Add microarchitecture detection for RISC-V clusters at HCA by julianmorillo · Pull Request #122 · EESSI/software-layer-scripts

julianmorillo · 2025-11-07T14:29:56Z

Results on the tested machines:

jmorillo@premier-1:~/premier/software-layer-scripts/init$ ./eessi_archdetect.sh -d cpupath
2025-11-07 15:26:06 [DEBUG] cpupath: Override variable set as ''
2025-11-07 15:26:06 [DEBUG] cpupath: Host CPU architecture identified as 'riscv64'
2025-11-07 15:26:06 [DEBUG] cpupath: CPU vendor of host system: '0x489'
2025-11-07 15:26:06 [DEBUG] cpupath: CPU flags of host system: 'rv64imafdch_zicsr_zifencei_zba_zbb_sscofpmf'
2025-11-07 15:26:06 [DEBUG] cpupath: host CPU best match updated to riscv64/sifive/p550
2025-11-07 15:26:06 [INFO] cpupath: best match for host CPU: riscv64/sifive/p550
riscv64/sifive/p550

jmorillo@bananaf3-6:~/bananaf3/software-layer-scripts/init$ ./eessi_archdetect.sh -d cpupath
2025-11-07 15:29:03 [DEBUG] cpupath: Override variable set as ''
2025-11-07 15:29:03 [DEBUG] cpupath: Host CPU architecture identified as 'riscv64'
2025-11-07 15:29:03 [DEBUG] cpupath: CPU vendor of host system: '0x710'
2025-11-07 15:29:03 [DEBUG] cpupath: CPU flags of host system: 'rv64imafdcv_zicbom_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zfhmin_zca_zcd_zba_zbb_zbc_zbs_zkt_zve32f_zve32x_zve64d_zve64f_zve64x_zvfh_zvfhmin_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt'
2025-11-07 15:29:03 [DEBUG] cpupath: host CPU best match updated to riscv64/spacemit/x60
2025-11-07 15:29:03 [INFO] cpupath: best match for host CPU: riscv64/spacemit/x60
riscv64/spacemit/x60

…o.hca.bsc.es/gitlab/epi-public/risc-v-software-development-vehicles/-/wikis/HCA-Nodes-and-Queues#commercial-risc-v-nodes)

boegel · 2025-11-14T09:42:23Z

@julianmorillo Can you look into also adding a test in tests/archdetect ?

You'll also need to update .github/workflows/tests_archdetect.yml to make sure that's picked up

julianmorillo · 2025-11-14T11:08:53Z

@julianmorillo Can you look into also adding a test in tests/archdetect ?

You'll also need to update .github/workflows/tests_archdetect.yml to make sure that's picked up

@boegel , done!

…e kernel used

julianmorillo · 2025-11-17T10:08:55Z

This is the result for the new added architecture:

jmorillo@bananaf3-6:~/bananaf3/software-layer-scripts/init$ ./eessi_archdetect.sh -d cpupath
2025-11-17 10:59:28 [DEBUG] cpupath: Override variable set as ''
2025-11-17 10:59:28 [DEBUG] cpupath: Host CPU architecture identified as 'riscv64'
2025-11-17 10:59:28 [DEBUG] cpupath: CPU vendor of host system: '0x710'
2025-11-17 10:59:28 [DEBUG] cpupath: CPU flags of host system: 'rv64imafdcv_zicbom_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zfhmin_zca_zcd_zba_zbb_zbc_zbs_zkt_zve32f_zve32x_zve64d_zve64f_zve64x_zvfh_zvfhmin_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt'
2025-11-17 10:59:28 [DEBUG] cpupath: host CPU best match updated to riscv64/spacemit/x60-k6.6
2025-11-17 10:59:28 [INFO] cpupath: best match for host CPU: riscv64/spacemit/x60-k6.6
riscv64/spacemit/x60-k6.6

trz42 · 2026-03-31T08:50:21Z

It also changes eb_hooks.py. Is that intentional?

julianmorillo · 2026-03-31T09:34:14Z

It also changes eb_hooks.py. Is that intentional?

