NVIDIA GeForce RTX 3060 Ti versus AMD Radeon RX 570

Comparaison des cartes vidéo NVIDIA GeForce RTX 3060 Ti and AMD Radeon RX 570 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 - 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 GeForce RTX 3060 Ti

versus

AMD Radeon RX 570

Différences

Raisons pour considerer le NVIDIA GeForce RTX 3060 Ti

La carte vidéo est plus nouvelle: date de sortie 3 ans 7 mois plus tard
Environ 52% plus haut vitesse du noyau: 1410 MHz versus 926-1168 MHz
Environ 38% plus de la vitesse augmenté: 1665 MHz versus 1206-1244 MHz
Environ 59% taux plus haut de remplissage de la texture: 253.1 GTexel/s versus 159.23 GTexel/s
2.4x plus de pipelines: 4864 versus 2048
Un nouveau processus de fabrication soutient une carte vidéo plus forte, mais moins chaude: 8 nm versus 14 nm
2.9x meilleur performance en PassMark - G3D Mark: 20394 versus 6967
Environ 58% meilleur performance en PassMark - G2D Mark: 989 versus 626
3x meilleur performance en Geekbench - OpenCL: 109075 versus 36107
3.1x meilleur performance en CompuBench 1.5 Desktop - Face Detection (mPixels/s): 323.141 versus 105.688
4.4x meilleur performance en CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 4756.579 versus 1083.926
4.3x meilleur performance en CompuBench 1.5 Desktop - T-Rex (Frames/s): 35.311 versus 8.251
Environ 91% meilleur performance en CompuBench 1.5 Desktop - Video Composition (Frames/s): 150.943 versus 79.029
2.8x meilleur performance en CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 1474.189 versus 520.089
3x meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Frames): 27478 versus 9172
Environ 3% meilleur performance en GFXBench 4.0 - Manhattan (Frames): 3717 versus 3624
3x meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Fps): 27478 versus 9172
Environ 3% meilleur performance en GFXBench 4.0 - Manhattan (Fps): 3717 versus 3624
3x meilleur performance en 3DMark Fire Strike - Graphics Score: 2671 versus 880

Caractéristiques
Date de sortie	1 Dec 2020 versus 18 April 2017
Vitesse du noyau	1410 MHz versus 926-1168 MHz
Vitesse augmenté	1665 MHz versus 1206-1244 MHz
Taux de remplissage de la texture	253.1 GTexel/s versus 159.23 GTexel/s
Pipelines	4864 versus 2048
Processus de fabrication	8 nm versus 14 nm
Référence
PassMark - G3D Mark	20394 versus 6967
PassMark - G2D Mark	989 versus 626
Geekbench - OpenCL	109075 versus 36107
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	323.141 versus 105.688
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	4756.579 versus 1083.926
CompuBench 1.5 Desktop - T-Rex (Frames/s)	35.311 versus 8.251
CompuBench 1.5 Desktop - Video Composition (Frames/s)	150.943 versus 79.029
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	1474.189 versus 520.089
GFXBench 4.0 - Car Chase Offscreen (Frames)	27478 versus 9172
GFXBench 4.0 - Manhattan (Frames)	3717 versus 3624
GFXBench 4.0 - T-Rex (Frames)	3360 versus 3346
GFXBench 4.0 - Car Chase Offscreen (Fps)	27478 versus 9172
GFXBench 4.0 - Manhattan (Fps)	3717 versus 3624
GFXBench 4.0 - T-Rex (Fps)	3360 versus 3346
3DMark Fire Strike - Graphics Score	2671 versus 880

Raisons pour considerer le AMD Radeon RX 570

Environ 33% consummation d’énergie moyen plus bas: 150 Watt versus 200 Watt
4x plus de vitesse de mémoire: 7000 MHz versus 1750 MHz (14 Gbps effective)

Thermal Design Power (TDP)	150 Watt versus 200 Watt
Vitesse de mémoire	7000 MHz versus 1750 MHz (14 Gbps effective)

Comparer les références

GPU 1: NVIDIA GeForce RTX 3060 Ti
GPU 2: AMD Radeon RX 570

PassMark - G3D Mark

GPU 1

GPU 2

20394

6967

PassMark - G2D Mark

GPU 1

GPU 2

989

626

Geekbench - OpenCL

GPU 1

GPU 2

109075

36107

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

323.141

105.688

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

GPU 1

GPU 2

4756.579

1083.926

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

GPU 1

GPU 2

35.311

8.251

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

150.943

79.029

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

1474.189

520.089

GFXBench 4.0 - Car Chase Offscreen (Frames)

