다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

sultinanimplementation thatcannotbeexecuted within Multimedia applications usually havethroughput constraints. these timing constraints. Itisnecessary totakethetiming An implementation mustmeetthese constraints, while it constraints intoaccount while minimizing thebuffers. Sevminimizes resource usageandenergyconsumption. The eralapproaches havebeenproposed forminimizing buffer computeintensive kernels oftheseapplications areoften requirements underathroughput constraint. In[9], atechspecified asSynchronous Dataflow Graphs.Communica- nique basedonlinear programming isproposed tocalculate tionbetween nodesinthesegraphs requires storage space aschedule thatrealizes themaximalthroughput whileit whichinfluences throughput. We present exacttechniquestries tominimize buffer sizes. Hwangetal.propose aheuristochart thePareto spaceofthroughput andstorage trade- ticthatcantakeresource constraints into account [10]. This offs, whichcanbeusedtodetermine theminimal storage methodistargeted towards a-cyclic graphs anditalways spaceneeded toexecute agraphunderagiven throughputmaximizes throughput rather thanusing athroughput conconstraint. Thefeasibility oftheapproach isdemonstratedstraint. Thus,itcouldleadtoadditional resource requirewithanumberofexamples. ments. In[13], buffer minimization formaximal throughput ofa subclass ofSDFGs(homogeneous SDFGs) isachieved Categories andSubject Descriptors: C.3[Special-pur- viaaninteger linear programming approach. Ingeneral, poseandApplication-based Systems] Signal processing sys- theminimal buffer sizes obtained withthisapproach cantems notbetranslated toexact minimal buffer sizes forarbitrary GeneralTerms:Algorithms, Experimentation, Theory. SDFGs.We propose, incontrast toexisting work, an ex

Exploring Trade-Offs inBuffer Requirements and Throughput Constraints forSynchronous Dataflow Graphs*

In the late 1990s, powerful economic forces led to the adoption of commodity desktop processors in high-performance computing. This transformation has been so effective that the June 2013 TOP500 list is still dominated by x86. In 2013, the largest commodity market in computing is not PCs or servers, but mobile computing, comprising smart-phones and tablets, most of which are built with ARM-based SoCs. This leads to the suggestion that once mobile SoCs deliver sufficient performance, mobile SoCs can help reduce the cost of HPC. This paper addresses this question in detail. We analyze the trend in mobile SoC performance, comparing it with the similar trend in the 1990s. We also present our experience evaluating performance and efficiency of mobile SoCs, deploying a cluster and evaluating the network and scalability of production applications. In summary, we give a first answer as to whether mobile SoCs are ready for HPC.

Supercomputing with commodity CPUs: are mobile SoCs ready for HPC?

In one embodiment, a data storage device comprises a buffer, a buffer manager, and a buffer client. The buffer client is configured to receive data to be stored in the buffer, to compute a difference between a bank boundary address of the buffer and a starting buffer address for the data, to generate a first data burst having a length equal to the computed difference and including a first portion of the data, and to send the first data burst to the buffer manager, wherein the buffer manager is configured to write the first data burst to the buffer.

Address optimized buffer transfer requests

Stream based languages are a popular approach to expressing parallelism in modern applications. The efficient mapping of streaming parallelism to multi-core processors is, however, highly dependent on the program and underlying architecture. We address this by developing a portable and automatic compiler-based approach to partitioning streaming programs using machine learning. Our technique predicts the ideal partition structure for a given streaming application using prior knowledge learned off-line. Using the predictor we rapidly search the program space (without executing any code) to generate and select a good partition. We applied this technique to standard StreamIt applications and compared against existing approaches. On a 4-core platform, our approach achieves 60% of the best performance found by iteratively compiling and executing over 3000 different partitions per program. We obtain, on average, a 1.90x speedup over the already tuned partitioning scheme of the StreamIt compiler. When compared against a state-of-the-art analytical, model-based approach, we achieve, on average, a 1.77x performance improvement. By porting our approach to a 8-core platform, we are able to obtain 1.8x improvement over the StreamIt default scheme, demonstrating the portability of our approach.

