EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)

Browse Source 
* [cl][adreno] Add Adreno GPU support

Add new OpenCL backend to support Adreno GPUs

---------

Co-authored-by: Skyler Szot <quic_sszot@quicinc.com>
Co-authored-by: Shangqing Gu <quic_shawngu@quicinc.com>
Co-authored-by: Alexander Angus <quic_aangus@quicinc.com>
Co-authored-by: Hongqiang Wang <quic_wangh@quicinc.com>
Co-authored-by: Max Krasnyansky <quic_maxk@quicinc.com>

* [cl][ci] Add workflow for CL

* [cl][adreno] Fix memory leak for non SMALL_ALLOC path

* opencl: integrate backend dyn.load interface and fix compiler and format warnings

* opencl: remove small-alloc support and fix build errors for non-opencl platforms

* opencl: fixed merge conflict (MUSA added twice in cmake)

* opencl-ci: use RUNNER_TEMP instead of github.workspace

* opencl: fix embed tool invocation with python3

* opencl: CI workflow fixes

* opencl: Clean up small-alloc in CMake files

* opencl: cleanup ggml-opencl2 header file

* opencl: use ulong for offsets and strides in ADD kernel

* opencl: use cl_ulong for all offsets

* opencl: use cl_ulong for sizes and strides

* opencl: use `GGML_LOG_xxx` instead of `fprintf(stderr, ...)`

* opencl: rename backend `opencl2` -> `opencl`

* opencl: rename kernel files `ggml-opencl2` -> `ggml-opencl`

* opencl: make OpenCL required, remove redundant lib and inc directories

* `ggml-base`, `..` and `.` are added by `ggml_add_backend_library`

* opencl: rename backend - funcs, structs, etc `opencl2` -> `opencl`

* opencl: remove copyright marker since main license already covers

* opencl: replace some more OPENCL2 leftovers

* opencl: remove limits on `tensor_extra`

* opencl: use pools for `tensor_extra`

* opencl: fix compiler warnings with GCC and Clang

Still getting the warning about clCreateCmdQueue being obsolete.
Will fix that separately.

* opencl: fail gracefully if opencl devices are not available

Also for unsupported GPUs.

* opencl: fix MSVC builds (string length error)

* opencl: check for various requirements, allow deprecated API

* opencl: update log message for unsupported GPUs

---------

Co-authored-by: Skyler Szot <quic_sszot@quicinc.com>
Co-authored-by: Shangqing Gu <quic_shawngu@quicinc.com>
Co-authored-by: Alexander Angus <quic_aangus@quicinc.com>
Co-authored-by: Hongqiang Wang <quic_wangh@quicinc.com>
Co-authored-by: Max Krasnyansky <quic_maxk@quicinc.com>
This commit is contained in:
lhez
2024-12-13 12:23:52 -08:00
committed by GitHub
parent c27ac678dd
commit a76c56fa1a
17 changed files with 9014 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
ggml/src/ggml-opencl/kernels/embed_kernel.py Normal file
View File

@@ -0,0 +1,26 @@
#
import sys
import logging
logger = logging.getLogger("opencl-embed-kernel")
def main():
logging.basicConfig(level=logging.INFO)
if len(sys.argv) != 3:
logger.info("Usage: python embed_kernel.py <input_file> <output_file>")
sys.exit(1)
ifile = open(sys.argv[1], "r")
ofile = open(sys.argv[2], "w")
for i in ifile:
ofile.write('R"({})"\n'.format(i))
ifile.close()
ofile.close()
if __name__ == "__main__":
main()