This op performs matrix-matrix-transpose multiplication of 4-d inputs as the following:
```
C[m1, n1, m0, n0] = sum_{k1, k0}(A[m1, k1, m0, k0] * B[n1, k1, n0, k0])
```
Reviewed By: Benoit
Differential Revision: https://reviews.llvm.org/D105244
This op performs matrix-matrix-transpose multiplication of 4-d inputs as the following:
```
C[m1, n1, m0, n0] = sum_{k1, k0}(A[m1, k1, m0, k0] * B[n1, k1, n0, k0])
```
Reviewed By: Benoit
Differential Revision: https://reviews.llvm.org/D105244