Search NASA⌕ Search

Engineering topics

Sundar, Hari

Publications and source records attributed to Sundar, Hari.

An autoencoder compression approach for accelerating large-scale inverse problems

Abstract Partial differential equation (PDE)-constrained inverse problems are some of the most challenging and computationally demanding problems in computational science today. Fine meshes required to accurately compute the PDE solution introduce an enormous number of parameters and require large-scale computing resources such as more processors and more memory to solve such systems in a reasonable time. For inverse problems constrained by time-dependent PDEs, the adjoint method often employed to compute gradients and higher order derivatives efficiently requires solving a time-reversed, so-called adjoint PDE that depends on the forward PDE solution at each timestep. This necessitates the storage of a high-dimensional forward solution vector at every timestep. Such a procedure quickly exhausts the available memory resources. Several approaches that trade additional computation for reduced memory footprint have been proposed to mitigate the memory bottleneck, including checkpointing and compression strategies. In this work, we propose a close-to-ideal scalable compression approach using autoencoders to eliminate the need for checkpointing and substantial memory storage, thereby reducing the time-to-solution and memory requirements. We compare our approach with checkpointing and an off-the-shelf compression approach on an earth-scale ill-posed seismic inverse problem. The results verify the expected close-to-ideal speedup for the gradient and Hessian-vector product using the proposed autoencoder compression approach. To highlight the usefulness of the proposed approach, we combine the autoencoder compression with the data-informed active subspace (DIAS) prior showing how the DIAS method can be affordably extended to large-scale problems without the need for checkpointing and large memory.

Mathematics↗

Machine and Application Aware Partitioning for Adaptive Mesh Refinement Applications. In: HPDC '17 Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing

Load balancing and partitioning are critical when it comes to parallel computations. Popular partitioning strategies based on space filling curves focus on equally dividing work. The partitions produced are independent of the architecture or the application. Given the ever-increasing relative cost of data movement and increasing heterogeneity of our architectures, it is no longer sufficient to only consider an equal partitioning of work. Minimizing communication costs are equally if not more important. Our hypothesis is that an unequal partitioning that minimizes communication costs significantly can scale and perform better than conventional equal-work partitioning schemes. This tradeoff is dependent on the architecture as well as the application. We validate our hypothesis in the context of a finite-element computation utilizing adaptive mesh-refinement. Our central contribution is a new partitioning scheme that minimizes the overall runtime of subsequent computations by performing architecture and application-aware non-uniform work assignment in order to decrease time to solution, primarily by minimizing data-movement. We evaluate our algorithm by comparing it against standard space-filling curve based partitioning algorithms and observing time-to-solution as well as energy-to-solution for solving Finite Element computations on adaptively refined meshes. We demonstrate excellent scalability of our new partition algorithm up to $262,144$ cores on ORNL's Titan and demonstrate that the proposed partitioning scheme reduces overall energy as well as time-to-solution for application codes by up to 22.0%.

Fernando, Milinda↗

Comparison of multigrid algorithms for high‐order continuous finite element discretizations

Summary We present a comparison of different multigrid approaches for the solution of systems arising from high‐order continuous finite element discretizations of elliptic partial differential equations on complex geometries. We consider the pointwise Jacobi, the Chebyshev‐accelerated Jacobi, and the symmetric successive over‐relaxation smoothers, as well as elementwise block Jacobi smoothing. Three approaches for the multigrid hierarchy are compared: (1) high‐order h ‐multigrid, which uses high‐order interpolation and restriction between geometrically coarsened meshes; (2) p ‐multigrid, in which the polynomial order is reduced while the mesh remains unchanged, and the interpolation and restriction incorporate the different‐order basis functions; and (3) a first‐order approximation multigrid preconditioner constructed using the nodes of the high‐order discretization. This latter approach is often combined with algebraic multigrid for the low‐order operator and is attractive for high‐order discretizations on unstructured meshes, where geometric coarsening is difficult. Based on a simple performance model, we compare the computational cost of the different approaches. Using scalar test problems in two and three dimensions with constant and varying coefficients, we compare the performance of the different multigrid approaches for polynomial orders up to 16. Overall, both h ‐multigrid and p ‐multigrid work well; the first‐order approximation is less efficient. For constant coefficients, all smoothers work well. For variable coefficients, Chebyshev and symmetric successive over‐relaxation smoothing outperform Jacobi smoothing. While all of the tested methods converge in a mesh‐independent number of iterations, none of them behaves completely independent of the polynomial order. When multigrid is used as a preconditioner in a Krylov method, the iteration number decreases significantly compared with using multigrid as a solver. Copyright © 2015 John Wiley & Sons, Ltd.

