NVIDIA GeForce GTX 590 vs AMD Radeon HD 6970M

Comparative analysis of NVIDIA GeForce GTX 590 and AMD Radeon HD 6970M 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.

NVIDIA GeForce GTX 590

AMD Radeon HD 6970M

Differences

Reasons to consider the NVIDIA GeForce GTX 590

Videocard is newer: launch date 2 month(s) later
Around 79% higher core clock speed: 1215 MHz vs 680 MHz
2.4x more texture fill rate: 77.7 billion / sec vs 32.6 GTexel / s
Around 7% higher pipelines: 1024 vs 960
Around 91% better floating-point performance: 2x 1,244.2 gflops vs 1,305.6 gflops
3x more maximum memory size: 3072 MB (1536 MB per GPU) vs 1 GB
Around 47% better performance in PassMark - G3D Mark: 3341 vs 2270
3.8x better performance in Geekbench - OpenCL: 12811 vs 3349
6.5x better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 30.921 vs 4.787
Around 81% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 1116.126 vs 617.819
4.1x better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 3.799 vs 0.927
2x better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 49.114 vs 24.456
Around 14% better performance in GFXBench 4.0 - Manhattan (Frames): 3683 vs 3229
Around 14% better performance in GFXBench 4.0 - Manhattan (Fps): 3683 vs 3229

Specifications (specs)
Launch date	24 March 2011 vs 4 January 2011
Core clock speed	1215 MHz vs 680 MHz
Texture fill rate	77.7 billion / sec vs 32.6 GTexel / s
Pipelines	1024 vs 960
Floating-point performance	2x 1,244.2 gflops vs 1,305.6 gflops
Maximum memory size	3072 MB (1536 MB per GPU) vs 1 GB
Benchmarks
PassMark - G3D Mark	3341 vs 2270
Geekbench - OpenCL	12811 vs 3349
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	30.921 vs 4.787
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1116.126 vs 617.819
CompuBench 1.5 Desktop - T-Rex (Frames/s)	3.799 vs 0.927
CompuBench 1.5 Desktop - Video Composition (Frames/s)	49.114 vs 24.456
GFXBench 4.0 - Manhattan (Frames)	3683 vs 3229
GFXBench 4.0 - Manhattan (Fps)	3683 vs 3229

Reasons to consider the AMD Radeon HD 6970M

4.9x lower typical power consumption: 75 Watt vs 365 Watt
2.1x more memory clock speed: 3600 MHz vs 1707 MHz
Around 66% better performance in PassMark - G2D Mark: 656 vs 394
Around 10% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 117.801 vs 107.239

Specifications (specs)
Thermal Design Power (TDP)	75 Watt vs 365 Watt
Memory clock speed	3600 MHz vs 1707 MHz
Benchmarks
PassMark - G2D Mark	656 vs 394
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	117.801 vs 107.239
GFXBench 4.0 - T-Rex (Frames)	3342 vs 3330
GFXBench 4.0 - T-Rex (Fps)	3342 vs 3330

Compare benchmarks

GPU 1: NVIDIA GeForce GTX 590
GPU 2: AMD Radeon HD 6970M

PassMark - G3D Mark

GPU 1

GPU 2

3341

2270

PassMark - G2D Mark

GPU 1

GPU 2

394

656

Geekbench - OpenCL

GPU 1

GPU 2

12811

3349

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

30.921

4.787

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

GPU 1

GPU 2

1116.126

617.819

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

GPU 1

GPU 2

3.799

0.927

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

49.114

24.456

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

107.239

117.801

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

3683

3229

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

3330

3342

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

3683

3229

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

3330

3342

Name	NVIDIA GeForce GTX 590	AMD Radeon HD 6970M
PassMark - G3D Mark	3341	2270
PassMark - G2D Mark	394	656
Geekbench - OpenCL	12811	3349
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	30.921	4.787
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1116.126	617.819
CompuBench 1.5 Desktop - T-Rex (Frames/s)	3.799	0.927
CompuBench 1.5 Desktop - Video Composition (Frames/s)	49.114	24.456
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	107.239	117.801
GFXBench 4.0 - Car Chase Offscreen (Frames)	4118
GFXBench 4.0 - Manhattan (Frames)	3683	3229
GFXBench 4.0 - T-Rex (Frames)	3330	3342
GFXBench 4.0 - Car Chase Offscreen (Fps)	4118
GFXBench 4.0 - Manhattan (Fps)	3683	3229
GFXBench 4.0 - T-Rex (Fps)	3330	3342
3DMark Fire Strike - Graphics Score	0

Compare specifications (specs)

	NVIDIA GeForce GTX 590	AMD Radeon HD 6970M
Essentials
Architecture	Fermi 2.0	TeraScale 2
Code name	GF110	Blackcomb
Launch date	24 March 2011	4 January 2011
Launch price (MSRP)	$699
Place in performance rating	790	791
Price now	$184
Type	Desktop	Laptop
Value for money (0-100)	30.41
Technical info
Core clock speed	1215 MHz	680 MHz
CUDA cores	1024
Floating-point performance	2x 1,244.2 gflops	1,305.6 gflops
Manufacturing process technology	40 nm	40 nm
Maximum GPU temperature	97 °C
Pipelines	1024	960
Texture fill rate	77.7 billion / sec	32.6 GTexel / s
Thermal Design Power (TDP)	365 Watt	75 Watt
Transistor count	3,000 million	1,700 million
Video outputs and ports
Audio input for HDMI	Internal
Display Connectors	3x DVI, 1x mini-DisplayPort, Three Dual Link DVI-IMini DisplayPort	No outputs
HDMI
Maximum VGA resolution	2048x1536
Multi monitor support
Compatibility, dimensions and requirements
Bus support	16x PCI-E 2.0
Height	4.376" (111 mm) (11.1 cm)
Interface	PCIe 2.0 x16	MXM-B (3.0)
Length	11" (280 mm) (27.9 cm)
SLI options	Quad
Supplementary power connectors	Two 8-pin	None
Laptop size		large
API support
DirectX	12.0 (11_0)	11.2 (11_0)
OpenGL	4.2	4.4
Memory
Maximum RAM amount	3072 MB (1536 MB per GPU)	1 GB
Memory bandwidth	327.7 GB / s	115.2 GB / s
Memory bus width	768-bit (384-bit per GPU)	256 Bit
Memory clock speed	1707 MHz	3600 MHz
Memory type	GDDR5	GDDR5
Shared memory	0	0
Technologies
3D Vision
CUDA
DSR
SLI
Surround