Add helpers to measure execution times #2740
Conversation
cupy/testing/time.py
Outdated
| func(*args) | ||
|
|
||
| for i in range(n): | ||
| ev1.synchronize() |
There was a problem hiding this comment.
I don't think you need this synchronization.
There was a problem hiding this comment.
The GPU time before function entry may be counted if this synchronization is missing.
There was a problem hiding this comment.
Only the ongoing work in the warmup loop might be counted in this case. How about moving this sync outside the current loop and putting it right after the warmup loop?
asi1024
force-pushed
the
time
branch
3 times, most recently
from
c48daf1
to
733a212
Compare
asi1024
changed the title
|
I will support context manager interface for measurement of time in another PR. |
cupyx/time.py
Outdated
| func(*args) | ||
|
|
||
| for i in range(n): | ||
| ev1.synchronize() |
There was a problem hiding this comment.
I think we have to record ev1 first (or synchronize the entire device instead of ev1) to avoid effect from warmup.
There was a problem hiding this comment.
Why? I think we should not record ev1 until all GPU threads finish computations.
There was a problem hiding this comment.
My understanding of CUDA event semantics is that:
ev1.record()queues the event to the current streamev1.synchronize()blocks until the event completes
https://devblogs.nvidia.com/how-implement-performance-metrics-cuda-cc/
|
PTAL. |
|
pfnCI, test this please. |
|
Successfully created a job for commit 36e9058: |
|
Jenkins CI test (for commit 36e9058, target branch master) succeeded! |
I want to officially support some helpers to measure CPU/GPU execution times.
CuPy organization has cupy-benchmark currently, but it is for the maintainers to show users the performance results. I want to support this feature for also external contributors and users.