Home GPU Comparison NVIDIA PG506 232 vs AMD Radeon HD 8990 OEM

NVIDIA PG506 232 vs AMD Radeon HD 8990 OEM

We compared two Desktop platform GPUs: 24GB VRAM PG506 232 and 3GB VRAM Radeon HD 8990 OEM to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA PG506 232 's Advantages
Released 8 years late
Boost Clock has increased by 44% (1440MHz vs 1000MHz)
More VRAM (24GB vs 3GB)
Larger VRAM bandwidth (933.1GB/s vs 288.0GB/s)
1536 additional rendering cores
Lower TDP (165W vs 375W)

Score

Benchmark

FP32 (float)
PG506 232 +151%
10.32 TFLOPS
Radeon HD 8990 OEM
4.096 TFLOPS
VS

Graphics Card

Apr 2021
Release Date
Apr 2013
Tesla
Generation
Sea Islands
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16

Clock Speeds

930 MHz
Base Clock
950 MHz
1440 MHz
Boost Clock
1000 MHz
1215 MHz
Memory Clock
1500 MHz

Memory

24GB
Memory Size
3GB
HBM2
Memory Type
GDDR5
3072bit
Memory Bus
384bit
933.1GB/s
Bandwidth
288.0GB/s

Render Config

56
SM Count
-
-
Compute Units
32
3584
Shading Units
2048
224
TMUs
128
96
ROPs
32
224
Tensor Cores
-
-
RT Cores
-
192 KB (per SM)
L1 Cache
16 KB (per CU)
24 MB
L2 Cache
768 KB

Theoretical Performance

138.2 GPixel/s
Pixel Rate
32.00 GPixel/s
322.6 GTexel/s
Texture Rate
128.0 GTexel/s
10.32 TFLOPS
FP16 (half)
-
10.32 TFLOPS
FP32 (float)
4.096 TFLOPS
5.161 TFLOPS
FP64 (double)
1024 GFLOPS

Graphics Processor

GA100
GPU Name
Malta
-
GPU Variant
Malta XT (215-0849026)
Ampere
Architecture
GCN 1.0
TSMC
Foundry
TSMC
7 nm
Process Size
28 nm
54.2 billion
Transistors
4.313 billion
826 mm²
Die Size
365 mm²

Board Design

165W
TDP
375W
450 W
Suggested PSU
750 W
No outputs
Outputs
1x DVI 4x mini-DisplayPort 1.2
8-pin EPS
Power Connectors
2x 8-pin

Graphics Features

N/A
DirectX
12 (11_1)
N/A
OpenGL
4.6
3.0
OpenCL
1.2
N/A
Vulkan
1.2
8.0
CUDA
-
N/A
Shader Model
5.1

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy