BA8/BA12全面下市, BIGADV正式轉向BA16

[a0911430500]

放棄了，我表明在硬件應用上6C/12T平台後就不會再追了，一時間更萌生退意....而且
總覺得我Upgrade了8C/16T之後Stanford又會把Bigadv入場下限調至10C/20T......

變成高分包只適合多路CPU 或大型計算中心能跑

大概是單核心個人電腦為參與F@H瘋狂超頻,爆掉未算完的計算包會影響整個計畫吧

 

[kazama]

變成高分包只適合多路CPU 或大型計算中心能跑
大概是單核心個人電腦為參與F@H瘋狂超頻,爆掉未算完的計算包會影響整個計畫吧

BA很重視時效性，bonus門檻算是低標準，即使能低空飛過也未必是理想的BA運算平台.

把BA留給能提前達交的平台運算以加速研究無可厚非，問題是出在依核心數判斷的作法，
雖易於實施但無法有效評估實際運算力.

 

[kaoh08]

變成高分包只適合多路CPU 或大型計算中心能跑

大概是單核心個人電腦為參與F@H瘋狂超頻,爆掉未算完的計算包會影響整個計畫吧

如果能給每個WU整理出benchmark，大概可以知道自己的配備跑不跑的到deadline，可以避免造成垃圾計算包。

--
會不會我們都太在意分數而忘記運算本來的意義了;ranger;

 

[a0911430500]

如果能給每個WU整理出benchmark，大概可以知道自己的配備跑不跑的到deadline，可以避免造成垃圾計算包。
會不會我們都太在意分數而忘記運算本來的意義了;ranger;

http://www.linuxforge.net/bonuscalc2.php
可以填入完成1%的時間推算 和WU的資訊

說實話,小弟有一陣子算壞不少個6903 ;oq;

 

[kaoh08]

http://www.linuxforge.net/bonuscalc2.php
可以填入完成1%的時間推算 和WU的資訊

說實話,小弟有一陣子算壞不少個6903 ;oq;

不對，我的意思是指，比如說你硬體super pi要跑出幾分，才有法算完某個WU這樣的統計方式，這樣預知而避免吃到吃不下的。



等到知道TPF時，你WU都給他接下去了。

 

[a0911430500]

不對，我的意思是指，比如說你硬體super pi要跑出幾分，才有法算完某個WU這樣的統計方式，這樣預知而避免吃到吃不下的。
等到知道TPF時，你WU都給他接下去了。

就論壇上的資訊分享(舉例 http://www.equn.com/forum/redirect.php?goto=findpost&ptid=34810&pid=462356 )
亞太區域 就是 滄者 PCDVD EQUN

 

[A4GTRS]

i7-980@4.2G 6C/12T 模擬 16T 以原生Linux 1.3.4 image跑P8101
結果一樣殘念，TPF約38分 ;em42;

[11:22:04] *------------------------------*
[11:22:04] Folding@Home Gromacs SMP Core
[11:22:04] Version 2.27 (Thu Feb 10 09:46:40 PST 2011)
[11:22:04]
[11:22:04] Preparing to commence simulation
[11:22:04] - Looking at optimizations...
[11:22:04] - Created dyn
[11:22:04] - Files status OK
[11:22:06] - Expanded 30311544 -> 33158016 (decompressed 109.3 percent)
[11:22:06] Called DecompressByteArray: compressed_data_size=30311544 data_size=33158016, decompressed_data_size=33158016 diff=0
[11:22:06] - Digital signature verified
[11:22:06]
[11:22:06] Project: 8101 (Run 0, Clone 10, Gen 22)
[11:22:06]
[11:22:06] Assembly optimizations on if available.
[11:22:06] Entering M.D.
[11:22:12] Mapping NT from 12 to 12
[11:22:17] Completed 0 out of 250000 steps (0%)
[12:01:02] Completed 2500 out of 250000 steps (1%)
[12:39:47] Completed 5000 out of 250000 steps (2%)
[12:47:53] - Autosending finished units... [August 8 12:47:53 UTC]
[12:47:53] Trying to send all finished work units
[12:47:53] + No unsent completed units remaining.
[12:47:53] - Autosend completed
[13:18:29] Completed 7500 out of 250000 steps (3%)
[13:57:14] Completed 10000 out of 250000 steps (4%)
[14:35:56] Completed 12500 out of 250000 steps (5%)
[15:14:39] Completed 15000 out of 250000 steps (6%)
[15:53:24] Completed 17500 out of 250000 steps (7%)
[16:32:05] Completed 20000 out of 250000 steps (8%)
[17:10:49] Completed 22500 out of 250000 steps (9%)
[17:49:30] Completed 25000 out of 250000 steps (10%)

