Новые клиенты для OGR Налаштування

[Tamagoch]

Текущая серия:

==========================================================================
Version change log: $Id: CHANGES.txt,v 1.66 2009/06/03 11:29:22 andreasb Exp $
==========================================================================

2.9100
------

2.9109.518 fix: all: OGR-NG codebase fixes (#4295)
fix: all: OGR-NG incorrect node count after full restart
of combined stub (#4290)
imp: all: a kind of stress test for OGR-NG
imp: cellbe: faster OGR-NG SPU ASM core
imp: all: log errors to file during tests and buffer update
fix: x86: possible division by zero in cpuinfo
imp: x86: CPU detect and core select updates (#4297,#4299,#4301)
imp: x86: AMD Opteron/Phenom detection (#4326,#4256)
fix: all: logging issues with more then 26 crunchers (#4345)
imp: ppc: recognize more PowerPC processors (#4349)
imp: ppc: core selection for Power6 series (#4349)
fix: win64: only 32 processors were used (#4352)


2.9105-511 fix: ppc: Fixed scalar and hybrid OGR-NG cores (#4187)
imp: cellbe: detect linux kernel SPU scheduler (spufs) bugs
new: linux: runs-on-battery-power detection via sysfs

2.9104-510 imp: all: handle lack of a supported cpu/gpu more gracefully
imp: gpgpu: terminate on unsupported driver/library installations
imp: gpgpu: raise rc5-72 buffer limit to 10000
new: cuda: switch to CUDA 2.1 (Linux and Windows only)
new: cuda: bundle runtime library (libcudart.so.2/libcudart.dylib/
cudart.dll) with the released client
imp: cuda: log errors to logfile (if enabled)
new: x86: three OGR-NG SSE2 ASM cores from Craig Johnston (#4177)
imp: cellbe: faster OGR-NG SPU ASM core


Загрузить клиент -=- FAQ по настройке

-->> https://distributed.net/download/prerelease.php <<--


Windows 32bit
1 [x86/Zipped] v2.9109.518 2010-11-10 http | ftp
2 [x86/CUDA-3.1] v2.9109.518 2010-11-10 http | ftp

Windows 64bit
3 [AMD64] v2.9109.518 2010-11-10 http | ftp

Mac OS X/Darwin
4 [AMD64] v2.9109.518 2010-11-10 http | ftp

[Tamagoch]

на АМД прирост в районе 1 меганода

[Tamagoch]

на Феноме дикий прирост на ядре sse2 вместо К8, клиент даже предложил отправить баг-репорт по этому поводу

[Death]

а на селероне 1200 как оно????
у меня тоже про багрепорт пишет.

[Tamagoch]

а на селероне 1200 как оно????
у меня тоже про багрепорт пишет.

это у меня разогнанный коппермайн, он показал преимущество старого ядра
очевидно, новые ядра только для П4/коре и новых АМД процессоров, где лучше реализованы функции sse2

[egorio]

на Феноме дикий прирост на ядре sse2 вместо К8, клиент даже предложил отправить баг-репорт по этому поводу

Насколько дикий? В процентах

[Tamagoch]

egorio,
сравнимо с приростом на коре2 - 25-30%
бенчмарк не успел записать, феном не мой, я просто запустил там огр ))

[Paul B.Atton]

2 месяца аптайма? ВААУ

Тю... Воно від ОС більше залежить.

[Jun 01 14:46:39 UTC] OGR-NG: Summary: 493 packets (88135.73 stats units)
96.04:04:40.54 - [10.61 Mnodes/s]

Хм... Ось тут цифри трохи більші:

[Jun 01 12:23:59 UTC] OGR-NG: Summary: 1174 packets (163277.34 stats units)
96.01:38:56.22 - [19.67 Mnodes/s]

# uname -a
SunOS test 5.8 Generic_117351-35 i86pc i386 i86pc

Tamagoch, шо то я твоих бенчей не вижу ))))

А моє підійде?

