NVIDIA GeForce RTX 3070 Ti versus NVIDIA GeForce RTX 2070 Super
Comparaison des cartes vidéo NVIDIA GeForce RTX 3070 Ti and NVIDIA GeForce RTX 2070 Super 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 - 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, CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s).
Différences
Raisons pour considerer le NVIDIA GeForce RTX 3070 Ti
- La carte vidéo est plus nouvelle: date de sortie 1 ans 10 mois plus tard
- 2.4x plus de pipelines: 6144 versus 2560
- Un nouveau processus de fabrication soutient une carte vidéo plus forte, mais moins chaude: 8 nm versus 12 nm
- Environ 29% meilleur performance en PassMark - G3D Mark: 23411 versus 18198
- Environ 20% meilleur performance en PassMark - G2D Mark: 1051 versus 879
- Environ 40% meilleur performance en Geekbench - OpenCL: 137664 versus 98281
- Environ 17% meilleur performance en CompuBench 1.5 Desktop - Face Detection (mPixels/s): 342.287 versus 293.508
- Environ 45% meilleur performance en CompuBench 1.5 Desktop - T-Rex (Frames/s): 42.369 versus 29.145
- Environ 26% meilleur performance en CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 1807.647 versus 1438.826
- Environ 25% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Frames): 31420 versus 25232
- 2.4x meilleur performance en GFXBench 4.0 - Manhattan (Frames): 8897 versus 3718
- 2.4x meilleur performance en GFXBench 4.0 - T-Rex (Frames): 8004 versus 3359
- Environ 25% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Fps): 31420 versus 25232
- 2.4x meilleur performance en GFXBench 4.0 - Manhattan (Fps): 8897 versus 3718
- 2.4x meilleur performance en GFXBench 4.0 - T-Rex (Fps): 8004 versus 3359
- 496.9x meilleur performance en 3DMark Fire Strike - Graphics Score: 3478 versus 7
| Caractéristiques | |
| Date de sortie | 31 May 2021 versus 2 July 2019 |
| Pipelines | 6144 versus 2560 |
| Processus de fabrication | 8 nm versus 12 nm |
| Référence | |
| PassMark - G3D Mark | 23411 versus 18198 |
| PassMark - G2D Mark | 1051 versus 879 |
| Geekbench - OpenCL | 137664 versus 98281 |
| CompuBench 1.5 Desktop - Face Detection (mPixels/s) | 342.287 versus 293.508 |
| CompuBench 1.5 Desktop - T-Rex (Frames/s) | 42.369 versus 29.145 |
| CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) | 1807.647 versus 1438.826 |
| GFXBench 4.0 - Car Chase Offscreen (Frames) | 31420 versus 25232 |
| GFXBench 4.0 - Manhattan (Frames) | 8897 versus 3718 |
| GFXBench 4.0 - T-Rex (Frames) | 8004 versus 3359 |
| GFXBench 4.0 - Car Chase Offscreen (Fps) | 31420 versus 25232 |
| GFXBench 4.0 - Manhattan (Fps) | 8897 versus 3718 |
| GFXBench 4.0 - T-Rex (Fps) | 8004 versus 3359 |
| 3DMark Fire Strike - Graphics Score | 3478 versus 7 |
Raisons pour considerer le NVIDIA GeForce RTX 2070 Super
- Environ 2% plus haut vitesse du noyau: 1605 MHz versus 1575 MHz
- Environ 35% consummation d’énergie moyen plus bas: 215 Watt versus 290 Watt
- 11.8x plus de vitesse de mémoire: 14000 MHz versus 1188 MHz, 19 Gbps effective
- Environ 8% meilleur performance en CompuBench 1.5 Desktop - Video Composition (Frames/s): 158.103 versus 146.214
| Caractéristiques | |
| Vitesse du noyau | 1605 MHz versus 1575 MHz |
| Thermal Design Power (TDP) | 215 Watt versus 290 Watt |
| Vitesse de mémoire | 14000 MHz versus 1188 MHz, 19 Gbps effective |
| Référence | |
| CompuBench 1.5 Desktop - Video Composition (Frames/s) | 158.103 versus 146.214 |
Comparer les références
GPU 1: NVIDIA GeForce RTX 3070 Ti
GPU 2: NVIDIA GeForce RTX 2070 Super
| PassMark - G3D Mark |
|
|
||||
| PassMark - G2D Mark |
|
|
||||
| Geekbench - OpenCL |
|
|
||||
