Report an Error

NVIDIA P104-100

Graphics Processor
GP104
Cores
1920
TMUs
120
ROPs
64
Memory Size
4 GB
Memory Type
GDDR5X
Bus Width
256 bit
The P104-100 is a professional graphics card by NVIDIA, launched in December 2017. Built on the 16 nm process, and based on the GP104 graphics processor, in its GP104-100-A1 variant, the card supports DirectX 12.0. The GP104 graphics processor is a large chip with a die area of 314 mm² and 7,200 million transistors. Unlike the fully unlocked GeForce GTX 1080, which uses the same GPU but has all 2560 shaders enabled, NVIDIA has disabled some shading units on the P104-100 to reach the product's target shader count. It features 1920 shading units, 120 texture mapping units and 64 ROPs. NVIDIA has placed 4,096 MB GDDR5X memory on the card, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 1607 MHz, which can be boosted up to 1733 MHz, memory is running at 1251 MHz.
Being a dual-slot card, the NVIDIA P104-100 draws power from 1x 8-pin power connectors, with power draw not exactly known. This device has no display connectivity, as it is not designed to have monitors connected to it. P104-100 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.

Graphics Processor

GPU Name
GP104
GPU Variant
GP104-100-A1
Architecture
Pascal
Foundry
TSMC
Process Size
16 nm
Transistors
7,200 million
Die Size
314 mm²

Graphics Card

Release Date
Dec 12th, 2017
Generation
Mining GPUs
Production
Active
Bus Interface
PCIe 3.0 x16

Relative Performance

1%
GeForce 210
2%
GeForce 9400 GT
2%
Radeon HD 4550
3%
Radeon HD 5450
4%
Radeon HD 6450
4%
GeForce GT 520
5%
GeForce GT 220
6%
GeForce GT 430
6%
Radeon HD 5570
7%
Radeon HD 4670
7%
GeForce GT 440
7%
GeForce GT 240
8%
GeForce 9600 GT
9%
Radeon HD 5670
9%
GeForce GT 640
10%
GeForce 9800 GT
10%
Radeon HD 6670
10%
Radeon HD 4830
11%
Radeon HD 4770
12%
Radeon HD 4850
12%
GeForce GTS 250
12%
GeForce GTS 450
13%
Radeon HD 5750
14%
Radeon HD 7750
15%
Radeon HD 5770
15%
GeForce GTX 260
15%
Radeon HD 4870
15%
Radeon Vega 8
15%
GeForce GTX 550 Ti
15%
GeForce GTX 650
16%
Radeon HD 5830
17%
Radeon HD 6790
17%
Radeon HD 4890
18%
GeForce GTX 460
18%
Radeon RX Vega 11
18%
GeForce GT 1030
18%
GeForce GTX 275
18%
Radeon HD 7770 GHz Edition
19%
GeForce GTX 280
19%
GeForce GTX 465
20%
Radeon HD 6850
20%
GeForce GTX 285
22%
Radeon HD 5850
22%
GeForce GTX 650 Ti
22%
Radeon HD 7790
23%
Radeon RX 550
23%
GeForce GTX 470
24%
Radeon HD 6870
25%
Radeon HD 5870
26%
GeForce GTX 560 Ti
26%
Radeon HD 4870 X2
27%
GeForce GTX 750 Ti
27%
Radeon HD 6950
28%
GeForce GTX 295
28%
GeForce GTX 650 Ti Boost
28%
Radeon HD 7850
29%
GeForce GTX 480
30%
Radeon HD 6970
31%
Radeon R7 265
31%
Radeon RX 460
31%
Radeon R7 370
32%
GeForce GTX 660
32%
GeForce GTX 570
32%
Radeon RX 560
34%
GeForce GTX 950
34%
Radeon HD 7870 GHz Edition
35%
Radeon R9 270X
36%
GeForce GTX 660 Ti
36%
GeForce GTX 580
36%
GeForce GTX 1050
36%
Radeon HD 7950
37%
Radeon HD 5970
38%
GeForce GTX 760
41%
GeForce GTX 670
42%
GeForce GTX 960
43%
Radeon R9 380
43%
Radeon R9 285
44%
Radeon HD 7970
44%
GeForce GTX 680
45%
GeForce GTX 1050 Ti
46%
GeForce GTX 770
47%
Radeon HD 6990
49%
Radeon R9 280X
49%
GeForce GTX 590
49%
Radeon HD 7970 GHz Edition
55%
GeForce GTX 780
57%
GeForce GTX 1650
60%
Radeon RX 470
61%
Radeon R9 290
64%
Radeon RX 570
65%
Radeon R9 390
65%
Radeon R9 290X
66%
GeForce GTX 970
67%
GeForce GTX TITAN
68%
GeForce GTX 780 Ti
69%
Radeon R9 390X
69%
Radeon HD 7990
70%
Radeon RX 480
70%
GeForce GTX 690
74%
Radeon RX 580
76%
GeForce GTX 980
76%
Radeon R9 FURY
76%
GeForce GTX 1060 6 GB
80%
Radeon RX 590
84%
Radeon R9 295X2
85%
GeForce GTX 1660
86%
Radeon R9 FURY X
87%
GeForce GTX 980 Ti
89%
GeForce GTX TITAN X
97%
GeForce GTX 1660 Ti
97%
GeForce GTX 1070
100%
P104-100
103%
Radeon RX Vega 56
110%
GeForce GTX 1070 Ti
113%
Radeon RX Vega 64
114%
GeForce GTX 1080
114%
GeForce RTX 2060
119%
Radeon RX 5700
128%
GeForce RTX 2060 SUPER
133%
GeForce RTX 2070
136%
Radeon RX 5700 XT
138%
Radeon VII
141%
TITAN X Pascal
146%
GeForce GTX 1080 Ti
147%
GeForce RTX 2070 SUPER
157%
GeForce RTX 2080
183%
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
1607 MHz
Boost Clock
1733 MHz
Memory Clock
1251 MHz
10008 MHz effective

Memory

Memory Size
4 GB
Memory Type
GDDR5X
Memory Bus
256 bit
Bandwidth
320.3 GB/s

Render Config

Shading Units
1920
TMUs
120
ROPs
64
SM Count
15
L1 Cache
48 KB (per SM)
L2 Cache
2 MB

Theoretical Performance

Pixel Rate
110.9 GPixel/s
Texture Rate
208.0 GTexel/s
FP16 (half) performance
104.0 GFLOPS (1:64)
FP32 (float) performance
6.655 TFLOPS
FP64 (double) performance
208.0 GFLOPS (1:32)

Board Design

Slot Width
Dual-slot
Length
10.5 inches
267 mm
TDP
unknown
Outputs
No outputs
Power Connectors
1x 8-pin
Board Number
PG413 SKU 100

Graphics Features

DirectX
12.0 (12_1)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1.109
CUDA
6.1
Shader Model
6.4

Retail boards based on this design (6)

Name GPU Clock Boost Clock Memory Clock Other Changes
ASUS P104-100 1607 MHz 1733 MHz 1251 MHz 10.63 inches/270 mm
GALAX P104-100 1607 MHz 1733 MHz 1251 MHz
GIGABYTE P104-100 1607 MHz 1733 MHz 1251 MHz 11.024 inches/280 mm
Inno3D P104-100 Twin X2 1607 MHz 1733 MHz 1251 MHz 10.63 inches/270 mm
MSI P104-100 MINER 1607 MHz 1733 MHz 1251 MHz
Palit P104-100 1607 MHz 1733 MHz 1251 MHz