| .. |
|
add_atomic_clean.cc
|
add graphkerneloptimize pass
|
2020-11-15 22:55:29 +08:00 |
|
add_atomic_clean.h
|
add graphkerneloptimize pass
|
2020-11-15 22:55:29 +08:00 |
|
add_atomic_clean_gpu.cc
|
absorb real scalar tensor
|
2021-03-02 10:19:57 +08:00 |
|
add_atomic_clean_gpu.h
|
[auto-monad] Support side-effects by auto-monad
|
2021-02-08 09:01:15 +08:00 |
|
add_stitch_atomic_clean_gpu.cc
|
set attr safetly
|
2021-02-05 09:12:27 +08:00 |
|
add_stitch_atomic_clean_gpu.h
|
stitch info
|
2021-02-01 10:20:55 +08:00 |
|
arithmetic_simplify.cc
|
Change TensorAdd to Add, from r1.1 to master
|
2021-02-01 17:53:52 +08:00 |
|
arithmetic_simplify.h
|
add new pass in graph kernel: arithmetic_simplify
|
2020-10-15 10:54:10 +08:00 |
|
axis_normalizer.cc
|
Normalize the Reduce nodes' axis in GraphKernel
|
2021-03-16 15:55:50 +08:00 |
|
axis_normalizer.h
|
Normalize the Reduce nodes' axis in GraphKernel
|
2021-03-16 15:55:50 +08:00 |
|
basic_ops_fusion.cc
|
exclude special node when expand or basic fusion
|
2021-02-09 16:13:35 +08:00 |
|
basic_ops_fusion.h
|
add graphkerneloptimize pass
|
2020-11-15 22:55:29 +08:00 |
|
clean_all_in_once.cc
|
clean batch when nodes is not empty
|
2020-12-09 15:54:29 +08:00 |
|
clean_all_in_once.h
|
clean batch buffer in once
|
2020-12-09 10:21:08 +08:00 |
|
composite_ops_fusion.cc
|
GraphKernel Fuser
|
2020-12-04 11:02:36 +08:00 |
|
composite_ops_fusion.h
|
GraphKernel Fuser
|
2020-12-04 11:02:36 +08:00 |
|
depend_formater.cc
|
only through pass target depend
|
2021-03-12 09:30:01 +08:00 |
|
depend_formater.h
|
support parallel fusion
|
2021-01-27 17:27:13 +08:00 |
|
eliminate_redundant_output.cc
|
Bugfix about execution-order after GraphKernelSplitter
|
2021-03-09 19:12:36 +08:00 |
|
eliminate_redundant_output.h
|
Bugfix about execution-order after GraphKernelSplitter
|
2021-03-09 19:12:36 +08:00 |
|
graph_kernel_cse.cc
|
process cast when activate graph kernel in amp
|
2020-12-03 15:37:31 +08:00 |
|
graph_kernel_cse.h
|
process cast when activate graph kernel in amp
|
2020-12-03 15:37:31 +08:00 |
|
graph_kernel_expander.cc
|
!13512 add some expander ops
|
2021-03-19 15:00:23 +08:00 |
|
graph_kernel_expander.h
|
Refactor GraphKernelExpander (1st submission)
|
2021-02-07 10:48:23 +08:00 |
|
graph_kernel_helper.cc
|
using cpp infer firstly
|
2021-03-09 15:37:17 +08:00 |
|
graph_kernel_helper.h
|
absorb real scalar tensor
|
2021-03-02 10:19:57 +08:00 |
|
graph_kernel_optimization.cc
|
Normalize the Reduce nodes' axis in GraphKernel
|
2021-03-16 15:55:50 +08:00 |
|
graph_kernel_optimization.h
|
Combine the GraphKernelOptimization of Gpu and Ascend
|
2021-03-01 14:14:12 +08:00 |
|
graph_kernel_splitter.cc
|
[auto-monad] Support side-effects by auto-monad
|
2021-02-08 09:01:15 +08:00 |
|
graph_kernel_splitter.h
|
GraphKernel supports GPU
|
2020-09-09 17:46:50 +08:00 |
|
optimize_assign.cc
|
fix exec order bug about monad
|
2021-02-18 11:01:06 +08:00 |
|
optimize_assign.h
|
[GraphKernel] Replace Assign with InplaceAssign
|
2021-02-01 17:15:35 +08:00 |
|
parallel_cost_model.cc
|
pipeline optimization for parallel fusion
|
2021-03-09 17:07:24 +08:00 |
|
parallel_cost_model.h
|
pipeline optimization for parallel fusion
|
2021-03-09 17:07:24 +08:00 |
|
parallel_fusion.cc
|
only through pass target depend
|
2021-03-12 09:30:01 +08:00 |
|
parallel_fusion.h
|
pipeline optimization for parallel fusion
|
2021-03-09 17:07:24 +08:00 |
|
raise_reduction_precision.cc
|
set attr safetly
|
2021-02-05 09:12:27 +08:00 |
|
raise_reduction_precision.h
|
Raise akg ReduceSum precision
|
2021-01-26 14:49:48 +08:00 |
|
reorder_ops.cc
|
add reorder_ops pass in graph kernel
|
2020-12-29 10:27:47 +08:00 |
|
reorder_ops.h
|
add reorder_ops pass in graph kernel
|
2020-12-29 10:27:47 +08:00 |
|
shape_ops_splitter.cc
|
eliminate redundant split ops
|
2021-02-09 14:10:57 +08:00 |
|
shape_ops_splitter.h
|
Combine the GraphKernelOptimization of Gpu and Ascend
|
2021-03-01 14:14:12 +08:00 |
|
split_assign.cc
|
add some expander ops
|
2021-03-18 19:03:36 +08:00 |
|
split_assign.h
|
[auto-monad] Support side-effects by auto-monad
|
2021-02-08 09:01:15 +08:00 |
|
substitute_dropout.cc
|
[auto-monad] Support side-effects by auto-monad
|
2021-02-08 09:01:15 +08:00 |
|
substitute_dropout.h
|
substitute dropout by cudnnuniformreal and dropout
|
2020-11-26 10:36:02 +08:00 |
|
tensor_promotion.cc
|
add graphkerneloptimize pass
|
2020-11-15 22:55:29 +08:00 |
|
tensor_promotion.h
|
absorb real scalar tensor
|
2021-03-02 10:19:57 +08:00 |
|
update_state_formatter.cc
|
Bugfix about execution-order after GraphKernelSplitter
|
2021-03-09 19:12:36 +08:00 |
|
update_state_formatter.h
|
Bugfix about execution-order after GraphKernelSplitter
|
2021-03-09 19:12:36 +08:00 |
|
value_graph_binder.cc
|
expand tanh_grad and reduce_mean, fix bug and add test_case in ci
|
2020-11-10 10:37:38 +08:00 |
|
value_graph_binder.h
|
promote complex tensor as graph's input and recorrect getitem index for graph kernels fusion.
|
2020-10-10 17:57:42 +08:00 |
mindspore-ci-bot
5b95409022