mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-11 17:00:18 +00:00
[CK_TILE] Grouped Convolution Backward Data Direct Load (#6624) ## Proposed changes Add Grouped Convolution Backward Data with Direct Load into DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3 device implementation. This enables direct global memory loading (bypassing LDS) for the backward data convolution path on gfx950, following the same pattern used in both backward weight and forward convolution. Direct load convolution backward data improves performance by avoiding LDS round-trips for certain configurations on gfx950, which supports a wider range of instructions. Currently correctness is checked only at usage point, but should be extended to a standalone UT in the future.