Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR Category
Custom Device
PR Types
Bug fixes
Description
card-85146
paddle/phi/kernels/gpu/check_numerics_kernel.cu
: HIP can now use the original CUDA Kernel, and there is no need to write a separate Kernel for HIP.paddle/phi/kernels/strings/gpu/strings_lower_upper_kernel.cu
: Need to reduce the number of threads to 256 on ROCm platform.test/cpp/fluid/elementwise/test_elementwise_op_grad_grad.h
: There are different standards for CUDA and HIP platforms, so the standards are unified.paddle/phi/kernels/gpu/group_norm_kernel.cu
: When the block size is less than the warp size,WarpReduce
will result in all zeros. It seems to be an internal problem of hipcub on DCU.