Report an Error

NVIDIA PG506-232

Graphics Processor
GA100
Cores
3584
TMUs
224
ROPs
96
Memory Size
24 GB
Memory Type
HBM2
Bus Width
3072 bit
GPU Chip
GPU
The PG506-232 is a professional graphics card by NVIDIA, launched on April 12th, 2021. Built on the 7 nm process, and based on the GA100 graphics processor, the card does not support DirectX. Since PG506-232 does not support DirectX 11 or DirectX 12, it might not be able to run all the latest games. The GA100 graphics processor is a large chip with a die area of 826 mm² and 54,200 million transistors. Unlike the fully unlocked DRIVE A100 PROD, which uses the same GPU but has all 6912 shaders enabled, NVIDIA has disabled some shading units on the PG506-232 to reach the product's target shader count. It features 3584 shading units, 224 texture mapping units, and 96 ROPs. Also included are 224 tensor cores which help improve the speed of machine learning applications. NVIDIA has paired 24 GB HBM2 memory with the PG506-232, which are connected using a 3072-bit memory interface. The GPU is operating at a frequency of 930 MHz, which can be boosted up to 1440 MHz, memory is running at 1215 MHz.
Being a dual-slot card, the NVIDIA PG506-232 draws power from an 8-pin EPS power connector, with power draw rated at 165 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. PG506-232 is connected to the rest of the system using a PCI-Express 4.0 x16 interface. The card measures 267 mm in length, 112 mm in width, and features a dual-slot cooling solution.

Graphics Processor

GPU Name
GA100
Architecture
Ampere
Foundry
TSMC
Process Size
7 nm
Transistors
54,200 million
Density
65.6M / mm²
Die Size
826 mm²
Chip Package
BGA-2743

Graphics Card

Release Date
Apr 12th, 2021
Availability
2021
Generation
Tesla Ampere
(Axx)
Predecessor
Tesla Turing
Successor
Tesla Ada
Production
Active
Bus Interface
PCIe 4.0 x16

