GeForce 9800 GT vs Radeon HD 8670 OEM
We compared two Desktop platform GPUs: 512MB VRAM GeForce 9800 GT and 2GB VRAM Radeon HD 8670 OEM to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon HD 8670 OEM 's Advantages
Released 4 years and 6 months late
Boost Clock1050MHz
More VRAM (2GB vs 512GB)
Larger VRAM bandwidth (73.60GB/s vs 57.60GB/s)
272 additional rendering cores
Lower TDP (75W vs 125W)
Score
Benchmark
FP32 (float)
GeForce 9800 GT
336
Radeon HD 8670 OEM
+139%
806
Graphics Card
Jul 2008
Release Date
Jan 2013
GeForce 9
Generation
Sea Islands
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 3.0 x8
Clock Speeds
-
Base Clock
1000 MHz
-
Boost Clock
1050 MHz
900 MHz
Memory Clock
1150 MHz
Memory
512MB
Memory Size
2GB
GDDR3
Memory Type
GDDR5
256bit
Memory Bus
128bit
57.60GB/s
Bandwidth
73.60GB/s
Render Config
-
Compute Units
6
14
SM Count
-
112
Shading Units
384
56
TMUs
24
16
ROPs
8
-
L1 Cache
16 KB (per CU)
64 KB
L2 Cache
256 KB
Theoretical Performance
9.600 GPixel/s
Pixel Rate
8.400 GPixel/s
33.60 GTexel/s
Texture Rate
25.20 GTexel/s
336.0 GFLOPS
FP32 (float)
806.4 GFLOPS
-
FP64 (double)
50.40 GFLOPS
Board Design
125W
TDP
75W
300 W
Suggested PSU
250 W
2x DVI
1x S-Video
Outputs
1x DVI
1x HDMI 1.4a
1x VGA
1x 6-pin
Power Connectors
None
Graphics Processor
G92B
GPU Name
Oland
G92-280-B1
GPU Variant
Oland XT
(215-0837000)
Tesla
Architecture
GCN 1.0
TSMC
Foundry
TSMC
55 nm
Process Size
28 nm
0.754 billion
Transistors
0.95 billion
260 mm²
Die Size
77 mm²
Graphics Features
11.1 (10_0)
DirectX
12 (11_1)
3.3
OpenGL
4.6
1.1
OpenCL
1.2
N/A
Vulkan
1.2
1.1
CUDA
-
4.0
Shader Model
5.1