GPU 1

GPU 2

27478

9172

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

3717

3624

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

3360

3346

GFXBench 4.0 - Car Chase Offscreen (Fps)

GPU 1

GPU 2

27478

9172

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

3717

3624

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

3360

3346

3DMark Fire Strike - Graphics Score

GPU 1

GPU 2

2671

880

Nom	NVIDIA GeForce RTX 3060 Ti	AMD Radeon RX 570
PassMark - G3D Mark	20394	6967
PassMark - G2D Mark	989	626
Geekbench - OpenCL	109075	36107
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	323.141	105.688
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	4756.579	1083.926
CompuBench 1.5 Desktop - T-Rex (Frames/s)	35.311	8.251
CompuBench 1.5 Desktop - Video Composition (Frames/s)	150.943	79.029
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	1474.189	520.089
GFXBench 4.0 - Car Chase Offscreen (Frames)	27478	9172
GFXBench 4.0 - Manhattan (Frames)	3717	3624
GFXBench 4.0 - T-Rex (Frames)	3360	3346
GFXBench 4.0 - Car Chase Offscreen (Fps)	27478	9172
GFXBench 4.0 - Manhattan (Fps)	3717	3624
GFXBench 4.0 - T-Rex (Fps)	3360	3346
3DMark Fire Strike - Graphics Score	2671	880

Comparer les caractéristiques

	NVIDIA GeForce RTX 3060 Ti	AMD Radeon RX 570
Essentiel
Architecture	Ampere	GCN 4.0
Nom de code	GA104	Polaris 20
Date de sortie	1 Dec 2020	18 April 2017
Prix de sortie (MSRP)	$399	$169
Position dans l’évaluation de la performance	104	405
Genre	Desktop	Desktop, Laptop
Conception		Radeon RX 500 Series
Génération GCN		4th Gen
Prix maintenant		$149.99
Valeur pour le prix (0-100)		59.00
Infos techniques
Vitesse augmenté	1665 MHz	1206-1244 MHz
Vitesse du noyau	1410 MHz	926-1168 MHz
Processus de fabrication	8 nm	14 nm
Peak Double Precision (FP64) Performance	253.1 GFLOPS (1:64)
Peak Half Precision (FP16) Performance	16.20 TFLOPS (1:1)
Peak Single Precision (FP32) Performance	16.20 TFLOPS
Pipelines	4864	2048
Pixel fill rate	133.2 GPixel/s	39.81 GP/s
Taux de remplissage de la texture	253.1 GTexel/s	159.23 GTexel/s
Thermal Design Power (TDP)	200 Watt	150 Watt
Compte de transistor	17400 million	5,700 million
Performance á point flottant		5.1 TFLOPs
Render output units		32
Stream Processors		2048
Texture Units		128
Sorties et ports de vidéo
Connecteurs d’écran	1x HDMI, 3x DisplayPort	1x DVI, 1x HDMI, 3x DisplayPort
Soutien de DisplayPort
Soutien de Dual-link DVI
HDMI
VGA
Compatibilité, dimensions et exigences
Facteur de forme	Dual-slot
Interface	PCIe 4.0 x16	PCIe 3.0 x16
Longeur	242 mm (9.5 inches)	241 mm
Énergie du systeme recommandé (PSU)	350 Watt	450 Watt
Connecteurs d’énergie supplementaires	1x 12-pin	1x 6-pin
Largeur	112 mm (4.4 inches)
Bridgeless CrossFire
Soutien API
DirectX	12.2	12.0 (12_0)
OpenCL	2.0	2.0
OpenGL	4.6	4.6
Shader Model	6.5
Vulkan
Mémoire
RAM maximale	8 GB	8 GB
Bande passante de la mémoire	448 GB/s	224 GB/s
Largeur du bus mémoire	256 bit	256 bit
Vitesse de mémoire	1750 MHz (14 Gbps effective)	7000 MHz
Genre de mémoire	GDDR6	GDDR5
Technologies
4K H264 Decode
4K H264 Encode
AMD Eyefinity
AMD Radeon™ Chill
AMD Radeon™ ReLive
CrossFire
FreeSync
H265/HEVC Decode
H265/HEVC Encode
HDMI 4K Support
PowerTune
Unified Video Decoder (UVD)
Virtual Super Resolution (VSR)