(Show/Hide)

dnetc v2.9104-510-GTR-09042813 for Win32 (WindowsNT 5.1).
Using email address (distributed.net ID) 'pbatton на ukr.net'

[Jun 01 15:14:45 UTC] Automatic processor type detection found
an Intel Core 2/Xeon processor.
[Jun 01 15:14:45 UTC] OGR-NG: using core #0 (FLEGE 2.0).
[Jun 01 15:15:06 UTC] OGR-NG: Benchmark for core #0 (FLEGE 2.0)
0.00:00:17.59 [13,039,508 nodes/sec]
[Jun 01 15:15:06 UTC] OGR-NG: using core #1 (rt-asm-generic).
[Jun 01 15:15:25 UTC] OGR-NG: Benchmark for core #1 (rt-asm-generic)
0.00:00:16.61 [17,063,677 nodes/sec]
[Jun 01 15:15:25 UTC] OGR-NG: using core #2 (rt-asm-mmx).
[Jun 01 15:15:44 UTC] OGR-NG: Benchmark for core #2 (rt-asm-mmx)
0.00:00:16.53 [23,187,456 nodes/sec]
[Jun 01 15:15:44 UTC] OGR-NG: using core #3 (cj-asm-sse2).
[Jun 01 15:16:03 UTC] OGR-NG: Benchmark for core #3 (cj-asm-sse2)
0.00:00:16.76 [29,063,284 nodes/sec]
[Jun 01 15:16:03 UTC] OGR-NG: using core #4 (cj-asm-sse-p4).
[Jun 01 15:16:24 UTC] OGR-NG: Benchmark for core #4 (cj-asm-sse-p4)
0.00:00:17.29 [23,305,832 nodes/sec]
[Jun 01 15:16:24 UTC] OGR-NG: using core #5 (cj-asm-sse-k8).
[Jun 01 15:16:44 UTC] OGR-NG: Benchmark for core #5 (cj-asm-sse-k8)
0.00:00:16.89 [23,452,041 nodes/sec]
[Jun 01 15:16:44 UTC] OGR-NG benchmark summary :
Default core : #3 (cj-asm-sse2)
Fastest core : #3 (cj-asm-sse2)
[Jun 01 15:16:44 UTC] RC5-72: using core #0 (SES 1-pipe).
[Jun 01 15:17:03 UTC] RC5-72: Benchmark for core #0 (SES 1-pipe)
0.00:00:16.37 [3,496,143 keys/sec]
[Jun 01 15:17:03 UTC] RC5-72: using core #1 (SES 2-pipe).
[Jun 01 15:17:24 UTC] RC5-72: Benchmark for core #1 (SES 2-pipe)
0.00:00:17.78 [5,829,371 keys/sec]
[Jun 01 15:17:24 UTC] RC5-72: using core #2 (DG 2-pipe).
[Jun 01 15:17:44 UTC] RC5-72: Benchmark for core #2 (DG 2-pipe)
0.00:00:17.09 [4,438,390 keys/sec]
[Jun 01 15:17:44 UTC] RC5-72: using core #3 (DG 3-pipe).
[Jun 01 15:18:04 UTC] RC5-72: Benchmark for core #3 (DG 3-pipe)
0.00:00:17.51 [5,939,661 keys/sec]
[Jun 01 15:18:04 UTC] RC5-72: using core #4 (DG 3-pipe alt).
[Jun 01 15:18:24 UTC] RC5-72: Benchmark for core #4 (DG 3-pipe alt)
0.00:00:16.73 [5,372,582 keys/sec]
[Jun 01 15:18:24 UTC] RC5-72: using core #5 (SS 2-pipe).
[Jun 01 15:18:44 UTC] RC5-72: Benchmark for core #5 (SS 2-pipe)
0.00:00:17.17 [4,976,640 keys/sec]
[Jun 01 15:18:44 UTC] RC5-72: using core #6 (GO 2-pipe).
[Jun 01 15:19:04 UTC] RC5-72: Benchmark for core #6 (GO 2-pipe)
0.00:00:16.59 [5,743,910 keys/sec]
[Jun 01 15:19:04 UTC] RC5-72: using core #7 (SGP 3-pipe).
[Jun 01 15:19:25 UTC] RC5-72: Benchmark for core #7 (SGP 3-pipe)
0.00:00:18.07 [5,644,932 keys/sec]
[Jun 01 15:19:25 UTC] RC5-72: using core #8 (MA 4-pipe).
[Jun 01 15:19:46 UTC] RC5-72: Benchmark for core #8 (MA 4-pipe)
0.00:00:17.64 [4,588,223 keys/sec]
[Jun 01 15:19:46 UTC] RC5-72: using core #9 (MMX 4-pipe).
[Jun 01 15:20:06 UTC] RC5-72: Benchmark for core #9 (MMX 4-pipe)
0.00:00:17.60 [3,824,456 keys/sec]
[Jun 01 15:20:06 UTC] RC5-72: using core #10 (GO 2-pipe alt).
[Jun 01 15:20:27 UTC] RC5-72: Benchmark for core #10 (GO 2-pipe alt)
0.00:00:17.57 [6,098,042 keys/sec]
[Jun 01 15:20:27 UTC] RC5-72 benchmark summary :
Default core : #10 (GO 2-pipe alt)
Fastest core : #10 (GO 2-pipe alt)

