mirror of
https://github.com/tile-ai/tilelang.git
synced 2026-10-20 06:30:07 +08:00
Lei Wang
8cdc185bb4
* [Doc] Update documentation structure and content: add overview section, revise project name, and change theme to Furo * [Feature] Add device-side debug printing functions and integrate into kernel interface * lint fix * remove debug print * implement test for debug * lint fix * add some comments * Enhance fragment design and assert fragment print * enhance debug print * add test for msg * lint fix
105 lines
2.6 KiB
Python
105 lines
2.6 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.Buffer((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.JITKernel(program, target="cuda")
|
|
profiler = jit_kernel.get_profiler()
|
|
profiler.run_once()
|
|
|
|
|
|
def test_debug_print_buffer():
|
|
debug_print_buffer(16, 16)
|
|
|
|
|
|
def debug_print_buffer_conditional(M=16, N=16):
|
|
dtype = "float16"
|
|
|
|
@T.prim_func
|
|
def program(Q: T.Buffer((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.JITKernel(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.Buffer((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.JITKernel(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.Buffer((M, N), dtype)):
|
|
with T.Kernel(4, 4, 2, threads=128 * 2) as (bx, by, bz):
|
|
shared_buf = T.alloc_fragment([M, N], dtype)
|
|
for i, j in T.Parallel(M, N):
|
|
T.print(shared_buf[i, j])
|
|
|
|
jit_kernel = tilelang.JITKernel(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.Buffer((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.JITKernel(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()
|