conjugate gradient methods; iterative methods; matrix algebra; message passing; optimisation; parallel processing; shared memory systems; 3D grid; CG convergence rate; Gauss-Seidel smoother parallelization; HPC applications; HPCG; MPI parallelization; TFLOPS; Tianhe-2 system; Xeon Phi shared-memory implementation; algorithmic optimizations; architecture-aware optimizations; block multicolor reordering; communication overhead; communication pattern; data access locality; high performance conjugate gradient benchmark; next generation extreme-scale computing systems; parallelism; sparse linear solvers; unstructured matrices; Benchmark testing; Convergence; Equations; Parallel processing; Sparse matrices; Synchronization; Vectors;
机译:针对Linux集群上非结构化有限元应用的高性能Fortran逐元素预处理共轭梯度求解器的并行化策略
机译:高性能共轭梯度基准:一种用于对高性能计算系统进行排名的新指标
机译:针对基于IA的多核和多核处理器的高性能共轭梯度基准测试的优化
机译:高性能共轭梯度基准的CUDA实现
机译:在理想域的扩展域上结合块对角矩阵族的可约性,并将其应用于矩阵子代数和子群。
机译:用于高性能照片3D打印应用中的加工性质关系的模型树脂系统的制定
机译:基于FpGa的高吞吐量密集矩阵浮点共轭梯度实现
机译:向量超级计算机的pCCG(预条件共轭梯度)方法的有效实现