[Death]

[Jun 01 15:15:44 UTC] OGR-NG: Benchmark for core #2 (rt-asm-mmx) 0.00:00:16.53 [23,187,456 nodes/sec]
[Jun 01 15:16:03 UTC] OGR-NG: Benchmark for core #3 (cj-asm-sse2) 0.00:00:16.76 [29,063,284 nodes/sec]

оч неплохо.
вот бы ещё ссе3 и ссе4 заюзали )))

[Death]

Paul B.Atton,

96.04:04:40.54

Ось тут цифри трохи більші:

96.01:38:56.22

Хехе. Накранчил больше, а аптайм на 3 часа меньше )))))))

кстате на пререлизах лежит 511б

2.9105-511 fix: ppc: Fixed scalar and hybrid OGR-NG cores (#4187)
imp: cellbe: detect linux kernel SPU scheduler (spufs) bugs
new: linux: runs-on-battery-power detection via sysfs

обновил шапко.

[Paul B.Atton]

Хехе. Накранчил больше, а аптайм на 3 часа меньше )))))))

Ги... мабуть, я кудись поспішав.
Ех, вчора довелось ребутнути сервак із аптаймом понад 420 діб...

[Death]

:: 27-Jul-2009 23:26 GMT (Monday) ::
Howdy folks,
We've just transferred some new clients from the pre-release page to the official release page: https://distributed.net/download/clients.php

*dnetc511-amigaos-68k.lha
*dnetc511-amigaos-ppc-pup.lha
*dnetc511-amigaos-ppc-wos.lha
*dnetc511-amigaos-ppc.lha
*dnetc511-morphos-ppc.lha
*dnetc511b-dos-x86.zip
*dnetc511b-linux-cellbe.tar.gz
*dnetc511b-linux-ppc.tar.gz
*dnetc511b-macosx-ppc.tar.gz
*dnetc511b-macosx-x86.tar.gz
*dnetc511b-os2-x86.zip
*dnetc511b-win32-x86.zip
*dnetc511b-win32-x86-setup.msi
*dnetc510-linux-x86-elf-uclibc.tar.gz

As mentioned in a previous plan, these new x86 clients contain three new OGR cores. Depending on your CPU type, the new cores may provide a significant speed improvement over the cores used in previous client versions.
Additionally we strongly recommend that users of OGR PowerPC clients version 2.9103 or 2.9104 upgrade to these newer versions. It was discovered that those two specific version numbers could process OGR-27 blocks incorrectly, so results from those client versions have been blocked. Users of PowerPC platforms should upgrade to client version 2.9105.511 or later.

We have also promoted the following personal proxy binaries from the pre-release page to the official release page:

*proxyper347-freebsd4-x86.tar.gz
*proxyper347-freebsd6-x86.tar.gz
*proxyper347-freebsd7-x86.tar.gz
*proxyper347-linux-cellbe.tar.gz
*proxyper347a-linux-x86-uclibc.tar.gz

We're very close to being able to finally mark the first three stubspaces for OGR-27 complete... The first one (OGR-27.1) was just finished up in the last few hours. There are just a very small number of stubs that we are waiting to be completed in OGR-27.2 and OGR-27.3.
We'll make another announcement when those are finally received.

Keep on crunching! ]:8)

[Death]

x64 clients!

