b, a);
+    }
+    return status;
+}
+
+#endif /* !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_blendfillrect.h

@@ -0,0 +1,27 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+
+extern int SDL_BlendFillRect(SDL_Surface * dst, const SDL_Rect * rect, SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a);
+extern int SDL_BlendFillRects(SDL_Surface * dst, const SDL_Rect * rects, int count, SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a);
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_blendline.c

@@ -0,0 +1,777 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#if !SDL_RENDER_DISABLED
+
+#include "SDL_draw.h"
+#include "SDL_blendline.h"
+#include "SDL_blendpoint.h"
+
+
+static void
+SDL_BlendLine_RGB2(SDL_Surface * dst, int x1, int y1, int x2, int y2,
+                   SDL_BlendMode blendMode, Uint8 _r, Uint8 _g, Uint8 _b, Uint8 _a,
+                   SDL_bool draw_end)
+{
+    const SDL_PixelFormat *fmt = dst->format;
+    unsigned r, g, b, a, inva;
+
+    if (blendMode == SDL_BLENDMODE_BLEND || blendMode == SDL_BLENDMODE_ADD) {
+        r = DRAW_MUL(_r, _a);
+        g = DRAW_MUL(_g, _a);
+        b = DRAW_MUL(_b, _a);
+        a = _a;
+    } else {
+        r = _r;
+        g = _g;
+        b = _b;
+        a = _a;
+    }
+    inva = (a ^ 0xff);
+
+    if (y1 == y2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            HLINE(Uint16, DRAW_SETPIXEL_BLEND_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            HLINE(Uint16, DRAW_SETPIXEL_ADD_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            HLINE(Uint16, DRAW_SETPIXEL_MOD_RGB, draw_end);
+            break;
+        default:
+            HLINE(Uint16, DRAW_SETPIXEL_RGB, draw_end);
+            break;
+        }
+    } else if (x1 == x2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            VLINE(Uint16, DRAW_SETPIXEL_BLEND_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            VLINE(Uint16, DRAW_SETPIXEL_ADD_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            VLINE(Uint16, DRAW_SETPIXEL_MOD_RGB, draw_end);
+            break;
+        default:
+            VLINE(Uint16, DRAW_SETPIXEL_RGB, draw_end);
+            break;
+        }
+    } else if (ABS(x1 - x2) == ABS(y1 - y2)) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            DLINE(Uint16, DRAW_SETPIXEL_BLEND_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            DLINE(Uint16, DRAW_SETPIXEL_ADD_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            DLINE(Uint16, DRAW_SETPIXEL_MOD_RGB, draw_end);
+            break;
+        default:
+            DLINE(Uint16, DRAW_SETPIXEL_RGB, draw_end);
+            break;
+        }
+    } else {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY2_BLEND_RGB, DRAW_SETPIXELXY2_BLEND_RGB,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY2_ADD_RGB, DRAW_SETPIXELXY2_ADD_RGB,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY2_MOD_RGB, DRAW_SETPIXELXY2_MOD_RGB,
+                   draw_end);
+            break;
+        default:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY2_RGB, DRAW_SETPIXELXY2_BLEND_RGB,
+                   draw_end);
+            break;
+        }
+    }
+}
+
+static void
+SDL_BlendLine_RGB555(SDL_Surface * dst, int x1, int y1, int x2, int y2,
+                     SDL_BlendMode blendMode, Uint8 _r, Uint8 _g, Uint8 _b, Uint8 _a,
+                     SDL_bool draw_end)
+{
+    unsigned r, g, b, a, inva;
+
+    if (blendMode == SDL_BLENDMODE_BLEND || blendMode == SDL_BLENDMODE_ADD) {
+        r = DRAW_MUL(_r, _a);
+        g = DRAW_MUL(_g, _a);
+        b = DRAW_MUL(_b, _a);
+        a = _a;
+    } else {
+        r = _r;
+        g = _g;
+        b = _b;
+        a = _a;
+    }
+    inva = (a ^ 0xff);
+
+    if (y1 == y2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            HLINE(Uint16, DRAW_SETPIXEL_BLEND_RGB555, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            HLINE(Uint16, DRAW_SETPIXEL_ADD_RGB555, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            HLINE(Uint16, DRAW_SETPIXEL_MOD_RGB555, draw_end);
+            break;
+        default:
+            HLINE(Uint16, DRAW_SETPIXEL_RGB555, draw_end);
+            break;
+        }
+    } else if (x1 == x2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            VLINE(Uint16, DRAW_SETPIXEL_BLEND_RGB555, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            VLINE(Uint16, DRAW_SETPIXEL_ADD_RGB555, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            VLINE(Uint16, DRAW_SETPIXEL_MOD_RGB555, draw_end);
+            break;
+        default:
+            VLINE(Uint16, DRAW_SETPIXEL_RGB555, draw_end);
+            break;
+        }
+    } else if (ABS(x1 - x2) == ABS(y1 - y2)) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            DLINE(Uint16, DRAW_SETPIXEL_BLEND_RGB555, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            DLINE(Uint16, DRAW_SETPIXEL_ADD_RGB555, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            DLINE(Uint16, DRAW_SETPIXEL_MOD_RGB555, draw_end);
+            break;
+        default:
+            DLINE(Uint16, DRAW_SETPIXEL_RGB555, draw_end);
+            break;
+        }
+    } else {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_BLEND_RGB555, DRAW_SETPIXELXY_BLEND_RGB555,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_ADD_RGB555, DRAW_SETPIXELXY_ADD_RGB555,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_MOD_RGB555, DRAW_SETPIXELXY_MOD_RGB555,
+                   draw_end);
+            break;
+        default:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_RGB555, DRAW_SETPIXELXY_BLEND_RGB555,
+                   draw_end);
+            break;
+        }
+    }
+}
+
+static void
+SDL_BlendLine_RGB565(SDL_Surface * dst, int x1, int y1, int x2, int y2,
+                     SDL_BlendMode blendMode, Uint8 _r, Uint8 _g, Uint8 _b, Uint8 _a,
+                     SDL_bool draw_end)
+{
+    unsigned r, g, b, a, inva;
+
+    if (blendMode == SDL_BLENDMODE_BLEND || blendMode == SDL_BLENDMODE_ADD) {
+        r = DRAW_MUL(_r, _a);
+        g = DRAW_MUL(_g, _a);
+        b = DRAW_MUL(_b, _a);
+        a = _a;
+    } else {
+        r = _r;
+        g = _g;
+        b = _b;
+        a = _a;
+    }
+    inva = (a ^ 0xff);
+
+    if (y1 == y2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            HLINE(Uint16, DRAW_SETPIXEL_BLEND_RGB565, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            HLINE(Uint16, DRAW_SETPIXEL_ADD_RGB565, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            HLINE(Uint16, DRAW_SETPIXEL_MOD_RGB565, draw_end);
+            break;
+        default:
+            HLINE(Uint16, DRAW_SETPIXEL_RGB565, draw_end);
+            break;
+        }
+    } else if (x1 == x2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            VLINE(Uint16, DRAW_SETPIXEL_BLEND_RGB565, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            VLINE(Uint16, DRAW_SETPIXEL_ADD_RGB565, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            VLINE(Uint16, DRAW_SETPIXEL_MOD_RGB565, draw_end);
+            break;
+        default:
+            VLINE(Uint16, DRAW_SETPIXEL_RGB565, draw_end);
+            break;
+        }
+    } else if (ABS(x1 - x2) == ABS(y1 - y2)) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            DLINE(Uint16, DRAW_SETPIXEL_BLEND_RGB565, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            DLINE(Uint16, DRAW_SETPIXEL_ADD_RGB565, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            DLINE(Uint16, DRAW_SETPIXEL_MOD_RGB565, draw_end);
+            break;
+        default:
+            DLINE(Uint16, DRAW_SETPIXEL_RGB565, draw_end);
+            break;
+        }
+    } else {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_BLEND_RGB565, DRAW_SETPIXELXY_BLEND_RGB565,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_ADD_RGB565, DRAW_SETPIXELXY_ADD_RGB565,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_MOD_RGB565, DRAW_SETPIXELXY_MOD_RGB565,
+                   draw_end);
+            break;
+        default:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_RGB565, DRAW_SETPIXELXY_BLEND_RGB565,
+                   draw_end);
+            break;
+        }
+    }
+}
+
+static void
+SDL_BlendLine_RGB4(SDL_Surface * dst, int x1, int y1, int x2, int y2,
+                   SDL_BlendMode blendMode, Uint8 _r, Uint8 _g, Uint8 _b, Uint8 _a,
+                   SDL_bool draw_end)
+{
+    const SDL_PixelFormat *fmt = dst->format;
+    unsigned r, g, b, a, inva;
+
+    if (blendMode == SDL_BLENDMODE_BLEND || blendMode == SDL_BLENDMODE_ADD) {
+        r = DRAW_MUL(_r, _a);
+        g = DRAW_MUL(_g, _a);
+        b = DRAW_MUL(_b, _a);
+        a = _a;
+    } else {
+        r = _r;
+        g = _g;
+        b = _b;
+        a = _a;
+    }
+    inva = (a ^ 0xff);
+
+    if (y1 == y2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            HLINE(Uint32, DRAW_SETPIXEL_BLEND_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            HLINE(Uint32, DRAW_SETPIXEL_ADD_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            HLINE(Uint32, DRAW_SETPIXEL_MOD_RGB, draw_end);
+            break;
+        default:
+            HLINE(Uint32, DRAW_SETPIXEL_RGB, draw_end);
+            break;
+        }
+    } else if (x1 == x2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            VLINE(Uint32, DRAW_SETPIXEL_BLEND_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            VLINE(Uint32, DRAW_SETPIXEL_ADD_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            VLINE(Uint32, DRAW_SETPIXEL_MOD_RGB, draw_end);
+            break;
+        default:
+            VLINE(Uint32, DRAW_SETPIXEL_RGB, draw_end);
+            break;
+        }
+    } else if (ABS(x1 - x2) == ABS(y1 - y2)) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            DLINE(Uint32, DRAW_SETPIXEL_BLEND_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            DLINE(Uint32, DRAW_SETPIXEL_ADD_RGB, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            DLINE(Uint32, DRAW_SETPIXEL_MOD_RGB, draw_end);
+            break;
+        default:
+            DLINE(Uint32, DRAW_SETPIXEL_RGB, draw_end);
+            break;
+        }
+    } else {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY4_BLEND_RGB, DRAW_SETPIXELXY4_BLEND_RGB,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY4_ADD_RGB, DRAW_SETPIXELXY4_ADD_RGB,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY4_MOD_RGB, DRAW_SETPIXELXY4_MOD_RGB,
+                   draw_end);
+            break;
+        default:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY4_RGB, DRAW_SETPIXELXY4_BLEND_RGB,
+                   draw_end);
+            break;
+        }
+    }
+}
+
+static void
+SDL_BlendLine_RGBA4(SDL_Surface * dst, int x1, int y1, int x2, int y2,
