AMD Radeon 660M vs NVIDIA Tesla M2070

Comparative analysis of AMD Radeon 660M and NVIDIA Tesla M2070 videocards for all known characteristics in the following categories: Essentials, Technical info, Compatibility, dimensions and requirements, API support, Video outputs and ports, Memory. Benchmark videocards performance analysis: 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).

AMD Radeon 660M

NVIDIA Tesla M2070

Differences

Reasons to consider the AMD Radeon 660M

Videocard is newer: launch date 10 year(s) 5 month(s) later
2.6x more core clock speed: 1500 MHz vs 574 MHz
1416.1x more texture fill rate: 45.60 GTexel/s vs 32.2 GTexel / s
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 6 nm vs 40 nm
15x lower typical power consumption: 15 Watt vs 225 Watt

Launch date	4 Jan 2022 vs 25 July 2011
Core clock speed	1500 MHz vs 574 MHz
Texture fill rate	45.60 GTexel/s vs 32.2 GTexel / s
Manufacturing process technology	6 nm vs 40 nm
Thermal Design Power (TDP)	15 Watt vs 225 Watt

Reasons to consider the NVIDIA Tesla M2070

Around 17% higher pipelines: 448 vs 384

Pipelines	448 vs 384

Compare benchmarks

GPU 1: AMD Radeon 660M
GPU 2: NVIDIA Tesla M2070

Name	AMD Radeon 660M	NVIDIA Tesla M2070
Geekbench - OpenCL	13430
CompuBench 1.5 Desktop - Face Detection (mPixels/s)		12.145
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		910.236
CompuBench 1.5 Desktop - T-Rex (Frames/s)		1.005
CompuBench 1.5 Desktop - Video Composition (Frames/s)		46.235
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)		94.442

Compare specifications (specs)

	AMD Radeon 660M	NVIDIA Tesla M2070
Essentials
Architecture	RDNA 2.0	Fermi
Code name	Rembrandt	GF100
Launch date	4 Jan 2022	25 July 2011
Place in performance rating	1356	1359
Launch price (MSRP)		$3,099
Type		Workstation
Technical info
Boost clock speed	1900 MHz
Compute units	6
Core clock speed	1500 MHz	574 MHz
Manufacturing process technology	6 nm	40 nm
Peak Double Precision (FP64) Performance	91.20 GFLOPS (1:16)
Peak Half Precision (FP16) Performance	2.918 TFLOPS (2:1)
Peak Single Precision (FP32) Performance	1459 GFLOPS
Pipelines	384	448
Pixel fill rate	30.40 GPixel/s
Texture fill rate	45.60 GTexel/s	32.2 GTexel / s
Thermal Design Power (TDP)	15 Watt	225 Watt
Transistor count	13100 million	3,100 million
Floating-point performance		1,030.4 gflops
Compatibility, dimensions and requirements
Form factor	IGP
Interface	PCIe 4.0 x8	PCIe 2.0 x16
Length		248 mm
Supplementary power connectors		1x 6-pin + 1x 8-pin
API support
DirectX	12.2	12.0 (11_0)
OpenCL	2.0
OpenGL	4.6	4.6
Shader Model	6.7
Vulkan
Video outputs and ports
Display Connectors		No outputs
Memory
Maximum RAM amount		6 GB
Memory bandwidth		150.3 GB / s
Memory bus width		384 Bit
Memory clock speed		3132 MHz
Memory type		GDDR5