AMD Radeon Pro Vega 48 versus NVIDIA GeForce GTX 1070 Max-Q
Comparaison des cartes vidéo AMD Radeon Pro Vega 48 and NVIDIA GeForce GTX 1070 Max-Q 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 - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (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), CompuBench 1.5 Desktop - Video Composition (Frames/s), 3DMark Fire Strike - Graphics Score.
Différences
Raisons pour considerer le AMD Radeon Pro Vega 48
- La carte vidéo est plus nouvelle: date de sortie 1 ans 8 mois plus tard
- times}x plus de taux de remplissage de la texture: 249.6 GTexel/s versus 176.5 GTexel / s
- Environ 50% de pipelines plus haut: 3072 versus 2048
- Un nouveau processus de fabrication soutient une carte vidéo plus forte, mais moins chaude: 14 nm versus 16 nm
- Environ 14% meilleur performance en PassMark - G3D Mark: 11300 versus 9934
- Environ 84% meilleur performance en PassMark - G2D Mark: 784 versus 427
- Environ 31% meilleur performance en Geekbench - OpenCL: 53770 versus 41185
- Environ 34% meilleur performance en CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 3063.269 versus 2293.496
- Environ 28% meilleur performance en CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 883.876 versus 692.9
- Environ 29% meilleur performance en GFXBench 4.0 - T-Rex (Frames): 10411 versus 8048
- Environ 29% meilleur performance en GFXBench 4.0 - T-Rex (Fps): 10411 versus 8048
Caractéristiques | |
Date de sortie | 19 March 2019 versus 27 June 2017 |
Taux de remplissage de la texture | 249.6 GTexel/s versus 176.5 GTexel / s |
Pipelines | 3072 versus 2048 |
Processus de fabrication | 14 nm versus 16 nm |
Référence | |
PassMark - G3D Mark | 11300 versus 9934 |
PassMark - G2D Mark | 784 versus 427 |
Geekbench - OpenCL | 53770 versus 41185 |
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) | 3063.269 versus 2293.496 |
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) | 883.876 versus 692.9 |
GFXBench 4.0 - T-Rex (Frames) | 10411 versus 8048 |
GFXBench 4.0 - T-Rex (Fps) | 10411 versus 8048 |
Raisons pour considerer le NVIDIA GeForce GTX 1070 Max-Q
- Environ 1% plus haut vitesse du noyau: 1215 MHz versus 1200 MHz
- Environ 6% plus de la vitesse augmenté: 1379 MHz versus 1300 MHz
- 108.7x consummation d’énergie moyen plus bas: 115 Watt versus 12500 million
- 10.2x plus de vitesse de mémoire: 8008 MHz versus 786 MHz (1572 MHz effective)
- Environ 58% meilleur performance en CompuBench 1.5 Desktop - Face Detection (mPixels/s): 214.123 versus 135.416
- Environ 25% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Frames): 14915 versus 11925
- 2.3x meilleur performance en GFXBench 4.0 - Manhattan (Frames): 8902 versus 3947
- Environ 25% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Fps): 14915 versus 11925
- 2.3x meilleur performance en GFXBench 4.0 - Manhattan (Fps): 8902 versus 3947
Caractéristiques | |
Vitesse du noyau | 1215 MHz versus 1200 MHz |
Vitesse augmenté | 1379 MHz versus 1300 MHz |
Thermal Design Power (TDP) | 115 Watt versus 12500 million |
Vitesse de mémoire | 8008 MHz versus 786 MHz (1572 MHz effective) |
Référence | |
CompuBench 1.5 Desktop - Face Detection (mPixels/s) | 214.123 versus 135.416 |
