Logo   Banner   TopRight
TopUnder
Transparent
Diamond Viper Radeon HD 2900 XT 1GB
Transparent
Date: Sep 28, 2007
Section:Graphics/Sound
Author: Marco Chiappetta
Transparent
Introduction, Specifications, and Bundle

viper_logo.jpg 

Just prior to the Radeon HD 2000 series' introduction, numerous rumors circulated regarding an ultra-high clocked ATI R600-based video card, that featured a large 1GB frame buffer.  Some went so far as to say the GPU would be clocked at or near 1GHz.  Spy shots even cropped up on the web showing the card in all its glory.  But sometime between then and the official launch, news of the card fizzled and when the R600 arrived in the form of the ATI Radeon HD 2900 XT, it was outfitted with “only” 512MB of frame buffer memory and its GPU core and memory clock speeds, while somewhat high, didn’t come close to the numbers put forth in those early rumors.

Some of AMD’s partners, however, have since decided to introduce R600-based products that show there was actually some truth to the stories that circulated early on.  The product we’re going to show you here today for example, the Diamond Viper HD 2900 XT 1GB, is based on the R600 GPU, but as its name implies the card features not 512MB of frame buffer memory but a full 1GB.  The memory on the card is also clocked higher than AMD’s reference ATI Radeon HD 2900 XT’s at 1GHz (2GHz DDR).  The GPU clock remains at 742MHz, however.

We got our hands on a pair of these 1GB monsters and have compared their performance to the original  512MB Radeon HD 2900 XT, and a trio of GeForce 8800 series cards, all running in both single- and multi-GPU CrossFire and SLI configurations with some interesting results.

 

small_bundle_1.JPG     

ATI Radeon HD 2900 XT
Features & Specifications
700 million transistors on 80nm HS fabrication process

512-bit 8-channel GDD4 memory interface

Ring Bus Memory Controller

  • Fully distributed design with 1024-bit internal ring bus for memory reads and writes
  • Optimized for high performance HDR (High Dynamic Range) rendering at high display resolutions

Unified Superscalar Shader Architecture

  • 320 stream processing units
    • Dynamic load balancing and resource allocation for vertex, geometry, and pixel shaders
    • Common instruction set and texture unit access supported for all types of shaders
    • Dedicated branch execution units and texture address processors
       
  • 128-bit floating point precision for all operations
  • Command processor for reduced CPU overhead
  • Shader instruction and constant caches
  • Up to 80 texture fetches per clock cycle
  • Up to 128 textures per pixel
  • Fully associative multi-level texture cache design
  • DXTC and 3Dc+ texture compression
  • High resolution texture support (up to 8192 x 8192)
  • Fully associative texture Z/stencil cache designs
  • Double-sided hierarchical Z/stencil buffer
  • Early Z test, Re-Z, Z Range optimization, and Fast Z Clear
  • Lossless Z & stencil compression (up to 128:1)
  • Lossless color compression (up to 8:1)
  • 8 render targets (MRTs) with anti-aliasing support
  • Physics processing support

Full support for Microsoft DirectX 10.0

  • Shader Model 4.0
  • Geometry Shaders
  • Stream Output
  • Integer and Bitwise Operations
  • Alpha to Coverage
  • Constant Buffers
  • State Objects
  • Texture Arrays

Dynamic Geometry Acceleration

  • High performance vertex cache
  • Programmable tessellation unit
  • Accelerated geometry shader path for geometry amplification
  • Memory read/write cache for improved stream output performance

Anti-aliasing features

  • Multi-sample anti-aliasing (up to 8 samples per pixel)
  • Up to 24x Custom Filter Anti-Aliasing (CFAA) for improved quality
  • Adaptive super-sampling and multi-sampling
  • Temporal anti-aliasing
  • Gamma correct
  • Super AA (CrossFire configurations only)
  • All anti-aliasing features compatible with HDR rendering

