NVIDIA GeForce 9600 GSO vs AMD Radeon HD 6870
We compared two Desktop platform GPUs: 384MB VRAM GeForce 9600 GSO and 1024MB VRAM Radeon HD 6870 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce 9600 GSO 's Advantages
Lower TDP (84W vs 151W)
AMD Radeon HD 6870 's Advantages
Released 2 years and 6 months late
More VRAM (1024GB vs 384GB)
Larger VRAM bandwidth (134.4GB/s vs 38.40GB/s)
1024 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce 9600 GSO
0.264 TFLOPS
Radeon HD 6870
+663%
2.016 TFLOPS
Graphics Card
Apr 2008
Release Date
Oct 2010
GeForce 9
Generation
Northern Islands
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
-
-
-
-
-
-
800 MHz
Memory Clock
1050 MHz
Memory
384MB
Memory Size
1024MB
GDDR3
Memory Type
GDDR5
192bit
Memory Bus
256bit
38.40GB/s
Bandwidth
134.4GB/s
Render Config
-
Compute Units
14
12
SM Count
-
96
Shading Units
1120
48
TMUs
56
12
ROPs
32
-
-
-
-
-
-
-
L1 Cache
8 KB (per CU)
48 KB
L2 Cache
512 KB
-
-
-
Theoretical Performance
6.600 GPixel/s
Pixel Rate
28.80 GPixel/s
26.40 GTexel/s
Texture Rate
50.40 GTexel/s
-
-
-
264.0 GFLOPS
FP32 (float)
2.016 TFLOPS
-
-
-
Board Design
84W
TDP
151W
250 W
Suggested PSU
450 W
2x DVI
1x S-Video
Outputs
2x DVI
1x HDMI 1.3a
2x mini-DisplayPort 1.1
1x 6-pin
Power Connectors
2x 6-pin
Graphics Processor
G92
GPU Name
Barts
-
GPU Variant
Barts XT
(215-0798000)
Tesla
Architecture
TeraScale 2
TSMC
Foundry
TSMC
65 nm
Process Size
40 nm
0.754 billion
Transistors
1.7 billion
324 mm²
Die Size
255 mm²
Graphics Features
11.1 (10_0)
DirectX
11.2 (11_0)
3.3
OpenGL
4.4
1.1
OpenCL
1.2
N/A
Vulkan
N/A
1.1
CUDA
-
4.0
Shader Model
5.0
