mirror of
https://github.com/ghostty-org/ghostty.git
synced 2026-05-29 16:25:20 +00:00
00dfd67bee
The previous runtime_detect.zig called std.zig.system.resolveTargetQuery which pulled in the entire Zig target/CPU model table infrastructure for every architecture (~4,000 symbols, ~175 KB of data tables, ~130 KB of code). This bloated the binary by ~500 KB and shifted code layout enough to cause a measurable icache/branch-predictor regression in unrelated hot paths like the terminal parser (~20% more cycles for identical instruction counts). Replace with minimal, direct CPU feature detection per architecture: CPUID + XGETBV inline assembly on x86, sysctlbyname on Darwin AArch64, and getauxval/prctl via std.os.linux (direct syscalls, no libc) on Linux for AArch64, PPC, S390x, RISC-V, and LoongArch. Split into per-architecture files under src/detect/ for maintainability.
27 lines
621 B
Zig
27 lines
621 B
Zig
const builtin = @import("builtin");
|
|
const HwyTargets = @import("../targets.zig").Targets;
|
|
const linux = @import("linux.zig");
|
|
|
|
pub fn detect() i64 {
|
|
var t: HwyTargets = .{};
|
|
|
|
if (comptime builtin.os.tag != .linux) return @bitCast(t);
|
|
|
|
const AT_HWCAP: usize = 16;
|
|
const hwcap = linux.getauxval(AT_HWCAP);
|
|
|
|
// From Linux arch/loongarch/include/uapi/asm/hwcap.h
|
|
const HWCAP_LSX: usize = 1 << 4;
|
|
const HWCAP_LASX: usize = 1 << 5;
|
|
|
|
if (hwcap & HWCAP_LSX != 0) {
|
|
t.lsx = true;
|
|
|
|
if (hwcap & HWCAP_LASX != 0) {
|
|
t.lasx = true;
|
|
}
|
|
}
|
|
|
|
return @bitCast(t);
|
|
}
|