[CPU] Gate the AVX10.2 paths on compiler support (#58133)
Signed-off-by: R <Ganesh.R@amd.com> Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
co-authored by
Cursor
Li, Jiang <jiang1.li@intel.com>
parent
cfd5c20286
commit
f34a0e0797
@@ -173,6 +173,18 @@ if (CMAKE_SYSTEM_PROCESSOR MATCHES "x86_64|amd64" OR ENABLE_X86_ISA)
|
||||
set(AMX_FP8_SUPPORTED FALSE)
|
||||
message(STATUS "AMX-FP8 disabled by ENABLE_AMX_FP8=OFF")
|
||||
endif()
|
||||
|
||||
# AVX10.2 arrived in GCC 15, so the target attribute, the fp8 convert
|
||||
# intrinsics and __builtin_cpu_supports("avx10.2") are all hard errors on
|
||||
# the 12.3+ the backend otherwise supports. Probe instead of assuming.
|
||||
check_cxx_compiler_flag("-mavx10.2" COMPILER_SUPPORTS_AVX10_2_FLAG)
|
||||
if (COMPILER_SUPPORTS_AVX10_2_FLAG)
|
||||
set(AVX10_2_SUPPORTED TRUE)
|
||||
else()
|
||||
set(AVX10_2_SUPPORTED FALSE)
|
||||
message(STATUS "AVX10.2 disabled: compiler does not support -mavx10.2 (compiler: ${CMAKE_CXX_COMPILER_ID} ${CMAKE_CXX_COMPILER_VERSION})")
|
||||
endif()
|
||||
|
||||
list(APPEND CXX_COMPILE_FLAGS_AVX2
|
||||
"-mavx2")
|
||||
elseif (POWER9_FOUND OR POWER10_FOUND OR POWER11_FOUND)
|
||||
@@ -629,6 +641,12 @@ if (ENABLE_X86_ISA)
|
||||
message(STATUS "AMX-FP8 (Diamond Rapids) enabled")
|
||||
endif()
|
||||
|
||||
# For the sgl-kernels AVX10.2 fp8 quantize paths
|
||||
if (AVX10_2_SUPPORTED)
|
||||
target_compile_definitions(_C PRIVATE "-DCPU_CAPABILITY_AVX10_2")
|
||||
message(STATUS "AVX10.2 enabled")
|
||||
endif()
|
||||
|
||||
# AVX512F
|
||||
define_extension_target(
|
||||
_C_AVX512
|
||||
|
||||
@@ -532,10 +532,17 @@ void zero_buffer(T* data, int64_t size) {
|
||||
#endif
|
||||
|
||||
#if defined(__x86_64__)
|
||||
// CPU_CAPABILITY_AVX10_2 is defined by cmake only when the compiler accepts
|
||||
// -mavx10.2; without it the builtin below is not merely absent but a hard
|
||||
// error, so the AVX512 paths have to stand in.
|
||||
bool avx10_2_available() {
|
||||
#ifdef CPU_CAPABILITY_AVX10_2
|
||||
// __builtin_cpu_supports returns the masked feature bit rather than 0/1.
|
||||
static const bool available = __builtin_cpu_supports("avx10.2");
|
||||
return available;
|
||||
#else
|
||||
return false;
|
||||
#endif
|
||||
}
|
||||
#endif
|
||||
|
||||
|
||||
@@ -772,6 +772,7 @@ inline __m128i cvtfp32_fp8e4m3(__m512& src) {
|
||||
return _mm512_cvtepi32_epi8(packed);
|
||||
}
|
||||
|
||||
#ifdef CPU_CAPABILITY_AVX10_2
|
||||
__attribute__((target("avx10.2"))) inline __m128i cvtfp32_fp8e4m3_avx10_2(__m512& src) {
|
||||
__m256i f16_vec = _mm512_cvt_roundps_ph(src, _MM_FROUND_TO_NEAREST_INT | _MM_FROUND_NO_EXC);
|
||||
return _mm256_cvtph_hf8(_mm256_castsi256_ph(f16_vec));
|
||||
@@ -805,6 +806,7 @@ __attribute__((target("avx10.2"))) void quantize_bf16_block_avx10_2(
|
||||
_mm_storeu_si128(reinterpret_cast<__m128i*>(dst + i + 16), fp8_vec2);
|
||||
}
|
||||
}
|
||||
#endif // CPU_CAPABILITY_AVX10_2
|
||||
|
||||
std::tuple<at::Tensor, at::Tensor> _quantize_fp8e4m3_bf16_per_tensor_no_scale(const at::Tensor& t) {
|
||||
constexpr float quant_max = 448.0f; // torch.finfo(torch.float8_e4m3fn).max
|
||||
@@ -861,10 +863,12 @@ std::tuple<at::Tensor, at::Tensor> _quantize_fp8e4m3_bf16_per_tensor_no_scale(co
|
||||
scale_data[c] = scale_val;
|
||||
|
||||
// Step 3: Scale and clamp using AVX512 (reuse the same loop structure)
|
||||
#ifdef CPU_CAPABILITY_AVX10_2
|
||||
if (avx10_2_available()) {
|
||||
quantize_bf16_block_avx10_2(channel_src, quant_dst, elements_per_channel, scale_reciprocal);
|
||||
continue;
|
||||
}
|
||||
#endif
|
||||
i = 0;
|
||||
const __m512 scale_recip_vec = _mm512_set1_ps(scale_reciprocal);
|
||||
const __m512 quant_max_vec = _mm512_set1_ps(quant_max);
|
||||
@@ -939,10 +943,12 @@ _quantize_fp8e4m3_bf16_per_tensor_with_scale(const at::Tensor& t, at::Tensor& sc
|
||||
const at::BFloat16* src_data = t_bf16.data_ptr<at::BFloat16>() + c * elements_per_channel;
|
||||
at::Float8_e4m3fn* quant_t_data = quant_t.data_ptr<at::Float8_e4m3fn>() + c * elements_per_channel;
|
||||
|
||||
#ifdef CPU_CAPABILITY_AVX10_2
|
||||
if (avx10_2_available()) {
|
||||
quantize_bf16_block_avx10_2(src_data, quant_t_data, elements_per_channel, scale_reciprocal);
|
||||
continue;
|
||||
}
|
||||
#endif
|
||||
|
||||
int64_t i = 0;
|
||||
// Process 32 elements at a time using AVX512
|
||||
|
||||
Reference in New Issue
Block a user