diff options
| author | Casey Primozic <casey@cprimozic.net> | 2023-03-21 07:35:42 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-03-21 15:35:42 +0100 |
| commit | 2e664f1ff413995506c9a54f3a8d5b8c64e37a91 (patch) | |
| tree | 0162d9c81e72e85d21a5806b35dbefc6587c105d /Makefile | |
| parent | 8cf9f34eddc124d4ab28f4d2fe8e99d574510bde (diff) | |
Add initial AVX512 support for dot product on Linux (#320)
* Update Makefile to detect AVX512 support and add compiler flags if it's available
* Based on existing AVX2 implementation, dot product on one 32-value block of 4-bit quantized ints at a time
* Perform 8 bit -> 16 bit sign extension and multiply+add on 32 values at time instead of 16
* Use built-in AVX512 horizontal reduce add to get sum at the end
* Manual unrolling on inner dot product loop to reduce loop counter overhead
Diffstat (limited to 'Makefile')
| -rw-r--r-- | Makefile | 32 |
1 files changed, 32 insertions, 0 deletions
@@ -95,6 +95,38 @@ ifeq ($(UNAME_M),$(filter $(UNAME_M),x86_64 i686)) ifneq (,$(findstring sse3,$(SSE3_M))) CFLAGS += -msse3 endif + AVX512F_M := $(shell grep "avx512f " /proc/cpuinfo) + ifneq (,$(findstring avx512f,$(AVX512F_M))) + CFLAGS += -mavx512f + endif + AVX512BW_M := $(shell grep "avx512bw " /proc/cpuinfo) + ifneq (,$(findstring avx512bw,$(AVX512BW_M))) + CFLAGS += -mavx512bw + endif + AVX512DQ_M := $(shell grep "avx512dq " /proc/cpuinfo) + ifneq (,$(findstring avx512dq,$(AVX512DQ_M))) + CFLAGS += -mavx512dq + endif + AVX512VL_M := $(shell grep "avx512vl " /proc/cpuinfo) + ifneq (,$(findstring avx512vl,$(AVX512VL_M))) + CFLAGS += -mavx512vl + endif + AVX512CD_M := $(shell grep "avx512cd " /proc/cpuinfo) + ifneq (,$(findstring avx512cd,$(AVX512CD_M))) + CFLAGS += -mavx512cd + endif + AVX512ER_M := $(shell grep "avx512er " /proc/cpuinfo) + ifneq (,$(findstring avx512er,$(AVX512ER_M))) + CFLAGS += -mavx512er + endif + AVX512IFMA_M := $(shell grep "avx512ifma " /proc/cpuinfo) + ifneq (,$(findstring avx512ifma,$(AVX512IFMA_M))) + CFLAGS += -mavx512ifma + endif + AVX512PF_M := $(shell grep "avx512pf " /proc/cpuinfo) + ifneq (,$(findstring avx512pf,$(AVX512PF_M))) + CFLAGS += -mavx512pf + endif else ifeq ($(UNAME_S),Haiku) AVX1_M := $(shell sysinfo -cpu | grep "AVX ") ifneq (,$(findstring avx,$(AVX1_M))) |