Report an Error

NVIDIA Jetson AGX Xavier

Graphics Processor
GV10B
Cores
512
TMUs
32
ROPs
16
Memory Size
System Shared
Memory Type
System Shared
Bus Width
System Shared
The Jetson AGX Xavier is a mobile integrated graphics solution by NVIDIA, launched in October 2018. Built on the 12 nm process, and based on the GV10B graphics processor, the device supports DirectX 12.0. It features 512 shading units, 32 texture mapping units and 16 ROPs. Also included are 8 tensor cores which help improve the speed of machine learning applications. The GPU is operating at a frequency of 854 MHz, which can be boosted up to 1400 MHz.
Its power draw is rated at 30 W maximum.

Graphics Processor

GPU Name
GV10B
Architecture
Volta
Foundry
TSMC
Process Size
12 nm
Transistors
9,000 million
Die Size
350 mm²

Graphics Card

Release Date
Oct 2018
Generation
Tegra
Production
Active
Bus Interface
IGP

Relative Performance

6%
GeForce 210
8%
GeForce 9400 GT
10%
Radeon HD 4550
13%
Radeon HD 5450
15%
Radeon HD 6450
16%
GeForce GT 520
20%
GeForce GT 220
26%
GeForce GT 430
26%
Radeon HD 5570
28%
Radeon HD 4670
30%
GeForce GT 440
31%
GeForce GT 240
35%
GeForce 9600 GT
37%
Radeon HD 5670
40%
GeForce GT 640
41%
GeForce 9800 GT
43%
Radeon HD 6670
44%
Radeon HD 4830
47%
Radeon HD 4770
50%
Radeon HD 4850
51%
GeForce GTS 250
53%
GeForce GTS 450
54%
Radeon HD 5750
62%
Radeon HD 7750
63%
Radeon HD 5770
64%
GeForce GTX 260
65%
Radeon HD 4870
65%
Radeon Vega 8
65%
GeForce GTX 550 Ti
66%
GeForce GTX 650
70%
Radeon HD 5830
73%
Radeon HD 6790
75%
Radeon HD 4890
77%
GeForce GTX 460
78%
Radeon RX Vega 11
79%
GeForce GT 1030
79%
GeForce GTX 275
80%
Radeon HD 7770 GHz Edition
80%
GeForce GTX 280
81%
GeForce GTX 465
85%
Radeon HD 6850
87%
GeForce GTX 285
93%
Radeon HD 5850
95%
GeForce GTX 650 Ti
95%
Radeon HD 7790
99%
Radeon RX 550
99%
GeForce GTX 470
100%
Jetson AGX Xavier
103%
Radeon HD 6870
110%
Radeon HD 5870
113%
GeForce GTX 560 Ti
114%
Radeon HD 4870 X2
116%
GeForce GTX 750 Ti
116%
Radeon HD 6950
120%
GeForce GTX 295
122%
GeForce GTX 650 Ti Boost
123%
Radeon HD 7850
125%
GeForce GTX 480
131%
Radeon HD 6970
133%
Radeon R7 265
135%
Radeon R7 370
135%
Radeon RX 560
136%
GeForce GTX 660
136%
GeForce GTX 570
147%
GeForce GTX 950
148%
Radeon HD 7870 GHz Edition
152%
Radeon R9 270X
154%
GeForce GTX 660 Ti
155%
GeForce GTX 580
156%
GeForce GTX 1050
156%
Radeon HD 7950
159%
Radeon RX 460
159%
Radeon HD 5970
164%
GeForce GTX 760
176%
GeForce GTX 670
181%
GeForce GTX 960
185%
Radeon R9 380
186%
Radeon R9 285
188%
Radeon HD 7970
190%
GeForce GTX 680
195%
GeForce GTX 1050 Ti
200%
GeForce GTX 770
204%
Radeon HD 6990
209%
Radeon R9 280X
212%
GeForce GTX 590
212%
Radeon HD 7970 GHz Edition
235%
GeForce GTX 780
259%
Radeon RX 470
262%
Radeon R9 290
280%
Radeon R9 390
282%
Radeon R9 290X
285%
GeForce GTX 970
289%
GeForce GTX TITAN
292%
Radeon RX 570
293%
GeForce GTX 780 Ti
297%
Radeon R9 390X
298%
Radeon HD 7990
300%
Radeon RX 480
302%
GeForce GTX 690
319%
Radeon RX 580
325%
GeForce GTX 980
329%
GeForce GTX 1060 6 GB
329%
Radeon R9 FURY
331%
Radeon RX 590
362%
Radeon R9 295X2
369%
Radeon R9 FURY X
375%
GeForce GTX 980 Ti
403%
GeForce GTX TITAN X
425%
GeForce GTX 1070
444%
Radeon RX Vega 56
481%
GeForce GTX 1070 Ti
494%
GeForce RTX 2060
494%
Radeon RX Vega 64
506%
GeForce GTX 1080
581%
GeForce RTX 2070
581%
Radeon VII
609%
TITAN X Pascal
625%
GeForce GTX 1080 Ti
675%
GeForce RTX 2080
781%
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
854 MHz
Boost Clock
1400 MHz
Memory Clock
System Shared

Memory

Memory Size
System Shared
Memory Type
System Shared
Memory Bus
System Shared
Bandwidth
System Dependent

Render Config

Shading Units
512
TMUs
32
ROPs
16
SM Count
4
Tensor Cores
8

Theoretical Performance

Pixel Rate
22.40 GPixel/s
Texture Rate
44.80 GTexel/s
FP16 (half) performance
2,867 GFLOPS (2:1)
FP32 (float) performance
1,434 GFLOPS
FP64 (double) performance
716.8 GFLOPS (1:2)

Board Design

Slot Width
IGP
TDP
30 W
Outputs
No outputs

Graphics Features

DirectX
12.0 (12_1)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1.96
CUDA
7.2
Shader Model
6.3