No jobs for newest AMD Epycs as the are diagnosed to lack sse and sse2?

Oliver Behnke
Oliver Behnke
Moderator
Administrator
Joined: 4 Sep 07
Posts: 984
Credit: 25171438
RAC: 28

Ian&Steve C. wrote: that was

Ian&Steve C. wrote:

that was actually a two layer fix, requiring both a client update and server update. it wouldnt make any impact for einstein unless they update the servers to the new code, which probably wont happen.

https://github.com/BOINC/boinc/issues/5122#issuecomment-1452884259

This issue has some history. Anyhow, we're going to fix this, presumably early next week, and keep you posted.

Thanks for your patience,
Oliver

 

Einstein@Home Project

Keith Myers
Keith Myers
Joined: 11 Feb 11
Posts: 4964
Credit: 18752120192
RAC: 7113177

That is great news Oliver.

That is great news Oliver. Thanks.

 

Oliver Behnke
Oliver Behnke
Moderator
Administrator
Joined: 4 Sep 07
Posts: 984
Credit: 25171438
RAC: 28

Unfortunately this is likely

Unfortunately this is likely going to take another week due to illness.

Sorry for the inconvenience,
Oliver

Einstein@Home Project

Armin Burkhardt speaking for MPI/FKF
Armin Burkhardt...
Joined: 21 Feb 05
Posts: 17
Credit: 15695016671
RAC: 4292161

Dear Oliver, health is

Dear Oliver,

health is first! Always! (and the guys at Milkyway@Home are happy for the boost:

https://milkyway.cs.rpi.edu/milkyway/hosts_user.php?userid=57498)

but whenever the fix ist ready, let me know and I will return to my favorite project.

 These machines are in the burn-in as compute cluster and will go in production some weeks from now.

 

Armin

Oliver Behnke
Oliver Behnke
Moderator
Administrator
Joined: 4 Sep 07
Posts: 984
Credit: 25171438
RAC: 28

Thanks Armin. Looks like

Thanks Armin. Looks like we're back in full affect. However, we noticed another related upstream issue. We might fix it alongside the known issues at our end first, I think, so I expect a fix (for you) in the coming days.

Best,
Oliver

Einstein@Home Project

Bernd Machenschalk
Bernd Machenschalk
Moderator
Administrator
Joined: 15 Oct 04
Posts: 4312
Credit: 250585517
RAC: 34422

The scheduler code as been

The scheduler code as been updated. the CPU featuress string should now be parsed correctly. Please give it a try and report.

BM

Armin Burkhardt speaking for MPI/FKF
Armin Burkhardt...
Joined: 21 Feb 05
Posts: 17
Credit: 15695016671
RAC: 4292161

Dear Bernd, I hope you are

Dear Bernd,

I hope you are doing well.

I attached E@H on my machine named alnode312, but at the moment it looks like it is getting no new jobs.

I attach the startup log of my client below.

Greetings from Stuttgart

Armin

 

