mirror of
https://github.com/tile-ai/tilelang.git
synced 2026-10-21 06:40:23 +08:00
Lei Wang
bf8a6fc142
* [Refactor] Improve flash attention example and layout comparison logic - Removed unnecessary annotation for `lse_local_split` in the flash attention example to streamline the code. - Updated the handling of `lse_local_split` to utilize parallel processing for better performance. - Refactored kernel compilation and profiling logic to enhance clarity and maintainability in the flash attention example. - Added a condition in `FragmentNode::IsEqual` to handle broadcast cases, improving the robustness of layout comparisons. * lint fix * [Enhancement] Add support for shared memory scope in Fill operation - Introduced handling for `shared.dyn` and `shared` memory scopes in the Fill operation. - Implemented parallel operation and layout inference for improved performance in shared memory scenarios. - Updated thread loop partitioning and vectorization logic to accommodate new memory scope handling. * [Refactor] Remove deprecated decorator and enhance Cython kernel handling - Removed the deprecated decorator from the main module and added a new implementation in the utils module for better organization. - Introduced a pointer map in the Cython kernel adapter to manage pointer arguments, improving runtime shape resolution. - Updated the Cython kernel wrapper to utilize the new pointer map for handling kernel arguments. - Enhanced error checking in the tensor utility functions to ensure static shapes are enforced. - Added a new proxy module for buffer and tensor handling, streamlining the interface for TIR programs. * [Feature] Add matrix multiplication test and kernel implementation - Introduced a new test file `test_tilelang_language_ptr.py` that implements a matrix multiplication function using TileLang's primitives. - The `matmul_test` function defines a kernel for performing tile-level GEMM operations with customizable block sizes and data types. - Added a `run_matmul` function to compile and execute the kernel, along with a test function to validate the implementation. - Updated the `proxy.py` file to enhance type handling for buffer and tensor proxies, ensuring compatibility with TIR programs. - Minor formatting improvements in `deprecated.py` for better readability. * lint fix * [Refactor] Update tensor creation in matrix multiplication test - Replaced `T.Tensor.from_ptr` with `T.make_tensor` in `matmul_test` for improved clarity and consistency. - Updated imports in `__init__.py` to include `make_tensor`. - Added `make_tensor` function in `proxy.py` to streamline tensor creation from pointers. * [Refactor] Update tensor definitions across multiple files - Replaced instances of `T.Tensor` with updated tensor definitions in various benchmark and example files to enhance consistency and clarity. - Adjusted tensor shapes and types in functions related to matrix multiplication, attention mechanisms, and other operations. - Improved documentation in README and example files to reflect changes in tensor usage. * lint fix * [Refactor] Update tensor types in attention and matrix multiplication examples - Replaced instances of `T.Tensor` with `T.SharedTensor` and `T.FragmentTensor` in various attention and matrix multiplication functions to improve consistency and clarity. - Adjusted tensor definitions in benchmark and example files to align with the new tensor types. - Enhanced the overall structure and readability of the code by standardizing tensor usage across multiple files. * lint fix * [Refactor] Update tensor types in GEMM example and test files - Replaced instances of `T.Tensor` with `T.LocalTensor` and `T.Buffer` in the GEMM example and related test functions to improve consistency and clarity. - Enhanced the overall structure of the code by standardizing tensor usage across multiple files, aligning with recent updates in tensor definitions. * [Refactor] Update tensor usage in customize.py - Replaced instances of `T.Tensor` with `T.Buffer` in the `reshape` and `view` functions to enhance consistency with recent tensor definitions. - Improved code clarity by standardizing buffer usage across the file. * [Refactor] Update tensor types in test_tilelang_transform_annotate_device_regions.py - Replaced instances of `T.Tensor` with `T.Buffer` in the `before` and `expected` methods of the `TestAnnotateThreadExtent` and `TestAnnotateDeviceScope` classes to enhance consistency with recent tensor definitions. - Improved code clarity by standardizing buffer usage across the test file. * [Refactor] Update tensor types to SharedBuffer and FragmentBuffer - Replaced instances of `T.SharedTensor` and `T.FragmentTensor` with `T.SharedBuffer` and `T.FragmentBuffer` across multiple benchmark, example, and test files to enhance consistency with recent tensor definitions. - Improved code clarity and structure by standardizing buffer usage in attention and matrix multiplication functions. * [Refactor] Introduce Tensor alias for Buffer in proxy.py - Added a new alias `Tensor` for `Buffer` in `proxy.py` to facilitate JIT compilation, ensuring that inputs and outputs are mapped with `torch.Tensor`. - This change enhances clarity and consistency in tensor usage across the codebase.
