ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (#12154)

Browse source 
* ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions

* cmake: Add GGML_BMI2 build option

* ggml: enable BMI2 on relevant CPU variants

* ggml-cpu: include BMI2 in backend score

* ggml-cpu: register BMI2 in ggml_backend_cpu_get_features

* ggml-cpu: add __BMI2__ define when using MSVC
This commit is contained in:
Rémy O 2025-03-06 02:26:10 +01:00 • committed by GitHub
parent 5e43f104cc
commit 07d1572347
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 68 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

12
ggml/src/CMakeLists.txt
View file

@ -289,7 +289,7 @@ function(ggml_add_cpu_backend_variant tag_name)
set(GGML_CPU_TAG_NAME ${tag_name})
# other: OPENMP LLAMAFILE CPU_HBM
foreach (feat NATIVE
AVX AVX2 AVX_VNNI FMA F16C
AVX AVX2 BMI2 AVX_VNNI FMA F16C
AVX512 AVX512_VBMI AVX512_VNNI AVX512_BF16
AMX_TILE AMX_INT8 AMX_BF16)
set(GGML_${feat} OFF)
@ -309,13 +309,13 @@ if (GGML_CPU_ALL_VARIANTS)
message(FATAL_ERROR "GGML_CPU_ALL_VARIANTS requires GGML_BACKEND_DL")
endif()
ggml_add_cpu_backend_variant(sandybridge AVX)
ggml_add_cpu_backend_variant(haswell AVX F16C AVX2 FMA)
ggml_add_cpu_backend_variant(skylakex AVX F16C AVX2 FMA AVX512)
ggml_add_cpu_backend_variant(icelake AVX F16C AVX2 FMA AVX512 AVX512_VBMI AVX512_VNNI)
ggml_add_cpu_backend_variant(alderlake AVX F16C AVX2 FMA AVX_VNNI)
ggml_add_cpu_backend_variant(haswell AVX F16C AVX2 BMI2 FMA)
ggml_add_cpu_backend_variant(skylakex AVX F16C AVX2 BMI2 FMA AVX512)
ggml_add_cpu_backend_variant(icelake AVX F16C AVX2 BMI2 FMA AVX512 AVX512_VBMI AVX512_VNNI)
ggml_add_cpu_backend_variant(alderlake AVX F16C AVX2 BMI2 FMA AVX_VNNI)
if (NOT MSVC)
# MSVC doesn't support AMX
ggml_add_cpu_backend_variant(sapphirerapids AVX F16C AVX2 FMA AVX512 AVX512_VBMI AVX512_VNNI AVX512_BF16 AMX_TILE AMX_INT8)
ggml_add_cpu_backend_variant(sapphirerapids AVX F16C AVX2 BMI2 FMA AVX512 AVX512_VBMI AVX512_VNNI AVX512_BF16 AMX_TILE AMX_INT8)
endif()
elseif (GGML_CPU)
ggml_add_cpu_backend_variant_impl("")