The RSX 'Reality Synthesizer' is a proprietary graphics processing unit

Graphics processing unit

A graphics processing unit or GPU is a specialized circuit designed to rapidly manipulate and alter memory in such a way so as to accelerate the building of images in a frame buffer intended for output to a display...

 (GPU) codeveloped by Nvidia

NVIDIA

Nvidia is an American global technology company based in Santa Clara, California. Nvidia is best known for its graphics processors . Nvidia and chief rival AMD Graphics Techonologies have dominated the high performance GPU market, pushing other manufacturers to smaller, niche roles...

 and Sony

Sony

, commonly referred to as Sony, is a Japanese multinational conglomerate corporation headquartered in Minato, Tokyo, Japan and the world's fifth largest media conglomerate measured by revenues....

 for the PlayStation 3

PlayStation 3

The is the third home video game console produced by Sony Computer Entertainment and the successor to the PlayStation 2 as part of the PlayStation series. The PlayStation 3 competes with Microsoft's Xbox 360 and Nintendo's Wii as part of the seventh generation of video game consoles...

 game console.

Unless otherwise noted, the following specifications are based on a press release by Sony at the E3 2005 conference, slides from the same conference, and slides from a Sony presentation at the 2006 Game Developer's Conference

Game Developers Conference

The Game Developers Conference is the largest annual gathering of professional video game developers, focusing on learning, inspiration, and networking...

.

Specifications

• 550 MHz on 90 nm process (shrunk to 65 nm in 2008 and to 40 nm
  Nanometre
  A nanometre is a unit of length in the metric system, equal to one billionth of a metre. The name combines the SI prefix nano- with the parent unit name metre .The nanometre is often used to express dimensions on the atomic scale: the diameter...
  
   in 2010)
• Based on NV47 Chip previously based on the 7800 but has been upgraded (Nvidia GeForce 7800 Architecture)
  • 300+ million transistors
  • Multi-way programmable parallel floating-point
    Floating point
    In computing, floating point describes a method of representing real numbers in a way that can support a wide range of values. Numbers are, in general, represented approximately to a fixed number of significant digits and scaled using an exponent. The base for the scaling is normally 2, 10 or 16...
    
     shader
    Shader
    In the field of computer graphics, a shader is a computer program that is used primarily to calculate rendering effects on graphics hardware with a high degree of flexibility...
    
     pipelines
    • Independent pixel/vertex shader architecture
    • 24 parallel pixel-shader ALU pipes clocked @ 550 MHz
      • 5 ALU operations per pipeline, per cycle (2 vector₄ , 2 scalar/dual/co-issue and fog ALU, 1 Texture ALU)
      • 27 floating-point operations
        FLOPS
        In computing, FLOPS is a measure of a computer's performance, especially in fields of scientific calculations that make heavy use of floating-point calculations, similar to the older, simpler, instructions per second...
        
         per pipeline, per cycle
    • 8 parallel vertex pipelines @550 MHz
      • 2 ALU operations per pipeline, per cycle (1 vector₄ and 1 scalar, dual issue)
      • 10 FLOPS per pipeline, per cycle
    • Floating Point Operations: 400.4 Gigaflops (24 * 27 Flops + 8 * 10 Flops * 550)
      • 74.8 billion shader operations per second (24 Pixel Shader Pipelines*5 ALUs*550 MHz) + (8 Vertex Shader Pipelines*2 ALUs*550 MHz)
  • 24 texture filtering
    Texture filtering
    In computer graphics, texture filtering or texture smoothing is the method used to determine the texture color for a texture mapped pixel, using the colors of nearby texels . Mathematically, texture filtering is a type of anti-aliasing, but it filters out high frequencies from the texture fill...
    
     units (TF) and 8 vertex texture addressing units (TA)
    • 24 filtered
      Texture filtering
      In computer graphics, texture filtering or texture smoothing is the method used to determine the texture color for a texture mapped pixel, using the colors of nearby texels . Mathematically, texture filtering is a type of anti-aliasing, but it filters out high frequencies from the texture fill...
      
       samples per clock
      • Maximum texel
        Texel (graphics)
        A texel, or texture element is the fundamental unit of texture space, used in computer graphics. Textures are represented by arrays of texels, just as pictures are represented by arrays of pixels....
        
