NVIDIA Quadro RTX 8000 versus NVIDIA Tesla V100 SXM2 16 GB

Comparaison des cartes vidéo NVIDIA Quadro RTX 8000 and NVIDIA Tesla V100 SXM2 16 GB 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 RTX 8000

versus

NVIDIA Tesla V100 SXM2 16 GB

Différences

Raisons pour considerer le NVIDIA Quadro RTX 8000

La carte vidéo est plus nouvelle: date de sortie 1 ans 1 mois plus tard
8x plus de vitesse de mémoire: 14000 MHz versus 1752 MHz
Environ 19% meilleur performance en PassMark - G3D Mark: 19370 versus 16235
2.1x meilleur performance en PassMark - G2D Mark: 869 versus 406
Environ 5% meilleur performance en CompuBench 1.5 Desktop - T-Rex (Frames/s): 43.914 versus 41.826
2.9x meilleur performance en CompuBench 1.5 Desktop - Video Composition (Frames/s): 215.219 versus 73.167
Environ 68% meilleur performance en CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 2101.927 versus 1253.829
Environ 32% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Frames): 21578 versus 16337
Environ 32% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Fps): 21578 versus 16337

Caractéristiques
Date de sortie	13 August 2018 versus 21 June 2017
Vitesse de mémoire	14000 MHz versus 1752 MHz
Référence
PassMark - G3D Mark	19370 versus 16235
PassMark - G2D Mark	869 versus 406
CompuBench 1.5 Desktop - T-Rex (Frames/s)	43.914 versus 41.826
CompuBench 1.5 Desktop - Video Composition (Frames/s)	215.219 versus 73.167
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	2101.927 versus 1253.829
GFXBench 4.0 - Car Chase Offscreen (Frames)	21578 versus 16337
GFXBench 4.0 - Car Chase Offscreen (Fps)	21578 versus 16337

Raisons pour considerer le NVIDIA Tesla V100 SXM2 16 GB

Environ 31% plus haut vitesse du noyau: 1312 MHz versus 1005 MHz
Environ 28% plus de la vitesse augmenté: 1530 MHz versus 1200 MHz
Environ 31% meilleur performance en Geekbench - OpenCL: 180318 versus 137748
Environ 25% meilleur performance en CompuBench 1.5 Desktop - Face Detection (mPixels/s): 500.053 versus 401.574
Environ 12% meilleur performance en CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 7209.392 versus 6432.348
Environ 2% meilleur performance en GFXBench 4.0 - Manhattan (Frames): 3719 versus 3652
Environ 2% meilleur performance en GFXBench 4.0 - T-Rex (Frames): 3360 versus 3290
Environ 2% meilleur performance en GFXBench 4.0 - Manhattan (Fps): 3719 versus 3652
Environ 2% meilleur performance en GFXBench 4.0 - T-Rex (Fps): 3360 versus 3290

Caractéristiques
Vitesse du noyau	1312 MHz versus 1005 MHz
Vitesse augmenté	1530 MHz versus 1200 MHz
Référence
Geekbench - OpenCL	180318 versus 137748
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	500.053 versus 401.574
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	7209.392 versus 6432.348
GFXBench 4.0 - Manhattan (Frames)	3719 versus 3652
GFXBench 4.0 - T-Rex (Frames)	3360 versus 3290
GFXBench 4.0 - Manhattan (Fps)	3719 versus 3652
GFXBench 4.0 - T-Rex (Fps)	3360 versus 3290

Comparer les références

GPU 1: NVIDIA Quadro RTX 8000
GPU 2: NVIDIA Tesla V100 SXM2 16 GB

PassMark - G3D Mark

GPU 1

GPU 2

19370

16235

PassMark - G2D Mark

GPU 1

GPU 2

869

406

Geekbench - OpenCL

GPU 1

GPU 2

137748

180318

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

401.574

500.053

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

GPU 1

GPU 2

6432.348

7209.392

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

GPU 1

GPU 2

43.914

41.826

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

215.219

73.167

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

2101.927

1253.829

GFXBench 4.0 - Car Chase Offscreen (Frames)

GPU 1

GPU 2

21578

16337

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

3652

3719

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

3290

3360

GFXBench 4.0 - Car Chase Offscreen (Fps)

GPU 1

GPU 2

21578

16337

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

3652

3719

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

3290

3360

Nom	NVIDIA Quadro RTX 8000	NVIDIA Tesla V100 SXM2 16 GB
PassMark - G3D Mark	19370	16235
PassMark - G2D Mark	869	406
Geekbench - OpenCL	137748	180318
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	401.574	500.053
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	6432.348	7209.392
CompuBench 1.5 Desktop - T-Rex (Frames/s)	43.914	41.826
CompuBench 1.5 Desktop - Video Composition (Frames/s)	215.219	73.167
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	2101.927	1253.829
GFXBench 4.0 - Car Chase Offscreen (Frames)	21578	16337
GFXBench 4.0 - Manhattan (Frames)	3652	3719
GFXBench 4.0 - T-Rex (Frames)	3290	3360
GFXBench 4.0 - Car Chase Offscreen (Fps)	21578	16337
GFXBench 4.0 - Manhattan (Fps)	3652	3719
GFXBench 4.0 - T-Rex (Fps)	3290	3360
3DMark Fire Strike - Graphics Score	0

Comparer les caractéristiques

	NVIDIA Quadro RTX 8000	NVIDIA Tesla V100 SXM2 16 GB
Essentiel
Architecture	Turing	Volta
Nom de code	TU102	GV100
Date de sortie	13 August 2018	21 June 2017
Prix de sortie (MSRP)	$9,999
Position dans l’évaluation de la performance	103	135
Genre	Workstation	Workstation
Infos techniques
Vitesse augmenté	1200 MHz	1530 MHz
Vitesse du noyau	1005 MHz	1312 MHz
Processus de fabrication	12 nm	12 nm
Thermal Design Power (TDP)	250 Watt	250 Watt
Compte de transistor	18,600 million	21,100 million
Performance á point flottant		14,029 gflops
Pipelines		5120
Taux de remplissage de la texture		438.4 GTexel / s
Sorties et ports de vidéo
Connecteurs d’écran	3x DisplayPort, 1x USB Type-C	No outputs
Compatibilité, dimensions et exigences
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Longeur	267 mm
Connecteurs d’énergie supplementaires	2x 8-pin	None
Soutien API
DirectX	12.0 (12_1)	12.0 (12_1)
OpenGL	4.6	4.6
Mémoire
Vitesse de mémoire	14000 MHz	1752 MHz
RAM maximale		16 GB
Bande passante de la mémoire		897.0 GB / s
Largeur du bus mémoire		4096 Bit
Genre de mémoire		HBM2