+                    SDL_BlendMode blendMode, Uint8 _r, Uint8 _g, Uint8 _b, Uint8 _a,
+                    SDL_bool draw_end)
+{
+    const SDL_PixelFormat *fmt = dst->format;
+    unsigned r, g, b, a, inva;
+
+    if (blendMode == SDL_BLENDMODE_BLEND || blendMode == SDL_BLENDMODE_ADD) {
+        r = DRAW_MUL(_r, _a);
+        g = DRAW_MUL(_g, _a);
+        b = DRAW_MUL(_b, _a);
+        a = _a;
+    } else {
+        r = _r;
+        g = _g;
+        b = _b;
+        a = _a;
+    }
+    inva = (a ^ 0xff);
+
+    if (y1 == y2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            HLINE(Uint32, DRAW_SETPIXEL_BLEND_RGBA, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            HLINE(Uint32, DRAW_SETPIXEL_ADD_RGBA, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            HLINE(Uint32, DRAW_SETPIXEL_MOD_RGBA, draw_end);
+            break;
+        default:
+            HLINE(Uint32, DRAW_SETPIXEL_RGBA, draw_end);
+            break;
+        }
+    } else if (x1 == x2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            VLINE(Uint32, DRAW_SETPIXEL_BLEND_RGBA, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            VLINE(Uint32, DRAW_SETPIXEL_ADD_RGBA, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            VLINE(Uint32, DRAW_SETPIXEL_MOD_RGBA, draw_end);
+            break;
+        default:
+            VLINE(Uint32, DRAW_SETPIXEL_RGBA, draw_end);
+            break;
+        }
+    } else if (ABS(x1 - x2) == ABS(y1 - y2)) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            DLINE(Uint32, DRAW_SETPIXEL_BLEND_RGBA, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            DLINE(Uint32, DRAW_SETPIXEL_ADD_RGBA, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            DLINE(Uint32, DRAW_SETPIXEL_MOD_RGBA, draw_end);
+            break;
+        default:
+            DLINE(Uint32, DRAW_SETPIXEL_RGBA, draw_end);
+            break;
+        }
+    } else {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY4_BLEND_RGBA, DRAW_SETPIXELXY4_BLEND_RGBA,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY4_ADD_RGBA, DRAW_SETPIXELXY4_ADD_RGBA,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY4_MOD_RGBA, DRAW_SETPIXELXY4_MOD_RGBA,
+                   draw_end);
+            break;
+        default:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY4_RGBA, DRAW_SETPIXELXY4_BLEND_RGBA,
+                   draw_end);
+            break;
+        }
+    }
+}
+
+static void
+SDL_BlendLine_RGB888(SDL_Surface * dst, int x1, int y1, int x2, int y2,
+                     SDL_BlendMode blendMode, Uint8 _r, Uint8 _g, Uint8 _b, Uint8 _a,
+                     SDL_bool draw_end)
+{
+    unsigned r, g, b, a, inva;
+
+    if (blendMode == SDL_BLENDMODE_BLEND || blendMode == SDL_BLENDMODE_ADD) {
+        r = DRAW_MUL(_r, _a);
+        g = DRAW_MUL(_g, _a);
+        b = DRAW_MUL(_b, _a);
+        a = _a;
+    } else {
+        r = _r;
+        g = _g;
+        b = _b;
+        a = _a;
+    }
+    inva = (a ^ 0xff);
+
+    if (y1 == y2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            HLINE(Uint32, DRAW_SETPIXEL_BLEND_RGB888, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            HLINE(Uint32, DRAW_SETPIXEL_ADD_RGB888, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            HLINE(Uint32, DRAW_SETPIXEL_MOD_RGB888, draw_end);
+            break;
+        default:
+            HLINE(Uint32, DRAW_SETPIXEL_RGB888, draw_end);
+            break;
+        }
+    } else if (x1 == x2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            VLINE(Uint32, DRAW_SETPIXEL_BLEND_RGB888, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            VLINE(Uint32, DRAW_SETPIXEL_ADD_RGB888, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            VLINE(Uint32, DRAW_SETPIXEL_MOD_RGB888, draw_end);
+            break;
+        default:
+            VLINE(Uint32, DRAW_SETPIXEL_RGB888, draw_end);
+            break;
+        }
+    } else if (ABS(x1 - x2) == ABS(y1 - y2)) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            DLINE(Uint32, DRAW_SETPIXEL_BLEND_RGB888, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            DLINE(Uint32, DRAW_SETPIXEL_ADD_RGB888, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            DLINE(Uint32, DRAW_SETPIXEL_MOD_RGB888, draw_end);
+            break;
+        default:
+            DLINE(Uint32, DRAW_SETPIXEL_RGB888, draw_end);
+            break;
+        }
+    } else {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_BLEND_RGB888, DRAW_SETPIXELXY_BLEND_RGB888,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_ADD_RGB888, DRAW_SETPIXELXY_ADD_RGB888,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_MOD_RGB888, DRAW_SETPIXELXY_MOD_RGB888,
+                   draw_end);
+            break;
+        default:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_RGB888, DRAW_SETPIXELXY_BLEND_RGB888,
+                   draw_end);
+            break;
+        }
+    }
+}
+
+static void
+SDL_BlendLine_ARGB8888(SDL_Surface * dst, int x1, int y1, int x2, int y2,
+                       SDL_BlendMode blendMode, Uint8 _r, Uint8 _g, Uint8 _b, Uint8 _a,
+                       SDL_bool draw_end)
+{
+    unsigned r, g, b, a, inva;
+
+    if (blendMode == SDL_BLENDMODE_BLEND || blendMode == SDL_BLENDMODE_ADD) {
+        r = DRAW_MUL(_r, _a);
+        g = DRAW_MUL(_g, _a);
+        b = DRAW_MUL(_b, _a);
+        a = _a;
+    } else {
+        r = _r;
+        g = _g;
+        b = _b;
+        a = _a;
+    }
+    inva = (a ^ 0xff);
+
+    if (y1 == y2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            HLINE(Uint32, DRAW_SETPIXEL_BLEND_ARGB8888, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            HLINE(Uint32, DRAW_SETPIXEL_ADD_ARGB8888, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            HLINE(Uint32, DRAW_SETPIXEL_MOD_ARGB8888, draw_end);
+            break;
+        default:
+            HLINE(Uint32, DRAW_SETPIXEL_ARGB8888, draw_end);
+            break;
+        }
+    } else if (x1 == x2) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            VLINE(Uint32, DRAW_SETPIXEL_BLEND_ARGB8888, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            VLINE(Uint32, DRAW_SETPIXEL_ADD_ARGB8888, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            VLINE(Uint32, DRAW_SETPIXEL_MOD_ARGB8888, draw_end);
+            break;
+        default:
+            VLINE(Uint32, DRAW_SETPIXEL_ARGB8888, draw_end);
+            break;
+        }
+    } else if (ABS(x1 - x2) == ABS(y1 - y2)) {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            DLINE(Uint32, DRAW_SETPIXEL_BLEND_ARGB8888, draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            DLINE(Uint32, DRAW_SETPIXEL_ADD_ARGB8888, draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            DLINE(Uint32, DRAW_SETPIXEL_MOD_ARGB8888, draw_end);
+            break;
+        default:
+            DLINE(Uint32, DRAW_SETPIXEL_ARGB8888, draw_end);
+            break;
+        }
+    } else {
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_BLEND_ARGB8888, DRAW_SETPIXELXY_BLEND_ARGB8888,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_ADD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_ADD_ARGB8888, DRAW_SETPIXELXY_ADD_ARGB8888,
+                   draw_end);
+            break;
+        case SDL_BLENDMODE_MOD:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_MOD_ARGB8888, DRAW_SETPIXELXY_MOD_ARGB8888,
+                   draw_end);
+            break;
+        default:
+            AALINE(x1, y1, x2, y2,
+                   DRAW_SETPIXELXY_ARGB8888, DRAW_SETPIXELXY_BLEND_ARGB8888,
+                   draw_end);
+            break;
+        }
+    }
+}
+
+typedef void (*BlendLineFunc) (SDL_Surface * dst,
+                               int x1, int y1, int x2, int y2,
+                               SDL_BlendMode blendMode,
+                               Uint8 r, Uint8 g, Uint8 b, Uint8 a,
+                               SDL_bool draw_end);
+
+static BlendLineFunc
+SDL_CalculateBlendLineFunc(const SDL_PixelFormat * fmt)
+{
+    switch (fmt->BytesPerPixel) {
+    case 2:
+        if (fmt->Rmask == 0x7C00) {
+            return SDL_BlendLine_RGB555;
+        } else if (fmt->Rmask == 0xF800) {
+            return SDL_BlendLine_RGB565;
+        } else {
+            return SDL_BlendLine_RGB2;
+        }
+        break;
+    case 4:
+        if (fmt->Rmask == 0x00FF0000) {
+            if (fmt->Amask) {
+                return SDL_BlendLine_ARGB8888;
+            } else {
+                return SDL_BlendLine_RGB888;
+            }
+        } else {
+            if (fmt->Amask) {
+                return SDL_BlendLine_RGBA4;
+            } else {
+                return SDL_BlendLine_RGB4;
+            }
+        }
+    }
+    return NULL;
+}
+
+int
+SDL_BlendLine(SDL_Surface * dst, int x1, int y1, int x2, int y2,
+              SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    BlendLineFunc func;
+
+    if (!dst) {
+        return SDL_SetError("SDL_BlendLine(): Passed NULL destination surface");
+    }
+
+    func = SDL_CalculateBlendLineFunc(dst->format);
+    if (!func) {
+        return SDL_SetError("SDL_BlendLine(): Unsupported surface format");
+    }
+
+    /* Perform clipping */
+    /* FIXME: We don't actually want to clip, as it may change line slope */
+    if (!SDL_IntersectRectAndLine(&dst->clip_rect, &x1, &y1, &x2, &y2)) {
+        return 0;
+    }
+
+    func(dst, x1, y1, x2, y2, blendMode, r, g, b, a, SDL_TRUE);
+    return 0;
+}
+
+int
+SDL_BlendLines(SDL_Surface * dst, const SDL_Point * points, int count,
+               SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    int i;
+    int x1, y1;
+    int x2, y2;
+    SDL_bool draw_end;
+    BlendLineFunc func;
+
+    if (!dst) {
+        return SDL_SetError("SDL_BlendLines(): Passed NULL destination surface");
+    }
+
+    func = SDL_CalculateBlendLineFunc(dst->format);
+    if (!func) {
+        return SDL_SetError("SDL_BlendLines(): Unsupported surface format");
+    }
+
+    for (i = 1; i < count; ++i) {
+        x1 = points[i-1].x;
+        y1 = points[i-1].y;
+        x2 = points[i].x;
+        y2 = points[i].y;
+
+        /* Perform clipping */
+        /* FIXME: We don't actually want to clip, as it may change line slope */
+        if (!SDL_IntersectRectAndLine(&dst->clip_rect, &x1, &y1, &x2, &y2)) {
+            continue;
+        }
+
+        /* Draw the end if it was clipped */
+        draw_end = (x2 != points[i].x || y2 != points[i].y);
+
+        func(dst, x1, y1, x2, y2, blendMode, r, g, b, a, draw_end);
+    }
+    if (points[0].x != points[count-1].x || points[0].y != points[count-1].y) {
+        SDL_BlendPoint(dst, points[count-1].x, points[count-1].y,
+                       blendMode, r, g, b, a);
+    }
+    return 0;
+}
+
+#endif /* !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_blendline.h

