mirror of
https://github.com/tile-ai/tilelang.git
synced 2026-10-21 06:40:23 +08:00
Lei Wang
f2e99180d5
* remove llvm build * [Refactor] Update kernel compilation and profiling in examples - Replaced `tilelang.lower` with `tilelang.compile` in multiple example scripts to streamline kernel compilation. - Updated profiling calls to utilize the new `get_profiler` method, enhancing performance measurement consistency. - Adjusted assertions and benchmarking methods to align with the new profiling structure across various examples, ensuring correctness and clarity in performance evaluations. * lint fix * License Update * [Refactor] Improve code formatting and documentation in CUDA header and HIP runtime files - Adjusted formatting in `cuda.h` for better readability, including alignment of comments and struct fields. - Cleaned up whitespace and improved comment clarity in `rt_mod_hip.cc` to enhance code maintainability. * [Refactor] Enhance formatting and clarity in CUDA header and HIP runtime files - Improved comment alignment and readability in `cuda.h`. - Cleaned up whitespace and formatting in `rt_mod_hip.cc` to enhance maintainability. * lint fix * lint fix * lint fix * lint fix * fix * License update * [Enhancement] Update JITKernel to use artifact for kernel source - Assigned the generated artifact to `self.artifact` for better management. - Updated kernel source references to use `artifact.kernel_source` for consistency in execution backend handling. * lint fix * Add @tilelang.testing.requires_llvm decorator to vectorization tests * Enhance setup.py and env.py for library management - Added functionality to remove original files after copying in CMakeBuild. - Updated TVM_LIBRARY_PATH in env.py to include the PyPI build library path for better integration. * Refactor TVM_LIBRARY_PATH assignment for improved readability in env.py * Refactor CMakeBuild file handling in setup.py - Added a check to ensure the target library directory exists before copying .so files. - Improved the logic for creating the target directory and copying files to enhance robustness. * bugfix * Rename BuildTLDebug to BuildTileLangCUDAWithoutCompile and update registration. Add @tilelang.testing.requires_llvm decorator to multiple tests for LLVM requirement. * lint fix * Enhance TileLang code generation by adding support for device code generation without compilation. Updated `host_codegen` and `device_codegen` functions to include new transformations and registration for `tilelang_hip_without_compile`. Refactored JIT kernel adapters to accommodate host and device modules, improving overall integration and flexibility. * lint fix * Add support for C target in device code generation - Updated `device_codegen_without_compile` to include handling for the C target by registering the `tilelang_cpp` function. * [Enhancement] Implement auto-clear cache feature based on environment variable * Added TILELANG_CLEAR_CACHE environment variable to control cache clearing. * Updated CI workflow to set TILELANG_CLEAR_CACHE during testing. * Modified cache initialization to clear cache if TILELANG_CLEAR_CACHE is set to true. * [Refactor] Update kernel invocation and import paths in tests and cache * Changed kernel invocation in `test_tilelang_kernel_dequantize_gemm.py` to return the result. * Updated import statements in `test_tilelang_kernel_int4_gemm_mma.py` to use `bitblas` instead of `tilelang`. * Refactored paths for artifact and parameters in `kernel_cache.py` for better maintainability. * [Refactor] Clean up whitespace and improve code formatting in kernel_cache.py * Removed unnecessary blank lines and adjusted spacing for better readability in the KernelCache class. * Enhanced overall code formatting to align with project standards. * [Enhancement] Add bfloat16 test case and improve kernel caching logic * Introduced a new test case for bfloat16 matrix multiplication in `test_tilelang_kernel_gemm_mma_intrinsic.py`. * Updated `KernelCache` to handle multiple kernel source files and improve error handling during saving and loading. * Refactored `JITKernel` to support instantiation from a database, enhancing flexibility in kernel management. * Adjusted `CtypesKernelAdapter` and `CythonKernelAdapter` to utilize the new kernel loading mechanism from the database. * Improved code formatting and readability across several files. * lint fix * Update bfloat16 matrix multiplication test case to use larger dimensions for improved coverage
93 lines
2.7 KiB
Python
93 lines
2.7 KiB
Python
from tilelang import tvm as tvm
|
|
import tilelang as tl
|
|
import tilelang.language as T
|
|
import tilelang.testing
|
|
|
|
|
|
def modify(
|
|
with_B: bool = False,
|
|
with_bias: bool = False,
|
|
):
|
|
|
|
@T.prim_func
|
|
def main(
|
|
A: T.Buffer((64, 64)),
|
|
B: T.Buffer((64, 64)),
|
|
C: T.Buffer((64, 64)),
|
|
D: T.Buffer((64, 64)),
|
|
bias: T.Buffer((64, 64)),
|
|
):
|
|
if with_B:
|
|
if with_bias:
|
|
T.gemm(A, bias, D)
|
|
T.gemm(A, B, D)
|
|
else:
|
|
with T.block():
|
|
A_shared = T.alloc_shared((64, 64), dtype="float32")
|
|
C_shared = T.alloc_shared((64, 64), dtype="float32")
|
|
D_shared = T.alloc_shared((64, 64), dtype="float32")
|
|
T.copy(A, A_shared)
|
|
T.copy(C, C_shared)
|
|
T.gemm(A_shared, C_shared, D_shared)
|
|
T.copy(D_shared, D)
|
|
|
|
return main
|
|
|
|
|
|
def test_modify(with_B=False, with_bias=False):
|
|
tester = modify(with_B=with_B, with_bias=with_bias)
|
|
mod = tvm.IRModule({tester.attrs["global_symbol"]: tester})
|
|
mod2 = tl.transform.Simplify()(mod)
|
|
assert mod != mod2
|
|
|
|
|
|
def matmul(M, N, K, block_M, block_N, block_K, dtype="float16", accum_dtype="float"):
|
|
|
|
@T.prim_func
|
|
def main(
|
|
a: T.handle,
|
|
b: T.handle,
|
|
c: T.handle,
|
|
):
|
|
A = T.match_buffer(a, (M, K), dtype=dtype)
|
|
B = T.match_buffer(b, (K, N), dtype=dtype)
|
|
C = T.match_buffer(c, (M, N), dtype=accum_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 main
|
|
|
|
|
|
def test_matmul():
|
|
func = matmul(1024, 1024, 1024, 128, 128, 32)
|
|
mod = tvm.IRModule({func.attrs["global_symbol"]: func})
|
|
mod = tl.transform.Simplify()(mod)
|
|
kernel = tl.compile(mod["main"], out_idx=[2])
|
|
|
|
import torch
|
|
a = torch.randn(1024, 1024, dtype=torch.float16).cuda().half()
|
|
b = torch.randn(1024, 1024, dtype=torch.float16).cuda().half()
|
|
c = kernel(a, b)
|
|
|
|
ref_c = a @ b
|
|
ref_c = ref_c.float()
|
|
torch.testing.assert_close(c, ref_c, rtol=1e-2, atol=1e-2)
|
|
|
|
# Get CUDA Source
|
|
print(kernel.get_kernel_source())
|
|
|
|
|
|
if __name__ == "__main__":
|
|
tilelang.testing.main()
|