(A)
| 59 | A = torch.randn(M, N, dtype=getattr(torch, dtype)).cuda() |
| 60 | |
| 61 | def ref_program(A): |
| 62 | ref_b = torch.empty_like(A) |
| 63 | for i in range(M // block_M): |
| 64 | for j in range(N // block_N): |
| 65 | ref_b[i * block_M : (i + 1) * block_M, j * block_N : (j + 1) * block_N] = A[ |
| 66 | i * block_M : (i + 1) * block_M, j * block_N : (j + 1) * block_N |
| 67 | ].cumsum(dim=dim) |
| 68 | if reverse: |
| 69 | ref_b[i * block_M : (i + 1) * block_M, j * block_N : (j + 1) * block_N] = ( |
| 70 | A[i * block_M : (i + 1) * block_M, j * block_N : (j + 1) * block_N] |
| 71 | .flip(dims=[dim]) |
| 72 | .cumsum(dim=dim) |
| 73 | .flip(dims=[dim]) |
| 74 | ) |
| 75 | return ref_b |
| 76 | |
| 77 | tilelang_res = jit_kernel(A) |
| 78 | ref_res = ref_program(A) |
no test coverage detected
searching dependent graphs…