CUTLASS 3.1 (#915)

Co-authored-by: Aniket Shivam <ashivam@nvidia.com>
2023-04-14 20:19:34 -07:00
parent 9b8166e3f0
commit d572cc1aab
482 changed files with 37184 additions and 16419 deletions
--- a/examples/09_turing_tensorop_conv2dfprop/turing_tensorop_conv2dfprop.cu
+++ b/examples/09_turing_tensorop_conv2dfprop/turing_tensorop_conv2dfprop.cu
@ -555,6 +555,7 @@ Result profile_convolution(Options const &options) {
      LayoutOutput,
      ElementComputeEpilogue,
      ElementAccumulator,
+      ElementOutput,
      cutlass::NumericConverterClamp<ElementOutput, ElementComputeEpilogue>
    >(
      problem_size,