Report an Error

NVIDIA Tesla V100 SXM2 32 GB

Graphics Processor
GV100
Cores
5120
TMUs
320
ROPs
128
Memory Size
32 GB
Memory Type
HBM2
Bus Width
4096 bit
The Tesla V100 SXM2 32 GB is a professional graphics card by NVIDIA, launched in March 2018. Built on the 12 nm process, and based on the GV100 graphics processor, the card supports DirectX 12.0. The GV100 graphics processor is a large chip with a die area of 815 mm² and 21,100 million transistors. It features 5120 shading units, 320 texture mapping units and 128 ROPs. Also included are 640 tensor cores which help improve the speed of machine learning applications. NVIDIA has placed 32,768 MB HBM2 memory on the card, which are connected using a 4096-bit memory interface. The GPU is operating at a frequency of 1290 MHz, which can be boosted up to 1530 MHz, memory is running at 876 MHz.
Being a dual-slot card, the NVIDIA Tesla V100 SXM2 32 GB does not require any additional power connector, its power draw is rated at 250 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Tesla V100 SXM2 32 GB is connected to the rest of the system using a PCI-Express 3.0 x16 interface.

Graphics Processor

GPU Name
GV100
Architecture
Volta
Foundry
TSMC
Process Size
12 nm
Transistors
21,100 million
Die Size
815 mm²

Graphics Card

Release Date
Mar 27th, 2018
Generation
Tesla
(Vxx)
Production
Active
Bus Interface
PCIe 3.0 x16

Relative Performance

1%
GeForce 210
1%
GeForce 9400 GT
1%
Radeon HD 4550
1%
Radeon HD 5450
2%
Radeon HD 6450
2%
GeForce GT 520
2%
GeForce GT 220
3%
GeForce GT 430
3%
Radeon HD 5570
3%
Radeon HD 4670
3%
GeForce GT 440
4%
GeForce GT 240
4%
GeForce 9600 GT
4%
Radeon HD 5670
5%
GeForce GT 640
5%
GeForce 9800 GT
5%
Radeon HD 6670
5%
Radeon HD 4830
5%
Radeon HD 4770
6%
Radeon HD 4850
6%
GeForce GTS 250
6%
GeForce GTS 450
6%
Radeon HD 5750
7%
Radeon HD 7750
7%
Radeon HD 5770
7%
GeForce GTX 260
7%
Radeon HD 4870
7%
Radeon Vega 8
8%
GeForce GTX 550 Ti
8%
GeForce GTX 650
8%
Radeon HD 5830
8%
Radeon HD 6790
9%
Radeon HD 4890
9%
GeForce GTX 460
9%
Radeon RX Vega 11
9%
GeForce GT 1030
9%
GeForce GTX 275
9%
Radeon HD 7770 GHz Edition
9%
GeForce GTX 280
9%
GeForce GTX 465
10%
Radeon HD 6850
10%
GeForce GTX 285
11%
Radeon HD 5850
11%
GeForce GTX 650 Ti
11%
Radeon HD 7790
11%
Radeon RX 550
11%
GeForce GTX 470
12%
Radeon HD 6870
13%
Radeon HD 5870
13%
GeForce GTX 560 Ti
13%
Radeon HD 4870 X2
13%
GeForce GTX 750 Ti
13%
Radeon HD 6950
14%
GeForce GTX 295
14%
GeForce GTX 650 Ti Boost
14%
Radeon HD 7850
14%
GeForce GTX 480
15%
Radeon HD 6970
15%
Radeon R7 265
16%
Radeon RX 460
16%
Radeon R7 370
16%
GeForce GTX 660
16%
GeForce GTX 570
16%
Radeon RX 560
17%
GeForce GTX 950
17%
Radeon HD 7870 GHz Edition
18%
Radeon R9 270X
18%
GeForce GTX 660 Ti
18%
GeForce GTX 580
18%
GeForce GTX 1050
18%
Radeon HD 7950
18%
Radeon HD 5970
19%
GeForce GTX 760
20%
GeForce GTX 670
21%
GeForce GTX 960
21%
Radeon R9 380
21%
Radeon R9 285
22%
Radeon HD 7970
22%
GeForce GTX 680
22%
GeForce GTX 1050 Ti
23%
GeForce GTX 770
24%
Radeon HD 6990
24%
Radeon R9 280X
24%
GeForce GTX 590
24%
Radeon HD 7970 GHz Edition
27%
GeForce GTX 780
28%
GeForce GTX 1650
30%
Radeon RX 470
30%
Radeon R9 290
32%
Radeon RX 570
32%
Radeon R9 390
32%
Radeon R9 290X
33%
GeForce GTX 970
33%
GeForce GTX TITAN
34%
GeForce GTX 780 Ti
34%
Radeon R9 390X
34%
Radeon HD 7990
35%
Radeon RX 480
35%
GeForce GTX 690
37%
Radeon RX 580
38%
GeForce GTX 980
38%
Radeon R9 FURY
38%
GeForce GTX 1060 6 GB
40%
Radeon RX 590
42%
Radeon R9 295X2
42%
GeForce GTX 1660
43%
Radeon R9 FURY X
43%
GeForce GTX 980 Ti
44%
GeForce GTX TITAN X
48%
GeForce GTX 1660 Ti
48%
GeForce GTX 1070
51%
Radeon RX Vega 56
54%
GeForce GTX 1070 Ti
56%
Radeon RX Vega 64
57%
GeForce GTX 1080
57%
GeForce RTX 2060
59%
Radeon RX 5700
64%
GeForce RTX 2060 SUPER
66%
GeForce RTX 2070
68%
Radeon RX 5700 XT
68%
Radeon VII
70%
TITAN X Pascal
72%
GeForce GTX 1080 Ti
73%
GeForce RTX 2070 SUPER
78%
GeForce RTX 2080
82%
GeForce RTX 2080 SUPER
91%
GeForce RTX 2080 Ti
100%
Tesla V100 SXM2 32 GB
Based on TPU review data: "Performance Summary" at 1920x1080
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

Base Clock
1290 MHz
Boost Clock
1530 MHz
Memory Clock
876 MHz
1752 MHz effective

Memory

Memory Size
32 GB
Memory Type
HBM2
Memory Bus
4096 bit
Bandwidth
897.0 GB/s

Render Config

Shading Units
5120
TMUs
320
ROPs
128
SM Count
80
Tensor Cores
640
L1 Cache
128 KB (per SM)
L2 Cache
6 MB

Theoretical Performance

Pixel Rate
195.8 GPixel/s
Texture Rate
489.6 GTexel/s
FP16 (half) performance
31.33 TFLOPS (2:1)
FP32 (float) performance
15.67 TFLOPS
FP64 (double) performance
7.834 TFLOPS (1:2)

Board Design

Slot Width
Dual-slot
TDP
250 W
Suggested PSU
600 W
Outputs
No outputs
Power Connectors
None

Graphics Features

DirectX
12.0 (12_1)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1.122
CUDA
7.0
Shader Model
6.4

Card Notes

Boost Clock:
Deep Learning: 125.338TFLOPs