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.

jakpiase edc06c6a1b Added fc + activation fuse pass (currently only gelu, sigmoid and tanh are supported) (#29772)		4 years ago
..
batch_norm_act_fuse_pass.cc	oneDNN BatchNorm + Act fusion pass. (#27912)	4 years ago
batch_norm_act_fuse_pass.h	oneDNN BatchNorm + Act fusion pass. (#27912)	4 years ago
batch_norm_act_fuse_pass_tester.cc	oneDNN BatchNorm + Act fusion pass. (#27912)	4 years ago
conv_activation_mkldnn_fuse_pass.cc	Register op_version for new attribute use_addto (#28463)	4 years ago
conv_activation_mkldnn_fuse_pass.h	use iwyu clean include (#27267)	4 years ago
conv_activation_mkldnn_fuse_pass_tester.cc	Add macro BOOST_GET to enrich the error information of boost :: get (#24175)	5 years ago
conv_bias_mkldnn_fuse_pass.cc	Register op_version for new attribute use_addto (#28463)	4 years ago
conv_bias_mkldnn_fuse_pass.h	use iwyu clean include (#27267)	4 years ago
conv_bias_mkldnn_fuse_pass_tester.cc	add op version checker to ir passes (#27329)	4 years ago
conv_concat_relu_mkldnn_fuse_pass.cc	Register op_version for new attribute use_addto (#28463)	4 years ago
conv_concat_relu_mkldnn_fuse_pass.h	use iwyu clean include (#27267)	4 years ago
conv_concat_relu_mkldnn_fuse_pass_tester.cc	Add macro BOOST_GET to enrich the error information of boost :: get (#24175)	5 years ago
conv_elementwise_add_mkldnn_fuse_pass.cc	Register op_version for new attribute use_addto (#28463)	4 years ago
conv_elementwise_add_mkldnn_fuse_pass.h	use iwyu clean include (#27267)	4 years ago
conv_elementwise_add_mkldnn_fuse_pass_tester.cc	add op version checker to ir passes (#27329)	4 years ago
cpu_bfloat16_pass.cc	Fix cpu_bfloat16_pass (#28730)	4 years ago
cpu_bfloat16_pass.h	Add bfloat16 passes (#26999)	4 years ago
cpu_bfloat16_pass_tester.cc	Fix cpu_bfloat16_pass (#28730)	4 years ago
cpu_bfloat16_placement_pass.cc	Add bfloat16 passes (#26999)	4 years ago
cpu_bfloat16_placement_pass.h	Add bfloat16 passes (#26999)	4 years ago
cpu_bfloat16_placement_pass_tester.cc	Add bf16 pool2d and unify bf16 unit tests (#29039)	4 years ago
cpu_quantize_pass.cc	Add quantization of multi_gru op and tests (#28615)	4 years ago
cpu_quantize_pass.h	Add quantization of multi_gru op and tests (#28615)	4 years ago
cpu_quantize_pass_tester.cc	Add quantization of multi_gru op and tests (#28615)	4 years ago
cpu_quantize_placement_pass.cc	use iwyu clean include (#27267)	4 years ago
cpu_quantize_placement_pass.h	use iwyu clean include (#27267)	4 years ago
cpu_quantize_placement_pass_tester.cc	Fix int8 performace drop cpu_quantize_placement_pass (#26715)	5 years ago
cpu_quantize_squash_pass.cc	Added support for quantization of fusion_gru (#27518)	4 years ago
cpu_quantize_squash_pass.h	use iwyu clean include (#27267)	4 years ago
cpu_quantize_squash_pass_tester.cc	fix some errmsg report, in framework/ir/mkldnn (#25467)	5 years ago
depthwise_conv_mkldnn_pass.cc	Register op_version for new attribute use_addto (#28463)	4 years ago
depthwise_conv_mkldnn_pass.h	use iwyu clean include (#27267)	4 years ago
depthwise_conv_mkldnn_pass_tester.cc	add op version checker to ir passes (#27329)	4 years ago
fc_act_mkldnn_fuse_pass.cc	Added fc + activation fuse pass (currently only gelu, sigmoid and tanh are supported) (#29772)	4 years ago
fc_act_mkldnn_fuse_pass.h	Added fc + activation fuse pass (currently only gelu, sigmoid and tanh are supported) (#29772)	4 years ago
fc_act_mkldnn_fuse_pass_tester.cc	Added fc + activation fuse pass (currently only gelu, sigmoid and tanh are supported) (#29772)	4 years ago
fc_mkldnn_pass.cc	use iwyu clean include (#27267)	4 years ago
fc_mkldnn_pass.h	use iwyu clean include (#27267)	4 years ago
matmul_transpose_reshape_fuse_pass.cc	Add compatibility check for four mkldnn pass (#27364)	4 years ago
matmul_transpose_reshape_fuse_pass.h	use iwyu clean include (#27267)	4 years ago
matmul_transpose_reshape_fuse_pass_tester.cc	added fusing matmul-transpose-reshape pass (#23866)	5 years ago
mkldnn_conv_bn_fuse_pass_tester.cc	[oneDNN] Clearing mkldnn cache in naiveexecutor destructor (#24756)	5 years ago
mkldnn_inplace_pass.cc	Op version python mkldnn_inplace test (#28354)	4 years ago
mkldnn_inplace_pass.h	[DNNL] Added MKL-DNN inplace pass for C-API inference (#23315)	5 years ago
mkldnn_inplace_pass_tester.cc	[DNNL] refine activations Inplace support (#24145)	5 years ago
mkldnn_placement_pass.cc	A a pass to enable the use of cudnn (#19346)	6 years ago
mkldnn_placement_pass.h	use iwyu clean include (#27267)	4 years ago
mkldnn_placement_pass_tester.cc	Add macro BOOST_GET to enrich the error information of boost :: get (#24175)	5 years ago
multi_gru_fuse_pass.cc	Add multi_gru_fuse_pass and tests (#28601)	4 years ago
multi_gru_fuse_pass.h	Add multi_gru_fuse_pass and tests (#28601)	4 years ago
multi_gru_fuse_pass_tester.cc	Add multi_gru_fuse_pass and tests (#28601)	4 years ago
multi_gru_seq_fuse_pass.cc	Add multi_gru_fuse_pass and tests (#28601)	4 years ago
multi_gru_seq_fuse_pass.h	Add multi_gru_seq_fuse_pass and tests (#28604)	4 years ago
multi_gru_seq_fuse_pass_tester.cc	Add multi_gru_seq_fuse_pass and tests (#28604)	4 years ago
reshape_transpose_matmul_mkldnn_fuse_pass.cc	added reshape transpose matmul fuse pass (#23754)	5 years ago
reshape_transpose_matmul_mkldnn_fuse_pass.h	use iwyu clean include (#27267)	4 years ago
reshape_transpose_matmul_mkldnn_fuse_pass_tester.cc	Reshape transpose matmul coverage (#24970)	5 years ago
scale_matmul_fuse_pass.cc	Add compatibility check for four mkldnn pass (#27364)	4 years ago
scale_matmul_fuse_pass.h	use iwyu clean include (#27267)	4 years ago
scale_matmul_fuse_pass_tester.cc	Add scale-matmul fuse pass (#23734)	5 years ago