Bandwidth and Locality Aware Task-stealing for Manycore Architectures with Bandwidth-Asymmetric Memory
نویسندگان
چکیده
منابع مشابه
Stealing bandwidth from BitTorrent seeders
BitTorrent continues to comprise the largest fraction of Internet traffic. While significant progress has been made in understanding the BitTorrent choking mechanism, its security vulnerabilities have not been investigated thoroughly. This paper presents an experimental analysis of bandwidth attacks against different choking algorithms in the BitTorrent seed state. We reveal a simple exploit th...
متن کاملBandwidth-aware divisible task scheduling for cloud computing
Task scheduling is a fundamental issue in achieving high efficiency in cloud computing. However, it is a big challenge for efficient scheduling algorithm design and implementation (as general scheduling problem is NP-complete). Most existing task-scheduling methods of cloud computing only consider task resource requirements for CPU and memory, without considering bandwidth requirements. In orde...
متن کاملTemperature-Aware Amdahl’s Law for Manycore Architectures
Small cores provide greater throughput per unit area and per watt when sufficient concurrency is available, motivating organizations with many simple cores. However, sufficient concurrency is often not available; even applications that can use many cores often have serial parts. Amdahl’s Law favors an asymmetric architecture and shows that one or more large, high-ILP cores are needed in these c...
متن کاملBandwidth Stealing via Link-targeted Roq Attacks
We present a scheme that enables a set of flows to acquire an unfair share of bandwidth by mounting an adversarial distributed Reduction of Quality (RoQ) attack on flows competing for that bandwidth. This adversarial behavior stands in sharp contrast to other network exploits, e.g., Denial-ofService (DoS) attacks, whose aim is to simply take down a resource, or severely limit access to a servic...
متن کاملLocality-Aware Work Stealing on Multi-CPU and Multi-GPU Architectures
Most recent HPC platforms have heterogeneous nodes composed of a combination of multi-core CPUs and accelerators, like GPUs. Scheduling on such architectures relies on a static partitioning and cost model. In this paper, we present a locality-aware work stealing scheduler for multi-CPU and multi-GPU architectures, which relies on the XKaapi runtime system. We show performance results on two den...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ACM Transactions on Architecture and Code Optimization
سال: 2019
ISSN: 1544-3566,1544-3973
DOI: 10.1145/3291058