From a723e1c62a27aeb39aaf7fcdeb3beb4e89fba32d Mon Sep 17 00:00:00 2001
From: Alexey <AlexeyAB@users.noreply.github.com>
Date: Wed, 15 Aug 2018 20:52:09 +0000
Subject: [PATCH] Merge pull request #766 from HotChick91/AlexeyAB-mask
---
Makefile | 16 ++++++++++++----
1 files changed, 12 insertions(+), 4 deletions(-)
diff --git a/Makefile b/Makefile
index b6119ae..ec74a81 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] \
@@ -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