Radeon Pro Duo Polaris vs GeForce 8800 Ultra
We compared two Desktop platform GPUs: 16GB VRAM Radeon Pro Duo Polaris and 768MB VRAM GeForce 8800 Ultra to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon Pro Duo Polaris 's Advantages
Released 9 years and 11 months late
More VRAM (16GB vs 768GB)
Larger VRAM bandwidth (224.0GB/s vs 103.7GB/s)
2176 additional rendering cores
GeForce 8800 Ultra 's Advantages
Lower TDP (171W vs 250W)
Score
Benchmark
FP32 (float)
Radeon Pro Duo Polaris
+1380%
5728
GeForce 8800 Ultra
387
Graphics Card
Apr 2017
Release Date
May 2007
Radeon Pro GCN
Generation
GeForce 8
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 1.0 x16
Clock Speeds
1750 MHz
Memory Clock
1080 MHz
Memory
16GB
Memory Size
768MB
GDDR5
Memory Type
GDDR3
256bit
Memory Bus
384bit
224.0GB/s
Bandwidth
103.7GB/s
Render Config
36
Compute Units
-
-
SM Count
16
2304
Shading Units
128
144
TMUs
32
32
ROPs
24
16 KB (per CU)
L1 Cache
-
2 MB
L2 Cache
96 KB
Theoretical Performance
39.78 GPixel/s
Pixel Rate
14.69 GPixel/s
179.0 GTexel/s
Texture Rate
39.17 GTexel/s
5.728 TFLOPS
FP16 (half)
-
5.728 TFLOPS
FP32 (float)
387.1 GFLOPS
358.0 GFLOPS
FP64 (double)
-
Board Design
250W
TDP
171W
600 W
Suggested PSU
450 W
1x HDMI 2.0b
3x DisplayPort 1.4a
Outputs
2x DVI
1x S-Video
1x 6-pin + 1x 8-pin
Power Connectors
2x 6-pin
Graphics Processor
Ellesmere
GPU Name
G80
Ellesmere Gemini GL
GPU Variant
G80-450-A3
GCN 4.0
Architecture
Tesla
GlobalFoundries
Foundry
TSMC
14 nm
Process Size
90 nm
5.7 billion
Transistors
0.681 billion
232 mm²
Die Size
484 mm²
Graphics Features
12 (12_0)
DirectX
11.1 (10_0)
4.6
OpenGL
3.3
2.1
OpenCL
1.1 (1.0)
1.3
Vulkan
N/A
-
CUDA
1.0
6.7
Shader Model
4.0
