NVIDIA GeForce GTX 260 vs ATI Radeon HD 3870

Comparative analysis of NVIDIA GeForce GTX 260 and ATI Radeon HD 3870 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory, Technologies. Benchmark videocards performance analysis: PassMark - G3D Mark, PassMark - G2D Mark, Geekbench - OpenCL, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps).

 

Differences

Reasons to consider the NVIDIA GeForce GTX 260

  • Videocard is newer: launch date 6 month(s) later
  • Around 60% higher core clock speed: 1242 MHz vs 777 MHz
  • 3x more texture fill rate: 36.9 billion / sec vs 12.43 GTexel / s
  • Around 75% higher maximum memory size: 896 MB vs 512 MB
  • 2.2x better performance in PassMark - G3D Mark: 1224 vs 555
  • Around 2% better performance in PassMark - G2D Mark: 59 vs 58
  • Around 7% better performance in GFXBench 4.0 - T-Rex (Frames): 3342 vs 3131
  • Around 7% better performance in GFXBench 4.0 - T-Rex (Fps): 3342 vs 3131
Specifications (specs)
Launch date 16 June 2008 vs 19 November 2007
Core clock speed 1242 MHz vs 777 MHz
Texture fill rate 36.9 billion / sec vs 12.43 GTexel / s
Maximum memory size 896 MB vs 512 MB
Benchmarks
PassMark - G3D Mark 1224 vs 555
PassMark - G2D Mark 59 vs 58
GFXBench 4.0 - T-Rex (Frames) 3342 vs 3131
GFXBench 4.0 - T-Rex (Fps) 3342 vs 3131

Reasons to consider the ATI Radeon HD 3870

  • Around 67% higher pipelines: 320 vs 192
  • Around 4% better floating-point performance: 497.3 gflops vs 476.9 gflops
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 55 nm vs 65 nm
  • Around 72% lower typical power consumption: 106 Watt vs 182 Watt
  • 2.3x more memory clock speed: 2252 MHz vs 999 MHz
Pipelines 320 vs 192
Floating-point performance 497.3 gflops vs 476.9 gflops
Manufacturing process technology 55 nm vs 65 nm
Thermal Design Power (TDP) 106 Watt vs 182 Watt
Memory clock speed 2252 MHz vs 999 MHz

Compare benchmarks

GPU 1: NVIDIA GeForce GTX 260
GPU 2: ATI Radeon HD 3870

PassMark - G3D Mark
GPU 1
GPU 2
1224
555
PassMark - G2D Mark
GPU 1
GPU 2
59
58
GFXBench 4.0 - T-Rex (Frames)
GPU 1
GPU 2
3342
3131
GFXBench 4.0 - T-Rex (Fps)
GPU 1
GPU 2
3342
3131
Name NVIDIA GeForce GTX 260 ATI Radeon HD 3870
PassMark - G3D Mark 1224 555
PassMark - G2D Mark 59 58
Geekbench - OpenCL 19512
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 8.664
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 477.327
CompuBench 1.5 Desktop - Video Composition (Frames/s) 24.906
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 29.525
GFXBench 4.0 - T-Rex (Frames) 3342 3131
GFXBench 4.0 - T-Rex (Fps) 3342 3131

Compare specifications (specs)

NVIDIA GeForce GTX 260 ATI Radeon HD 3870

Essentials

Architecture Tesla 2.0 TeraScale
Code name GT200 RV670
Launch date 16 June 2008 19 November 2007
Launch price (MSRP) $449 $269
Place in performance rating 1386 1388
Price now $95.38
Type Desktop Desktop
Value for money (0-100) 13.70

Technical info

Core clock speed 1242 MHz 777 MHz
CUDA cores 192
Floating-point performance 476.9 gflops 497.3 gflops
Manufacturing process technology 65 nm 55 nm
Maximum GPU temperature 105 °C
Pipelines 192 320
Texture fill rate 36.9 billion / sec 12.43 GTexel / s
Thermal Design Power (TDP) 182 Watt 106 Watt
Transistor count 1,400 million 666 million

Video outputs and ports

Audio input for HDMI S / PDIF
Display Connectors 2x DVI, 1x S-Video, Dual Link DVIHDTV 2x DVI, 1x S-Video
HDMI
Maximum VGA resolution 2048x1536
Multi monitor support

Compatibility, dimensions and requirements

Height 4.376" (111 mm) (11.1 cm)
Interface PCIe 2.0 x16 PCIe 2.0 x16
Length 10.5" (267 mm) (26.7 cm) 241 mm
SLI options 2-way3-way
Supplementary power connectors 2x 6-pin 1x 6-pin

API support

DirectX 10.0 10.0
OpenGL 2.1 3.3

Memory

Maximum RAM amount 896 MB 512 MB
Memory bandwidth 111.9 GB / s 72.1 GB / s
Memory bus width 448 Bit 256 Bit
Memory clock speed 999 MHz 2252 MHz
Memory type GDDR3 GDDR4

Technologies

3D Vision
CUDA
SLI