From eae7b34cc0906268ddef2e64551ea5ca0951c0c8 Mon Sep 17 00:00:00 2001
From: Ruslan_Lenin <9992012@gmail.com>
Date: Fri, 29 Jun 2018 08:39:03 +0000
Subject: [PATCH] Update gemm.c
---
Makefile | 12 ++++++++++--
1 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/Makefile b/Makefile
index b6119ae..5c39df1 100644
--- a/Makefile
+++ b/Makefile
@@ -2,10 +2,16 @@
CUDNN=0
CUDNN_HALF=0
OPENCV=0
-DEBUG=0
+AVX=0
OPENMP=0
LIBSO=0
+# set GPU=1 and CUDNN=1 to speedup on GPU
+# set CUDNN_HALF=1 to further speedup 3 x times (Mixed-precision using Tensor Cores) on GPU Tesla V100, Titan V, DGX-2
+# set AVX=1 and OPENMP=1 to speedup on CPU (if error occurs then set AVX=0)
+
+DEBUG=0
+
ARCH= -gencode arch=compute_30,code=sm_30 \
-gencode arch=compute_35,code=sm_35 \
-gencode arch=compute_50,code=[sm_50,compute_50] \
@@ -50,7 +56,9 @@
ifeq ($(DEBUG), 1)
OPTS= -O0 -g
else
-CFLAGS+= -ffp-contract=fast -mavx
+ifeq ($(AVX), 1)
+CFLAGS+= -ffp-contract=fast -mavx -msse4.1 -msse4a
+endif
endif
CFLAGS+=$(OPTS)
--
Gitblit v1.10.0