Not at all, these chages were intended for another branch. I already left eb_hooks.py as the original.

bedroge

Lgtm

bedroge · 2026-05-11T09:53:43Z

bot: build repo:eessi.io-2025.06-software instance:eessi-bot-deucalion for:arch=aarch64/a64fx

eessi-bot-deucalion · 2026-05-11T09:53:52Z

New job on instance eessi-bot-deucalion for repository eessi.io-2025.06-software
Building on: a64fx
Building for: aarch64/a64fx
Job dir: /home/eessibot/new-bot/jobs/2026.05/pr_122/1252199

date	job status	comment
May 11 09:53:50 UTC 2026	submitted	job id `1252199` awaits release by job manager
May 11 09:54:47 UTC 2026	released	job awaits launch by Slurm scheduler
May 11 09:55:51 UTC 2026	running	job `1252199` is running
May 11 10:04:07 UTC 2026	finished	😁 SUCCESS (click triangle for details) Details ✅ job output file `slurm-1252199.out` ✅ no message matching `FATAL:` ✅ no message matching `ERROR:` ✅ no message matching `FAILED:` ✅ no message matching `required modules missing:` ✅ found message(s) matching `No missing installations` ✅ found message matching `.tar.* created!` Artefacts `eessi-2025.06-software-linux-aarch64-a64fx-17784935130.tar.zst` size: 0 MiB (4043 bytes) entries: 2 modules under 2025.06/software/linux/aarch64/a64fx/modules/all no module files in tarball software under 2025.06/software/linux/aarch64/a64fx/software no software packages in tarball reprod directories under 2025.06/software/linux/aarch64/a64fx/reprod no reprod directories in tarball other under 2025.06/software/linux/aarch64/a64fx `2025.06/init/arch_specs/eessi_arch_riscv.spec` `2025.06/init/eessi_archdetect.sh`
May 11 10:04:07 UTC 2026	test result	😁 SUCCESS (click triangle for details) ReFrame Summary [ SKIP ] (1/5) EESSI_OSU_coll %benchmark_info=mpi.collective.osu_allreduce %module_name=OSU-Micro-Benchmarks/7.5-gompi-2025a %scale=1_node %device_type=cpu /e4bf9965 @BotBuildTests:a64fx+default [Skipping test: nodes in this partition only have 30720 MiB memory available (per node) according to the current ReFrame configuration, but 49152 MiB is needed] [ SKIP ] (2/5) EESSI_OSU_coll %benchmark_info=mpi.collective.osu_alltoall %module_name=OSU-Micro-Benchmarks/7.5-gompi-2025a %scale=1_node %device_type=cpu /3da4890b @BotBuildTests:a64fx+default [Skipping test: nodes in this partition only have 30720 MiB memory available (per node) according to the current ReFrame configuration, but 49152 MiB is needed] [ OK ] (3/5) EESSI_OSU_pt2pt_CPU %benchmark_info=mpi.pt2pt.osu_latency %module_name=OSU-Micro-Benchmarks/7.5-gompi-2025a %scale=1_node /3255009a @BotBuildTests:a64fx+default P: latency: 0.87 us (r:0, l:None, u:None) [ OK ] (4/5) EESSI_OSU_pt2pt_CPU %benchmark_info=mpi.pt2pt.osu_bw %module_name=OSU-Micro-Benchmarks/7.5-gompi-2025a %scale=1_node /59f4b331 @BotBuildTests:a64fx+default P: bandwidth: 8081.35 MB/s (r:0, l:None, u:None) [ OK ] (5/5) EESSI_LAMMPS_lj %device_type=cpu %module_name=LAMMPS/22Jul2025-foss-2024a-kokkos %scale=1_node /ade8cad7 @BotBuildTests:a64fx+default P: perf: 556.704 timesteps/s (r:0, l:None, u:None) [ PASSED ] Ran 3/5 test case(s) from 5 check(s) (0 failure(s), 2 skipped, 0 aborted) Details ✅ job output file `slurm-1252199.out` ✅ no message matching `ERROR:` ✅ no message matching `[\sFAILED\s].Ran . test case`
May 12 19:35:41 UTC 2026	uploaded	transfer of `eessi-2025.06-software-linux-aarch64-a64fx-17784935130.tar.zst` to S3 bucket succeeded

bedroge · 2026-05-11T14:06:19Z

Since this only works with 2025.06, we need a solution for https://gitlab.com/eessi/support/-/work_items/251 first.

