(iv, tld)
| 404 | |
| 405 | @tilelang.jit |
| 406 | def var_init_kernel(iv, tld): |
| 407 | @T.prim_func |
| 408 | def kernel(out: T.Tensor((N,), tld)) -> None: |
| 409 | with T.Kernel(1, threads=N) as _: |
| 410 | v = T.alloc_var(tld, init=iv) |
| 411 | for i in T.Parallel(N): |
| 412 | out[i] = v |
| 413 | |
| 414 | return kernel |
| 415 | |
| 416 | out = torch.zeros(N, dtype=torch_dtype, device="cuda") |
| 417 | var_init_kernel(init_val, tl_dtype)(out) |
no outgoing calls
no test coverage detected
searching dependent graphs…