Report an Error

AMD Radeon Pro Vega 20

Graphics Processor
Vega 12
Cores
1280
TMUs
80
ROPs
32
Memory Size
4 GB
Memory Type
HBM2
Bus Width
1024 bit
The Radeon Pro Vega 20 is a professional graphics card by AMD, launched in November 2018. Built on the 14 nm process, and based on the Vega 12 graphics processor, in its Vega 12 XTA variant, the card supports DirectX 12.0. It features 1280 shading units, 80 texture mapping units and 32 ROPs. AMD has placed 4,096 MB HBM2 memory on the card, which are connected using a 1024-bit memory interface. The GPU is operating at a frequency of 318 MHz, which can be boosted up to 1190 MHz, memory is running at 1200 MHz.
Being a igp card, its power draw is rated at 100 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Radeon Pro Vega 20 is connected to the rest of the system using a PCI-Express 3.0 x16 interface.

Graphics Processor

GPU Name
Vega 12
GPU Variant
Vega 12 XTA
Architecture
GCN 5.0
Foundry
GlobalFoundries
Process Size
14 nm
Transistors
unknown
Die Size
unknown

Graphics Card

Release Date
Nov 14th, 2018
Generation
Radeon Pro
(Pro Vega)
Production
Active
Bus Interface
PCIe 3.0 x16

Relative Performance

5%
GeForce 210
6%
GeForce 9400 GT
7%
Radeon HD 4550
9%
Radeon HD 5450
11%
Radeon HD 6450
12%
GeForce GT 520
15%
GeForce GT 220
19%
GeForce GT 430
19%
Radeon HD 5570
21%
Radeon HD 4670
22%
GeForce GT 440
22%
GeForce GT 240
26%
GeForce 9600 GT
27%
Radeon HD 5670
29%
GeForce GT 640
30%
GeForce 9800 GT
32%
Radeon HD 6670
33%
Radeon HD 4830
35%
Radeon HD 4770
37%
Radeon HD 4850
38%
GeForce GTS 250
39%
GeForce GTS 450
40%
Radeon HD 5750
46%
Radeon HD 7750
46%
Radeon HD 5770
47%
GeForce GTX 260
47%
Radeon HD 4870
48%
Radeon Vega 8
48%
GeForce GTX 550 Ti
48%
GeForce GTX 650
51%
Radeon HD 5830
54%
Radeon HD 6790
55%
Radeon HD 4890
57%
GeForce GTX 460
57%
Radeon RX Vega 11
58%
GeForce GT 1030
58%
GeForce GTX 275
59%
Radeon HD 7770 GHz Edition
59%
GeForce GTX 280
60%
GeForce GTX 465
63%
Radeon HD 6850
64%
GeForce GTX 285
69%
Radeon HD 5850
70%
Radeon HD 7790
70%
GeForce GTX 650 Ti
73%
Radeon RX 550
73%
GeForce GTX 470
76%
Radeon HD 6870
81%
Radeon HD 5870
83%
GeForce GTX 560 Ti
84%
Radeon HD 4870 X2
85%
GeForce GTX 750 Ti
86%
Radeon HD 6950
89%
GeForce GTX 295
90%
GeForce GTX 650 Ti Boost
90%
Radeon HD 7850
92%
GeForce GTX 480
96%
Radeon HD 6970
98%
Radeon R7 265
100%
Radeon R7 370
100%
Radeon RX 560
100%
GeForce GTX 660
100%
Radeon Pro Vega 20
100%
GeForce GTX 570
108%
GeForce GTX 950
109%
Radeon HD 7870 GHz Edition
112%
Radeon R9 270X
113%
GeForce GTX 660 Ti
114%
GeForce GTX 580
115%
GeForce GTX 1050
115%
Radeon HD 7950
117%
Radeon RX 460
117%
Radeon HD 5970
120%
GeForce GTX 760
130%
GeForce GTX 670
133%
GeForce GTX 960
136%
Radeon R9 380
137%
Radeon R9 285
139%
Radeon HD 7970
140%
GeForce GTX 680
143%
GeForce GTX 1050 Ti
147%
GeForce GTX 770
150%
Radeon HD 6990
154%
Radeon R9 280X
156%
GeForce GTX 590
156%
Radeon HD 7970 GHz Edition
173%
GeForce GTX 780
191%
Radeon RX 470
193%
Radeon R9 290
206%
Radeon R9 390
207%
Radeon R9 290X
210%
GeForce GTX 970
213%
GeForce GTX TITAN
215%
Radeon RX 570
216%
GeForce GTX 780 Ti
219%
Radeon R9 390X
220%
Radeon HD 7990
221%
Radeon RX 480
223%
GeForce GTX 690
235%
Radeon RX 580
239%
GeForce GTX 980
242%
Radeon R9 FURY
242%
GeForce GTX 1060 6 GB
267%
Radeon R9 295X2
271%
Radeon R9 FURY X
276%
GeForce GTX 980 Ti
297%
GeForce GTX TITAN X
326%
GeForce GTX 1070
337%
Radeon RX Vega 56
363%
GeForce GTX 1070 Ti
363%
Radeon RX Vega 64
383%
GeForce GTX 1080
428%
GeForce RTX 2070
448%
TITAN X Pascal
460%
GeForce GTX 1080 Ti
501%
GeForce RTX 2080
570%
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
318 MHz
Boost Clock
1190 MHz
Memory Clock
1200 MHz
2400 MHz effective

Memory

Memory Size
4 GB
Memory Type
HBM2
Memory Bus
1024 bit
Bandwidth
307.2 GB/s

Render Config

Shading Units
1280
TMUs
80
ROPs
32
Compute Units
20

Theoretical Performance

Pixel Rate
38.08 GPixel/s
Texture Rate
95.20 GTexel/s
FP16 (half) performance
6,093 GFLOPS (2:1)
FP32 (float) performance
3,046 GFLOPS
FP64 (double) performance
190.4 GFLOPS (1:16)

Board Design

Slot Width
IGP
TDP
100 W
Outputs
No outputs

Graphics Features

DirectX
12.0 (12_1)
OpenGL
4.6
OpenCL
2.0
Vulkan
1.1.86
Shader Model
6.2

Vega 12 GPU Notes

CLRX Version: GCN 1.4
Graphics/Compute: GFX9 (gfx904)
Display Core Engine: 12.0
Unified Video Decoder: 7.0
Video Compression Engine: 4.0