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.

Jacek Czaja 5cf2d38594 - Removed passing X from FWD to GRAD via device context (#18911) ... test=develop - Extracted key generation from FWD and GRAD into separate function test=develop - Compilation fix test=develop - another compilation test=develop		6 years ago
..
activation_mkldnn_op.cc	- Removed passing X from FWD to GRAD via device context (#18911)	6 years ago
batch_norm_mkldnn_op.cc	[MKL-DNN] Thread-Safety for MKL-DNN reusing Part 1 (#17965)	6 years ago
concat_mkldnn_op.cc	[MKL-DNN] Fix int8 performance regression (#18758)	6 years ago
conv_mkldnn_op.cc	[MKL-DNN] Fix int8 performance regression (#18758)	6 years ago
conv_transpose_mkldnn_op.cc	Remove attribute in Allocator::Allocate (#17878)	6 years ago
dequantize_mkldnn_op.cc	Optimize INT8 DeQuantize Op with primitive reuse.	7 years ago
fc_mkldnn_op.cc	Remove attribute in Allocator::Allocate (#17878)	6 years ago
gaussian_random_mkldnn_op.cc	[MKL-DNN] Tensor modifications revert (#16462)	7 years ago
lrn_mkldnn_op.cc	[MKL-DNN] Extended LRN with reusing via Acquire API (#18675)	6 years ago
mkldnn_activation_op.h	Make separate folders for mkldnn codes	7 years ago
mul_mkldnn_op.cc	fix mul_mkldnn_op build failure (#18816)	6 years ago
pool_mkldnn_op.cc	[MKL-DNN] Reimplemented pool2d mkl-dnn to use Acquire API (#18585)	6 years ago
quantize_mkldnn_op.cc	Fix bug in quantize kernel which cause crash in vgg16/19 model (#17964)	6 years ago
requantize_mkldnn_op.cc	Add Requantize OP (#15318)	7 years ago
softmax_mkldnn_op.cc	[MKL-DNN] Thread-Safety for MKL-DNN reusing Part 1 (#17965)	6 years ago
sum_mkldnn_op.cc	[MKL-DNN] Tensor modifications revert (#16462)	7 years ago
transpose_mkldnn_op.cc	remove unused TransposeINT8Op for higher UT coverage (#18791)	6 years ago