mersenneforum.org  

Go Back   mersenneforum.org > Search Forums

Showing results 1 to 25 of 1000
Search took 0.37 seconds.
Search: Posts Made By: kriesel
Forum: GpuOwl 2020-10-26, 09:19
Replies: 146
Views: 4,428
Posted By kriesel
Gpuowl FFT limits from the help.txt files ...

Gpuowl FFT limits from the help.txt files

v7.1-1:
FFT 30M [ 47.19M - 560.64M] 1K:15:1K 4K:15:256
FFT 32M [ 50.33M - 599.62M] 4K:8:512 4K:4:1K

V6.11-364:
FFT 30M [ 47.19M - ...
Forum: Data 2020-10-26, 01:00
Replies: 3,335
Views: 217,145
Posted By kriesel
Yes. Snow today.

Yes. Snow today.
Forum: GPU Computing 2020-10-26, 00:55
Replies: 3,408
Views: 296,336
Posted By kriesel
Would someone please post CUDA11 mfaktc (2047...

Would someone please post CUDA11 mfaktc (2047 limit or higher GpuSieveSize; at least more-classes) compiled packages for Ubuntu Linux or Windows 7-10? I haven't seen any of either.

TheJudger tells...
Forum: Information & Answers 2020-10-26, 00:28
Replies: 12
Views: 323
Posted By kriesel
gpuowl generates a p-1 NF or factor found record...

gpuowl generates a p-1 NF or factor found record after completing the P-1 stage 2 gcd. It continues on to complete the PRP, and presumably produces a separate result record for PRP then.
I have...
Forum: GPU Computing 2020-10-25, 20:48
Replies: 3,408
Views: 296,336
Posted By kriesel
The known usually bad factor 388...407 comes up...

The known usually bad factor 388...407 comes up in discussion about annually at least since 2017. From my recently updated mfaktc thread notes file:

posts 2787 - 2806 2017-12-31...
Forum: GPU Computing 2020-10-25, 18:23
Replies: 3,408
Views: 296,336
Posted By kriesel
It's a known factor that is valid for one of the...

It's a known factor that is valid for one of the selftest exponents, and that frequently appears when there is an error, regardless of the current exponent being tested.
If a factor is reported...
Forum: News 2020-10-25, 14:40
Replies: 571
Views: 57,981
Posted By kriesel
What Would Bierce's Devil's Dictionary say?...

What Would Bierce's Devil's Dictionary say? Perhaps something like:
Luck: that name given to certain outcomes coincident with a blend of ignorance of statistical variation and superstition. It has...
Forum: GpuOwl 2020-10-25, 14:29
Replies: 146
Views: 4,428
Posted By kriesel
FYI

-use STATS some quick try on existing runs results, supplemented with ~binary search with new worktodo lines:
123M PRP, v7.0-40, ok
150M PRP, V6.11-364 ok
177.8M LL, V6.11-364 ok
181M LL,...
Forum: kriesel 2020-10-24, 20:42
Replies: 13
Views: 2,575
Posted By kriesel
GPU models no longer available to me for test ...

GPU models no longer available to me for test
GTX 480
Tesla C2075
GTX 1070
Forum: GpuOwl 2020-10-24, 18:05
Replies: 146
Views: 4,428
Posted By kriesel
-use STATS fail

It's repeatable in V7.0-35, on both error looping and normally running worktodo lines.
Seen on a system with 16GB ram, Celeron G1840 cpu, Win 10 Pro x64, Radeon VII, gpuowl-win v7.0-35-gf06bc5b....
Forum: GpuOwl 2020-10-24, 17:59
Replies: 146
Views: 4,428
Posted By kriesel
Race conditions are not just for computers, or...

Race conditions are not just for computers, or speed sports. 'salright.
Forum: GpuOwl 2020-10-24, 17:56
Replies: 35
Views: 718
Posted By kriesel
There's always at least one 0 wiseacre in every...

There's always at least one 0 wiseacre in every crowd.
Forum: Lounge 2020-10-24, 17:50
Replies: 39
Views: 891
Posted By kriesel
Check whether your current settings and exponents...

Check whether your current settings and exponents are reaching the bounds required to retire the P-1 task from the database. Repeated P-1 with increasing bounds is wasteful. Aim to finish the task...
Forum: GpuOwl 2020-10-24, 12:18
Replies: 64
Views: 2,715
Posted By kriesel
On gpuowl-win V6.11-364-g36f4e2a, Windows 10 Pro...

