Chiphell - 分享与交流用户体验

 找回密码
 加入我们
搜索
      
查看: 3099|回复: 15

[PC硬件] Bullet Physics劈腿了:刚和AMD好上又和NV眉来眼去

[复制链接]
发表于 2009-9-24 07:42 | 显示全部楼层 |阅读模式
Erwin,Bullet physics创始人声称:AMD 的物理加速将适用于任何Opencl标准的驱动。我们正在用Geforce卡来开发,甚至用NV的opencl sdk 代码。很不错!!
NV对physx的推广简直无处不在。。。


ATI supported Bullet Physics developed on Geforce                                                                        

http://www.fudzilla.com/content/view/15642/1/
Slap in the face

We have seen a presentation where Nvidia claims that Mr. Erwin Coumans, the creator of Bullet Physics Engine, said that he developed Bullet physics on Geforce cards. The bad thing for ATI is that they are betting on this open standard physics tech as the one that they want to accelerate on their GPUs.

"ATI’s Bullet GPU acceleration via Open CL will work with any compliant drivers, we use NVIDIA Geforce cards for our development and even use code from their OpenCL SDK, they are a great technology partner. “ said Erwin.

This means that Bullet physics is being developed on Nvidia Geforce cards even though ATI is supposed to get driver and hardware acceleration for Bullet Physics. With such a statement we comes to question whether ATI has any kind of OpenCL driver that it can push for its own Physics. Even if they do, Nvidia is far ahead with PhysX and Intel won’t let them accelerate Havok, as this is a good task for Larrabee, whenever that comes.

To spice things up, Bullet (AMD/ ATI supported) physics is listing that PhysX with 26.8 percent is the most popular physics library, at least according to Gamedeveloper magazine. Intel’s Havok is second with saucy 22.7 percent and Bullet is third with 10.4 percent. The AMD supported API is clearly behind the competition, but it's still better than Open Dynamics Engine (ODE) that has 4.1 percent of the market.

You can check this here.  
 楼主| 发表于 2009-9-24 07:43 | 显示全部楼层
人心啊变得真快
发表于 2009-9-24 08:23 | 显示全部楼层
amd本身就不准备支持私有标准的东西
opencl的框架里,随便谁的都应该会支持吧
 楼主| 发表于 2009-9-24 08:26 | 显示全部楼层
amd本身就不准备支持私有标准的东西
opencl的框架里,随便谁的都应该会支持吧
jeandja 发表于 2009-9-24 08:23


就算同一个通用标准,执行效率还是有差别的。
发表于 2009-9-24 08:37 | 显示全部楼层
哎~~AMD咋就套不住个人呢
发表于 2009-9-24 10:59 | 显示全部楼层
老黄真会花钱
发表于 2009-9-24 11:15 | 显示全部楼层
无耻者无畏.
发表于 2009-9-24 11:17 | 显示全部楼层
本帖最后由 idle.man5216 于 2009-9-24 11:18 编辑

AMD 是从 CUDA 把 Bullet Physics 移植到 OpenCL 之上,NVIDIA 又在炫耀自己了。*/-91
而且又是 Fudzilla,现在 Fudzilla 像 BSN 一样越来越 N 枪了。*/-27
发表于 2009-9-24 11:57 | 显示全部楼层
没法子,谁让nv有银子呢
发表于 2009-9-24 12:40 | 显示全部楼层
AMD 是从 CUDA 把 Bullet Physics 移植到 OpenCL 之上,NVIDIA 又在炫耀自己了。*/-91
而且又是 Fudzilla,现在 Fudzilla 像 BSN 一样越来越 N 枪了。*/-27
idle.man5216 发表于 2009-9-24 11:17


意思是BULLET本来属于CUDA框架?
发表于 2009-9-24 13:56 | 显示全部楼层
这跟physx有一毛钱的关系吗!!!!
发表于 2009-9-24 20:02 | 显示全部楼层
AMD又杯具了
发表于 2009-9-24 20:11 | 显示全部楼层
LS的都是怎么理解的?NV还要到Opencl插一腿,就足以证明连NV自己都没信心死守CUDA。NV折腾得越欢,就说明CUDA前景越黯淡,杯具的是NV。
发表于 2009-9-24 20:41 | 显示全部楼层
*/-16LS的好象也有一定道理
发表于 2009-9-24 21:15 | 显示全部楼层
OPENCL早點定下標準 還改什麽
发表于 2009-9-24 23:44 | 显示全部楼层
也不是坏事來的 */-12
您需要登录后才可以回帖 登录 | 加入我们

本版积分规则

小黑屋|手机版|Archiver|Chiphell ( 沪ICP备12027953号-5 )沪公网备310112100042806 上海市互联网违法与不良信息举报中心

GMT+8, 2020-11-27 20:14 , Processed in 0.009844 second(s), 20 queries , Gzip On, Redis On.

Powered by Discuz! X3.2

© 2007-2020 Chiphell.com All rights reserved.

快速回复 返回顶部 返回列表