Radeon RX 580 OEM vs Radeon HD 6870 X2
We compared two Desktop platform GPUs: 8GB VRAM Radeon RX 580 OEM and 1024MB VRAM Radeon HD 6870 X2 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon RX 580 OEM Advantages
Released 4 years and 11 months late
Boost Clock1266MHz
More VRAM (8GB vs 1024GB)
Larger VRAM bandwidth (256.0GB/s vs 134.4GB/s)
1184 additional rendering cores
Lower TDP (150W vs 300W)
Score
Benchmark
FP32 (float)
Radeon RX 580 OEM
+189%
5834
Radeon HD 6870 X2
2016
Graphics Card
Jun 2016
Release Date
Jul 2011
Polaris
Generation
Northern Islands
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1120 MHz
Base Clock
-
1266 MHz
Boost Clock
-
2000 MHz
Memory Clock
1050 MHz
Memory
8GB
Memory Size
1024MB
GDDR5
Memory Type
GDDR5
256bit
Memory Bus
256bit
256.0GB/s
Bandwidth
134.4GB/s
Render Config
36
Compute Units
14
2304
Shading Units
1120
144
TMUs
56
32
ROPs
32
16 KB (per CU)
L1 Cache
8 KB (per CU)
2 MB
L2 Cache
512 KB
Theoretical Performance
40.51 GPixel/s
Pixel Rate
28.80 GPixel/s
182.3 GTexel/s
Texture Rate
50.40 GTexel/s
5.834 TFLOPS
FP16 (half)
-
5.834 TFLOPS
FP32 (float)
2.016 TFLOPS
364.6 GFLOPS
FP64 (double)
-
Board Design
150W
TDP
300W
450 W
Suggested PSU
700 W
1x HDMI 2.0b
3x DisplayPort 1.4a
3x DisplayPort 1.4a
Outputs
2x DVI
1x HDMI 1.3a
2x mini-DisplayPort 1.1
1x HDMI 1.3a
2x mini-DisplayPort 1.1
1x 6-pin
Power Connectors
-
Graphics Processor
Ellesmere
GPU Name
Barts
Polaris 10 XT
(215-0876184)
(215-0876184)
GPU Variant
Barts XT
(215-0798000)
(215-0798000)
GCN 4.0
Architecture
TeraScale 2
GlobalFoundries
Foundry
TSMC
14 nm
Process Size
40 nm
5.7 billion
Transistors
1.7 billion
232 mm²
Die Size
255 mm²
Graphics Features
12 (12_0)
DirectX
11.2 (11_0)
4.6
OpenGL
4.4
2.1
OpenCL
1.2
1.2
Vulkan
N/A
6.4
Shader Model
5.0
