AMD FireStream 9170 vs NVIDIA GeForce GT 620
We compared two Desktop platform GPUs: 2GB VRAM FireStream 9170 and 1024MB VRAM GeForce GT 620 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD FireStream 9170 's Advantages
More VRAM (2GB vs 1024GB)
Larger VRAM bandwidth (51.33GB/s vs 14.40GB/s)
224 additional rendering cores
NVIDIA GeForce GT 620 's Advantages
Released 4 years and 6 months late
Lower TDP (49W vs 105W)
Score
Benchmark
FP32 (float)
FireStream 9170
+84%
0.497 TFLOPS
GeForce GT 620
0.269 TFLOPS
Graphics Card
Nov 2007
Release Date
May 2012
FireStream
Generation
GeForce 600
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
-
-
-
-
-
-
802 MHz
Memory Clock
900 MHz
Memory
2GB
Memory Size
1024MB
GDDR3
Memory Type
DDR3
256bit
Memory Bus
64bit
51.33GB/s
Bandwidth
14.40GB/s
Render Config
4
Compute Units
-
-
SM Count
2
320
Shading Units
96
16
TMUs
16
16
ROPs
4
-
-
-
-
-
-
-
L1 Cache
64 KB (per SM)
256 KB
L2 Cache
128 KB
-
-
-
Theoretical Performance
12.43 GPixel/s
Pixel Rate
2.800 GPixel/s
12.43 GTexel/s
Texture Rate
11.20 GTexel/s
-
-
-
497.3 GFLOPS
FP32 (float)
268.8 GFLOPS
99.46 GFLOPS
FP64 (double)
22.40 GFLOPS
Board Design
105W
TDP
49W
300 W
Suggested PSU
200 W
2x DVI
1x S-Video
Outputs
1x DVI
1x HDMI 1.3a
1x VGA
1x 6-pin
Power Connectors
None
Graphics Processor
RV670
GPU Name
GF108
-
GPU Variant
GF108-100-KB-A1
TeraScale
Architecture
Fermi
TSMC
Foundry
TSMC
55 nm
Process Size
40 nm
0.666 billion
Transistors
0.585 billion
192 mm²
Die Size
116 mm²
Graphics Features
10.1 (10_1)
DirectX
12 (11_0)
3.3 (full)
4.0 (partial)
OpenGL
4.6
N/A
OpenCL
1.1
N/A
Vulkan
N/A
-
CUDA
2.1
4.1
Shader Model
5.1
