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

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

Browse source 
* 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
Download patch file Download diff file Expand all files Collapse all files

12
CMakeLists.txt
View file

@ -126,6 +126,7 @@ set(LLAMA_METAL_MACOSX_VERSION_MIN "" CACHE STRING
set(LLAMA_METAL_STD "" CACHE STRING "llama: metal standard version (-std flag)")
option(LLAMA_KOMPUTE "llama: use Kompute" OFF)
option(LLAMA_RPC "llama: use RPC" OFF)
option(LLAMA_OPENMP "llama: use OpenMP" ON)
option(LLAMA_SYCL "llama: use SYCL" OFF)
option(LLAMA_SYCL_F16 "llama: use 16 bit floats for sycl calculations" OFF)
set(LLAMA_SYCL_TARGET "INTEL" CACHE STRING "llama: sycl target device")
@ -296,6 +297,17 @@ if (LLAMA_METAL)
)
endif()
if (LLAMA_OPENMP)
find_package(OpenMP)
if (OpenMP_FOUND)
message(STATUS "OpenMP found")
add_compile_definitions(GGML_USE_OPENMP)
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} OpenMP::OpenMP_C OpenMP::OpenMP_CXX)
else()
message(WARNING "OpenMP not found")
endif()
endif()
if (LLAMA_BLAS)
if (LLAMA_STATIC)
set(BLA_STATIC ON)