NVIDIA Quadro P2200 versus NVIDIA Tesla T4

Comparaison des cartes vidéo NVIDIA Quadro P2200 and NVIDIA Tesla T4 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), 3DMark Fire Strike - Graphics Score.

NVIDIA Quadro P2200

versus

NVIDIA Tesla T4

Différences

Raisons pour considerer le NVIDIA Quadro P2200

La carte vidéo est plus nouvelle: date de sortie 8 mois plus tard
Environ 54% meilleur performance en PassMark - G2D Mark: 918 versus 596
Environ 1% meilleur performance en CompuBench 1.5 Desktop - Video Composition (Frames/s): 120.742 versus 119.936
Environ 88% meilleur performance en GFXBench 4.0 - Manhattan (Frames): 3717 versus 1976
Environ 88% meilleur performance en GFXBench 4.0 - Manhattan (Fps): 3717 versus 1976

Caractéristiques
Date de sortie	10 June 2019 versus 13 September 2018
Référence
PassMark - G2D Mark	918 versus 596
CompuBench 1.5 Desktop - Video Composition (Frames/s)	120.742 versus 119.936
GFXBench 4.0 - Manhattan (Frames)	3717 versus 1976
GFXBench 4.0 - Manhattan (Fps)	3717 versus 1976

Raisons pour considerer le NVIDIA Tesla T4

Environ 1% plus haut vitesse du noyau: 1005 MHz versus 1000 MHz
Environ 1% plus de la vitesse augmenté: 1515 MHz versus 1493 MHz
Un nouveau processus de fabrication soutient une carte vidéo plus forte, mais moins chaude: 12 nm versus 16 nm
Environ 17% meilleur performance en PassMark - G3D Mark: 10909 versus 9324
Environ 95% meilleur performance en Geekbench - OpenCL: 61276 versus 31480
Environ 5% meilleur performance en CompuBench 1.5 Desktop - Face Detection (mPixels/s): 127.622 versus 121.124
Environ 55% meilleur performance en CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 3026.812 versus 1958.592
2.2x meilleur performance en CompuBench 1.5 Desktop - T-Rex (Frames/s): 18.798 versus 8.452
Environ 78% meilleur performance en CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 910.721 versus 510.941
Environ 23% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Frames): 14076 versus 11437
Environ 6% meilleur performance en GFXBench 4.0 - T-Rex (Frames): 1781 versus 1676
Environ 23% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Fps): 14076 versus 11437
Environ 6% meilleur performance en GFXBench 4.0 - T-Rex (Fps): 1781 versus 1676

Caractéristiques
Vitesse du noyau	1005 MHz versus 1000 MHz
Vitesse augmenté	1515 MHz versus 1493 MHz
Processus de fabrication	12 nm versus 16 nm
Référence
PassMark - G3D Mark	10909 versus 9324
Geekbench - OpenCL	61276 versus 31480
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	127.622 versus 121.124
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	3026.812 versus 1958.592
CompuBench 1.5 Desktop - T-Rex (Frames/s)	18.798 versus 8.452
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	910.721 versus 510.941
GFXBench 4.0 - Car Chase Offscreen (Frames)	14076 versus 11437
GFXBench 4.0 - T-Rex (Frames)	1781 versus 1676
GFXBench 4.0 - Car Chase Offscreen (Fps)	14076 versus 11437
GFXBench 4.0 - T-Rex (Fps)	1781 versus 1676

Comparer les références

GPU 1: NVIDIA Quadro P2200
GPU 2: NVIDIA Tesla T4

PassMark - G3D Mark

GPU 1

GPU 2

9324

10909

PassMark - G2D Mark

GPU 1

GPU 2

918

596

Geekbench - OpenCL

GPU 1

GPU 2

31480

61276

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

121.124

127.622

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

GPU 1

GPU 2

1958.592

3026.812

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

GPU 1

GPU 2

8.452

18.798

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

120.742

119.936

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

510.941

910.721

GFXBench 4.0 - Car Chase Offscreen (Frames)

GPU 1

GPU 2

11437

14076

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

3717

1976

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

1676

1781

GFXBench 4.0 - Car Chase Offscreen (Fps)

GPU 1

GPU 2

11437

14076

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

3717

1976

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

1676

1781

Nom	NVIDIA Quadro P2200	NVIDIA Tesla T4
PassMark - G3D Mark	9324	10909
PassMark - G2D Mark	918	596
Geekbench - OpenCL	31480	61276
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	121.124	127.622
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1958.592	3026.812
CompuBench 1.5 Desktop - T-Rex (Frames/s)	8.452	18.798
CompuBench 1.5 Desktop - Video Composition (Frames/s)	120.742	119.936
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	510.941	910.721
GFXBench 4.0 - Car Chase Offscreen (Frames)	11437	14076
GFXBench 4.0 - Manhattan (Frames)	3717	1976
GFXBench 4.0 - T-Rex (Frames)	1676	1781
GFXBench 4.0 - Car Chase Offscreen (Fps)	11437	14076
GFXBench 4.0 - Manhattan (Fps)	3717	1976
GFXBench 4.0 - T-Rex (Fps)	1676	1781
3DMark Fire Strike - Graphics Score	3404

Comparer les caractéristiques

	NVIDIA Quadro P2200	NVIDIA Tesla T4
Essentiel
Architecture	Pascal	Turing
Nom de code	GP106	TU104
Date de sortie	10 June 2019	13 September 2018
Position dans l’évaluation de la performance	304	263
Genre	Workstation	Workstation
Infos techniques
Vitesse augmenté	1493 MHz	1515 MHz
Vitesse du noyau	1000 MHz	1005 MHz
Processus de fabrication	16 nm	12 nm
Peak Double Precision (FP64) Performance	119.4 GFLOPS
Peak Half Precision (FP16) Performance	59.72 GFLOPS
Peak Single Precision (FP32) Performance	3.822 TFLOPS
Pipelines	1280
Pixel fill rate	59.72 GPixel/s
Taux de remplissage de la texture	119.4 GTexel/s
Thermal Design Power (TDP)	75 Watt	75 Watt
Compte de transistor	4400 million	13,600 million
Sorties et ports de vidéo
Connecteurs d’écran	4x DisplayPort	No outputs
Compatibilité, dimensions et exigences
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Longeur	201 mm (7.9")
Connecteurs d’énergie supplementaires	None	None
Soutien API
DirectX	12.0	12.0 (12_1)
OpenCL	1.2
OpenGL	4.6	4.6
Shader Model	6.4
Vulkan
Mémoire
RAM maximale	5 GB
Bande passante de la mémoire	200.2 GB/s
Largeur du bus mémoire	160 bit
Genre de mémoire	GDDR5X
Vitesse de mémoire		10000 MHz