CUTLASS 3.6.0 (#1850)

* v3.6

* update changelog

* update readme

* fix typo

* fixing typos

* hopper gemm with weight prefetch

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
This commit is contained in:
Yujia Zhai
2024-10-09 12:33:27 -07:00
committed by GitHub
parent 0837a2a00a
commit cc3c29a81a
354 changed files with 105943 additions and 8203 deletions

View File

@@ -588,12 +588,14 @@ OpcodeClassNames = {
OpcodeClass.Simt: 'simt',
OpcodeClass.TensorOp: 'tensorop',
OpcodeClass.WmmaTensorOp: 'wmma_tensorop',
OpcodeClass.SparseTensorOp: 'sptensorop',
}
OpcodeClassTag = {
OpcodeClass.Simt: 'cutlass::arch::OpClassSimt',
OpcodeClass.TensorOp: 'cutlass::arch::OpClassTensorOp',
OpcodeClass.WmmaTensorOp: 'cutlass::arch::OpClassWmmaTensorOp',
OpcodeClass.SparseTensorOp: 'cutlass::arch::OpClassSparseTensorOp',
}
###################################################################################################