Back in 2005 ATI released its top-to-bottom family of DirectX 9 shader model 3.0 chips in October. But that happened due to the fact that the company failed to launch the Radeon X1800 (R520) on time in May 2005, six month after the initial tape-out due to failures with the design, which resulted in lower-than-expected yield at high speeds. As a result of that, the chip was delayed for so long that two mainstream products managed to reach production stage. This time, however, the high-end part – R600 – is to be launched ahead of the other products, however, the time gap between the releases should be less than historical, sources indicated.
According to sources familiar with the plans of ATI Technologies as well as some media reports, ATI R600 will have 64 unified shader processors – an unprecedented number so far, 16 texture units – inline with today’s GPUs, clock-speed beyond 650MHz and support for high-speed GDDR4 memory controller. Obviously, components designated for lower-end market segments will have less unified shader processors.
The release of the RS700, which is to be made using 65nm process technology, in mid-2007 will put ATI behind Intel Corp.’s DirectX 10-supporting Graphics Media Accelerator 3000 built-in core in terms of functionality, as the latter is to be released in late Q3 2006, according to some reports. ATI is already behind of Nvidia Corp. in terms of integrated graphics feature-set, as even the company’s forthcoming RS600 core-logic only supports DirectX 9 shader model 2.0b, while Nvidia’s already shipping GeForce 6100-series products already features shader model 3.0. On the other hand, none of the integrated graphics processors (IGPs) developers plan to create shader model 3.0 IGPs, except of the Santa Clara, California-based supplier. ATI, Intel and SiS are known to have DirectX 10 IGPs in the roadmap for 2006 – 2007 timeframe, while plans of Nvidia Corp. are unclear.
Traditional GPUs have dedicated pixel shader and vertex shader processors. In cases, where a frame being rendered contains a lot of geometry and just a few pixel shaders to determine colour, the performance is limited by vertex shaders, while pixel processors are standing idle. GPUs with unified shader processors will have special scheduler inside them, which will determine the load from pixel, vertex and geometry shaders and then assign appropriate number of processors for every kind of work. This will allow to utilize all the computing power of the GPU, believes ATI. Nevertheless, rival Nvidia Corp. believes that implementation of a unified shader architecture should be gradual and cautious.
Officials from ATI Technologies declined to comment on the news-story.
According to sources familiar with the plans of ATI Technologies as well as some media reports, ATI R600 will have 64 unified shader processors – an unprecedented number so far, 16 texture units – inline with today’s GPUs, clock-speed beyond 650MHz and support for high-speed GDDR4 memory controller. Obviously, components designated for lower-end market segments will have less unified shader processors.
The release of the RS700, which is to be made using 65nm process technology, in mid-2007 will put ATI behind Intel Corp.’s DirectX 10-supporting Graphics Media Accelerator 3000 built-in core in terms of functionality, as the latter is to be released in late Q3 2006, according to some reports. ATI is already behind of Nvidia Corp. in terms of integrated graphics feature-set, as even the company’s forthcoming RS600 core-logic only supports DirectX 9 shader model 2.0b, while Nvidia’s already shipping GeForce 6100-series products already features shader model 3.0. On the other hand, none of the integrated graphics processors (IGPs) developers plan to create shader model 3.0 IGPs, except of the Santa Clara, California-based supplier. ATI, Intel and SiS are known to have DirectX 10 IGPs in the roadmap for 2006 – 2007 timeframe, while plans of Nvidia Corp. are unclear.
Traditional GPUs have dedicated pixel shader and vertex shader processors. In cases, where a frame being rendered contains a lot of geometry and just a few pixel shaders to determine colour, the performance is limited by vertex shaders, while pixel processors are standing idle. GPUs with unified shader processors will have special scheduler inside them, which will determine the load from pixel, vertex and geometry shaders and then assign appropriate number of processors for every kind of work. This will allow to utilize all the computing power of the GPU, believes ATI. Nevertheless, rival Nvidia Corp. believes that implementation of a unified shader architecture should be gradual and cautious.
Officials from ATI Technologies declined to comment on the news-story.