Report an Error

ATI Xbox 360 GPU

Graphics Processor
Xenos
Cores
240
TMUs
16
ROPs
8
Memory Size
512 MB
Memory Type
GDDR3
Bus Width
128 bit
The Xbox 360 GPU was a graphics card by ATI, launched in November 2005. Built on the 90 nm process, and based on the Xenos graphics processor, in its Crayola 6 variant, the card supports DirectX 9.0c. The Xenos graphics processor is an average sized chip with a die area of 182 mm² and 232 million transistors. It features 240 shading units, 16 texture mapping units and 8 ROPs. ATI has placed 512 MB GDDR3 memory on the card, 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.
Being a igp card, its power draw is not exactly known. This device has no display connectivity, as it is not designed to have monitors connected to it.

Graphics Processor

GPU Name
Xenos
GPU Variant
Crayola 6
Architecture
TeraScale
Foundry
TSMC
Process Size
90 nm
Transistors
232 million
Die Size
182 mm²

Graphics Card

Release Date
Nov 22nd, 2005
Generation
Console GPU
(Microsoft)
Production
End-of-life
Bus Interface
IGP

Relative Performance

45%
GeForce 210
58%
GeForce 9400 GT
71%
Radeon HD 4550
91%
Radeon HD 5450
100%
Xbox 360 GPU
107%
Radeon HD 6450
112%
GeForce GT 520
139%
GeForce GT 220
182%
GeForce GT 430
184%
Radeon HD 5570
200%
Radeon HD 4670
211%
GeForce GT 440
215%
GeForce GT 240
247%
GeForce 9600 GT
263%
Radeon HD 5670
282%
GeForce GT 640
291%
GeForce 9800 GT
303%
Radeon HD 6670
313%
Radeon HD 4830
334%
Radeon HD 4770
352%
Radeon HD 4850
360%
GeForce GTS 250
370%
GeForce GTS 450
383%
Radeon HD 5750
438%
Radeon HD 7750
441%
Radeon HD 5770
449%
GeForce GTX 260
455%
Radeon HD 4870
456%
Radeon Vega 8
460%
GeForce GTX 550 Ti
464%
GeForce GTX 650
491%
Radeon HD 5830
517%
Radeon HD 6790
525%
Radeon HD 4890
545%
GeForce GTX 460
549%
Radeon RX Vega 11
554%
GeForce GT 1030
559%
GeForce GTX 275
561%
Radeon HD 7770 GHz Edition
562%
GeForce GTX 280
573%
GeForce GTX 465
601%
Radeon HD 6850
612%
GeForce GTX 285
657%
Radeon HD 5850
669%
GeForce GTX 650 Ti
669%
Radeon HD 7790
697%
Radeon RX 550
699%
GeForce GTX 470
724%
Radeon HD 6870
773%
Radeon HD 5870
797%
GeForce GTX 560 Ti
801%
Radeon HD 4870 X2
816%
GeForce GTX 750 Ti
820%
Radeon HD 6950
849%
GeForce GTX 295
859%
GeForce GTX 650 Ti Boost
865%
Radeon HD 7850
880%
GeForce GTX 480
921%
Radeon HD 6970
939%
Radeon R7 265
954%
Radeon R7 370
954%
Radeon RX 560
957%
GeForce GTX 660
960%
GeForce GTX 570
1037%
GeForce GTX 950
1046%
Radeon HD 7870 GHz Edition
1071%
Radeon R9 270X
1084%
GeForce GTX 660 Ti
1089%
GeForce GTX 580
1098%
GeForce GTX 1050
1100%
Radeon HD 7950
1120%
Radeon RX 460
1122%
Radeon HD 5970
1153%
GeForce GTX 760
1242%
GeForce GTX 670
1274%
GeForce GTX 960
1306%
Radeon R9 380
1314%
Radeon R9 285
1327%
Radeon HD 7970
1341%
GeForce GTX 680
1372%
GeForce GTX 1050 Ti
1408%
GeForce GTX 770
1441%
Radeon HD 6990
1475%
Radeon R9 280X
1496%
GeForce GTX 590
1497%
Radeon HD 7970 GHz Edition
1659%
GeForce GTX 780
1825%
Radeon RX 470
1850%
Radeon R9 290
1974%
Radeon R9 390
1985%
Radeon R9 290X
2011%
GeForce GTX 970
2038%
GeForce GTX TITAN
2055%
Radeon RX 570
2065%
GeForce GTX 780 Ti
2095%
Radeon R9 390X
2104%
Radeon HD 7990
2114%
Radeon RX 480
2132%
GeForce GTX 690
2246%
Radeon RX 580
2293%
GeForce GTX 980
2322%
GeForce GTX 1060 6 GB
2322%
Radeon R9 FURY
2334%
Radeon RX 590
2554%
Radeon R9 295X2
2599%
Radeon R9 FURY X
2643%
GeForce GTX 980 Ti
2841%
GeForce GTX TITAN X
2980%
GeForce GTX 1660 Ti
2995%
GeForce GTX 1070
3127%
Radeon RX Vega 56
3391%
GeForce GTX 1070 Ti
3479%
Radeon RX Vega 64
3479%
GeForce RTX 2060
3567%
GeForce GTX 1080
4096%
Radeon VII
4096%
GeForce RTX 2070
4294%
TITAN X Pascal
4404%
GeForce GTX 1080 Ti
4757%
GeForce RTX 2080
5505%
GeForce RTX 2080 Ti
Based on TPU review data: "Performance Summary" at 1920x1080
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

GPU Clock
500 MHz
Memory Clock
700 MHz
1400 MHz effective

Memory

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

Render Config

Shading Units
240
TMUs
16
ROPs
8
Compute Units
3

Theoretical Performance

Pixel Rate
4.000 GPixel/s
Texture Rate
8.000 GTexel/s
FP32 (float) performance
240.0 GFLOPS

Board Design

Slot Width
IGP
TDP
unknown
Outputs
No outputs

Graphics Features

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

Xenos 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)

Maximum vertex count:
6 billion vertices per second
((48 shader vector processors × 2 ops per cycle × 500 MHz) / 8 vector ops per vertex)
for simple transformed and lit polygons

Maximum polygon count:
500 million triangles per second

Maximum shader operations:
96 billion shader operations per second
(3 shader pipelines × 16 processors × 4 ALUs × 500 MHz)

240 GFLOPS
MEMEXPORT shader function

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

Maximum texel fillrate:
8 gigatexels per second
(16 textures × 500 MHz)

16 unfiltered texture samples per clock

Maximum 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
90 nm, 80 nm (since 2008)
65nm (since 2010)

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.

8 Render Output units

Maximum pixel fillrate:
16 gigasamples per second fillrate using 4X multisample anti aliasing (MSAA)

32 gigasamples using
Z-only operation;
4 gigapixels per second without MSAA
(8 ROPs × 500 MHz)

Maximum Z sample rate:
8 gigasamples per second
(2 Z samples × 8 ROPs × 500 MHz)

32 gigasamples per second using 4X anti aliasing
(2 Z samples × 8 ROPs × 4X AA × 500 MHz)

Maximum anti-aliasing sample rate:
16 gigasamples per second
(4 AA samples × 8 ROPs × 500 MHz)