“Canonical Kernel Team” team

~canonical-kernel-team/+git/stress-ng:master

  1. Git
  2. lp:~canonical-kernel-team/+git/stress-ng
  3. master
Last commit made on 2024-06-25
Get this branch:
git clone -b master https://git.launchpad.net/~canonical-kernel-team/+git/stress-ng
Members of Canonical Kernel Team can upload to this branch. Log in for directions.

Branch merges

Branch information

Name:
master
Repository:
lp:~canonical-kernel-team/+git/stress-ng

Recent commits

5afb941... by Po-Hsu Lin

stress-cache: check RISCV_HWPROBE_EXT_ZICBOZ support for stress_cache_bzero

RISCV_HWPROBE_EXT_ZICBOZ flag from kernel headers on RISC-V was only
added in 6.7, test build will fail with an older kernel with:
    error: ‘RISCV_HWPROBE_EXT_ZICBOZ’ undeclared

Check the flag first to fix this issue.

Fixes: f8654a05f4 ("stress-cache: add stress_cache_bzero() to support cache-based bzero")
Signed-off-by: Po-Hsu Lin <email address hidden>

6bde040... by Colin Ian King

README.md: add 4 more kernel issues found with stress-ng

Signed-off-by: Colin Ian King <email address hidden>

5be042a... by Colin Ian King

stress-min-nanosleep: report scheduler name

Useful to report this for test logging

Signed-off-by: Colin Ian King <email address hidden>

9992df1... by Colin Ian King

stress-cpu: minor code clean-ups

Signed-off-by: Colin Ian King <email address hidden>

40321d3... by Colin Ian King

README.md: update contributors name list

Signed-off-by: Colin Ian King <email address hidden>

874a0ef... by Daniel Andriesse <email address hidden>

stress-vecwide: fix verify option by setting results vector res

The verify option does not work because the result buffers in
vec_args are never set. Fix this.

Signed-off-by: Daniel Andriesse <email address hidden>
Signed-off-by: Colin Ian King <email address hidden>

a9f5bac... by Colin Ian King

stress-cpu: matrixprod: align matrices

Improves performance by ~7% on a i5-8350U.

Signed-off-by: Colin Ian King <email address hidden>

c9ca331... by Colin Ian King

stress-cpu: idct: re-factor, move some calculations out of loop

Moving multiplications out of loop optimized performance by ~35%
on a i5-8350U.

Signed-off-by: Colin Ian King <email address hidden>

d6201a1... by Colin Ian King

stress-cpu: fft: align data and pass as restrict pointers

Minor optimizations, improves performance by ~5% on a i5-8350U

Signed-off-by: Colin Ian King <email address hidden>

a43c17a... by Colin Ian King

stress-min-nanosleep: use the more optimial log2 function

Signed-off-by: Colin Ian King <email address hidden>