AMD Radeon HD 8970M vs NVIDIA GeForce GTX 670

Comparative analysis of AMD Radeon HD 8970M and NVIDIA GeForce GTX 670 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 - 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 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps), 3DMark Fire Strike - Graphics Score.

 

Differences

Reasons to consider the AMD Radeon HD 8970M

  • Videocard is newer: launch date 1 year(s) 0 month(s) later
  • Around 70% lower typical power consumption: 100 Watt vs 170 Watt
  • 2x more maximum memory size: 4 GB vs 2 GB
  • 800x more memory clock speed: 4800 MHz vs 6.0 GB/s
  • Around 50% better performance in PassMark - G2D Mark: 807 vs 537
  • Around 35% better performance in Geekbench - OpenCL: 20899 vs 15511
  • Around 38% better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 57.241 vs 41.613
  • Around 26% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 1223.742 vs 971.208
  • Around 35% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 5.78 vs 4.281
  • 2.2x better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 89.306 vs 40.404
  • 3.1x better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 268.643 vs 86.208
Specifications (specs)
Launch date 14 May 2013 vs 10 May 2012
Thermal Design Power (TDP) 100 Watt vs 170 Watt
Maximum memory size 4 GB vs 2 GB
Memory clock speed 4800 MHz vs 6.0 GB/s
Benchmarks
PassMark - G2D Mark 807 vs 537
Geekbench - OpenCL 20899 vs 15511
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 57.241 vs 41.613
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 1223.742 vs 971.208
CompuBench 1.5 Desktop - T-Rex (Frames/s) 5.78 vs 4.281
CompuBench 1.5 Desktop - Video Composition (Frames/s) 89.306 vs 40.404
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 268.643 vs 86.208
GFXBench 4.0 - Manhattan (Frames) 3688 vs 3686
GFXBench 4.0 - Manhattan (Fps) 3688 vs 3686

Reasons to consider the NVIDIA GeForce GTX 670

  • Around 15% higher core clock speed: 980 MHz vs 850 MHz
  • Around 15% higher boost clock speed: 980 MHz vs 850 MHz
  • Around 42% higher texture fill rate: 102.5 billion / sec vs 72 GTexel / s
  • Around 5% higher pipelines: 1344 vs 1280
  • Around 7% better floating-point performance: 2,459.5 gflops vs 2,304 gflops
  • Around 38% better performance in PassMark - G3D Mark: 5345 vs 3876
  • 2.8x better performance in GFXBench 4.0 - Car Chase Offscreen (Frames): 7038 vs 2521
  • Around 30% better performance in GFXBench 4.0 - T-Rex (Frames): 3361 vs 2595
  • 2.8x better performance in GFXBench 4.0 - Car Chase Offscreen (Fps): 7038 vs 2521
  • Around 30% better performance in GFXBench 4.0 - T-Rex (Fps): 3361 vs 2595
Specifications (specs)
Core clock speed 980 MHz vs 850 MHz
Boost clock speed 980 MHz vs 850 MHz
Texture fill rate 102.5 billion / sec vs 72 GTexel / s
Pipelines 1344 vs 1280
Floating-point performance 2,459.5 gflops vs 2,304 gflops
Benchmarks
PassMark - G3D Mark 5345 vs 3876
GFXBench 4.0 - Car Chase Offscreen (Frames) 7038 vs 2521
GFXBench 4.0 - T-Rex (Frames) 3361 vs 2595
GFXBench 4.0 - Car Chase Offscreen (Fps) 7038 vs 2521
GFXBench 4.0 - T-Rex (Fps) 3361 vs 2595

