NVIDIA GeForce GTX 260 vs ATI Radeon HD 4670

NVIDIA GeForce GTX 260 $400
ATI Radeon HD 4670 $79
192 Shaders
896MB GDDR3
576MHz
320 Shaders
512MB GDDR3
750MHz
Peak AI Performance
0.48 TOPS
INT32
Peak AI Performance
480 GFLOPS
FP32
FP32
480 GFLOPS
FP32
480 GFLOPS
Form Factor
PCIe Card
2.0-Slots
Form Factor
PCIe Card
1.0-Slots
TDP
182W
TDP
59W
Power Connectors
2x 6-Pin
-
-

Peak AI Performance

  • Same Performance vs Radeon HD 4670
  • Same Performance vs GeForce GTX 260
GeForce GTX 260 - 0.48 TOPS INT32
x1
Radeon HD 4670 - 480 GFLOPS FP32
x1

FP32

  • Same Performance vs Radeon HD 4670
  • Same Performance vs GeForce GTX 260
GeForce GTX 260 - 480 GFLOPS FP32
x1
Radeon HD 4670 - 480 GFLOPS FP32
x1
  • 6.99x faster vs Radeon HD 4670
  • 86% slower vs GeForce GTX 260
GeForce GTX 260 - 111.9GB/s
x6.99
Radeon HD 4670 - 16GB/s
x1
  • 208% higher vs Radeon HD 4670
  • 68% lower vs GeForce GTX 260
GeForce GTX 260 - 182W
x3.08
Radeon HD 4670 - 59W
x1
Manufacturer
NVIDIA
Manufacturer
ATI
Chip Designer
NVIDIA
Chip Designer
ATI
Architecture
Tesla 2
Architecture
TeraScale 1
Family
GeForce 200
Family
Radeon HD 4000
Codename
NVA0
GT200
Variant
GT200-100-A2
Codename
Mario
RV730
Variant
RV730 XT
Market Segment
Desktop
Market Segment
Desktop
Release Date
6/16/2008
Release Date
9/10/2008
Foundry
TSMC
Foundry
TSMC
Fabrication Node
65nm
Fabrication Node
55nm
Die Size
576 mm²
Die Size
146 mm²
Transistor Count
1.4 Billion
Transistor Count
514 Million
Transistor Density
2.43M/mm²
Transistor Density
3.52M/mm²
Form
PCIe Card
Form
PCIe Card
Shading Units
192 Shaders
Shading Units
320 Shaders
Texture Mapping Units
64 TMUs
Texture Mapping Units
32 TMUs
Render Output Units
28 ROPs
Render Output Units
8 ROPs
Streaming Multiprocessors
24 SMs
-
-
-
-
Compute Units
4 CUs
1242MHz Shader
576MHz
-
750MHz
Peak AI Performance
0.48 TOPS
INT32
Peak AI Performance
480 GFLOPS
FP32
FP32
480 GFLOPS
FP32
480 GFLOPS
FP64
60 GFLOPS
-
-
INT32
0.48 TOPS
-
-
Pixel Fillrate
16.128 GPixel/s
Pixel Fillrate
6 GPixel/s
Texture Fillrate
36.864 GTexel/s
Texture Fillrate
24 GTexel/s
L1
-
Unknown
L1
16KB/CU
-
L2
256KB Shared
L2
128KB Shared
896MB
GDDR3
512MB
GDDR3
Bus Width
448Bit
Bus Width
128Bit
Clock
999MHz
Transfer Rate
2GT/s
Bandwidth
111.9GB/s
Clock
500MHz
Transfer Rate
1GT/s
Bandwidth
16GB/s
TDP
182W
TDP
59W
1x S-Video
2x DVI-I Dual-Link
1x S-Video
2x DVI-I Dual-Link
Max Resolution
2560x1600
Max Resolution
2560x1600
Max Resolution Refresh Rate
60Hz
Max Resolution Refresh Rate
60Hz
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
11
Direct 3D
10_0
Direct X
10
Direct 3D
10_1
OpenGL
3.3
OpenCL
1.1
OpenGL
3.3
OpenCL
1.1
Shader Model
4.0
CUDA
1.3
-
-
PureVideo HD
VP2
VDPAU
Feature Set A
Shader Model
4.1
-
-
GFX
3
-
-
-
-
1x Fan
1x Fan
Power Connectors
2x 6-Pin
-
-
Slots Required
2.0
PCIe Version
2.0
PCIe Lanes
16
Slots Required
1.0
PCIe Version
2.0
PCIe Lanes
16
Multi GPU Support
Supported
Type
3-way SLI
Multi GPU Support
Supported
Type
2-way CrossFireX
Height
111 mm (4.37 in)
Width
267 mm (10.51 in)
Depth
38 mm (1.5 in)
-
-
-
-
-
-
Change Comparison