From 9bae70b22549b68f5cdeece8b6c3b3de00c22714 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Mon, 16 Apr 2018 23:51:11 +0000
Subject: [PATCH] Accelerated by another 5% using FP16/32 Batch-norm for Tensor Cores.

---
 Makefile |   13 +++++++++++--
 1 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index 2c5fdb6..b6119ae 100644
--- a/Makefile
+++ b/Makefile
@@ -1,5 +1,6 @@
 GPU=0
 CUDNN=0
+CUDNN_HALF=0
 OPENCV=0
 DEBUG=0
 OPENMP=0
@@ -44,10 +45,12 @@
 OPTS=-Ofast
 LDFLAGS= -lm -pthread 
 COMMON= 
-CFLAGS=-Wall -Wfatal-errors
+CFLAGS=-Wall -Wfatal-errors -Wno-unused-result -Wno-unknown-pragmas
 
 ifeq ($(DEBUG), 1) 
-OPTS=-O0 -g
+OPTS= -O0 -g
+else
+CFLAGS+= -ffp-contract=fast -mavx
 endif
 
 CFLAGS+=$(OPTS)
@@ -85,6 +88,12 @@
 endif
 endif
 
+ifeq ($(CUDNN_HALF), 1)
+COMMON+= -DCUDNN_HALF
+CFLAGS+= -DCUDNN_HALF
+ARCH+= -gencode arch=compute_70,code=[sm_70,compute_70]
+endif
+
 OBJ=http_stream.o gemm.o utils.o cuda.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o detector.o layer.o compare.o classifier.o local_layer.o swag.o shortcut_layer.o activation_layer.o rnn_layer.o gru_layer.o rnn.o rnn_vid.o crnn_layer.o demo.o tag.o cifar.o go.o batchnorm_layer.o art.o region_layer.o reorg_layer.o reorg_old_layer.o super.o voxel.o tree.o yolo_layer.o upsample_layer.o
 ifeq ($(GPU), 1) 
 LDFLAGS+= -lstdc++ 

--
Gitblit v1.10.0