The proceedings contain 10 papers. The topics discussed include: optimized scatter/gather data operations for parallel storage;software-defined storage for fast trajectory queries using a DeltaFS indexed massive direc...
ISBN:
(纸本)9781450351348
The proceedings contain 10 papers. The topics discussed include: optimized scatter/gather data operations for parallel storage;software-defined storage for fast trajectory queries using a DeltaFS indexed massive directory;CoSS: proposing a contract-based storage system for HPC;EMPRESS extensible metadata provider for extreme-scale scientific simulations;taming metadata storms in parallel filesystems with MetaFS;architecting HBM as a high bandwidth, high capacity, self-managed last-level cache;diving into petascale production file systems through large scale profiling and analysis;performanceanalysis of emerging data analytics and HPC workloads;and toward scalable monitoring on large-scale storage for software defined cyberinfrastructure.
The proceedings contain 8 papers. The topics discussed include: efficient transactions for parallel data movement;asynchronous object storage with QoS for scientific and commercial big data;performance and scalability...
ISBN:
(纸本)9781450325059
The proceedings contain 8 papers. The topics discussed include: efficient transactions for parallel data movement;asynchronous object storage with QoS for scientific and commercial big data;performance and scalability evaluation of the ceph parallel file system;structuring PLFS for extensibility;SDS: a framework for scientific data services;predicting intermediate storageperformance for workflow applications;active data: a data-centric approach to data life-cycle management;and Fourier-assisted machine learning of hard disk drive access time models.
The proceedings contain 108 papers. The topics discussed include: versatile Datapath soft error detection on the cheap for HPC applications;network-offloaded bandwidth-optimal broadcast and allgather for distributed A...
ISBN:
(纸本)9798350352917
The proceedings contain 108 papers. The topics discussed include: versatile Datapath soft error detection on the cheap for HPC applications;network-offloaded bandwidth-optimal broadcast and allgather for distributed AI;asynchronous distributed-memory parallel algorithms for influence maximization;EXO: accelerating storage paravirtualization with EBPF;understanding data movement patterns in HPC: a NERSC case study;hZCCL: accelerating collective communication with co-designed homomorphic compression;MProt-DPO: breaking the ExaFLOPS barrier for multimodal protein design workflows with direct preference optimization;scaling molecular dynamics with ab initio accuracy to 149 nanoseconds per day;and AutoCheck: automatically identifying variables for checkpointing by data dependency analysis.
The proceedings contain 9 papers. The topics discussed include: scalable in situ analysis of molecular dynamics simulations;in situ visualization of radiation transport geometry;cosmological particle data compression ...
ISBN:
(纸本)9781450351393
The proceedings contain 9 papers. The topics discussed include: scalable in situ analysis of molecular dynamics simulations;in situ visualization of radiation transport geometry;cosmological particle data compression in practice;in situ visualization with task-based parallelism;in situ workflows at exascale: system software to the rescue;a novel shard-based approach for asynchronous many-task models for in situ analysis;in situ summarization with VTK-m;performance impacts of in situ wavelet compression on scientific simulations;and the ALPINE in situ infrastructure: ascending from the ashes of strawman.
The proceedings contain 9 papers. The topics discussed include: self-adjusting two-failure tolerant disk arrays;using a shared storage class memory device to improve the reliability of RAID arrays;semantic data placem...
ISBN:
(纸本)9781424489121
The proceedings contain 9 papers. The topics discussed include: self-adjusting two-failure tolerant disk arrays;using a shared storage class memory device to improve the reliability of RAID arrays;semantic data placement for power management in archival storage;workload characterization of a leadership class storage cluster;performanceanalysis of commodity and enterprise class flash devices;virtualization-based bandwidth management for parallel storage systems;and towards parallel access of multi-dimensional, multi-resolution scientific data.
The proceedings contain 99 papers. The topics discussed include: SYnergy: fine-grained energy-efficient heterogeneous computing for scalable energy saving;5 ExaFlop/s HPL-MxP benchmark with linear scalability on the 4...
ISBN:
(纸本)9798400701092
The proceedings contain 99 papers. The topics discussed include: SYnergy: fine-grained energy-efficient heterogeneous computing for scalable energy saving;5 ExaFlop/s HPL-MxP benchmark with linear scalability on the 40-million-core Sunway supercomputer;GreenNFV: energy-efficient network function virtualization with service level agreement constraints;demystifying and mitigating cross-layer deficiencies of soft error protection in instruction duplication;a quantitative approach for adopting disaggregated memory in HPC systems;legate sparse: distributed sparse computing in Python;large-scale simulation of structural dynamics computing on GPU clusters;NNQS-transformer: an efficient and scalable neural network quantum states approach for ab initio quantum chemistry;and a high-performance MST implementation for GPUs.
The proceedings contain 5 papers. The topics discussed include: adaptation and policy-based resource allocation for efficient bulk data transfers in highperformancecomputing environments;analysis of the effect of co...
ISBN:
(纸本)9781479970193
The proceedings contain 5 papers. The topics discussed include: adaptation and policy-based resource allocation for efficient bulk data transfers in highperformancecomputing environments;analysis of the effect of core affinity on high-throughput flows;towards energy awareness in hadoop;towards managed terabit/s scientific data flows;and flexible scheduling and control of bandwidth and in-transit services for end-to-end application workflows.
The proceedings contain 2 papers. The topics discussed include: improving HPC security with targeted Syscall fuzzing;and SpackNVD: a vulnerability audit tool for Spack packages.
ISBN:
(纸本)9781665475211
The proceedings contain 2 papers. The topics discussed include: improving HPC security with targeted Syscall fuzzing;and SpackNVD: a vulnerability audit tool for Spack packages.
The proceedings contain 6 papers. The topics discussed include: a project-based HPC course for single-box computers;20 years of teaching parallel processing to computer science seniors;teaching MPI from mental models;...
ISBN:
(纸本)9781509038275
The proceedings contain 6 papers. The topics discussed include: a project-based HPC course for single-box computers;20 years of teaching parallel processing to computer science seniors;teaching MPI from mental models;computational science education focused on future domain scientists;scholar: a campus HPC resource to enable computational literacy;and next generation HPC workforce development: the computer system, cluster, and networking summer institute.
暂无评论