Home GPU Comparison NVIDIA PG506 232 vs NVIDIA GeForce RTX 3090

NVIDIA PG506 232 vs NVIDIA GeForce RTX 3090

We compared two Desktop platform GPUs: 24GB VRAM PG506 232 and 24GB VRAM GeForce RTX 3090 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA PG506 232 's Advantages
Released 7 months late
Lower TDP (165W vs 350W)
NVIDIA GeForce RTX 3090 's Advantages
Boost Clock has increased by 18% (1695MHz vs 1440MHz)
Larger VRAM bandwidth (936.2GB/s vs 933.1GB/s)
6912 additional rendering cores

Score

Benchmark

FP32 (float)
PG506 232
10.32 TFLOPS
GeForce RTX 3090 +244%
35.58 TFLOPS
VS

Graphics Card

Apr 2021
Release Date
Sep 2020
Tesla
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

930 MHz
Base Clock
1395 MHz
1440 MHz
Boost Clock
1695 MHz
1215 MHz
Memory Clock
1219 MHz

Memory

24GB
Memory Size
24GB
HBM2
Memory Type
GDDR6X
3072bit
Memory Bus
384bit
933.1GB/s
Bandwidth
936.2GB/s

Render Config

-
-
-
56
SM Count
82
3584
Shading Units
10496
224
TMUs
328
96
ROPs
112
224
Tensor Cores
328
-
RT Cores
82
192 KB (per SM)
L1 Cache
128 KB (per SM)
24 MB
L2 Cache
6 MB
-
-
-

Theoretical Performance

138.2 GPixel/s
Pixel Rate
189.8 GPixel/s
322.6 GTexel/s
Texture Rate
556.0 GTexel/s
10.32 TFLOPS
FP16 (half)
35.58 TFLOPS
10.32 TFLOPS
FP32 (float)
35.58 TFLOPS
5.161 TFLOPS
FP64 (double)
556.0 GFLOPS

Board Design

165W
TDP
350W
450 W
Suggested PSU
750 W
No outputs
Outputs
1x HDMI 2.1 3x DisplayPort 1.4a
8-pin EPS
Power Connectors
1x 12-pin

Graphics Processor

GA100
GPU Name
GA102
-
GPU Variant
GA102-300-A1
Ampere
Architecture
Ampere
TSMC
Foundry
Samsung
7 nm
Process Size
8 nm
54.2 billion
Transistors
28.3 billion
826 mm²
Die Size
628 mm²

Graphics Features

N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
8.0
CUDA
8.6
N/A
Shader Model
6.6

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy