{2023.06}[2023a,GPU] LAMMPS 2Aug2023 CUDA 12.1.1 #711

laraPPr · 2024-09-18T10:46:44Z

eessi-build-deploy-bot-deucalion · 2024-09-18T10:46:48Z

Instance boegel-bot-deucalion is configured to build for:

architectures: aarch64/a64fx
repositories: eessi.io-2023.06-software

eessi-bot · 2024-09-18T10:46:48Z

Instance eessi-bot-mc-aws is configured to build for:

architectures: x86_64/generic, x86_64/intel/haswell, x86_64/intel/skylake_avx512, x86_64/amd/zen2, x86_64/amd/zen3, aarch64/generic, aarch64/neoverse_n1, aarch64/neoverse_v1
repositories: eessi-hpc.org-2023.06-compat, eessi-hpc.org-2023.06-software, eessi.io-2023.06-software, eessi.io-2023.06-compat

eessi-bot · 2024-09-18T10:46:49Z

Instance eessi-bot-mc-azure is configured to build for:

architectures: x86_64/amd/zen4
repositories: eessi-hpc.org-2023.06-compat, eessi.io-2023.06-compat, eessi-hpc.org-2023.06-software, eessi.io-2023.06-software

laraPPr · 2024-09-18T12:18:46Z

Waiting on #710

boegel · 2024-09-18T15:27:01Z

@laraPPr NCCL will also be built as a dependency, we should make sure that the LICENSE.txt file is included in the installation there

laraPPr · 2024-09-18T15:28:36Z

bot: build repo:eessi.io-2023.06-software arch:x86_64/amd/zen2 accel:nvidia/cc80

eessi-bot · 2024-09-18T15:28:40Z

Updates by the bot instance eessi-bot-mc-aws (click for details)

parsing the bot command build repo:eessi.io-2023.06-software arch:x86_64/amd/zen2 accel:nvidia/cc80, received from sender laraPPr, failed

eessi-bot · 2024-09-18T15:28:40Z

Updates by the bot instance eessi-bot-mc-azure (click for details)

parsing the bot command build repo:eessi.io-2023.06-software arch:x86_64/amd/zen2 accel:nvidia/cc80, received from sender laraPPr, failed

eessi-build-deploy-bot-deucalion · 2024-09-18T15:28:41Z

Updates by the bot instance boegel-bot-deucalion (click for details)

account laraPPr has NO permission to send commands to the bot

boegel · 2024-09-18T17:34:11Z

@laraPPr The production bots need to be updated to be aware of the new accel filter, so it won't work yet until that's taken care of

laraPPr · 2024-09-19T07:42:32Z

@boegel we are already shipping NCCL

laraPPr · 2024-09-19T14:29:35Z

Opened a pull request in easybuild-easyblock to add the license of NCCL in the installation

enhance custom easyblock for NCCL: add licence to NCCL installation easybuilders/easybuild-easyblocks#3451

boegel · 2024-09-25T21:32:13Z

bot: build repo:eessi.io-2023.06-software arch:x86_64/amd/zen2 accel:nvidia/cc80

eessi-build-deploy-bot-deucalion · 2024-09-25T21:32:17Z

Updates by the bot instance boegel-bot-deucalion (click for details)

received bot command build repo:eessi.io-2023.06-software arch:x86_64/amd/zen2 accel:nvidia/cc80 from boegel
- expanded format: build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen2 accelerator:nvidia/cc80
handling command build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen2 accelerator:nvidia/cc80 resulted in:
- no jobs were submitted

eessi-bot · 2024-09-25T21:32:17Z

Updates by the bot instance eessi-bot-mc-aws (click for details)

received bot command build repo:eessi.io-2023.06-software arch:x86_64/amd/zen2 accel:nvidia/cc80 from boegel
- expanded format: build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen2 accelerator:nvidia/cc80
handling command build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen2 accelerator:nvidia/cc80 resulted in:
- submitted job 19875, for details & status see {2023.06}[2023a,GPU] LAMMPS 2Aug2023 CUDA 12.1.1 #711 (comment)

eessi-bot · 2024-09-25T21:32:17Z

Updates by the bot instance eessi-bot-mc-azure (click for details)

received bot command build repo:eessi.io-2023.06-software arch:x86_64/amd/zen2 accel:nvidia/cc80 from boegel
- expanded format: build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen2 accelerator:nvidia/cc80
handling command build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen2 accelerator:nvidia/cc80 resulted in:
- no jobs were submitted

eessi-bot · 2024-09-25T21:32:21Z

New job on instance eessi-bot-mc-aws for CPU micro-architecture x86_64-amd-zen2 and accelerator nvidia/cc80 for repository eessi.io-2023.06-software in job dir /project/def-users/SHARED/jobs/2024.09/pr_711/19875

date	job status	comment
Sep 25 21:32:20 UTC 2024	submitted	job id `19875` awaits release by job manager
Sep 25 21:32:33 UTC 2024	released	job awaits launch by Slurm scheduler
Sep 25 21:39:04 UTC 2024	running	job `19875` is running
Sep 25 22:37:54 UTC 2024	finished	😁 SUCCESS (click triangle for details) Details ✅ job output file `slurm-19875.out` ✅ 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.gz created!` Artefacts `eessi-2023.06-software-linux-x86_64-amd-zen2-1727302843.tar.gz` size: 259 MiB (271874626 bytes) entries: 4461 modules under 2023.06/software/linux/x86_64/amd/zen2/accel/nvidia/cc80/modules/all `LAMMPS/2Aug2023_update2-foss-2023a-kokkos-CUDA-12.1.1.lua` software under 2023.06/software/linux/x86_64/amd/zen2/accel/nvidia/cc80/software `LAMMPS/2Aug2023_update2-foss-2023a-kokkos-CUDA-12.1.1` other under 2023.06/software/linux/x86_64/amd/zen2/accel/nvidia/cc80 no other files in tarball
Sep 25 22:37:54 UTC 2024	test result	😁 SUCCESS (click triangle for details) ReFrame Summary [ PASSED ] Ran 9/9 test case(s) from 9 check(s) (0 failure(s), 0 skipped, 0 aborted) Details ✅ job output file `slurm-19875.out` ✅ no message matching `ERROR:` ✅ no message matching `[\sFAILED\s].Ran . test case`
Sep 26 13:32:29 UTC 2024	uploaded	transfer of `eessi-2023.06-software-linux-x86_64-amd-zen2-1727302843.tar.gz` to S3 bucket succeeded

boegel · 2024-09-26T08:18:08Z

bot: build repo:eessi.io-2023.06-software arch:x86_64/amd/zen3 accel:nvidia/cc80

eessi-bot · 2024-09-26T08:18:11Z

Updates by the bot instance eessi-bot-mc-aws (click for details)

received bot command build repo:eessi.io-2023.06-software arch:x86_64/amd/zen3 accel:nvidia/cc80 from boegel
- expanded format: build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen3 accelerator:nvidia/cc80
handling command build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen3 accelerator:nvidia/cc80 resulted in:
- submitted job 20003, for details & status see {2023.06}[2023a,GPU] LAMMPS 2Aug2023 CUDA 12.1.1 #711 (comment)

eessi-build-deploy-bot-deucalion · 2024-09-26T08:18:11Z

Updates by the bot instance boegel-bot-deucalion (click for details)

received bot command build repo:eessi.io-2023.06-software arch:x86_64/amd/zen3 accel:nvidia/cc80 from boegel
- expanded format: build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen3 accelerator:nvidia/cc80
handling command build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen3 accelerator:nvidia/cc80 resulted in:
- no jobs were submitted

eessi-bot · 2024-09-26T08:18:11Z

Updates by the bot instance eessi-bot-mc-azure (click for details)

received bot command build repo:eessi.io-2023.06-software arch:x86_64/amd/zen3 accel:nvidia/cc80 from boegel
- expanded format: build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen3 accelerator:nvidia/cc80
handling command build repository:eessi.io-2023.06-software architecture:x86_64/amd/zen3 accelerator:nvidia/cc80 resulted in:
- no jobs were submitted

eessi-bot · 2024-09-26T08:18:15Z

New job on instance eessi-bot-mc-aws for CPU micro-architecture x86_64-amd-zen3 and accelerator nvidia/cc80 for repository eessi.io-2023.06-software in job dir /project/def-users/SHARED/jobs/2024.09/pr_711/20003

