基于OpenACC的核结构组态相互作用迭代本征解器的GPUs加速
Accelerating an Iterative Eigensolver for Nuclear Structure Configuration Interaction Calculations on GPUs using OpenACC
摘要:
为了加速在配备通用图形处理单元(GPU)的分布式内存并行系统上解决核物理多体计算中产生的大型本征值问题,我们修改了之前开发的本征值求解器的混合MPI/OpenMP实现。使用基于OpenACC指令的编程模型,以FORTRAN 90编写。这种方法需要对原始代码进行最小的更改,并且能够将大规模核结构模拟从分布式存储器众核CPU系统平滑迁移到分布式GPU系统。然而,为了使基于OpenACC的特征值求解器在GPU上高效运行,我们需要考虑众核CPU和GPU设备之间的架构差异。因此,插入OpenACC指令的最佳方式可能与插入OpenMP指令的原始方式不同。我们指出这些差异的实施稀疏矩阵矩阵乘法(SpMM),这构成了本征解算器的主要成本,以及其他差异的预处理步骤和密集的线性代数运算。我们比较了基于OpenACC的实现在多个GPU上执行的性能与分布式内存众核CPU上的性能,并证明了GPU上实现的显着加速比众核CPU的节点上性能。我们还表明,多个GPU上的特征值求解器的整体性能提高是更温和的,由于不同的MPI行列之间的通信开销。
英文摘要:
To accelerate the solution of large eigenvalue problems arising from many-body calculations in nuclear physics on distributed-memory parallel systems equipped with general-purpose Graphic Processing Units (GPUs), we modified a previously developed hybrid MPI/OpenMP implementation of an eigensolver written in FORTRAN 90 by using an OpenACC directives based programming model. Such an approach requires making minimal changes to the original code and enables a smooth migration of large-scale nuclear structure simulations from a distributed-memory many-core CPU system to a distributed GPU system. However, in order to make the OpenACC based eigensolver run efficiently on GPUs, we need to take into account the architectural differences between a many-core CPU and a GPU device. Consequently, the optimal way to insert OpenACC directives may be different from the original way of inserting OpenMP directives. We point out these differences in the implementation of sparse matrix-matrix multiplications (SpMM), which constitutes the main cost of the eigensolver, as well as other differences in the preconditioning step and dense linear algebra operations. We compare the performance of the OpenACC based implementation executed on multiple GPUs with the performance on distributed-memory many-core CPUs, and demonstrate significant speedup achieved on GPUs compared to the on-node performance of a many-core CPU. We also show that the overall performance improvement of the eigensolver on multiple GPUs is more modest due to the communication overhead among different MPI ranks.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。