GeForce RTX 2070 vs Radeon RX 580
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 2070 and 8GB VRAM Radeon RX 580 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 2070 's Advantages
Released 1 years and 6 months late
Boost Clock has increased by 21% (1620MHz vs 1340MHz)
Larger VRAM bandwidth (448.0GB/s vs 256.0GB/s)
Lower TDP (175W vs 185W)
Score
Benchmark
FP32 (float)
GeForce RTX 2070
+20%
7465
Radeon RX 580
6175
3DMark Time Spy
GeForce RTX 2070
+109%
9088
Radeon RX 580
4347
3DMark Time Spy Extreme
GeForce RTX 2070
+118%
4309
Radeon RX 580
1968
Shadow of the Tomb Raider 2160p
GeForce RTX 2070
+117%
37
Radeon RX 580
17
Shadow of the Tomb Raider 1440p
GeForce RTX 2070
+94%
68
Radeon RX 580
35
Shadow of the Tomb Raider 1080p
GeForce RTX 2070
+96%
98
Radeon RX 580
50
Battlefield 5 2160p
GeForce RTX 2070
+100%
54
Radeon RX 580
27
Battlefield 5 1440p
GeForce RTX 2070
+77%
96
Radeon RX 580
54
Battlefield 5 1080p
GeForce RTX 2070
+64%
128
Radeon RX 580
78
GTA 5 1440p
GeForce RTX 2070
+50%
90
Radeon RX 580
60
Graphics Card
Oct 2018
Release Date
Apr 2017
GeForce 20
Generation
Polaris
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1410 MHz
Base Clock
1257 MHz
1620 MHz
Boost Clock
1340 MHz
1750 MHz
Memory Clock
2000 MHz
Memory
8GB
Memory Size
8GB
GDDR6
Memory Type
GDDR5
256bit
Memory Bus
256bit
448.0GB/s
Bandwidth
256.0GB/s
Render Config
-
Compute Units
36
36
SM Count
-
2304
Shading Units
2304
144
TMUs
144
64
ROPs
32
288
Tensor Cores
-
36
RT Cores
-
64 KB (per SM)
L1 Cache
16 KB (per CU)
4 MB
L2 Cache
2 MB
Theoretical Performance
103.7 GPixel/s
Pixel Rate
42.88 GPixel/s
233.3 GTexel/s
Texture Rate
193.0 GTexel/s
14.93 TFLOPS
FP16 (half)
6.175 TFLOPS
7.465 TFLOPS
FP32 (float)
6.175 TFLOPS
233.3 GFLOPS
FP64 (double)
385.9 GFLOPS
Board Design
175W
TDP
185W
450 W
Suggested PSU
450 W
1x DVI
1x HDMI 2.0
2x DisplayPort 1.4a
1x USB Type-C
Outputs
1x HDMI 2.0b
3x DisplayPort 1.4a
1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
TU106
GPU Name
Polaris 20
TU106-400A-A1
GPU Variant
Polaris 20 XTX
(215-0910038)
Turing
Architecture
GCN 4.0
TSMC
Foundry
GlobalFoundries
12 nm
Process Size
14 nm
10.8 billion
Transistors
5.7 billion
445 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
