CUTLASS 2.4 (Implicit GEMM convolution) (#147)

CUTLASS 2.4 (Implicit GEMM Convolution)

Co-authored-by: Manish Gupta <manigupta@nvidia.com>, Haicheng Wu <haichengw@nvidia.com>, Dustyn Blasig <dblasig@nvidia.com>, Andrew Kerr <akerr@nvidia.com>
This commit is contained in:
Manish Gupta
2020-11-19 21:25:25 -08:00
committed by GitHub
co-authored by Manish Gupta <manigupta@nvidia.com>, Haicheng Wu <haichengw@nvidia.com>, Dustyn Blasig <dblasig@nvidia.com>, Andrew Kerr <akerr@nvidia.com>
parent c2b80ad4e4
commit 6615010cd0
224 changed files with 43939 additions and 1061 deletions
@@ -582,7 +582,7 @@ public:
semaphore.fetch();
// Indicate which position in a serial reduction the output operator is currently updating
output_op.set_k_partition(threadblock_tile_offset.k());
output_op.set_k_partition(threadblock_tile_offset.k(), params.grid_tiled_shape.k());
}
}
else if (params.mode == GemmUniversalMode::kGemmSplitKParallel) {