         fillrate: 13.2 GigaTexels per second (24 textures * 550 MHz)
    • 32 unfiltered texture samples per clock, ( 8 TA x 4 texture samples )
  • 8 Render Output unit
    Render Output unit
    The Render Output Unit, often abbreviated as "ROP", and sometimes called Raster Operations Pipeline, is one of the final steps in the rendering process of modern 3D accelerator boards. The pixel pipelines take pixel and texel information and process it, via specific matrix and vector operations,...
    
    s / pixel rendering pipelines
    • Peak pixel fillrate (theoretical): 4.4 Gigapixel per second
    • Maximum Z
      Z-buffering
      In computer graphics, z-buffering is the management of image depth coordinates in three-dimensional graphics, usually done in hardware, sometimes in software. It is one solution to the visibility problem, which is the problem of deciding which elements of a rendered scene are visible, and which...
      
       sample rate: 8.8 GigaSamples per second (2 Z-samples * 8 ROPs * 550 MHz)
  • Maximum Dot product
    Dot product
    In mathematics, the dot product or scalar product is an algebraic operation that takes two equal-length sequences of numbers and returns a single number obtained by multiplying corresponding entries and then summing those products...
    
     operations: 56 billion per second (combined with Cell CPU)
  • 128-bit pixel precision offers rendering of scenes with High dynamic range rendering
    High dynamic range rendering
    In 3D computer graphics, high dynamic range rendering , also known as high dynamic range lighting, is the rendering of computer graphics scenes by using lighting calculations done in a larger dynamic range. This allows preservation of details that may be lost due to limiting contrast ratios...
    
     (HDR)
  • 256 MB
    Megabyte
    The megabyte is a multiple of the unit byte for digital information storage or transmission with two different values depending on context: bytes generally for computer memory; and one million bytes generally for computer storage. The IEEE Standards Board has decided that "Mega will mean 1 000...
    
     GDDR3 RAM at 700 MHz
    • 128-bit memory bus width
    • 22.4 GB
      Gigabyte
      The gigabyte is a multiple of the unit byte for digital information storage. The prefix giga means 109 in the International System of Units , therefore 1 gigabyte is...
      
      /s read and write bandwidth
  • Cell
    Cell microprocessor
    Cell is a microprocessor architecture jointly developed by Sony, Sony Computer Entertainment, Toshiba, and IBM, an alliance known as "STI". The architectural design and first implementation were carried out at the STI Design Center in Austin, Texas over a four-year period beginning March 2001 on a...
    
     FlexIO bus interface
    • 20 GB
      Gigabyte
      The gigabyte is a multiple of the unit byte for digital information storage. The prefix giga means 109 in the International System of Units , therefore 1 gigabyte is...
      
      /s read to the Cell and XDR
      XDR DRAM
      XDR DRAM or extreme data rate dynamic random access memory is a high-performance RAM interface and successor to the Rambus RDRAM it is based on, competing with the rival DDR2 SDRAM and GDDR4 technology. XDR was designed to be effective in small, high-bandwidth consumer systems, high-performance...
      
       memory
    • 15 GB/s write to the Cell and XDR memory
  • Support for PSGL
    PSGL
    PSGL is a 3D computer graphics API based on OpenGL ES and Nvidia's CG for Sony's PlayStation 3. A previous version of PSGL was available for the PlayStation 2 but was largely unused.-Features:*Programmable shading with Cg...
    
     (OpenGL ES 1.1 + Nvidia Cg)
  • Support for S3TC
    S3 Texture Compression
    S3 Texture Compression is a group of related lossy texture compression algorithms originally developed by Iourcha et al. of S3 Graphics, Ltd. for use in their Savage 3D computer graphics accelerator...
    
     texture compression

Press Releases

Sony staff were quoted in PlayStation Magazine saying that the "RSX shares a lot of inner workings with NVIDIA 7800 which is based on G70 architecture." Since the G70 is capable of carrying out 136 shader operations per clock cycle, the RSX was expected to feature the same number of parallel pixel and vertex shader pipelines as the G70, which contains 24 pixel and 8 vertex pipelines.

NVIDIA CEO Jen-Hsun Huang

Jen-Hsun Huang

Jen-Hsun "Jensen" Huang is a Taiwanese American entrepreneur and businessman. A native of Taiwan, he grew up in Oregon, graduating from Oregon State University before moving to California where he graduated from Stanford University. He co-founded the graphics-processor company Nvidia and serves...

 stated during Sony's pre-show press conference at E3 2005 that the RSX is twice as powerful as the GeForce 6800 Ultra.