【全球缉拿】R600吹催的GPGPU环节怎么不见了？

phk

Programmable tessellation unit
o Accelerated geometry shader path for geometry amplification
o Memory read/write cache for improved stream output performance
• Anti-aliasing features
o Multi-sample anti-aliasing (up to 8 samples per pixel)
o Up to 24x Custom Filter Anti-Aliasing (CFAA) for improved quality
o Adaptive super-sampling and multi-sampling
o Temporal anti-aliasing
o Gamma correct
o Super AA (CrossFire configurations only)
o All anti-aliasing features compatible with HDR rendering
• Texture filtering features
o 2x/4x/8x/16x high quality adaptive anisotropic filtering modes (up to 128
taps per pixel)
o 128-bit floating point HDR texture filtering
o Bicubic filtering
o sRGB filtering (gamma/degamma)
o Percentage Closer Filtering (PCF)
o Depth & stencil texture (DST) format support
o Shared exponent HDR (RGBE 9:9:9:5) texture format support
• CrossFire™ Multi-GPU Technology
o Scale up rendering performance and image quality with 2 or more GPUs
o Integrated compositing engine
o High performance dual channel interconnect
• ATI Avivo™ HD Video and Display Platform
o Two independent display controllers
􀂃 Drive two displays simultaneously with independent resolutions,
refresh rates, color controls and video overlays for each display
􀂃 Full 30-bit display processing
􀂃 Programmable piecewise linear gamma correction, color correction,
and color space conversion
􀂃 Spatial/temporal dithering provides 30-bit color quality on 24-bit
and 18-bit displays
􀂃 High quality pre- and post-scaling engines, with underscan support
for all display outputs
􀂃 Content-adaptive de-flicker filtering for interlaced displays
􀂃 Fast, glitch-free mode switching
􀂃 Hardware cursor
o Two integrated dual-link DVI display outputs
􀂃 Each supports 18-, 24-, and 30-bit digital displays at all resolutions
up to 1920x1200 (single-link DVI) or 2560x1600 (dual-link DVI)1
􀂃 Each includes a dual-link HDCP encoder with on-chip key storage for
high resolution playback of protected content2
o Two integrated 400 MHz 30-bit RAMDACs

将文件里里外外都翻透还是没找到R600吹催的general purpose GPU环节

嘿哈哈哈哈

[ 本帖最后由 phk 于 2007-5-1 02:09 编辑 ]

phk

ATI Radeon™ HD 2900 XT Specs
Stream Processing Units 320
Clock Speed 740 MHz
Math Processing Rate
(Multiply-Add) 475 GigaFLOPS
Pixel Processing Rate 47.5 Gigapixels/sec
Triangle Processing Rate 742 Mtri/sec
Texture Units 16
Render Back-Ends 16
Memory Frame Buffer 512MB GDDR3
Memory Interface Width 512 bits
Memory Clock 825 MHz
Memory Bandwidth 106 GB/sec
Transistors 700 million
Process Technology 80HS
Outputs D+DL+DVI w/HDCP (HDMI adaptor


这东西轻轻带过，下图没再提及了



[ 本帖最后由 phk 于 2007-5-1 02:23 编辑 ]

天之福音

:lol: :lol: 看看就行了

PS5

在吹就破了，所以不敢吹了

lqf3dnow

对阿，NV吹捧的CUDA哪去了？PHK回答阿！

the_god_of_pig

传说x1k完美支持的物理加速连个影子都没有，YY了半天的视频加速还没人家完全交给VPU来的效果好，结果R6xx自己也改成完全用协处理电路了:wacko:

有种炒作的感觉(_(

[ 本帖最后由 the_god_of_pig 于 2007-5-1 12:35 编辑 ]

phk

原帖由 lqf3dnow 于 2007-5-1 12:24 发表
对阿，NV吹捧的CUDA哪去了？PHK回答阿！

在这里，欢迎lqf3dnow从火星归来w00t)

http://developer.nvidia.com/page/home

CUDA SDK version 0.8.1 beta released
We're glad to announce the release of the CUDA SDK version 0.8.1 beta for Linux and Windows XP. This version of the SDK contains 10 new samples, most of them are more advanced samples such as Image Processing and Finance...

CUDA Occupancy Calculator
The CUDA Occupancy Calculator is a programmer tool that allows you to compute the multiprocessor occupancy of a GPU by a given CUDA kernel. The multiprocessor occupancy is the ratio of active warps to the maximum number of warps supported...

lqf3dnow

the_god_of_pig

原帖由 phk 于 2007-5-1 12:44 发表


在这里，欢迎lqf3dnow从火星归来w00t)

http://developer.nvidia.com/page/home



lqf3dnow[img]http://www.techreport.com/etc/2007q2/planet.jpghttp://vietnamglobalteam.org/images/smilies/BBP/15.gif[/img]

只是怀疑性能远没有宣传的那么神(_(

Eji

原帖由 RacingPHT 于 2007-5-1 12:21 发表
G80还好像到现在还不能跑Folding@home吧？

省省吧

可能要另外寫一個....
不過我想真的要實用的話，不能用什麼特殊版Driver.....
那一點用都沒有。

cool_exorcist

原帖由 Eji 于 2007-5-2 17:28 发表


可能要另外寫一個....
不過我想真的要實用的話，不能用什麼特殊版Driver.....
那一點用都沒有。

作为创新而言，Folding@home是个不错的主意
就现在的实用性而言，现在还不实用