ATI Radeon HD 5870 Eyefinity 6 vs NVIDIA GeForce GTX 660
We compared two Desktop platform GPUs: 2GB VRAM Radeon HD 5870 Eyefinity 6 and 2GB VRAM GeForce GTX 660 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
ATI Radeon HD 5870 Eyefinity 6 's Advantages
Larger VRAM bandwidth (153.6GB/s vs 144.2GB/s)
640 additional rendering cores
NVIDIA GeForce GTX 660 's Advantages
Released 2 years and 6 months late
Boost Clock1032MHz
Lower TDP (140W vs 228W)
Score
Benchmark
FP32 (float)
Radeon HD 5870 Eyefinity 6
+37%
2.72 TFLOPS
GeForce GTX 660
1.981 TFLOPS
Graphics Card
Mar 2010
Release Date
Sep 2012
Evergreen
Generation
GeForce 600
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
Base Clock
980 MHz
-
Boost Clock
1032 MHz
1200 MHz
Memory Clock
1502 MHz
Memory
2GB
Memory Size
2GB
GDDR5
Memory Type
GDDR5
256bit
Memory Bus
192bit
153.6GB/s
Bandwidth
144.2GB/s
Render Config
20
Compute Units
-
-
-
-
1600
Shading Units
960
80
TMUs
80
32
ROPs
24
-
-
-
-
-
-
8 KB (per CU)
L1 Cache
16 KB (per SMX)
512 KB
L2 Cache
384 KB
-
-
-
Theoretical Performance
27.20 GPixel/s
Pixel Rate
20.64 GPixel/s
68.00 GTexel/s
Texture Rate
82.56 GTexel/s
-
-
-
2.720 TFLOPS
FP32 (float)
1.981 TFLOPS
544.0 GFLOPS
FP64 (double)
82.56 GFLOPS
Board Design
228W
TDP
140W
550 W
Suggested PSU
300 W
6x mini-DisplayPort 1.1
Outputs
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
1x 6-pin + 1x 8-pin
Power Connectors
1x 6-pin
Graphics Processor
Cypress
GPU Name
GK106
Cypress XT
(215-0735033)
GPU Variant
GK106-400-A1
TeraScale 2
Architecture
Kepler
TSMC
Foundry
TSMC
40 nm
Process Size
28 nm
2.154 billion
Transistors
2.54 billion
334 mm²
Die Size
221 mm²
Graphics Features
11.2 (11_0)
DirectX
12 (11_0)
4.4
OpenGL
4.6
1.2
OpenCL
3.0
N/A
Vulkan
1.1
-
CUDA
3.0
5.0
Shader Model
5.1
