mirror of
https://github.com/tile-ai/tilelang.git
synced 2026-10-21 06:40:23 +08:00
Lei Wang
c8fc0cbbcd
* bump version into v0.1.0 * [Enhancement] Add custom develop command for editable installs and update .gitignore * [Documentation] Update README to include system dependencies installation instructions * [Build] Update setup.py to support library file copying for both release and develop modes * [Build] Refactor library file copying logic in setup.py * [Documentation] Remove unnecessary install section header in Installation.md * [Build] Add tox configuration and local distribution script for multi-Python version support * [Build] Improve git submodule update function with better error handling * [Build] Update LLVM configuration path in ROCm installation script * [Build] Add .tox/ to .gitignore for tox testing environment * [Build] Add support for TVM prebuild path configuration in CMakeLists.txt * [Cleanup] Remove unused TVM runtime error codes header * [Cleanup] Fix TVM grid constant type reference in CUDA module * [Cleanup] Remove unused customized_code function from IR module * [Feature] Add TileLang thread synchronization and storage access analysis passes * [Build] Reorder DLL search path directories for more flexible library loading * [Refactor] Improve thread synchronization and library path handling - Rename ThreadSync and TileLangThreadSync functions in C++ code - Update Python docstring for ThreadSync with more detailed description - Reorder library path detection in tilelang environment setup - Minor comment and code cleanup in CUDA and warp specialization modules * [Refactor] Improve thread synchronization code style and formatting - Standardize pointer type spacing in storage_access.h and storage_access.cc - Update whitespace and indentation in thread_storage_sync.cc - Reorder include statements in thread_partial_sync.cc - Minor code formatting improvements across thread synchronization files * [Refactor] Fix global function registration for ThreadSync - Correct global function registration to use ThreadSync instead of TileLangThreadSync - Update TVM global registration to match recent refactoring efforts * [Refactor] Simplify ThreadSync global function registration - Remove unnecessary whitespace in global function registration - Compact the TVM global registration line for ThreadSync * [Feature] Add WebGPU code generation support in TileLang - Implement WebGPU code generator (codegen_webgpu.cc and codegen_webgpu.h) - Add WebGPU target support in lower.py and target.py - Update CMakeLists.txt to include WebGPU codegen source files - Introduce WebGPU-specific code generation for WGSL shader language * [Refactor] Improve WebGPU code generation formatting and readability - Enhance code formatting in codegen_webgpu.cc and codegen_webgpu.h - Standardize pointer type spacing and indentation - Improve line breaks and reduce line length for better readability - Minor code style improvements in WebGPU code generation * [Test] Add WebGPU matrix multiplication code generation test - Implement test_webgpu_codegen.py for WebGPU matrix multiplication - Add assert_gemm_codegen function to validate WebGPU code generation - Include basic matrix multiplication kernel test case * Update README with WebGPU codegen support announcement
64 lines
1.7 KiB
Python
64 lines
1.7 KiB
Python
# Copyright (c) Microsoft Corporation.
|
|
# Licensed under the MIT License.
|
|
|
|
import tilelang
|
|
from tilelang import tvm as tvm
|
|
import tilelang.testing
|
|
import tilelang.language as T
|
|
|
|
|
|
def matmul(M, N, K, block_M, block_N, block_K, dtype="float16", accum_dtype="float"):
|
|
|
|
@T.prim_func
|
|
def main(
|
|
A: T.Buffer((M, K), dtype),
|
|
B: T.Buffer((K, N), dtype),
|
|
C: T.Buffer((M, N), dtype),
|
|
):
|
|
# Initialize Kernel Context
|
|
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 ko in T.Pipelined(T.ceildiv(K, block_K), num_stages=0):
|
|
T.copy(A[by * block_M, ko * block_K], A_shared, coalesced_width=2)
|
|
T.copy(B[ko * block_K, bx * block_N], B_shared, coalesced_width=2)
|
|
|
|
for i, j, k in T.Parallel(block_M, block_N, block_K):
|
|
C_local[i, j] += A_shared[i, k] * B_shared[k, j]
|
|
|
|
T.copy(C_local, C[by * block_M, bx * block_N], coalesced_width=2)
|
|
|
|
return main
|
|
|
|
|
|
def assert_gemm_codegen(
|
|
M,
|
|
N,
|
|
K,
|
|
block_M,
|
|
block_N,
|
|
block_K,
|
|
dtype="float16",
|
|
accum_dtype="float",
|
|
):
|
|
func = matmul(M, N, K, block_M, block_N, block_K, dtype=dtype, accum_dtype=accum_dtype)
|
|
print(func)
|
|
|
|
rt_mod, _ = tilelang.lower(func, target="webgpu")
|
|
|
|
src_code = rt_mod.imported_modules[0].get_source()
|
|
|
|
assert src_code is not None
|
|
|
|
|
|
def test_gemm_codegen():
|
|
assert_gemm_codegen(1024, 1024, 1024, 16, 16, 16)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
tilelang.testing.main()
|