Introduce Warm-up Phase for Dudect Measurement #289
+14
−2
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The commit messages were misleading:
Clarify them before reviewing. |
|
@HeatCrab, ping? |
Inspired by 'Reparaz et al.'s' 2016 paper, this change adds a warm-up phase to the function that collects and processes measurement batches, skipping the first batch to reduce timing variance in queue operations like insert and remove. Unlike the author's implementation, which uses dynamic percentile checks, this approach uses a static boolean to mark the initial run, suiting the fixed test loop. Experiments in simulation mode with qtest.c and perf show a minor 1.5% reduction in standard deviation (from 449ms to 442ms), suggesting a small improvement in execution stability. Reference: 'Reparaz et al.', "Dude, is my code constant time?", 2016, https://eprint.iacr.org/2016/1123.pdf Change-Id: I71692702401c130cd7cac1d424209308baecb87b
HeatCrab
force-pushed
the
add-warmup-to-measurement
branch
from
0af65c5 to
a51c643
Compare
|
Hi, I’ve submitted a new commit and update the PR comment. Experiments in simulation mode with perf showed a 1.5% timing variance reduction (stddev: 449ms to 442ms), suggesting slight improvements in execution stability. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request introduces a warm-up phase to the function that collects and processes measurement batches in qtest.c, skipping the first batch to reduce timing variance in queue operations, such as insert_tail. Inspired by Reparaz et al.’s 2016 paper, "Dude, is my code constant time?", this change adapts the leakage detection approach from the dudect prototype. Unlike the author’s implementation , which uses dynamic percentile checks, this approach employs a static boolean to mark the initial run, better suiting the fixed test loop. Experiments in simulation mode with insert_tail, using perf, show a minor 1.5% reduction in standard deviation (from 449ms to 442ms), suggesting a small improvement in execution stability.