zzy34407230
/
mindspore2022
Not watched
1
0
Fork 0
Code
Releases 22 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
20175 Commits
18 Branches
584 MB
67 Download
 
 
 
 
 
 
Tree: 693b4cfdc8
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '693b4cfdc8'
${ noResults }
mindspore2022/mindspore/ccsrc/backend/optimizer/graph_kernel
dayschan a2967330ea Normalize the Reduce nodes' axis in GraphKernel 5 years ago
..
add_atomic_clean.cc add graphkerneloptimize pass 5 years ago
add_atomic_clean.h add graphkerneloptimize pass 5 years ago
add_atomic_clean_gpu.cc absorb real scalar tensor 5 years ago
add_atomic_clean_gpu.h [auto-monad] Support side-effects by auto-monad 5 years ago
add_stitch_atomic_clean_gpu.cc set attr safetly 5 years ago
add_stitch_atomic_clean_gpu.h stitch info 5 years ago
arithmetic_simplify.cc Change TensorAdd to Add, from r1.1 to master 5 years ago
arithmetic_simplify.h add new pass in graph kernel: arithmetic_simplify 5 years ago
axis_normalizer.cc Normalize the Reduce nodes' axis in GraphKernel 5 years ago
axis_normalizer.h Normalize the Reduce nodes' axis in GraphKernel 5 years ago
basic_ops_fusion.cc exclude special node when expand or basic fusion 5 years ago
basic_ops_fusion.h add graphkerneloptimize pass 5 years ago
clean_all_in_once.cc clean batch when nodes is not empty 5 years ago
clean_all_in_once.h clean batch buffer in once 5 years ago
composite_ops_fusion.cc GraphKernel Fuser 5 years ago
composite_ops_fusion.h GraphKernel Fuser 5 years ago
depend_formater.cc only through pass target depend 5 years ago
depend_formater.h support parallel fusion 5 years ago
eliminate_redundant_output.cc Bugfix about execution-order after GraphKernelSplitter 5 years ago
eliminate_redundant_output.h Bugfix about execution-order after GraphKernelSplitter 5 years ago
graph_kernel_cse.cc process cast when activate graph kernel in amp 5 years ago
graph_kernel_cse.h process cast when activate graph kernel in amp 5 years ago
graph_kernel_expander.cc Refactor GraphKernelExpander (2nd submission) 5 years ago
graph_kernel_expander.h Refactor GraphKernelExpander (1st submission) 5 years ago
graph_kernel_helper.cc using cpp infer firstly 5 years ago
graph_kernel_helper.h absorb real scalar tensor 5 years ago
graph_kernel_optimization.cc Normalize the Reduce nodes' axis in GraphKernel 5 years ago
graph_kernel_optimization.h Combine the GraphKernelOptimization of Gpu and Ascend 5 years ago
graph_kernel_splitter.cc [auto-monad] Support side-effects by auto-monad 5 years ago
graph_kernel_splitter.h GraphKernel supports GPU 5 years ago
optimize_assign.cc fix exec order bug about monad 5 years ago
optimize_assign.h [GraphKernel] Replace Assign with InplaceAssign 5 years ago
parallel_cost_model.cc pipeline optimization for parallel fusion 5 years ago
parallel_cost_model.h pipeline optimization for parallel fusion 5 years ago
parallel_fusion.cc only through pass target depend 5 years ago
parallel_fusion.h pipeline optimization for parallel fusion 5 years ago
raise_reduction_precision.cc set attr safetly 5 years ago
raise_reduction_precision.h Raise akg ReduceSum precision 5 years ago
reorder_ops.cc add reorder_ops pass in graph kernel 5 years ago
reorder_ops.h add reorder_ops pass in graph kernel 5 years ago
shape_ops_splitter.cc eliminate redundant split ops 5 years ago
shape_ops_splitter.h Combine the GraphKernelOptimization of Gpu and Ascend 5 years ago
split_assign.cc [auto-monad] Support side-effects by auto-monad 5 years ago
split_assign.h [auto-monad] Support side-effects by auto-monad 5 years ago
substitute_dropout.cc [auto-monad] Support side-effects by auto-monad 5 years ago
substitute_dropout.h substitute dropout by cudnnuniformreal and dropout 5 years ago
tensor_promotion.cc add graphkerneloptimize pass 5 years ago
tensor_promotion.h absorb real scalar tensor 5 years ago
update_state_formatter.cc Bugfix about execution-order after GraphKernelSplitter 5 years ago
update_state_formatter.h Bugfix about execution-order after GraphKernelSplitter 5 years ago
value_graph_binder.cc expand tanh_grad and reduce_mean, fix bug and add test_case in ci 5 years ago
value_graph_binder.h promote complex tensor as graph's input and recorrect getitem index for graph kernels fusion. 5 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

阿对对队

C++ Python Text C Unity3D Asset other