GeForce RTX 2080 SUPER vs Radeon RX 470
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 2080 SUPER and 4GB VRAM Radeon RX 470 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 2080 SUPER 's Advantages
Released 2 years and 11 months late
Boost Clock has increased by 50% (1815MHz vs 1206MHz)
More VRAM (8GB vs 4GB)
Larger VRAM bandwidth (495.9GB/s vs 211.2GB/s)
1024 additional rendering cores
Radeon RX 470 's Advantages
Lower TDP (120W vs 250W)
Score
Benchmark
FP32 (float)
GeForce RTX 2080 SUPER
+125%
11150
Radeon RX 470
4940
3DMark Time Spy
GeForce RTX 2080 SUPER
+215%
11621
Radeon RX 470
3679
3DMark Time Spy Extreme
GeForce RTX 2080 SUPER
+216%
5382
Radeon RX 470
1701
Shadow of the Tomb Raider 2160p
GeForce RTX 2080 SUPER
+300%
48
Radeon RX 470
12
Shadow of the Tomb Raider 1440p
GeForce RTX 2080 SUPER
+264%
91
Radeon RX 470
25
Shadow of the Tomb Raider 1080p
GeForce RTX 2080 SUPER
+222%
129
Radeon RX 470
40
GTA 5 1440p
GeForce RTX 2080 SUPER
+247%
118
Radeon RX 470
34
GTA 5 1080p
GeForce RTX 2080 SUPER
+83%
180
Radeon RX 470
98
Graphics Card
Jul 2019
Release Date
Aug 2016
GeForce 20
Generation
Arctic Islands
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1650 MHz
Base Clock
926 MHz
1815 MHz
Boost Clock
1206 MHz
1937 MHz
Memory Clock
1650 MHz
Memory
8GB
Memory Size
4GB
GDDR6
Memory Type
GDDR5
256bit
Memory Bus
256bit
495.9GB/s
Bandwidth
211.2GB/s
Render Config
-
Compute Units
32
48
SM Count
-
3072
Shading Units
2048
192
TMUs
128
64
ROPs
32
384
Tensor Cores
-
48
RT Cores
-
64 KB (per SM)
L1 Cache
16 KB (per CU)
4 MB
L2 Cache
2 MB
Theoretical Performance
116.2 GPixel/s
Pixel Rate
38.59 GPixel/s
348.5 GTexel/s
Texture Rate
154.4 GTexel/s
22.30 TFLOPS
FP16 (half)
4.940 TFLOPS
11.15 TFLOPS
FP32 (float)
4.940 TFLOPS
348.5 GFLOPS
FP64 (double)
308.7 GFLOPS
Board Design
250W
TDP
120W
600 W
Suggested PSU
300 W
1x HDMI 2.0
3x DisplayPort 1.4a
1x USB Type-C
Outputs
1x HDMI 2.0b
3x DisplayPort 1.4a
1x 6-pin + 1x 8-pin
Power Connectors
1x 6-pin
Graphics Processor
TU104
GPU Name
Ellesmere
TU104-450-A1
GPU Variant
Polaris 10 PRO
(215-0876204)
Turing
Architecture
GCN 4.0
TSMC
Foundry
GlobalFoundries
12 nm
Process Size
14 nm
13.6 billion
Transistors
5.7 billion
545 mm²
Die Size
232 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2
7.5
CUDA
-
6.6
Shader Model
6.4