Report an Error

NVIDIA Playstation 3 RSX 90nm

Graphics Processor
RSX-CXD2953
Pixel Shaders
24
Vertex Shaders
8
TMUs
24
ROPs
8
Memory Size
256 MB
Memory Type
GDDR3
Bus Width
128 bit
The Playstation 3 RSX 90nm was a gaming console graphics solution by NVIDIA, launched in November 2006. Built on the 90 nm process, and based on the RSX-CXD2953 graphics processor, the device does not support DirectX. The RSX-CXD2953 graphics processor is an average sized chip with a die area of 258 mm² and 300 million transistors. It features 24 pixel shaders and 8 vertex shaders, 24 texture mapping units and 8 ROPs. NVIDIA includes 256 MB GDDR3 memory, which are connected using a 128-bit memory interface. The GPU is operating at a frequency of 500 MHz, memory is running at 700 MHz.
Its power draw is rated at 80 W maximum.

Graphics Processor

GPU Name
RSX-CXD2953
Architecture
Curie
Foundry
Sony
Process Size
90 nm
Transistors
300 million
Die Size
258 mm²

Mobile Graphics

Release Date
Nov 11th, 2006
Generation
Console GPU
(Sony)
Production
End-of-life
Bus Interface
IGP

Clock Speeds

GPU Clock
500 MHz
Memory Clock
700 MHz
1400 MHz effective

Memory

Memory Size
256 MB
Memory Type
GDDR3
Memory Bus
128 bit
Bandwidth
22.40 GB/s

Render Config

Pixel Shaders
24
Vertex Shaders
8
TMUs
24
ROPs
8

Theoretical Performance

Pixel Rate
4.000 GPixel/s
Vertex Rate
1.000 GVertices/s
Texture Rate
12.00 GTexel/s

Board Design

Slot Width
IGP
TDP
80 W
Outputs
No outputs

Graphics Features

DirectX
N/A
OpenGL
ES 1.1
OpenCL
N/A
Vulkan
N/A
Pixel Shader
3.0
Vertex Shader
3.0

RSX-CXD2953 GPU Notes

Multi-way programmable parallel floating-point shader pipelines

Independent pixel/vertex shader architecture

24 parallel pixel-shader ALU pipes clocked @ 500 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 per pipeline, per cycle

8 parallel vertex pipelines @ 500 MHz
2 ALU operations per pipeline, per cycle
- 1 vector4
- 1 scalar, dual issue

10 floating-point operations per pipeline, per cycle

Floating Point Operations:
230 Gigaflops
(500MHz x 24 Shaders x 2 ops per clock per ALU)

68.0 billion shader operations/s
(24 Pixel Shader Pipelines x 5 ALUs x 500 MHz)+
(8 Vertex Shader Pipelines x 2 ALUs x 500 MHz)

24 texture filtering units (TF)
8 vertex texture addressing units (TA)
24 filtered samples per clock

Peak texel fillrate:
12.0 GigaTexels per second
(24 textures x 500 MHz)

32 unfiltered texture samples per clock
(8 TA x 4 texture samples)

8 Render Output units / pixel rendering pipelines

Peak pixel fillrate:
4.4 Gigapixel/s

Peak Z sample rate:
8.0 GigaSamples/s
(2 Z-samples x 8 ROPs x 500 MHz)

Peak Dot product operations:
56 billion/s (combined with Cell CPU)

128-bit pixel precision offers rendering of scenes with High dynamic range rendering (HDR)

Cell FlexIO bus interface
20 GB/s read to the Cell and XDR memory
15 GB/s write to the Cell and XDR memory

Support for PSGL (OpenGL ES 1.1 + Nvidia Cg)
Support for S3TC texture compression