CUTLASS 3.3.0 (#1167)
* Release 3.3.0 Adds support for mixed precision GEMMs On Hopper and Ampere Adds support for < 16B aligned GEMMs on Hopper Enhancements to EVT Enhancements to Python interface Enhancements to Sub-byte type handling in CuTe Several other bug-fixes and performance improvements. * minor doc update
This commit is contained in:
@@ -287,6 +287,10 @@ template <> struct OpcodeClassMap<arch::OpClassTensorOp> {
|
||||
static OpcodeClassID const kId = OpcodeClassID::kTensorOp;
|
||||
};
|
||||
|
||||
template <> struct OpcodeClassMap<arch::OpClassSparseTensorOp> {
|
||||
static OpcodeClassID const kId = OpcodeClassID::kSparseTensorOp;
|
||||
};
|
||||
|
||||
template <> struct OpcodeClassMap<arch::OpClassWmmaTensorOp> {
|
||||
static OpcodeClassID const kId = OpcodeClassID::kWmmaTensorOp;
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user