On gpuowl-win V6.11-364-g36f4e2a, Windows 10 Pro x64, Radeon VII gpu, Celeron G1840 cpu, 16 GB system ram:
LL 182585281 hit a reproducible jacobi=1 error 2020-09-29 between 151148000 and 151500000,...
Forum: GpuOwl 2020-10-24, 11:57
Replies: 146
Views: 4,428
Posted By kriesel
How much difference do you see in iteration...

How much difference do you see in iteration timings between ASM and NO_ASM on linux on Radeon VII? Only in ROCm?
Forum: GpuOwl 2020-10-24, 11:46
Replies: 146
Views: 4,428
Posted By kriesel
No, avoiding the delay of a compile that fails is...

No, avoiding the delay of a compile that fails is why I skip the ASM attempt that generates an error and NO_ASM retry. Same worktodo file, same gpuowl version, same Win 10 system:

2020-10-24...
Forum: GpuOwl 2020-10-24, 11:35
Replies: 146
Views: 4,428
Posted By kriesel
It's not keep doing nothing, it's try something...

It's not keep doing nothing, it's try something else (next assignment) and see if that works.
Forum: GpuOwl 2020-10-24, 11:24
Replies: 146
Views: 4,428
Posted By kriesel
Yes I think so. config.txt last modifed 18 Oct...

Yes I think so. config.txt last modifed 18 Oct 2020 was
-user kriesel -cpu asr2/radeonvii1 -d 1 -maxAlloc 14G -proof 8 -log 100000 -use NO_ASM
Forum: GpuOwl 2020-10-24, 11:10
Replies: 146
Views: 4,428
Posted By kriesel
Thanks for the prompt action. I see by...

Thanks for the prompt action.
I see by scanning the commit, you've changed it from loop on repeated error, to stop the program on repeated error. Either of those results in up to a lost gpu day if...
Forum: GpuOwl 2020-10-24, 08:51
Replies: 146
Views: 4,428
Posted By kriesel
Error loop

An example of gpuowl getting stuck in an error loop until manual intervention. This was gpuowl-win v7.0-35-gf06bc5b on Radeon VII gpu, Celeron G1840 cpu, Windows 10 x64 Pro, system ram 16 GB. Gpu was...
Forum: Lounge 2020-10-24, 01:11
Replies: 39
Views: 891
Posted By kriesel
Go bigger if it won't get in the way of other...

Go bigger if it won't get in the way of other things. And make day and night values the same to avoid restarts of stage 2 when the limits change with the time of day.

George's example is for 6GB....
Forum: Lounge 2020-10-23, 16:14
Replies: 39
Views: 891
Posted By kriesel
Amen on benchmarks. What's optimal in prime95...

Amen on benchmarks. What's optimal in prime95 depends on both hardware details and on what you run on it; big exponents or small or medium, for example.
See...
Forum: Data 2020-10-23, 14:55
Replies: 3,335
Views: 217,145
Posted By kriesel
1 left to 94M

https://www.mersenne.org/assignments/?exp_lo=93911551&exp_hi=94000000&execm=1&exp1=1&extf=1&exdchk=1
The next few minor milestones in first tests also contain very few remaining.


...
Forum: GpuOwl 2020-10-23, 13:34
Replies: 35
Views: 718
Posted By kriesel
Bug reports are intended at least partly for the...

Bug reports are intended at least partly for the software authors, yes?
The time of these rare few very talented programmers is precious.
Let's make an effort to use it well.
The post writer's...
Forum: GpuOwl 2020-10-23, 10:02
Replies: 15
Views: 1,807
Posted By kriesel
gpuowl-win v7.1-1-g0f73d04

As usual, build-log.txt, and a .7z holding the other files. This has proof V2. Heed Preda's caution about finishing a run before switching versions.
If I understand...
Showing results 1 to 25 of 1000

 
All times are UTC. The time now is 13:19.

Mon Oct 26 13:19:17 UTC 2020 up 46 days, 10:30, 0 users, load averages: 1.55, 1.58, 1.62

Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2020, Jelsoft Enterprises Ltd.

This forum has received and complied with 0 (zero) government requests for information.

Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.
A copy of the license is included in the FAQ.