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.

JiabinYang 656040c726 merge reyoung optimization		6 years ago
..
detail	Windows/online (#14474)	6 years ago
CMakeLists.txt	add prelu gpu inference	6 years ago
algorithm.h	test=develop	6 years ago
blas.cc	…
blas.h	Use mkl	6 years ago
blas_impl.cu.h	Refine cublas to support CUBLAS_TENSOR_OP_MATH (#13929)	6 years ago
blas_impl.h	Use mkl	6 years ago
compound_functors.h	Feature/op_fuse_pass (#12440)	7 years ago
concat.hip.cu	…
concat_and_split.cc	Refine Split op (#13967)	6 years ago
concat_and_split.cu	Refine Split op (#13967)	6 years ago
concat_and_split.h	Refine Split op (#13967)	6 years ago
concat_test.cc	Refine Split op (#13967)	6 years ago
context_project.cc	…
context_project.cu	Fix Eigen macro when using GPU	6 years ago
context_project.h	…
cos_sim_functor.cc	…
cos_sim_functor.cu	Fix SelectedRowsAdd bug (#14309)	6 years ago
cos_sim_functor.h	…
cpu_vec.h	remove jit namespace	6 years ago
cpu_vec_test.cc	remove jit namespace	6 years ago
cross_entropy.cc	Add ignore_index in cross_entropy op (#13217)	7 years ago
cross_entropy.cu	hot fix log (#14293)	6 years ago
cross_entropy.h	Add fp16 backward support (#14202)	6 years ago
depthwise_conv.cu	optimize depthwise conv by register memory (#13778)	6 years ago
depthwise_conv.h	Optimization of Kernels that related to DeepLabv3+ (#13534)	6 years ago
fc_compute.h	add Set/GetCPUNumThreads api	6 years ago
functors.h	Feature/op_fuse_pass (#12440)	7 years ago
gru_compute.cc	…
gru_compute.cu	…
gru_compute.h	…
im2col.cc	…
im2col.cu	…
im2col.h	…
im2col_cfo_cpu.h	…
im2col_test.cc	fix unit test cases	6 years ago
jit_code.cc	remove jit namespace	6 years ago
jit_code.h	remove jit namespace	6 years ago
jit_gen.cc	remove jit namespace	6 years ago
jit_gen.h	add jit gencode	6 years ago
jit_kernel.cc	remove jit namespace	6 years ago
jit_kernel.h	add gru refer code and remove redundant avx code	6 years ago
jit_kernel_blas.cc	remove jit namespace	6 years ago
jit_kernel_crf_decode.cc	remove jit namespace	6 years ago
jit_kernel_exp.cc	remove jit namespace	6 years ago
jit_kernel_impl.h	add gru refer code and remove redundant avx code	6 years ago
jit_kernel_layer_norm.cc	Fix the issue to run on AVX2 and AVX512F machines (#14851)	6 years ago
jit_kernel_macro.h	remove jit namespace	6 years ago
jit_kernel_refer.h	add comments and follow comments	6 years ago
jit_kernel_rnn.cc	enable gru jitcode and refine act and lstm jitcode	6 years ago
jit_kernel_test.cc	remove jit namespace	6 years ago
lstm_compute.cc	…
lstm_compute.cu	…
lstm_compute.h	…
math_function.cc	Change tensor uses proto::VarType::type	6 years ago
math_function.cu	Change tensor uses proto::VarType::type	6 years ago
math_function.h	"fix compile error" (#13579)	6 years ago
math_function_impl.h	…
math_function_test.cc	…
math_function_test.cu	…
matrix_bit_code.cc	Polish code	6 years ago
matrix_bit_code.h	merge reyoung optimization	6 years ago
maxouting.cc	…
maxouting.cu	…
maxouting.h	fix style (#13142)	7 years ago
padding.h	Add pad_constant_like_op (#12943)	7 years ago
pooling.cc	fix doc errors. test=develop	6 years ago
pooling.cu	fix doc errors. test=develop	6 years ago
pooling.h	fix doc errors. test=develop	6 years ago
prelu.cu	add prelu gpu inference	6 years ago
prelu.h	add prelu gpu inference	6 years ago
sampler.cc	Make NCE_OP more efficient and support SelectedRows (#14469)	6 years ago
sampler.h	Make NCE_OP more efficient and support SelectedRows (#14469)	6 years ago
selected_rows_functor.cc	Revert the changes of VLOG	6 years ago
selected_rows_functor.cu	Revert the changes of VLOG	6 years ago
selected_rows_functor.h	merge from develop	6 years ago
selected_rows_functor_test.cc	sum op handle empty input	6 years ago
selected_rows_functor_test.cu.cc	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into rewrite_allocation	6 years ago
sequence2batch.cc	refine seq2batch	7 years ago
sequence2batch.cu	Fix Eigen macro when using GPU	6 years ago
sequence2batch.h	refine cpu gru batch mode	7 years ago
sequence_padding.cc	update function	7 years ago
sequence_padding.cu	update function	7 years ago
sequence_padding.h	…
sequence_padding_test.cc	…
sequence_pooling.cc	Rebase of seqpool-max optimization	6 years ago
sequence_pooling.cu	minor fix	6 years ago
sequence_pooling.h	Rebase of seqpool-max optimization	6 years ago
sequence_pooling_test.cc	fix some compiler warning	6 years ago
sequence_scale.cc	…
sequence_scale.cu	…
sequence_scale.h	…
softmax.cc	- Softmax for Inference is enabled when ON_INFER is set	6 years ago
softmax.cu	Fix Eigen macro when using GPU	6 years ago
softmax.h	- Removing partial specialization of sotmax for inference for GPU	6 years ago
softmax_impl.h	Add reduce sparse tensor feature. (#14757)	6 years ago
unpooling.cc	…
unpooling.cu	…
unpooling.h	…
vol2col.cc	…
vol2col.cu	…
vol2col.h	…
vol2col_test.cc	…