Home GPU Comparison AMD Radeon HD 7970 X2 vs NVIDIA GeForce RTX 5090

AMD Radeon HD 7970 X2 vs NVIDIA GeForce RTX 5090

We compared two Desktop platform GPUs: 3GB VRAM Radeon HD 7970 X2 and 32GB VRAM GeForce RTX 5090 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce RTX 5090 's Advantages
Released 12 years and 5 months late
Boost Clock2520MHz
More VRAM (32GB vs 3GB)
Larger VRAM bandwidth (1.52TB/s vs 264.0GB/s)
19712 additional rendering cores

Score

Benchmark

FP32 (float)
Radeon HD 7970 X2
3.789 TFLOPS
GeForce RTX 5090 +2795%
109.7 TFLOPS
VS

Graphics Card

Aug 2012
Release Date
Jan 2025
Southern Islands
Generation
GeForce 50
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 5.0 x16

Clock Speeds

-
Base Clock
2235 MHz
-
Boost Clock
2520 MHz
1375 MHz
Memory Clock
1875 MHz

Memory

3GB
Memory Size
32GB
GDDR5
Memory Type
GDDR7
384bit
Memory Bus
512bit
264.0GB/s
Bandwidth
1.52TB/s

Render Config

32
Compute Units
-
-
SM Count
170
2048
Shading Units
21760
128
TMUs
680
32
ROPs
192
-
Tensor Cores
680
-
RT Cores
170
16 KB (per CU)
L1 Cache
128 KB (per SM)
768 KB
L2 Cache
88 MB
-
-
-

Theoretical Performance

29.60 GPixel/s
Pixel Rate
483.8 GPixel/s
118.4 GTexel/s
Texture Rate
1714 GTexel/s
-
FP16 (half)
109.7 TFLOPS
3.789 TFLOPS
FP32 (float)
109.7 TFLOPS
947.2 GFLOPS
FP64 (double)
1.714 TFLOPS

Board Design

500W
TDP
500W
900 W
Suggested PSU
900 W
2x DVI 1x HDMI 1.4a 2x mini-DisplayPort 1.2
Outputs
1x HDMI 2.1 3x DisplayPort 2.1a
3x 8-pin
Power Connectors
1x 16-pin

Graphics Processor

New Zealand
GPU Name
GB202
-
GPU Variant
GB202-400-A1
GCN 1.0
Architecture
Blackwell 2.0
TSMC
Foundry
TSMC
28 nm
Process Size
4 nm
4.313 billion
Transistors
Unknown
352 mm²
Die Size
Unknown

Graphics Features

12 (11_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
1.2
OpenCL
3.0
1.2
Vulkan
1.3
-
CUDA
10.1
5.1
Shader Model
6.8

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy