mirror of
https://github.com/tile-ai/tilelang.git
synced 2026-10-22 06:50:25 +08:00
5f202fe5c1
* tilelang frontend v2 * syntax sugar: defining a local var by annotation * [Refactor] fix type linting warning like `T.float32` * Add tl.local_var_init for new tl.float32 * allow passing default argument as function annotation * allow default arguments as annotation * fix lint error * minor fix * [Refactor] refactor tilelang.jit and tilelang.autotune * minor fix * minor fix * minor fix * fix metal get function name * add par_compile impl and tests * Type consistency on tvm datatype 1. isinstance(tl.float32, tvm.DataType) == True 2. Allow `tl.float32` as function annotations 3. Allow `tl.float32` as argument to be passed to `tl.alloc` or other functions * fix lint error * add more warning in frontend * update tvm version * Minor fix on tvm_ffi annotations * add document and examples * fix lint error * Simplify index calculations in example_chunk_o_bwd.py Refactor index calculations for dg_last_fragment assignment. * minor fix * lint fix --------- Co-authored-by: Lei Wang <leiwang1999@outlook.com> Co-authored-by: Lei Wang <34334180+LeiWang1999@users.noreply.github.com>
47 lines
1.3 KiB
Python
47 lines
1.3 KiB
Python
import tilelang
|
|
import tilelang.testing
|
|
import tilelang.language as T
|
|
import torch
|
|
|
|
|
|
@tilelang.jit(
|
|
pass_configs={
|
|
tilelang.PassConfigKey.TL_DISABLE_TMA_LOWER: True,
|
|
tilelang.PassConfigKey.TL_DISABLE_WARP_SPECIALIZED: True,
|
|
},)
|
|
def chain_equal(N, block_size, dtype="float32"):
|
|
|
|
@T.prim_func
|
|
def main(
|
|
A: T.Tensor((N,), dtype),
|
|
B: T.Tensor((N,), dtype),
|
|
C: T.Tensor((N,), dtype),
|
|
):
|
|
with T.Kernel(T.ceildiv(N, block_size), threads=block_size) as bx:
|
|
for lane in T.Parallel(block_size):
|
|
idx = bx * block_size + lane
|
|
A[idx] = B[idx] = C[idx] = 1
|
|
|
|
return main
|
|
|
|
|
|
def run_chain_equal(N=128, block_size=64, dtype="float32"):
|
|
kernel = chain_equal(N, block_size, dtype)
|
|
A = torch.zeros((N,), dtype=torch.float32, device="cuda")
|
|
B = torch.zeros((N,), dtype=torch.float32, device="cuda")
|
|
C = torch.zeros((N,), dtype=torch.float32, device="cuda")
|
|
kernel(A, B, C)
|
|
ref = torch.ones_like(A)
|
|
torch.testing.assert_close(A, ref)
|
|
torch.testing.assert_close(B, ref)
|
|
torch.testing.assert_close(C, ref)
|
|
|
|
|
|
@tilelang.testing.requires_cuda
|
|
def test_chain_equal():
|
|
run_chain_equal()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
tilelang.testing.main()
|