@@ -0,0 +1,27 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+
+extern int SDL_BlendLine(SDL_Surface * dst, int x1, int y1, int x2, int y2, SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a);
+extern int SDL_BlendLines(SDL_Surface * dst, const SDL_Point * points, int count, SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a);
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_blendpoint.c

@@ -0,0 +1,343 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#if !SDL_RENDER_DISABLED
+
+#include "SDL_draw.h"
+#include "SDL_blendpoint.h"
+
+
+static int
+SDL_BlendPoint_RGB555(SDL_Surface * dst, int x, int y, SDL_BlendMode blendMode, Uint8 r,
+                      Uint8 g, Uint8 b, Uint8 a)
+{
+    unsigned inva = 0xff - a;
+
+    switch (blendMode) {
+    case SDL_BLENDMODE_BLEND:
+        DRAW_SETPIXELXY_BLEND_RGB555(x, y);
+        break;
+    case SDL_BLENDMODE_ADD:
+        DRAW_SETPIXELXY_ADD_RGB555(x, y);
+        break;
+    case SDL_BLENDMODE_MOD:
+        DRAW_SETPIXELXY_MOD_RGB555(x, y);
+        break;
+    default:
+        DRAW_SETPIXELXY_RGB555(x, y);
+        break;
+    }
+    return 0;
+}
+
+static int
+SDL_BlendPoint_RGB565(SDL_Surface * dst, int x, int y, SDL_BlendMode blendMode, Uint8 r,
+                      Uint8 g, Uint8 b, Uint8 a)
+{
+    unsigned inva = 0xff - a;
+
+    switch (blendMode) {
+    case SDL_BLENDMODE_BLEND:
+        DRAW_SETPIXELXY_BLEND_RGB565(x, y);
+        break;
+    case SDL_BLENDMODE_ADD:
+        DRAW_SETPIXELXY_ADD_RGB565(x, y);
+        break;
+    case SDL_BLENDMODE_MOD:
+        DRAW_SETPIXELXY_MOD_RGB565(x, y);
+        break;
+    default:
+        DRAW_SETPIXELXY_RGB565(x, y);
+        break;
+    }
+    return 0;
+}
+
+static int
+SDL_BlendPoint_RGB888(SDL_Surface * dst, int x, int y, SDL_BlendMode blendMode, Uint8 r,
+                      Uint8 g, Uint8 b, Uint8 a)
+{
+    unsigned inva = 0xff - a;
+
+    switch (blendMode) {
+    case SDL_BLENDMODE_BLEND:
+        DRAW_SETPIXELXY_BLEND_RGB888(x, y);
+        break;
+    case SDL_BLENDMODE_ADD:
+        DRAW_SETPIXELXY_ADD_RGB888(x, y);
+        break;
+    case SDL_BLENDMODE_MOD:
+        DRAW_SETPIXELXY_MOD_RGB888(x, y);
+        break;
+    default:
+        DRAW_SETPIXELXY_RGB888(x, y);
+        break;
+    }
+    return 0;
+}
+
+static int
+SDL_BlendPoint_ARGB8888(SDL_Surface * dst, int x, int y, SDL_BlendMode blendMode,
+                        Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    unsigned inva = 0xff - a;
+
+    switch (blendMode) {
+    case SDL_BLENDMODE_BLEND:
+        DRAW_SETPIXELXY_BLEND_ARGB8888(x, y);
+        break;
+    case SDL_BLENDMODE_ADD:
+        DRAW_SETPIXELXY_ADD_ARGB8888(x, y);
+        break;
+    case SDL_BLENDMODE_MOD:
+        DRAW_SETPIXELXY_MOD_ARGB8888(x, y);
+        break;
+    default:
+        DRAW_SETPIXELXY_ARGB8888(x, y);
+        break;
+    }
+    return 0;
+}
+
+static int
+SDL_BlendPoint_RGB(SDL_Surface * dst, int x, int y, SDL_BlendMode blendMode, Uint8 r,
+                   Uint8 g, Uint8 b, Uint8 a)
+{
+    SDL_PixelFormat *fmt = dst->format;
+    unsigned inva = 0xff - a;
+
+    switch (fmt->BytesPerPixel) {
+    case 2:
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            DRAW_SETPIXELXY2_BLEND_RGB(x, y);
+            break;
+        case SDL_BLENDMODE_ADD:
+            DRAW_SETPIXELXY2_ADD_RGB(x, y);
+            break;
+        case SDL_BLENDMODE_MOD:
+            DRAW_SETPIXELXY2_MOD_RGB(x, y);
+            break;
+        default:
+            DRAW_SETPIXELXY2_RGB(x, y);
+            break;
+        }
+        return 0;
+    case 4:
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            DRAW_SETPIXELXY4_BLEND_RGB(x, y);
+            break;
+        case SDL_BLENDMODE_ADD:
+            DRAW_SETPIXELXY4_ADD_RGB(x, y);
+            break;
+        case SDL_BLENDMODE_MOD:
+            DRAW_SETPIXELXY4_MOD_RGB(x, y);
+            break;
+        default:
+            DRAW_SETPIXELXY4_RGB(x, y);
+            break;
+        }
+        return 0;
+    default:
+        return SDL_Unsupported();
+    }
+}
+
+static int
+SDL_BlendPoint_RGBA(SDL_Surface * dst, int x, int y, SDL_BlendMode blendMode, Uint8 r,
+                    Uint8 g, Uint8 b, Uint8 a)
+{
+    SDL_PixelFormat *fmt = dst->format;
+    unsigned inva = 0xff - a;
+
+    switch (fmt->BytesPerPixel) {
+    case 4:
+        switch (blendMode) {
+        case SDL_BLENDMODE_BLEND:
+            DRAW_SETPIXELXY4_BLEND_RGBA(x, y);
+            break;
+        case SDL_BLENDMODE_ADD:
+            DRAW_SETPIXELXY4_ADD_RGBA(x, y);
+            break;
+        case SDL_BLENDMODE_MOD:
+            DRAW_SETPIXELXY4_MOD_RGBA(x, y);
+            break;
+        default:
+            DRAW_SETPIXELXY4_RGBA(x, y);
+            break;
+        }
+        return 0;
+    default:
+        return SDL_Unsupported();
+    }
+}
+
+int
+SDL_BlendPoint(SDL_Surface * dst, int x, int y, SDL_BlendMode blendMode, Uint8 r,
+               Uint8 g, Uint8 b, Uint8 a)
+{
+    if (!dst) {
+        return SDL_SetError("Passed NULL destination surface");
+    }
+
+    /* This function doesn't work on surfaces < 8 bpp */
+    if (dst->format->BitsPerPixel < 8) {
+        return SDL_SetError("SDL_BlendPoint(): Unsupported surface format");
+    }
+
+    /* Perform clipping */
+    if (x < dst->clip_rect.x || y < dst->clip_rect.y ||
+        x >= (dst->clip_rect.x + dst->clip_rect.w) ||
+        y >= (dst->clip_rect.y + dst->clip_rect.h)) {
+        return 0;
+    }
+
+    if (blendMode == SDL_BLENDMODE_BLEND || blendMode == SDL_BLENDMODE_ADD) {
+        r = DRAW_MUL(r, a);
+        g = DRAW_MUL(g, a);
+        b = DRAW_MUL(b, a);
+    }
+
+    switch (dst->format->BitsPerPixel) {
+    case 15:
+        switch (dst->format->Rmask) {
+        case 0x7C00:
+            return SDL_BlendPoint_RGB555(dst, x, y, blendMode, r, g, b, a);
+        }
+        break;
+    case 16:
+        switch (dst->format->Rmask) {
+        case 0xF800:
+            return SDL_BlendPoint_RGB565(dst, x, y, blendMode, r, g, b, a);
+        }
+        break;
+    case 32:
+        switch (dst->format->Rmask) {
+        case 0x00FF0000:
+            if (!dst->format->Amask) {
+                return SDL_BlendPoint_RGB888(dst, x, y, blendMode, r, g, b,
+                                             a);
+            } else {
+                return SDL_BlendPoint_ARGB8888(dst, x, y, blendMode, r, g, b,
+                                               a);
+            }
+            break;
+        }
+        break;
+    default:
+        break;
+    }
+
+    if (!dst->format->Amask) {
+        return SDL_BlendPoint_RGB(dst, x, y, blendMode, r, g, b, a);
+    } else {
+        return SDL_BlendPoint_RGBA(dst, x, y, blendMode, r, g, b, a);
+    }
+}
+
+int
+SDL_BlendPoints(SDL_Surface * dst, const SDL_Point * points, int count,
+                SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a)
+{
+    int minx, miny;
+    int maxx, maxy;
+    int i;
+    int x, y;
+    int (*func)(SDL_Surface * dst, int x, int y,
+                SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a) = NULL;
+    int status = 0;
+
+    if (!dst) {
+        return SDL_SetError("Passed NULL destination surface");
+    }
+
+    /* This function doesn't work on surfaces < 8 bpp */
+    if (dst->format->BitsPerPixel < 8) {
+        return SDL_SetError("SDL_BlendPoints(): Unsupported surface format");
+    }
+
+    if (blendMode == SDL_BLENDMODE_BLEND || blendMode == SDL_BLENDMODE_ADD) {
+        r = DRAW_MUL(r, a);
+        g = DRAW_MUL(g, a);
+        b = DRAW_MUL(b, a);
+    }
+
+    /* FIXME: Does this function pointer slow things down significantly? */
+    switch (dst->format->BitsPerPixel) {
+    case 15:
+        switch (dst->format->Rmask) {
+        case 0x7C00:
+            func = SDL_BlendPoint_RGB555;
+            break;
+        }
+        break;
+    case 16:
+        switch (dst->format->Rmask) {
+        case 0xF800:
+            func = SDL_BlendPoint_RGB565;
+            break;
+        }
+        break;
+    case 32:
+        switch (dst->format->Rmask) {
+        case 0x00FF0000:
+            if (!dst->format->Amask) {
+                func = SDL_BlendPoint_RGB888;
+            } else {
+                func = SDL_BlendPoint_ARGB8888;
+            }
+            break;
+        }
+        break;
+    default:
+        break;
+    }
+
+    if (!func) {
+        if (!dst->format->Amask) {
+            func = SDL_BlendPoint_RGB;
+        } else {
+            func = SDL_BlendPoint_RGBA;
+        }
+    }
+
+    minx = dst->clip_rect.x;
+    maxx = dst->clip_rect.x + dst->clip_rect.w - 1;
+    miny = dst->clip_rect.y;
+    maxy = dst->clip_rect.y + dst->clip_rect.h - 1;
+
+    for (i = 0; i < count; ++i) {
+        x = points[i].x;
+        y = points[i].y;
+
+        if (x < minx || x > maxx || y < miny || y > maxy) {
+            continue;
+        }
+        status = func(dst, x, y, blendMode, r, g, b, a);
+    }
+    return status;
+}
+
+#endif /* !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_blendpoint.h

