GeForce 9800 GT vs Radeon RX 470
We compared two Desktop platform GPUs: 512MB VRAM GeForce 9800 GT and 4GB VRAM Radeon RX 470 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon RX 470 's Advantages
Released 8 years and 1 months late
Boost Clock1206MHz
More VRAM (4GB vs 512GB)
Larger VRAM bandwidth (211.2GB/s vs 57.60GB/s)
1936 additional rendering cores
Lower TDP (120W vs 125W)
Score
Benchmark
FP32 (float)
GeForce 9800 GT
336
Radeon RX 470
+1370%
4940
3DMark Time Spy
GeForce 9800 GT
394
Radeon RX 470
+833%
3679
Graphics Card
Jul 2008
Release Date
Aug 2016
GeForce 9
Generation
Arctic Islands
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
Base Clock
926 MHz
-
Boost Clock
1206 MHz
900 MHz
Memory Clock
1650 MHz
Memory
512MB
Memory Size
4GB
GDDR3
Memory Type
GDDR5
256bit
Memory Bus
256bit
57.60GB/s
Bandwidth
211.2GB/s
Render Config
-
Compute Units
32
14
SM Count
-
112
Shading Units
2048
56
TMUs
128
16
ROPs
32
-
L1 Cache
16 KB (per CU)
64 KB
L2 Cache
2 MB
Theoretical Performance
9.600 GPixel/s
Pixel Rate
38.59 GPixel/s
33.60 GTexel/s
Texture Rate
154.4 GTexel/s
-
FP16 (half)
4.940 TFLOPS
336.0 GFLOPS
FP32 (float)
4.940 TFLOPS
-
FP64 (double)
308.7 GFLOPS
Board Design
125W
TDP
120W
300 W
Suggested PSU
300 W
2x DVI
1x S-Video
Outputs
1x HDMI 2.0b
3x DisplayPort 1.4a
1x 6-pin
Power Connectors
1x 6-pin
Graphics Processor
G92B
GPU Name
Ellesmere
G92-280-B1
GPU Variant
Polaris 10 PRO
(215-0876204)
Tesla
Architecture
GCN 4.0
TSMC
Foundry
GlobalFoundries
55 nm
Process Size
14 nm
0.754 billion
Transistors
5.7 billion
260 mm²
Die Size
232 mm²
Graphics Features
11.1 (10_0)
DirectX
12 (12_0)
3.3
OpenGL
4.6
1.1
OpenCL
2.1
N/A
Vulkan
1.2
1.1
CUDA
-
4.0
Shader Model
6.4