Partitioning streaming parallelism for multi-cores: a machine learning based approach

In 2013, U. S. data centers accounted for 2.2% of the country's total electricity consumption, a figure that is projected to increase rapidly over the next decade. Many important workloads are interactive, and they demand strict levels of quality-of-service (QoS) to meet user expectations, making it challenging to reduce power consumption due to increasing performance demands. This paper introduces Hipster, a technique that combines heuristics and reinforcement learning to manage latency-critical workloads. Hipster's goal is to improve resource efficiency in data centers while respecting the QoS of the latency-critical workloads. Hipster achieves its goal by exploring heterogeneous multi-cores and dynamic voltage and frequency scaling (DVFS). To improve data center utilization and make best usage of the available resources, Hipster can dynamically assign remaining cores to batch workloads without violating the QoS constraints for the latency-critical workloads. We perform experiments using a 64-bit ARM big.LITTLE platform, and show that, compared to prior work, Hipster improves the QoS guarantee for Web-Search from 80% to 96%, and for Memcached from 92% to 99%, while reducing the energy consumption by up to 18%.

/pdf/hipster-hybrid-task-manager-for-latency-critical-cloud-1g5x4aw2ak.pdf

Hipster: Hybrid Task Manager for Latency-Critical Cloud Workloads

EUROSERVER is a collaborative project that aims to dramatically improve data centre energy-efficiency, cost, and software efficiency. It is addressing these important challenges through the coordinated application of several key recent innovations: 64-bit ARM cores, 3D heterogeneous silicon-on-silicon integration, and fully-depleted silicon-on-insulator (FD SOI) process technology, together with new software techniques for efficient resource management, including resource sharing and workload isolation. We are pioneering a system architecture approach that allows specialized silicon devices to be built even for low-volume markets where NRE costs are currently prohibitive. The EUROSERVER device will embed multiple silicon "chiplets" on an active silicon interposer. Its system architecture is being driven by requirements from three use cases: data centres and cloud computing, telecom infrastructures, and high-end embedded systems. We will build two fully integrated full-system prototypes, based on a common micro-server board, and targeting embedded servers and enterprise servers.

EUROSERVER: Energy Efficient Node for European Micro-Servers

Many of the important services running on data centres are latency-critical, time-varying, and demand strict user satisfaction. Stringent tail-latency targets for colocated services and increasing system complexity make it challenging to reduce the power consumption of data centres. Data centres typically sacrifice server efficiency to maintain tail-latency targets resulting in an increased total cost of ownership. This paper introduces Twig, a scalable quality-of-service (QoS) aware task manager for latency-critical services co-located on a server system. Twig successfully leverages deep reinforcement learning to characterise tail latency using hardware performance counters and to drive energy-efficient task management decisions in data centres. We evaluate Twig on a typical data centre server managing four widely used latency-critical services. Our results show that Twig outperforms prior works in reducing energy usage by up to 38% while achieving up to 99% QoS guarantee for latency-critical services.

/pdf/twig-multi-agent-task-management-for-colocated-latency-8569ne321q.pdf

Twig: Multi-Agent Task Management for Colocated Latency-Critical Cloud Services

This paper presents a partitioning and allocation algorithm for an iterative stream compiler, targeting heterogeneous multiprocessors with constrained distributed memory and any communications topology. We introduce a novel definition of connectedness that enables the algorithm to model the capabilities of the compiler. The algorithm uses convexity and connectedness constraints to produce partitions that are easier to compile and require short pipelines. Software pipelining is an effective transformation, but it increases memory footprint and latency, and has a startup overhead. Our algorithm takes account of these downstream costs. We show results for the StreamIt 2.1.1 benchmarks for an SMP, 2*2 mesh, SMP plus accelerator, and IBM QS20 blade, which has two Cell processors. Our results show that the average performance is within 5% of the unrestricted optimum found using a brute force search, while seldom requiring software pipelining. The heuristic is robust, and fast enough to be inside the feedback loop of an iterative compiler.

Paul M. Carpenter

Papers

Supercomputing with commodity CPUs: are mobile SoCs ready for HPC?

Hipster: Hybrid Task Manager for Latency-Critical Cloud Workloads

EUROSERVER: Energy Efficient Node for European Micro-Servers

Twig: Multi-Agent Task Management for Colocated Latency-Critical Cloud Services

Mapping stream programs onto heterogeneous multiprocessor systems