Report an Error

NVIDIA Tesla P40

Graphics Processor
GP102
Cores
3840
TMUs
240
ROPs
96
Memory Size
24 GB
Memory Type
GDDR5X
Bus Width
384 bit
The Tesla P40 is a enthusiast-class professional graphics card by NVIDIA, launched in September 2016. Built on the 16 nm process, and based on the GP102 graphics processor, the card supports DirectX 12.0. The GP102 graphics processor is a large chip with a die area of 471 mm² and 11,800 million transistors. It features 3840 shading units, 240 texture mapping units and 96 ROPs. NVIDIA has placed 24,576 MB GDDR5X memory on the card, which are connected using a 384-bit memory interface. The GPU is operating at a frequency of 1303 MHz, which can be boosted up to 1531 MHz, memory is running at 1251 MHz.
Being a dual-slot card, the NVIDIA Tesla P40 draws power from 1x 6-pin + 1x 8-pin power connectors, with power draw rated at 250 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Tesla P40 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 5699 US Dollars.

Graphics Processor

GPU Name
GP102
Architecture
Pascal
Foundry
TSMC
Process Size
16 nm
Transistors
11,800 million
Die Size
471 mm²

Graphics Card

Release Date
Sep 13th, 2016
Generation
Tesla
(Pxx)
Production
Active
Launch Price
5,699 USD
Bus Interface
PCIe 3.0 x16

Relative Performance

1%
GeForce 210
1%
GeForce 9400 GT
2%
Radeon HD 4550
2%
Radeon HD 5450
2%
Radeon HD 6450
2%
GeForce GT 520
3%
GeForce GT 220
4%
GeForce GT 430
4%
Radeon HD 5570
4%
Radeon HD 4670
5%
GeForce GT 440
5%
GeForce GT 240
5%
GeForce 9600 GT
6%
Radeon HD 5670
6%
GeForce GT 640
6%
GeForce 9800 GT
7%
Radeon HD 6670
7%
Radeon HD 4830
7%
Radeon HD 4770
8%
Radeon HD 4850
8%
GeForce GTS 250
8%
GeForce GTS 450
8%
Radeon HD 5750
10%
Radeon HD 7750
10%
Radeon HD 5770
10%
GeForce GTX 260
10%
Radeon HD 4870
10%
Radeon Vega 8
10%
GeForce GTX 550 Ti
10%
GeForce GTX 650
11%
Radeon HD 5830
11%
Radeon HD 6790
11%
Radeon HD 4890
12%
GeForce GTX 460
12%
Radeon RX Vega 11
12%
GeForce GT 1030
12%
GeForce GTX 275
12%
Radeon HD 7770 GHz Edition
12%
GeForce GTX 280
12%
GeForce GTX 465
13%
Radeon HD 6850
13%
GeForce GTX 285
14%
Radeon HD 5850
15%
GeForce GTX 650 Ti
15%
Radeon HD 7790
15%
Radeon RX 550
15%
GeForce GTX 470
16%
Radeon HD 6870
17%
Radeon HD 5870
17%
GeForce GTX 560 Ti
17%
Radeon HD 4870 X2
18%
GeForce GTX 750 Ti
18%
Radeon HD 6950
18%
GeForce GTX 295
19%
GeForce GTX 650 Ti Boost
19%
Radeon HD 7850
19%
GeForce GTX 480
20%
Radeon HD 6970
20%
Radeon R7 265
21%
Radeon R7 370
21%
Radeon RX 560
21%
GeForce GTX 660
21%
GeForce GTX 570
23%
GeForce GTX 950
23%
Radeon HD 7870 GHz Edition
23%
Radeon R9 270X
24%
GeForce GTX 660 Ti
24%
GeForce GTX 580
24%
GeForce GTX 1050
24%
Radeon HD 7950
24%
Radeon RX 460
24%
Radeon HD 5970
25%
GeForce GTX 760
27%
GeForce GTX 670
28%
GeForce GTX 960
28%
Radeon R9 380
29%
Radeon R9 285
29%
Radeon HD 7970
29%
GeForce GTX 680
30%
GeForce GTX 1050 Ti
31%
GeForce GTX 770
31%
Radeon HD 6990
32%
Radeon R9 280X
33%
GeForce GTX 590
33%
Radeon HD 7970 GHz Edition
36%
GeForce GTX 780
37%
GeForce GTX 1650
40%
Radeon RX 470
40%
Radeon R9 290
43%
Radeon R9 390
43%
Radeon R9 290X
44%
GeForce GTX 970
44%
GeForce GTX TITAN
45%
Radeon RX 570
45%
GeForce GTX 780 Ti
46%
Radeon R9 390X
46%
Radeon HD 7990
46%
Radeon RX 480
46%
GeForce GTX 690
49%
Radeon RX 580
50%
GeForce GTX 980
50%
GeForce GTX 1060 6 GB
50%
Radeon R9 FURY
51%
Radeon RX 590
56%
Radeon R9 295X2
56%
Radeon R9 FURY X
57%
GeForce GTX 980 Ti
62%
GeForce GTX TITAN X
65%
GeForce GTX 1660 Ti
65%
GeForce GTX 1070
68%
Radeon RX Vega 56
74%
GeForce GTX 1070 Ti
76%
Radeon RX Vega 64
76%
GeForce RTX 2060
78%
GeForce GTX 1080
89%
GeForce RTX 2070
89%
Radeon VII
93%
TITAN X Pascal
96%
GeForce GTX 1080 Ti
100%
Tesla P40
103%
GeForce RTX 2080
120%
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
1303 MHz
Boost Clock
1531 MHz
Memory Clock
1251 MHz
10008 MHz effective

Memory

Memory Size
24 GB
Memory Type
GDDR5X
Memory Bus
384 bit
Bandwidth
480.4 GB/s

Render Config

Shading Units
3840
TMUs
240
ROPs
96
SM Count
30
L1 Cache
48 KB (per SM)
L2 Cache
3 MB

Theoretical Performance

Pixel Rate
147.0 GPixel/s
Texture Rate
367.4 GTexel/s
FP16 (half) performance
183.7 GFLOPS (1:64)
FP32 (float) performance
11.76 TFLOPS
FP64 (double) performance
367.4 GFLOPS (1:32)

Board Design

Slot Width
Dual-slot
Length
10.5 inches
267 mm
TDP
250 W
Outputs
No outputs
Power Connectors
1x 6-pin + 1x 8-pin

Graphics Features

DirectX
12.0 (12_1)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1.103
CUDA
6.1
Shader Model
6.4