Bookmark and Share


We told you about a week ago in the part one of our CeBIT Coverage that NVIDIA’s next-generation NV35 graphics solution shows significant improvement in performance over the current NV30 also known as the GeForce FX 5800 Ultra. Today I noticed over this German web-site more details about the NV35-based graphics card demonstrated behind the closed doors at CeBIT 2003 in Hannover, Germany.

Firstly I should mention that the NV35 powered reference design demonstrated at the tradeshow worked only at 250/500MHz for core and memory. In order to demonstrate the advantages brought by the new graphics processor, NVIDIA set the core and memory frequencies of the GeForce FX 5800-based graphics card also at 250/500MHz. According to the source, NV35 was able to render 110fps in Quake III Arena (demo 001) at 1600x1200 with 4x FSAA and 8x Anisotropic Filtering, while the NV30 only achieved 48fps in the benchmark. The Achilles’ hill of the current GeForce FX 5800 is its 128-bit bus, what seems to be the reason why the NV30 is outperformed by the NV35 that features 256-bit memory bus by roughly 130% in some cases. Since we have no information about performance scalability of the NV30 and NV35 graphics processors we can hardly draw a precise conclusion right now, however, I can state for sure that the NV35-based graphics cards will be a lot more powerful and efficient compared to the current NV30.

Wonder why NVIDIA clocks the upcoming NV35 at lower speeds? Well, there can be at least two reasons why the Santa Clara, California-based semiconductor developer decided to showcase the slower than designated graphics card:

  • NVIDIA does not want to show the rivals any exact performance figures of the NV35, but wants its partners and investors to realise that the forthcoming chip will definitely be a lot better than the current.
  • NVIDIA again has problems with achieving high frequencies of the graphics processor itself, or there are problems with the current revision of the PCB. Problems with the GPU are in general more likely than problems with PCB.

NVIDIA’s NV35 graphics processor is based on the NV3x architecture, manufactured using TSMC’s 0.13 micron technology and incorporates 130 million transistors. The novelty is expected to be officially announced in the second quarter this year.


Comments currently: 1
Discussion started: 03/23/03 11:56:38 AM
Latest comment: 03/23/03 11:56:39 AM

Add your Comment

Related news

Latest News

Tuesday, July 15, 2014

6:11 am | Apple Teams Up with IBM to Make iPhone and iPad Ultimate Tools for Businesses and Enterprises. IBM to Sell Business-Optimized iPhone and iPad Devices

Monday, July 14, 2014

6:01 am | IBM to Invest $3 Billion In Research of Next-Gen Chips, Process Technologies. IBM to Fund Development of 7nm and Below Process Technologies, Help to Create Post-Silicon Future

5:58 am | Intel Postpones Launch of High-End “Broadwell-K” Processors to July – September, 2015. High-End Core i “Broadwell” Processors Scheduled to Arrive in Q3 2015

5:50 am | Intel Delays Introduction of Core M “Broadwell” Processors Further. Low-Power Broadwell Chips Due in Late 2014

Wednesday, July 9, 2014

4:04 pm | Intel Readies New Quark “Dublin Bay” Microprocessors. Intel’s “Dublin Bay” Chips Due in 2015