detect x86 avx-ne-convert (#131)

nihui · Oct 24, 2024 · 0f5e250 · 0f5e250
1 parent ea54bc5
commit 0f5e250
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -62,7 +62,7 @@ int main()
 
 |CPU|ISA|
 |:---:|---|
-|x86|`mmx` `sse` `sse2` `sse3` `ssse3` `sse41` `sse42` `sse4a` `xop` `avx` `f16c` `fma` `fma4` `avx2` `avx512f` `avx512bw` `avx512cd` `avx512dq` `avx512vl` `avx512vnni` `avx512bf16` `avx512ifma` `avx512vbmi` `avx512vbmi2` `avx512fp16` `avx512er` `avx5124fmaps` `avx5124vnniw` `avxvnni` `avxvnniint8` `avxvnniint16` `avxifma` `amxfp16` `amxbf16` `amxint8` `amxtile` `bmi1` `bmi2` `gfni` `aesni` `vaes` `sha1` `sha256` `sha512` `sm3` `sm4` `rdrand` `rdseed` `tsx`|
+|x86|`mmx` `sse` `sse2` `sse3` `ssse3` `sse41` `sse42` `sse4a` `xop` `avx` `f16c` `fma` `fma4` `avx2` `avx512f` `avx512bw` `avx512cd` `avx512dq` `avx512vl` `avx512vnni` `avx512bf16` `avx512ifma` `avx512vbmi` `avx512vbmi2` `avx512fp16` `avx512er` `avx5124fmaps` `avx5124vnniw` `avxvnni` `avxvnniint8` `avxvnniint16` `avxifma` `avxneconvert` `amxfp16` `amxbf16` `amxint8` `amxtile` `bmi1` `bmi2` `gfni` `aesni` `vaes` `sha1` `sha256` `sha512` `sm3` `sm4` `rdrand` `rdseed` `tsx`|
 |arm|`half` `edsp` `neon` `vfpv4` `idiv`|
 |aarch64|`neon` `vfpv4` `lse` `cpuid` `asimdrdm` `asimdhp` `asimddp` `asimdfhm` `bf16` `i8mm` `frint` `jscvt` `fcma` `mte` `mte2` `sve` `sve2` `svebf16` `svei8mm` `svef32mm` `svef64mm` `sme` `smef16f16` `smef64f64` `smei64i64` `pmull` `crc32` `aes` `sha1` `sha2` `sha3` `sha512` `sm3` `sm4` `svepmull` `svebitperm` `sveaes` `svesha3` `svesm4` `amx`|
 |mips|`msa` `mmi` `sx` `asx` `msa2` `crypto`|
@@ -839,4 +839,4 @@ ruapu determines whether the CPU supports certain instruction sets by trying to
 * [@whyb](https://github.com/whyb) &emsp;_Detect more x86 AMX*, SHA*, AVX512*, SM*_
 
 ## License
-MIT License
+MIT License
diff --git a/main.c b/main.c
@@ -48,6 +48,7 @@ int main()
     PRINT_ISA_SUPPORT(avxvnniint8)
     PRINT_ISA_SUPPORT(avxvnniint16)
     PRINT_ISA_SUPPORT(avxifma)
+    PRINT_ISA_SUPPORT(avxneconvert)
     PRINT_ISA_SUPPORT(amxfp16)
     PRINT_ISA_SUPPORT(amxbf16)
     PRINT_ISA_SUPPORT(amxint8)

diff --git a/ruapu.h b/ruapu.h
@@ -221,6 +221,7 @@ RUAPU_INSTCODE(avxvnni, 0xc4, 0xe2, 0x7d, 0x52, 0xc0) // vpdpwssd ymm0,ymm0,ymm0
 RUAPU_INSTCODE(avxvnniint8, 0xc4, 0xe2, 0x7f, 0x50, 0xc0) // vpdpbssd ymm0,ymm0,ymm0
 RUAPU_INSTCODE(avxvnniint16, 0xc4, 0xe2, 0x7e, 0xd2, 0xc0) // vpdpwsud ymm0,ymm0,ymm0
 RUAPU_INSTCODE(avxifma, 0xc4, 0xe2, 0xfd, 0xb4, 0xc0) // vpmadd52luq ymm0,ymm0,ymm0
+RUAPU_INSTCODE(avxneconvert, 0xc4, 0xe2, 0x7e, 0x72, 0xc0) // vcvtneps2bf16 xmm0,ymm0
 RUAPU_INSTCODE(amxfp16, 0xc4, 0xe2, 0x7b, 0x5c, 0xd1) // tdpfp16ps %tmm0, %tmm1, %tmm2
 RUAPU_INSTCODE(amxbf16, 0xc4, 0xe2, 0x7a, 0x5c, 0xd1) // tdpbf16ps %tmm0, %tmm1, %tmm2
 RUAPU_INSTCODE(amxint8, 0xc4, 0xe2, 0x7b, 0x5e, 0xd1) // tdpbssd %tmm0, %tmm1, %tmm2
@@ -445,6 +446,7 @@ RUAPU_ISAENTRY(avxvnni)
 RUAPU_ISAENTRY(avxvnniint8)
 RUAPU_ISAENTRY(avxvnniint16)
 RUAPU_ISAENTRY(avxifma)
+RUAPU_ISAENTRY(avxneconvert)
 RUAPU_ISAENTRY(amxfp16)
 RUAPU_ISAENTRY(amxbf16)
 RUAPU_ISAENTRY(amxint8)