@@ -0,0 +1,27 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+
+extern int SDL_BlendPoint(SDL_Surface * dst, int x, int y, SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a);
+extern int SDL_BlendPoints(SDL_Surface * dst, const SDL_Point * points, int count, SDL_BlendMode blendMode, Uint8 r, Uint8 g, Uint8 b, Uint8 a);
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_draw.h

@@ -0,0 +1,576 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#include "../../video/SDL_blit.h"
+
+/* This code assumes that r, g, b, a are the source color,
+ * and in the blend and add case, the RGB values are premultiplied by a.
+ */
+
+#define DRAW_MUL(_a, _b) (((unsigned)(_a)*(_b))/255)
+
+#define DRAW_FASTSETPIXEL(type) \
+    *pixel = (type) color
+
+#define DRAW_FASTSETPIXEL1 DRAW_FASTSETPIXEL(Uint8)
+#define DRAW_FASTSETPIXEL2 DRAW_FASTSETPIXEL(Uint16)
+#define DRAW_FASTSETPIXEL4 DRAW_FASTSETPIXEL(Uint32)
+
+#define DRAW_FASTSETPIXELXY(x, y, type, bpp, color) \
+    *(type *)((Uint8 *)dst->pixels + (y) * dst->pitch \
+                                   + (x) * bpp) = (type) color
+
+#define DRAW_FASTSETPIXELXY1(x, y) DRAW_FASTSETPIXELXY(x, y, Uint8, 1, color)
+#define DRAW_FASTSETPIXELXY2(x, y) DRAW_FASTSETPIXELXY(x, y, Uint16, 2, color)
+#define DRAW_FASTSETPIXELXY4(x, y) DRAW_FASTSETPIXELXY(x, y, Uint32, 4, color)
+
+#define DRAW_SETPIXEL(setpixel) \
+do { \
+    unsigned sr = r, sg = g, sb = b, sa = a; (void) sa; \
+    setpixel; \
+} while (0)
+
+#define DRAW_SETPIXEL_BLEND(getpixel, setpixel) \
+do { \
+    unsigned sr, sg, sb, sa = 0xFF; \
+    getpixel; \
+    sr = DRAW_MUL(inva, sr) + r; \
+    sg = DRAW_MUL(inva, sg) + g; \
+    sb = DRAW_MUL(inva, sb) + b; \
+    sa = DRAW_MUL(inva, sa) + a; \
+    setpixel; \
+} while (0)
+
+#define DRAW_SETPIXEL_ADD(getpixel, setpixel) \
+do { \
+    unsigned sr, sg, sb, sa; (void) sa; \
+    getpixel; \
+    sr += r; if (sr > 0xff) sr = 0xff; \
+    sg += g; if (sg > 0xff) sg = 0xff; \
+    sb += b; if (sb > 0xff) sb = 0xff; \
+    setpixel; \
+} while (0)
+
+#define DRAW_SETPIXEL_MOD(getpixel, setpixel) \
+do { \
+    unsigned sr, sg, sb, sa; (void) sa; \
+    getpixel; \
+    sr = DRAW_MUL(sr, r); \
+    sg = DRAW_MUL(sg, g); \
+    sb = DRAW_MUL(sb, b); \
+    setpixel; \
+} while (0)
+
+#define DRAW_SETPIXELXY(x, y, type, bpp, op) \
+do { \
+    type *pixel = (type *)((Uint8 *)dst->pixels + (y) * dst->pitch \
+                                                + (x) * bpp); \
+    op; \
+} while (0)
+
+/*
+ * Define draw operators for RGB555
+ */
+
+#define DRAW_SETPIXEL_RGB555 \
+    DRAW_SETPIXEL(RGB555_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXEL_BLEND_RGB555 \
+    DRAW_SETPIXEL_BLEND(RGB_FROM_RGB555(*pixel, sr, sg, sb), \
+                        RGB555_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXEL_ADD_RGB555 \
+    DRAW_SETPIXEL_ADD(RGB_FROM_RGB555(*pixel, sr, sg, sb), \
+                      RGB555_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXEL_MOD_RGB555 \
+    DRAW_SETPIXEL_MOD(RGB_FROM_RGB555(*pixel, sr, sg, sb), \
+                      RGB555_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXELXY_RGB555(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_RGB555)
+
+#define DRAW_SETPIXELXY_BLEND_RGB555(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_BLEND_RGB555)
+
+#define DRAW_SETPIXELXY_ADD_RGB555(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_ADD_RGB555)
+
+#define DRAW_SETPIXELXY_MOD_RGB555(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_MOD_RGB555)
+
+/*
+ * Define draw operators for RGB565
+ */
+
+#define DRAW_SETPIXEL_RGB565 \
+    DRAW_SETPIXEL(RGB565_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXEL_BLEND_RGB565 \
+    DRAW_SETPIXEL_BLEND(RGB_FROM_RGB565(*pixel, sr, sg, sb), \
+                        RGB565_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXEL_ADD_RGB565 \
+    DRAW_SETPIXEL_ADD(RGB_FROM_RGB565(*pixel, sr, sg, sb), \
+                      RGB565_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXEL_MOD_RGB565 \
+    DRAW_SETPIXEL_MOD(RGB_FROM_RGB565(*pixel, sr, sg, sb), \
+                      RGB565_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXELXY_RGB565(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_RGB565)
+
+#define DRAW_SETPIXELXY_BLEND_RGB565(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_BLEND_RGB565)
+
+#define DRAW_SETPIXELXY_ADD_RGB565(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_ADD_RGB565)
+
+#define DRAW_SETPIXELXY_MOD_RGB565(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_MOD_RGB565)
+
+/*
+ * Define draw operators for RGB888
+ */
+
+#define DRAW_SETPIXEL_RGB888 \
+    DRAW_SETPIXEL(RGB888_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXEL_BLEND_RGB888 \
+    DRAW_SETPIXEL_BLEND(RGB_FROM_RGB888(*pixel, sr, sg, sb), \
+                        RGB888_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXEL_ADD_RGB888 \
+    DRAW_SETPIXEL_ADD(RGB_FROM_RGB888(*pixel, sr, sg, sb), \
+                      RGB888_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXEL_MOD_RGB888 \
+    DRAW_SETPIXEL_MOD(RGB_FROM_RGB888(*pixel, sr, sg, sb), \
+                      RGB888_FROM_RGB(*pixel, sr, sg, sb))
+
+#define DRAW_SETPIXELXY_RGB888(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_RGB888)
+
+#define DRAW_SETPIXELXY_BLEND_RGB888(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_BLEND_RGB888)
+
+#define DRAW_SETPIXELXY_ADD_RGB888(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_ADD_RGB888)
+
+#define DRAW_SETPIXELXY_MOD_RGB888(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_MOD_RGB888)
+
+/*
+ * Define draw operators for ARGB8888
+ */
+
+#define DRAW_SETPIXEL_ARGB8888 \
+    DRAW_SETPIXEL(ARGB8888_FROM_RGBA(*pixel, sr, sg, sb, sa))
+
+#define DRAW_SETPIXEL_BLEND_ARGB8888 \
+    DRAW_SETPIXEL_BLEND(RGBA_FROM_ARGB8888(*pixel, sr, sg, sb, sa), \
+                        ARGB8888_FROM_RGBA(*pixel, sr, sg, sb, sa))
+
+#define DRAW_SETPIXEL_ADD_ARGB8888 \
+    DRAW_SETPIXEL_ADD(RGBA_FROM_ARGB8888(*pixel, sr, sg, sb, sa), \
+                      ARGB8888_FROM_RGBA(*pixel, sr, sg, sb, sa))
+
+#define DRAW_SETPIXEL_MOD_ARGB8888 \
+    DRAW_SETPIXEL_MOD(RGBA_FROM_ARGB8888(*pixel, sr, sg, sb, sa), \
+                      ARGB8888_FROM_RGBA(*pixel, sr, sg, sb, sa))
+
+#define DRAW_SETPIXELXY_ARGB8888(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_ARGB8888)
+
+#define DRAW_SETPIXELXY_BLEND_ARGB8888(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_BLEND_ARGB8888)
+
+#define DRAW_SETPIXELXY_ADD_ARGB8888(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_ADD_ARGB8888)
+
+#define DRAW_SETPIXELXY_MOD_ARGB8888(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_MOD_ARGB8888)
+
+/*
+ * Define draw operators for general RGB
+ */
+
+#define DRAW_SETPIXEL_RGB \
+    DRAW_SETPIXEL(PIXEL_FROM_RGB(*pixel, fmt, sr, sg, sb))
+
+#define DRAW_SETPIXEL_BLEND_RGB \
+    DRAW_SETPIXEL_BLEND(RGB_FROM_PIXEL(*pixel, fmt, sr, sg, sb), \
+                        PIXEL_FROM_RGB(*pixel, fmt, sr, sg, sb))
+
+#define DRAW_SETPIXEL_ADD_RGB \
+    DRAW_SETPIXEL_ADD(RGB_FROM_PIXEL(*pixel, fmt, sr, sg, sb), \
+                      PIXEL_FROM_RGB(*pixel, fmt, sr, sg, sb))
+
+#define DRAW_SETPIXEL_MOD_RGB \
+    DRAW_SETPIXEL_MOD(RGB_FROM_PIXEL(*pixel, fmt, sr, sg, sb), \
+                      PIXEL_FROM_RGB(*pixel, fmt, sr, sg, sb))
+
+#define DRAW_SETPIXELXY2_RGB(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_RGB)
+
+#define DRAW_SETPIXELXY4_RGB(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_RGB)
+
+#define DRAW_SETPIXELXY2_BLEND_RGB(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_BLEND_RGB)
+
+#define DRAW_SETPIXELXY4_BLEND_RGB(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_BLEND_RGB)
+
+#define DRAW_SETPIXELXY2_ADD_RGB(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_ADD_RGB)
+
+#define DRAW_SETPIXELXY4_ADD_RGB(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_ADD_RGB)
+
+#define DRAW_SETPIXELXY2_MOD_RGB(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint16, 2, DRAW_SETPIXEL_MOD_RGB)
+
+#define DRAW_SETPIXELXY4_MOD_RGB(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_MOD_RGB)
+
+
+/*
+ * Define draw operators for general RGBA
+ */
+
+#define DRAW_SETPIXEL_RGBA \
+    DRAW_SETPIXEL(PIXEL_FROM_RGBA(*pixel, fmt, sr, sg, sb, sa))
+
+#define DRAW_SETPIXEL_BLEND_RGBA \
+    DRAW_SETPIXEL_BLEND(RGBA_FROM_PIXEL(*pixel, fmt, sr, sg, sb, sa), \
+                        PIXEL_FROM_RGBA(*pixel, fmt, sr, sg, sb, sa))
+
+#define DRAW_SETPIXEL_ADD_RGBA \
+    DRAW_SETPIXEL_ADD(RGBA_FROM_PIXEL(*pixel, fmt, sr, sg, sb, sa), \
+                      PIXEL_FROM_RGBA(*pixel, fmt, sr, sg, sb, sa))
+
+#define DRAW_SETPIXEL_MOD_RGBA \
+    DRAW_SETPIXEL_MOD(RGBA_FROM_PIXEL(*pixel, fmt, sr, sg, sb, sa), \
+                      PIXEL_FROM_RGBA(*pixel, fmt, sr, sg, sb, sa))
+
+#define DRAW_SETPIXELXY4_RGBA(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_RGBA)
+
+#define DRAW_SETPIXELXY4_BLEND_RGBA(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_BLEND_RGBA)
+
+#define DRAW_SETPIXELXY4_ADD_RGBA(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_ADD_RGBA)
+
+#define DRAW_SETPIXELXY4_MOD_RGBA(x, y) \
+    DRAW_SETPIXELXY(x, y, Uint32, 4, DRAW_SETPIXEL_MOD_RGBA)
+
+/*
+ * Define line drawing macro
+ */
+
+#define ABS(_x) ((_x) < 0 ? -(_x) : (_x))
+
+/* Horizontal line */
+#define HLINE(type, op, draw_end) \
+{ \
+    int length; \
+    int pitch = (dst->pitch / dst->format->BytesPerPixel); \
+    type *pixel; \
+    if (x1 <= x2) { \
+        pixel = (type *)dst->pixels + y1 * pitch + x1; \
+        length = draw_end ? (x2-x1+1) : (x2-x1); \
+    } else { \
+        pixel = (type *)dst->pixels + y1 * pitch + x2; \
+        if (!draw_end) { \
+            ++pixel; \
+        } \
+        length = draw_end ? (x1-x2+1) : (x1-x2); \
+    } \
+    while (length--) { \
+        op; \
+        ++pixel; \
+    } \
+}
+
+/* Vertical line */
+#define VLINE(type, op, draw_end) \
+{ \
+    int length; \
+    int pitch = (dst->pitch / dst->format->BytesPerPixel); \
+    type *pixel; \
+    if (y1 <= y2) { \
+        pixel = (type *)dst->pixels + y1 * pitch + x1; \
+        length = draw_end ? (y2-y1+1) : (y2-y1); \
+    } else { \
+        pixel = (type *)dst->pixels + y2 * pitch + x1; \
+        if (!draw_end) { \
+            pixel += pitch; \
+        } \
+        length = draw_end ? (y1-y2+1) : (y1-y2); \
+    } \
+    while (length--) { \
+        op; \
+        pixel += pitch; \
+    } \
+}
+
+/* Diagonal line */
+#define DLINE(type, op, draw_end) \
+{ \
+    int length; \
+    int pitch = (dst->pitch / dst->format->BytesPerPixel); \
+    type *pixel; \
+    if (y1 <= y2) { \
+        pixel = (type *)dst->pixels + y1 * pitch + x1; \
+        if (x1 <= x2) { \
+            ++pitch; \
+        } else { \
+            --pitch; \
+        } \
+        length = (y2-y1); \
+    } else { \
+        pixel = (type *)dst->pixels + y2 * pitch + x2; \
+        if (x2 <= x1) { \
+            ++pitch; \
+        } else { \
+            --pitch; \
+        } \
+        if (!draw_end) { \
+            pixel += pitch; \
+        } \
+        length = (y1-y2); \
+    } \
+    if (draw_end) { \
+        ++length; \
+    } \
+    while (length--) { \
+        op; \
+        pixel += pitch; \
+    } \
+}
+
+/* Bresenham's line algorithm */
+#define BLINE(x1, y1, x2, y2, op, draw_end) \
+{ \
+    int i, deltax, deltay, numpixels; \
+    int d, dinc1, dinc2; \
+    int x, xinc1, xinc2; \
+    int y, yinc1, yinc2; \
+ \
+    deltax = ABS(x2 - x1); \
+    deltay = ABS(y2 - y1); \
+ \
+    if (deltax >= deltay) { \
+        numpixels = deltax + 1; \
+        d = (2 * deltay) - deltax; \
+        dinc1 = deltay * 2; \
+        dinc2 = (deltay - deltax) * 2; \
+        xinc1 = 1; \
+        xinc2 = 1; \
+        yinc1 = 0; \
+        yinc2 = 1; \
+    } else { \
+        numpixels = deltay + 1; \
+        d = (2 * deltax) - deltay; \
+        dinc1 = deltax * 2; \
+        dinc2 = (deltax - deltay) * 2; \
+        xinc1 = 0; \
+        xinc2 = 1; \
+        yinc1 = 1; \
+        yinc2 = 1; \
+    } \
+ \
+    if (x1 > x2) { \
+        xinc1 = -xinc1; \
+        xinc2 = -xinc2; \
+    } \
+    if (y1 > y2) { \
+        yinc1 = -yinc1; \
+        yinc2 = -yinc2; \
+    } \
+ \
+    x = x1; \
+    y = y1; \
+ \
+    if (!draw_end) { \
+        --numpixels; \
+    } \
+    for (i = 0; i < numpixels; ++i) { \
+        op(x, y); \
+        if (d < 0) { \
+            d += dinc1; \
+            x += xinc1; \
+            y += yinc1; \
+        } else { \
+            d += dinc2; \
+            x += xinc2; \
+            y += yinc2; \
+        } \
+    } \
+}
+
+/* Xiaolin Wu's line algorithm, based on Michael Abrash's implementation */
+#define WULINE(x1, y1, x2, y2, opaque_op, blend_op, draw_end) \
+{ \
+    Uint16 ErrorAdj, ErrorAcc; \
+    Uint16 ErrorAccTemp, Weighting; \
+    int DeltaX, DeltaY, Temp, XDir; \
+    unsigned r, g, b, a, inva; \
+ \
+    /* Draw the initial pixel, which is always exactly intersected by \
+       the line and so needs no weighting */ \
+    opaque_op(x1, y1); \
+ \
+    /* Draw the final pixel, which is always exactly intersected by the line \
+       and so needs no weighting */ \
+    if (draw_end) { \
+        opaque_op(x2, y2); \
+    } \
+ \
+    /* Make sure the line runs top to bottom */ \
+    if (y1 > y2) { \
+        Temp = y1; y1 = y2; y2 = Temp; \
+        Temp = x1; x1 = x2; x2 = Temp; \
+    } \
+    DeltaY = y2 - y1; \
+ \
+    if ((DeltaX = x2 - x1) >= 0) { \
+        XDir = 1; \
+    } else { \
+        XDir = -1; \
+        DeltaX = -DeltaX; /* make DeltaX positive */ \
+    } \
+ \
+    /* line is not horizontal, diagonal, or vertical */ \
+    ErrorAcc = 0;  /* initialize the line error accumulator to 0 */ \
+ \
+    /* Is this an X-major or Y-major line? */ \
+    if (DeltaY > DeltaX) { \
+        /* Y-major line; calculate 16-bit fixed-point fractional part of a \
+          pixel that X advances each time Y advances 1 pixel, truncating the \
+          result so that we won't overrun the endpoint along the X axis */ \
+        ErrorAdj = ((unsigned long) DeltaX << 16) / (unsigned long) DeltaY; \
+        /* Draw all pixels other than the first and last */ \
+        while (--DeltaY) { \
+            ErrorAccTemp = ErrorAcc;   /* remember currrent accumulated error */ \
+            ErrorAcc += ErrorAdj;      /* calculate error for next pixel */ \
+            if (ErrorAcc <= ErrorAccTemp) { \
+                /* The error accumulator turned over, so advance the X coord */ \
+                x1 += XDir; \
+            } \
+            y1++; /* Y-major, so always advance Y */ \
+            /* The IntensityBits most significant bits of ErrorAcc give us the \
+             intensity weighting for this pixel, and the complement of the \
+             weighting for the paired pixel */ \
+            Weighting = ErrorAcc >> 8; \
+            { \
+                a = DRAW_MUL(_a, (Weighting ^ 255)); \
+                r = DRAW_MUL(_r, a); \
+                g = DRAW_MUL(_g, a); \
+                b = DRAW_MUL(_b, a); \
+                inva = (a ^ 0xFF); \
+                blend_op(x1, y1); \
+            } \
+            { \
+                a = DRAW_MUL(_a, Weighting); \
+                r = DRAW_MUL(_r, a); \
+                g = DRAW_MUL(_g, a); \
+                b = DRAW_MUL(_b, a); \
+                inva = (a ^ 0xFF); \
+                blend_op(x1 + XDir, y1); \
+            } \
+        } \
+    } else { \
+        /* X-major line; calculate 16-bit fixed-point fractional part of a \
+           pixel that Y advances each time X advances 1 pixel, truncating the \
+           result to avoid overrunning the endpoint along the X axis */ \
+        ErrorAdj = ((unsigned long) DeltaY << 16) / (unsigned long) DeltaX; \
+        /* Draw all pixels other than the first and last */ \
+        while (--DeltaX) { \
+            ErrorAccTemp = ErrorAcc;   /* remember currrent accumulated error */ \
+            ErrorAcc += ErrorAdj;      /* calculate error for next pixel */ \
+            if (ErrorAcc <= ErrorAccTemp) { \
+                /* The error accumulator turned over, so advance the Y coord */ \
+                y1++; \
+            } \
+            x1 += XDir; /* X-major, so always advance X */ \
+            /* The IntensityBits most significant bits of ErrorAcc give us the \
+              intensity weighting for this pixel, and the complement of the \
+              weighting for the paired pixel */ \
+            Weighting = ErrorAcc >> 8; \
+            { \
+                a = DRAW_MUL(_a, (Weighting ^ 255)); \
+                r = DRAW_MUL(_r, a); \
+                g = DRAW_MUL(_g, a); \
+                b = DRAW_MUL(_b, a); \
+                inva = (a ^ 0xFF); \
+                blend_op(x1, y1); \
+            } \
+            { \
+                a = DRAW_MUL(_a, Weighting); \
+                r = DRAW_MUL(_r, a); \
+                g = DRAW_MUL(_g, a); \
+                b = DRAW_MUL(_b, a); \
+                inva = (a ^ 0xFF); \
+                blend_op(x1, y1 + 1); \
+            } \
+        } \
+    } \
+}
+
+#ifdef AA_LINES
+#define AALINE(x1, y1, x2, y2, opaque_op, blend_op, draw_end) \
+            WULINE(x1, y1, x2, y2, opaque_op, blend_op, draw_end)
+#else
+#define AALINE(x1, y1, x2, y2, opaque_op, blend_op, draw_end) \
+            BLINE(x1, y1, x2, y2, opaque_op, draw_end)
+#endif
+
+/*
+ * Define fill rect macro
+ */
+
+#define FILLRECT(type, op) \
+do { \
+    int width = rect->w; \
+    int height = rect->h; \
+    int pitch = (dst->pitch / dst->format->BytesPerPixel); \
+    int skip = pitch - width; \
+    type *pixel = (type *)dst->pixels + rect->y * pitch + rect->x; \
+    while (height--) { \
+        { int n = (width+3)/4; \
+            switch (width & 3) { \
+            case 0: do {   op; pixel++; \
+            case 3:        op; pixel++; \
+            case 2:        op; pixel++; \
+            case 1:        op; pixel++; \
+                    } while ( --n > 0 ); \
+            } \
+        } \
+        pixel += skip; \
+    } \
+} while (0)
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_drawline.c

