↓ 1 callersFunctionrun_alloc_var(
N,
block_N,
dtype,
min=None,
max=None,
)
testing/python/language/test_tilelang_language_alloc.py:26
↓ 1 callersFunctionrun_atomic_add(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:25
↓ 1 callersFunctionrun_atomic_add_auto_vectorized(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:218
↓ 1 callersFunctionrun_atomic_add_complicated_parallel(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:257
↓ 1 callersFunctionrun_atomic_max(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:432
↓ 1 callersFunctionrun_atomic_memory_order(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:51
↓ 1 callersFunctionrun_atomic_min(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:465
↓ 1 callersFunctionrun_cutedsl_kernel_do_bench(
M, N, K, trans_A, trans_B, in_dtype, out_dtype, dtypeAccum, block_M, block_N, block_K, num_stages=3, num
testing/python/jit/test_tilelang_jit_cutedsl.py:237
↓ 1 callersFunctionrun_cutedsl_kernel_multi_stream(
M, N, K, trans_A, trans_B, in_dtype, out_dtype, dtypeAccum, block_M, block_N, block_K, num_stages=3, num
testing/python/jit/test_tilelang_jit_cutedsl.py:277
↓ 1 callersFunctionrun_cython_dynamic_shape_with_out_idx(
M, N, K, trans_A, trans_B, in_dtype, out_dtype, dtypeAccum, block_M, block_N, block_K, num_stages=3, num
testing/python/jit/test_tilelang_jit_gemm_cython.py:309
↓ 1 callersFunctionrun_cython_kernel_do_bench(
M, N, K, trans_A, trans_B, in_dtype, out_dtype, dtypeAccum, block_M, block_N, block_K, num_stages=3, num
testing/python/jit/test_tilelang_jit_gemm_cython.py:177
↓ 1 callersFunctionrun_cython_kernel_multi_stream(
M, N, K, trans_A, trans_B, in_dtype, out_dtype, dtypeAccum, block_M, block_N, block_K, num_stages=3, num
testing/python/jit/test_tilelang_jit_gemm_cython.py:215
↓ 1 callersFunctionrun_gemm(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
maint/gemm/correctness_evaluation_tcgen05.py:94
↓ 1 callersFunctionrun_gemm(
M,
N,
K,
in_dtype,
out_dtype,
accum_dtype,
block_M,
block_N,
block_K,
maint/gemm/correctness_evaluation_tcgen05_2cta.py:93
↓ 1 callersFunctionrun_gemm(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/jit/test_tilelang_jit_callback.py:55
↓ 1 callersFunctionrun_gemm_batched(
batch,
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
b
testing/python/kernel/test_tilelang_kernel_gemm_batched.py:55
↓ 1 callersFunctionrun_gemm_jit_kernel(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/jit/test_tilelang_jit_cutedsl.py:162
↓ 1 callersFunctionrun_gemm_jit_kernel(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/jit/test_tilelang_jit_tvm_ffi.py:101
↓ 1 callersFunctionrun_gemm_jit_kernel(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/jit/test_tilelang_jit_gemm_cython.py:103
↓ 1 callersFunctionrun_gemm_jit_kernel(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/jit/test_tilelang_jit_callback.py:171
↓ 1 callersFunctionrun_gemm_jit_kernel(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/jit/test_tilelang_jit_nvrtc.py:101
↓ 1 callersFunctionrun_gemm_kernel_jit(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/jit/test_tilelang_jit_gemm.py:56
↓ 1 callersFunctionrun_gemm_rr(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/tilelibrary/test_tilelang_tilelibrary_gemm_sp.py:594
↓ 1 callersFunctionrun_gemm_rr_false_true(m, n, k, in_dtype, out_dtype, accum_dtype, num_threads=128)
maint/gemm/correctness_evaluation.py:495
↓ 1 callersFunctionrun_gemm_rs(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/tilelibrary/test_tilelang_tilelibrary_gemm_sp.py:253
↓ 1 callersFunctionrun_gemm_rs(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/kernel/test_tilelang_kernel_gemm.py:482
↓ 1 callersFunctionrun_gemm_rs_false_true(m, n, k, in_dtype, out_dtype, accum_dtype, num_threads=128)
maint/gemm/correctness_evaluation.py:463
↓ 1 callersFunctionrun_gemm_sr(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/tilelibrary/test_tilelang_tilelibrary_gemm_sp.py:421
↓ 1 callersFunctionrun_gemm_sr(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/kernel/test_tilelang_kernel_gemm.py:362
↓ 1 callersFunctionrun_gemm_sr_false_true(m, n, k, in_dtype, out_dtype, accum_dtype, num_threads=128)
maint/gemm/correctness_evaluation.py:479
↓ 1 callersFunctionrun_gemm_with_stride_ss(M: int, N: int, K: int, block_M: int, block_N: int, block_K: int)
testing/python/kernel/test_tilelang_kernel_gemm_with_stride.py:46