 

[金鹏FAH]

i7-980@4.2G 6C/12T 模擬 16T 以原生Linux 1.3.4 image跑P8101
結果一樣殘念，TPF約38分 ;em42;

[11:22:04] *------------------------------*
[11:22:04] Folding@Home Gromacs SMP Core
[11:22:04] Version 2.27 (Thu Feb 10 09:46:40 PST 2011)
[11:22:04]
[11:22:04] Preparing to commence simulation
[11:22:04] - Looking at optimizations...
[11:22:04] - Created dyn
[11:22:04] - Files status OK
[11:22:06] - Expanded 30311544 -> 33158016 (decompressed 109.3 percent)
[11:22:06] Called DecompressByteArray: compressed_data_size=30311544 data_size=33158016, decompressed_data_size=33158016 diff=0
[11:22:06] - Digital signature verified
[11:22:06]
[11:22:06] Project: 8101 (Run 0, Clone 10, Gen 22)
[11:22:06]
[11:22:06] Assembly optimizations on if available.
[11:22:06] Entering M.D.
[11:22:12] Mapping NT from 12 to 12
[11:22:17] Completed 0 out of 250000 steps (0%)
[12:01:02] Completed 2500 out of 250000 steps (1%)
[12:39:47] Completed 5000 out of 250000 steps (2%)
[12:47:53] - Autosending finished units... [August 8 12:47:53 UTC]
[12:47:53] Trying to send all finished work units
[12:47:53] + No unsent completed units remaining.
[12:47:53] - Autosend completed
[13:18:29] Completed 7500 out of 250000 steps (3%)
[13:57:14] Completed 10000 out of 250000 steps (4%)
[14:35:56] Completed 12500 out of 250000 steps (5%)
[15:14:39] Completed 15000 out of 250000 steps (6%)
[15:53:24] Completed 17500 out of 250000 steps (7%)
[16:32:05] Completed 20000 out of 250000 steps (8%)
[17:10:49] Completed 22500 out of 250000 steps (9%)
[17:49:30] Completed 25000 out of 250000 steps (10%)

首先感谢A大分享的8102 TPF

目前看来在单路U想跑完8101只有4.5G+ SNB-E 12T和 3.2G+的SNB-EP 16T,使用Virtualbox Image 或者Native Image 以及 Ubuntu是必需的
通过 kasson 吐露的任务包信息来看,未来BA16包只有8101是个门槛挡住了大部分的超频台机,其他的BA16包 6902 6905 6906 8102 都还是可以尝试计算
特别是目前的8102包PPD同台机器下能达到8101包的1.5倍PPD

by kasson » Mon Jul 30, 2012 11:19 pm

Thanks, everyone, for testing 8102. The good news and the bad news is that we will adjust points to bring them in line with 6901, 6902, 6905, 6906, 8101. So by all means enjoy a points bump in our initial stages of release, but please do be aware that it may not last.

 

[oegg]

忍痛拋掉一顆 3930K, 敗了 E5 2690 C0 ES 用 Windows + Virtual BOX + Linux Native Image
測試看看能不能在期限內達交 如果不行 就還是得要雙路以上才能 跑 bidadv

 

[Raziel]

F@H的理念是"讓所有的人都有適合自己狀況的F@H project可運算"，
而非"讓所有的人都能運算所有的F@H project".

推這句
我覺得別強求去能算到所有種類的任務, 在適合自己的前提下, 有可貢獻的部分就已經非常好了.
這個世界很大, 各種人都有, 倒不需刻意跟別人比配備,名次或分數, 讓自己能堅持付出下去反而是更可貴的.
我這幾個月在受訓比較忙, 希望很快能回來多跟大家見面.