CUTLASS 2.10 (#615)

Co-authored-by: Aniket Shivam <ashivam@nvidia.com>
2022-09-03 18:48:46 -04:00
parent ca23ff7924
commit b72cbf957d
289 changed files with 43708 additions and 2513 deletions
@@ -188,6 +188,7 @@ public:
    IteratorA iterator_A,                             ///< iterator over A operand in global memory
    IteratorB iterator_B,                             ///< iterator over B operand in global memory
    FragmentC const &src_accum,                       ///< source accumulator tile
+    int gemm_k_iterations_per_channel = 0,             ///< number of iterations per channel
    TransformA transform_A = TransformA(),            ///< transformation applied to A fragment
    TransformB transform_B = TransformB()) {          ///< transformation applied to B fragment