Leveraging Automatic High-Level Synthesis Resource Sharing to Maximize Dynamical Voltage Overscaling with Error Control

Approximate Computing has emerged as an alternative way to further reduce the power consumption of integrated circuits (ICs) by trading off errors at the output with simpler, more efficient logic. So far the main approaches in approximate computing have been to simplify the hardware circuit by pruning the circuit until the maximum error threshold is met. One of the critical issues, though, is the training data used to prune the circuit. The output error can significantly exceed the maximum error if the final workload does not match the training data. Thus, most previous work typically assumes that training data matches with the workload data distribution. In this work, we present a method that dynamically overscales the supply voltage based on different workload distribution at runtime. This allows to adaptively select the supply voltage that leads to the largest power savings while ensuring that the error will never exceed the maximum error threshold. This approach also allows restoring of the original error-free circuit if no matching workload distribution is found. The proposed method also leverages the ability of High-Level Synthesis (HLS) to automatically generate circuits with different properties by setting different synthesis constraints to maximize the available timing slack and, hence, maximize the power savings. Experimental results show that our proposed method works very well, saving on average 47.08% of power as compared to the exact output circuit and 20.25% more than a traditional approximation method.

The Use of the Nursing Interventions Classification in Identifying the Workload of a Nursing Team in a Pediatric Oncology Center

The activities/interventions performed by the nursing team and the time required for their performance have become a widely discussed topic due to their impact on the quality of patient safety and staff working conditions. Nursing Interventions Classification (NIC) was used as a more accurate indicator as it identified activities/interventions. This study analyzed the workload distribution of nursing team in a pediatric oncology center.

Distributed multi-robot sweep coverage for a region with unknown workload distribution

This paper considers the scenario where multiple robots collaboratively cover a region in which the exact distribution of workload is unknown prior to the operation. The workload distribution is not uniform in the region, meaning that the time required to cover a unit area varies at different locations of the region. In our approach, we divide the target region into multiple horizontal stripes, and the robots sweep the current stripe while partitioning the next stripe concurrently. We propose a distributed workload partition algorithm and prove that the operation time on each stripe converges to the minimum under the discrete-time update law. We conduct comprehensive simulation studies and compare our method with the existing methods to verify the theoretical results and the advantage of the proposed method. Flight experiments on mini drones are also conducted to demonstrate the practicality of the proposed algorithm.

Accelerating distributed deep neural network training with pipelined MPI allreduce

TensorFlow (TF) is usually combined with the Horovod (HVD) workload distribution package to obtain a parallel tool to train deep neural network on clusters of computers. HVD in turn utilizes a blocking Allreduce primitive to share information among processes, combined with a communication thread to overlap communication with computation. In this work, we perform a thorough experimental analysis to expose (1) the importance of selecting the best algorithm in MPI libraries to realize the Allreduce operation; and (2) the performance acceleration that can be attained when replacing a blocking Allreduce with its non-blocking counterpart (while maintaining the blocking behaviour via the appropriate synchronization mechanism). Furthermore, (3) we explore the benefits of applying pipelining to the communication exchange, demonstrating that these improvements carry over to distributed training via TF+HVD. Finally, (4) we show that pipelining can also boost performance for applications that make heavy use of other collectives, such as Broadcast and Reduce-Scatter.

Research on multi-objective optimal scheduling considering the balance of labor workload distribution

In order to solve the problem of unbalanced workload of employees in parallel flow shop scheduling, a method of job standard balance is proposed to describe the work balance of employees. The minimum delay time of completion and the imbalance of employee work are taken as the two goals of the model. A bi-objective nonlinear integer programming model is proposed. NSGA-II-EDSP, NSGA-II-KES, and NSGA-II-QKES heuristic rule algorithms are designed to solve the problem. A number of computational experiments of different sizes are conducted, and compared with solutions generated by NSGA-II. The experimental results show the advantages of the proposed model and method, which error is reduced 14.56%, 15.16% and 15.67%.

SOLVING THE BOTTLENECK PROBLEM IN A WAREHOUSE USING SIMULATIONS

The uneven workload distribution and working time utilisation create a bottleneck, leading to inefficient utilisation of capacity and increased costs. A bottleneck is a limiting and risk factor for any business entity. In the case of a distribution warehouse, the bottleneck limits its ability to meet the requirements for sending an order within the required time limit. Delays at any phase of a distribution process may result in non-compliance with customer requirements. In solving capacity problems and bottlenecks elimination, computer simulations and optimisation are often used. The article presents a basic simulation analysis of workload distribution and work times, useful for logistics companies, thus for the area of human and financial resources. In the article, the use of simulations in the ExtendSim9 program to eliminate the bottleneck is discussed. The bottleneck is solved by experiments on a simulation model when optimal workers assignment to individual workplaces of the warehouse is sought. The two final proposals for workers allocation, with the current and increased number of workers, are compared in workforce utilisation and system stability. The simulation method allows verification of the proposals' impacts in advance and practically with no financial costs.