CrossFire Multi-GPU Technology

  • Scale up rendering performance and image quality with 2 or more GPUs
  • Integrated compositing engine
  • High performance dual channel interconnect
Texture filtering features
  • 2x/4x/8x/16x high quality adaptive anisotropic filtering modes (up to 128 taps per pixel)
  • 128-bit floating point HDR texture filtering
  • Bicubic filtering
  • sRGB filtering (gamma/degamma)
  • Percentage Closer Filtering (PCF)
  • Depth & stencil texture (DST) format support
  • Shared exponent HDR (RGBE 9:9:9:5) texture format support

ATI Avivo HD Video and Display Platform

  • 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
       
  • 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)
    • Each includes a dual-link HDCP encoder with on-chip key storage for high resolution playback of protected content
       
  • Two integrated 400 MHz 30-bit RAMDACs
    • Each supports analog displays connected by VGA at all resolutions up to 2048x1536
       
  • HDMI output support
    • Supports all display resolutions up to 1920x1080
    • Integrated HD audio controller with multi-channel (5.1) AC3 support, enabling a plug-and-play cable-less audio solution
       
  • Integrated Xilleon HDTV encoder
    • Provides high quality analog TV output (component / S-video / composite)
    • Supports SDTV and HDTV resolutions
    • Underscan and overscan compensation
       
  • HD decode for H.264/AVC, VC-1, DivX and MPEG-2 video formats
    • Flawless DVD, HD DVD, and Blu-Ray playback
    • Motion compensation and IDCT (Inverse Discrete Cosine Transformation)
       
  • HD video processing
    • Advanced vector adaptive per-pixel de-interlacing
    • De-blocking and noise reduction filtering
    • Edge enhancement
    • Inverse telecine (2:2 and 3:2 pull-down correction)
    • Bad edit correction
    • High fidelity gamma correction, color correction, color space conversion, and scaling
  • MPEG-2, MPEG-4, DivX, WMV9, VC-1, and H.264/AVC encoding and transcoding
  • Seamless integration of pixel shaders with video in real time
  • VGA mode support on all display outputs

PCI Express x16 bus interface

OpenGL 2.0 support

 

 


    

 

Diamond bundles their Viper HD 2900 XT 1GB with a typical assortment of accessories for an HD 2000 series graphics card.  Included with the Viper were two DVI-to-VGA adapters, a single DVI-to-HDMI w/ audio adapter, component video output cables, a ViVo dongle with S-Video and composite inputs  and outputs, and a single CrossFire bridge connector.  In addition to these items we also found a driver CD and some basic documentation.  Finally, there was also a coupon for Valve’s Black Box gaming bundle (now called Orange box) that features Half Life 2: Episode 2, Team Fortress 2, and Portal.  And unlike the original HL2 / Radeon bundle, Orange box isn’t going to take forever to arrive.  In fact, news broke recently that it has gone gold and should be available soon.

Transparent
The Viper Radeon HD 2900 XT 1GB

viper_logo.jpg 

Like ATI's reference Radeon HD 2900 XT, the Diamond Viper HD 2900 XT 1GB features a dual-slot cooling solution that covers almost the entire front side of the card. It's built almost completely from copper and features multiple heat-pipes connected to its base plate and heatsink fins.  The cooling unit's barrel fan draws air into the shroud, where it is forced through the heatsink and exhausted from the system through vents in the card's mounting plate.

 

    

 

In a stock configuration, the GPU on the Diamond Viper HD 2900 XT 1GB is clocked at 742MHz and its 1GB of GDDR4 RAM is clocked at 1000MHz (2GHz DDR), please note that a high-clocked version is in the works and is currently shown on the Diamond website.  At these frequencies that card has a theoretical peak pixel processing rate of 47.5 Gigapixels/sec and a peak triangle processing rate of 742M triangles/s.  It also has up to 128GB/s of memory bandwidth thanks to its 512-bit memory interface, and increase from 106GB/s on reference 512MB cards.

