Functionkernel(data, kernel, S, D, P, block_M, block_N, block_K, num_stages, threads, dtype=T.float16, accum_dtype=T.float32
examples/analyze/example_conv_analyze.py:20
Functionkernel(x: T.Tensor((N,), T.float32), y: T.Tensor((N,), T.float32))
testing/python/components/test_cuda_restrict_codegen.py:20
Functionkernel(
A: T.Tensor((32,), T.float16),
B: T.Tensor((32,), T.float16),
C: T.Tensor((32,), T.f
testing/python/components/test_cuda_shared_memory_alias_codegen.py:9
Functionkernel(a: T.Tensor((length,), dtype), out: T.Tensor((1,), dtype))
testing/python/language/test_tilelang_language_reduce_maxmin_nan.py:22
Functionkernel(inp: T.Tensor((1,), T.int32), out: T.Tensor((1,), T.int32))
testing/python/issue/test_tilelang_issue_2188.py:19
Functionkernel(status: T.Tensor((num_tiles,), T.int32), out: T.Tensor((1,), T.int32))
testing/python/issue/test_tilelang_issue_2123.py:13
Functionkernel(
A: T.Tensor((M, K), T.float16),
B: T.Tensor((K, N), T.float16),
C: T.Tensor((M, N),
testing/python/transform/test_tilelang_transform_inject_set_max_nreg.py:172
Functionkernel(
A: T.Tensor((M, N), "float16"),
B: T.Tensor((M, N), "float16"),
)
testing/python/cuda/test_tma_multicast_demo.py:11
Functionkernel_body_annot(x: T.Tensor((N,), T.float32), y: T.Tensor((N,), T.float32))
testing/python/components/test_cuda_restrict_codegen.py:35
Methodldmatrix_a(self, A_local_buf, A_buf, ki, rk=0, pid_m=None, pid_n=None)
tilelang/rocm/intrinsics/mfma_macro_generator.py:846
Methodldmatrix_b(self, B_local_buf, B_buf, ki, rk=0, pid_m=None, pid_n=None)
tilelang/rocm/intrinsics/mfma_macro_generator.py:920
Methodlower(
self, layout_map: dict, target: Target, thread_bounds: Range, thread_var: tirx.Var, mbar_phase_expr:
tilelang/rocm/op/gemm/gemm_wmma.py:73