ATI Radeon HD 5470 vs NVIDIA GeForce GTS 450

Comparative analysis of ATI Radeon HD 5470 and NVIDIA GeForce GTS 450 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, GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps), Geekbench - OpenCL, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), 3DMark Fire Strike - Graphics Score.

 

Differences

Reasons to consider the ATI Radeon HD 5470

  • Videocard is newer: launch date 1 year(s) 5 month(s) later
  • 5.6x lower typical power consumption: 19 Watt vs 106 Watt
Launch date 13 February 2012 vs 13 September 2010
Thermal Design Power (TDP) 19 Watt vs 106 Watt

Reasons to consider the NVIDIA GeForce GTS 450

  • 2.4x more core clock speed: 1566 MHz vs 650 MHz
  • 4.8x more texture fill rate: 25.1 billion / sec vs 5.2 GTexel / s
  • 2.4x more pipelines: 192 vs 80
  • 5.8x better floating-point performance: 601.3 gflops vs 104.0 gflops
  • 2x more maximum memory size: 1 GB vs 512 MB
  • 2.3x more memory clock speed: 1804 (3608 data rate) MHz vs 800 MHz
  • 4.9x better performance in PassMark - G3D Mark: 1323 vs 268
  • Around 2% better performance in PassMark - G2D Mark: 303 vs 298
  • 3.5x better performance in GFXBench 4.0 - Manhattan (Frames): 3365 vs 960
  • 3.5x better performance in GFXBench 4.0 - Manhattan (Fps): 3365 vs 960
  • Around 88% better performance in GFXBench 4.0 - T-Rex (Frames): 3325 vs 1771
  • Around 88% better performance in GFXBench 4.0 - T-Rex (Fps): 3325 vs 1771
Specifications (specs)
Core clock speed 1566 MHz vs 650 MHz
Texture fill rate 25.1 billion / sec vs 5.2 GTexel / s
Pipelines 192 vs 80
Floating-point performance 601.3 gflops vs 104.0 gflops
Maximum memory size 1 GB vs 512 MB
Memory clock speed 1804 (3608 data rate) MHz vs 800 MHz
Benchmarks
PassMark - G3D Mark 1323 vs 268
PassMark - G2D Mark 303 vs 298
GFXBench 4.0 - Manhattan (Frames) 3365 vs 960
GFXBench 4.0 - Manhattan (Fps) 3365 vs 960
GFXBench 4.0 - T-Rex (Frames) 3325 vs 1771
GFXBench 4.0 - T-Rex (Fps) 3325 vs 1771

Compare benchmarks

GPU 1: ATI Radeon HD 5470
GPU 2: NVIDIA GeForce GTS 450

PassMark - G3D Mark
GPU 1
GPU 2
268
1323
PassMark - G2D Mark
GPU 1
GPU 2
298
303
GFXBench 4.0 - Manhattan (Frames)
GPU 1
GPU 2
960
3365
GFXBench 4.0 - Manhattan (Fps)
GPU 1
GPU 2
960
3365
GFXBench 4.0 - T-Rex (Frames)
GPU 1
GPU 2
1771
3325
GFXBench 4.0 - T-Rex (Fps)
GPU 1
GPU 2
1771
3325
Name ATI Radeon HD 5470 NVIDIA GeForce GTS 450
PassMark - G3D Mark 268 1323
PassMark - G2D Mark 298 303
GFXBench 4.0 - Manhattan (Frames) 960 3365
GFXBench 4.0 - Manhattan (Fps) 960 3365
GFXBench 4.0 - T-Rex (Frames) 1771 3325
GFXBench 4.0 - T-Rex (Fps) 1771 3325
Geekbench - OpenCL 4923
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 14.758
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 302.509
CompuBench 1.5 Desktop - T-Rex (Frames/s) 0.965
CompuBench 1.5 Desktop - Video Composition (Frames/s) 14.925
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 27.656
GFXBench 4.0 - Car Chase Offscreen (Frames) 2160
GFXBench 4.0 - Car Chase Offscreen (Fps) 2160
3DMark Fire Strike - Graphics Score 0

Compare specifications (specs)

ATI Radeon HD 5470 NVIDIA GeForce GTS 450

Essentials

Architecture TeraScale 2 Fermi
Code name Cedar GF106
Launch date 13 February 2012 13 September 2010
Place in performance rating 1077 1137
Type Desktop Desktop
Launch price (MSRP) $129
Price now $64.99
Value for money (0-100) 26.46

Technical info

Core clock speed 650 MHz 1566 MHz
Floating-point performance 104.0 gflops 601.3 gflops
Manufacturing process technology 40 nm 40 nm
Pipelines 80 192
Texture fill rate 5.2 GTexel / s 25.1 billion / sec
Thermal Design Power (TDP) 19 Watt 106 Watt
Transistor count 292 million 1,170 million
CUDA cores 192
Maximum GPU temperature 100 °C

Video outputs and ports

Display Connectors 1x DVI, 1x HDMI, 1x VGA 2x DVI, 1x mini-HDMI, Mini HDMITwo Dual Link DVI
Audio input for HDMI Internal
HDMI
Maximum VGA resolution 2048x1536

Compatibility, dimensions and requirements

Interface PCIe 2.0 x16 PCIe 2.0 x16
Length 170 mm 8.25" (210 mm) (21 cm)
Supplementary power connectors None 6-pin
Bus support PCI-E 2.0 x 16
Height 4.376" (111 mm) (11.1 cm)
SLI options 2-way

API support

DirectX 11.2 (11_0) 12.0 (11_0)
OpenGL 4.4 4.2

Memory

Maximum RAM amount 512 MB 1 GB
Memory bandwidth 6.4 GB / s 57.7 GB / s
Memory bus width 64 Bit 128 Bit
Memory clock speed 800 MHz 1804 (3608 data rate) MHz
Memory type GDDR3 GDDR5

Technologies

3D Vision
CUDA
DSR
SLI