The Diamond Viper HD 2900 XT 1GB cards are outfitted with two supplemental power connectors, one common 6-pin PCI Express connector and one 8-pin PCI Express power connector.  The card will function properly with a pair of 6-pin power feeds, but users won't be able to overclock their cards unless an 8-pin feed in connected. This supplemental power connector configuration is necessary because a single Radeon HD 2900 XT can consume upwards of 215 watts.

 

    

 

As you probably expect, the card also has native CrossFire support and doesn't require an external dongle. Updates to ATI's drivers further enhance CrossFire by eliminating the need for application specific profiles.  According to ATI, upcoming Catalyst drivers will default to AFR mode to accelerate an application right out of the gate.  But the drivers also have a built-in mechanism to detect whether or not an application is AFR compatible, and if it isn't, a different mode will be used.

 

    

 

The Diamond Viper HD 2900 XT 1GB cards are equipped with dual, dual-link DVI outputs with HDCP support and cards outfitted with a Theater 200 chip and feature ViVo functionality as well.  And as is the case with other Radeon HD 2000 series cards, these have the ability to output digital audio over HDMI though the use of a special adapter that's included with the cards as well.

Transparent
Our Test Systems and 3DMark06

viper_logo.jpg

HOW WE CONFIGURED THE TEST SYSTEMS: We tested all of the graphics cards used in this article on either an EVGA nForce 680i SLI motherboard (NVIDIA GPUs) or an Intel D975XBX2 board (ATI GPUs) powered by a Core 2 Extreme X6800 dual-core processor and 2GB of low-latency Corsair RAM. The first thing we did when configuring the test system was enter the BIOS and set all values to their "optimized" default settings. Then we manually configured the memory timings and disabled any integrated peripherals that wouldn't be put to use. The hard drive was then formatted, and Windows XP Pro with SP2 and the April '07 DX9 update was installed. When the installation was complete, we then installed the latest chipset drivers available, installed all of the other drivers necessary for the rest of our components, and removed Windows Messenger from the system.  Auto-Updating and System Restore were also disabled, the hard drive was defragmented, and a 1024MB permanent page file was created on the same partition as the Windows installation. Lastly, we set Windows XP's Visual Effects to "best performance," installed all of the benchmarking software, and ran the tests.

The HotHardware Test System
Core 2 Extreme Powered


Processor -

Motherboard -






Video Cards -





Memory -


Audio -

Hard Drive
-

Hardware Used:
Core 2 Extreme X6800 (2.93GHz)


EVGA nForce 680i SLI
nForce 680i SLI chipset

Intel D975XBX2
975X Express 

Viper Radeon HD 2900 XT 1GB (2)
GeForce 8800 GTX (2)
GeForce 8800 GTS (2)
EVGA GeForce 8800 GTS (2)  

Radeon HD 2900 XT (2)

2048MB Corsair PC2-6400C3
2 X 1GB

Integrated on board

Western Digital "Raptor"

74GB - 10,000RPM - SATA


OS -
Chipset Drivers -
DirectX -

Video Drivers
-



Synthetic (DX) -
DirectX -
DirectX -
DirectX -
DirectX -
OpenGL -
 

 
 
Relevant Software:
Windows XP Pro SP2
nForce Drivers v9.53
DirectX 9.0c (April '07 Redist.)

NVIDIA Forceware v158.19
ATI Catalyst v7.9


Benchmarks Used:
3DMark06 v1.0.2
S.T.A.L.K.E.R.*
F.E.A.R. v1.08
Half Life 2: Episode 1*
Prey v1.3*

* - Custom Test (HH Exclusive demo)

Performance Comparisons with 3DMark06 v1.0.2
Details: www.futuremark.com/products/3dmark06


3DMark06
3DMark06 is the most recent addition to the 3DMark franchise. This version differs from 3Dmark05 in a number of ways, and includes not only Shader Model 2.0 tests, but Shader Model 3.0 and HDR tests as well. Some of the assets from 3DMark05 have been re-used, but the scenes are now rendered with much more geometric detail and the shader complexity is vastly increased as well. Max shader length in 3DMark05 was 96 instructions, while 3DMark06 ups that number to 512. 3DMark06 also employs much more lighting and there is extensive use of soft shadows. With 3DMark06, Futuremark has also updated how the final score is tabulated. In this latest version of the benchmark, SM 2.0 and HDR / SM3.0 tests are weighted and the CPU score is factored into the final tally as well.