Compare benchmarks

GPU 1: AMD Radeon HD 8970M
GPU 2: NVIDIA GeForce GTX 670

PassMark - G3D Mark
GPU 1
GPU 2
3876
5345
PassMark - G2D Mark
GPU 1
GPU 2
807
537
Geekbench - OpenCL
GPU 1
GPU 2
20899
15511
CompuBench 1.5 Desktop - Face Detection (mPixels/s)
GPU 1
GPU 2
57.241
41.613
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)
GPU 1
GPU 2
1223.742
971.208
CompuBench 1.5 Desktop - T-Rex (Frames/s)
GPU 1
GPU 2
5.78
4.281
CompuBench 1.5 Desktop - Video Composition (Frames/s)
GPU 1
GPU 2
89.306
40.404
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)
GPU 1
GPU 2
268.643
86.208
GFXBench 4.0 - Car Chase Offscreen (Frames)
GPU 1
GPU 2
2521
7038
GFXBench 4.0 - Manhattan (Frames)
GPU 1
GPU 2
3688
3686
GFXBench 4.0 - T-Rex (Frames)
GPU 1
GPU 2
2595
3361
GFXBench 4.0 - Car Chase Offscreen (Fps)
GPU 1
GPU 2
2521
7038
GFXBench 4.0 - Manhattan (Fps)
GPU 1
GPU 2
3688
3686
GFXBench 4.0 - T-Rex (Fps)
GPU 1
GPU 2
2595
3361
Name AMD Radeon HD 8970M NVIDIA GeForce GTX 670
PassMark - G3D Mark 3876 5345
PassMark - G2D Mark 807 537
Geekbench - OpenCL 20899 15511
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 57.241 41.613
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 1223.742 971.208
CompuBench 1.5 Desktop - T-Rex (Frames/s) 5.78 4.281
CompuBench 1.5 Desktop - Video Composition (Frames/s) 89.306 40.404
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 268.643 86.208
GFXBench 4.0 - Car Chase Offscreen (Frames) 2521 7038
GFXBench 4.0 - Manhattan (Frames) 3688 3686
GFXBench 4.0 - T-Rex (Frames) 2595 3361
GFXBench 4.0 - Car Chase Offscreen (Fps) 2521 7038
GFXBench 4.0 - Manhattan (Fps) 3688 3686
GFXBench 4.0 - T-Rex (Fps) 2595 3361
3DMark Fire Strike - Graphics Score 0 1839

Compare specifications (specs)

AMD Radeon HD 8970M NVIDIA GeForce GTX 670

Essentials

Architecture GCN 1.0 Kepler
Code name Neptune GK104
Design AMD Radeon HD 8000M Series
Launch date 14 May 2013 10 May 2012
Place in performance rating 553 554
Type Desktop Desktop
Launch price (MSRP) $399
Price now $474.99
Value for money (0-100) 13.20

Technical info

Boost clock speed 850 MHz 980 MHz
Compute units 20
Core clock speed 850 MHz 980 MHz
Floating-point performance 2,304 gflops 2,459.5 gflops
Manufacturing process technology 28 nm 28 nm
Pipelines 1280 1344
Texture fill rate 72 GTexel / s 102.5 billion / sec
Thermal Design Power (TDP) 100 Watt 170 Watt
Transistor count 2,800 million 3,540 million
CUDA cores 1344
Maximum GPU temperature 97 °C

Video outputs and ports

Display Connectors No outputs One Dual Link DVI-I, One Dual Link DVI-D, One HDMI..., 2x DVI, 1x HDMI, 1x DisplayPort
Audio input for HDMI Internal
G-SYNC support
HDCP
HDMI
Maximum VGA resolution 2048x1536
Multi monitor support

Compatibility, dimensions and requirements

Interface PCIe 3.0 x16 PCIe 3.0 x16
Laptop size large
Bus support PCI Express 3.0
Height 4.376" (11.1 cm)
Length 9.5" (24.1 cm)
SLI options 3-way
Supplementary power connectors Two 6-pin

API support

DirectX 11 12.0 (11_0)
OpenGL 4.5 4.2

Memory

Maximum RAM amount 4 GB 2 GB
Memory bandwidth 153.6 GB/s 192.2 GB / s
Memory bus width 256 Bit 256-bit GDDR5
Memory clock speed 4800 MHz 6.0 GB/s
Memory type GDDR5 GDDR5
Shared memory 0

Technologies

AMD Eyefinity
PowerTune
ZeroCore
3D Blu-Ray
3D Gaming
3D Vision
Adaptive VSync
CUDA
FXAA
GPU Boost
SLI
TXAA