NVIDIA GeForce GTX 580M vs AMD Radeon HD 6870M
NVIDIA GeForce GTX 580M
AMD Radeon HD 6870M
|
384 Shaders
2GB GDDR5
620MHz
|
800 Shaders
1GB GDDR5
675MHz
|
|
Peak AI Performance
0.95 TOPS
INT32
|
Peak AI Performance
1.08 TFLOPS
FP32
|
|
FP32
950 GFLOPS
|
FP32
1.08 TFLOPS
|
|
Form Factor
Soldered
|
Form Factor
Soldered
|
|
TDP
100W
|
TDP
50W
|
Peak AI Performance
|
|
GeForce GTX 580M - 0.95 TOPS INT32
x1
Radeon HD 6870M - 1.08 TFLOPS FP32
x1.14
FP32
|
|
GeForce GTX 580M - 950 GFLOPS FP32
x1
Radeon HD 6870M - 1.08 TFLOPS FP32
x1.14
|
|
GeForce GTX 580M - 96GB/s
x1.5
Radeon HD 6870M - 64GB/s
x1
|
|
GeForce GTX 580M - 100W
x2
Radeon HD 6870M - 50W
x1
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
Manufacturer
NVIDIA
|
Manufacturer
AMD
|
|
Chip Designer
NVIDIA
|
Chip Designer
AMD
|
|
Architecture
Fermi
|
Architecture
TeraScale 2
|
|
Family
GeForce 500
|
Family
Radeon HD 6000
|
|
Codename
NVCE
GF114
-
-
|
Codename
Juniper
RV840
Variant
Granville XT
|
|
Market Segment
Laptop
|
Market Segment
Laptop
|
|
Release Date
6/28/2011
|
Release Date
1/4/2011
|
|
Foundry
TSMC
|
Foundry
TSMC
|
|
Fabrication Node
40nm
|
Fabrication Node
40nm
|
|
Die Size
1950 mm²
|
Die Size
166 mm²
|
|
Transistor Count
332 Million
|
Transistor Count
1 Billion
|
|
Transistor Density
0.17M/mm²
|
Transistor Density
6.27M/mm²
|
|
Form
Soldered
|
Form
Soldered
|
|
Shading Units
384 Shaders
|
Shading Units
800 Shaders
|
|
Texture Mapping Units
64 TMUs
|
Texture Mapping Units
40 TMUs
|
|
Render Output Units
32 ROPs
|
Render Output Units
16 ROPs
|
|
Streaming Multiprocessors
8 SMs
|
-
-
|
|
-
-
|
Compute Units
10 CUs
|
|
1240MHz Shader
620MHz
|
-
675MHz
|
|
Peak AI Performance
0.95 TOPS
INT32
|
Peak AI Performance
1.08 TFLOPS
FP32
|
|
FP32
950 GFLOPS
|
FP32
1.08 TFLOPS
|
|
FP64
80 GFLOPS
|
-
-
|
|
INT32
0.95 TOPS
|
-
-
|
|
Pixel Fillrate
19.84 GPixel/s
|
Pixel Fillrate
10.8 GPixel/s
|
|
Texture Fillrate
39.68 GTexel/s
|
Texture Fillrate
27 GTexel/s
|
|
L1
64KB/SM
-
|
L1
-
8KB/CU
|
|
L2
512KB Shared
|
L2
256KB Shared
|
|
2GB
GDDR5
|
1GB
GDDR5
|
|
Bus Width
256Bit
|
Bus Width
128Bit
|
|
Clock
750MHz
Transfer Rate
3GT/s
Bandwidth
96GB/s
|
Clock
1000MHz
Transfer Rate
4GT/s
Bandwidth
64GB/s
|
|
TDP
100W
|
TDP
50W
|
|
Max Resolution
2560x1600
|
Max Resolution
2560x1600
|
|
Max Resolution Refresh Rate
60Hz
|
Max Resolution Refresh Rate
60Hz
|
|
Variable Refresh Rate
|
Variable Refresh Rate
|
|
Display Stream Compression (DSC)
Not Supported
|
Display Stream Compression (DSC)
Not Supported
|
|
Multi Monitor Support
2
|
Multi Monitor Support
2
|
|
No Encoders
|
No Encoders
|
|
No Decoders
|
Model
UVD 2.2
|
|
-
-
|
Codec
VC-1
AVC (H.264)
|
|
Direct X
12
Direct 3D
11_0
|
Direct X
11
Direct 3D
11_0
|
|
OpenGL
4.6
OpenCL
1.1
|
OpenGL
4.5
OpenCL
1.2
|
|
Shader Model
5.1
CUDA
2.1
-
-
PureVideo HD
VP4
VDPAU
Feature Set C
|
Shader Model
5.0
-
-
GFX
4
-
-
-
-
|
|
Not a Card
|
Not a Card
|
|
PCIe Version
2.0
PCIe Lanes
16
|
PCIe Version
2.1
PCIe Lanes
16
|
Copy Link