Performance and energy efficiency are key aspects of next-generation AIoT\ua0hardware. This chapter presents a scalable, heterogeneous hardware platform for accelerated AIoT based on microserver technology. It integrates several\ua0accelerator platforms based on technologies like CPUs, embedded GPUs,\ua0FPGAs, or specialized ASICs, supporting the full range of the cloud−edgeIoT continuum. The modular microserver approach enables the integrationof different, heterogeneous accelerators into one platform. Benchmarking\ua0the various accelerators takes performance, energy efficiency, and accuracy\ua0into account. The results provide a solid overview of available acceleratorsolutions and guide hardware selection for AIoT applications from the fa...
The performance of a platform is evaluated based on its ability to deal with the processing of multi...
Oleksiak A, Kierzynka M, Porrmann M, et al. M2DC – A Novel Heterogeneous Hyperscale Microserver Plat...
The stringent power constraints of complex microcontroller based devices (e.g. smart sensors for the...
Griessl R, Porrmann F, Kucza N, et al. Evaluation of heterogeneous AIoT Accelerators within VEDLIoT....
Kaiser M, Griessl R, Hagemeyer J, et al. A Reconfigurable Heterogeneous Microserver Architecture for...
The VEDLIoT project aims to develop energy-efficient Deep Learning methodologies for distributed Art...
AbstractThis position paper presents a novel heterogeneous CPU-GPU multi-level cloud acceleration fo...
The goal of reaching exascale computing is made especially challenging by the highly heterogeneous n...
The constant growth of datacenters and cloud computing comes with an increase of power consumption. ...
In the context of today’s artificial intelligence, the volume of data is exploding. Although scaling...
Hardware accelerators implement custom architectures to significantly speed up computations in a wid...
High performance computing platform is moving from homogeneous individual unites to heterogeneous sy...
The use of specialized accelerators is among the most promising paths to better energy efficiency fo...
Data centers are experiencing an exponential increase in the amount of network traffic that they hav...
With the upcoming 5G deployment and the exponentially increasing data transmitted over cellular netw...
The performance of a platform is evaluated based on its ability to deal with the processing of multi...
Oleksiak A, Kierzynka M, Porrmann M, et al. M2DC – A Novel Heterogeneous Hyperscale Microserver Plat...
The stringent power constraints of complex microcontroller based devices (e.g. smart sensors for the...
Griessl R, Porrmann F, Kucza N, et al. Evaluation of heterogeneous AIoT Accelerators within VEDLIoT....
Kaiser M, Griessl R, Hagemeyer J, et al. A Reconfigurable Heterogeneous Microserver Architecture for...
The VEDLIoT project aims to develop energy-efficient Deep Learning methodologies for distributed Art...
AbstractThis position paper presents a novel heterogeneous CPU-GPU multi-level cloud acceleration fo...
The goal of reaching exascale computing is made especially challenging by the highly heterogeneous n...
The constant growth of datacenters and cloud computing comes with an increase of power consumption. ...
In the context of today’s artificial intelligence, the volume of data is exploding. Although scaling...
Hardware accelerators implement custom architectures to significantly speed up computations in a wid...
High performance computing platform is moving from homogeneous individual unites to heterogeneous sy...
The use of specialized accelerators is among the most promising paths to better energy efficiency fo...
Data centers are experiencing an exponential increase in the amount of network traffic that they hav...
With the upcoming 5G deployment and the exponentially increasing data transmitted over cellular netw...
The performance of a platform is evaluated based on its ability to deal with the processing of multi...
Oleksiak A, Kierzynka M, Porrmann M, et al. M2DC – A Novel Heterogeneous Hyperscale Microserver Plat...
The stringent power constraints of complex microcontroller based devices (e.g. smart sensors for the...