Skip to content

change the name of activation kernel #32374

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 4 commits into from
Closed

change the name of activation kernel #32374

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7d58b91
Merge pull request #1 from PaddlePaddle/develop
AnnaTrainingG Mar 25, 2021
1021e08
Merge pull request #2 from PaddlePaddle/develop
AnnaTrainingG Mar 29, 2021
43f53fe
Merge pull request #3 from PaddlePaddle/develop
AnnaTrainingG Apr 19, 2021
efb3a5d
modified the name of activation kernel
AnnaTrainingG Apr 19, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 7 additions & 6 deletions paddle/fluid/operators/activation_op.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,8 +412,8 @@ namespace plat = paddle::platform;
ops::grad_functor<plat::float16>>);
FOR_EACH_ACTIVATION_OP(REGISTER_ACTIVATION_CUDA_KERNEL);

#define REGISTER_ACTIVATION_GPU_KERNEL(act_type, op_name, functor, \
grad_functor) \
#define REGISTER_ACTIVATION_HIGH_PERFORMANCE_KERNEL(act_type, op_name, \
functor, grad_functor) \
REGISTER_OP_CUDA_KERNEL( \
act_type, ops::ActivationGPUKernel<paddle::platform::CUDADeviceContext, \
ops::functor<float>>, \
Expand All @@ -430,8 +430,9 @@ FOR_EACH_ACTIVATION_OP(REGISTER_ACTIVATION_CUDA_KERNEL);
ops::grad_functor<plat::float16>>);

/* ======================== leaky relu register ============================ */
REGISTER_ACTIVATION_GPU_KERNEL(leaky_relu, LeakyRelu, LeakyReluGPUFunctor,
LeakyReluGradGPUFunctor);
REGISTER_ACTIVATION_HIGH_PERFORMANCE_KERNEL(leaky_relu, LeakyRelu,
LeakyReluGPUFunctor,
LeakyReluGradGPUFunctor);

REGISTER_OP_CUDA_KERNEL(
leaky_relu_grad_grad,
Expand All @@ -454,9 +455,9 @@ REGISTER_OP_CUDA_KERNEL(
ops::ELUDoubleGradKernel<plat::CUDADeviceContext,
ops::ELUGradGradFunctor<plat::float16>>);
/* ========================================================================== */

/* =========================== relu register ============================ */
REGISTER_ACTIVATION_GPU_KERNEL(relu, Relu, ReluGPUFunctor, ReluGradGPUFunctor);
REGISTER_ACTIVATION_HIGH_PERFORMANCE_KERNEL(relu, Relu, ReluGPUFunctor,
ReluGradGPUFunctor);

REGISTER_OP_CUDA_KERNEL(
relu_grad_grad,
Expand Down