GeForce GTX 480 vs Radeon HD 3850 X2
We compared two Desktop platform GPUs: 1536MB VRAM GeForce GTX 480 and 512MB VRAM Radeon HD 3850 X2 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce GTX 480 Advantages
Released 1 years and 11 months late
More VRAM (1536GB vs 512GB)
Larger VRAM bandwidth (177.4GB/s vs 52.99GB/s)
160 additional rendering cores
Radeon HD 3850 X2 Advantages
Lower TDP (140W vs 250W)
Score
Benchmark
FP32 (float)
GeForce GTX 480
+214%
1345
Radeon HD 3850 X2
428
Graphics Card
Mar 2010
Release Date
Apr 2008
GeForce 400
Generation
Radeon R600
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
924 MHz
Memory Clock
828 MHz
Memory
1536MB
Memory Size
512MB
GDDR5
Memory Type
GDDR3
384bit
Memory Bus
256bit
177.4GB/s
Bandwidth
52.99GB/s
Render Config
-
Compute Units
4
15
SM Count
-
480
Shading Units
320
60
TMUs
16
48
ROPs
16
64 KB (per SM)
L1 Cache
-
768 KB
L2 Cache
256 KB
Theoretical Performance
21.03 GPixel/s
Pixel Rate
10.70 GPixel/s
42.06 GTexel/s
Texture Rate
10.70 GTexel/s
1345 GFLOPS
FP32 (float)
428.2 GFLOPS
168.1 GFLOPS
FP64 (double)
85.63 GFLOPS
Board Design
250W
TDP
140W
600 W
Suggested PSU
300 W
2x DVI
1x mini-HDMI 1.3a
1x mini-HDMI 1.3a
Outputs
2x DVI
1x S-Video
1x S-Video
1x 6-pin + 1x 8-pin
Power Connectors
-
Graphics Processor
GF100
GPU Name
RV670
GF100-375-A3
GPU Variant
RV670 PRO
(215-0708003)
(215-0708003)
Fermi
Architecture
TeraScale
TSMC
Foundry
TSMC
40 nm
Process Size
55 nm
3.1 billion
Transistors
0.666 billion
529 mm²
Die Size
192 mm²
Graphics Features
12 (11_0)
DirectX
10.1 (10_1)
4.6
OpenGL
3.3 (full)
4.0 (partial)
4.0 (partial)
1.1
OpenCL
N/A
N/A
Vulkan
N/A
2.0
CUDA
-
5.1
Shader Model
4.1