@@ -0,0 +1,209 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#if !SDL_RENDER_DISABLED
+
+#include "SDL_draw.h"
+#include "SDL_drawline.h"
+#include "SDL_drawpoint.h"
+
+
+static void
+SDL_DrawLine1(SDL_Surface * dst, int x1, int y1, int x2, int y2, Uint32 color,
+              SDL_bool draw_end)
+{
+    if (y1 == y2) {
+        int length;
+        int pitch = (dst->pitch / dst->format->BytesPerPixel);
+        Uint8 *pixel;
+        if (x1 <= x2) {
+            pixel = (Uint8 *)dst->pixels + y1 * pitch + x1;
+            length = draw_end ? (x2-x1+1) : (x2-x1);
+        } else {
+            pixel = (Uint8 *)dst->pixels + y1 * pitch + x2;
+            if (!draw_end) {
+                ++pixel;
+            }
+            length = draw_end ? (x1-x2+1) : (x1-x2);
+        }
+        SDL_memset(pixel, color, length);
+    } else if (x1 == x2) {
+        VLINE(Uint8, DRAW_FASTSETPIXEL1, draw_end);
+    } else if (ABS(x1 - x2) == ABS(y1 - y2)) {
+        DLINE(Uint8, DRAW_FASTSETPIXEL1, draw_end);
+    } else {
+        BLINE(x1, y1, x2, y2, DRAW_FASTSETPIXELXY1, draw_end);
+    }
+}
+
+static void
+SDL_DrawLine2(SDL_Surface * dst, int x1, int y1, int x2, int y2, Uint32 color,
+              SDL_bool draw_end)
+{
+    if (y1 == y2) {
+        HLINE(Uint16, DRAW_FASTSETPIXEL2, draw_end);
+    } else if (x1 == x2) {
+        VLINE(Uint16, DRAW_FASTSETPIXEL2, draw_end);
+    } else if (ABS(x1 - x2) == ABS(y1 - y2)) {
+        DLINE(Uint16, DRAW_FASTSETPIXEL2, draw_end);
+    } else {
+        Uint8 _r, _g, _b, _a;
+        const SDL_PixelFormat * fmt = dst->format;
+        SDL_GetRGBA(color, fmt, &_r, &_g, &_b, &_a);
+        if (fmt->Rmask == 0x7C00) {
+            AALINE(x1, y1, x2, y2,
+                   DRAW_FASTSETPIXELXY2, DRAW_SETPIXELXY_BLEND_RGB555,
+                   draw_end);
+        } else if (fmt->Rmask == 0xF800) {
+            AALINE(x1, y1, x2, y2,
+                   DRAW_FASTSETPIXELXY2, DRAW_SETPIXELXY_BLEND_RGB565,
+                   draw_end);
+        } else {
+            AALINE(x1, y1, x2, y2,
+                   DRAW_FASTSETPIXELXY2, DRAW_SETPIXELXY2_BLEND_RGB,
+                   draw_end);
+        }
+    }
+}
+
+static void
+SDL_DrawLine4(SDL_Surface * dst, int x1, int y1, int x2, int y2, Uint32 color,
+              SDL_bool draw_end)
+{
+    if (y1 == y2) {
+        HLINE(Uint32, DRAW_FASTSETPIXEL4, draw_end);
+    } else if (x1 == x2) {
+        VLINE(Uint32, DRAW_FASTSETPIXEL4, draw_end);
+    } else if (ABS(x1 - x2) == ABS(y1 - y2)) {
+        DLINE(Uint32, DRAW_FASTSETPIXEL4, draw_end);
+    } else {
+        Uint8 _r, _g, _b, _a;
+        const SDL_PixelFormat * fmt = dst->format;
+        SDL_GetRGBA(color, fmt, &_r, &_g, &_b, &_a);
+        if (fmt->Rmask == 0x00FF0000) {
+            if (!fmt->Amask) {
+                AALINE(x1, y1, x2, y2,
+                       DRAW_FASTSETPIXELXY4, DRAW_SETPIXELXY_BLEND_RGB888,
+                       draw_end);
+            } else {
+                AALINE(x1, y1, x2, y2,
+                       DRAW_FASTSETPIXELXY4, DRAW_SETPIXELXY_BLEND_ARGB8888,
+                       draw_end);
+            }
+        } else {
+            AALINE(x1, y1, x2, y2,
+                   DRAW_FASTSETPIXELXY4, DRAW_SETPIXELXY4_BLEND_RGB,
+                   draw_end);
+        }
+    }
+}
+
+typedef void (*DrawLineFunc) (SDL_Surface * dst,
+                              int x1, int y1, int x2, int y2,
+                              Uint32 color, SDL_bool draw_end);
+
+static DrawLineFunc
+SDL_CalculateDrawLineFunc(const SDL_PixelFormat * fmt)
+{
+    switch (fmt->BytesPerPixel) {
+    case 1:
+        if (fmt->BitsPerPixel < 8) {
+            break;
+        }
+        return SDL_DrawLine1;
+    case 2:
+        return SDL_DrawLine2;
+    case 4:
+        return SDL_DrawLine4;
+    }
+    return NULL;
+}
+
+int
+SDL_DrawLine(SDL_Surface * dst, int x1, int y1, int x2, int y2, Uint32 color)
+{
+    DrawLineFunc func;
+
+    if (!dst) {
+        return SDL_SetError("SDL_DrawLine(): Passed NULL destination surface");
+    }
+
+    func = SDL_CalculateDrawLineFunc(dst->format);
+    if (!func) {
+        return SDL_SetError("SDL_DrawLine(): Unsupported surface format");
+    }
+
+    /* Perform clipping */
+    /* FIXME: We don't actually want to clip, as it may change line slope */
+    if (!SDL_IntersectRectAndLine(&dst->clip_rect, &x1, &y1, &x2, &y2)) {
+        return 0;
+    }
+
+    func(dst, x1, y1, x2, y2, color, SDL_TRUE);
+    return 0;
+}
+
+int
+SDL_DrawLines(SDL_Surface * dst, const SDL_Point * points, int count,
+              Uint32 color)
+{
+    int i;
+    int x1, y1;
+    int x2, y2;
+    SDL_bool draw_end;
+    DrawLineFunc func;
+
+    if (!dst) {
+        return SDL_SetError("SDL_DrawLines(): Passed NULL destination surface");
+    }
+
+    func = SDL_CalculateDrawLineFunc(dst->format);
+    if (!func) {
+        return SDL_SetError("SDL_DrawLines(): Unsupported surface format");
+    }
+
+    for (i = 1; i < count; ++i) {
+        x1 = points[i-1].x;
+        y1 = points[i-1].y;
+        x2 = points[i].x;
+        y2 = points[i].y;
+
+        /* Perform clipping */
+        /* FIXME: We don't actually want to clip, as it may change line slope */
+        if (!SDL_IntersectRectAndLine(&dst->clip_rect, &x1, &y1, &x2, &y2)) {
+            continue;
+        }
+
+        /* Draw the end if it was clipped */
+        draw_end = (x2 != points[i].x || y2 != points[i].y);
+
+        func(dst, x1, y1, x2, y2, color, draw_end);
+    }
+    if (points[0].x != points[count-1].x || points[0].y != points[count-1].y) {
+        SDL_DrawPoint(dst, points[count-1].x, points[count-1].y, color);
+    }
+    return 0;
+}
+
+#endif /* !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_drawline.h

@@ -0,0 +1,27 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+
+extern int SDL_DrawLine(SDL_Surface * dst, int x1, int y1, int x2, int y2, Uint32 color);
+extern int SDL_DrawLines(SDL_Surface * dst, const SDL_Point * points, int count, Uint32 color);
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_drawpoint.c

@@ -0,0 +1,114 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#if !SDL_RENDER_DISABLED
+
+#include "SDL_draw.h"
+#include "SDL_drawpoint.h"
+
+
+int
+SDL_DrawPoint(SDL_Surface * dst, int x, int y, Uint32 color)
+{
+    if (!dst) {
+        return SDL_SetError("Passed NULL destination surface");
+    }
+
+    /* This function doesn't work on surfaces < 8 bpp */
+    if (dst->format->BitsPerPixel < 8) {
+        return SDL_SetError("SDL_DrawPoint(): Unsupported surface format");
+    }
+
+    /* Perform clipping */
+    if (x < dst->clip_rect.x || y < dst->clip_rect.y ||
+        x >= (dst->clip_rect.x + dst->clip_rect.w) ||
+        y >= (dst->clip_rect.y + dst->clip_rect.h)) {
+        return 0;
+    }
+
+    switch (dst->format->BytesPerPixel) {
+    case 1:
+        DRAW_FASTSETPIXELXY1(x, y);
+        break;
+    case 2:
+        DRAW_FASTSETPIXELXY2(x, y);
+        break;
+    case 3:
+        return SDL_Unsupported();
+    case 4:
+        DRAW_FASTSETPIXELXY4(x, y);
+        break;
+    }
+    return 0;
+}
+
+int
+SDL_DrawPoints(SDL_Surface * dst, const SDL_Point * points, int count,
+               Uint32 color)
+{
+    int minx, miny;
+    int maxx, maxy;
+    int i;
+    int x, y;
+
+    if (!dst) {
+        return SDL_SetError("Passed NULL destination surface");
+    }
+
+    /* This function doesn't work on surfaces < 8 bpp */
+    if (dst->format->BitsPerPixel < 8) {
+        return SDL_SetError("SDL_DrawPoints(): Unsupported surface format");
+    }
+
+    minx = dst->clip_rect.x;
+    maxx = dst->clip_rect.x + dst->clip_rect.w - 1;
+    miny = dst->clip_rect.y;
+    maxy = dst->clip_rect.y + dst->clip_rect.h - 1;
+
+    for (i = 0; i < count; ++i) {
+        x = points[i].x;
+        y = points[i].y;
+
+        if (x < minx || x > maxx || y < miny || y > maxy) {
+            continue;
+        }
+
+        switch (dst->format->BytesPerPixel) {
+        case 1:
+            DRAW_FASTSETPIXELXY1(x, y);
+            break;
+        case 2:
+            DRAW_FASTSETPIXELXY2(x, y);
+            break;
+        case 3:
+            return SDL_Unsupported();
+        case 4:
+            DRAW_FASTSETPIXELXY4(x, y);
+            break;
+        }
+    }
+    return 0;
+}
+
+#endif /* !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_drawpoint.h

@@ -0,0 +1,27 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+
+extern int SDL_DrawPoint(SDL_Surface * dst, int x, int y, Uint32 color);
+extern int SDL_DrawPoints(SDL_Surface * dst, const SDL_Point * points, int count, Uint32 color);
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_render_sw.c