date	job status	comment
Sep 26 08:18:14 UTC 2024	submitted	job id `20003` awaits release by job manager
Sep 26 08:18:55 UTC 2024	released	job awaits launch by Slurm scheduler
Sep 26 08:20:31 UTC 2024	running	job `20003` is running
Sep 26 09:08:44 UTC 2024	finished	😁 SUCCESS (click triangle for details) Details ✅ job output file `slurm-20003.out` ✅ 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.gz created!` Artefacts `eessi-2023.06-software-linux-x86_64-amd-zen3-1727340843.tar.gz` size: 259 MiB (271862815 bytes) entries: 4461 modules under 2023.06/software/linux/x86_64/amd/zen3/accel/nvidia/cc80/modules/all `LAMMPS/2Aug2023_update2-foss-2023a-kokkos-CUDA-12.1.1.lua` software under 2023.06/software/linux/x86_64/amd/zen3/accel/nvidia/cc80/software `LAMMPS/2Aug2023_update2-foss-2023a-kokkos-CUDA-12.1.1` other under 2023.06/software/linux/x86_64/amd/zen3/accel/nvidia/cc80 no other files in tarball
Sep 26 09:08:44 UTC 2024	test result	😁 SUCCESS (click triangle for details) ReFrame Summary [ PASSED ] Ran 9/9 test case(s) from 9 check(s) (0 failure(s), 0 skipped, 0 aborted) Details ✅ job output file `slurm-20003.out` ✅ no message matching `ERROR:` ✅ no message matching `[\sFAILED\s].Ran . test case`
Sep 26 13:32:51 UTC 2024	uploaded	transfer of `eessi-2023.06-software-linux-x86_64-amd-zen3-1727340843.tar.gz` to S3 bucket succeeded

boegel

lgtm

boegel · 2024-09-26T14:55:55Z

I tested this build on our AMD Milan A100 GPU cluster, results (interactive Slurm job with 1x A100, 12 CPU cores):

With CPU-only LAMMPS (LAMMPS/2Aug2023_update2-foss-2023a-kokkos module), using rhodo test case from EESSI test suite:

single-core (lmp -in in.rhodo): Performance: 0.841 ns/day
12-core (unset OMP_PROC_BIND; mpirun -np 12 lmp -in in.rhodo): Performance: 8.968 ns/day
12-core w/ Kokkos (lmp -in in.rhodo -kokkos on t 12 -suffix kk -package kokkos newton on neigh half): Performance: 6.153 ns/day

GPU (LAMMPS/2Aug2023_update2-foss-2023a-kokkos-CUDA-12.1.1):

export EESSI_OVERRIDE_GPU_CHECK=1
export LD_PRELOAD=/usr/lib64/libcuda.so
lmp -in in.rhodo -kokkos on t 12 g 1 -suffix kk -package kokkos newton on neigh half

=> Performance: 34.778 ns/day

🥳

boegel · 2024-09-26T18:34:35Z

ingest PRs merged, deploy under way, so merging this...

eessi-bot · 2024-09-26T18:34:42Z

PR merged! Moved ['/project/def-users/SHARED/jobs/2024.09/pr_711/19875', '/project/def-users/SHARED/jobs/2024.09/pr_711/20003'] to /project/def-users/SHARED/trash_bin/EESSI/software-layer/2024.09.26

eessi-build-deploy-bot-deucalion · 2024-09-26T18:34:42Z

PR merged! Moved [] to $HOME/trash_bin/EESSI/software-layer/2024.09.26

eessi-bot · 2024-09-26T18:34:43Z

PR merged! Moved [] to /project/def-users/SHARED/trash_bin/EESSI/software-layer/2024.09.26

{2023.06}[2023a,GPU] LAMMPS 2Aug2023 CUDA 12.1.1

1fca317

laraPPr added 2023.06-software.eessi.io 2023.06 version of software.eessi.io accel:nvidia labels Sep 18, 2024

lara added 2 commits September 19, 2024 16:32

Merge branch '2023.06-software.eessi.io' into GPU_builds

2026c7a

Merge branch '2023.06-software.eessi.io' into GPU_builds

f389620

lara added 2 commits September 26, 2024 15:07

Merge branch '2023.06-software.eessi.io' into GPU_builds

83a564e

use subdir accel for CUDA builds

e20f1dd

boegel added the bot:deploy Ask bot to deploy missing software installations to EESSI label Sep 26, 2024

create nvidia directory

5915390

boegel approved these changes Sep 26, 2024

View reviewed changes

boegel merged commit 00c7e6b into EESSI:2023.06-software.eessi.io Sep 26, 2024
35 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

