Report an Error

NVIDIA TITAN V

GV100
Graphics Processor
5120
Cores
320
TMUs
96
ROPs
12288 MB
Memory Size
HBM2
Memory Type
3072 bit
Bus Width
NVIDIA TITAN V Photo NVIDIA GV100 Photo
The TITAN V is a high-end graphics card by NVIDIA, launched in December 2017. Built on the 12 nm process, and based on the GV100 graphics processor, in its GV100-400-A1 variant, 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 96 ROPs. Also included are 640 tensor cores which help improve the speed of machine learning applications. NVIDIA has placed 12,288 MB HBM2 memory on the card, which are connected using a 3072-bit memory interface. The GPU is operating at a frequency of 1200 MHz, which can be boosted up to 1455 MHz, memory is running at 850 MHz.
Being a dual-slot card, the NVIDIA TITAN V draws power from 1x 6-pin + 1x 8-pin power connectors, with power draw rated at 250 W maximum. Display outputs include: 1x HDMI, 3x DisplayPort. TITAN V is connected to the rest of the system using a PCI-Express 3.0 x16 interface. The card measures 267 mm in length, and features a dual-slot cooling solution. Its price at launch was 2,999 US Dollars.

Graphics Processor

GPU Name
GV100
GPU Variant
GV100-400-A1
Architecture
Volta
Process Size
12 nm
Transistors
21,100 million
Die Size
815 mm²

Graphics Card

Release Date
Dec 7th, 2017
Generation
GeForce 1000
Production Status
Active
Launch Price
2,999 USD
Bus Interface
PCIe 3.0 x16

Relative Performance

1%
1%
1%
2%
2%
2%
2%
3%
3%
3%
4%
4%
4%
5%
5%
5%
5%
5%
6%
6%
6%
6%
7%
8%
8%
8%
8%
8%
8%
8%
8%
9%
9%
9%
9%
10%
10%
10%
10%
10%
10%
11%
11%
12%
12%
12%
12%
13%
13%
14%
14%
14%
14%
15%
15%
15%
15%
16%
16%
16%
16%
17%
17%
18%
18%
19%
19%
19%
19%
19%
19%
19%
20%
21%
22%
23%
23%
23%
23%
24%
24%
25%
25%
26%
26%
29%
32%
32%
34%
34%
35%
35%
36%
36%
36%
36%
37%
37%
39%
40%
40%
40%
44%
45%
46%
49%
54%
56%
60%
60%
63%
74%
76%
83%
94%
100%
TITAN V
Based on TPU review data: "Performance Summary" at 1920x1080
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

GPU Clock
1200 MHz
Boost Clock
1455 MHz
Memory Clock
850 MHz
1700 MHz effective

Memory

Memory Size
12288 MB
Memory Type
HBM2
Memory Bus
3072 bit
Bandwidth
652.8 GB/s

Render Config

Shading Units
5120
TMUs
320
ROPs
96
SM Count
80
Tensor Cores
640

Theoretical Performance

Pixel Rate
139.7 GPixel/s
Texture Rate
465.6 GTexel/s
FP16 (half) performance
29,798 GFLOPS (2:1)
FP32 (float) performance
14,899 GFLOPS
FP64 (double) performance
7,450 GFLOPS (1:2)

Board Design

Slot Width
Dual-slot
Length
10.5 inches
267 mm
TDP
250 W
Outputs
1x HDMI
3x DisplayPort
Power Connectors
1x 6-pin + 1x 8-pin
Board Number
PG500 SKU 0

Graphics Features

DirectX
12.0 (12_1)
OpenGL
4.6
OpenCL
2.0
Vulkan
1.1.82
CUDA
7.0
Shader Model
6.1

Card Notes

Base Clock:
Deep Learning: 98.304TFLOPs

Boost Clock:
Deep Learning: 119.193TFLOPs

GV100 GPU Notes

PureVideo HD: VP9
VDPAU: Feature Set I