@@ -0,0 +1,726 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+#include "../../SDL_internal.h"
+
+#if !SDL_RENDER_DISABLED
+
+#include "../SDL_sysrender.h"
+#include "SDL_render_sw_c.h"
+#include "SDL_hints.h"
+
+#include "SDL_draw.h"
+#include "SDL_blendfillrect.h"
+#include "SDL_blendline.h"
+#include "SDL_blendpoint.h"
+#include "SDL_drawline.h"
+#include "SDL_drawpoint.h"
+#include "SDL_rotate.h"
+
+/* SDL surface based renderer implementation */
+
+static SDL_Renderer *SW_CreateRenderer(SDL_Window * window, Uint32 flags);
+static void SW_WindowEvent(SDL_Renderer * renderer,
+                           const SDL_WindowEvent *event);
+static int SW_GetOutputSize(SDL_Renderer * renderer, int *w, int *h);
+static int SW_CreateTexture(SDL_Renderer * renderer, SDL_Texture * texture);
+static int SW_SetTextureColorMod(SDL_Renderer * renderer,
+                                 SDL_Texture * texture);
+static int SW_SetTextureAlphaMod(SDL_Renderer * renderer,
+                                 SDL_Texture * texture);
+static int SW_SetTextureBlendMode(SDL_Renderer * renderer,
+                                  SDL_Texture * texture);
+static int SW_UpdateTexture(SDL_Renderer * renderer, SDL_Texture * texture,
+                            const SDL_Rect * rect, const void *pixels,
+                            int pitch);
+static int SW_LockTexture(SDL_Renderer * renderer, SDL_Texture * texture,
+                          const SDL_Rect * rect, void **pixels, int *pitch);
+static void SW_UnlockTexture(SDL_Renderer * renderer, SDL_Texture * texture);
+static int SW_SetRenderTarget(SDL_Renderer * renderer, SDL_Texture * texture);
+static int SW_UpdateViewport(SDL_Renderer * renderer);
+static int SW_UpdateClipRect(SDL_Renderer * renderer);
+static int SW_RenderClear(SDL_Renderer * renderer);
+static int SW_RenderDrawPoints(SDL_Renderer * renderer,
+                               const SDL_FPoint * points, int count);
+static int SW_RenderDrawLines(SDL_Renderer * renderer,
+                              const SDL_FPoint * points, int count);
+static int SW_RenderFillRects(SDL_Renderer * renderer,
+                              const SDL_FRect * rects, int count);
+static int SW_RenderCopy(SDL_Renderer * renderer, SDL_Texture * texture,
+                         const SDL_Rect * srcrect, const SDL_FRect * dstrect);
+static int SW_RenderCopyEx(SDL_Renderer * renderer, SDL_Texture * texture,
+                          const SDL_Rect * srcrect, const SDL_FRect * dstrect,
+                          const double angle, const SDL_FPoint * center, const SDL_RendererFlip flip);
+static int SW_RenderReadPixels(SDL_Renderer * renderer, const SDL_Rect * rect,
+                               Uint32 format, void * pixels, int pitch);
+static void SW_RenderPresent(SDL_Renderer * renderer);
+static void SW_DestroyTexture(SDL_Renderer * renderer, SDL_Texture * texture);
+static void SW_DestroyRenderer(SDL_Renderer * renderer);
+
+
+SDL_RenderDriver SW_RenderDriver = {
+    SW_CreateRenderer,
+    {
+     "software",
+     SDL_RENDERER_SOFTWARE | SDL_RENDERER_TARGETTEXTURE,
+     8,
+     {
+      SDL_PIXELFORMAT_ARGB8888,
+      SDL_PIXELFORMAT_ABGR8888,
+      SDL_PIXELFORMAT_RGBA8888,
+      SDL_PIXELFORMAT_BGRA8888,
+      SDL_PIXELFORMAT_RGB888,
+      SDL_PIXELFORMAT_BGR888,
+      SDL_PIXELFORMAT_RGB565,
+      SDL_PIXELFORMAT_RGB555
+     },
+     0,
+     0}
+};
+
+typedef struct
+{
+    SDL_Surface *surface;
+    SDL_Surface *window;
+} SW_RenderData;
+
+
+static SDL_Surface *
+SW_ActivateRenderer(SDL_Renderer * renderer)
+{
+    SW_RenderData *data = (SW_RenderData *) renderer->driverdata;
+
+    if (!data->surface) {
+        data->surface = data->window;
+    }
+    if (!data->surface) {
+        SDL_Surface *surface = SDL_GetWindowSurface(renderer->window);
+        if (surface) {
+            data->surface = data->window = surface;
+
+            SW_UpdateViewport(renderer);
+            SW_UpdateClipRect(renderer);
+        }
+    }
+    return data->surface;
+}
+
+SDL_Renderer *
+SW_CreateRendererForSurface(SDL_Surface * surface)
+{
+    SDL_Renderer *renderer;
+    SW_RenderData *data;
+
+    if (!surface) {
+        SDL_SetError("Can't create renderer for NULL surface");
+        return NULL;
+    }
+
+    renderer = (SDL_Renderer *) SDL_calloc(1, sizeof(*renderer));
+    if (!renderer) {
+        SDL_OutOfMemory();
+        return NULL;
+    }
+
+    data = (SW_RenderData *) SDL_calloc(1, sizeof(*data));
+    if (!data) {
+        SW_DestroyRenderer(renderer);
+        SDL_OutOfMemory();
+        return NULL;
+    }
+    data->surface = surface;
+    data->window = surface;
+
+    renderer->WindowEvent = SW_WindowEvent;
+    renderer->GetOutputSize = SW_GetOutputSize;
+    renderer->CreateTexture = SW_CreateTexture;
+    renderer->SetTextureColorMod = SW_SetTextureColorMod;
+    renderer->SetTextureAlphaMod = SW_SetTextureAlphaMod;
+    renderer->SetTextureBlendMode = SW_SetTextureBlendMode;
+    renderer->UpdateTexture = SW_UpdateTexture;
+    renderer->LockTexture = SW_LockTexture;
+    renderer->UnlockTexture = SW_UnlockTexture;
+    renderer->SetRenderTarget = SW_SetRenderTarget;
+    renderer->UpdateViewport = SW_UpdateViewport;
+    renderer->UpdateClipRect = SW_UpdateClipRect;
+    renderer->RenderClear = SW_RenderClear;
+    renderer->RenderDrawPoints = SW_RenderDrawPoints;
+    renderer->RenderDrawLines = SW_RenderDrawLines;
+    renderer->RenderFillRects = SW_RenderFillRects;
+    renderer->RenderCopy = SW_RenderCopy;
+    renderer->RenderCopyEx = SW_RenderCopyEx;
+    renderer->RenderReadPixels = SW_RenderReadPixels;
+    renderer->RenderPresent = SW_RenderPresent;
+    renderer->DestroyTexture = SW_DestroyTexture;
+    renderer->DestroyRenderer = SW_DestroyRenderer;
+    renderer->info = SW_RenderDriver.info;
+    renderer->driverdata = data;
+
+    SW_ActivateRenderer(renderer);
+
+    return renderer;
+}
+
+SDL_Renderer *
+SW_CreateRenderer(SDL_Window * window, Uint32 flags)
+{
+    SDL_Surface *surface;
+
+    surface = SDL_GetWindowSurface(window);
+    if (!surface) {
+        return NULL;
+    }
+    return SW_CreateRendererForSurface(surface);
+}
+
+static void
+SW_WindowEvent(SDL_Renderer * renderer, const SDL_WindowEvent *event)
+{
+    SW_RenderData *data = (SW_RenderData *) renderer->driverdata;
+
+    if (event->event == SDL_WINDOWEVENT_SIZE_CHANGED) {
+        data->surface = NULL;
+        data->window = NULL;
+    }
+}
+
+static int
+SW_GetOutputSize(SDL_Renderer * renderer, int *w, int *h)
+{
+    SDL_Surface *surface = SW_ActivateRenderer(renderer);
+
+    if (surface) {
+        if (w) {
+            *w = surface->w;
+        }
+        if (h) {
+            *h = surface->h;
+        }
+        return 0;
+    } else {
+        SDL_SetError("Software renderer doesn't have an output surface");
+        return -1;
+    }
+}
+
+static int
+SW_CreateTexture(SDL_Renderer * renderer, SDL_Texture * texture)
+{
+    int bpp;
+    Uint32 Rmask, Gmask, Bmask, Amask;
+
+    if (!SDL_PixelFormatEnumToMasks
+        (texture->format, &bpp, &Rmask, &Gmask, &Bmask, &Amask)) {
+        return SDL_SetError("Unknown texture format");
+    }
+
+    texture->driverdata =
+        SDL_CreateRGBSurface(0, texture->w, texture->h, bpp, Rmask, Gmask,
+                             Bmask, Amask);
+    SDL_SetSurfaceColorMod(texture->driverdata, texture->r, texture->g,
+                           texture->b);
+    SDL_SetSurfaceAlphaMod(texture->driverdata, texture->a);
+    SDL_SetSurfaceBlendMode(texture->driverdata, texture->blendMode);
+
+    if (texture->access == SDL_TEXTUREACCESS_STATIC) {
+        SDL_SetSurfaceRLE(texture->driverdata, 1);
+    }
+
+    if (!texture->driverdata) {
+        return -1;
+    }
+    return 0;
+}
+
+static int
+SW_SetTextureColorMod(SDL_Renderer * renderer, SDL_Texture * texture)
+{
+    SDL_Surface *surface = (SDL_Surface *) texture->driverdata;
+    return SDL_SetSurfaceColorMod(surface, texture->r, texture->g,
+                                  texture->b);
+}
+
+static int
+SW_SetTextureAlphaMod(SDL_Renderer * renderer, SDL_Texture * texture)
+{
+    SDL_Surface *surface = (SDL_Surface *) texture->driverdata;
+    return SDL_SetSurfaceAlphaMod(surface, texture->a);
+}
+
+static int
+SW_SetTextureBlendMode(SDL_Renderer * renderer, SDL_Texture * texture)
+{
+    SDL_Surface *surface = (SDL_Surface *) texture->driverdata;
+    return SDL_SetSurfaceBlendMode(surface, texture->blendMode);
+}
+
+static int
+SW_UpdateTexture(SDL_Renderer * renderer, SDL_Texture * texture,
+                 const SDL_Rect * rect, const void *pixels, int pitch)
+{
+    SDL_Surface *surface = (SDL_Surface *) texture->driverdata;
+    Uint8 *src, *dst;
+    int row;
+    size_t length;
+
+    if(SDL_MUSTLOCK(surface))
+        SDL_LockSurface(surface);
+    src = (Uint8 *) pixels;
+    dst = (Uint8 *) surface->pixels +
+                        rect->y * surface->pitch +
+                        rect->x * surface->format->BytesPerPixel;
+    length = rect->w * surface->format->BytesPerPixel;
+    for (row = 0; row < rect->h; ++row) {
+        SDL_memcpy(dst, src, length);
+        src += pitch;
+        dst += surface->pitch;
+    }
+    if(SDL_MUSTLOCK(surface))
+        SDL_UnlockSurface(surface);
+    return 0;
+}
+
+static int
+SW_LockTexture(SDL_Renderer * renderer, SDL_Texture * texture,
+               const SDL_Rect * rect, void **pixels, int *pitch)
+{
+    SDL_Surface *surface = (SDL_Surface *) texture->driverdata;
+
+    *pixels =
+        (void *) ((Uint8 *) surface->pixels + rect->y * surface->pitch +
+                  rect->x * surface->format->BytesPerPixel);
+    *pitch = surface->pitch;
+    return 0;
+}
+
+static void
+SW_UnlockTexture(SDL_Renderer * renderer, SDL_Texture * texture)
+{
+}
+
+static int
+SW_SetRenderTarget(SDL_Renderer * renderer, SDL_Texture * texture)
+{
+    SW_RenderData *data = (SW_RenderData *) renderer->driverdata;
+
+    if (texture ) {
+        data->surface = (SDL_Surface *) texture->driverdata;
+    } else {
+        data->surface = data->window;
+    }
+    return 0;
+}
+
+static int
+SW_UpdateViewport(SDL_Renderer * renderer)
+{
+    SW_RenderData *data = (SW_RenderData *) renderer->driverdata;
+    SDL_Surface *surface = data->surface;
+
+    if (!surface) {
+        /* We'll update the viewport after we recreate the surface */
+        return 0;
+    }
+
+    SDL_SetClipRect(data->surface, &renderer->viewport);
+    return 0;
+}
+
+static int
+SW_UpdateClipRect(SDL_Renderer * renderer)
+{
+    SW_RenderData *data = (SW_RenderData *) renderer->driverdata;
+    SDL_Surface *surface = data->surface;
+    if (surface) {
+        if (renderer->clipping_enabled) {
+            SDL_SetClipRect(surface, &renderer->clip_rect);
+        } else {
+            SDL_SetClipRect(surface, NULL);
+        }
+    }
+    return 0;
+}
+
+static int
+SW_RenderClear(SDL_Renderer * renderer)
+{
+    SDL_Surface *surface = SW_ActivateRenderer(renderer);
+    Uint32 color;
+    SDL_Rect clip_rect;
+
+    if (!surface) {
+        return -1;
+    }
+
+    color = SDL_MapRGBA(surface->format,
+                        renderer->r, renderer->g, renderer->b, renderer->a);
+
+    /* By definition the clear ignores the clip rect */
+    clip_rect = surface->clip_rect;
+    SDL_SetClipRect(surface, NULL);
+    SDL_FillRect(surface, NULL, color);
+    SDL_SetClipRect(surface, &clip_rect);
+    return 0;
+}
+
+static int
+SW_RenderDrawPoints(SDL_Renderer * renderer, const SDL_FPoint * points,
+                    int count)
+{
+    SDL_Surface *surface = SW_ActivateRenderer(renderer);
