Skip to content

Fix pcp so the log files contains the expected test metrics.#52

Merged
dvalinrh merged 6 commits intomainfrom
fix_pcp
Jan 28, 2026
Merged

Fix pcp so the log files contains the expected test metrics.#52
dvalinrh merged 6 commits intomainfrom
fix_pcp

Conversation

@dvalinrh
Copy link
Contributor

@dvalinrh dvalinrh commented Jan 12, 2026

Description

It fixes the original pcp submission so we know report actual values.
Also adds timestamps, and switches from colons to , for field separator

Before/After Comparison

before
o.w.iteration o.w.running o.w.numthreads o.w.runtime o.w.throughput o.w.latency

13:55:40 N/A N/A N/A N/A N/A N/A
13:55:41 0.000 0.000 0.000 NaN NaN NaN
13:55:42 0.000 0.000 0.000 NaN NaN NaN
13:55:43 0.000 0.000 0.000 NaN NaN NaN
13:55:44 0.000 0.000 0.000 NaN NaN NaN
13:55:45 0.000 0.000 0.000 NaN NaN NaN
13:55:46 0.000 0.000 0.000 NaN NaN NaN
13:55:47 0.000 0.000 0.000 NaN NaN NaN
13:55:48 0.000 0.000 0.000 NaN NaN NaN
13:55:49 0.000 0.000 0.000 NaN NaN NaN
13:55:50 0.000 0.000 0.000 NaN NaN NaN
13:55:51 0.000 0.000 0.000 NaN NaN NaN
<continues, no data>

After
o.w.iteration o.w.multicore o.w.core o.w.nnet_test o.w.cjpegrose7preset o.w.loopsallmid10ksp o.w.parser125k o.w.radix2big64k o.w.shatest o.w.ziptest o.w.CoreMarkPRO o.w.linear_algmid100x100sp
15:01:35 1.000 0.000 1.700 7.410 147.060 6.370 34.480 609.010 192.310 125.000 NaN 147.930
15:01:36 1.000 0.000 1.700 7.410 147.060 6.370 34.480 609.010 192.310 125.000 NaN 147.930
15:01:37 1.000 0.000 1.700 7.410 147.060 6.370 34.480 609.010 192.310 125.000 NaN 147.930
15:01:38 1.000 0.000 1.700 7.410 147.060 6.370 34.480 609.010 192.310 125.000 5265.550 147.930
15:01:39 1.000 0.000 1.700 7.410 147.060 6.370 34.480 609.010 192.310 125.000 5265.550 147.930
15:01:40 1.000 0.000 1.700 7.410 147.060 6.370 34.480 609.010 192.310 125.000 5265.550 147.930
15:01:41 1.000 0.000 1.700 7.410 147.060 6.370 34.480 609.010 192.310 125.000 5265.550 147.930

Clerical Stuff

This closes #51

Relates to JIRA: RPOPC-762

Test information

Command executed
/home/ec2-user/workloads/coremark_pro-wrapper-2.1/coremark_pro/coremark_pro_run --run_user ec2-user --home_parent /home --iterations 1 --tuned_setting tuned_none_sys_file_ --host_config "m5.xlarge" --sysname "m5.xlarge" --sys_type aws --no-overrides --use_pcp

CSV File

Test,Multi iterations,Single Iterations,Scaling,Start_Date,End_Date
cjpeg-rose7-preset,1250.00,227.27,5.50,2026-01-27T19:03:08Z,2026-01-27T19:03:40Z
core,13.72,2.68,5.12,2026-01-27T19:03:08Z,2026-01-27T19:03:40Z
linear_alg-mid-100x100-sp,1219.51,320.51,3.80,2026-01-27T19:03:08Z,2026-01-27T19:03:40Z
loops-all-mid-10k-sp,49.21,11.30,4.35,2026-01-27T19:03:08Z,2026-01-27T19:03:40Z
nnet_test,54.95,14.62,3.76,2026-01-27T19:03:08Z,2026-01-27T19:03:40Z
parser-125k,444.44,62.50,7.11,2026-01-27T19:03:08Z,2026-01-27T19:03:40Z
radix2-big-64k,5847.95,987.17,5.92,2026-01-27T19:03:08Z,2026-01-27T19:03:40Z
sha-test,1000.00,357.14,2.80,2026-01-27T19:03:08Z,2026-01-27T19:03:40Z
zip-test,888.89,200.00,4.44,2026-01-27T19:03:08Z,2026-01-27T19:03:40Z
Score,42593.26,9262.65,0,0,2026-01-27T19:03:08Z,2026-01-27T19:03:40Z

===============================
partial pcp output

      o.w.iteration  o.w.running  o.w.runtime  o.w.throughput  o.w.latency  o.w.numthread  o.w.multicore  o.w.cjpegrose7preset  o.w.core  o.w.linear_algmid100x100sp  o.w.loopsallmid10ksp  o.w.nnet_test  o.w.parser125k  o.w.radix2big64k  o.w.shatest  o.w.ziptest  o.w.CoreMarkPRO

19:03:52 1.000 1.000 NaN NaN NaN NaN 1.000 1250.000 13.720 1219.510 49.210 54.950 444.440 5847.950 1000.000 888.890 42593.260

===========================================
Screenoutput from test

coremark_pro.txt

@github-actions
Copy link

This relates to RPOPC-762

@dvalinrh dvalinrh requested a review from grdumas January 22, 2026 20:27
grdumas
grdumas previously approved these changes Jan 26, 2026
Copy link
Collaborator

@grdumas grdumas left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Latest changes look good overall. I might want to add some degree of error handling in the event that the results file doesn't exist or value extraction fails for some reason, but that could be a future enhancement and does not need to block merging.

@dvalinrh dvalinrh requested a review from grdumas January 27, 2026 19:15
@grdumas grdumas added the bug Something isn't working label Jan 28, 2026
grdumas
grdumas previously approved these changes Jan 28, 2026
Copy link
Collaborator

@grdumas grdumas left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@grdumas grdumas added the group_review_lgtm Indicates approval after a group review meeting label Jan 28, 2026
Copy link
Collaborator

@grdumas grdumas left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@dvalinrh dvalinrh merged commit 0da48ab into main Jan 28, 2026
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

bug Something isn't working group_review_lgtm Indicates approval after a group review meeting

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add the pcp test metrics.

2 participants