CUDA、OpenMP、OpenACC

和并行计算相关的基础知识：并行计算

1. A compression-based memory-efficient optimization for out-of-core GPU stencil computation
2. A Compute Unified System Architecture for Graphics Clusters Incorporating Data-Locality
3. A Device‑Side Execution Model for Multi‑GPU Task Graphs
4. A Method for Estimating Task Granularity for Automating GPU Cycle Sharing
5. A Performance Model for Evaluating Inter-Node Device-Side Communication
6. Accelerating GPU-Based Out-of-Core Stencil Computation with On-the-Fly Compression
7. Automated Code Generation of High-Order Stencils for a Dataflow Architecture
8. DCUDA Dynamic GPU Scheduling with Live Migration Support
9. GPUサイクル共有システムにおける分散深層学習の高速化
10. Lightning Scaling the GPU Programming Model Beyond a Single GPU
11. Multi‑GPU work sharing in a task‑based dataflow programming model
12. PACC An Extension of OpenACC for Pipelined Processing of Large Data on a GPU
13. PaRSEC Parallel Runtime Scheduling and Execution Controller
14. STAPL standard template adaptive parallel library
15. Towards Automating Multi-dimensional Data Decomposition for Executing a Single-GPU Code on a Multi-GPU System
16. GPU上のアウトオブコア・ステンシル計算を高速化するための実行パラメータの選定
17. 単一GPUコードをマルチGPU環境で実行するための多次元データ分割手法の検討

期刊、会议：

1. Future Generation Computer Systems (FGCS)

• Stencil
  • 加速方法
    • 数据重用
    • 数据压缩
    • 压缩索引
    • 优先计算中心部分
    • 时间分块（一次计算多步）
    • 梯形压缩（不太理解？）
    • Wavefront
    • Temporal Blocking
  • 边缘部分叫作【Halo】
• Cholesky 分解
  • 可以分解为Task DAG
• …