Home GPU Comparison AMD Radeon Pro Duo vs NVIDIA PG506 232

AMD Radeon Pro Duo vs NVIDIA PG506 232

We compared two Desktop platform GPUs: 4GB VRAM Radeon Pro Duo and 24GB VRAM PG506 232 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

AMD Radeon Pro Duo 's Advantages
512 additional rendering cores
NVIDIA PG506 232 's Advantages
Released 5 years late
Boost Clock1440MHz
More VRAM (24GB vs 4GB)
Larger VRAM bandwidth (933.1GB/s vs 512.0GB/s)
Lower TDP (165W vs 350W)

Score

Benchmark

FP32 (float)
Radeon Pro Duo
8.192 TFLOPS
PG506 232 +25%
10.32 TFLOPS
VS

Graphics Card

Apr 2016
Release Date
Apr 2021
Radeon Pro
Generation
Tesla
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

-
Base Clock
930 MHz
-
Boost Clock
1440 MHz
500 MHz
Memory Clock
1215 MHz

Memory

4GB
Memory Size
24GB
HBM
Memory Type
HBM2
4096bit
Memory Bus
3072bit
512.0GB/s
Bandwidth
933.1GB/s

Render Config

64
Compute Units
-
-
SM Count
56
4096
Shading Units
3584
256
TMUs
224
64
ROPs
96
-
Tensor Cores
224
-
-
-
16 KB (per CU)
L1 Cache
192 KB (per SM)
2 MB
L2 Cache
24 MB
-
-
-

Theoretical Performance

64.00 GPixel/s
Pixel Rate
138.2 GPixel/s
256.0 GTexel/s
Texture Rate
322.6 GTexel/s
8.192 TFLOPS
FP16 (half)
10.32 TFLOPS
8.192 TFLOPS
FP32 (float)
10.32 TFLOPS
512.0 GFLOPS
FP64 (double)
5.161 TFLOPS

Board Design

350W
TDP
165W
750 W
Suggested PSU
450 W
1x HDMI 1.4a 3x DisplayPort 1.2
Outputs
No outputs
3x 8-pin
Power Connectors
8-pin EPS

Graphics Processor

Capsaicin
GPU Name
GA100
Capsaicin XT
GPU Variant
-
GCN 3.0
Architecture
Ampere
TSMC
Foundry
TSMC
28 nm
Process Size
7 nm
8.9 billion
Transistors
54.2 billion
596 mm²
Die Size
826 mm²

Graphics Features

12 (12_0)
DirectX
N/A
4.6
OpenGL
N/A
2.0
OpenCL
3.0
1.2
Vulkan
N/A
-
CUDA
8.0
6.0
Shader Model
N/A

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy