Radeon Pro Duo Polaris vs Radeon HD 5670
We compared two Desktop platform GPUs: 16GB VRAM Radeon Pro Duo Polaris and 1024MB VRAM Radeon HD 5670 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon Pro Duo Polaris 's Advantages
Released 7 years and 3 months late
More VRAM (16GB vs 1024GB)
Larger VRAM bandwidth (224.0GB/s vs 64.00GB/s)
1904 additional rendering cores
Radeon HD 5670 's Advantages
Lower TDP (64W vs 250W)
Score
Benchmark
FP32 (float)
Radeon Pro Duo Polaris
+823%
5728
Radeon HD 5670
620
Graphics Card
Apr 2017
Release Date
Jan 2010
Radeon Pro GCN
Generation
Evergreen
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1750 MHz
Memory Clock
1000 MHz
Memory
16GB
Memory Size
1024MB
GDDR5
Memory Type
GDDR5
256bit
Memory Bus
128bit
224.0GB/s
Bandwidth
64.00GB/s
Render Config
36
Compute Units
5
2304
Shading Units
400
144
TMUs
20
32
ROPs
8
16 KB (per CU)
L1 Cache
8 KB (per CU)
2 MB
L2 Cache
256 KB
Theoretical Performance
39.78 GPixel/s
Pixel Rate
6.200 GPixel/s
179.0 GTexel/s
Texture Rate
15.50 GTexel/s
5.728 TFLOPS
FP16 (half)
-
5.728 TFLOPS
FP32 (float)
620.0 GFLOPS
358.0 GFLOPS
FP64 (double)
-
Board Design
250W
TDP
64W
600 W
Suggested PSU
250 W
1x HDMI 2.0b
3x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 1.3a
1x VGA
1x 6-pin + 1x 8-pin
Power Connectors
None
Graphics Processor
Ellesmere
GPU Name
Redwood
Ellesmere Gemini GL
GPU Variant
Redwood XT
(215-0757002)
GCN 4.0
Architecture
TeraScale 2
GlobalFoundries
Foundry
TSMC
14 nm
Process Size
40 nm
5.7 billion
Transistors
0.627 billion
232 mm²
Die Size
104 mm²
Graphics Features
12 (12_0)
DirectX
11.2 (11_0)
4.6
OpenGL
4.4
2.1
OpenCL
1.2
1.3
Vulkan
N/A
6.7
Shader Model
5.0
