Report an Error

NVIDIA Tesla V100 PCIe

GV100
Graphics Processor
5120
Cores
320
TMUs
128
ROPs
16384 MB
Memory Size
HBM2
Memory Type
4096 bit
Bus Width
NVIDIA Tesla V100 PCIe Image NVIDIA GV100 Image
The Tesla V100 PCIe is a professional graphics card by NVIDIA, launched in June 2017. 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 16,384 MB HBM2 memory on the card, which are connected using a 4096-bit memory interface. The GPU is operating at a frequency of 1246 MHz, which can be boosted up to 1380 MHz, memory is running at 879 MHz.
Being a dual-slot card, the NVIDIA Tesla V100 PCIe draws power from 2x 8-pin power connectors, with power draw rated at 250 W maximum. Tesla V100 PCIe is connected to the rest of the system using a PCIe 3.0 x16 interface.

Graphics Processor

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

Graphics Card

Released: Jun 21st, 2017
Production Status: Active
Bus Interface: PCIe 3.0 x16

Relative Performance

1%
1%
1%
2%
2%
2%
3%
3%
3%
4%
4%
4%
4%
5%
5%
5%
5%
6%
6%
6%
7%
7%
7%
8%
8%
8%
8%
8%
8%
8%
9%
9%
9%
10%
10%
10%
10%
10%
10%
10%
11%
11%
12%
12%
12%
13%
13%
13%
14%
14%
14%
15%
15%
15%
16%
16%
16%
17%
17%
17%
17%
17%
17%
19%
19%
19%
20%
20%
20%
20%
20%
20%
21%
22%
23%
24%
24%
24%
24%
25%
25%
26%
27%
27%
27%
30%
33%
33%
36%
36%
36%
37%
37%
37%
38%
38%
38%
39%
41%
42%
42%
42%
46%
48%
50%
51%
56%
58%
64%
64%
66%
78%
80%
100%
Tesla V100 PCIe
Based on TPU review data: "Performance Summary" at 1920x1080
Tesla V100 PCIe performance estimated based on architecture, shader count and clocks.

Clock Speeds

GPU Clock: 1246 MHz
Boost Clock: 1380 MHz
Memory Clock: 879 MHz
1758 MHz effective

Memory

Memory Size: 16384 MB
Memory Type: HBM2
Memory Bus: 4096 bit
Bandwidth: 900.1 GB/s

Render Config

Shading Units: 5120
TMUs: 320
ROPs: 128
SM Count: 80
Tensor Cores: 640
Pixel Rate: 176.6 GPixel/s
Texture Rate: 441.6 GTexel/s
Floating-point performance: 14,131 GFLOPS

Board Design

Slot Width: Dual-slot
TDP: 250 W
Power Connectors: 2x 8-pin
Board Number: PG500 SKU 200

Graphics Features

DirectX: 12.0
OpenGL: 4.6
OpenCL: 2.0
CUDA: 7.0
Shader Model: 5.0