| CompuBench 1.5 Desktop - Face Detection (mPixels/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 |
|
|
| Nom | NVIDIA GeForce RTX 3070 Ti | NVIDIA GeForce RTX 2070 Super |
|---|---|---|
| PassMark - G3D Mark | 23411 | 18198 |
| PassMark - G2D Mark | 1051 | 879 |
| Geekbench - OpenCL | 137664 | 98281 |
| CompuBench 1.5 Desktop - Face Detection (mPixels/s) | 342.287 | 293.508 |
| CompuBench 1.5 Desktop - T-Rex (Frames/s) | 42.369 | 29.145 |
| CompuBench 1.5 Desktop - Video Composition (Frames/s) | 146.214 | 158.103 |
| CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) | 1807.647 | 1438.826 |
| GFXBench 4.0 - Car Chase Offscreen (Frames) | 31420 | 25232 |
| GFXBench 4.0 - Manhattan (Frames) | 8897 | 3718 |
| GFXBench 4.0 - T-Rex (Frames) | 8004 | 3359 |
| GFXBench 4.0 - Car Chase Offscreen (Fps) | 31420 | 25232 |
| GFXBench 4.0 - Manhattan (Fps) | 8897 | 3718 |
| GFXBench 4.0 - T-Rex (Fps) | 8004 | 3359 |
| 3DMark Fire Strike - Graphics Score | 3478 | 7 |
| CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) | 4045.784 |
Comparer les caractéristiques
| NVIDIA GeForce RTX 3070 Ti | NVIDIA GeForce RTX 2070 Super | |
|---|---|---|
Essentiel |
||
| Architecture | Ampere | Turing |
| Nom de code | GA104 | TU104 |
| Date de sortie | 31 May 2021 | 2 July 2019 |
| Prix de sortie (MSRP) | $599 | $499 |
| Position dans l’évaluation de la performance | 66 | 129 |
| Genre | Desktop | Desktop |
Infos techniques |
||
| Vitesse augmenté | 1770 MHz | 1770 MHz |
| Vitesse du noyau | 1575 MHz | 1605 MHz |
| Processus de fabrication | 8 nm | 12 nm |
| Peak Double Precision (FP64) Performance | 339.8 GFLOPS (1:64) | |
| Peak Half Precision (FP16) Performance | 21.75 TFLOPS (1:1) | |
| Peak Single Precision (FP32) Performance | 21.75 TFLOPS | |
| Pipelines | 6144 | 2560 |
| Pixel fill rate | 169.9 GPixel/s | |
| Taux de remplissage de la texture | 339.8 GTexel/s | |
| Thermal Design Power (TDP) | 290 Watt | 215 Watt |
| Compte de transistor | 17400 million | 13.6 B |
| Noyaux CUDA | 2560 | |
| Température maximale du GPU | 88 C | |
| Render output units | 64 | |
Sorties et ports de vidéo |
||
| Connecteurs d’écran | 1x HDMI 2.1, 3x DisplayPort 1.4a | |
| Display Port | 1.4 | |
| Soutien de DisplayPort | ||
| Soutien de Dual-link DVI | ||
| Soutien de G-SYNC | ||
| HDCP | ||
| HDMI | ||
| Soutien de plusiers moniteurs | ||
| Nombre d’écrans á la fois | 4 | |
Compatibilité, dimensions et exigences |
||
| Facteur de forme | Dual-slot | |
| Interface | PCIe 4.0 x16 | |
| Longeur | 267 mm, 10.5 inches | 10.5” (266.74mm) |
| Énergie du systeme recommandé (PSU) | 600 Watt | 650 Watt |
| Connecteurs d’énergie supplementaires | 1x 12-pin | 6 pin + 8 pin |
| Largeur | 112 mm, 4.4 inches | 2-Slot |
| Hauteur | 4.556” (115.7mm) | |
Soutien API |
||
| DirectX | 12 Ultimate (12_2) | 12.1 |
| OpenCL | 3.0 | |
| OpenGL | 4.6 | 4.5 |
| Shader Model | 6.7 | 6.4 |
| Vulkan | ||
Mémoire |
||
| RAM maximale | 8 GB | 8 GB |
| Bande passante de la mémoire | 608.3 GB/s | 448 GB/s |
| Largeur du bus mémoire | 256 bit | 256 bit |
| Vitesse de mémoire | 1188 MHz, 19 Gbps effective | 14000 MHz |
| Genre de mémoire | GDDR6X | GDDR6 |
Technologies |
||
| Ansel | ||
| HDMI 2.0b | ||
| SLI | ||
| VR Ready | ||
Navigation
Choisir un GPU
Comparer les cartes vidéo
Comparer NVIDIA GeForce RTX 3070 Ti avec des autres
NVIDIAGeForce RTX 3070 Ti vs
AMDRadeon Pro V520
NVIDIAGeForce RTX 3070 Ti vs
NVIDIARTX A5000
NVIDIAGeForce RTX 3070 Ti vs
AMDRadeon Pro W6600
NVIDIAGeForce RTX 3070 Ti vs
NVIDIAA10G
NVIDIAGeForce RTX 3070 Ti vs
NVIDIARTX A5500 Mobile
NVIDIAGeForce RTX 3070 Ti vs
NVIDIARTX 3500 Ada Generation
