NVIDIA Tesla M2070 vs NVIDIA Tesla M2090

Comparative analysis of NVIDIA Tesla M2070 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: 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), Geekbench - OpenCL.

NVIDIA Tesla M2070

NVIDIA Tesla M2090

Differences

Reasons to consider the NVIDIA Tesla M2070

Around 11% lower typical power consumption: 225 Watt vs 250 Watt

Thermal Design Power (TDP)	225 Watt vs 250 Watt

Reasons to consider the NVIDIA Tesla M2090

Around 13% higher core clock speed: 650 MHz vs 574 MHz
Around 13% higher texture fill rate: 36.4 GTexel / s vs 32.2 GTexel / s
Around 14% higher pipelines: 512 vs 448
Around 29% better floating-point performance: 1,331.2 gflops vs 1,030.4 gflops
Around 18% higher memory clock speed: 3700 MHz vs 3132 MHz
2.8x better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 33.87 vs 12.145
Around 24% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 1127.187 vs 910.236
3.8x better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 3.833 vs 1.005
Around 24% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 57.33 vs 46.235
Around 26% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 119.136 vs 94.442

Specifications (specs)
Core clock speed	650 MHz vs 574 MHz
Texture fill rate	36.4 GTexel / s vs 32.2 GTexel / s
Pipelines	512 vs 448
Floating-point performance	1,331.2 gflops vs 1,030.4 gflops
Memory clock speed	3700 MHz vs 3132 MHz
Benchmarks
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	33.87 vs 12.145
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1127.187 vs 910.236
CompuBench 1.5 Desktop - T-Rex (Frames/s)	3.833 vs 1.005
CompuBench 1.5 Desktop - Video Composition (Frames/s)	57.33 vs 46.235
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	119.136 vs 94.442

Compare benchmarks

GPU 1: NVIDIA Tesla M2070
GPU 2: NVIDIA Tesla M2090

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

12.145

33.87

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

GPU 1

GPU 2

910.236

1127.187

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

GPU 1

GPU 2

1.005

3.833

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

46.235

57.33

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

94.442

119.136

Name	NVIDIA Tesla M2070	NVIDIA Tesla M2090
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	12.145	33.87
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	910.236	1127.187
CompuBench 1.5 Desktop - T-Rex (Frames/s)	1.005	3.833
CompuBench 1.5 Desktop - Video Composition (Frames/s)	46.235	57.33
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	94.442	119.136
Geekbench - OpenCL		13075

Compare specifications (specs)

	NVIDIA Tesla M2070	NVIDIA Tesla M2090
Essentials
Architecture	Fermi	Fermi 2.0
Code name	GF100	GF110
Launch date	25 July 2011	25 July 2011
Launch price (MSRP)	$3,099
Place in performance rating	1327	1090
Type	Workstation	Workstation
Technical info
Core clock speed	574 MHz	650 MHz
Floating-point performance	1,030.4 gflops	1,331.2 gflops
Manufacturing process technology	40 nm	40 nm
Pipelines	448	512
Texture fill rate	32.2 GTexel / s	36.4 GTexel / s
Thermal Design Power (TDP)	225 Watt	250 Watt
Transistor count	3,100 million	3,000 million
Video outputs and ports
Display Connectors	No outputs	No outputs
Compatibility, dimensions and requirements
Interface	PCIe 2.0 x16	PCIe 2.0 x16
Length	248 mm	248 mm
Supplementary power connectors	1x 6-pin + 1x 8-pin	1x 6-pin + 1x 8-pin
API support
DirectX	12.0 (11_0)	12.0 (11_0)
OpenGL	4.6	4.6
Memory
Maximum RAM amount	6 GB	6 GB
Memory bandwidth	150.3 GB / s	177.6 GB / s
Memory bus width	384 Bit	384 Bit
Memory clock speed	3132 MHz	3700 MHz
Memory type	GDDR5	GDDR5