MEDWEL introduces its latest product MEDM-B601 for the medical device market
As one of the earliest specialized R&D enterprises in medical device area, MEDWEL, a Premier member of AMD®, provides hardware solution for the development and production of the medical device including ultrasound, MRI and PET etc. Such applications require high-speed serial buses and high computing power for data acquisition and processing compliant with strict medical regulations. Since such demand rising from the market, MEDWEL introduces the AMD latest Merlin Falcon platform MEDM-B601 and Bald eagle MEDM-B600 with its powerful computing power and advanced graphic processing ability
Powerful quad core computing power with lower power consumption
There are totally three configurations of processor for MEDM-B601 including Quad Core RE421, RE418 processor and dual core RE216 processor with 3.4, 3.2 and 3.0 max CPU clock GHz repetitively. More importantly, the power consumption ranges only from 12~35W depends on different configuration. This would be helpful for the system integrator that requires high performance with lower TDP solution.
Outstanding graphic engine and advanced multimedia and display features
MEDM-B601 features AMD® Radeon™ HD 10000 graphics chip on the same die with CPU processor. It could be helpful for the demand that require higher graphic processing ability. For the video output, MEDM-B601 boasts three display outputs with capability of single link to DP, HDMI and DVI, and the graphics chip allow for DirectX 12 graphics and a UVD 6 decoder.
Heterogeneous System Architecture (HSA)
Since a growing number of mainstream applications require the high performance and power efficiency, AMD® has introduced the new technology called Heterogeneous System Architecture (HSA), it not only enhance the efficiency of data processing through the highly parallel computation, but also improve the power efficiency.
Currently CPUs and GPUs have been designed as separate processing elements and do not work together efficiently – and are cumbersome to program. Each has a separate memory space, requiring an application to explicitly copy data from CPU to GPU and then back again.
But now, HSA creates an improved processor design that put GPU and CPU together into one chip to work seamlessly. With HSA, in the comparison for a CPU/GPU implementation in OpenCL™ against an HSA implementation, the HSA version seamlessly shares data between CPU and GPU, without memory copies or cache flushes because it assigns each part of the workload to the most appropriate processor with minimal dispatch overhead.
Some of the key features of MEDM-B601 are highlighted below: