Report an Error

ATI Xenos Falcon

Default
Xenos Falcon
Die Shot
Die Shot
ATI's Xenos Falcon GPU uses the TeraScale architecture and is made using a 80 nm production process at TSMC. With a die size of 156 mm² and a transistor count of 232 million it is a small chip. Xenos Falcon supports DirectX 9.0c (Feature Level 9_3). Modern GPU compute technologies are not available. It features 240 shading units, 16 texture mapping units and 8 ROPs.

Graphics Processor

Released
Oct 27th, 2007
GPU Name
Xenos Falcon
Architecture
TeraScale
Foundry
TSMC
Process Size
80 nm
Transistors
232 million
Density
1.5M / mm²
Die Size
156 mm²

Graphics Features

DirectX
9.0c (9_3)
OpenGL
N/A
OpenCL
N/A
Vulkan
N/A
Shader Model
3.0

Render Config

Shading Units
240
TMUs
16
ROPs
8
Compute Units
3
Max. TDP
175 W

All TeraScale GPUs

ATI GPU Architecture History

Graphics cards using the ATI Xenos Falcon GPU

Name Chip Memory Shaders TMUs ROPs GPU Clock Memory Clock
Crayola 6 512 MB 240 16 8 500 MHz 700 MHz

Xenos Falcon GPU Notes

48 floating-point vector processors for shader execution, divided in three dynamically scheduled SIMD groups of 16 processors each.

Unified shading architecture
(each pipeline is capable of running either pixel or vertex shaders)

10 FP ops per vector processor per cycle
(5 fused multiply-add)

Peak vertex count:
6.0 GVertices/s
((48 shader vector processors × 2 ops per cycle × 500 MHz) / 8 vector ops per vertex)
for simple transformed and lit polygons

Peak polygon count:
500 million triangles per second

Peak shader operations:
96.0 billion shader operations/s
(3 shader pipelines × 16 processors × 4 ALUs × 500 MHz)

Floating Point Operations:
240.0 GFLOPS
(3 shader pipelines × 16 processors × 500 MHz)

MEMEXPORT shader function

16 texture filtering units
16 texture addressing units
16 filtered samples per clock

Peak texel fillrate:
8.0 GTexel/s
(16 textures × 500 MHz)

16 unfiltered texture samples per clock
(16 texture addressing units)

8 Render Output units / pixel rendering pipelines

Peak pixel fillrate:
4.0 GPixel/s without MSAA
(8 ROPs × 500 MHz)

Peak Z sample rate:
8.0 GSamples/s
(2 Z samples × 8 ROPs × 500 MHz)

32.0 GSamples/s using 4X anti aliasing
(2 Z samples × 8 ROPs × 4X AA × 500 MHz)

Peak anti-aliasing sample rate:
16.0 GSamples/s
(4 AA samples × 8 ROPs × 500 MHz)

Peak Dot product operations:
24 billion per second

Support for a superset of
DirectX Xbox 360

10 MiB daughter embedded DRAM (at 256GB/s) framebuffer on

NEC designed eDRAM die includes additional logic
105 million transistors
(192 parallel pixel processors)
for color, alpha compositing, Z/stencil buffering, and anti-aliasing called “Intelligent Memory”, giving developers 4-sample anti-aliasing at very little performance cost.
Nov 18th, 2024 17:18 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts