AMD Radeon HD 6670 versus ATI Radeon HD 5870

Comparaison des cartes vidéo AMD Radeon HD 6670 and ATI Radeon HD 5870 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.

AMD Radeon HD 6670

versus

ATI Radeon HD 5870

Différences

Raisons pour considerer le AMD Radeon HD 6670

La carte vidéo est plus nouvelle: date de sortie 1 ans 6 mois plus tard
2.8x consummation d’énergie moyen plus bas: 66 Watt versus 188 Watt
Environ 3% meilleur performance en Geekbench - OpenCL: 1905 versus 1858

Caractéristiques
Date de sortie	19 April 2011 versus 23 September 2009
Thermal Design Power (TDP)	66 Watt versus 188 Watt
Référence
Geekbench - OpenCL	1905 versus 1858

Raisons pour considerer le ATI Radeon HD 5870

Environ 6% plus de la vitesse augmenté: 850 MHz versus 800 MHz
times}x plus de taux de remplissage de la texture: 68.0 GTexel / s versus 19.2 GTexel / s
3.3x plus de pipelines: 1600 versus 480
3.5x de meilleur performance á point flottant: 2,720.0 gflops versus 768.0 gflops
4.6x plus de vitesse de mémoire: 4800 MHz versus 1050 MHz
3x meilleur performance en PassMark - G3D Mark: 2199 versus 724
Environ 68% meilleur performance en PassMark - G2D Mark: 416 versus 247
3.9x meilleur performance en CompuBench 1.5 Desktop - Face Detection (mPixels/s): 18.789 versus 4.861
5.7x meilleur performance en CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 1339.688 versus 235.463
3.8x meilleur performance en CompuBench 1.5 Desktop - T-Rex (Frames/s): 1.775 versus 0.463
2.7x meilleur performance en CompuBench 1.5 Desktop - Video Composition (Frames/s): 43.496 versus 15.918
6.4x meilleur performance en CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 245.813 versus 38.551
2.9x meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Frames): 4541 versus 1564
Environ 13% meilleur performance en GFXBench 4.0 - Manhattan (Frames): 3671 versus 3260
2.9x meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Fps): 4541 versus 1564
Environ 13% meilleur performance en GFXBench 4.0 - Manhattan (Fps): 3671 versus 3260

Caractéristiques
Vitesse augmenté	850 MHz versus 800 MHz
Taux de remplissage de la texture	68.0 GTexel / s versus 19.2 GTexel / s
Pipelines	1600 versus 480
Performance á point flottant	2,720.0 gflops versus 768.0 gflops
Vitesse de mémoire	4800 MHz versus 1050 MHz
Référence
PassMark - G3D Mark	2199 versus 724
PassMark - G2D Mark	416 versus 247
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	18.789 versus 4.861
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1339.688 versus 235.463
CompuBench 1.5 Desktop - T-Rex (Frames/s)	1.775 versus 0.463
CompuBench 1.5 Desktop - Video Composition (Frames/s)	43.496 versus 15.918
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	245.813 versus 38.551
GFXBench 4.0 - Car Chase Offscreen (Frames)	4541 versus 1564
GFXBench 4.0 - Manhattan (Frames)	3671 versus 3260
GFXBench 4.0 - T-Rex (Frames)	3349 versus 3348
GFXBench 4.0 - Car Chase Offscreen (Fps)	4541 versus 1564
GFXBench 4.0 - Manhattan (Fps)	3671 versus 3260
GFXBench 4.0 - T-Rex (Fps)	3349 versus 3348

Comparer les références

GPU 1: AMD Radeon HD 6670
GPU 2: ATI Radeon HD 5870

PassMark - G3D Mark

GPU 1

GPU 2

724

2199

PassMark - G2D Mark

GPU 1

GPU 2

247

416

Geekbench - OpenCL

GPU 1

GPU 2

1905

1858

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

4.861

18.789

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

GPU 1

GPU 2

235.463

1339.688

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

GPU 1

GPU 2

0.463

1.775

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

15.918

43.496

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

38.551

245.813

GFXBench 4.0 - Car Chase Offscreen (Frames)

GPU 1

GPU 2

1564

4541

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

3260

3671

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

3348

3349

GFXBench 4.0 - Car Chase Offscreen (Fps)

GPU 1

GPU 2

1564

4541

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

3260

3671

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

3348

3349

Nom	AMD Radeon HD 6670	ATI Radeon HD 5870
PassMark - G3D Mark	724	2199
PassMark - G2D Mark	247	416
Geekbench - OpenCL	1905	1858
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	4.861	18.789
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	235.463	1339.688
CompuBench 1.5 Desktop - T-Rex (Frames/s)	0.463	1.775
CompuBench 1.5 Desktop - Video Composition (Frames/s)	15.918	43.496
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	38.551	245.813
GFXBench 4.0 - Car Chase Offscreen (Frames)	1564	4541
GFXBench 4.0 - Manhattan (Frames)	3260	3671
GFXBench 4.0 - T-Rex (Frames)	3348	3349
GFXBench 4.0 - Car Chase Offscreen (Fps)	1564	4541
GFXBench 4.0 - Manhattan (Fps)	3260	3671
GFXBench 4.0 - T-Rex (Fps)	3348	3349
3DMark Fire Strike - Graphics Score	0	0

Comparer les caractéristiques

	AMD Radeon HD 6670	ATI Radeon HD 5870
Essentiel
Architecture	TeraScale 2	TeraScale 2
Nom de code	Turks	Cypress
Conception	AMD Radeon HD 6000 Series	ATI Radeon HD 5000 Series
Date de sortie	19 April 2011	23 September 2009
Prix de sortie (MSRP)	$99	$399
Position dans l’évaluation de la performance	1255	770
Prix maintenant	$102.99
Genre	Desktop	Desktop
Valeur pour le prix (0-100)	13.12
Infos techniques
Vitesse augmenté	800 MHz	850 MHz
Performance á point flottant	768.0 gflops	2,720.0 gflops
Processus de fabrication	40 nm	40 nm
Pipelines	480	1600
Taux de remplissage de la texture	19.2 GTexel / s	68.0 GTexel / s
Thermal Design Power (TDP)	66 Watt	188 Watt
Compte de transistor	716 million	2,154 million
Vitesse du noyau		850 MHz
Sorties et ports de vidéo
Connecteurs d’écran	1x DVI, 1x HDMI, 1x VGA	2x DVI, 1x HDMI, 1x DisplayPort
Soutien de DisplayPort
Soutien de Dual-link DVI
Eyefinity
HDMI
VGA
Compatibilité, dimensions et exigences
Soutien de bus	PCIe 2.0 x16
Interface	PCIe 2.0 x16	PCIe 2.0 x16
Longeur	168 mm	282 mm
Connecteurs d’énergie supplementaires	None	2x 6-pin
Soutien API
DirectX	11	11
OpenGL	4.4	4.4
Mémoire
RAM maximale	1 GB	1 GB
Bande passante de la mémoire	64 GB/s	153.6 GB / s
Largeur du bus mémoire	128 Bit	256 Bit
Vitesse de mémoire	1050 MHz	4800 MHz
Genre de mémoire	GDDR5	GDDR5
Technologies
AMD Eyefinity
CrossFire