zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-06-24 09:21:16 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Adapt the torch benchmark to run in CUDA

Browse Source
This commit is contained in:
Angelos Katharopoulos 2025-06-17 15:56:33 -07:00
parent 5adf185f86
commit ab7c310914
1 changed files with 20 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
benchmarks/python/comparative/bench_torch.py
View File

@ -5,6 +5,7 @@ import os
import time import time
import torch import torch
import torch.cuda
import torch.mps import torch.mps
@ -44,8 +45,10 @@ def bench(f, *args):
def sync_if_needed(x): def sync_if_needed(x):
if x.device != torch.device("cpu"): if x.device == torch.device("mps"):
torch.mps.synchronize() torch.mps.synchronize()
elif x.device == torch.device("cuda"):
torch.cuda.synchronize()
@torch.no_grad() @torch.no_grad()
@ -99,6 +102,14 @@ def reduction(op, axis, x):
sync_if_needed(x) sync_if_needed(x)
@torch.no_grad()
def sum_and_add(axis, x, y):
z = x.sum(axis=axis, keepdims=True)
for i in range(50):
z = (z + y).sum(axis=axis, keepdims=True)
sync_if_needed(x)
@torch.no_grad() @torch.no_grad()
def softmax(axis, x): def softmax(axis, x):
ys = [] ys = []
@ -340,7 +351,11 @@ if __name__ == "__main__":
args.axis.pop(0) args.axis.pop(0)
torch.set_num_threads(1) torch.set_num_threads(1)
device = "cpu" if args.cpu else "mps" device = "mps"
if torch.cuda.is_available():
device = "cuda"
if args.cpu:
device = "cpu"
types = args.dtype types = args.dtype
if not types: if not types:
@ -460,5 +475,8 @@ if __name__ == "__main__":
elif args.benchmark == "selu": elif args.benchmark == "selu":
print(bench(selu, x)) print(bench(selu, x))
elif args.benchmark == "sum_and_add":
print(bench(sum_and_add, axis, *xs))
else: else:
raise ValueError(f"Unknown benchmark `{args.benchmark}`.") raise ValueError(f"Unknown benchmark `{args.benchmark}`.")