NVIDIA GeForce RTX 3090 versus NVIDIA GeForce RTX 3070

Comparaison des cartes vidéo NVIDIA GeForce RTX 3090 and NVIDIA GeForce RTX 3070 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.

 

Différences

Raisons pour considerer le NVIDIA GeForce RTX 3090

  • Environ 75% taux plus haut de remplissage de la texture: 556.0 GTexel/s versus 317.4 GTexel/s
  • Environ 78% de pipelines plus haut: 10496 versus 5888
  • 3x plus de taille maximale de mémoire : 24 GB versus 8 GB
  • Environ 19% meilleur performance en PassMark - G3D Mark: 26733 versus 22372
  • Environ 5% meilleur performance en PassMark - G2D Mark: 1050 versus 997
  • Environ 56% meilleur performance en Geekbench - OpenCL: 191412 versus 122918
  • Environ 61% meilleur performance en CompuBench 1.5 Desktop - Face Detection (mPixels/s): 732.196 versus 453.922
  • Environ 31% meilleur performance en CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 7585.258 versus 5803.174
  • Environ 55% meilleur performance en CompuBench 1.5 Desktop - T-Rex (Frames/s): 63.011 versus 40.757
  • Environ 36% meilleur performance en CompuBench 1.5 Desktop - Video Composition (Frames/s): 247.569 versus 182.055
  • Environ 47% meilleur performance en CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 2441.384 versus 1664.554
  • Environ 5% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Frames): 33398 versus 31716
  • Environ 5% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Fps): 33398 versus 31716
  • Environ 46% meilleur performance en 3DMark Fire Strike - Graphics Score: 19948 versus 13676
Caractéristiques
Taux de remplissage de la texture 556.0 GTexel/s versus 317.4 GTexel/s
Pipelines 10496 versus 5888
Taille de mémore maximale 24 GB versus 8 GB
Référence
PassMark - G3D Mark 26733 versus 22372
PassMark - G2D Mark 1050 versus 997
Geekbench - OpenCL 191412 versus 122918
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 732.196 versus 453.922
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 7585.258 versus 5803.174
CompuBench 1.5 Desktop - T-Rex (Frames/s) 63.011 versus 40.757
CompuBench 1.5 Desktop - Video Composition (Frames/s) 247.569 versus 182.055
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 2441.384 versus 1664.554
GFXBench 4.0 - Car Chase Offscreen (Frames) 33398 versus 31716
GFXBench 4.0 - Car Chase Offscreen (Fps) 33398 versus 31716
3DMark Fire Strike - Graphics Score 19948 versus 13676

Raisons pour considerer le NVIDIA GeForce RTX 3070

  • Environ 8% plus haut vitesse du noyau: 1500 MHz versus 1395 MHz
  • Environ 2% plus de la vitesse augmenté: 1725 MHz versus 1695 MHz
  • Environ 59% consummation d’énergie moyen plus bas: 220 Watt versus 350 Watt
  • Environ 44% plus haut de vitesse de mémoire: 1750 MHz, 14 Gbps effective versus 1219 MHz (19.5 Gbps effective)
  • 3.7x meilleur performance en GFXBench 4.0 - Manhattan (Frames): 13566 versus 3713
  • 9.5x meilleur performance en GFXBench 4.0 - T-Rex (Frames): 31930 versus 3354
  • 3.7x meilleur performance en GFXBench 4.0 - Manhattan (Fps): 13566 versus 3713
  • 9.5x meilleur performance en GFXBench 4.0 - T-Rex (Fps): 31930 versus 3354
Caractéristiques
Vitesse du noyau 1500 MHz versus 1395 MHz
Vitesse augmenté 1725 MHz versus 1695 MHz
Thermal Design Power (TDP) 220 Watt versus 350 Watt
Vitesse de mémoire 1750 MHz, 14 Gbps effective versus 1219 MHz (19.5 Gbps effective)
Référence
GFXBench 4.0 - Manhattan (Frames) 13566 versus 3713
GFXBench 4.0 - T-Rex (Frames) 31930 versus 3354
GFXBench 4.0 - Manhattan (Fps) 13566 versus 3713
GFXBench 4.0 - T-Rex (Fps) 31930 versus 3354