Sundar, Hari↗

HykSort: a new variant of hypercube quicksort on distributed memory architectures. In: ICS '13 Proceedings of the 27th international ACM conference on International conference on supercomputing

In this paper, we present HykSort, an optimized comparison sort for distributed memory architectures that attains more than 2× improvement over bitonic sort and samplesort. The algorithm is based on the hypercube quicksort, but instead of a binary recursion, we perform a k-way recursion in which the pivots are selected accurately with an iterative parallel select algorithm. The single-node sort is performed using a vectorized and multithreaded merge sort. The advantages of HykSort are lower communication costs, better load balancing, and avoidance of O(p)-collective communication primitives. We also present a staged communication samplesort, which is more robust than the original samplesort for large core counts. We conduct an experimental study in which we compare hypercube sort, bitonic sort, the original samplesort, the staged samplesort, and HykSort. We report weak and strong scaling results and study the effect of the grain size. It turns out that no single algorithm performs best and a hybridization strategy is necessary. As a highlight of our study, on our largest experiment on 262,144 AMD cores of the CRAY XK7 "Titan" platform at the Oak Ridge National Laboratory we sorted 8 trillion 32-bit integer keys in 37 seconds achieving 0.9TB/s effective throughput.

Sundar, Hari↗

Algorithms for high-throughput disk-to-disk sorting, In: SC '13 Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis

In this paper, we present a new out-of-core sort algorithm, designed for problems that are too large to fit into the aggregate RAM available on modern supercomputers. We analyze the performance including the cost of IO and demonstrate the fastest (to the best of our knowledge) reported throughput using the canonical sortBenchmark on a general-purpose, production HPC resource running Lustre. By clever use of available storage and a formulation of asynchronous data transfer mechanisms, we are able to almost completely hide the computation (sorting) behind the IO latency. This latency hiding enables us to achieve comparable execution times, including the additional temporary IO required, between a large sort problem (5TB) run as a single, in-RAM sort and our out-of-core approach using 1/10th the amount of RAM. In our largest run, sorting 100TB of records using 1792 hosts, we achieved an end-to-end throughput of 1.24TB/min using our general-purpose sorter, improving on the current Daytona record holder by 65%.

Computer Science↗

Parallel fast gauss transform

We present fast adaptive parallel algorithms to compute the sum of N Gaussians at N points. Direct sequential computation of this sum would take O(N{sup 2}) time. The parallel time complexity estimates for our algorithms are O(N/n{sub p}) for uniform point distributions and O( (N/n{sub p}) log (N/n{sub p}) + n{sub p}log n{sub p}) for non-uniform distributions using n{sub p} CPUs. We incorporate a plane-wave representation of the Gaussian kernel which permits 'diagonal translation'. We use parallel octrees and a new scheme for translating the plane-waves to efficiently handle non-uniform distributions. Computing the transform to six-digit accuracy at 120 billion points took approximately 140 seconds using 4096 cores on the Jaguar supercomputer. Our implementation is 'kernel-independent' and can handle other 'Gaussian-type' kernels even when explicit analytic expression for the kernel is not known. These algorithms form a new class of core computational machinery for solving parabolic PDEs on massively parallel architectures.

99 GENERAL AND MISCELLANEOUS↗