性能

Highly concentrated functions play an important role in many research fields including control system analysis and physics, and they turned out to be the key idea behind inverse Laplace transform methods as well. This paper uses the…

There is a large body of legacy scientific code written in languages like Fortran that is not optimised to get the best performance out of heterogeneous acceleration devices like GPUs and FPGAs, and manually porting such code into parallel…

Dynamic affinity scheduling has been an open problem for nearly three decades. The problem is to dynamically schedule multi-type tasks to multi-skilled servers such that the resulting queueing system is both stable in the capacity region…

This note argues for more use of simple models beyond Amdahl's Law: Bottleneck Analysis, Little's Law, and a M/M/1 Queue.

We first consider the static problem of allocating resources to ( i.e. , scheduling) multiple distributed application framework s, possibly with different priorities and server preferences , in a private cloud with heterogeneous servers.…

In recent years, enterprise Solid-State Drives (SSDs) are used in the caching layer of high-performance servers to close the growing performance gap between processing units and storage subsystem. SSD-based I/O caching is typically not…

Optimizing scientific applications to take full advan-tage of modern memory subsystems is a continual challenge forapplication and compiler developers. Factors beyond working setsize affect performance. A benchmark framework that…

Machine learning, as a tool to learn and model complicated (non)linear relationships between input and output data sets, has shown preliminary success in some HPC problems. Using machine learning, scientists are able to augment existing…

SSDs are emerging storage devices which unlike HDDs, do not have mechanical parts and therefore, have superior performance compared to HDDs. Due to the high cost of SSDs, entirely replacing HDDs with SSDs is not economically justified.…

The purpose of this paper is to analyze the so-called back-off technique of the IEEE 802.11 protocol in broadcast mode with waiting queues. In contrast to existing models, packets arriving when a station (or node) is in back-off state are…

Deep Learning system architects strive to design a balanced system where the computational accelerator -- FPGA, GPU, etc, is not starved for data. Feeding training data fast enough to effectively keep the accelerator utilization high is…

The need for Linux system administrators to do performance management has returned with a vengeance. Why? The cloud. Resource consumption in the cloud is all about pay-as-you-go. This article shows you how performance models can find the…

The L-CSC (Lattice Computer for Scientific Computing) is a general purpose compute cluster built with commodity hardware installed at GSI. Its main operational purpose is Lattice QCD (LQCD) calculations for physics simulations. Quantum…

In this paper, we present benchmark data for Intel Memory Drive Technology (IMDT), which is a new generation of Software-defined Memory (SDM) based on Intel ScaleMP collaboration and using 3D XPointTM based Intel Solid-State Drives (SSDs)…

Measuring and analyzing the performance of software has reached a high complexity, caused by more advanced processor designs and the intricate interaction between user programs, the operating system, and the processor's microarchitecture.…

Scheduling to minimize mean response time in an M/G/1 queue is a classic problem. The problem is usually addressed in one of two scenarios. In the perfect-information scenario, the scheduler knows each job's exact size, or service…

The design and construction of high performance computing (HPC) systems relies on exhaustive performance analysis and benchmarking. Traditionally this activity has been geared exclusively towards simulation scientists, who, unsurprisingly,…

Deep Neural Networks (DNNs) require very large amounts of computation both for training and for inference when deployed in the field. Many different algorithms have been proposed to implement the most computationally expensive layers of…

We study how erasure coding can improve service reliability in Data Center Networks (DCN). To this end, we find that coding can be best deployed in systems, where i) traffic is split into multiple parallel sub-flows, ii) each sub-flow is…

Automatic compiler phase selection/ordering has traditionally been focused on CPUs and, to a lesser extent, FPGAs. We present experiments regarding compiler phase ordering specialization of OpenCL kernels targeting a GPU. We use iterative…