106 lines
2.7 KiB
Python
106 lines
2.7 KiB
Python
# type: ignore
|
|
|
|
import tilelang
|
|
import tilelang.testing
|
|
import tilelang.language as T
|
|
|
|
|
|
def debug_print_buffer(M=16, N=16, dtype="float16"):
|
|
|
|
@T.prim_func
|
|
def program(Q: T.Tensor((M, N), dtype)):
|
|
with T.Kernel(4, 4, 2, threads=128 * 2) as (bx, by, bz):
|
|
shared_buf = T.alloc_shared([M, N], dtype)
|
|
T.print(shared_buf)
|
|
|
|
jit_kernel = tilelang.compile(program, target="cuda")
|
|
profiler = jit_kernel.get_profiler()
|
|
profiler.run_once()
|
|
|
|
|
|
def test_debug_print_buffer():
|
|
debug_print_buffer(16, 16, dtype="float")
|
|
debug_print_buffer(16, 16, dtype="float16")
|
|
debug_print_buffer(16, 16, dtype="uint8")
|
|
|
|
|
|
def debug_print_buffer_conditional(M=16, N=16):
|
|
dtype = "float16"
|
|
|
|
@T.prim_func
|
|
def program(Q: T.Tensor((M, N), dtype)):
|
|
with T.Kernel(4, 4, 2, threads=128 * 2) as (bx, by, bz):
|
|
shared_buf = T.alloc_shared([M, N], dtype)
|
|
|
|
if bx == 0 and by == 0 and bz == 0:
|
|
T.print(shared_buf)
|
|
|
|
jit_kernel = tilelang.compile(program, target="cuda")
|
|
profiler = jit_kernel.get_profiler()
|
|
profiler.run_once()
|
|
|
|
|
|
def test_debug_print_buffer_conditional():
|
|
debug_print_buffer_conditional(16, 16)
|
|
|
|
|
|
def debug_print_value_conditional(M=16, N=16):
|
|
dtype = "float16"
|
|
|
|
@T.prim_func
|
|
def program(Q: T.Tensor((M, N), dtype)):
|
|
with T.Kernel(4, 4, 2, threads=128 * 2) as (bx, by, bz):
|
|
tid = T.get_thread_binding()
|
|
if tid == 0:
|
|
T.print(bx + by + bz)
|
|
|
|
jit_kernel = tilelang.compile(program, target="cuda")
|
|
profiler = jit_kernel.get_profiler()
|
|
profiler.run_once()
|
|
|
|
|
|
def test_debug_print_value_conditional():
|
|
debug_print_value_conditional(16, 16)
|
|
|
|
|
|
def debug_print_register_files(M=16, N=16):
|
|
dtype = "float16"
|
|
|
|
@T.prim_func
|
|
def program(Q: T.Tensor((M, N), dtype)):
|
|
with T.Kernel(4, 4, 2, threads=128 * 2) as (bx, by, bz):
|
|
register_buf = T.alloc_fragment([M, N], dtype)
|
|
for i, j in T.Parallel(M, N):
|
|
T.print(register_buf[i, j])
|
|
|
|
jit_kernel = tilelang.compile(program, target="cuda")
|
|
profiler = jit_kernel.get_profiler()
|
|
profiler.run_once()
|
|
|
|
|
|
def test_debug_print_register_files():
|
|
debug_print_register_files(16, 16)
|
|
|
|
|
|
def debug_print_msg(M=16, N=16):
|
|
dtype = "float16"
|
|
|
|
@T.prim_func
|
|
def program(Q: T.Tensor((M, N), dtype)):
|
|
with T.Kernel(4, 4, 2, threads=128 * 2) as (bx, by, bz):
|
|
tid = T.get_thread_binding()
|
|
if tid == 0:
|
|
T.print(bx + by + bz, msg="hello world")
|
|
|
|
jit_kernel = tilelang.compile(program, target="cuda")
|
|
profiler = jit_kernel.get_profiler()
|
|
profiler.run_once()
|
|
|
|
|
|
def test_debug_print_msg():
|
|
debug_print_msg(16, 16)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
tilelang.testing.main()
|