ASUS EAX1950PRO Radeon X1950 PRO video card review
As we seem to be mentioning ever-more frequently on the hallowed pages of Elite Bastards these days, the $199 price point is a really important one for the graphics IHVs, where there is money aplenty to be made. Recent months have seen this price point dominated by NVIDIA, courtesy of their GeForce 7900 GS, but last week ATI made a comeback thanks to their first 80nm desktop GPU, the RV570-based Radeon X1950 PRO.
As boards based on this SKU are slowly beginning to find their way to retail outlets, we take a look at ASUS' take on the Radeon X1950 PRO, the EAX1950PRO. With ATI allowing more freedom over both cooling solutions and clock speeds these days, the differentiation between AIB partner's boards is becoming ever-more important, so let's take a look at what ASUS has brought to the table this time around.
RV570 architecture
We covered the architecture behind the Radeon X1950 PRO, in the form of the RV570 core, in some detail on its launch day here, but let's just recap for the sake of this review. RV570 is the first desktop GPU to be manufactured using the 80 nanometre process, and this core is designed specifically as a replacement for ATI's previous, R580 based, Radeon X1900 GT. As a result, its architecture is broadly similar to that seen on the aforementioned part, meaning that it features eight vertex shaders and twelve pixel pipelines, each of which contains a single texturing unit and three pixel shader units, giving it a total of thirty-six. Alongside this, the core features twelve ROPs, and its Ultra Threaded Despatch Processor can handle 384 threads in flight at any one time, compared to 512 on high-end R580-based boards.
ATI's reference core clock speed for the Radeon X1950 PRO is 575MHz, with 256MB of GDDR3 memory clocked at 690MHz. The inclusion of video in capabilities is optional for this particular SKU, but HDCP support is featured and mandatory for AIB partners.
You can see the entire feature set of the Radeon X1950 PRO below.
- Ultra Threaded Shader Engine
- Support of DirectX9 Programmable Vertex and Pixel Shaders
- VS3.0 Vertex Shader functionality
- 1280 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
- HDR Blending on FP16, Int10 and Custom Formats
- 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