It used to be a small chip, that Riva... That's Riva128 on the photo below. This name awakens memories of barefooted childhood, toys, and FidoNet. There were so many disputes and fights about this card, and it begot whole camps of Voodoo and Riva fans.

I recall one story of a devoted Riva128 fan: "My girl-friend would always ask me who that Riva was? She was eager to meet her rival. And she was very offended when she learned that it was just a graphics card!"

The chip was growing together with its parent, changed its name (from Riva to GeForce), and now we've got a monster that contains about 128 of those Rivas inside. One could say that Riva128 has grown into the "128Riva". That's not an exact number, of course. It's now impossible to count how many old processors can be in one modern GPU, because the pipeline notion has disappeared to be replaced with new solutions. There is no common denominator anymore, except for the number of transistors. But this value cannot be used to evaluate performance. You cannot say that if a GPU has 100 times as many transistors, it will be 100 times as fast. The number and size of caches have grown, there have appeared new hardware features - they all require their share of transistors.

But it's sometimes very interesting to compare the first processors with the latest GPUs. Along with the above-mentioned differences, there is another one, no less important. Products were not renamed at those times, no little modifications under new names. Unlike GeForce256, GeForce2 got twice as many texture units. GeForce3 introduced the first shaders as well as new types of anisotropic filtering and antialiasing. GeForce4 Ti got twice as much memory and support for new shader versions. GeForce FX upgraded to the next DX version, etc. And what's the difference between GeForce 9800 GTX and 8800 GTX? They support the same DX version, they contain the same number of unified processors, its memory bus is even narrower. The same concerns memory. What has been changed? Only frequencies? Is that it? Add to that marketing allusions to 3-Way SLI and other innovations, which could have been easily implemented with 8800 GTX. That's all. But the name has grown by 1000. Why name this product as a next generation solution? Only because the time has come? That's not an argument.

So, we should note once again that GeForce 9800 GTX is based on the same G92 core as GeForce 8800 GTS 512 and 8800 GT (the latter has smaller number of processors). It differs little from 8800 GTS 512, as our tests have proved it.

But today we are going to examine two cards operating at significantly increased frequencies. So even though both cards are of the reference design, they are still very interesting to review.

Graphics Cards

BFG GeForce 9800 GTX OCX 512MB PCI-E
GPU: GeForce 9800 GTX (G92) Interface: PCI-Express x16 GPU frequencies (ROPs/Shaders): 756/1890 MHz (nominal - 675/1688 MHz) Memory frequencies (physical (effective)): 1152 (2304) MHz (nominal - 1100 (2200) MHz) Memory bus width: 256bit Vertex processors: - Pixel processors: - Unified processors: 128 Texture processors: 64 (BLF/TLF) ROPs: 16 Dimensions: 270x100x32 mm (the last figure is maximum thickness of the graphics card). PCB color: black RAMDACs/TDMS: integrated into GPU. Output connectors: 2xDVI (Dual-Link/HDMI), TV-Out. VIVO: not available TV-out: integrated into GPU. Multi-GPU operation: SLI (Hardware).
Zotac GeForce 9800 GTX AMP! Edition 512MB PCI-E
GPU: GeForce 9800 GTX (G92) Interface: PCI-Express x16 GPU frequencies (ROPs/Shaders): 756/1890 MHz (nominal - 675/1688 MHz) Memory frequencies (physical (effective)): 1152 (2304) MHz (nominal - 1100 (2200) MHz) Memory bus width: 256bit Vertex processors: - Pixel processors: - Unified processors: 128 Texture processors: 64 (BLF/TLF) ROPs: 16 Dimensions: 270x100x32 mm (the last figure is maximum thickness of the graphics card). PCB color: black RAMDACs/TDMS: integrated into GPU. Output connectors: 2xDVI (Dual-Link/HDMI), TV-Out. VIVO: not available TV-out: integrated into GPU. Multi-GPU operation: SLI (Hardware).

BFG GeForce 9800 GTX OCX 512MB PCI-E Zotac GeForce 9800 GTX AMP! Edition 512MB PCI-E
Each graphics card has 512 MB of GDDR3 SDRAM allocated in eight chips on the front side of the PCB. Samsung memory chips (GDDR3). 0.8 ns memory access time, which corresponds to 1250 (2500) MHz.

Comparison with the reference design, front view
Zotac GeForce 9800 GTX AMP! Edition 512MB PCI-E	Reference card NVIDIA GeForce 9800 GTX
BFG GeForce 9800 GTX OCX 512MB PCI-E

Comparison with the reference design, back view
Zotac GeForce 9800 GTX AMP! Edition 512MB PCI-E	Reference card NVIDIA GeForce 9800 GTX
BFG GeForce 9800 GTX OCX 512MB PCI-E

There is no need to describe the design, I guess. They are just reference cards, examined here.

The same concerns their cooling systems.

Both cards have TV-Out with a unique jack. You will need a special bundled adapter to output video to a TV-set via S-Video or RCA.

Analog monitors with d-Sub (VGA) interface are connected with special DVI-to-d-Sub adapters. The bundle also includes DVI-to-HDMI adapters (these graphics cards support video/audio transfer to HDMI receivers), so there should be no problems with such monitors. Maximum resolutions and frequencies:

• 240 Hz Max Refresh Rate
• 2048 x 1536 x 32bit x85Hz Max - analog interface
• 2560 x 1600 @ 60Hz Max - digital interface (all DVIs with Dual-Link)

Speaking of MPEG2 playback (DVD-Video), little has changed since 2002. CPU load during video playback on modern graphics cards does not exceed 25%.

Speaking of HDTV, there's a related review here.

Both cards require additional power supply, so each card is bundled with an adapter from molex to 6-pin, even though all modern PSUs are equipped with these cables.

Write a comment below. No registration needed!