Download links

Windows 32bit
1 [x86/Zipped] v2.9109.518 2010-11-10 http | ftp
2 [x86/CUDA-3.1] v2.9109.518 2010-11-10 http | ftp
1. Release candidate.
2. Release candidate. nVidia CUDA video card accelerated client. RC5-72 only. Matching CUDA driver version must be pre-installed. See readme.cuda
Windows 64bit
3 [AMD64] v2.9109.518 2010-11-10 http | ftp
3. Release candidate. Native 64-bit. Requires x64 edition of Win2k3/WinXP/Vista.
Mac OS X/Darwin
4 [AMD64] v2.9109.518 2010-11-10 http | ftp
5 [x86/CUDA-3.1] v2.9109.518 2010-11-10 http | ftp
6 [x86] v2.9109.518 2010-11-10 http | ftp
4. first 64-bit release candidate
5. Release candidate. nVidia CUDA video card accelerated client. RC5-72 only. Matching CUDA driver version must be pre-installed. See readme.cuda
6. Release candidate.
Linux
7 [PPC] v2.9109.518 2010-08-01 http | ftp
8 [CellBE] v2.9109.518 2010-08-01 http | ftp
7. release candidate.
8. Cell Broadband Engine, PlayStation 3. Release candidate.
FreeBSD
9 [8.x/PPC] v2.9109.518 2010-07-13 http | ftp
9. First release for this platform, supports altivec. Release candidate.
NetBSD
10 [MIPSEB] v2.9109.518 2010-10-17 http | ftp
11 [x86] v2.9109.518 2010-08-01 http | ftp
10. Release candidate. built on NetBSD 4.0.1
11. release candidate. Built on NetBSD 4.0
OpenBSD
12 [SGI] v2.9109.518 2010-10-25 http | ftp
12. OpenBSD 4.3 on SGI. Release candidate.
Solaris/SunOS
13 [10.x/amd64] v2.9108.517 2010-07-13 http | ftp
14 [7.x/Sparc64] v2.9109.518 2010-07-13 http | ftp
15 [2.6/Sparc] v2.9109.518 2010-07-13 http | ftp
16 [x86] v2.9109.518 2010-07-13 http | ftp

[Alexis Kravtchenko]

Новости от 11.04.2011, OGR-27 client issues :

Dear friends,

We are pleased to announce that we have recently identified and fixed some bugs in our OGR client codebase. One of them causes the client to skip part of a packet in very rare cases. It can happen only in OGR-27 and above, so previous projects were not affected. Fixes are included in our updated client, v2.9109.518.

Due to the severity of this bug, we decided to change the rules for stub verification. Now not only two returned results must have the same node count, but also at least one of the results must be returned by a fixed (.518) client. Thus we will be sure that no rulers were skipped. Since we have not started the second pass of OGR-27.4 yet, this is an ideal time to introduce a validation change like this.

We’re asking you to update all of your systems to the fixed client, v2.9109.518, as soon as possible. Results sent from older clients will still be accepted and counted in stats. Updating to the latest client will help us to complete the project faster.

The updated client also recognizes the new Intel Core i3 and AMD Phenom processors, which are becoming increasingly popular among budget-conscious consumers.

You can download the updated client for all major platforms at: https://distributed.net/Download_clients.

We thank you for your continued participation in this ground-breaking project.

Moo!

Если кратко, то рекомендуют всем обновиться до v2.9109.518, так как в предыдущих версиях клиента изредка возможен пропуск сканирования диапазона. Результаты будут засчитаны всё равно, но для верификации блока нужно, что бы хотя бы один клиент был свежий.

Да интересно, что часть клиентов(.518) была собрана в конце 2010г., а часть 11.03.2011 ...

[Death]

==========================================================================
Version change log: $Id: CHANGES.txt,v 1.111 2011/04/14 23:46:43 snikkel Exp $
==========================================================================

2.9100
------

2.9110.519 new: amd64: New GO-2c core
new: amd64: New GO-2d core
chg: amd64: Core pre-selection for most processors
fix: x86: OGR core pre-selection for Intel Core iX (#4376)
imp: x86/amd64: Intel Sandy Bridge detection/selection


