github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-07 22:23:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

assembly gemm clean ups, instructions for cli (#13892)

Browse Source
This commit is contained in:
qazal
2025-12-30 16:14:06 +09:00
committed by GitHub
parent d7e1f26e3d
commit b557c46233
3 changed files with 11 additions and 2926 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2922
extra/gemm/asm/gemm.s
View File

File diff suppressed because it is too large Load Diff

9
extra/gemm/asm/test.py
View File

@@ -1,7 +1,7 @@
# Run assembly on the AMD runtime and check correctness
# VIZ=2 to profile
import pathlib
from tinygrad import Tensor, Device, dtypes
from tinygrad import Tensor, Device, dtypes, Context
from tinygrad.engine.realize import ExecItem, CompiledRunner
from tinygrad.renderer import ProgramSpec
from tinygrad.uop.ops import track_rewrites, UOp
@@ -55,9 +55,10 @@ def get_asm_prg() -> ProgramSpec:
eis.append(ExecItem(ast, [C_asm.uop.buffer, from_torch(B).uop.buffer, from_torch(A).uop.buffer], fixedvars={"SZ":N, "NUM_WG":NUM_WG},
prg=CompiledRunner(get_asm_prg())))
for ei in eis:
et = ei.run(wait=True)
print(f"{(N*N*N*2 / et)*1e-12:.2f} REAL TFLOPS")
with Context(DEBUG=2):
for ei in eis:
et = ei.run(wait=True)
print(f"{(N*N*N*2 / et)*1e-12:.2f} REAL TFLOPS")
# ** correctness