arXiv subjects

Gourab Panigrahi

Publications and source records attributed to Gourab Panigrahi.

3 recordsLinked to original sources

arXiv2026

Towards exascale fully relativistic pseudopotential density functional theory calculations enabled by mixed-precision computation and compressed-communication using residual based subspace iteration

Materials exhibiting noncollinear magnetism or strong spin-orbit-coupling underpin many spintronic and topological applications, but their simulations require complex two-component spinors and costs substantially more than scalar density functional theory (DFT). We present a GPU-centric exascale finite-element DFT framework with noncollinear magnetism and spin-orbit-coupling, combining (i) adaptive higher-order finite-element discretization, (ii) a matrix-free Poisson solver, (iii) residual-based Chebyshev filtered subspace iteration (R-ChFSI) for sparse generalized eigenproblems, (iv) R-ChFSI-enabled mixed precision computation with block floating-point compressed MPI communication, and (v) communication-efficient band partitioning. R-ChFSI permits inexact matrix-multivector products and $4\times$--$6.4\times$ compression of communicated data relative to FP64 while preserving double-precision robustness and reducing computation and data movement. Results demonstrate strong scaling on Aurora and Frontier, with up to $3.4\times$ faster Chebyshev filtering. On Aurora, total self-consistent-field (SCF) solve wall time reduces by $2\times$. An 800-node (9,600-GPU) calculation demonstrates fully relativistic pseudopotential DFT for $\sim$80,000 electrons in under 7 minutes per SCF iteration.

cond-mat.mtrl-sci↗

arXiv2026

Matrix-free algorithms for fast ab initio calculations on distributed CPU architectures using finite-element discretization

Finite-element (FE) discretisations have emerged as a powerful real-space alternative to large-scale Kohn-Sham density functional theory (DFT) calculations, offering systematic convergence, excellent parallel scalability, while accommodating generic boundary conditions. However, the dominant computational bottleneck in FE-based DFT arises from the repeated application of the discretised sparse Hamiltonian to large blocks of trial vectors during iterations in an iterative eigensolver. Traditional sparse matrix-vector multiplications and FE cell-matrix approaches encounter memory limitations and high data-movement overheads, particularly at higher polynomial orders, typically used in DFT calculations. To overcome these challenges, this work develops matrix-free algorithms for FE-discretised DFT that substantially accelerate these products by doing on-the-fly operations that utilize structured tensor contractions over 1D basis functions and quadrature data. A unified multilevel batched data layout that handles both real and complex-valued operators is introduced to maximise cache reuse and SIMD utilisation on Frontier (AVX2), Param Pravega (AVX512) and Fugaku (SVE). We also combine terms for optimal cache reuse, even-odd decomposition to reduce FLOP, and mixed-precision intrinsics. Extensive benchmarks show that for large multivector pseudopotential DFT calculations, the matrix-free kernels deliver 1.5-4x speedups over the state-of-the-art cell-matrix approach baselines. For all-electron DFT calculations, the matrix-free operator achieves gains of up to 5.8x due to its efficient implementation and superior arithmetic intensity. When integrated with an error-tolerant Chebyshev-filtered subspace iteration eigensolver, the matrix-free formalism yields substantial reductions in end-to-end time-to-solution using FE meshes that deliver desired accuracies in ground-state properties.

physics.comp-ph↗

arXiv2023

Fast hardware-aware matrix-free algorithm for higher-order finite-element discretized matrix multivector products on distributed systems

Recent hardware-aware matrix-free algorithms for higher-order finite-element (FE) discretized matrix-vector multiplications reduce floating point operations and data access costs compared to traditional sparse matrix approaches. This work proposes efficient matrix-free algorithms for evaluating FE discretized matrix-multivector products on both multi-node CPU and GPU architectures. We address a critical gap in existing matrix-free implementations, which are well suited only for the action of FE discretized matrices on a single vector. We employ batched evaluation strategies, with the batchsize tailored to underlying hardware architectures, leading to better data locality and enabling further parallelization. On CPUs, we utilize even-odd decomposition, SIMD vectorization, and overlapping computation and communication strategies. On GPUs, we employ strategies to overlap compute and data movement in conjunction with GPU shared memory, constant memory, and kernel fusion to reduce data accesses. Our implementation outperforms the baselines for Helmholtz operator action, achieving up to 1.4x improvement on one CPU node and up to 2.8x on one GPU node, while reaching up to 4.4x and 1.5x improvement on multiple nodes for CPUs ($\sim 3000$ cores) and GPUs ($\sim$ 25 GPUs), respectively. We further benchmark the performance of the proposed implementation for solving a model eigenvalue problem for 1024 smallest eigenvalue-eigenvector pairs by employing the Chebyshev Filtered Subspace Iteration method, achieving up to 1.5x improvement on one CPU node and up to 2.2x on one GPU node while reaching up to 3.0x and 1.4x improvement on multinode CPUs ($\sim 3000$ cores) and GPUs ($\sim$ 25 GPUs), respectively.

physics.comp-ph↗