Download links
Windows 32bit
1 [x86/Zipped] v2.9110.519b 2011-04-15 http | ftp
2 [x86/CUDA-3.1] v2.9110.519b 2011-04-15 http | ftp
1. Release candidate.
2. Release candidate. nVidia CUDA video card accelerated client. RC5-72 only. Matching CUDA driver version must be pre-installed. See readme.cuda
Windows 64bit
3 [AMD64] v2.9110.519b 2011-04-15 http | ftp
3. Release candidate. Native 64-bit. Requires x64 edition of Win2k3/WinXP/Vista/Win7.
Mac OS X/Darwin
4 [x86] v2.9110.519 2011-04-15 http | ftp
4 [PPC] v2.9110.519 2011-04-15 http | ftp
5 [AMD64] v2.9110.519 2011-04-15 http | ftp
6 [Universal] v2.9110.519 2011-04-15 http | ftp
4. Release candidate.
5. 64-bit release candidate
6. Universal binary. release candidate.
Linux
7 [AMD64/ELF] v2.9110.519b 2011-04-17 http | ftp
8 [x86/ELF/uclibc] v2.9110.519 2011-04-13 http | ftp
9 [AMD64/Stream] v2.9110.519 2011-04-13 http | ftp
7. native 64-bit build for AMD x86-64 or Intel EM64T. Release candidate
8. release candidate.
9. Linux AMD/ATI Stream video card accelerated client. RC5-72 only. Stream drivers must be pre-installed.
FreeBSD
10 [7.x/AMD64] v2.9110.519 2011-04-13 http | ftp
[8.x/AMD64] v2.9110.519 2011-04-13 http | ftp
10. only FreeBSD >= 7
Solaris/SunOS
11 [10.x/amd64] v2.9110.519 2011-04-02 http | ftp
11. release candidate. Solaris 10

[Death]

ОСТАЛОСЬ МЕНЬШЕ МЕСЯЦА! ТОЛКАЕМ в ТОП10 в ФИНАЛЕ!

[Jan 21 11:08:28 UTC] OGR-NG: using core #0 (FLEGE-64 2.0).
[Jan 21 11:08:47 UTC] OGR-NG: Benchmark for core #0 (FLEGE-64 2.0)
0.00:00:16.50 [23,377,425 nodes/sec]
[Jan 21 11:08:48 UTC] OGR-NG: using core #1 (cj-asm-generic).
[Jan 21 11:09:07 UTC] OGR-NG: Benchmark for core #1 (cj-asm-generic)
0.00:00:16.78 [27,331,681 nodes/sec]
[Jan 21 11:09:07 UTC] OGR-NG: using core #2 (cj-asm-sse2).
[Jan 21 11:09:27 UTC] OGR-NG: Benchmark for core #2 (cj-asm-sse2)
0.00:00:17.45 [19,432,697 nodes/sec]
[Jan 21 11:09:27 UTC] OGR-NG benchmark summary :
Default core : #1 (cj-asm-generic) 27,331,681 nodes/sec
Fastest core : #1 (cj-asm-generic) 27,331,681 nodes/sec
[Jan 21 11:09:27 UTC] RC5-72: using core #0 (SNJL 3-pipe).
[Jan 21 11:09:47 UTC] RC5-72: Benchmark for core #0 (SNJL 3-pipe)
0.00:00:17.45 [8,237,376 keys/sec]
[Jan 21 11:09:47 UTC] RC5-72: using core #1 (KBE-64 3-pipe).
[Jan 21 11:10:06 UTC] RC5-72: Benchmark for core #1 (KBE-64 3-pipe)
0.00:00:16.42 [8,767,055 keys/sec]
[Jan 21 11:10:06 UTC] RC5-72: using core #2 (GO 2-pipe c).
[Jan 21 11:10:25 UTC] RC5-72: Benchmark for core #2 (GO 2-pipe c)
0.00:00:17.20 [10,236,517 keys/sec]
[Jan 21 11:10:25 UTC] RC5-72: using core #3 (GO 2-pipe d).
[Jan 21 11:10:45 UTC] RC5-72: Benchmark for core #3 (GO 2-pipe d)
0.00:00:16.69 [10,908,734 keys/sec]
[Jan 21 11:10:45 UTC] RC5-72 benchmark summary :
Default core : #3 (GO 2-pipe d) 10,908,734 keys/sec
Fastest core : #3 (GO 2-pipe d) 10,908,734 keys/sec
[Jan 21 11:10:45 UTC] Compare and share your rates in the speeds database at
https://distributed.net/speed/
(benchmark rates are for a single processor core)