Bookmark and Share


NVIDIA’s driver for graphics processing units released hours ago supports graphics cards with 512MB frame-buffer, it transpired. While currently there are no graphics cards with that lot of memory onboard, they are likely to be available in future and it may appear that in not too-distant-future.

ForceWare 66.93 drivers released on the 9th of November, 2004, correct certain bugs, are designed to improve performance in 3D applications and also enable NVIDIA’s programmable video processor. Additionally, the new drivers contain a number of enhancements, such as support for GeForce 6600, GeForce 6600 GT, and GeForce 6200, SLI multi-GPU configurations, HDTV use over DVI connectors, advanced DVI timing on all GeForce 6 series GPUs, 512 MB frame buffer GPUs and some more capabilities.

Currently there are no graphics cards with 512MB frame-buffer aimed at consumers. Only professional graphics cards, such as certain versions of NVIDIA Quadro, sport 512MB frame-buffer. It is not clear whether it is enough cost-effective for graphics chips designers to vow for 512MB graphics cards, as GDDR3 memory currently used on high-end graphics products is pretty expensive.

NVIDIA’s new ForceWare drivers does not support any new GPUs, such as code-named NV50, NV47 and NV48. Therefore, upcoming 512MB graphics cards may be based on current generation of graphics processing units.

Leading developers of graphics processors, such as NVIDIA Corp. and ATI Technologies, usually tend to double the amount of on-board memory on high-end graphics products every 12 to 18 months. More on-board memory allows graphics cards to store more textures near the graphics chip, which in some cases improves performance, as the processor does not have to pump the data it needs from system memory via AGP or PCI Express bus. However, the first generation of graphics cards that feature doubled amount of memory compared to predecessors usually do not make much use of this advantage because contemporary games are developed with lower amount of graphics memory in mind, while the future titles require visual processing units with higher computing power.

The first graphics cards with 256MB of memory for consumers were released in mid-2003 along with the GeForce FX 5900 Ultra and RADEON 9800 PRO 256MB products. Currently even entry-level offerings feature 256MB of relatively slow memory. Besides technology-related reasons to put more memory onboard, there is a marketing reason for that – a lot of end-users tend to get graphics card with more graphics random access memory hoping to get higher speed.

NVIDIA Corp. officials did not comment on the story. X-bit labs polled representatives for NVIDIA, NVIDIA’s add-in-card partners, ATI Technologies and ATI’s add-in-card partners. While the majority declined to comment, some of ATI’s partners said 512MB boards would emerge only when it is economically feasible to make such products.


Comments currently: 4
Discussion started: 11/10/04 08:57:53 AM
Latest comment: 09/23/07 08:26:24 PM

Add your Comment

Related news

Latest News

Thursday, August 21, 2014

10:59 pm | Khronos Group to Follow DirectX 12 with Cross-Platform Low-Level API. Khronos Unveils Next-Generation OpenGL Initiative

10:33 pm | Avexir Readies 3.40GHz DDR4 Memory Modules. DDR4 Could Hit 3.40GHz This Year

12:10 pm | AMD to Lower Prices of A-Series APUs for Back-to-School Season. New Prices of AMD A-Series APUs Revealed

Wednesday, August 20, 2014

10:53 am | AMD to Cut Prices on FX-9000, Other FX Processors: New Prices Revealed. AMD to Make FX Chips More Affordable, Discontinue Low-End Models

10:32 am | LG to Introduce World’s First Curved 21:9 Ultra-Wide Display. LG Brings Curved Displays to Gamers, Professionals

9:59 am | AMD Readies FX-8370, FX-8370E Microprocessors. AMD Preps Two New “Mainstream” FX Chips