Home GPU Comparison NVIDIA GeForce GTX 470 PhysX Edition vs ATI Radeon HD 3870 AGP

NVIDIA GeForce GTX 470 PhysX Edition vs ATI Radeon HD 3870 AGP

We compared two Desktop platform GPUs: 1280MB VRAM GeForce GTX 470 PhysX Edition and 512MB VRAM Radeon HD 3870 AGP to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce GTX 470 PhysX Edition 's Advantages
More VRAM (1280GB vs 512GB)
Larger VRAM bandwidth (133.9GB/s vs 72.06GB/s)
128 additional rendering cores
ATI Radeon HD 3870 AGP 's Advantages
Lower TDP (106W vs 215W)

Score

Benchmark

FP32 (float)
GeForce GTX 470 PhysX Edition +119%
1.089 TFLOPS
Radeon HD 3870 AGP
0.497 TFLOPS
VS

Graphics Card

Unknown
Release Date
Unknown
GeForce 400
Generation
Radeon R600
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
AGP 8x

Clock Speeds

-
-
-
-
-
-
837 MHz
Memory Clock
1126 MHz

Memory

1280MB
Memory Size
512MB
GDDR5
Memory Type
GDDR4
320bit
Memory Bus
256bit
133.9GB/s
Bandwidth
72.06GB/s

Render Config

-
Compute Units
4
14
SM Count
-
448
Shading Units
320
56
TMUs
16
40
ROPs
16
-
-
-
-
-
-
64 KB (per SM)
L1 Cache
-
640 KB
L2 Cache
256 KB
-
-
-

Theoretical Performance

17.02 GPixel/s
Pixel Rate
12.43 GPixel/s
34.05 GTexel/s
Texture Rate
12.43 GTexel/s
-
-
-
1089 GFLOPS
FP32 (float)
497.3 GFLOPS
-
FP64 (double)
99.46 GFLOPS

Board Design

215W
TDP
106W
550 W
Suggested PSU
300 W
2x DVI 1x mini-HDMI 1.3a
Outputs
2x DVI 1x S-Video
1x 6-pin + 1x 8-pin
Power Connectors
1x 8-pin

Graphics Processor

GT215
GPU Name
RV670
GT215-400-A2
GPU Variant
RV670 XT (215-0708005)
Tesla 2.0
Architecture
TeraScale
TSMC
Foundry
TSMC
40 nm
Process Size
55 nm
0.727 billion
Transistors
0.666 billion
144 mm²
Die Size
192 mm²

Graphics Features

12 (11_0)
DirectX
10.1 (10_1)
4.6
OpenGL
3.3 (full) 4.0 (partial)
1.1
OpenCL
N/A
N/A
Vulkan
N/A
2.0
CUDA
-
5.1
Shader Model
4.1

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy