NVIDIA Tesla K10 versus NVIDIA GeForce GTX 670M
Comparaison des cartes vidéo NVIDIA Tesla K10 and NVIDIA GeForce GTX 670M 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: 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), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps), PassMark - G3D Mark, PassMark - G2D Mark, 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.
Différences
Raisons pour considerer le NVIDIA Tesla K10
- La carte vidéo est plus nouvelle: date de sortie 1 mois plus tard
- Environ 25% plus haut vitesse du noyau: 745 MHz versus 598 MHz
- times}x plus de taux de remplissage de la texture: 2x 95.36 GTexel / s billion / sec versus 33.5 billion / sec
- 9.1x plus de pipelines: 2x 1536 versus 336
- 5.7x de meilleur performance á point flottant: 2x 2,289 gflops versus 803.7 gflops
- Un nouveau processus de fabrication soutient une carte vidéo plus forte, mais moins chaude: 28 nm versus 40 nm
- 5.4x plus de taille maximale de mémoire : 2x 4 GB versus 1526 MB
- 3.3x plus de vitesse de mémoire: 5000 MHz versus 1500 MHz
- 2.2x meilleur performance en Geekbench - OpenCL: 14029 versus 6357
- 2.7x meilleur performance en CompuBench 1.5 Desktop - Face Detection (mPixels/s): 40.736 versus 15.053
- Environ 66% meilleur performance en CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 975.508 versus 588.645
- Environ 97% meilleur performance en CompuBench 1.5 Desktop - T-Rex (Frames/s): 3.39 versus 1.72
Caractéristiques | |
Date de sortie | 1 May 2012 versus 22 March 2012 |
Vitesse du noyau | 745 MHz versus 598 MHz |
Taux de remplissage de la texture | 2x 95.36 GTexel / s billion / sec versus 33.5 billion / sec |
Pipelines | 2x 1536 versus 336 |
Performance á point flottant | 2x 2,289 gflops versus 803.7 gflops |
Processus de fabrication | 28 nm versus 40 nm |
Taille de mémore maximale | 2x 4 GB versus 1526 MB |
Vitesse de mémoire | 5000 MHz versus 1500 MHz |
Référence | |
Geekbench - OpenCL | 14029 versus 6357 |
CompuBench 1.5 Desktop - Face Detection (mPixels/s) | 40.736 versus 15.053 |
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) | 975.508 versus 588.645 |
CompuBench 1.5 Desktop - T-Rex (Frames/s) | 3.39 versus 1.72 |
GFXBench 4.0 - Manhattan (Frames) | 3632 versus 3627 |
GFXBench 4.0 - Manhattan (Fps) | 3632 versus 3627 |
GFXBench 4.0 - T-Rex (Frames) | 3353 versus 3346 |
GFXBench 4.0 - T-Rex (Fps) | 3353 versus 3346 |
Raisons pour considerer le NVIDIA GeForce GTX 670M
- 3x consummation d’énergie moyen plus bas: 75 Watt versus 225 Watt
Thermal Design Power (TDP) | 75 Watt versus 225 Watt |
Comparer les références
GPU 1: NVIDIA Tesla K10
GPU 2: NVIDIA GeForce GTX 670M
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) |
|
|
||||
GFXBench 4.0 - Manhattan (Frames) |
|
|
||||
GFXBench 4.0 - Manhattan (Fps) |
|
|
||||
GFXBench 4.0 - T-Rex (Frames) |
|
|
||||
GFXBench 4.0 - T-Rex (Fps) |
|
|
Nom | NVIDIA Tesla K10 | NVIDIA GeForce GTX 670M |
---|---|---|
Geekbench - OpenCL | 14029 | 6357 |
CompuBench 1.5 Desktop - Face Detection (mPixels/s) | 40.736 | 15.053 |
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) | 975.508 | 588.645 |
CompuBench 1.5 Desktop - T-Rex (Frames/s) | 3.39 | 1.72 |
GFXBench 4.0 - Manhattan (Frames) | 3632 | 3627 |
GFXBench 4.0 - Manhattan (Fps) | 3632 | 3627 |
GFXBench 4.0 - T-Rex (Frames) | 3353 | 3346 |
GFXBench 4.0 - T-Rex (Fps) | 3353 | 3346 |
PassMark - G3D Mark | 1746 | |
PassMark - G2D Mark | 303 | |
CompuBench 1.5 Desktop - Video Composition (Frames/s) | 35.916 | |
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) | 52.899 | |
GFXBench 4.0 - Car Chase Offscreen (Frames) | 2731 | |
GFXBench 4.0 - Car Chase Offscreen (Fps) | 2731 | |
3DMark Fire Strike - Graphics Score | 2062 |
Comparer les caractéristiques
NVIDIA Tesla K10 | NVIDIA GeForce GTX 670M | |
---|---|---|
Essentiel |
||
Architecture | Kepler | Fermi 2.0 |
Nom de code | GK104 | GF114 |
Date de sortie | 1 May 2012 | 22 March 2012 |
Prix de sortie (MSRP) | $5,099 | |
Position dans l’évaluation de la performance | 979 | 980 |
Genre | Workstation | Laptop |
Infos techniques |
||
Vitesse du noyau | 745 MHz | 598 MHz |
Performance á point flottant | 2x 2,289 gflops | 803.7 gflops |
Processus de fabrication | 28 nm | 40 nm |
Pipelines | 2x 1536 | 336 |
Taux de remplissage de la texture | 2x 95.36 GTexel / s billion / sec | 33.5 billion / sec |
Thermal Design Power (TDP) | 225 Watt | 75 Watt |
Compte de transistor | 3,540 million | 1,950 million |
Noyaux CUDA | 336 | |
Sorties et ports de vidéo |
||
Connecteurs d’écran | No outputs | No outputs |
HDCP | ||
HDMI | ||
Résolution VGA maximale | Up to 2048x1536 | |
Compatibilité, dimensions et exigences |
||
Interface | PCIe 3.0 x16 | MXM-B (3.0) |
Longeur | 272 mm | |
Connecteurs d’énergie supplementaires | 1x 6-pin + 1x 8-pin | |
Soutien de bus | PCI Express 2.0 | |
Taille du laptop | large | |
Options SLI | 2-way | |
Soutien API |
||
DirectX | 12.0 (11_0) | 12 API |
OpenGL | 4.6 | 4.5 |
OpenCL | 1.1 | |
Mémoire |
||
RAM maximale | 2x 4 GB | 1526 MB |
Bande passante de la mémoire | 2x 160.0 GB / s | 72.0 GB / s |
Largeur du bus mémoire | 2x 256 Bit | 192bit |
Vitesse de mémoire | 5000 MHz | 1500 MHz |
Genre de mémoire | GDDR5 | GDDR5 |
Mémoire partagé | 0 | |
Technologies |
||
3D Vision | ||
3D Vision / 3DTV Play | ||
Adaptive VSync | ||
CUDA | ||
FXAA | ||
SLI |