ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-02 21:27:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make sure all strides in ComputePtrOffset are at least value initialized to avoid undefined strides. Not convinced this struct is properly initialized in other code / future code.

Browse Source
This commit is contained in:
kiefer
2025-10-01 07:59:42 +00:00
parent 28706e6173
commit d0f59a5ebe
1 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_utils.hpp
View File

@@ -198,10 +198,10 @@ struct ComputePtrOffsetOfStridedBatch<NumATensor,
return static_cast<long_index_t>(g_idx) * BatchStrideE_;
}
Array<long_index_t, NumATensor> BatchStrideA_;
Array<long_index_t, NumBTensor> BatchStrideB_;
Array<long_index_t, NumDTensor> BatchStrideDs_;
long_index_t BatchStrideE_;
Array<long_index_t, NumATensor> BatchStrideA_{};
Array<long_index_t, NumBTensor> BatchStrideB_{};
Array<long_index_t, NumDTensor> BatchStrideDs_{};
long_index_t BatchStrideE_{};
long_index_t& BatchStrideC_ = BatchStrideE_; // alias for kernels without multiple D
};
@@ -253,10 +253,10 @@ struct ComputePtrOffsetOfStridedBatch<NumATensor,
return static_cast<long_index_t>(g_idx) * BatchStrideE_;
}
long_index_t BatchStrideA_;
long_index_t BatchStrideB_;
Array<long_index_t, NumDTensor> BatchStrideDs_;
long_index_t BatchStrideE_;
long_index_t BatchStrideA_{};
long_index_t BatchStrideB_{};
Array<long_index_t, NumDTensor> BatchStrideDs_{};
long_index_t BatchStrideE_{};
long_index_t& BatchStrideC_ = BatchStrideE_; // alias for kernels without multiple D
};