From 176260d82a4d82ce4ce1f09cd6139a50e1a2aa84 Mon Sep 17 00:00:00 2001
From: Edmond Yoo <hj3yoo@uwaterloo.ca>
Date: Sun, 16 Sep 2018 06:29:06 +0000
Subject: [PATCH] Card matching algo
---
Makefile | 24 ++++++++++++++++--------
1 files changed, 16 insertions(+), 8 deletions(-)
diff --git a/Makefile b/Makefile
index b6119ae..2ffccf7 100644
--- a/Makefile
+++ b/Makefile
@@ -1,10 +1,16 @@
-GPU=0
-CUDNN=0
+GPU=1
+CUDNN=1
CUDNN_HALF=0
-OPENCV=0
-DEBUG=0
+OPENCV=1
+AVX=0
OPENMP=0
-LIBSO=0
+LIBSO=1
+
+# 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 \
@@ -23,8 +29,8 @@
# GP100/Tesla P100 � DGX-1
# ARCH= -gencode arch=compute_60,code=sm_60
-# For Jetson Tx1 uncomment:
-# ARCH= -gencode arch=compute_51,code=[sm_51,compute_51]
+# For Jetson TX1, Tegra X1, DRIVE CX, DRIVE PX - uncomment:
+# ARCH= -gencode arch=compute_53,code=[sm_53,compute_53]
# For Jetson Tx2 or Drive-PX2 uncomment:
# ARCH= -gencode arch=compute_62,code=[sm_62,compute_62]
@@ -50,7 +56,9 @@
ifeq ($(DEBUG), 1)
OPTS= -O0 -g
else
-CFLAGS+= -ffp-contract=fast -mavx
+ifeq ($(AVX), 1)
+CFLAGS+= -ffp-contract=fast -mavx -mavx2 -msse3 -msse4.1 -msse4.2 -msse4a
+endif
endif
CFLAGS+=$(OPTS)
--
Gitblit v1.10.0