You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

guomingz 2281ebf0f3 Enable the convolution/relu6(bounded_relu) fusion for FP32 on Intel platform. (#17130) ... * Relu6 is the bottleneck op for Mobilenet-v2. As the mkldnn supports the conv/relu6 fusion, we implement it fusion via cpass way. Due to the int8 enabling for this fusion will be supported in MKLDNN v0.20, so this PR is focused on the fp32 optimization. Below table shows the benchmark(FPS) which measured on skx-8180(28 cores) Batch size | with fusion | without fusion -- | -- | -- 1 | 214.7 | 53.4 50 | 1219.727 | 137.280 test=develop * Fix the format issue test=develop * Add the missing nolint comments. test=develop * Fix the typos. test=develop * Register the conv_brelu_mkldnn_fuse_pass for the MKLDNN engine. test=develop * Adjust the indentation. test=develop * Add the test_conv_brelu_mkldnn_fuse_pass case. test=develop * Slightly update the code per Baidu comments. Let the parameter definition embedded into the code. That's will make the code easy to understand. test=develop		7 years ago
..
activation_mkldnn_op.cc	[MKL-DNN] Tensor modifications revert (#16462)	7 years ago
batch_norm_mkldnn_op.cc	[MKL-DNN] Added reusing of primitive descriptors (fp32) (#16667)	7 years ago
concat_mkldnn_op.cc	[MKL-DNN] Tensor modifications revert (#16462)	7 years ago
conv_mkldnn_op.cc	Enable the convolution/relu6(bounded_relu) fusion for FP32 on Intel platform. (#17130)	7 years ago
conv_transpose_mkldnn_op.cc	Enable the convolution/relu6(bounded_relu) fusion for FP32 on Intel platform. (#17130)	7 years ago
dequantize_mkldnn_op.cc	Optimize INT8 DeQuantize Op with primitive reuse.	7 years ago
fc_mkldnn_op.cc	refine with comments	7 years ago
gaussian_random_mkldnn_op.cc	[MKL-DNN] Tensor modifications revert (#16462)	7 years ago
lrn_mkldnn_op.cc	[MKL-DNN] Tensor modifications revert (#16462)	7 years ago
mkldnn_activation_op.h	Make separate folders for mkldnn codes	7 years ago
pool_mkldnn_op.cc	INT8 Pool kernel Key Creation Optimization. (#15883)	7 years ago
quantize_mkldnn_op.cc	Optimize Quantize Op with primitive reuse. (#15929)	7 years ago
requantize_mkldnn_op.cc	Add Requantize OP (#15318)	7 years ago
softmax_mkldnn_op.cc	[MKL-DNN] Added reusing of primitive descriptors (fp32) (#16667)	7 years ago
sum_mkldnn_op.cc	[MKL-DNN] Tensor modifications revert (#16462)	7 years ago
transpose_mkldnn_op.cc	[MKL-DNN] Tensor modifications revert (#16462)	7 years ago