Chebyshev Filter Diagonalization on Modern Manycore Processors and GPGPUs

Abstract

Chebyshev filter diagonalization is well established in quantum chemistry and quantum physics to compute bulks of eigenvalues of large sparse matrices. Choosing a block vector implementation, we investigate optimization opportunities on the new class of high-performance compute devices featuring both high-bandwidth and low-bandwidth memory. We focus on the transparent access to the full address space supported by both architectures under consideration: Intel Xeon Phi "Knights Landing" and Nvidia "Pascal." We propose two optimizations: (1) Subspace blocking is applied for improved performance and data access efficiency. We also show that it allows transparently handling problems much larger than the high-bandwidth memory without significant performance penalties. (2) Pipelining of communication and computation phases of successive subspaces is implemented to hide communication costs without extra memory traffic. As an application scenario we use filter diagonalization studies on topological insulator materials. Performance numbers on up to 512 nodes of the OakForest-PACS and Piz Daint supercomputers are presented, achieving beyond 100 Tflop/s for computing 100 inner eigenvalues of sparse matrices of dimension one billion.

arXiv comment18 pages, 8 figures

References in corpus (11)

• The Kernel Polynomial Method
• LIKWID: Lightweight Performance Tools
• A unified sparse matrix data format for efficient general sparse matrix-vector multiply on modern processors with wide SIMD units
• Topological insulators in magnetic fields: Quantum Hall effect and edge channels with non-quantized θ-term
• The fate of topological-insulator surface states under strong disorder
• High-performance implementation of Chebyshev filter diagonalization for interior eigenvalue computations
• Chebyshev polynomial filtered subspace iteration in the Discontinuous Galerkin method for large-scale electronic structure calculations
• Metal-to-insulator transition and electron-hole puddle formation in disordered graphene nanoribbons
• Sparse matrix-vector multiplication on GPGPU clusters: A new storage format and a scalable implementation
• GHOST: Building blocks for high performance sparse linear algebra on heterogeneous systems
• Performance Engineering of the Kernel Polynomial Method on Large-Scale CPU-GPU Systems

Cited by in corpus (6)

• A Recursive Algebraic Coloring Technique for Hardware-Efficient Symmetric Sparse Matrix-Vector Multiplication
• Polynomial filter diagonalization of large Floquet unitary operators
• The Role of Idle Waves, Desynchronization, and Bottleneck Evasion in the Performance of Parallel Programs
• Desynchronization and Wave Pattern Formation in MPI-Parallel and Hybrid Memory-Bound Programs
• A domain-specific language and matrix-free stencil code for investigating electronic properties of Dirac and topological materials
• Orthogonal layers of parallelism in large-scale eigenvalue computations