 

Despite having much faster memory and double the frame buffer, the Viper Radeon HD 2900 XT 1GB just missed the mark set by the 512MB Radeon HD 2900 XT in 3DMark06's overall score.  The reason behind the discrepancy is revealed as we dig a little deeper into the result.

 

 

As you can see the Viper Radeon HD 2900 XT 1GB came in just behind the 512MB card in the Shader Model 2.0 test and by slightly ahead of it in the more taxing Shader Model 3.0 and HDR test, but due to the way scores are weighted in 3DMark06 the overall result shows a win for the 512MB card.

 

Transparent
Half Life 2: Episode 1

viper_logo.jpg 

Performance Comparisons with Half-Life 2: Episode 1

Details: www.half-life2.com


Half Life 2:
Episode 1

Thanks to the dedication of hardcore PC gamers and a huge mod-community, the original Half-Life became one of the most successful first person shooters of all time.  And thanks to an updated game engine, gorgeous visual, and intelligent weapong and level design, Half Life 2 became almost as popular.  Armed with the latest episodic update to HL2, Episode 1, we benchmarked the game with a long, custom-recorded timedemo that takes us through both outdoor and indoor environments. These tests were run at resolutions of 1,280 x 1,024 through 1,920 x 1,200 with 4X anti-aliasing and 16X anisotropic filtering enabled concurrently, and with color correction and HDR rendering enabled in the game engine as well.

 

 

As the resolution was increased, the Viper Radeon HD 2900 XT 1GB card's performance was slightly better than its 512MB counterpart.  Overall though, the various flavors of GeForce 8800 cards we tested were clearly faster at every resolution.

Transparent
F.E.A.R.

viper_logo.jpg 

Performance Comparisons with F.E.A.R
More Info: www.whatisfear.com/us

F.E.A.R
One of the most highly anticipated titles of recent years was Monolith's paranormal thriller F.E.A.R. According to the game's minimum system requirements, it needs at least a 1.7GHz Pentium 4 with 512MB of system memory and a 64MB graphics card in the Radeon 9x00 or GeForce4 Ti-classes or better, to adequately run. Using the full retail release of the game patched to v1.08, we put the graphics cards in this article through their paces to see how they fared with a popular title. Here, all graphics settings within the game were set to their maximum values, but with soft shadows disabled (Soft shadows and anti-aliasing do not work together currently). Benchmark runs were then completed at resolutions of 1,280x1,024 through 1,920 x 1,200, with 4x anti-aliasing and 16x anisotropic filtering enabled.

 

 

The Viper Radeon HD 2900 XT 1GB card's huge frame buffer didn't result in significantly higher performance in the F.E.A.R. benchmark.  It was a single frame per second faster than the 512MB Radeon HD 2900 XT at a couple of the resolutions we tested, and it performed slightly better than the reference GeForce 8800 GTS, but the factory overclocked EVGA GTS and the GeForce 8800 GTS were much faster across the board.

Transparent
Prey

viper_logo.jpg 

Performance Comparisons with Prey
Details: www.prey.com


Prey
After many years of development, Take-Two Interactive recently released the highly anticipated game Prey. Prey is based upon an updated and modified version of the Doom 3 engine, and as such performance characteristics between it and Doom 3 are quite similar.  Also like Doom 3, Prey is an OpenGL-based game that uses extremely high-detailed textures and a plethora of dynamic lighting and shadows.  But unlike Doom, Prey features a fare share of outdoor environments as well.  We ran these Prey benchmarks using a custom recorded timedemo with the game set to its "High-Quality" graphics mode, at resolutions of 1,280 x 1,024 through 1,920 x 1,200 with 4X AA and 16X anisotropic filtering enabled simultaneously.

