mirror of
https://github.com/tile-ai/tilelang.git
synced 2026-10-22 06:50:25 +08:00
Lei WangandZhiwen Mo
f8dc61c02c
* test: trim CI runtime for slow Python suites * remove useless test * Update TVM submodule to latest commit and remove manual device assert test from CI. Replace with a call to tilelang.testing.main(). * lint fix * fix * revert test for eager jit --------- Co-authored-by: Zhiwen Mo <zm125@ic.ac.uk>
57 lines
1.6 KiB
Python
57 lines
1.6 KiB
Python
import tilelang
|
|
import tilelang.language as T
|
|
import pytest
|
|
|
|
|
|
@tilelang.jit(out_idx=[-1])
|
|
def matmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32):
|
|
@T.prim_func
|
|
def gemm(
|
|
A: T.Tensor((M, K), dtype),
|
|
B: T.Tensor((K, N), dtype),
|
|
C: T.Tensor((M, N), dtype),
|
|
):
|
|
with T.Kernel(T.ceildiv(N, block_N), T.ceildiv(M, block_M), threads=128) as (bx, by):
|
|
A_shared = T.alloc_shared((block_M, block_K), dtype)
|
|
B_shared = T.alloc_shared((block_K, block_N), dtype)
|
|
C_local = T.alloc_fragment((block_M, block_N), accum_dtype)
|
|
|
|
T.clear(C_local)
|
|
for k in T.Pipelined(T.ceildiv(K, block_K), num_stages=3):
|
|
T.copy(A[by * block_M, k * block_K], A_shared)
|
|
T.copy(B[k * block_K, bx * block_N], B_shared)
|
|
T.gemm(A_shared, B_shared, C_local)
|
|
|
|
T.copy(C_local, C[by * block_M, bx * block_N])
|
|
|
|
return gemm
|
|
|
|
|
|
@pytest.mark.perf
|
|
def test_profiler():
|
|
kernel = matmul(1024, 1024, 1024, 128, 128, 32)
|
|
|
|
import torch
|
|
|
|
a = torch.randn(1024, 1024).cuda().half()
|
|
b = torch.randn(1024, 1024).cuda().half()
|
|
|
|
c = kernel(a, b)
|
|
ref_c = a @ b
|
|
torch.testing.assert_close(c, ref_c, rtol=1e-2, atol=1e-2)
|
|
|
|
# benchmark
|
|
profiler = kernel.get_profiler()
|
|
|
|
# use cupti backend
|
|
cupti_latency = profiler.do_bench(backend="cupti")
|
|
|
|
# use event backend
|
|
event_latency = profiler.do_bench(backend="event")
|
|
print(f"cupti Latency: {cupti_latency}ms")
|
|
print(f"event Latency: {event_latency}ms")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
tilelang.testing.main()
|