edit: okay, so having this deployed to 2023.06 as well shouldn't be an issue, let's get it deployed then.

bedroge · 2026-05-12T18:19:40Z

bot: build repo:eessi.io-2023.06-software instance:eessi-bot-deucalion for:arch=aarch64/a64fx

eessi-bot-deucalion · 2026-05-12T18:19:51Z

New job on instance eessi-bot-deucalion for repository eessi.io-2023.06-software
Building on: a64fx
Building for: aarch64/a64fx
Job dir: /home/eessibot/new-bot/jobs/2026.05/pr_122/1256162

date	job status	comment
May 12 18:19:50 UTC 2026	submitted	job id `1256162` awaits release by job manager
May 12 18:20:29 UTC 2026	released	job awaits launch by Slurm scheduler
May 12 18:21:35 UTC 2026	running	job `1256162` is running
May 12 18:31:15 UTC 2026	finished	😁 SUCCESS (click triangle for details) Details ✅ job output file `slurm-1256162.out` ✅ no message matching `FATAL:` ✅ no message matching `ERROR:` ✅ no message matching `FAILED:` ✅ no message matching `required modules missing:` ✅ found message(s) matching `No missing installations` ✅ found message matching `.tar.* created!` Artefacts `eessi-2023.06-software-linux-aarch64-a64fx-17786102420.tar.zst` size: 0 MiB (4021 bytes) entries: 2 modules under 2023.06/software/linux/aarch64/a64fx/modules/all no module files in tarball software under 2023.06/software/linux/aarch64/a64fx/software no software packages in tarball reprod directories under 2023.06/software/linux/aarch64/a64fx/reprod no reprod directories in tarball other under 2023.06/software/linux/aarch64/a64fx `2023.06/init/arch_specs/eessi_arch_riscv.spec` `2023.06/init/eessi_archdetect.sh`
May 12 18:31:15 UTC 2026	test result	😁 SUCCESS (click triangle for details) ReFrame Summary [ SKIP ] ( 1/10) Skipping test: nodes in this partition only have 30720 MiB memory available (per node) according to the current ReFrame configuration, but 49152 MiB is needed [ SKIP ] ( 2/10) Skipping test: nodes in this partition only have 30720 MiB memory available (per node) according to the current ReFrame configuration, but 49152 MiB is needed [ SKIP ] ( 3/10) Skipping test: nodes in this partition only have 30720 MiB memory available (per node) according to the current ReFrame configuration, but 49152 MiB is needed [ SKIP ] ( 4/10) Skipping test: nodes in this partition only have 30720 MiB memory available (per node) according to the current ReFrame configuration, but 49152 MiB is needed [ OK ] ( 5/10) EESSI_OSU_pt2pt_CPU %benchmark_info=mpi.pt2pt.osu_latency %module_name=OSU-Micro-Benchmarks/7.2-gompi-2023b %scale=1_node /15cad6c4 @BotBuildTests:a64fx+default P: latency: 1.74 us (r:0, l:None, u:None) [ OK ] ( 6/10) EESSI_OSU_pt2pt_CPU %benchmark_info=mpi.pt2pt.osu_latency %module_name=OSU-Micro-Benchmarks/7.1-1-gompi-2023a %scale=1_node /6672deda @BotBuildTests:a64fx+default P: latency: 1.76 us (r:0, l:None, u:None) [ OK ] ( 7/10) EESSI_OSU_pt2pt_CPU %benchmark_info=mpi.pt2pt.osu_bw %module_name=OSU-Micro-Benchmarks/7.2-gompi-2023b %scale=1_node /2a9a47b1 @BotBuildTests:a64fx+default P: bandwidth: 8756.99 MB/s (r:0, l:None, u:None) [ OK ] ( 8/10) EESSI_OSU_pt2pt_CPU %benchmark_info=mpi.pt2pt.osu_bw %module_name=OSU-Micro-Benchmarks/7.1-1-gompi-2023a %scale=1_node /1b24ab8e @BotBuildTests:a64fx+default P: bandwidth: 8773.3 MB/s (r:0, l:None, u:None) [ OK ] ( 9/10) EESSI_LAMMPS_lj %device_type=cpu %module_name=LAMMPS/29Aug2024-foss-2023b-kokkos %scale=1_node /aeb2d9df @BotBuildTests:a64fx+default P: perf: 524.108 timesteps/s (r:0, l:None, u:None) [ OK ] (10/10) EESSI_LAMMPS_lj %device_type=cpu %module_name=LAMMPS/2Aug2023_update2-foss-2023a-kokkos %scale=1_node /04ff9ece @BotBuildTests:a64fx+default P: perf: 579.235 timesteps/s (r:0, l:None, u:None) [ PASSED ] Ran 6/10 test case(s) from 10 check(s) (0 failure(s), 4 skipped, 0 aborted) Details ✅ job output file `slurm-1256162.out` ✅ no message matching `ERROR:` ✅ no message matching `[\sFAILED\s].Ran . test case`
May 12 19:35:32 UTC 2026	uploaded	transfer of `eessi-2023.06-software-linux-aarch64-a64fx-17786102420.tar.zst` to S3 bucket succeeded

