—Khronos SYCL is a C++ based open-source speci- fication that aims to increase the programmability of heterogeneous architectures. Several SYCL implementations exist, with variations both in terms of conformance to the specification; as well as in the range of hardware they target. Intel recently contributed the first open-source feature-complete SYCL implementation to the LLVM compiler project. The triSYCL project is another open-source SYCL implementation which targets Xilinx FPGAs. We describe here initial work to combine components of the triSYCL implementation with Intel’s SYCL implementation, and provide details of the resulting updated compiler infrastruc- ture for targeting the FPGA. We also highlight what is currently possible with the new hybrid triSYCL implementation alongside some interesting extensions for Xilinx FPGAs.
This paper presents, describes and evaluates the Machine Learning Performance Monitor (MLPM), an innovative Machine Learning (ML) approach to forecast and extrapolate the performance of several network features (e.g., latency, throughput) in a Multipath TCP (MPTCP) subflow pool. MLPM uses linear regression to predict the performance of network features along with Artificial Neural Network linear classifier to choose the best subflow (i.e., network path) capable of delivering the best performance to a given set of the network features. Results show that MLPM delivers better performance in terms of throughput and latency compared to existing schemes as it improves the MPTCP scheduler performance.
The last few years have witnessed significant developments in various aspects of Biomedical Informatics, including Bioinformatics, Medical Informatics, Public Health Informatics, and Biomedical Imaging. The explosion of medical and biological data requires an associated increase in the scale and sophistication of the automated systems and intelligent tools to enable the researchers to take full advantage of the available databases. The availability of vast amount of biological data continues to represent unlimited opportunities as well as great challenges in biomedical research. Developing innovative data mining techniques and clever parallel computational methods to implement them will surely play an important role in efficiently extracting useful knowledge from the raw data currently available. The proper integration of carefully selected/developed algorithms along with efficient utilization of high performance computing systems form the key ingredients in the process of reaching new discoveries from biological data. This tutorial focuses on addressing several key issues related to the effective utilization of High Performance Computing (HPC) in biomedical informatics research, in particular, how to efficiently utilize high performance systems in the analysis of massive biological data. A major key issue in that regard is how to develop innovative network models that allow researchers to integrate different types of biological data and extract useful knowledge out of all available datasets. Another major issue is how to design energy-aware parallel computational models for executing computationallyintensive biomedical applications on HPC systems. The integration between biomedical informatics and HPC will undoubtedly be a major driver in the next generation of biomedical research.
