The proceedings contain 226 papers. The topics discussed include: analyzing HPC utilization with PIKA and Vampir;portable cross-facility workflows for X-ray ptychography;towards sustainable post-exascale leadership co...
ISBN:
(纸本)9798350355543
The proceedings contain 226 papers. The topics discussed include: analyzing HPC utilization with PIKA and Vampir;portable cross-facility workflows for X-ray ptychography;towards sustainable post-exascale leadership computing;SANReN’s 100 Gbps data transfer service: transferring data fast!;framework for integrating machine learning methods for path-aware source routing;an Ising-based decision method for intra prediction mode in video coding;LLM-inference-bench: inference benchmarking of large language models on AI accelerators;ActorProf: a framework for profiling and visualizing fine-grained asynchronous bulk synchronous parallel execution;LIDC: a location independent multi-cluster computing framework for data intensive science;and Parsl+CWL: towards combining the Python and CWL ecosystems.
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 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 99 papers. The topics discussed include: 5 ExaFlop/s HPL-MxP benchmark with linear scalability on the 40-million-core Sunway Supercomputer;big data assimilation: real-time 30-second-refresh hea...
ISBN:
(纸本)9798400701092
The proceedings contain 99 papers. The topics discussed include: 5 ExaFlop/s HPL-MxP benchmark with linear scalability on the 40-million-core Sunway Supercomputer;big data assimilation: real-time 30-second-refresh heavy rain forecast using Fugaku during Tokyo Olympics and Paralympics;rapid simulations of atmospheric data assimilation of hourly-scale phenomena with modern neural networks;Graphine: enhanced neutral atom quantum computing using application-specific Rydberg atom arrangement;legate sparse: distributed sparse computing in python;clover: toward sustainable ai with carbon-aware machine learning inference service;toward sustainable HPC: carbon footprint estimation and environmental implications of HPC systems;and scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic size.
The proceedings contain 7 papers. The topics discussed include: UnoAPI: balancing performance, portability, and productivity (P3) in HPC education;challenges and triumphs teaching distributed computing topics at a sma...
ISBN:
(纸本)9781665473668
The proceedings contain 7 papers. The topics discussed include: UnoAPI: balancing performance, portability, and productivity (P3) in HPC education;challenges and triumphs teaching distributed computing topics at a small liberal arts college;bridging the gap between education and research: a retrospective on simulating an HPC conference;lightning talks of EduHPC 2022;peachy parallel assignments (EduHPC 2022);adopting heterogeneous computing modules: experiences from a ToUCH Summer Workshop;and OpenMPI+ Java as a highperformance language.
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 4 papers. The topics discussed include: maximizing performance through memory hierarchy-driven data layout transformations;evaluating emerging CXL-enabled memory pooling for HPC systems;reducin...
ISBN:
(纸本)9781665472821
The proceedings contain 4 papers. The topics discussed include: maximizing performance through memory hierarchy-driven data layout transformations;evaluating emerging CXL-enabled memory pooling for HPC systems;reducing memory-bus energy consumption of GPUs via software-based bit-flip minimization;and assessing the memory wall in complex codes.
The proceedings contain 4 papers. The topics discussed include: enabling VirtIO driver support on FPGAs;a first step towards support for MPI partitioned communication on SYCL-programmed FPGAs;fast and energy-efficient...
ISBN:
(纸本)9781665463430
The proceedings contain 4 papers. The topics discussed include: enabling VirtIO driver support on FPGAs;a first step towards support for MPI partitioned communication on SYCL-programmed FPGAs;fast and energy-efficient derivatives risk analysis: streaming option Greeks on Xilinx and Intel FPGAs;and accelerating kernel ridge regression with conjugate gradient method for large-scale data using FPGA high-level synthesis.
The proceedings contain 87 papers. The topics discussed include: reshaping geostatistical modeling and prediction for extreme-scale environmental applications;pushing the frontier in the design of laser-based electron...
ISBN:
(纸本)9781665454445
The proceedings contain 87 papers. The topics discussed include: reshaping geostatistical modeling and prediction for extreme-scale environmental applications;pushing the frontier in the design of laser-based electron accelerators with groundbreaking mesh-refined particle-in-cell simulations on exascale-class supercomputers;extreme scale earthquake simulation with uncertainty quantification;exaflops biomedical knowledge graph analytics;scaling correlated fragment molecular orbital calculations on summit;image gradient decomposition for parallel and memory-efficient ptychographic reconstruction;building blocks for network-accelerated distributed file systems;combining hard and soft constraints in quantum constraint-satisfaction systems;large-scale simulation of quantum computational chemistry on a new Sunway supercomputer;charter: identifying the most-critical gate operations in quantum circuits via amplified gate reversibility;study of workload interference with intelligent routing on dragonfly;and symmetric block-cyclic distribution: fewer communications leads to faster dense Cholesky factorization.
暂无评论