Successfully identified regression in *llvm* in CI configuration
tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2. So far, this commit has
regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2
Culprit:
<cut>
commit d39d3a327b1303012370e47d991459ffbfce45ef
Author: Peyton, Jonathan L <jonathan.l.pey...@intel.com>
Date: Fri Aug 20 16:06:13 2021 -0500
[OpenMP][test] fix omp_get_wtime.c test to be more accommodating
The omp_get_wtime.c test fails intermittently if the recorded times are
off by too much which can happen when many tests are run in parallel.
Instead of failing if one timing is a little off, take average of 100
timings minus the 10 worst.
Differential Revision: https://reviews.llvm.org/D108488
</cut>
Results regressed to (for first_bad == d39d3a327b1303012370e47d991459ffbfce45ef)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2
artifacts/build-d39d3a327b1303012370e47d991459ffbfce45ef/results_id:
1
# 447.dealII,dealII_base.default regressed by 105
from (for last_good == f77174d4b8cfba3c0a53c78e53edbbaf57e37fc5)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2
artifacts/build-f77174d4b8cfba3c0a53c78e53edbbaf57e37fc5/results_id:
1
Artifacts of last_good build:
https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-aarch64-spec2k6-O2/17/artifact/artifacts/build-f77174d4b8cfba3c0a53c78e53edbbaf57e37fc5/
Results ID of last_good:
tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2/4734
Artifacts of first_bad build:
https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-aarch64-spec2k6-O2/17/artifact/artifacts/build-d39d3a327b1303012370e47d991459ffbfce45ef/
Results ID of first_bad:
tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2/4757
Build top page/logs:
https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-aarch64-spec2k6-O2/17/
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-d39d3a327b1303012370e47d991459ffbfce45ef
cd investigate-llvm-d39d3a327b1303012370e47d991459ffbfce45ef
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh
https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-aarch64-spec2k6-O2/17/artifact/artifacts/manifests/build-baseline.sh
--fail
curl -o artifacts/manifests/build-parameters.sh
https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-aarch64-spec2k6-O2/17/artifact/artifacts/manifests/build-parameters.sh
--fail
curl -o artifacts/test.sh
https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-aarch64-spec2k6-O2/17/artifact/artifacts/test.sh
--fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/
--exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach d39d3a327b1303012370e47d991459ffbfce45ef
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach f77174d4b8cfba3c0a53c78e53edbbaf57e37fc5
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results:
https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/ci/tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2
Artifacts:
https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-aarch64-spec2k6-O2/17/artifact/artifacts/
Build log:
https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-aarch64-spec2k6-O2/17/consoleText
Full commit (up to 1000 lines):
<cut>
commit d39d3a327b1303012370e47d991459ffbfce45ef
Author: Peyton, Jonathan L <jonathan.l.pey...@intel.com>
Date: Fri Aug 20 16:06:13 2021 -0500
[OpenMP][test] fix omp_get_wtime.c test to be more accommodating
The omp_get_wtime.c test fails intermittently if the recorded times are
off by too much which can happen when many tests are run in parallel.
Instead of failing if one timing is a little off, take average of 100
timings minus the 10 worst.
Differential Revision: https://reviews.llvm.org/D108488
---
openmp/runtime/test/api/omp_get_wtime.c | 75 ++++++++++++++++++++++++++-------
1 file changed, 59 insertions(+), 16 deletions(-)
diff --git a/openmp/runtime/test/api/omp_get_wtime.c
b/openmp/runtime/test/api/omp_get_wtime.c
index e2bb211e0ce4..a862e07fc5a2 100644
--- a/openmp/runtime/test/api/omp_get_wtime.c
+++ b/openmp/runtime/test/api/omp_get_wtime.c
@@ -4,30 +4,73 @@
#include "omp_testsuite.h"
#include "omp_my_sleep.h"
-int test_omp_get_wtime()
-{
+#define NTIMES 100
+
+// This is the error % threshold. Be generous with the error threshold since
+// this test may be run in parallel with many other tests it may throw off the
+// sleep timing.
+#define THRESHOLD 33.0
+
+double test_omp_get_wtime(double desired_wait_time) {
double start;
double end;
- double measured_time;
- double wait_time = 0.2;
start = 0;
end = 0;
start = omp_get_wtime();
- my_sleep (wait_time);
+ my_sleep(desired_wait_time);
end = omp_get_wtime();
- measured_time = end-start;
- return ((measured_time > 0.97 * wait_time) && (measured_time < 1.03 *
wait_time)) ;
+ return end - start;
}
-int main()
-{
- int i;
- int num_failed=0;
+int compare_times(const void *lhs, const void *rhs) {
+ const double *a = (const double *)lhs;
+ const double *b = (const double *)rhs;
+ return *a - *b;
+}
+
+int main() {
+ int i, final_count;
+ double percent_off;
+ double *begin, *end, *ptr;
+ double wait_time = 0.01;
+ double average = 0.0;
+ double n = 0.0;
+ double *times = (double *)malloc(sizeof(double) * NTIMES);
+
+ // Get each timing
+ for (i = 0; i < NTIMES; i++) {
+ times[i] = test_omp_get_wtime(wait_time);
+ }
+
+ // Remove approx the "worst" tenth of the timings
+ qsort(times, NTIMES, sizeof(double), compare_times);
+ begin = times;
+ end = times + NTIMES;
+ for (i = 0; i < NTIMES / 10; ++i) {
+ if (i % 2 == 0)
+ begin++;
+ else
+ end--;
+ }
+
+ // Get the average of the remaining timings
+ for (ptr = begin, final_count = 0; ptr != end; ++ptr, ++final_count)
+ average += times[i];
+ average /= (double)final_count;
+ free(times);
+
+ // Calculate the percent off of desired wait time
+ percent_off = (average - wait_time) / wait_time * 100.0;
+ // Should always be positive, but just in case
+ if (percent_off < 0)
+ percent_off = -percent_off;
- for(i = 0; i < REPETITIONS; i++) {
- if(!test_omp_get_wtime()) {
- num_failed++;
- }
+ if (percent_off > (double)THRESHOLD) {
+ fprintf(stderr, "error: average of %d runs (%lf) is of by %lf%%\n", NTIMES,
+ average, percent_off);
+ return EXIT_FAILURE;
}
- return num_failed;
+ printf("pass: average of %d runs (%lf) is only off by %lf%%\n", NTIMES,
+ average, percent_off);
+ return EXIT_SUCCESS;
}
</cut>
_______________________________________________
linaro-toolchain mailing list
linaro-toolchain@lists.linaro.org
https://lists.linaro.org/mailman/listinfo/linaro-toolchain
