From 5ecff35151156118c2df74899637ad34ee384b9b Mon Sep 17 00:00:00 2001
From: Kawrakow <48489457+ikawrakow@users.noreply.github.com>
Date: Tue, 18 Apr 2023 21:00:14 +0200
Subject: Adding a simple program to measure speed of dot products (#1041)

On my Mac, the direct Q4_1 product is marginally slower
(~69 vs ~55 us for Q4_0). The SIMD-ified ggml version
is now almost 2X slower (~121 us).

On a Ryzen 7950X CPU, the direct product for Q4_1 quantization
is faster than the AVX2 implementation (~60 vs ~62 us).

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
---
 Makefile | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'Makefile')

diff --git a/Makefile b/Makefile
index e7470d5..071d956 100644
--- a/Makefile
+++ b/Makefile
@@ -133,7 +133,7 @@ $(info I CC:       $(CCV))
 $(info I CXX:      $(CXXV))
 $(info )
 
-default: main quantize quantize-stats perplexity embedding
+default: main quantize quantize-stats perplexity embedding vdot
 
 #
 # Build library
@@ -169,6 +169,9 @@ perplexity: examples/perplexity/perplexity.cpp ggml.o llama.o common.o
 embedding: examples/embedding/embedding.cpp ggml.o llama.o common.o
 	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
 
+vdot: pocs/vdot/vdot.cpp ggml.o
+	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
+
 libllama.so: llama.o ggml.o
 	$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
 
-- 
cgit v1.2.3