add patch to fix [cz]asums in OpenBLAS 0.3.24

[SebastianAchilles]

(created using eb --new-pr)
This PR adds the patch OpenMathLib/OpenBLAS#4326 from @bartoldeman to fix [cz]asum. Without the patch 55 LAPACK test failurs can be observed. I noticed this on a Intel Sapphire Rapids system.

[SebastianAchilles]

Test report by @SebastianAchilles
SUCCESS
Build succeeded for 1 out of 1 (1 easyconfigs in total)
bwd-rockylinux-93 - Linux Rocky Linux 9.3 (Blue Onyx), x86_64, Intel(R) Core(TM) i7-6900K CPU @ 3.20GHz (broadwell), 2 x NVIDIA NVIDIA GeForce GTX 1060 6GB, 535.129.03, Python 3.9.18
See https://gist.github.com/SebastianAchilles/28bac7a611a6b25b2659f4ff20e0ec49 for a full test report.

[SebastianAchilles]

Test report by @SebastianAchilles
SUCCESS
Build succeeded for 1 out of 1 (1 easyconfigs in total)
jrc0880.jureca - Linux Rocky Linux 8.8, x86_64, Intel(R) Xeon(R) Platinum 8452Y (sapphirerapids), 4 x NVIDIA NVIDIA H100 PCIe, 535.104.12, Python 3.6.8
See https://gist.github.com/SebastianAchilles/1c847b991aff950fb3e4c6dd63957ea4 for a full test report.

[SebastianAchilles]

@boegelbot please test @ jsc-zen2

[boegelbot]

@SebastianAchilles: Request for testing this PR well received on jsczen2l1.int.jsc-zen2.easybuild-test.cluster

PR test command 'EB_PR=19331 EB_ARGS= EB_REPO=easybuild-easyconfigs /opt/software/slurm/bin/sbatch --mem-per-cpu=4000M --job-name test_PR_19331 --ntasks=8 ~/boegelbot/eb_from_pr_upload_jsc-zen2.sh' executed!

• exit code: 0
• output:

Submitted batch job 3820

Test results coming soon (I hope)...

- notification for comment with ID 1829681522 processed

Message to humans: this is just bookkeeping information for me,
it is of no use to you (unless you think I have a bug, which I don't).

[boegelbot]

Test report by @boegelbot
SUCCESS
Build succeeded for 1 out of 1 (1 easyconfigs in total)
jsczen2c1.int.jsc-zen2.easybuild-test.cluster - Linux Rocky Linux 8.5, x86_64, AMD EPYC 7742 64-Core Processor (zen2), Python 3.6.8
See https://gist.github.com/boegelbot/0c3a5996dbcbe9adad15c36fe9b82cd5 for a full test report.

[SebastianAchilles]

@boegelbot please test @ generoso

[boegelbot]

@SebastianAchilles: Request for testing this PR well received on login1

PR test command 'EB_PR=19331 EB_ARGS= EB_CONTAINER= EB_REPO=easybuild-easyconfigs /opt/software/slurm/bin/sbatch --job-name test_PR_19331 --ntasks=4 ~/boegelbot/eb_from_pr_upload_generoso.sh' executed!

• exit code: 0
• output:

Submitted batch job 12282

Test results coming soon (I hope)...

- notification for comment with ID 1829697868 processed

Message to humans: this is just bookkeeping information for me,
it is of no use to you (unless you think I have a bug, which I don't).

[bartoldeman]

In this case, while the patch doesn't hurt, it would be better to enable the avx512 microkernel on sapphire rapids.
OpenMathLib/OpenBLAS#4287
that microkernel is buggy for LLVM-based compilers (Intel/NVHPC), that was fixed in OpenMathLib/OpenBLAS#4330, though for GCC that doesn't matter here.

[SebastianAchilles]

In this case, while the patch doesn't hurt, it would be better to enable the avx512 microkernel on sapphire rapids. OpenMathLib/OpenBLAS#4287 that microkernel is buggy for LLVM-based compilers (Intel/NVHPC), that was fixed in OpenMathLib/OpenBLAS#4330, though for GCC that doesn't matter here.

Good point. The patch OpenMathLib/OpenBLAS#4287 was already added in #19159 Using that patch building OpenBLAS for me on Sapphire Rapids.

[boegel]

@boegelbot please test @ generoso

[boegelbot]

@boegel: Request for testing this PR well received on login1

PR test command 'EB_PR=19331 EB_ARGS= EB_CONTAINER= EB_REPO=easybuild-easyconfigs /opt/software/slurm/bin/sbatch --job-name test_PR_19331 --ntasks=4 ~/boegelbot/eb_from_pr_upload_generoso.sh' executed!

• exit code: 0
• output:

Submitted batch job 12326

Test results coming soon (I hope)...

- notification for comment with ID 1842581323 processed

Message to humans: this is just bookkeeping information for me,
it is of no use to you (unless you think I have a bug, which I don't).

[boegelbot]

Test report by @boegelbot
SUCCESS
Build succeeded for 1 out of 1 (1 easyconfigs in total)
cns1 - Linux Rocky Linux 8.5, x86_64, Intel(R) Xeon(R) CPU E5-2667 v3 @ 3.20GHz (haswell), Python 3.6.8
See https://gist.github.com/boegelbot/354d3618217cd932241e852b6414d44b for a full test report.

[boegel]

Test report by @boegel
SUCCESS
Build succeeded for 1 out of 1 (1 easyconfigs in total)
node3119.skitty.os - Linux RHEL 8.8, x86_64, Intel(R) Xeon(R) Gold 6140 CPU @ 2.30GHz (skylake_avx512), Python 3.6.8
See https://gist.github.com/boegel/89b41ed04dcb7ae521aa9db106cd7218 for a full test report.

[boegel]

lgtm

[boegel]

Going in, thanks @SebastianAchilles!