http://folding.typepad.com/news/201...ing-opencl.html




Here is an update and some more details on the third generation GPU core. As I stated before, this core is built on OpenMM, which brings the science further along and allows us to make easier updates. OpenMM supports OpenCL in beta form in its 1.0 release (scheduled for late January 2010), but it is important to stress that the OpenCL support is very early and so we will not be relying on OpenCL in the first releases of the GPU3 core.

This means that the core will only roll out for NVIDIA first. ATI has depreciated Brook, but does not have a fully-functioning OpenCL implementation, so we are stuck in between support on the ATI side. Once the OpenCL implementation matures (on both ATI and NVIDIA), we will be able to finish and optimize our OpenCL code (we can't reliably optimize code until the implementations are more finalized), and then the OpenCL portions will go into QA.

So, if you are interested in OpenCL (especially in terms of ATI support), this will not be in the initial release, but once the environment has matured, we will push forward. By the way, once OpenCL support for multi-core boxes has matured, we will also see about porting the GPU3 code as a new SMP2 style core as well (i.e. threads-based SMP support). If the performance is strong, it's appealing to think that we can go back to having a single dominant code base for much of FAH's calculations.

Posted at 05:36 PM in code development | Permalink


重點
1.第三世代的 GPU Core，在後期的才會導入完整的OpenCL。
2.ATI的顯卡在短期內的支援度還是較差。
3.OpenCL可以讓GPU像CPU在運算F@H時有SMP(SLI or CF?)的效果，但還要評估效率。

這是給新的費米用的嗎?

各位
N卡有 新WU

大家回報一下PPD吧

9800GTX Core:750 RAM 2300 Shader 1890

Project : 5781
Core : GPUv2 Gromacs
Frames : 100
Credit : 783


-- FAHlog.txt --

Min. Time / Frame : 1mn 53s - 5986.83 ppd
Avg. Time / Frame : 1mn 53s - 5986.83 ppd
Cur. Time / Frame : 2mn 09s - 5244.28 ppd
R3F. Time / Frame : 1mn 58s - 5733.15 ppd
Eff. Time / Frame : 2mn 00s - 5637.60 ppd

那些資訊怎麼得到的, 要自己換算?! :ase
忘了說, 我先前的ATi 4670 有用CCC 超778/1120 (GPU-Z寫1116?!)
511points 似乎很易使介面遲頓,
剛回來用電腦有列表的都會一行一行慢慢顯示出來, 限制跟暫止WCG 沒用後就暫止F@H 才解決...
看一下CCC 忘了小超一下, 用CCC超頻好麻煩 :ase
但再啟動F@H 又不會這樣了?! :confused: 但看FahMon 怎還是在暫止的圖示咩?!

請問除了觀察log外，有沒有其他統計F@H client發生unstable machine次數的軟體阿？？
礙於兵役，我的主機常常兩個星期沒人去理他，有時掛了我都不知道Orz
只能等放假來調校，這次就因為重開機沒登入XP結果前面有三四天成績是0
好囧

在FahMon程式按 Ctrl+B




那就讓XP自動登入吧...

除了自動登入，
我還在BIOS中的"AC Back Function"項目設定成"Full-On"..
這樣即使是跳電或是斷電，只要電力恢復時都能自動開始。 :)

大概還是要從log著手.

建議降低時脈與改善散熱. 例如使用預設時脈或略低, 再稍降電壓(若無過熱問題可不改這個)

能穩定的長久跑才會是最大產值, 超頻不過多幾%, 但是不穩一次就是掉幾成.

除了自動開機與登入, Windows update也改成"僅通知但不自動下載安裝"都有助於恆定運作.

平地一聲雷 強力助拳人 出現
 

近期咱們的隊伍又有一位助拳人出現 : ykhung :flash:



歡迎歡迎~ :like:

歡迎助拳人ykhung加入!!

每小時的分數都是1920的倍數，應該是純CPU跑的。




另外現在Stanford官網提供查詢統計的資訊越來越少，
早先是移除統計個人完成的WU種類及數量，
現在連最後完成WU的時間，和運作中核心數量的資訊都移除了，

SMP2 approaches, client update posted!
 

http://en.fah-addict.net/news/news-...date-posted.php


SMP2 approaches, client update posted!

Peter Kasson, SMP/SMP2 project manager, has just put a new version of the clients online for download. The Windows, Linux, and Mac OS X SMP clients have been updated, but the OS X installer has not yet.

The new clients, versioned 6.29, contain just two changes. One is a minor bugfix related to bigadv, but it is the other we are interested in. Client v6.29 supports SMP2! SMP2 has not yet reached public beta but when it does, this client will ensure you are ready for it.

However, there is no need to rush, as no SMP2 release date has yet been announced. As such, this is the first soft release in the history of Folding@home. You may update your clients at your leisure. However, if you fold bigadv units, it is recommended to update your clients as soon as possible as this client version will soon be required for bigadv assignments.

For Linux and OSX downloads (except the Installer), please visit:
http://folding.stanford.edu/English/Download

For the new Windows installer, please visit:
http://folding.stanford.edu/English/DownloadWinOther


用SMP跑的隊友可以參考一下。