AMD Radeon HD 7670 OEM vs NVIDIA Tesla M2090

Comparative analysis of AMD Radeon HD 7670 OEM and NVIDIA Tesla M2090 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory. Benchmark videocards performance analysis: PassMark - G3D Mark, PassMark - G2D Mark, Geekbench - OpenCL, CompuBench 1.5 Desktop - Face Detection (mPixels/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 - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s).

AMD Radeon HD 7670 OEM

NVIDIA Tesla M2090

Differences

Reasons to consider the AMD Radeon HD 7670 OEM

Videocard is newer: launch date 5 month(s) later
Around 23% higher core clock speed: 800 MHz vs 650 MHz
3.8x lower typical power consumption: 66 Watt vs 250 Watt
Around 8% higher memory clock speed: 4000 MHz vs 3700 MHz

Launch date	5 January 2012 vs 25 July 2011
Core clock speed	800 MHz vs 650 MHz
Thermal Design Power (TDP)	66 Watt vs 250 Watt
Memory clock speed	4000 MHz vs 3700 MHz

Reasons to consider the NVIDIA Tesla M2090

Around 90% higher texture fill rate: 36.4 GTexel / s vs 19.2 GTexel / s
Around 7% higher pipelines: 512 vs 480
Around 73% better floating-point performance: 1,331.2 gflops vs 768.0 gflops
12x more maximum memory size: 6 GB vs 512 MB
4.7x better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 33.87 vs 7.266
8.3x better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 3.833 vs 0.464
Around 66% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 119.136 vs 71.832

Specifications (specs)
Texture fill rate	36.4 GTexel / s vs 19.2 GTexel / s
Pipelines	512 vs 480
Floating-point performance	1,331.2 gflops vs 768.0 gflops
Maximum memory size	6 GB vs 512 MB
Benchmarks
Geekbench - OpenCL	11728 vs 11715
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	33.87 vs 7.266
CompuBench 1.5 Desktop - T-Rex (Frames/s)	3.833 vs 0.464
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	119.136 vs 71.832

Compare benchmarks

GPU 1: AMD Radeon HD 7670 OEM
GPU 2: NVIDIA Tesla M2090

Geekbench - OpenCL

GPU 1

GPU 2

11715

11728

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

7.266

33.87

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

GPU 1

GPU 2

0.464

3.833

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

71.832

119.136

Name	AMD Radeon HD 7670 OEM	NVIDIA Tesla M2090
PassMark - G3D Mark	814
PassMark - G2D Mark	330
Geekbench - OpenCL	11715	11728
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	7.266	33.87
CompuBench 1.5 Desktop - T-Rex (Frames/s)	0.464	3.833
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	71.832	119.136
GFXBench 4.0 - Car Chase Offscreen (Frames)	1366
GFXBench 4.0 - Manhattan (Frames)	2385
GFXBench 4.0 - T-Rex (Frames)	3357
GFXBench 4.0 - Car Chase Offscreen (Fps)	1366
GFXBench 4.0 - Manhattan (Fps)	2385
GFXBench 4.0 - T-Rex (Fps)	3357
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		1127.187
CompuBench 1.5 Desktop - Video Composition (Frames/s)		57.33

Compare specifications (specs)

	AMD Radeon HD 7670 OEM	NVIDIA Tesla M2090
Essentials
Architecture	TeraScale 2	Fermi 2.0
Code name	Turks	GF110
Launch date	5 January 2012	25 July 2011
Place in performance rating	1106	1107
Type	Desktop	Workstation
Technical info
Core clock speed	800 MHz	650 MHz
Floating-point performance	768.0 gflops	1,331.2 gflops
Manufacturing process technology	40 nm	40 nm
Pipelines	480	512
Texture fill rate	19.2 GTexel / s	36.4 GTexel / s
Thermal Design Power (TDP)	66 Watt	250 Watt
Transistor count	716 million	3,000 million
Video outputs and ports
Display Connectors	1x DVI, 1x DisplayPort, 1x VGA	No outputs
Compatibility, dimensions and requirements
Interface	PCIe 2.0 x16	PCIe 2.0 x16
Length	145 mm	248 mm
Supplementary power connectors	None	1x 6-pin + 1x 8-pin
API support
DirectX	11.2 (11_0)	12.0 (11_0)
OpenGL	4.4	4.6
Memory
Maximum RAM amount	512 MB	6 GB
Memory bandwidth	64 GB / s	177.6 GB / s
Memory bus width	128 Bit	384 Bit
Memory clock speed	4000 MHz	3700 MHz
Memory type	GDDR5	GDDR5