AMD Radeon HD 6970 vs NVIDIA GeForce GTX 580

Comparative analysis of AMD Radeon HD 6970 and NVIDIA GeForce GTX 580 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory, Technologies. Benchmark videocards performance analysis: 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 6970

NVIDIA GeForce GTX 580

Differences

Reasons to consider the AMD Radeon HD 6970

Videocard is newer: launch date 1 month(s) later
Around 71% higher texture fill rate: 84.5 GTexel / s vs 49.4 billion / sec
3x more pipelines: 1536 vs 512
Around 71% better floating-point performance: 2,703.4 gflops vs 1,581.1 gflops
Around 33% higher maximum memory size: 2 GB vs 1536 MB
2.4x better performance in Geekbench - OpenCL: 35739 vs 15182
Around 5% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 920.398 vs 872.651
Around 61% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 52.219 vs 32.378
2.1x better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 273.175 vs 132.363

Specifications (specs)
Launch date	14 December 2010 vs 9 November 2010
Texture fill rate	84.5 GTexel / s vs 49.4 billion / sec
Pipelines	1536 vs 512
Floating-point performance	2,703.4 gflops vs 1,581.1 gflops
Maximum memory size	2 GB vs 1536 MB
Benchmarks
Geekbench - OpenCL	35739 vs 15182
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	920.398 vs 872.651
CompuBench 1.5 Desktop - Video Composition (Frames/s)	52.219 vs 32.378
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	273.175 vs 132.363
GFXBench 4.0 - T-Rex (Frames)	3358 vs 3357
GFXBench 4.0 - T-Rex (Fps)	3358 vs 3357

Reasons to consider the NVIDIA GeForce GTX 580

2.3x lower typical power consumption: 244 Watt vs 550 Watt
Around 46% higher memory clock speed: 2004 MHz (4008 data rate) vs 1375 MHz
Around 63% better performance in PassMark - G3D Mark: 4630 vs 2839
Around 13% better performance in PassMark - G2D Mark: 490 vs 432
2.1x better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 40.048 vs 18.676
2.4x better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 4.338 vs 1.835
Around 11% better performance in GFXBench 4.0 - Car Chase Offscreen (Frames): 5953 vs 5372
Around 11% better performance in GFXBench 4.0 - Car Chase Offscreen (Fps): 5953 vs 5372

Specifications (specs)
Thermal Design Power (TDP)	244 Watt vs 550 Watt
Memory clock speed	2004 MHz (4008 data rate) vs 1375 MHz
Benchmarks
PassMark - G3D Mark	4630 vs 2839
PassMark - G2D Mark	490 vs 432
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	40.048 vs 18.676
CompuBench 1.5 Desktop - T-Rex (Frames/s)	4.338 vs 1.835
GFXBench 4.0 - Car Chase Offscreen (Frames)	5953 vs 5372
GFXBench 4.0 - Manhattan (Frames)	3717 vs 3716
GFXBench 4.0 - Car Chase Offscreen (Fps)	5953 vs 5372
GFXBench 4.0 - Manhattan (Fps)	3717 vs 3716

Compare benchmarks

GPU 1: AMD Radeon HD 6970
GPU 2: NVIDIA GeForce GTX 580

PassMark - G3D Mark

GPU 1

GPU 2

2839

4630

PassMark - G2D Mark

GPU 1

GPU 2

432

490

Geekbench - OpenCL

GPU 1

GPU 2

35739

15182

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

18.676

40.048

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

GPU 1

GPU 2

920.398

872.651

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

GPU 1

GPU 2

1.835

4.338

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

52.219

32.378

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

273.175

132.363

GFXBench 4.0 - Car Chase Offscreen (Frames)

GPU 1

GPU 2

5372

5953

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

3716

3717

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

3358

3357

GFXBench 4.0 - Car Chase Offscreen (Fps)

GPU 1

GPU 2

5372

5953

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

3716

3717

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

3358

3357

Name	AMD Radeon HD 6970	NVIDIA GeForce GTX 580
PassMark - G3D Mark	2839	4630
PassMark - G2D Mark	432	490
Geekbench - OpenCL	35739	15182
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	18.676	40.048
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	920.398	872.651
CompuBench 1.5 Desktop - T-Rex (Frames/s)	1.835	4.338
CompuBench 1.5 Desktop - Video Composition (Frames/s)	52.219	32.378
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	273.175	132.363
GFXBench 4.0 - Car Chase Offscreen (Frames)	5372	5953
GFXBench 4.0 - Manhattan (Frames)	3716	3717
GFXBench 4.0 - T-Rex (Frames)	3358	3357
GFXBench 4.0 - Car Chase Offscreen (Fps)	5372	5953
GFXBench 4.0 - Manhattan (Fps)	3716	3717
GFXBench 4.0 - T-Rex (Fps)	3358	3357
3DMark Fire Strike - Graphics Score	0	809

Compare specifications (specs)

	AMD Radeon HD 6970	NVIDIA GeForce GTX 580
Essentials
Architecture	TeraScale 3	Fermi 2.0
Code name	Cayman	GF110
Design	AMD Radeon HD 6000 Series
Launch date	14 December 2010	9 November 2010
Launch price (MSRP)	$369	$499
Place in performance rating	662	620
Price now	$94.99	$289.88
Type	Desktop	Desktop
Value for money (0-100)	48.01	19.21
Technical info
Boost clock speed	880 MHz
Floating-point performance	2,703.4 gflops	1,581.1 gflops
Manufacturing process technology	40 nm	40 nm
Pipelines	1536	512
Texture fill rate	84.5 GTexel / s	49.4 billion / sec
Thermal Design Power (TDP)	550 Watt	244 Watt
Transistor count	2,640 million	3,000 million
Core clock speed		1544 MHz
CUDA cores		512
Maximum GPU temperature		97 °C
Video outputs and ports
Display Connectors	2x DVI, 1x HDMI, 2x mini-DisplayPort	Mini HDMITwo Dual Link DVI, 2x DVI, 1x mini-HDMI
DisplayPort support
Dual-link DVI support
Eyefinity
HDMI
VGA
Audio input for HDMI		Internal
Maximum VGA resolution		2048x1536
Multi monitor support
Compatibility, dimensions and requirements
Bus support	PCIe 2.0 x16	PCI-E 2.0 x 16
Interface	PCIe 2.0 x16	PCIe 2.0 x16
Length	267 mm	10.5" (267 mm) (26.7 cm)
Supplementary power connectors	1x 6-pin + 1x 8-pin	One 6-pin and One 8-pin
Height		4.376" (111 mm) (11.1 cm)
SLI options		3-way
API support
DirectX	11	12.0 (11_0)
OpenGL	4.4	4.2
Memory
Maximum RAM amount	2 GB	1536 MB
Memory bus width	256 Bit	384 Bit
Memory clock speed	1375 MHz	2004 MHz (4008 data rate)
Memory type	DDR5	GDDR5
Memory bandwidth		192.4 GB / s
Technologies
AMD Eyefinity
CrossFire
3D Vision
CUDA
DSR
SLI
Surround