open cl，到底是谁的悲劇？最新更新——胆敢说OPEN CL是AMD杯具的蚍蜉们！颤抖吧！

贵甲 · 发表于 2010-1-14 12:21

本帖最后由贵甲于 2010-1-15 12:51 编辑

folding@home news January 13, 2010
Some more details on the GPU3 core, regarding OpenCL
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.

最新更新：
A饭怒了！愤怒了！最终决战型暴怒了！
昨天，FAH官方论坛被A饭各种谩骂爆缸，最终无奈之下项目组老大亲自写了这个公告

January 14, 2010
Important update on my post on OpenCL
Just an update on my blog post.  I want to make it clear that we're  seeing problems in both of our ATI and NVIDIA GPU OpenCL implementations for OpenMM. Maybe it's on our side (I'm bet some bugs are on our side), but we suspect there could possibly be some issues with both the NVIDIA and ATI OpenCL implementations (and maybe even Apple's). We are working with everyone closely to either fix our bugs or get our code compliant with the OpenCL implementations.
Also, it looks like I should have been more careful in my wording of my previous post.  I was referring to the issues above when talking about whether the ATI implementation was "fully functional" and some groups have gotten this out of my intended context.  As far as I understand, the ATI OpenCL implementation is fully functional.
Finally, it is important to note that our Brook code is still supported, just not actively developed so Folding@Home/OpenMM is concentrating on shifting to OpenCL, so no more active development using Brook.

恩，基本上就是说“A卡对OpenCL的支持没有问题，只是我们没法在FAH上实现A卡对OpenCL的支持，都是我们的错！”

敢说A卡不完全支持OPEN CL的蚍蜉们！颤抖吧！

jocover · 发表于 2010-1-14 12:30

5870目前只能用256MB的global mem，而且很多opencl扩展还不支持

贵甲 · 发表于 2010-1-14 12:36

换言之，RV870的OPEN CL算是悲剧到底无可翻身了？

jocover · 发表于 2010-1-14 12:42

目前不清楚是硬件问题还是软件问题
stream 2.0 beta4时候local mem size只有16KB，2.0正式版发布后修正改为32KB，但是global mem问题还是没解决

Edison · 发表于 2010-1-14 12:45

AMD opencl 目前应该还没有 image 支持、opengl 协作也不是完全遵照 opencl 规范。

256 mb 似乎是指可以一次分配的内存大小，在 amd 的设计里好像就是只有 1/4 物理内存的大小。

贵甲 · 发表于 2010-1-14 13:08

在准备好新接口之前就抛弃brook+，与这有关么

mooncocoon · 发表于 2010-1-14 17:10

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

厄……好多人還在YY說GPU3一出來，沒了CUDA和塞錢的NV，RV8甚至RV7的咚隳芰Χ寄鼙弧笆┓拧背鰜砟豛r

看來，茶几了……

toshibacom · 发表于 2010-1-14 19:40

没事，PC上是windows说了算，只要MS的directcompute支持的好就可以了。

红发IXFXI · 发表于 2010-1-14 21:17

简单的说就是amd还是以游戏卡为主。。。什么通用计算amd没认真做

xiao069532 · 发表于 2010-1-14 21:26

全英文看不懂

贵甲 · 发表于 2010-1-15 12:48

全新杯具颤抖更新

yamhill · 发表于 2010-1-15 12:52

通用计算强就“不务正业”

通用计算差就“游戏为主”

233................

嗯，不是针对某楼～

yamhill · 发表于 2010-1-15 12:57

作为一个世界知名而且是最大的单项生化分布式运算科研项目的负责人，说出这种话足见他受了多大的刺激

233.........

yinruowen · 发表于 2010-1-15 12:58

那你们以为 A 卡能干什么

只看该作者 · 发表于 2010-1-15 13:02

提示: 作者被禁止或删除内容自动屏蔽

yinruowen · 发表于 2010-1-15 13:05

Just an update on my blog post. I want to make it clear that we're seeing problems in both of our ATI and NVIDIA GPU OpenCL implementations for OpenMM. Maybe it's on our side (I'm bet some bugs are on our side), but we suspect there could possibly be some issues with both the NVIDIA and ATI OpenCL implementations (and maybe even Apple's). We are working with everyone closely to either fix our bugs or get our code compliant with the OpenCL implementations.
Also, it looks like I should have been more careful in my wording of my previous post. I was referring to the issues above when talking about whether the ATI implementation was "fully functional" and some groups have gotten this out of my intended context. As far as I understand, the ATI OpenCL implementation is fully functional.

Finally, it is important to note that our Brook code is still supported, just not actively developed so Folding@Home/OpenMM is concentrating on shifting to OpenCL, so no more active development using Brook.

maoliwudi1 · 发表于 2010-1-15 13:20

fanyi de bu cuo

Ju1pX · 发表于 2010-1-15 13:38

这贴把某个词替换成另一个词，回复频率能高5倍。

yinruowen · 发表于 2010-1-15 13:39

Finally, it is important to note that our Brook code is still supported, just not actively developed so Folding@Home/OpenMM is concentrating on shifting to OpenCL, so no more active development using Brook.

最后,必须指出,我们的Brook代码仍然支持,只是没有积极发展,所以F@H这个项目逐渐转移到OpenCL这个中心上去,所以没有更积极的发展Brook

说白了就是Brook【请注意文明用词】去死吧

jocover · 发表于 2010-1-15 14:23

06年的G80都能完整支持opencl 1.0，AMD到了10年还没完整支持，实在是大悲剧

帐号		自动登录	找回密码
密码			注册

westlee 该用户已被删除	15^# 发表于 2010-1-15 13:02 \| 只看该作者提示: 作者被禁止或删除内容自动屏蔽
westlee 该用户已被删除
	回复支持反对使用道具举报显身卡