mirror of
https://github.com/Nexoniarz/Finch.git
synced 2026-11-03 00:44:27 +00:00
04f1f94a21- comparisons of vectors give masks (boolxN): select(m, a, b), m.any/all/count, & | ^ !;
f32x8(list, i, fill) and v.store_part(list, i) for the end of a list (masked load/store)
- v.shuffle(constant lanes), v.lo(), v.hi(), concat(a, b), table.lookup(indices):
pshufb / vpshufb on x86 (SSSE3 and up), tbl on ARM64 (checked in the assembly, LLVM 18 and 21)
- acc.dot_add(a, b): i32 lanes gain 4 byte products each, exactly; vpdpbusd with AVX-VNNI or AVX-512 VNNI,
usdot/sdot/udot on ARM64, the sum written out elsewhere (pmaddwd); run here with all three paths agreeing
- @cpu("avx2,fma") fn: LLVM target-features for one function (+evex512 for AVX-512, which LLVM 18+ needs);
cpu_has("avx2"): CPUID + XGETBV on x86, hwcaps on Linux ARM64, sysctl on macOS; a wide vector can't be passed
between functions with different @cpu (its registers differ), and the compiler says so
- the compiler asks clang which features --cpu means (its predefined macros, cached), so dot_add picks the instruction
- Nix's clang wrapper dropped -march=native in nix-shell (reproduced): finch tells it NIX_ENFORCE_NO_NATIVE=0, shell.nix too,
and warns if --cpu native still made no difference
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Psc42moPLwP43Cmb9oZqSR
9 lines
605 B
Text
9 lines
605 B
Text
boolx8(false, false, false, true, true, true, false, true) 4 true false true
|
|
f32x8(0, 0, 0, 1, 2, 3, 0, 5) f32x8(-2, -1, 0, -1, -1, -1, -4, -1)
|
|
boolx8(false, true, true, true, true, false, false, false) boolx8(false, false, true, false, false, false, false, true) boolx8(false, false, false, true, false, false, false, false)
|
|
i32x4(4, 5, 4, 7) true true
|
|
true i32x4(0, 1, 0, 1) f32x4(1, 0, 1, 0)
|
|
boolx4(false, true, false, true) boolx4(true, false, true, false)
|
|
78
|
|
[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
|
|
f32x8(9, 10, 11, 12, 13, -1, -1, -1) f32x8(9, 9, 9, 9, 9, 9, 9, 9) f32x8(7, 7, 7, 7, 7, 7, 7, 7)
|