Comparer les références

GPU 1: NVIDIA GeForce RTX 3090
GPU 2: NVIDIA GeForce RTX 3070

PassMark - G3D Mark
GPU 1
GPU 2
26733
22372
PassMark - G2D Mark
GPU 1
GPU 2
1050
997
Geekbench - OpenCL
GPU 1
GPU 2
191412
122918
CompuBench 1.5 Desktop - Face Detection (mPixels/s)
GPU 1
GPU 2
732.196
453.922
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)
GPU 1
GPU 2
7585.258
5803.174
CompuBench 1.5 Desktop - T-Rex (Frames/s)
GPU 1
GPU 2
63.011
40.757
CompuBench 1.5 Desktop - Video Composition (Frames/s)
GPU 1
GPU 2
247.569
182.055
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)
GPU 1
GPU 2
2441.384
1664.554
GFXBench 4.0 - Car Chase Offscreen (Frames)
GPU 1
GPU 2
33398
31716
GFXBench 4.0 - Manhattan (Frames)
GPU 1
GPU 2
3713
13566
GFXBench 4.0 - T-Rex (Frames)
GPU 1
GPU 2
3354
31930
GFXBench 4.0 - Car Chase Offscreen (Fps)
GPU 1
GPU 2
33398
31716
GFXBench 4.0 - Manhattan (Fps)
GPU 1
GPU 2
3713
13566
GFXBench 4.0 - T-Rex (Fps)
GPU 1
GPU 2
3354
31930
3DMark Fire Strike - Graphics Score
GPU 1
GPU 2
19948
13676
Nom NVIDIA GeForce RTX 3090 NVIDIA GeForce RTX 3070
PassMark - G3D Mark 26733 22372
PassMark - G2D Mark 1050 997
Geekbench - OpenCL 191412 122918
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 732.196 453.922
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 7585.258 5803.174
CompuBench 1.5 Desktop - T-Rex (Frames/s) 63.011 40.757
CompuBench 1.5 Desktop - Video Composition (Frames/s) 247.569 182.055
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 2441.384 1664.554
GFXBench 4.0 - Car Chase Offscreen (Frames) 33398 31716
GFXBench 4.0 - Manhattan (Frames) 3713 13566
GFXBench 4.0 - T-Rex (Frames) 3354 31930
GFXBench 4.0 - Car Chase Offscreen (Fps) 33398 31716
GFXBench 4.0 - Manhattan (Fps) 3713 13566
GFXBench 4.0 - T-Rex (Fps) 3354 31930
3DMark Fire Strike - Graphics Score 19948 13676

Comparer les caractéristiques

NVIDIA GeForce RTX 3090 NVIDIA GeForce RTX 3070

Essentiel

Architecture Ampere Ampere
Nom de code GA102 GA104
Date de sortie 1 Sep 2020 1 Sep 2020
Prix de sortie (MSRP) $1499 $499
Position dans l’évaluation de la performance 44 47
Genre Desktop Desktop

Infos techniques

Vitesse augmenté 1695 MHz 1725 MHz
Vitesse du noyau 1395 MHz 1500 MHz
Processus de fabrication 8 nm 8 nm
Peak Double Precision (FP64) Performance 556.0 GFLOPS (1:64) 317.4 GFLOPS (1:64)
Peak Half Precision (FP16) Performance 35.58 TFLOPS (1:1) 20.31 TFLOPS (1:1)
Peak Single Precision (FP32) Performance 35.58 TFLOPS 20.31 TFLOPS
Pipelines 10496 5888
Pixel fill rate 189.8 GPixel/s 165.6 GPixel/s
Taux de remplissage de la texture 556.0 GTexel/s 317.4 GTexel/s
Thermal Design Power (TDP) 350 Watt 220 Watt
Compte de transistor 28300 million 17400 million

Sorties et ports de vidéo

Connecteurs d’écran 1x HDMI, 3x DisplayPort 1x HDMI 2.1, 3x DisplayPort 1.4a

Compatibilité, dimensions et exigences

Hauteur 138 mm (5.4 inches) 112 mm (4.4 inches)
Interface PCIe 4.0 x16 PCIe 4.0 x16
Longeur 313 mm (12.3 inches) 242 mm, 9.5 inches
Énergie du systeme recommandé (PSU) 750 Watt 550 Watt
Connecteurs d’énergie supplementaires 1x 12-pin 1x 12-pin
Largeur Triple-slot 112 mm, 4.4 inches
Facteur de forme Dual-slot

Soutien API

DirectX 12.2 12 Ultimate (12_2)
OpenCL 2.0 3.0
OpenGL 4.6 4.6
Shader Model 6.5 6.7
Vulkan

Mémoire

RAM maximale 24 GB 8 GB
Bande passante de la mémoire 936.2 GB/s 448.0 GB/s
Largeur du bus mémoire 384 bit 256 bit
Vitesse de mémoire 1219 MHz (19.5 Gbps effective) 1750 MHz, 14 Gbps effective
Genre de mémoire GDDR6X GDDR6