PowerColor Radeon X1900 GT video card review
Written by Hanners  
Tuesday, 16 May 2006 00:00
Article Index
PowerColor Radeon X1900 GT video card review
Board, bundle and packaging
Test setup, synthetic benchmarks
Oblivion, Quake 4
DoD Source, Lost Coast
F.E.A.R., Age of Empires III
NFS: Most Wanted, Call of Duty 2
Chaos Theory, Adaptive AA
Overclocking, Conclusions

  

PowerColor Radeon X1900 GT video card review

The launch of the Radeon X1900 series of boards at the beginning of this year marked the end of what had been a difficult period for ATI - After losing the overall technological leadership to NVIDIA's GeForce 6 series, due to their decision to stick to using a Shader Model 2.0 based architecture while their rivals moved to Shader Model 3.0, to make matters worse ATI's foray into the Shader Model 3.0 marketplace was delayed due to issues with their flagship R520 chip that took some time to resolve, thus pushing back the launch of the Radeon X1000 series.

Finally, everything came right with R580, aka the Radeon X1900 - It arrived on time, and took the performance crown.  NVIDIA have since retaliated with the GeForce 7900 series of parts, but ATI are still now perceived as sitting pretty at the high-end, thanks to their innovative architecture, comprehensive feature set and impressive performance.

There has, however, been one crack in ATI's high-end crown, namely the lack of a direct competitor for the GeForce 7900 GT.  Today, we're going to be taking a look at the product that removes this imbalance by utilising a cut-down version of the R580 core, the Radeon X1900 GT.

Radeon X1900 architecture

We discussed the underlying architecture behind the Radeon X1900, aka R580, in some depth at the product's initial launch, so check out our coverage at the time if you want to get a better technical grounding behind the architecture.

As with ATI's reduced Radeon X1800 part, the X1800 GTO, the Radeon X1900 GT incorporates the full feature set of the R580 architecture, but with one functional unit disabled.  The main upshot of this is that the number of pixel pipelines in this part is reduced to twelve, which also leaves the core with 36 pixel shader units compared to 48 on a full Radeon X1900.  Despite being effectively 'decoupled' from the pixel pipelines in this architecture, the number of texture units in the X1900 GT is also reduced to twelve compared to sixteen on a full R580 core.

Clock speeds are also reduced in this part compared to the X1900 XT and XTX, with the X1900 GT exhibiting a core clock speed of 575MHz, and a memory clock of 600MHz.  You can see the full list of features available on this part below. 

    • Ultra Threaded Shader Engine
      • Support of DirectX9 Programmable Vertex and Pixel Shaders
      • VS3.0 Vertex Shader functionality
        • 1024 Instructions (Unlimited with flow control)
        • Single Cycle Trigonometric Operations (SIN & COS)
      • PS3.0 Pixel Shaders
        • Ultra Thread Pixel Shader Engine
        • Fast Dynamic Branching
        • Single Precision 128-bit Floating Point (FP32) Processing
        • 16 textures per rendering pass
        • 32 temporary and constant registers per pixel
        • Facing register for two-sided lighting
        • Multiple render target support
        • Shadow volume rendering acceleration
        • 128-bit, 64-bit & 32-bit per pixel floating point colour formats
    • Advanced Image Quality Features
      • HDR Blending on FP16, Int10 and Custom Formats
        • All Blending modes work with all Anti-Aliasing Modes
      • 3Dc+ Normal Map Compression
        • High quality 4:1 Normal Map Compression
        • Two Channel & Single Channel format support
      • 2x/4x/6x Multi-Sampling full scene Anti-Aliasing modes, adaptive algorithm with programmable sample patterns and colour buffer compression
      • Adaptive Anti-Aliasing for Transparent Surfaces
      • Temporal Anti-Aliasing
      • Lossless Color Compression (up to 6:1) at all resolutions, including widescreen HDTV resolutions
      • High Quality, Angle Invariant, Anisotropic Filter Mode
      • 2x/4x/8x/16x Anisotropic Filtering modes
      • 4Kx4X texture Support
    • Memory Controller
      • Internal Ring Bus Architecture (RV530)
      • Programmable Arbitration Logic
      • Fully Associative Caches
      • 3-level, Floating Point, Hierarchical Z-Buffer with early Z test
      • Lossless Z-Buffer compression (up to 48:1)
      • Fast Z-Buffer Clear
      • Z Cache Optimisations for shadow rendering
      • Optimized for performance at high display resolutions, including widescreen HDTV resolutions
    • AVIVO
      • Dual 10-bit Display Pipelines
      • Dual Integrated Dual Link TMDS Transmitters, Dual 400MHz RAMDACS, Xilleon Derived TV Output.
      • Hardware Accelerated H.264 Decode