 

 

Our custom Prey benchmark proved to be somewhat of a strong point for the Viper Radeon HD 2900 XT 1GB.  At all three resolutions it was a couple of frames per second faster than the 512MB version and it outpaced both of the GeForce 8800 GTS cards at all but the lowest resolution.  It still couldn't come close to the performance put forth by the GeForce 8800 GTX, however.

Transparent
S.T.A.L.K.E.R.

viper_logo.jpg

Performance Comparisons with S.T.A.L.K.E.R.
Details: www.stalker-game.com

small_stalk.jpg
S.T.A.L.K.E.R.
The highly anticipated game S.T.A.L.K.E.R. makes use of a proprietary DX9 game engine, dubbed "X-Ray" by its developers. It features an advanced DX9 renderer with Defferred Shading capabilities, which allows the engine to draw a vast amount of dynamic light sources with correct materials and light ‘feedback’. Becuase S.T.A.L.K.E.R. does not have a built-in benchmarking tool, we tested the game using FRAPS at resolutions of 1,280x1,024 through 2,560 x 1,600 with the in-game anti-aliasing and anisotropic filtering options set to their maximum values, and with full dynamic lighting enabled. We should also note that 'grass shadows' were disabled due to the dramatic slowdowns this feature causes during gameplay.

 

 

 

The Viper Radeon HD 2900 XT 1GB card's larger and faster frame buffer gave it a marked advantage over the 512MB Radeon HD 2900 XT in S.T.A.L.K.E.R. and gave it the ability to hang just behind the reference GeForce 8800 GTS.  However, the factory overclocked EVGA GeForece 8800 GTS and GeForce 8800 GTX were measurably faster at all resolutions.

Transparent
3DMark06 (Multi-GPU)

viper_logo.jpg 

From this point forward, we'll be comparing the performance of the Diamond Viper Radeon HD 2900 XT 1GB to its competition in dual-card, CrossFire and SLI configurations.

Performance Comparisons with 3DMark06 v1.0.2
Details: www.futuremark.com/products/3dmark06


3DMark06
3DMark06 is the most recent addition to the 3DMark franchise. This version differs from 3Dmark05 in a number of ways, and includes not only Shader Model 2.0 tests, but Shader Model 3.0 and HDR tests as well. Some of the assets from 3DMark05 have been re-used, but the scenes are now rendered with much more geometric detail and the shader complexity is vastly increased as well. Max shader length in 3DMark05 was 96 instructions, while 3DMark06 ups that number to 512. 3DMark06 also employs much more lighting and there is extensive use of soft shadows. With 3DMark06, Futuremark has also updated how the final score is tabulated. In this latest version of the benchmark, SM 2.0 and HDR / SM3.0 tests are weighted and the CPU score is factored into the final tally as well.

 

Just like we saw in the single card tests, the dual card Viper Radeon HD 2900 XT 1GB CrossFire configuration put up an overall 3DMark06 score just slightly lower than its 512MB counterpart.

 

 

 

This time around, however, the Viper Radeon HD 2900 XT 1GB CrossFire rig finished behind the 512MB Radeon HD 2900 XT CrossFire configuration in both the Shader Model 2.0 and Shader Model 3.0 / HDR tests.  At these settings, 3DMark06 is limited by the GPU's shader performance and fillrate, and not so much by its frame buffer size and memory bandwidth.

 

Transparent
Half Life 2: Episode 1 (Multi-GPU)

viper_logo.jpg

Performance Comparisons with Half-Life 2: Episode 1

Details: www.half-life2.com


Half Life 2:
Episode 1

Thanks to the dedication of hardcore PC gamers and a huge mod-community, the original Half-Life became one of the most successful first person shooters of all time.  And thanks to an updated game engine, gorgeous visual, and intelligent weapong and level design, Half Life 2 became almost as popular.  Armed with the latest episodic update to HL2, Episode 1, we benchmarked the game with a long, custom-recorded timedemo that takes us through both outdoor and indoor environments. These tests were run at resolutions of 1,280 x 1,024 through 21,920 x 1,200 with 4X anti-aliasing and 16X anisotropic filtering enabled concurrently, and with color correction and HDR rendering enabled in the game engine as well.

