NVIDIA Tesla T4 versus NVIDIA Tesla P40
Comparaison des cartes vidéo NVIDIA Tesla T4 and NVIDIA Tesla P40 pour tous les caractéristiques connus dans les catégories suivants: Essentiel, Infos techniques, Sorties et ports de vidéo, Compatibilité, dimensions et exigences, Soutien API, Mémoire. 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).
Différences
Raisons pour considerer le NVIDIA Tesla T4
- La carte vidéo est plus nouvelle: date de sortie 2 ans 0 mois plus tard
- Un nouveau processus de fabrication soutient une carte vidéo plus forte, mais moins chaude: 12 nm versus 16 nm
- 3.3x consummation d’énergie moyen plus bas: 75 Watt versus 250 Watt
- Environ 35% meilleur performance en PassMark - G2D Mark: 592 versus 439
- Environ 48% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Frames): 14076 versus 9538
- Environ 48% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Fps): 14076 versus 9538
Caractéristiques | |
Date de sortie | 13 September 2018 versus 13 September 2016 |
Processus de fabrication | 12 nm versus 16 nm |
Thermal Design Power (TDP) | 75 Watt versus 250 Watt |
Référence | |
PassMark - G2D Mark | 592 versus 439 |
GFXBench 4.0 - Car Chase Offscreen (Frames) | 14076 versus 9538 |
GFXBench 4.0 - Car Chase Offscreen (Fps) | 14076 versus 9538 |
Raisons pour considerer le NVIDIA Tesla P40
- Environ 30% plus haut vitesse du noyau: 1303 MHz versus 1005 MHz
- Environ 1% plus de la vitesse augmenté: 1531 MHz versus 1515 MHz
- Environ 16% meilleur performance en PassMark - G3D Mark: 12267 versus 10616
- Environ 2% meilleur performance en Geekbench - OpenCL: 62287 versus 61276
- 2.4x meilleur performance en CompuBench 1.5 Desktop - Face Detection (mPixels/s): 300.355 versus 127.622
- Environ 18% meilleur performance en CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 3559.383 versus 3026.812
- Environ 5% meilleur performance en CompuBench 1.5 Desktop - T-Rex (Frames/s): 19.757 versus 18.798
- Environ 70% meilleur performance en CompuBench 1.5 Desktop - Video Composition (Frames/s): 204.32 versus 119.936
- Environ 33% meilleur performance en CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 1214.142 versus 910.721
- Environ 87% meilleur performance en GFXBench 4.0 - Manhattan (Frames): 3699 versus 1976
- Environ 88% meilleur performance en GFXBench 4.0 - T-Rex (Frames): 3340 versus 1781
- Environ 87% meilleur performance en GFXBench 4.0 - Manhattan (Fps): 3699 versus 1976
- Environ 88% meilleur performance en GFXBench 4.0 - T-Rex (Fps): 3340 versus 1781
Caractéristiques | |
Vitesse du noyau | 1303 MHz versus 1005 MHz |
Vitesse augmenté | 1531 MHz versus 1515 MHz |
Vitesse de mémoire | 10008 MHz versus 10000 MHz |
Référence | |
PassMark - G3D Mark | 12267 versus 10616 |
Geekbench - OpenCL | 62287 versus 61276 |
CompuBench 1.5 Desktop - Face Detection (mPixels/s) | 300.355 versus 127.622 |
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) | 3559.383 versus 3026.812 |
CompuBench 1.5 Desktop - T-Rex (Frames/s) | 19.757 versus 18.798 |
CompuBench 1.5 Desktop - Video Composition (Frames/s) | 204.32 versus 119.936 |
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) | 1214.142 versus 910.721 |
GFXBench 4.0 - Manhattan (Frames) | 3699 versus 1976 |
GFXBench 4.0 - T-Rex (Frames) | 3340 versus 1781 |
GFXBench 4.0 - Manhattan (Fps) | 3699 versus 1976 |
GFXBench 4.0 - T-Rex (Fps) | 3340 versus 1781 |
Comparer les références
GPU 1: NVIDIA Tesla T4
GPU 2: NVIDIA Tesla P40
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) |
|
|
Nom | NVIDIA Tesla T4 | NVIDIA Tesla P40 |
---|---|---|
PassMark - G3D Mark | 10616 | 12267 |
PassMark - G2D Mark | 592 | 439 |
Geekbench - OpenCL | 61276 | 62287 |
CompuBench 1.5 Desktop - Face Detection (mPixels/s) | 127.622 | 300.355 |
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) | 3026.812 | 3559.383 |
CompuBench 1.5 Desktop - T-Rex (Frames/s) | 18.798 | 19.757 |
CompuBench 1.5 Desktop - Video Composition (Frames/s) | 119.936 | 204.32 |
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) | 910.721 | 1214.142 |
GFXBench 4.0 - Car Chase Offscreen (Frames) | 14076 | 9538 |
GFXBench 4.0 - Manhattan (Frames) | 1976 | 3699 |
GFXBench 4.0 - T-Rex (Frames) | 1781 | 3340 |
GFXBench 4.0 - Car Chase Offscreen (Fps) | 14076 | 9538 |
GFXBench 4.0 - Manhattan (Fps) | 1976 | 3699 |
GFXBench 4.0 - T-Rex (Fps) | 1781 | 3340 |
Comparer les caractéristiques
NVIDIA Tesla T4 | NVIDIA Tesla P40 | |
---|---|---|
Essentiel |
||
Architecture | Turing | Pascal |
Nom de code | TU104 | GP102 |
Date de sortie | 13 September 2018 | 13 September 2016 |
Position dans l’évaluation de la performance | 270 | 234 |
Genre | Workstation | Workstation |
Prix de sortie (MSRP) | $5,699 | |
Infos techniques |
||
Vitesse augmenté | 1515 MHz | 1531 MHz |
Vitesse du noyau | 1005 MHz | 1303 MHz |
Processus de fabrication | 12 nm | 16 nm |
Thermal Design Power (TDP) | 75 Watt | 250 Watt |
Compte de transistor | 13,600 million | 11,800 million |
Performance á point flottant | 11,758 gflops | |
Pipelines | 3840 | |
Taux de remplissage de la texture | 367.4 GTexel / s | |
Sorties et ports de vidéo |
||
Connecteurs d’écran | No outputs | No outputs |
Compatibilité, dimensions et exigences |
||
Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Connecteurs d’énergie supplementaires | None | 1x 6-pin + 1x 8-pin |
Longeur | 267 mm | |
Soutien API |
||
DirectX | 12.0 (12_1) | 12.0 (12_1) |
OpenGL | 4.6 | 4.6 |
Mémoire |
||
Vitesse de mémoire | 10000 MHz | 10008 MHz |
RAM maximale | 24 GB | |
Bande passante de la mémoire | 480.4 GB / s | |
Largeur du bus mémoire | 384 Bit | |
Genre de mémoire | GDDR5X |