{2023.06}[2023a,GPU] LAMMPS 2Aug2023 CUDA 12.1.1 #711

{2023.06}[2023a,GPU] LAMMPS 2Aug2023 CUDA 12.1.1 #711

laraPPr commented Sep 18, 2024 •

edited by boegel

Loading

eessi-build-deploy-bot-deucalion bot commented Sep 18, 2024

eessi-bot bot commented Sep 18, 2024

eessi-bot bot commented Sep 18, 2024

laraPPr commented Sep 18, 2024

boegel commented Sep 18, 2024

laraPPr commented Sep 18, 2024

eessi-bot bot commented Sep 18, 2024

eessi-bot bot commented Sep 18, 2024

eessi-build-deploy-bot-deucalion bot commented Sep 18, 2024

boegel commented Sep 18, 2024

laraPPr commented Sep 19, 2024

laraPPr commented Sep 19, 2024 •

edited

Loading

boegel commented Sep 25, 2024

eessi-build-deploy-bot-deucalion bot commented Sep 25, 2024 •

edited

Loading

eessi-bot bot commented Sep 25, 2024 •

edited

Loading

eessi-bot bot commented Sep 25, 2024 •

edited

Loading

eessi-bot bot commented Sep 25, 2024 •

edited

Loading

boegel commented Sep 26, 2024

eessi-bot bot commented Sep 26, 2024 •

edited

Loading

eessi-build-deploy-bot-deucalion bot commented Sep 26, 2024 •

edited

Loading

eessi-bot bot commented Sep 26, 2024 •

edited

Loading

eessi-bot bot commented Sep 26, 2024 •

edited

Loading

boegel left a comment

boegel commented Sep 26, 2024 •

edited

Loading

boegel commented Sep 26, 2024

eessi-bot bot commented Sep 26, 2024

eessi-build-deploy-bot-deucalion bot commented Sep 26, 2024

eessi-bot bot commented Sep 26, 2024

{2023.06}[2023a,GPU] LAMMPS 2Aug2023 CUDA 12.1.1 #711

{2023.06}[2023a,GPU] LAMMPS 2Aug2023 CUDA 12.1.1 #711

Conversation

laraPPr commented Sep 18, 2024 • edited by boegel Loading

eessi-build-deploy-bot-deucalion bot commented Sep 18, 2024

eessi-bot bot commented Sep 18, 2024

eessi-bot bot commented Sep 18, 2024

laraPPr commented Sep 18, 2024

boegel commented Sep 18, 2024

laraPPr commented Sep 18, 2024

eessi-bot bot commented Sep 18, 2024

eessi-bot bot commented Sep 18, 2024

eessi-build-deploy-bot-deucalion bot commented Sep 18, 2024

boegel commented Sep 18, 2024

laraPPr commented Sep 19, 2024

laraPPr commented Sep 19, 2024 • edited Loading

boegel commented Sep 25, 2024

eessi-build-deploy-bot-deucalion bot commented Sep 25, 2024 • edited Loading

eessi-bot bot commented Sep 25, 2024 • edited Loading

eessi-bot bot commented Sep 25, 2024 • edited Loading

eessi-bot bot commented Sep 25, 2024 • edited Loading

boegel commented Sep 26, 2024

eessi-bot bot commented Sep 26, 2024 • edited Loading

eessi-build-deploy-bot-deucalion bot commented Sep 26, 2024 • edited Loading

eessi-bot bot commented Sep 26, 2024 • edited Loading

eessi-bot bot commented Sep 26, 2024 • edited Loading

boegel left a comment

Choose a reason for hiding this comment

boegel commented Sep 26, 2024 • edited Loading

boegel commented Sep 26, 2024

eessi-bot bot commented Sep 26, 2024

eessi-build-deploy-bot-deucalion bot commented Sep 26, 2024

eessi-bot bot commented Sep 26, 2024

laraPPr commented Sep 18, 2024 •

edited by boegel

Loading

laraPPr commented Sep 19, 2024 •

edited

Loading

eessi-build-deploy-bot-deucalion bot commented Sep 25, 2024 •

edited

Loading

eessi-bot bot commented Sep 25, 2024 •

edited

Loading

eessi-bot bot commented Sep 25, 2024 •

edited

Loading

eessi-bot bot commented Sep 25, 2024 •

edited

Loading

eessi-bot bot commented Sep 26, 2024 •

edited

Loading

eessi-build-deploy-bot-deucalion bot commented Sep 26, 2024 •

edited

Loading

eessi-bot bot commented Sep 26, 2024 •

edited

Loading

eessi-bot bot commented Sep 26, 2024 •

edited

Loading

boegel commented Sep 26, 2024 •

edited

Loading