+    SDL_Point *final_points;
+    int i, status;
+
+    if (!surface) {
+        return -1;
+    }
+
+    final_points = SDL_stack_alloc(SDL_Point, count);
+    if (!final_points) {
+        return SDL_OutOfMemory();
+    }
+    if (renderer->viewport.x || renderer->viewport.y) {
+        int x = renderer->viewport.x;
+        int y = renderer->viewport.y;
+
+        for (i = 0; i < count; ++i) {
+            final_points[i].x = (int)(x + points[i].x);
+            final_points[i].y = (int)(y + points[i].y);
+        }
+    } else {
+        for (i = 0; i < count; ++i) {
+            final_points[i].x = (int)points[i].x;
+            final_points[i].y = (int)points[i].y;
+        }
+    }
+
+    /* Draw the points! */
+    if (renderer->blendMode == SDL_BLENDMODE_NONE) {
+        Uint32 color = SDL_MapRGBA(surface->format,
+                                   renderer->r, renderer->g, renderer->b,
+                                   renderer->a);
+
+        status = SDL_DrawPoints(surface, final_points, count, color);
+    } else {
+        status = SDL_BlendPoints(surface, final_points, count,
+                                renderer->blendMode,
+                                renderer->r, renderer->g, renderer->b,
+                                renderer->a);
+    }
+    SDL_stack_free(final_points);
+
+    return status;
+}
+
+static int
+SW_RenderDrawLines(SDL_Renderer * renderer, const SDL_FPoint * points,
+                   int count)
+{
+    SDL_Surface *surface = SW_ActivateRenderer(renderer);
+    SDL_Point *final_points;
+    int i, status;
+
+    if (!surface) {
+        return -1;
+    }
+
+    final_points = SDL_stack_alloc(SDL_Point, count);
+    if (!final_points) {
+        return SDL_OutOfMemory();
+    }
+    if (renderer->viewport.x || renderer->viewport.y) {
+        int x = renderer->viewport.x;
+        int y = renderer->viewport.y;
+
+        for (i = 0; i < count; ++i) {
+            final_points[i].x = (int)(x + points[i].x);
+            final_points[i].y = (int)(y + points[i].y);
+        }
+    } else {
+        for (i = 0; i < count; ++i) {
+            final_points[i].x = (int)points[i].x;
+            final_points[i].y = (int)points[i].y;
+        }
+    }
+
+    /* Draw the lines! */
+    if (renderer->blendMode == SDL_BLENDMODE_NONE) {
+        Uint32 color = SDL_MapRGBA(surface->format,
+                                   renderer->r, renderer->g, renderer->b,
+                                   renderer->a);
+
+        status = SDL_DrawLines(surface, final_points, count, color);
+    } else {
+        status = SDL_BlendLines(surface, final_points, count,
+                                renderer->blendMode,
+                                renderer->r, renderer->g, renderer->b,
+                                renderer->a);
+    }
+    SDL_stack_free(final_points);
+
+    return status;
+}
+
+static int
+SW_RenderFillRects(SDL_Renderer * renderer, const SDL_FRect * rects, int count)
+{
+    SDL_Surface *surface = SW_ActivateRenderer(renderer);
+    SDL_Rect *final_rects;
+    int i, status;
+
+    if (!surface) {
+        return -1;
+    }
+
+    final_rects = SDL_stack_alloc(SDL_Rect, count);
+    if (!final_rects) {
+        return SDL_OutOfMemory();
+    }
+    if (renderer->viewport.x || renderer->viewport.y) {
+        int x = renderer->viewport.x;
+        int y = renderer->viewport.y;
+
+        for (i = 0; i < count; ++i) {
+            final_rects[i].x = (int)(x + rects[i].x);
+            final_rects[i].y = (int)(y + rects[i].y);
+            final_rects[i].w = SDL_max((int)rects[i].w, 1);
+            final_rects[i].h = SDL_max((int)rects[i].h, 1);
+        }
+    } else {
+        for (i = 0; i < count; ++i) {
+            final_rects[i].x = (int)rects[i].x;
+            final_rects[i].y = (int)rects[i].y;
+            final_rects[i].w = SDL_max((int)rects[i].w, 1);
+            final_rects[i].h = SDL_max((int)rects[i].h, 1);
+        }
+    }
+
+    if (renderer->blendMode == SDL_BLENDMODE_NONE) {
+        Uint32 color = SDL_MapRGBA(surface->format,
+                                   renderer->r, renderer->g, renderer->b,
+                                   renderer->a);
+        status = SDL_FillRects(surface, final_rects, count, color);
+    } else {
+        status = SDL_BlendFillRects(surface, final_rects, count,
+                                    renderer->blendMode,
+                                    renderer->r, renderer->g, renderer->b,
+                                    renderer->a);
+    }
+    SDL_stack_free(final_rects);
+
+    return status;
+}
+
+static int
+SW_RenderCopy(SDL_Renderer * renderer, SDL_Texture * texture,
+              const SDL_Rect * srcrect, const SDL_FRect * dstrect)
+{
+    SDL_Surface *surface = SW_ActivateRenderer(renderer);
+    SDL_Surface *src = (SDL_Surface *) texture->driverdata;
+    SDL_Rect final_rect;
+
+    if (!surface) {
+        return -1;
+    }
+
+    if (renderer->viewport.x || renderer->viewport.y) {
+        final_rect.x = (int)(renderer->viewport.x + dstrect->x);
+        final_rect.y = (int)(renderer->viewport.y + dstrect->y);
+    } else {
+        final_rect.x = (int)dstrect->x;
+        final_rect.y = (int)dstrect->y;
+    }
+    final_rect.w = (int)dstrect->w;
+    final_rect.h = (int)dstrect->h;
+
+    if ( srcrect->w == final_rect.w && srcrect->h == final_rect.h ) {
+        return SDL_BlitSurface(src, srcrect, surface, &final_rect);
+    } else {
+        return SDL_BlitScaled(src, srcrect, surface, &final_rect);
+    }
+}
+
+static int
+GetScaleQuality(void)
+{
+    const char *hint = SDL_GetHint(SDL_HINT_RENDER_SCALE_QUALITY);
+
+    if (!hint || *hint == '0' || SDL_strcasecmp(hint, "nearest") == 0) {
+        return 0;
+    } else {
+        return 1;
+    }
+}
+
+static int
+SW_RenderCopyEx(SDL_Renderer * renderer, SDL_Texture * texture,
+                const SDL_Rect * srcrect, const SDL_FRect * dstrect,
+                const double angle, const SDL_FPoint * center, const SDL_RendererFlip flip)
+{
+    SDL_Surface *surface = SW_ActivateRenderer(renderer);
+    SDL_Surface *src = (SDL_Surface *) texture->driverdata;
+    SDL_Rect final_rect, tmp_rect;
+    SDL_Surface *surface_rotated, *surface_scaled;
+    Uint32 colorkey;
+    int retval, dstwidth, dstheight, abscenterx, abscentery;
+    double cangle, sangle, px, py, p1x, p1y, p2x, p2y, p3x, p3y, p4x, p4y;
+
+    if (!surface) {
+        return -1;
+    }
+
+    if (renderer->viewport.x || renderer->viewport.y) {
+        final_rect.x = (int)(renderer->viewport.x + dstrect->x);
+        final_rect.y = (int)(renderer->viewport.y + dstrect->y);
+    } else {
+        final_rect.x = (int)dstrect->x;
+        final_rect.y = (int)dstrect->y;
+    }
+    final_rect.w = (int)dstrect->w;
+    final_rect.h = (int)dstrect->h;
+
+    surface_scaled = SDL_CreateRGBSurface(SDL_SWSURFACE, final_rect.w, final_rect.h, src->format->BitsPerPixel,
+                                          src->format->Rmask, src->format->Gmask,
+                                          src->format->Bmask, src->format->Amask );
+    if (surface_scaled) {
+        SDL_GetColorKey(src, &colorkey);
+        SDL_SetColorKey(surface_scaled, SDL_TRUE, colorkey);
+        tmp_rect = final_rect;
+        tmp_rect.x = 0;
+        tmp_rect.y = 0;
+
+        retval = SDL_BlitScaled(src, srcrect, surface_scaled, &tmp_rect);
+        if (!retval) {
+            SDLgfx_rotozoomSurfaceSizeTrig(tmp_rect.w, tmp_rect.h, -angle, &dstwidth, &dstheight, &cangle, &sangle);
+            surface_rotated = SDLgfx_rotateSurface(surface_scaled, -angle, dstwidth/2, dstheight/2, GetScaleQuality(), flip & SDL_FLIP_HORIZONTAL, flip & SDL_FLIP_VERTICAL, dstwidth, dstheight, cangle, sangle);
+            if(surface_rotated) {
+                /* Find out where the new origin is by rotating the four final_rect points around the center and then taking the extremes */
+                abscenterx = final_rect.x + (int)center->x;
+                abscentery = final_rect.y + (int)center->y;
+                /* Compensate the angle inversion to match the behaviour of the other backends */
+                sangle = -sangle;
+
+                /* Top Left */
+                px = final_rect.x - abscenterx;
+                py = final_rect.y - abscentery;
+                p1x = px * cangle - py * sangle + abscenterx;
+                p1y = px * sangle + py * cangle + abscentery;
+
+                /* Top Right */
+                px = final_rect.x + final_rect.w - abscenterx;
+                py = final_rect.y - abscentery;
+                p2x = px * cangle - py * sangle + abscenterx;
+                p2y = px * sangle + py * cangle + abscentery;
+
+                /* Bottom Left */
+                px = final_rect.x - abscenterx;
+                py = final_rect.y + final_rect.h - abscentery;
+                p3x = px * cangle - py * sangle + abscenterx;
+                p3y = px * sangle + py * cangle + abscentery;
+
+                /* Bottom Right */
+                px = final_rect.x + final_rect.w - abscenterx;
+                py = final_rect.y + final_rect.h - abscentery;
+                p4x = px * cangle - py * sangle + abscenterx;
+                p4y = px * sangle + py * cangle + abscentery;
+
+                tmp_rect.x = (int)MIN(MIN(p1x, p2x), MIN(p3x, p4x));
+                tmp_rect.y = (int)MIN(MIN(p1y, p2y), MIN(p3y, p4y));
+                tmp_rect.w = dstwidth;
+                tmp_rect.h = dstheight;
+
+                retval = SDL_BlitSurface(surface_rotated, NULL, surface, &tmp_rect);
+                SDL_FreeSurface(surface_scaled);
+                SDL_FreeSurface(surface_rotated);
+                return retval;
+            }
+        }
+        return retval;
+    }
+
+    return -1;
+}
+
+static int
+SW_RenderReadPixels(SDL_Renderer * renderer, const SDL_Rect * rect,
+                    Uint32 format, void * pixels, int pitch)
+{
+    SDL_Surface *surface = SW_ActivateRenderer(renderer);
+    Uint32 src_format;
+    void *src_pixels;
+    SDL_Rect final_rect;
+
+    if (!surface) {
+        return -1;
+    }
+
+    if (renderer->viewport.x || renderer->viewport.y) {
+        final_rect.x = renderer->viewport.x + rect->x;
+        final_rect.y = renderer->viewport.y + rect->y;
+        final_rect.w = rect->w;
+        final_rect.h = rect->h;
+        rect = &final_rect;
+    }
+
+    if (rect->x < 0 || rect->x+rect->w > surface->w ||
+        rect->y < 0 || rect->y+rect->h > surface->h) {
+        return SDL_SetError("Tried to read outside of surface bounds");
+    }
+
+    src_format = surface->format->format;
+    src_pixels = (void*)((Uint8 *) surface->pixels +
+                    rect->y * surface->pitch +
+                    rect->x * surface->format->BytesPerPixel);
+
+    return SDL_ConvertPixels(rect->w, rect->h,
+                             src_format, src_pixels, surface->pitch,
+                             format, pixels, pitch);
+}
+
+static void
+SW_RenderPresent(SDL_Renderer * renderer)
+{
+    SDL_Window *window = renderer->window;
+
+    if (window) {
+        SDL_UpdateWindowSurface(window);
+    }
+}
+
+static void
+SW_DestroyTexture(SDL_Renderer * renderer, SDL_Texture * texture)
+{
+    SDL_Surface *surface = (SDL_Surface *) texture->driverdata;
+
+    SDL_FreeSurface(surface);
+}
+
+static void
+SW_DestroyRenderer(SDL_Renderer * renderer)
+{
+    SW_RenderData *data = (SW_RenderData *) renderer->driverdata;
+
+    SDL_free(data);
+    SDL_free(renderer);
+}
+
+#endif /* !SDL_RENDER_DISABLED */
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_render_sw_c.h