 

 

 

Our multi-GPU HL 2: Episode 1 tests mirror those of the single card tests from a few pages back.  The Diamond Viper HD 2900 XT 1GB CrossFire configuration is marginally faster than the 512MB Radeon HD 2900 XT setup, but the GeForce cards held a commmanding lead.

Transparent
F.E.A.R. (Multi-GPU)

viper_logo.jpg 

Performance Comparisons with F.E.A.R
More Info: www.whatisfear.com/us

F.E.A.R
One of the most highly anticipated titles of recent years was Monolith's paranormal thriller F.E.A.R. According to the game's minimum system requirements, it needs at least a 1.7GHz Pentium 4 with 512MB of system memory and a 64MB graphics card in the Radeon 9x00 or GeForce4 Ti-classes or better, to adequately run. Using the full retail release of the game patched to v1.08, we put the graphics cards in this article through their paces to see how they fared with a popular title. Here, all graphics settings within the game were set to their maximum values, but with soft shadows disabled (Soft shadows and anti-aliasing do not work together currently). Benchmark runs were then completed at resolutions of 1,280x1,024 through 1,920 x 1,200, with 4x anti-aliasing and 16x anisotropic filtering enabled.

 

 

Our multi-GPU F.E.A.R. tests proved to be rather interesting.  Here, the Diamond Viper HD 2900 XT 1GB CrossFire configuration was about 10% faster than its dual-512MB card counterpart and it performed on about the same level as the reference GeForce 8800 GTS SLI rig.  The factory overclocked GTSs and the GeForce 8800 GTX SLI setup, however, were clearly more powerful.

Transparent
Prey (Multi-GPU)

viper_logo.jpg

Performance Comparisons with Prey
Details: www.prey.com


Prey
After many years of development, Take-Two Interactive recently released the highly anticipated game Prey. Prey is based upon an updated and modified version of the Doom 3 engine, and as such performance characteristics between it and Doom 3 are quite similar.  Also like Doom 3, Prey is an OpenGL-based game that uses extremely high-detailed textures and a plethora of dynamic lighting and shadows.  But unlike Doom, Prey features a fare share of outdoor environments as well.  We ran these Prey benchmarks using a custom recorded timedemo with the game set to its "High-Quality" graphics mode, at resolutions of 1,280 x 1,024 through 1,920 x 1,200 with 4X AA and 16X anisotropic filtering enabled simultaneously.

 

 

The Diamond Video HD 2900 XT 1GB CrossFire rig performed relatively well in our custom Prey benchmark.  Here, the dual 1GB-card setup was on par with the 512MB Radeons and both GeForce 8800 GTS configurations.  The GeForce 8800 GTX SLI configuration was much faster than everything else though.

 

Transparent
S.T.A.L.K.E.R. (Multi-GPU)

viper_logo.jpg 

Performance Comparisons with S.T.A.L.K.E.R.
Details: www.stalker-game.com
small_stalk.jpg
S.T.A.L.K.E.R.
The highly anticipated game S.T.A.L.K.E.R. makes use of a proprietary DX9 game engine, dubbed "X-Ray" by its developers. It features an advanced DX9 renderer with Defferred Shading capabilities, which allows the engine to draw a vast amount of dynamic light sources with correct materials and light ‘feedback’. Becuase S.T.A.L.K.E.R. does not have a built-in benchmarking tool, we tested the game using FRAPS at resolutions of 1,280x1,024 through 1,920 x 1,200 with the in-game anti-aliasing and anisotropic filtering options set to their maximum values, and with full dynamic lighting enabled. We should also note that 'grass shadows' were disabled due to the dramatic slowdowns this feature causes during gameplay.

