diff options
| author | SebastianApel <13675545+SebastianApel@users.noreply.github.com> | 2023-04-13 14:46:23 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-04-13 15:46:23 +0300 |
| commit | 95ea26f6e92d620a5437f576b80868aee7f808d6 (patch) | |
| tree | 9256b919bf5939cbc18a91a6975f453f0fcb45a5 /Makefile | |
| parent | 82d146df9b43cf677e0dbce20b03cf864958a0cc (diff) | |
benchmark : add tool for timing q4_0 matrix multiplication (#653)
* Initial version of q4_0 matrix multiplication benchmark
* Bugfix: Added dependency to ggml.o to benchmark
* Reviewer requests: added parameter for threads, switched to ggml_time_us()
* Reviewer input: removed rtsc, use epsilon for check
* Review comment: Removed set_locale
* Feature: Param for numer of iterations, Bugfix for use of parameter threads
* Reviewer suggestion: Moved to examples
* Reviewer feedback: Updated clean: and benchmark: sections
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'Makefile')
| -rw-r--r-- | Makefile | 7 |
1 files changed, 6 insertions, 1 deletions
@@ -149,7 +149,7 @@ common.o: examples/common.cpp examples/common.h $(CXX) $(CXXFLAGS) -c examples/common.cpp -o common.o clean: - rm -vf *.o main quantize quantize-stats perplexity embedding + rm -vf *.o main quantize quantize-stats perplexity embedding benchmark-q4_0-matmult main: examples/main/main.cpp ggml.o llama.o common.o $(CXX) $(CXXFLAGS) examples/main/main.cpp ggml.o llama.o common.o -o main $(LDFLAGS) @@ -171,10 +171,15 @@ embedding: examples/embedding/embedding.cpp ggml.o llama.o common.o libllama.so: llama.o ggml.o $(CXX) $(CXXFLAGS) -shared -fPIC -o libllama.so llama.o ggml.o $(LDFLAGS) + # # Tests # +benchmark: ggml.o + $(CXX) $(CXXFLAGS) examples/benchmark/benchmark-q4_0-matmult.c ggml.o -o benchmark-q4_0-matmult $(LDFLAGS) + ./benchmark-q4_0-matmult + .PHONY: tests tests: bash ./tests/run-tests.sh |