@@ -0,0 +1,24 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+
+extern SDL_Renderer * SW_CreateRendererForSurface(SDL_Surface * surface);
+
+/* vi: set ts=4 sw=4 expandtab: */

src/render/software/SDL_rotate.c

@@ -0,0 +1,501 @@
+/*
+
+SDL_rotate.c: rotates 32bit or 8bit surfaces
+
+Shamelessly stolen from SDL_gfx by Andreas Schiffler. Original copyright follows:
+
+Copyright (C) 2001-2011  Andreas Schiffler
+
+This software is provided 'as-is', without any express or implied
+warranty. In no event will the authors be held liable for any damages
+arising from the use of this software.
+
+Permission is granted to anyone to use this software for any purpose,
+including commercial applications, and to alter it and redistribute it
+freely, subject to the following restrictions:
+
+   1. The origin of this software must not be misrepresented; you must not
+   claim that you wrote the original software. If you use this software
+   in a product, an acknowledgment in the product documentation would be
+   appreciated but is not required.
+
+   2. Altered source versions must be plainly marked as such, and must not be
+   misrepresented as being the original software.
+
+   3. This notice may not be removed or altered from any source
+   distribution.
+
+Andreas Schiffler -- aschiffler at ferzkopp dot net
+
+*/
+#include "../../SDL_internal.h"
+
+#if defined(__WIN32__)
+#include "../../core/windows/SDL_windows.h"
+#endif
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "SDL.h"
+#include "SDL_rotate.h"
+
+/* ---- Internally used structures */
+
+/* !
+\brief A 32 bit RGBA pixel.
+*/
+typedef struct tColorRGBA {
+    Uint8 r;
+    Uint8 g;
+    Uint8 b;
+    Uint8 a;
+} tColorRGBA;
+
+/* !
+\brief A 8bit Y/palette pixel.
+*/
+typedef struct tColorY {
+    Uint8 y;
+} tColorY;
+
+/* !
+\brief Returns maximum of two numbers a and b.
+*/
+#define MAX(a,b)    (((a) > (b)) ? (a) : (b))
+
+/* !
+\brief Number of guard rows added to destination surfaces.
+
+This is a simple but effective workaround for observed issues.
+These rows allocate extra memory and are then hidden from the surface.
+Rows are added to the end of destination surfaces when they are allocated.
+This catches any potential overflows which seem to happen with
+just the right src image dimensions and scale/rotation and can lead
+to a situation where the program can segfault.
+*/
+#define GUARD_ROWS (2)
+
+/* !
+\brief Lower limit of absolute zoom factor or rotation degrees.
+*/
+#define VALUE_LIMIT 0.001
+
+/* !
+\brief Returns colorkey info for a surface
+*/
+static Uint32
+_colorkey(SDL_Surface *src)
+{
+    Uint32 key = 0;
+    SDL_GetColorKey(src, &key);
+    return key;
+}
+
+
+/* !
+\brief Internal target surface sizing function for rotations with trig result return.
+
+\param width The source surface width.
+\param height The source surface height.
+\param angle The angle to rotate in degrees.
+\param dstwidth The calculated width of the destination surface.
+\param dstheight The calculated height of the destination surface.
+\param cangle The sine of the angle
+\param sangle The cosine of the angle
+
+*/
+void
+SDLgfx_rotozoomSurfaceSizeTrig(int width, int height, double angle,
+                               int *dstwidth, int *dstheight,
+                               double *cangle, double *sangle)
+{
+    double x, y, cx, cy, sx, sy;
+    double radangle;
+    int dstwidthhalf, dstheighthalf;
+
+    /*
+    * Determine destination width and height by rotating a centered source box
+    */
+    radangle = angle * (M_PI / 180.0);
+    *sangle = SDL_sin(radangle);
+    *cangle = SDL_cos(radangle);
+    x = (double)(width / 2);
+    y = (double)(height / 2);
+    cx = *cangle * x;
+    cy = *cangle * y;
+    sx = *sangle * x;
+    sy = *sangle * y;
+
+    dstwidthhalf = MAX((int)
+        SDL_ceil(MAX(MAX(MAX(SDL_fabs(cx + sy), SDL_fabs(cx - sy)), SDL_fabs(-cx + sy)), SDL_fabs(-cx - sy))), 1);
+    dstheighthalf = MAX((int)
+        SDL_ceil(MAX(MAX(MAX(SDL_fabs(sx + cy), SDL_fabs(sx - cy)), SDL_fabs(-sx + cy)), SDL_fabs(-sx - cy))), 1);
+    *dstwidth = 2 * dstwidthhalf;
+    *dstheight = 2 * dstheighthalf;
+}
+
+
+/* !
+\brief Internal 32 bit rotozoomer with optional anti-aliasing.
+
+Rotates and zooms 32 bit RGBA/ABGR 'src' surface to 'dst' surface based on the control
+parameters by scanning the destination surface and applying optionally anti-aliasing
+by bilinear interpolation.
+Assumes src and dst surfaces are of 32 bit depth.
+Assumes dst surface was allocated with the correct dimensions.
+
+\param src Source surface.
+\param dst Destination surface.
+\param cx Horizontal center coordinate.
+\param cy Vertical center coordinate.
+\param isin Integer version of sine of angle.
+\param icos Integer version of cosine of angle.
+\param flipx Flag indicating horizontal mirroring should be applied.
+\param flipy Flag indicating vertical mirroring should be applied.
+\param smooth Flag indicating anti-aliasing should be used.
+*/
+static void
+_transformSurfaceRGBA(SDL_Surface * src, SDL_Surface * dst, int cx, int cy, int isin, int icos, int flipx, int flipy, int smooth)
+{
+    int x, y, t1, t2, dx, dy, xd, yd, sdx, sdy, ax, ay, ex, ey, sw, sh;
+    tColorRGBA c00, c01, c10, c11, cswap;
+    tColorRGBA *pc, *sp;
+    int gap;
+
+    /*
+    * Variable setup
+    */
+    xd = ((src->w - dst->w) << 15);
+    yd = ((src->h - dst->h) << 15);
+    ax = (cx << 16) - (icos * cx);
+    ay = (cy << 16) - (isin * cx);
+    sw = src->w - 1;
+    sh = src->h - 1;
+    pc = (tColorRGBA*) dst->pixels;
+    gap = dst->pitch - dst->w * 4;
+
+    /*
+    * Switch between interpolating and non-interpolating code
+    */
+    if (smooth) {
+        for (y = 0; y < dst->h; y++) {
+            dy = cy - y;
+            sdx = (ax + (isin * dy)) + xd;
+            sdy = (ay - (icos * dy)) + yd;
+            for (x = 0; x < dst->w; x++) {
+                dx = (sdx >> 16);
+                dy = (sdy >> 16);
+                if (flipx) dx = sw - dx;
+                if (flipy) dy = sh - dy;
+                if ((dx > -1) && (dy > -1) && (dx < (src->w-1)) && (dy < (src->h-1))) {
+                    sp = (tColorRGBA *)src->pixels;
+                    sp += ((src->pitch/4) * dy);
+                    sp += dx;
+                    c00 = *sp;
+                    sp += 1;
+                    c01 = *sp;
+                    sp += (src->pitch/4);
+                    c11 = *sp;
+                    sp -= 1;
+                    c10 = *sp;
+                    if (flipx) {
+                        cswap = c00; c00=c01; c01=cswap;
+                        cswap = c10; c10=c11; c11=cswap;
+                    }
+                    if (flipy) {
+                        cswap = c00; c00=c10; c10=cswap;
+                        cswap = c01; c01=c11; c11=cswap;
+                    }
+                    /*
+                    * Interpolate colors
+                    */
+                    ex = (sdx & 0xffff);
+                    ey = (sdy & 0xffff);
+                    t1 = ((((c01.r - c00.r) * ex) >> 16) + c00.r) & 0xff;
+                    t2 = ((((c11.r - c10.r) * ex) >> 16) + c10.r) & 0xff;
+                    pc->r = (((t2 - t1) * ey) >> 16) + t1;
+                    t1 = ((((c01.g - c00.g) * ex) >> 16) + c00.g) & 0xff;
+                    t2 = ((((c11.g - c10.g) * ex) >> 16) + c10.g) & 0xff;
+                    pc->g = (((t2 - t1) * ey) >> 16) + t1;
+                    t1 = ((((c01.b - c00.b) * ex) >> 16) + c00.b) & 0xff;
+                    t2 = ((((c11.b - c10.b) * ex) >> 16) + c10.b) & 0xff;
+                    pc->b = (((t2 - t1) * ey) >> 16) + t1;
+                    t1 = ((((c01.a - c00.a) * ex) >> 16) + c00.a) & 0xff;
+                    t2 = ((((c11.a - c10.a) * ex) >> 16) + c10.a) & 0xff;
+                    pc->a = (((t2 - t1) * ey) >> 16) + t1;
+                }
+                sdx += icos;
+                sdy += isin;
+                pc++;
+            }
+            pc = (tColorRGBA *) ((Uint8 *) pc + gap);
+        }
+    } else {
+        for (y = 0; y < dst->h; y++) {
+            dy = cy - y;
+            sdx = (ax + (isin * dy)) + xd;
+            sdy = (ay - (icos * dy)) + yd;
+            for (x = 0; x < dst->w; x++) {
+                dx = (short) (sdx >> 16);
+                dy = (short) (sdy >> 16);
+                if (flipx) dx = (src->w-1)-dx;
+                if (flipy) dy = (src->h-1)-dy;
+                if ((dx >= 0) && (dy >= 0) && (dx < src->w) && (dy < src->h)) {
+                    sp = (tColorRGBA *) ((Uint8 *) src->pixels + src->pitch * dy);
+                    sp += dx;
+                    *pc = *sp;
+                }
+                sdx += icos;
+                sdy += isin;
+                pc++;
+            }
+            pc = (tColorRGBA *) ((Uint8 *) pc + gap);
+        }
+    }
+}
+
+/* !
+
+\brief Rotates and zooms 8 bit palette/Y 'src' surface to 'dst' surface without smoothing.
+
+Rotates and zooms 8 bit RGBA/ABGR 'src' surface to 'dst' surface based on the control
+parameters by scanning the destination surface.
+Assumes src and dst surfaces are of 8 bit depth.
+Assumes dst surface was allocated with the correct dimensions.
+
+\param src Source surface.
+\param dst Destination surface.
+\param cx Horizontal center coordinate.
+\param cy Vertical center coordinate.
+\param isin Integer version of sine of angle.
+\param icos Integer version of cosine of angle.
+\param flipx Flag indicating horizontal mirroring should be applied.
+\param flipy Flag indicating vertical mirroring should be applied.
+*/
+static void
+transformSurfaceY(SDL_Surface * src, SDL_Surface * dst, int cx, int cy, int isin, int icos, int flipx, int flipy)
+{
+    int x, y, dx, dy, xd, yd, sdx, sdy, ax, ay;
+    tColorY *pc, *sp;
+    int gap;
+
+    /*
+    * Variable setup
+    */
+    xd = ((src->w - dst->w) << 15);
+    yd = ((src->h - dst->h) << 15);
+    ax = (cx << 16) - (icos * cx);
+    ay = (cy << 16) - (isin * cx);
+    pc = (tColorY*) dst->pixels;
+    gap = dst->pitch - dst->w;
+    /*
+    * Clear surface to colorkey
+    */
+    SDL_memset(pc, (int)(_colorkey(src) & 0xff), dst->pitch * dst->h);
+    /*
+    * Iterate through destination surface
+    */
+    for (y = 0; y < dst->h; y++) {
+        dy = cy - y;
+        sdx = (ax + (isin * dy)) + xd;
+        sdy = (ay - (icos * dy)) + yd;
+        for (x = 0; x < dst->w; x++) {
+            dx = (short) (sdx >> 16);
+            dy = (short) (sdy >> 16);
+            if (flipx) dx = (src->w-1)-dx;
+            if (flipy) dy = (src->h-1)-dy;
+            if ((dx >= 0) && (dy >= 0) && (dx < src->w) && (dy < src->h)) {
+                sp = (tColorY *) (src->pixels);
+                sp += (src->pitch * dy + dx);
+                *pc = *sp;
+            }
+            sdx += icos;
+            sdy += isin;
+            pc++;
+        }
+        pc += gap;
+    }
+}
+
+
+/* !
+\brief Rotates and zooms a surface with different horizontal and vertival scaling factors and optional anti-aliasing.
+
+Rotates a 32bit or 8bit 'src' surface to newly created 'dst' surface.
+'angle' is the rotation in degrees, 'centerx' and 'centery' the rotation center. If 'smooth' is set
+then the destination 32bit surface is anti-aliased. If the surface is not 8bit
+or 32bit RGBA/ABGR it will be converted into a 32bit RGBA format on the fly.
+
+\param src The surface to rotozoom.
+\param angle The angle to rotate in degrees.
+\param centerx The horizontal coordinate of the center of rotation
+\param zoomy The vertical coordinate of the center of rotation
+\param smooth Antialiasing flag; set to SMOOTHING_ON to enable.
+\param flipx Set to 1 to flip the image horizontally
+\param flipy Set to 1 to flip the image vertically
+\param dstwidth The destination surface width
+\param dstheight The destination surface height
+\param cangle The angle cosine
+\param sangle The angle sine
+\return The new rotated surface.
+
+*/
+
+SDL_Surface *
+SDLgfx_rotateSurface(SDL_Surface * src, double angle, int centerx, int centery, int smooth, int flipx, int flipy, int dstwidth, int dstheight, double cangle, double sangle)
+{
+    SDL_Surface *rz_src;
+    SDL_Surface *rz_dst;
+    int is32bit;
+    int i, src_converted;
+    Uint8 r,g,b;
+    Uint32 colorkey = 0;
+    int colorKeyAvailable = 0;
+    double sangleinv, cangleinv;
+
+    /*
+    * Sanity check
+    */
+    if (src == NULL)
+        return (NULL);
+
+    if (src->flags & SDL_TRUE/* SDL_SRCCOLORKEY */)
+    {
+        colorkey = _colorkey(src);
+        SDL_GetRGB(colorkey, src->format, &r, &g, &b);
+        colorKeyAvailable = 1;
+    }
+    /*
+    * Determine if source surface is 32bit or 8bit
+    */
+    is32bit = (src->format->BitsPerPixel == 32);
+    if ((is32bit) || (src->format->BitsPerPixel == 8)) {
+        /*
+        * Use source surface 'as is'
+        */
+        rz_src = src;
+        src_converted = 0;
+    } else {
+        /*
+        * New source surface is 32bit with a defined RGBA ordering
+        */
+        rz_src =
+            SDL_CreateRGBSurface(SDL_SWSURFACE, src->w, src->h, 32,
+#if SDL_BYTEORDER == SDL_LIL_ENDIAN
+            0x000000ff, 0x0000ff00, 0x00ff0000, 0xff000000
+#else
+            0xff000000,  0x00ff0000, 0x0000ff00, 0x000000ff
+#endif
+            );
+        if(colorKeyAvailable)
+            SDL_SetColorKey(src, 0, 0);
+
+        SDL_BlitSurface(src, NULL, rz_src, NULL);
+
+        if(colorKeyAvailable)
+            SDL_SetColorKey(src, SDL_TRUE /* SDL_SRCCOLORKEY */, colorkey);
+        src_converted = 1;
+        is32bit = 1;
+    }
+
+
+    /* Determine target size */
+    /* _rotozoomSurfaceSizeTrig(rz_src->w, rz_src->h, angle, &dstwidth, &dstheight, &cangle, &sangle); */
+
+    /*
+    * Calculate target factors from sin/cos and zoom
+    */
+    sangleinv = sangle*65536.0;
+    cangleinv = cangle*65536.0;
+
+    /*
+    * Alloc space to completely contain the rotated surface
+    */
+    rz_dst = NULL;
+    if (is32bit) {
+        /*
+        * Target surface is 32bit with source RGBA/ABGR ordering
+        */
+        rz_dst =
+            SDL_CreateRGBSurface(SDL_SWSURFACE, dstwidth, dstheight + GUARD_ROWS, 32,
+            rz_src->format->Rmask, rz_src->format->Gmask,
+            rz_src->format->Bmask, rz_src->format->Amask);
+    } else {
+        /*
+        * Target surface is 8bit
+        */
+        rz_dst = SDL_CreateRGBSurface(SDL_SWSURFACE, dstwidth, dstheight + GUARD_ROWS, 8, 0, 0, 0, 0);
+    }
+
+    /* Check target */
+    if (rz_dst == NULL)
+        return NULL;
+
+    /* Adjust for guard rows */
+    rz_dst->h = dstheight;
+
+    if (colorKeyAvailable == 1){
+        colorkey = SDL_MapRGB(rz_dst->format, r, g, b);
+
+        SDL_FillRect(rz_dst, NULL, colorkey );
+    }
+
+    /*
+    * Lock source surface
+    */
+    if (SDL_MUSTLOCK(rz_src)) {
+        SDL_LockSurface(rz_src);
+    }
+
+    /*
+    * Check which kind of surface we have
+    */
+    if (is32bit) {
+        /*
+        * Call the 32bit transformation routine to do the rotation (using alpha)
+        */
+        _transformSurfaceRGBA(rz_src, rz_dst, centerx, centery,
+            (int) (sangleinv), (int) (cangleinv),
+            flipx, flipy,
+            smooth);
+        /*
+        * Turn on source-alpha support
+        */
+        /* SDL_SetAlpha(rz_dst, SDL_SRCALPHA, 255); */
+        SDL_SetColorKey(rz_dst, /* SDL_SRCCOLORKEY */ SDL_TRUE | SDL_RLEACCEL, _colorkey(rz_src));
+    } else {
+        /*
+        * Copy palette and colorkey info
+        */
+        for (i = 0; i < rz_src->format->palette->ncolors; i++) {
+            rz_dst->format->palette->colors[i] = rz_src->format->palette->colors[i];
+        }
+        rz_dst->format->palette->ncolors = rz_src->format->palette->ncolors;
+        /*
+        * Call the 8bit transformation routine to do the rotation
+        */
+        transformSurfaceY(rz_src, rz_dst, centerx, centery,
+            (int) (sangleinv), (int) (cangleinv),
+            flipx, flipy);
+        SDL_SetColorKey(rz_dst, /* SDL_SRCCOLORKEY */ SDL_TRUE | SDL_RLEACCEL, _colorkey(rz_src));
+    }
+    /*
+    * Unlock source surface
+    */
+    if (SDL_MUSTLOCK(rz_src)) {
+        SDL_UnlockSurface(rz_src);
+    }
+
+    /*
+    * Cleanup temp surface
+    */
+    if (src_converted) {
+        SDL_FreeSurface(rz_src);
+    }
+
+    /*
+    * Return destination surface
+    */
+    return (rz_dst);
+}

src/render/software/SDL_rotate.h

@@ -0,0 +1,28 @@
+/*
+  Simple DirectMedia Layer
+  Copyright (C) 1997-2014 Sam Lantinga <slouken@libsdl.org>
+
+  This software is provided 'as-is', without any express or implied
+  warranty.  In no event will the authors be held liable for any damages
+  arising from the use of this software.
+
+  Permission is granted to anyone to use this software for any purpose,
+  including commercial applications, and to alter it and redistribute it
+  freely, subject to the following restrictions:
+
+  1. The origin of this software must not be misrepresented; you must not
+     claim that you wrote the original software. If you use this software
+     in a product, an acknowledgment in the product documentation would be
+     appreciated but is not required.
+  2. Altered source versions must be plainly marked as such, and must not be
+     misrepresented as being the original software.
+  3. This notice may not be removed or altered from any source distribution.
+*/
+
+#ifndef MIN
+#define MIN(a,b)    (((a) < (b)) ? (a) : (b))
+#endif
+
+extern SDL_Surface *SDLgfx_rotateSurface(SDL_Surface * src, double angle, int centerx, int centery, int smooth, int flipx, int flipy, int dstwidth, int dstheight, double cangle, double sangle);
+extern void SDLgfx_rotozoomSurfaceSizeTrig(int width, int height, double angle, int *dstwidth, int *dstheight, double *cangle, double *sangle);
+