 

 

Score one for the Radeons.  In dual-GPU CrossFire configurations, the Radeons, and more specifically the Diamond Viper HD 2900 XT 1GB cards put up the best overall scores in our custom S.T.A.L.K.E.R. benchmark, outpacing even the GeForce 8800 GTX SLI setup.  The Radeon's lead dwindles as the resolution increases, however.

 

Transparent
Overclocking the Viper

viper_logo.jpg 

For our next set of performance metrics, we spent some time overclocking the Diamond Viper HD 2900 XT 1GB using ATI Tool.

Please note, that overclocking is NOT supported on Radeon HD 2900 XT cards with the Catalyst drivers unless an 8-Pin PCI Express supplemental power connector is plugged into the card, along with a secondary 6-Pin feed. When asked why they made the 8-Pin connector a requirement for overclocking, representative from ATI said it was due to major variations in power consumption between not only stock and overclocked configurations, but between different HD 2900 XT GPUs. It seems TSMC's 80nm HS process allowed ATI to clock the R600 relatively high, but once the upper limits of the GPU's clock speed are hit, power consumption can vary considerable from card to card. Having the 8-Pin supplemental feed available means there should always be ample power available to the card.

Overclocking the Viper Radeon HD 2900 XT 1GB
(Fast 3D Video Card) + Overclocking = Even Faster Card

To find the Radeon HD 2900 XT's peak core and memory frequencies, we slowly raised their respective sliders until we begun to see visual artifacts on-screen while running a game or benchmark, or until our test system was no longer stable.

 

 

In the end, we were able to take the Diamond Viper Radeon HD 2900 XT up from its stock GPU core and memory clock speeds of 742MHz / 1000MHz, to 858MHz / 1089MHz.  While we had the card overclocked we re-ran a couple of high-resolution benchmarks and saw significant performance increases in both. F.E.A.R. in particular liked the cards higher clocks, which resulted in a 7 FPS increase.

 

Transparent
Our Summary and Conclusion

viper_logo.jpg 

Performance Summary: The Diamond Viper HD 2900 XT 1GB performed well throughout our tests, but its higher capacity and faster frame buffer did not result in very large performance gains.  Generally, the Viper HD 2900 XT 1GB was between 1% and 12% faster than a reference 512MB Radeon HD 2900 XT; some of its larger gains came at higher resolutions with games like F.E.A.R. and S.T.A.L.K.E.R.  In comprison to stock and factory overclocked GeForce 8800 GTS cards, the Viper HD 2900 XT 1GB's performance falls somewhere in between the two, winning in some tests and losing in others.  And overall the GeForce 8800 GTX was clearly the best performer.

 

 

 

The Diamond Viper HD 2900 XT 1GB is arguably the most powerful ATI GPU-based video card on the market.  With it's 1GB of fast GDDR4 memory and 512-bit memory interface, this card offers an impressive 128GB/s of peak bandwidth.  Unfortunately, with an R600 clocked at 742MHz, it seems the GPU just can satisy the frame buffer's hunger for data fast enough to significantly impact performance.  As our overclocking tests showed, there is some serious headroom left in the GPU so better-than-stock performance is almost a given with these cards. But better than stock still puts it on about the same level as a factory overclocked, yet more affordable, GeForce 8800 GTS.  In fact, at about $499 - $530, the Diamond Viper HD 2900 XT 1GB costs about as much as a GeForce 8800 GTX, which is a much higher performing card overall.  We also found the GeForces to be quieter and as out testing showed in our initial launch coverage, NVIDIA's cards consume less power too.  The Radeon does offer some more features and anti-aliasing modes, audio over HDMI, and a copy of Valve's Orange Box, which enhances its value proposition somewhat, but at its current price point this card is a tough sell.

 

  • Good Performance
  • Decent Overclocker
  • Great Image Quality
  • 1GB Frame Buffer
  • Expensive
  • Outperformed by less expensive cards
  • Somewhat Loud

Discuss This Article With Other HotHardware Readers!

 

A Forum Thread Has Already Been Started For You!

  



Content Property of HotHardware.com