Report an Error

AMD Xbox One GPU

Graphics Processor
Durango
Cores
768
TMUs
48
ROPs
16
Memory Size
8 GB
Memory Type
DDR3
Bus Width
256 bit
GPU Chip
GPU
Back
Back
The Xbox One GPU was a high-end gaming console graphics solution by AMD, launched on November 22nd, 2013. Built on the 28 nm process, and based on the Durango graphics processor, in its X871363-001 variant, the device supports DirectX 11.2. The Durango graphics processor is a large chip with a die area of 363 mm² and 5,000 million transistors. It features 768 shading units, 48 texture mapping units, and 16 ROPs. AMD includes 8 GB DDR3 memory, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 853 MHz, memory is running at 1066 MHz.
Its power draw is rated at 95 W maximum. The console's dimensions are 333 mm x 274 mm x 79 mm, and it features a igp cooling solution. Its price at launch was 499 US Dollars.

Graphics Processor

GPU Name
Durango
GPU Variant
X871363-001
Architecture
GCN 1.0
Foundry
TSMC
Process Size
28 nm
Transistors
5,000 million
Die Size
363 mm²

Graphics Card

Release Date
Nov 22nd, 2013
Generation
Console GPU
(Microsoft)
Production
End-of-life
Launch Price
499 USD

Clock Speeds

GPU Clock
853 MHz
Memory Clock
1066 MHz
2.1 Gbps effective

Memory

Memory Size
8 GB
Memory Type
DDR3
Memory Bus
256 bit
Bandwidth
68.22 GB/s

Render Config

Shading Units
768
TMUs
48
ROPs
16
Compute Units
12

Theoretical Performance

Pixel Rate
13.65 GPixel/s
Texture Rate
40.94 GTexel/s
FP32 (float) performance
1,310 GFLOPS

Board Design

Length
333 mm
13.1 inches
Width
274 mm
10.8 inches
Height
79 mm
3.1 inches
Weight
3.5 kg (7.8 lbs)
TDP
95 W
Outputs
No outputs

Graphics Features

DirectX
11.2 (11_0)
OpenGL
N/A
OpenCL
1.2
Vulkan
1.1
Shader Model
5.1

Durango GPU Notes

Architecture Codename: Sea Islands
CLRX Version: GCN 1.0

Instruction issue rate:
12 SCs * 4 SIMDs * 16 threads/clock = 768 ops/clock

FLOPs:
768 ops/clock * (1 mul + 1 add) * 800 MHz = 1.2 TFLOPS

Interpolation:
(768 ops/clock / 2 ops) * 800 MHz = 307.2 Gfloat/sec

Triangle rate:
2 tri/clock * 800 MHz = 1.6 Gtri/sec

Vertex rate:
2 vert/clock * 800 MHz = 1.6 Gvert/sec

Vertex/buffer fetch rate: (4 bytes)
4 elements/clock * 12 SCs * 800 MHz = 38.4 Gelement/sec

Vertex/Buffer data rate from cache:
38.4 Gelements/sec * 4 bytes = 153.6 GB/sec

Peak throughput from main RAM:
68.2 GB/sec

Peak throughput from ESRAM:
128 bytes/clock * 800 MHz = 102.4 GB/sec

ESRAM size:
32 MB

GSM size:
64 KB

LSM size:
12 SCs * 64 KB = 768 KB

L2 cache size:
4 x 128 KB = 512 KB (shared)

Bilinear fetch rate: (4 bytes)
4 fetches/clock * 12 SCs * 800 MHz = 38.4 Gtexels/sec

Bilinear data rate from cache:
38.4 Gtexels/sec * 4 bytes = 153.6 GB/sec

L1 cache size:
16 KB/SC * 12 SCs = 192 KB (nonshared)

Pixel clear rate:
1 8×8 tile/clock * 4 DBs * 800 MHz = 204.8 Gpixel/sec

Pixel hierarchical Z Rate:
1 8×8 tile/clock * 4 DBs * 800 MHz = 204.8 Gpixel/sec

Sample Z rate:
16 /clock * 4 DBs * 800 MHz = 51.2 Gsample/sec

Pixel rate:
4 /clock * 4 DBs * 800 MHz = 12.8 Gpixel/sec