16-Oct-2023 11:20:08 [---] Starting BOINC client version 7.22.0 for x86_64-suse-linux-gnu
16-Oct-2023 11:20:08 [---] log flags: file_xfer, sched_ops, task
16-Oct-2023 11:20:08 [---] Libraries: libcurl/8.0.1 OpenSSL/1.1.1l-fips zlib/1.2.11 brotli/1.0.7 zstd/1.5.0 libidn2/2.2.0 libpsl/0.20.1 (+libidn2/2.2.0) libssh/0.9.6/openssl/zlib nghttp2/1.40.0
16-Oct-2023 11:20:08 [---] Data directory: /scratch/alnode312
16-Oct-2023 11:20:08 [---] No usable GPUs found
16-Oct-2023 11:20:08 [---] libc:  version 2.31
16-Oct-2023 11:20:08 [---] Host name: alnode312
16-Oct-2023 11:20:08 [---] Processor: 256 AuthenticAMD AMD EPYC 9554 64-Core Processor [Family 25 Model 17 Stepping 1]
16-Oct-2023 11:20:08 [---] Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl avx512vbmi umip p
16-Oct-2023 11:20:08 [---] OS: Linux SLES: SUSE Linux Enterprise Server 15 SP5 [5.14.21-150400.24.81-default|libc 2.31]
16-Oct-2023 11:20:08 [---] Memory: 1.48 TB physical, 4.00 GB virtual
16-Oct-2023 11:20:08 [---] Disk: 5.82 TB total, 5.81 TB free
16-Oct-2023 11:20:08 [---] Local time is UTC +2 hours
16-Oct-2023 11:20:08 [Milkyway@Home] General prefs: from Milkyway@Home (last modified 02-Oct-2023 14:26:40)
16-Oct-2023 11:20:08 [Milkyway@Home] Computer location: home
16-Oct-2023 11:20:08 [---] General prefs: using separate prefs for home
16-Oct-2023 11:20:08 [---] Preferences:
16-Oct-2023 11:20:08 [---] -  When computer is in use
16-Oct-2023 11:20:08 [---] -     'In use' means mouse/keyboard input in last 3.0 minutes
16-Oct-2023 11:20:08 [---] -     max CPUs used: 256
16-Oct-2023 11:20:08 [---] -     Use at most 80% of the CPU time
16-Oct-2023 11:20:08 [---] -     suspend if non-BOINC CPU load exceeds 25%
16-Oct-2023 11:20:08 [---] -     max memory usage: 226.71 GB
16-Oct-2023 11:20:08 [---] -  When computer is not in use
16-Oct-2023 11:20:08 [---] -     max CPUs used: 256
16-Oct-2023 11:20:08 [---] -     Use at most 100% of the CPU time
16-Oct-2023 11:20:08 [---] -     suspend if non-BOINC CPU load exceeds 50%
16-Oct-2023 11:20:08 [---] -     max memory usage: 755.69 GB
16-Oct-2023 11:20:08 [---] -  Suspend if running on batteries
16-Oct-2023 11:20:08 [---] -  Leave apps in memory if not running
16-Oct-2023 11:20:08 [---] -  Store at least 0.10 days of work
16-Oct-2023 11:20:08 [---] -  Store up to an additional 0.25 days of work
16-Oct-2023 11:20:08 [---] -  max disk usage: 8.00 GB
16-Oct-2023 11:20:08 [---] -  (to change preferences, visit a project web site or select Preferences in the Manager)
16-Oct-2023 11:20:08 [---] Setting up project and slot directories
16-Oct-2023 11:20:08 [---] Checking active tasks
16-Oct-2023 11:20:08 [Einstein@Home] URL https://einstein.phys.uwm.edu/; Computer ID 13160262; resource share 1000
16-Oct-2023 11:20:08 [Milkyway@Home] URL http://milkyway.cs.rpi.edu/milkyway/; Computer ID 1006039; resource share 10
16-Oct-2023 11:20:08 [---] Setting up GUI RPC socket
16-Oct-2023 11:20:08 [---] Checking presence of 26 project files
16-Oct-2023 11:20:08 Initialization completed

 

 

 

Armin Burkhardt speaking for MPI/FKF
Armin Burkhardt...
Joined: 21 Feb 05
Posts: 17
Credit: 15695016671
RAC: 4292161

processor still lacks feature

processor still lacks feature sse.....

2023-10-16 09:40:43.9026 [PID=2702275] [version] Checking plan class 'FGRPSSE'
2023-10-16 09:40:43.9026 [PID=2702275] [version] CPU [' family 25 model 17 stepping 1 '] lacks feature ' sse '
2023-10-16 09:40:43.9026 [PID=2702275] [version] no app version available: APP#46 (hsgamma_FGRP5) PLATFORM#7 (x86_64-pc-linux-gnu) min_version 0
2023-10-16 09:40:43.9051 [PID=2702275] [send] [HOST#13160265] is looking for work from a non-preferred application
2023-10-16 09:40:43.9052 [PID=2702275] [version] no app version available: APP#25 (einsteinbinary_BRP4G) PLATFORM#7 (x86_64-pc-linux-gnu) min_version 0
2023-10-16 09:40:43.9103 [PID=2702275] [debug] [HOST#13160265] MSG(high) No work sent


Bernd Machenschalk
Bernd Machenschalk
Moderator
Administrator
Joined: 15 Oct 04
Posts: 4312
Credit: 250585517
RAC: 34422

OK, if the client doesn't

OK, if the client doesn't report it, it's a problem on the client, and there's not much E@H can do this. The server code should work now.

I'll dig around. In the upstream code there is an omission that would prevent the current server code from functioning properly, I'm fixing this at the very moment. I'm not sure though whether this affects the client as well, I'll dig around.

BM

Bernd Machenschalk
Bernd Machenschalk
Moderator
Administrator
Joined: 15 Oct 04
Posts: 4312
Credit: 250585517
RAC: 34422

This is weird, though. The

This is weird, though. The list is certainly cut off, but SSE and SSE2 are relatively early in the list of features. Maybe this is something completely different...

BM

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.