julianmorillo added 2 commits November 7, 2025 12:56

Add content to RISC-V spec file

f9f2106

Provide correct detection for the RISC-V clusters at HCA (https://rep…

8309c1c

…o.hca.bsc.es/gitlab/epi-public/risc-v-software-development-vehicles/-/wikis/HCA-Nodes-and-Queues#commercial-risc-v-nodes)

julianmorillo and others added 2 commits November 14, 2025 12:00

Add tests for added RISC-V microarchitectures

aed30ea

Merge branch 'main' into main

cb80e79

Add a new Banana Pi F3 architecture as the detected isa depends on th…

ac6c22e

…e kernel used

julianmorillo and others added 3 commits November 17, 2025 15:40

Merge branch 'main' into main

ba004ec

Merge branch 'EESSI:main' into main

e403c45

Reduce the parallelism level for building SciPy-bundle (in RISC-V)

cb1378b

Undo changes in eb_hooks.py that where intended for other branch

716d68c

julianmorillo and others added 4 commits April 8, 2026 12:30

Merge branch 'EESSI:main' into main

d621af8

Merge branch 'EESSI:main' into main

569a667

Merge branch 'main' into main

567f928

Merge branch 'main' into main

c149d8f

bedroge approved these changes May 11, 2026

View reviewed changes

bedroge added the bot:deploy label May 12, 2026

bedroge merged commit a592a9c into EESSI:main May 12, 2026
88 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add microarchitecture detection for RISC-V clusters at HCA #122

Add microarchitecture detection for RISC-V clusters at HCA #122
bedroge merged 13 commits into
EESSI:mainfrom
julianmorillo:main

julianmorillo commented Nov 7, 2025

Uh oh!

boegel commented Nov 14, 2025 •

edited

Loading

Uh oh!

julianmorillo commented Nov 14, 2025

Uh oh!

julianmorillo commented Nov 17, 2025

Uh oh!

trz42 commented Mar 31, 2026

Uh oh!

julianmorillo commented Mar 31, 2026

Uh oh!

bedroge left a comment

Uh oh!

bedroge commented May 11, 2026

Uh oh!

eessi-bot-deucalion Bot commented May 11, 2026 •

edited

Loading

Uh oh!

bedroge commented May 11, 2026 •

edited

Loading

Uh oh!

bedroge commented May 12, 2026

Uh oh!

eessi-bot-deucalion Bot commented May 12, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Conversation

julianmorillo commented Nov 7, 2025

Uh oh!

boegel commented Nov 14, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

julianmorillo commented Nov 14, 2025

Uh oh!

julianmorillo commented Nov 17, 2025

Uh oh!

trz42 commented Mar 31, 2026

Uh oh!

julianmorillo commented Mar 31, 2026

Uh oh!

bedroge left a comment

Choose a reason for hiding this comment

Uh oh!

bedroge commented May 11, 2026

Uh oh!

eessi-bot-deucalion Bot commented May 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

bedroge commented May 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

bedroge commented May 12, 2026

Uh oh!

eessi-bot-deucalion Bot commented May 12, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

boegel commented Nov 14, 2025 •

edited

Loading

eessi-bot-deucalion Bot commented May 11, 2026 •

edited

Loading

bedroge commented May 11, 2026 •

edited

Loading

eessi-bot-deucalion Bot commented May 12, 2026 •

edited

Loading