ggml : use OpenMP as a thread pool (#7606)

* ggml: Added OpenMP for multi-threads processing

* ggml : Limit the number of threads used to avoid deadlock

* update shared state n_threads in parallel region

* clear numa affinity for main thread even with openmp

* enable openmp by default

* fix msvc build

* disable openmp on macos

* ci : disable openmp with thread sanitizer

* Update ggml.c

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Masaya, Kato 2024-06-04 00:14:15 +09:00 committed by GitHub
parent 0b832d53ba
commit a5735e4426
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 103 additions and 38 deletions

View file

@ -57,6 +57,8 @@ ifeq ($(UNAME_S),Darwin)
LLAMA_METAL := 1
endif
LLAMA_NO_OPENMP := 1
ifneq ($(UNAME_P),arm)
SYSCTL_M := $(shell sysctl -n hw.optional.arm64 2>/dev/null)
ifeq ($(SYSCTL_M),1)
@ -405,6 +407,12 @@ ifndef LLAMA_NO_ACCELERATE
endif
endif # LLAMA_NO_ACCELERATE
ifndef LLAMA_NO_OPENMP
MK_CPPFLAGS += -DGGML_USE_OPENMP
MK_CFLAGS += -fopenmp
MK_CXXFLAGS += -fopenmp
endif # LLAMA_NO_OPENMP
ifdef LLAMA_OPENBLAS
MK_CPPFLAGS += -DGGML_USE_OPENBLAS $(shell pkg-config --cflags-only-I openblas)
MK_CFLAGS += $(shell pkg-config --cflags-only-other openblas)