Skip to content

Moved cuda synch outside of warmup loop #145

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Tyler-Hilbert wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Moved cuda synch outside of warmup loop #145

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions src/kernelbench/timing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -238,7 +238,7 @@ def time_execution_with_cuda_event(
# Warm ups
for _ in range(num_warmup):
kernel_fn(*args)
torch.cuda.synchronize(device=device)
torch.cuda.synchronize(device=device)

# note this only release PyTorch’s CUDA caching allocator, not necessarily clearing device's L2 cache
torch.cuda.empty_cache()
Expand Down Expand Up @@ -465,7 +465,7 @@ def time_execution_with_host_time(
# Warm ups
for _ in range(num_warmup):
kernel_fn(*args)
torch.cuda.synchronize(device=device)
torch.cuda.synchronize(device=device)

print(f"[Profiling] Using device: {device} {torch.cuda.get_device_name(device)}, warm up {num_warmup}, trials {num_trials}")
elapsed_times = []
Expand Down Expand Up @@ -534,7 +534,7 @@ def time_execution_with_nsight_python(
# Warm ups
for _ in range(num_warmup):
kernel_fn(*args)
torch.cuda.synchronize(device=device)
torch.cuda.synchronize(device=device)

# Clear cache for cold start
torch.cuda.empty_cache()
Expand Down