Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_tensorrt_pooling_converter

Author: NHZlX

CMakeLists.txt

@@ -136,6 +136,12 @@ else()
     set(THIRD_PARTY_BUILD_TYPE Release)
 endif()
 
+if(WITH_MKL)
+  option(MKL_SPLIT_GEMM "PaddlePaddle MKL gemm would split to small ones" OFF)
+  if (MKL_SPLIT_GEMM)
+    add_definitions(-DPADDLE_MKL_SPLIT_GEMM)
+  endif()
+endif()
 set(WITH_MKLML ${WITH_MKL})
 if (NOT DEFINED WITH_MKLDNN)
     if (WITH_MKL AND AVX2_FOUND)

README.md

@@ -18,7 +18,21 @@ learning to many products at Baidu.
 Our vision is to enable deep learning for everyone via PaddlePaddle.
 Please refer to our [release announcement](https://github.com/PaddlePaddle/Paddle/releases) to track the latest feature of PaddlePaddle.
 
-### Lastest PaddlePaddle Version: [Fluid](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/fluid)
+
+### Latest PaddlePaddle Release: [Fluid 0.14.0](https://github.com/PaddlePaddle/Paddle/tree/v0.14.0)
+### Install Latest Stable Release:
+```
+# Linux CPU
+pip install paddlepaddle
+# Linux GPU cuda9cudnn7
+pip install paddlepaddle-gpu
+# Linux GPU cuda8cudnn7
+pip install paddlepaddle-gpu==0.14.0.post87
+# Linux GPU cuda8cudnn5
+pip install paddlepaddle-gpu==0.14.0.post85
+
+# For installation on other platform, refer to http://paddlepaddle.org/
+```
 
 ## Features
 

benchmark/paddle/image/run.sh

@@ -1,3 +1,5 @@
+#!/bin/bash
+
 set -e
 
 function train() {

benchmark/paddle/image/run_mkl_infer.sh

@@ -1,3 +1,5 @@
+#!/bin/bash
+
 set -e
 
 function clock_to_seconds() {

benchmark/paddle/image/run_mkl_train.sh

@@ -1,3 +1,5 @@
+#!/bin/bash
+
 set -e
 
 function train() {

benchmark/paddle/image/run_openblas_infer.sh

@@ -1,3 +1,5 @@
+#!/bin/bash
+
 set -e
 
 function clock_to_seconds() {

benchmark/paddle/image/run_openblas_train.sh

@@ -1,3 +1,5 @@
+#!/bin/bash
+
 set -e
 
 function train() {

benchmark/paddle/rnn/run.sh

@@ -1,3 +1,5 @@
+#!/bin/bash
+
 set -e
 
 function train() {

benchmark/tensorflow/image/run.sh

@@ -1,3 +1,5 @@
+#!/bin/bash
+
 set -e
 
 function test() {

benchmark/tensorflow/image/run_multi.sh

@@ -1,3 +1,5 @@
+#!/bin/bash
+
 set -e
 
 function test() {