ATI Radeon X1900 Manual Leaked
If you can't wait next week's official release, download the manual of ATI's X1900 here.
The http://www.dailytech.com website has provided the manual of ATI's next graphics cards, the Radeon X1900 series.
ATI will launch two versions of the Radeon X1900; the Radeon X1900XT and the Radeon X1900XTX. The X1900XTX is the same card as the X1900XT, but with slightly higher clock speeds. ATI also plans to release the Radeon X1900 CF (CrossFire). This card has the same core clocks as the X1900XT, but replaces some of the outputs with a VHDCI connector for CrossFire support.
According to the website, the XT and XTX are clocked at 625MHz and 650MHz, respectively, with their DDR memory buffers set to run at 1.45GHz and 1.55GHz, respectively. Both chips support up to 512MB of GDDR 3.
The 90nm R580 core has 48 pixel shaders.
Graphic Features
- Native PCI Express X16 bus support.
- 256MB or 512 MB GDDR3 on-board memory.
- Full support for Microsoft DirectX Shader Model 3.x.
- High performance Ultra-Threaded shader engine.
- Eight vertex shader processors.
- Forty-eight pixel shader processors.
- 512-bit internal ring-bus memory controller.
- 256-bit 8-channel memory interface.
- Native PCI Express x16 bus interface.
SmoothVision
- Full-scene anti-aliasing method that smooths uneven edges and improves blurred images.
- 2x/4x/6x Anti-aliasing modes with a loss-less compression up to a ratio of 6:1 at all resolutions.
- 2x/4x//8x/16x Anisotropic Filtering modes with up to 128-tap texture filtering.
HyperZ
- Ensures optimal hardware performance by discarding irrelevant object data that is not visible to the user.
- Conserves video memory bandwidth.
- Loss-less Z-buffer compression
- Z Cache optimized for real-time shadow rendering.
VideoShader
- Seamlessly integrates pixel shaders with video in real time.
- All format DTV/HDTV decoding.
- Adaptive Per-Pixel- De-interlacing and Frame Rate Conversion.
512-bit Ring Bus Memory Controller
- Programmable intelligent arbitration logic.
- New fully associative texture, color, and Z/stencil cache designs.
- Hierarchal Z-buffer with Early Z test.
- Lossless Z Compression (up to 48.1)
- Fast Z-Buffer Clear.
- Z Cache optimized for real-time shadow rendering.
- Optimized for performance at high display resolutions, including widescreen HDTV resolutions.
Ultra-Threaded Shader Engine
- Support for Microsoft DirectX 9.0 Shader Model 3.0
programmable vertex and pixel shaders in hardware.
- Full speed 128-bit floating point processing.
- Up to 512 simultaneous pixel threads.
- Dedicated branch execution units for high performance dynamic branching and flow control.
- Dedicated texture address units for improved efficiency.
- High resolution texture support (up to 4k x 4k).
- Up to 1,536 instructions per rendering pass.
- 3Dc+ texture compression
- High quality 4:1 compression for normal maps and luminance maps.
- Works with any single-channel or two-channel data format.
- Multiple Render Target (MRT) support.
- Render-to-vertex buffer support.
- Complete feature set also supported in OpenGL 2.0
High Dynamic Range (HDR) Rendering
- 64-bit floating point HDR supported throughout the pipeline
- Includes support for blending and multi-sample anti-aliasing.
- High precision 10:10:10:2 integer format support.
- Includes support for blending and multi-sample anti-aliasing.
- 2x/4x/6x Anti-Aliasing modes
- Sparse multi-sample algorithm with gamma correction, programmable sample patterns, and centroid sampling.
- New Adaptive Anti-Aliasing modes.
- Temporal Anti-Aliasing mode.
- Lossless Color Compression (up to 6:1) at all resolutions, including widescreen HDTV resolutions.
- 2x/4x/8x/16x Anisotropic Filtering modes
- Up to 128-tap texture filtering.
- Adaptive algorithm with performance and quality options.
ATI will launch two versions of the Radeon X1900; the Radeon X1900XT and the Radeon X1900XTX. The X1900XTX is the same card as the X1900XT, but with slightly higher clock speeds. ATI also plans to release the Radeon X1900 CF (CrossFire). This card has the same core clocks as the X1900XT, but replaces some of the outputs with a VHDCI connector for CrossFire support.
According to the website, the XT and XTX are clocked at 625MHz and 650MHz, respectively, with their DDR memory buffers set to run at 1.45GHz and 1.55GHz, respectively. Both chips support up to 512MB of GDDR 3.
The 90nm R580 core has 48 pixel shaders.
Graphic Features
- Native PCI Express X16 bus support.
- 256MB or 512 MB GDDR3 on-board memory.
- Full support for Microsoft DirectX Shader Model 3.x.
- High performance Ultra-Threaded shader engine.
- Eight vertex shader processors.
- Forty-eight pixel shader processors.
- 512-bit internal ring-bus memory controller.
- 256-bit 8-channel memory interface.
- Native PCI Express x16 bus interface.
SmoothVision
- Full-scene anti-aliasing method that smooths uneven edges and improves blurred images.
- 2x/4x/6x Anti-aliasing modes with a loss-less compression up to a ratio of 6:1 at all resolutions.
- 2x/4x//8x/16x Anisotropic Filtering modes with up to 128-tap texture filtering.
HyperZ
- Ensures optimal hardware performance by discarding irrelevant object data that is not visible to the user.
- Conserves video memory bandwidth.
- Loss-less Z-buffer compression
- Z Cache optimized for real-time shadow rendering.
VideoShader
- Seamlessly integrates pixel shaders with video in real time.
- All format DTV/HDTV decoding.
- Adaptive Per-Pixel- De-interlacing and Frame Rate Conversion.
512-bit Ring Bus Memory Controller
- Programmable intelligent arbitration logic.
- New fully associative texture, color, and Z/stencil cache designs.
- Hierarchal Z-buffer with Early Z test.
- Lossless Z Compression (up to 48.1)
- Fast Z-Buffer Clear.
- Z Cache optimized for real-time shadow rendering.
- Optimized for performance at high display resolutions, including widescreen HDTV resolutions.
Ultra-Threaded Shader Engine
- Support for Microsoft DirectX 9.0 Shader Model 3.0
programmable vertex and pixel shaders in hardware.
- Full speed 128-bit floating point processing.
- Up to 512 simultaneous pixel threads.
- Dedicated branch execution units for high performance dynamic branching and flow control.
- Dedicated texture address units for improved efficiency.
- High resolution texture support (up to 4k x 4k).
- Up to 1,536 instructions per rendering pass.
- 3Dc+ texture compression
- High quality 4:1 compression for normal maps and luminance maps.
- Works with any single-channel or two-channel data format.
- Multiple Render Target (MRT) support.
- Render-to-vertex buffer support.
- Complete feature set also supported in OpenGL 2.0
High Dynamic Range (HDR) Rendering
- 64-bit floating point HDR supported throughout the pipeline
- Includes support for blending and multi-sample anti-aliasing.
- High precision 10:10:10:2 integer format support.
- Includes support for blending and multi-sample anti-aliasing.
- 2x/4x/6x Anti-Aliasing modes
- Sparse multi-sample algorithm with gamma correction, programmable sample patterns, and centroid sampling.
- New Adaptive Anti-Aliasing modes.
- Temporal Anti-Aliasing mode.
- Lossless Color Compression (up to 6:1) at all resolutions, including widescreen HDTV resolutions.
- 2x/4x/8x/16x Anisotropic Filtering modes
- Up to 128-tap texture filtering.
- Adaptive algorithm with performance and quality options.