CompuBench 1.5 Desktop - T-Rex (Frames/s) | 12.704 versus 12.678 |
GFXBench 4.0 - Car Chase Offscreen (Frames) | 14915 versus 11925 |
GFXBench 4.0 - Manhattan (Frames) | 8902 versus 3947 |
GFXBench 4.0 - Car Chase Offscreen (Fps) | 14915 versus 11925 |
GFXBench 4.0 - Manhattan (Fps) | 8902 versus 3947 |
Comparer les références
GPU 1: AMD Radeon Pro Vega 48
GPU 2: NVIDIA GeForce GTX 1070 Max-Q
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 - 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 | AMD Radeon Pro Vega 48 | NVIDIA GeForce GTX 1070 Max-Q |
---|---|---|
PassMark - G3D Mark | 11300 | 9934 |
PassMark - G2D Mark | 784 | 427 |
Geekbench - OpenCL | 53770 | 41185 |
CompuBench 1.5 Desktop - Face Detection (mPixels/s) | 135.416 | 214.123 |
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) | 3063.269 | 2293.496 |
CompuBench 1.5 Desktop - T-Rex (Frames/s) | 12.678 | 12.704 |
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) | 883.876 | 692.9 |
GFXBench 4.0 - Car Chase Offscreen (Frames) | 11925 | 14915 |
GFXBench 4.0 - Manhattan (Frames) | 3947 | 8902 |
GFXBench 4.0 - T-Rex (Frames) | 10411 | 8048 |
GFXBench 4.0 - Car Chase Offscreen (Fps) | 11925 | 14915 |
GFXBench 4.0 - Manhattan (Fps) | 3947 | 8902 |
GFXBench 4.0 - T-Rex (Fps) | 10411 | 8048 |
CompuBench 1.5 Desktop - Video Composition (Frames/s) | 139.717 | |
3DMark Fire Strike - Graphics Score | 4887 |
Comparer les caractéristiques
AMD Radeon Pro Vega 48 | NVIDIA GeForce GTX 1070 Max-Q | |
---|---|---|
Essentiel |
||
Architecture | Vega 10 PRO | Pascal |
Nom de code | Greenland | GP104 |
Génération GCN | GCN 5.0 | |
Date de sortie | 19 March 2019 | 27 June 2017 |
Position dans l’évaluation de la performance | 236 | 233 |
Genre | Desktop | Laptop |
Infos techniques |
||
Vitesse augmenté | 1300 MHz | 1379 MHz |
Vitesse du noyau | 1200 MHz | 1215 MHz |
Processus de fabrication | 14 nm | 16 nm |
Peak Double Precision (FP64) Performance | 499.2 GFLOPS | |
Peak Half Precision (FP16) Performance | 15.97 TFLOPS | |
Peak Single Precision (FP32) Performance | 7.987 TFLOPS | |
Pipelines | 3072 | 2048 |
Pixel fill rate | 83.20 GPixel/s | |
Taux de remplissage de la texture | 249.6 GTexel/s | 176.5 GTexel / s |
Thermal Design Power (TDP) | 12500 million | 115 Watt |
Performance á point flottant | 5,648 gflops | |
Compte de transistor | 7,200 million | |
Sorties et ports de vidéo |
||
Connecteurs d’écran | No outputs | No outputs |
Soutien de G-SYNC | ||
Compatibilité, dimensions et exigences |
||
Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Taille du laptop | large | |
Connecteurs d’énergie supplementaires | None | |
Soutien API |
||
DirectX | 12.1 | 12.0 (12_1) |
OpenCL | 2.0 | |
OpenGL | 4.6 | 4.6 |
Shader Model | 6.3 | |
Vulkan | ||
Mémoire |
||
Mémoire de la bande passante haute (HBM) | ||
RAM maximale | 8 GB | 8 GB |
Bande passante de la mémoire | 402.4 GB/s | 256.3 GB / s |
Largeur du bus mémoire | 2048 bit | 256 Bit |
Vitesse de mémoire | 786 MHz (1572 MHz effective) | 8008 MHz |
Genre de mémoire | HBM2 | GDDR5 |
Mémoire partagé | 0 | |
Technologies |
||
Unified Video Decoder (UVD) | ||
Video Code Engine (VCE) | ||
Multi Monitor | ||
Multi-Projection | ||
VR Ready |