From 95ea26f6e92d620a5437f576b80868aee7f808d6 Mon Sep 17 00:00:00 2001
From: SebastianApel <13675545+SebastianApel@users.noreply.github.com>
Date: Thu, 13 Apr 2023 14:46:23 +0200
Subject: 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>
---
 Makefile | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'Makefile')

diff --git a/Makefile b/Makefile
index 3e58a28..fe2f26e 100644
--- a/Makefile
+++ b/Makefile
@@ -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
-- 
cgit v1.2.3