CCF Transactions on High Performance Computing
Издатель: Springer Nature · ISSN 2524-4922,2524-4930 · 97 статей
- An online resource-aware leader election algorithm based on Kubernetes load balancing
- Deep learning-based prediction of major page faults in cluster systems
- A barotropic solver capable of reducing global synchronization latency in parallel ocean program
- Adaptive container scheduling based on reinforcement learning in kubernetes
-
$$\nu$$GNN: Non-Uniformly partitioned full-graph GNN training on mixed GPUs
Abstract Graph neural networks (GNNs) can be adapted to GPUs with high computing capability due to massive arithmetic operations. Compared with mini-batch training, full-graph training does not require sampling of the input graph and...
- Implementation and optimization of batch 3D FFT for sunway many-core processor
- Practice and observation: live migration for MPI workload
- Adaptive point cloud compression based on precision-aware floating-point encoding
- Superfaas: a non-invasive FaaS interface for high performance computing systems
- Optimization of fault tolerance for iterative graph algorithm in spark GraphX based on high performance computing cluster
- A high-performance matrix transposition for a new MIMD architecture processor PEZY-SC3s
- Star-gen: an HPC-AI framework for constructing large-scale computational materials database
-
SyncNOVA: an end-to-end fine-grained profiling tool oN lOck behaVior detection and critical section diAgnosis
Abstract Synchronization performance issues related to lock such as too large critical section and improper lock usage, are inevitable in scientific computing. Even skilled programmers suffer from complicated reports of existing lock...
- Mixed precision block-Jacobi preconditioner: algorithms, performance evaluation and feature analysis
- FUS: FPGA-based Universal Sketch with homogeneous and heterogeneous memory architectures
-
An optimized hierarchical MapReduce framework in supercomputing Internet environment
Abstract Distributed computing frameworks play a crucial role in supporting compute-intensive applications in the era of big data. The growing demand for computing resources has spurred the interconnection of data centers, leading to...
- Hotspy: identifying performance hotspot with graph neural network based static analysis
- SuCL: supply unified communication layer to improve SYCL-based heterogeneous computing
- Mixed precision SpMV on GPUs for irregular data with hierarchical precision selection
- An empirical study of error-free transformations for enhancing mathematical function precision
- Research on GPU transplantation optimization of PRM scalar advection scheme in GRAPES global forecast system
- KANETAS: an elastic scheduler for heterogeneous many-core systems
- Optimizing 2D convolution for DCUs
-
An interpretable DeePMD-kit performance model for emerging supercomputers
Abstract Deep potential (DP) scheme has increased the simulation temporal and spatial scales while maintaining the ab initio accuracy of the molecular dynamics. DeePMD-kit is an outstanding application that implements DP scheme...
- GPU acceleration for DNA sequence alignment algorithm and its application
- An empirical performance evaluation of SYCL on ARM multi-core processors
- SparkAttention: high-performance multi-head attention for large models on Volta GPU architecture
- TxCocket: an innovative solution for efficient cross-node data transmission enabled by CXL-based shared memory
-
Convergence-aware operator-wise mixed-precision training
Abstract With the support of more precision formats in emerging hardware architectures, mixed-precision has become a popular approach to accelerate deep learning (DL) training. Applying low-precision formats such as FP16 and BF16 to...
-
Fine-grained vectorized merge sorting on RISC-V: from register to cache
Abstract Merge sort as a divide-sort-merge paradigm has been widely applied in computer science fields. As modern reduced instruction set computing architectures like the fifth generation (RISC-V) regard multiple registers as a vector...