Relative Performance

GeForce 210
1%
GeForce 9400 GT
2%
Radeon HD 4550
2%
Radeon HD 5450
3%
Radeon HD 6450
3%
GeForce GT 520
3%
GeForce GT 220
4%
GeForce GT 430
6%
Radeon HD 5570
6%
Radeon HD 4670
6%
GeForce GT 440
6%
GeForce GT 240
7%
GeForce 9600 GT
8%
Radeon HD 5670
8%
GeForce GT 640
9%
GeForce 9800 GT
9%
Radeon HD 6670
9%
Radeon HD 4830
10%
Radeon HD 4770
10%
Radeon HD 4850
11%
GeForce GTS 250
11%
GeForce GTS 450
11%
Radeon HD 5750
12%
Radeon HD 7750
13%
Radeon HD 5770
14%
GeForce GTX 260
14%
Radeon HD 4870
14%
Radeon Vega 8
14%
GeForce GTX 550 Ti
14%
GeForce GTX 650
14%
Radeon HD 5830
15%
Radeon HD 6790
16%
Radeon HD 4890
16%
GeForce GTX 460
17%
Radeon RX Vega 11
17%
GeForce GT 1030
17%
GeForce GTX 275
17%
Radeon HD 7770 GHz Edition
17%
GeForce GTX 280
17%
GeForce GTX 465
18%
Radeon HD 6850
18%
GeForce GTX 285
19%
Radeon HD 5850
20%
GeForce GTX 650 Ti
20%
Radeon HD 7790
20%
Radeon RX 550
21%
GeForce GTX 470
21%
Radeon HD 6870
22%
Radeon HD 5870
24%
GeForce GTX 560 Ti
24%
Radeon HD 4870 X2
25%
GeForce GTX 750 Ti
25%
Radeon HD 6950
25%
GeForce GTX 295
26%
GeForce GTX 650 Ti Boost
26%
Radeon HD 7850
26%
GeForce GTX 480
27%
Radeon HD 6970
28%
Radeon R7 265
29%
Radeon RX 460
29%
Radeon R7 370
29%
GeForce GTX 660
29%
GeForce GTX 570
29%
Radeon RX 560
30%
GeForce GTX 950
32%
Radeon HD 7870 GHz Edition
32%
Radeon R9 270X
33%
GeForce GTX 660 Ti
33%
GeForce GTX 580
33%
GeForce GTX 1050
34%
Radeon HD 7950
34%
GeForce GTX 1630
34%
Radeon HD 5970
34%
GeForce GTX 760
35%
GeForce GTX 670
38%
GeForce GTX 960
39%
Radeon R9 380
40%
Radeon R9 285
40%
Radeon HD 7970
41%
GeForce GTX 680
41%
GeForce GTX 1050 Ti
42%
GeForce GTX 770
43%
Radeon HD 6990
44%
Radeon R9 280X
45%
GeForce GTX 590
46%
Radeon HD 7970 GHz Edition
46%
GeForce GTX 780
51%
Arc A380
51%
Radeon RX 6400
52%
GeForce GTX 1650
53%
Radeon RX 470
56%
Radeon R9 290
57%
Radeon RX 570
60%
Radeon R9 390
60%
Radeon R9 290X
61%
GeForce GTX 970
62%
GeForce GTX TITAN
62%
GeForce GTX 780 Ti
63%
Radeon R9 390X
64%
Radeon HD 7990
64%
Radeon RX 480
65%
GeForce GTX 690
65%
GeForce GTX 1060 6 GB
67%
Radeon RX 5500 OEM
68%
Radeon RX 580
69%
Radeon RX 5500 XT
69%
Radeon RX 6500 XT
70%
GeForce GTX 980
70%
GeForce GTX 1650 SUPER
71%
Radeon R9 FURY
71%
Radeon RX 590
74%
Radeon R9 295X2
78%
GeForce GTX 1660
79%
Radeon R9 FURY X
80%
GeForce GTX 980 Ti
81%
GeForce GTX TITAN X
83%
GeForce GTX 1660 SUPER
85%
GeForce GTX 1070
90%
GeForce GTX 1660 Ti
90%
GeForce RTX 3050 8 GB
92%
Radeon RX Vega 56
96%
PG506-232
100%
GeForce GTX 1070 Ti
102%
Radeon RX 5600 XT
103%
Radeon RX Vega 64
105%
GeForce GTX 1080
106%
GeForce RTX 2060
106%
Radeon RX 5700
111%
Arc A580
111%
Radeon RX 6600
115%
GeForce RTX 2060 SUPER
119%
GeForce RTX 2070
121%
Radeon RX 5700 XT
121%
GeForce RTX 3060 12 GB
123%
Arc A750
127%
Radeon VII
128%
TITAN X Pascal
131%
Radeon RX 6600 XT
133%
GeForce GTX 1080 Ti
135%
Arc A770
137%
GeForce RTX 2070 SUPER
137%
Radeon RX 6650 XT
144%
Radeon RX 7600
146%
GeForce RTX 4060
146%
GeForce RTX 2080
147%
Radeon RX 7600 XT
150%
GeForce RTX 2080 SUPER
154%
GeForce RTX 3060 Ti
158%
Radeon RX 6700 XT
164%
Radeon RX 6750 XT
174%
GeForce RTX 4060 Ti 8 GB
176%
GeForce RTX 2080 Ti
177%
GeForce RTX 3070
185%
GeForce RTX 3070 Ti
198%
Radeon RX 7700 XT
200%
Radeon RX 6800
204%
GeForce RTX 4070
226%
Radeon RX 6800 XT
232%
GeForce RTX 3080
241%
Radeon RX 7800 XT
243%
Radeon RX 6900 XT
250%
GeForce RTX 4070 SUPER
262%
Radeon RX 7900 GRE
267%
GeForce RTX 3080 Ti
270%
Radeon RX 6950 XT
270%
GeForce RTX 3090
275%
GeForce RTX 4070 Ti
282%
GeForce RTX 4070 Ti SUPER
308%
Radeon RX 7900 XT
316%
GeForce RTX 3090 Ti
319%
GeForce RTX 4080
358%
GeForce RTX 4080 SUPER
363%
Radeon RX 7900 XTX
366%
GeForce RTX 4090
449%
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

Base Clock
930 MHz
Boost Clock
1440 MHz
Memory Clock
1215 MHz
2.4 Gbps effective

Memory

Memory Size
24 GB
Memory Type
HBM2
Memory Bus
3072 bit
Bandwidth
933.1 GB/s

Render Config

Shading Units
3584
TMUs
224
ROPs
96
SM Count
56
Tensor Cores
224
L1 Cache
192 KB (per SM)
L2 Cache
24 MB

Theoretical Performance

Pixel Rate
138.2 GPixel/s
Texture Rate
322.6 GTexel/s
FP16 (half)
10.32 TFLOPS (1:1)
FP32 (float)
10.32 TFLOPS
FP64 (double)
5.161 TFLOPS (1:2)

Board Design

Slot Width
Dual-slot
Length
267 mm
10.5 inches
Width
112 mm
4.4 inches
TDP
165 W
Suggested PSU
450 W
Outputs
No outputs
Power Connectors
8-pin EPS
Board Number
P1001 SKU 205

Graphics Features

DirectX
N/A
OpenGL
N/A
OpenCL
3.0
Vulkan
N/A
CUDA
8.0
Shader Model
N/A

GA100 GPU Notes

Tensor Cores: 3rd Gen
NVENC: No Support
NVDEC: 4th Gen x5
PureVideo HD: VP10
VDPAU: Feature Set J
Apr 19th, 2024 22:51 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts