github/ROCm
1
1
Fork 0
mirror of https://github.com/ROCm/ROCm.git synced 2026-04-05 03:01:17 -04:00
Code Issues Packages Projects Releases Wiki Activity

[TUTORIALS] Remove unneeded quantiles parameter (#2408)

Browse Source 
The fix is to remove the quantiles parameter in both the triton and
torch calls for the benchmark.
This commit is contained in:
evelynmitchell
2023-09-28 11:48:38 -06:00
committed by GitHub
parent 721bdebee1
commit 99af23f6f4
3 changed files with 7 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
python/tutorials/01-vector-add.py
View File

@@ -124,11 +124,10 @@ print(
def benchmark(size, provider):
x = torch.rand(size, device='cuda', dtype=torch.float32)
y = torch.rand(size, device='cuda', dtype=torch.float32)
quantiles = [0.5, 0.2, 0.8]
if provider == 'torch':
ms, min_ms, max_ms = triton.testing.do_bench(lambda: x + y, quantiles=quantiles)
ms, min_ms, max_ms = triton.testing.do_bench(lambda: x + y)
if provider == 'triton':
ms, min_ms, max_ms = triton.testing.do_bench(lambda: add(x, y), quantiles=quantiles)
ms, min_ms, max_ms = triton.testing.do_bench(lambda: add(x, y))
gbps = lambda ms: 12 * size / ms * 1e-6
return gbps(ms), gbps(max_ms), gbps(min_ms)

7
python/tutorials/02-fused-softmax.py
View File

@@ -180,13 +180,12 @@ assert torch.allclose(y_triton, y_torch), (y_triton, y_torch)
)
def benchmark(M, N, provider):
x = torch.randn(M, N, device='cuda', dtype=torch.float32)
quantiles = [0.5, 0.2, 0.8]
if provider == 'torch-native':
ms, min_ms, max_ms = triton.testing.do_bench(lambda: torch.softmax(x, axis=-1), quantiles=quantiles)
ms, min_ms, max_ms = triton.testing.do_bench(lambda: torch.softmax(x, axis=-1))
if provider == 'triton':
ms, min_ms, max_ms = triton.testing.do_bench(lambda: softmax(x), quantiles=quantiles)
ms, min_ms, max_ms = triton.testing.do_bench(lambda: softmax(x))
if provider == 'torch-jit':
ms, min_ms, max_ms = triton.testing.do_bench(lambda: naive_softmax(x), quantiles=quantiles)
ms, min_ms, max_ms = triton.testing.do_bench(lambda: naive_softmax(x))
gbps = lambda ms: 2 * x.nelement() * x.element_size() * 1e-9 / (ms * 1e-3)
return gbps(ms), gbps(max_ms), gbps(min_ms)

5
python/tutorials/03-matrix-multiplication.py
View File

@@ -338,11 +338,10 @@ else:
def benchmark(M, N, K, provider):
a = torch.randn((M, K), device='cuda', dtype=torch.float16)
b = torch.randn((K, N), device='cuda', dtype=torch.float16)
quantiles = [0.5, 0.2, 0.8]
if provider == 'cublas':
ms, min_ms, max_ms = triton.testing.do_bench(lambda: torch.matmul(a, b), quantiles=quantiles)
ms, min_ms, max_ms = triton.testing.do_bench(lambda: torch.matmul(a, b))
if provider == 'triton':
ms, min_ms, max_ms = triton.testing.do_bench(lambda: matmul(a, b), quantiles=quantiles)
ms, min_ms, max_ms = triton.testing.do_bench(lambda: matmul(a, b))
perf = lambda ms: 2 * M * N * K * 1e-12 / (ms * 1e-3)
return perf(ms), perf(max_ms), perf(min_ms)