NVIDIA GeForce GTX 670M versus NVIDIA GeForce GTX 675M

Comparaison des cartes vidéo NVIDIA GeForce GTX 670M and NVIDIA GeForce GTX 675M pour tous les caractéristiques connus dans les catégories suivants: Essentiel, Infos techniques, Sorties et ports de vidéo, Compatibilité, dimensions et exigences, Soutien API, Mémoire, Technologies. Analyse du performance de référence des cartes vidéo: 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.

NVIDIA GeForce GTX 670M

versus

NVIDIA GeForce GTX 675M

Différences

Raisons pour considerer le NVIDIA GeForce GTX 670M

Environ 33% consummation d’énergie moyen plus bas: 75 Watt versus 100 Watt
Environ 2% meilleur performance en Geekbench - OpenCL: 6497 versus 6362
Environ 6% meilleur performance en CompuBench 1.5 Desktop - Video Composition (Frames/s): 35.916 versus 33.983
Environ 3% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Frames): 2731 versus 2649
Environ 3% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Fps): 2731 versus 2649

Caractéristiques
Thermal Design Power (TDP)	75 Watt versus 100 Watt
Référence
Geekbench - OpenCL	6497 versus 6362
CompuBench 1.5 Desktop - Video Composition (Frames/s)	35.916 versus 33.983
GFXBench 4.0 - Car Chase Offscreen (Frames)	2731 versus 2649
GFXBench 4.0 - Car Chase Offscreen (Fps)	2731 versus 2649

Raisons pour considerer le NVIDIA GeForce GTX 675M

Environ 4% plus haut vitesse du noyau: 620 MHz versus 598 MHz
Environ 19% taux plus haut de remplissage de la texture: 39.7 billion / sec versus 33.5 billion / sec
Environ 14% de pipelines plus haut: 384 versus 336
Environ 18% de meilleur performance á point flottant: 952.3 gflops versus 803.7 gflops
Environ 34% plus de taille maximale de mémoire: 2 GB versus 1526 MB
Environ 10% meilleur performance en PassMark - G3D Mark: 1925 versus 1745
Environ 2% meilleur performance en PassMark - G2D Mark: 312 versus 307
Environ 47% meilleur performance en CompuBench 1.5 Desktop - Face Detection (mPixels/s): 22.12 versus 15.053
Environ 13% meilleur performance en CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 664.78 versus 588.645
Environ 16% meilleur performance en CompuBench 1.5 Desktop - T-Rex (Frames/s): 2.003 versus 1.72
Environ 12% meilleur performance en CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 59.007 versus 52.899
Environ 2% meilleur performance en GFXBench 4.0 - Manhattan (Frames): 3690 versus 3627
Environ 2% meilleur performance en GFXBench 4.0 - Manhattan (Fps): 3690 versus 3627

Caractéristiques
Vitesse du noyau	620 MHz versus 598 MHz
Taux de remplissage de la texture	39.7 billion / sec versus 33.5 billion / sec
Pipelines	384 versus 336
Performance á point flottant	952.3 gflops versus 803.7 gflops
Taille de mémore maximale	2 GB versus 1526 MB
Référence
PassMark - G3D Mark	1925 versus 1745
PassMark - G2D Mark	312 versus 307
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	22.12 versus 15.053
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	664.78 versus 588.645
CompuBench 1.5 Desktop - T-Rex (Frames/s)	2.003 versus 1.72
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	59.007 versus 52.899
GFXBench 4.0 - Manhattan (Frames)	3690 versus 3627
GFXBench 4.0 - T-Rex (Frames)	3347 versus 3346
GFXBench 4.0 - Manhattan (Fps)	3690 versus 3627
GFXBench 4.0 - T-Rex (Fps)	3347 versus 3346

Comparer les références

GPU 1: NVIDIA GeForce GTX 670M
GPU 2: NVIDIA GeForce GTX 675M

PassMark - G3D Mark

GPU 1

GPU 2

1745

1925

PassMark - G2D Mark

GPU 1

GPU 2

307

312

Geekbench - OpenCL

GPU 1

GPU 2

6497

6362

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

15.053

22.12

CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)

GPU 1

GPU 2

588.645

664.78

CompuBench 1.5 Desktop - T-Rex (Frames/s)

GPU 1

GPU 2

1.72

2.003

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

35.916

33.983

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

52.899

59.007

GFXBench 4.0 - Car Chase Offscreen (Frames)

GPU 1

GPU 2

2731

2649

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

3627

3690

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

3346

3347

GFXBench 4.0 - Car Chase Offscreen (Fps)

GPU 1

GPU 2

2731

2649

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

3627

3690

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

3346

3347

Nom	NVIDIA GeForce GTX 670M	NVIDIA GeForce GTX 675M
PassMark - G3D Mark	1745	1925
PassMark - G2D Mark	307	312
Geekbench - OpenCL	6497	6362
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	15.053	22.12
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	588.645	664.78
CompuBench 1.5 Desktop - T-Rex (Frames/s)	1.72	2.003
CompuBench 1.5 Desktop - Video Composition (Frames/s)	35.916	33.983
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	52.899	59.007
GFXBench 4.0 - Car Chase Offscreen (Frames)	2731	2649
GFXBench 4.0 - Manhattan (Frames)	3627	3690
GFXBench 4.0 - T-Rex (Frames)	3346	3347
GFXBench 4.0 - Car Chase Offscreen (Fps)	2731	2649
GFXBench 4.0 - Manhattan (Fps)	3627	3690
GFXBench 4.0 - T-Rex (Fps)	3346	3347
3DMark Fire Strike - Graphics Score	2062

Comparer les caractéristiques

	NVIDIA GeForce GTX 670M	NVIDIA GeForce GTX 675M
Essentiel
Architecture	Fermi 2.0	Fermi 2.0
Nom de code	GF114	GF114
Date de sortie	22 March 2012	22 March 2012
Position dans l’évaluation de la performance	928	929
Genre	Laptop	Laptop
Infos techniques
Vitesse du noyau	598 MHz	620 MHz
Noyaux CUDA	336	384
Performance á point flottant	803.7 gflops	952.3 gflops
Processus de fabrication	40 nm	40 nm
Pipelines	336	384
Taux de remplissage de la texture	33.5 billion / sec	39.7 billion / sec
Thermal Design Power (TDP)	75 Watt	100 Watt
Compte de transistor	1,950 million	1,950 million
Sorties et ports de vidéo
Connecteurs d’écran	No outputs	No outputs
HDCP
HDMI
Résolution VGA maximale	Up to 2048x1536	Up to 2048x1536
Compatibilité, dimensions et exigences
Soutien de bus	PCI Express 2.0	PCI Express 2.0
Interface	MXM-B (3.0)	MXM-B (3.0)
Taille du laptop	large	large
Options SLI	2-way	2-way
Soutien API
DirectX	12 API	12 API
OpenCL	1.1	1.1
OpenGL	4.5	4.5
Mémoire
RAM maximale	1526 MB	2 GB
Bande passante de la mémoire	72.0 GB / s	96.0 GB / s
Largeur du bus mémoire	192bit	256bit
Vitesse de mémoire	1500 MHz	1500 MHz
Genre de mémoire	GDDR5	GDDR5
Mémoire partagé	0	0
Technologies
3D Vision
3D Vision / 3DTV Play
Adaptive VSync
CUDA
FXAA
SLI
DirectX 11		DirectX 11