Engineering topics

Schanen, Michel

Publications and source records attributed to Schanen, Michel.

8 records

DOE OSTI2024

JACC: Leveraging HPC Meta-Programming and Performance Portability with the Just-in-Time and LLVM-based Julia Language

We present JACC (Julia for Accelerators), the first high-level, and performance-portable model for the just-in-time and LLVM-based Julia language. JACC provides a unified and lightweight front end across different back ends available in Julia, enabling the same Julia code to run efficiently on many HPC CPU and GPU targets. We evaluated the performance of JACC for common HPC kernels as well as for the most computationally demanding kernels used in applications, HPCCG, a supercomputing benchmark test for sparse domains, and HARVEY, a blood flow simulator to assist in the diagnosis and treatment of patients suffering from vascular diseases. We carried out the performance analysis on the most advanced US DOE supercomputers: Aurora, Frontier, and Perlmutter. Overall, we show that JACC has a negligible overhead versus vendor-specific solutions, reporting GPU speedups with no extra cost to programmability.

Valero-Lara, Pedro↗

DOE OSTI2024

Parallel interior-point solver for block-structured nonlinear programs on SIMD/GPU architectures

Here, we investigate how to port the standard interior-point method to new exascale architectures for block-structured nonlinear programs with state equations. Computationally, we decompose the interior-point algorithm into two successive operations: the evaluation of the derivatives and the solution of the associated Karush-Kuhn-Tucker (KKT) linear system. Our method accelerates both operations using two levels of parallelism. First, we distribute the computations on multiple processes using coarse parallelism. Second, each process uses SIMD/GPU accelerators locally to accelerate the operations using fine-grained parallelism. The KKT system is reduced by eliminating the inequalities and the state variables from the corresponding equations. We demonstrate our method's capability on the supercomputer Polaris, a testbed for the future exascale Aurora system. Each node is equipped with four GPUs, a setup amenable to our two-level approach. Our experiments on the stochastic optimal power flow problem show that the reduction method is 50x faster than the sparse linear solver HSL MA57 running in serial on the CPU, and 6x faster than Pardiso running in parallel on CPU on the same number of processes.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Fitting Matérn smoothness parameters using automatic differentiation

The Mat$\acute{e}$rn covariance function is ubiquitous in the application of Gaussian processes to spatial statistics and beyond. Perhaps the most important reason for this is that the smoothness parameter $\nu$ gives complete control over the mean-square differentiability of the process, which has significant implications for the behavior of estimated quantities such as interpolants and forecasts. Unfortunately, derivatives of the Mat$\acute{e}$rn covariance function with respect to $\nu$ require derivatives of the modified second-kind Bessel function $K$ $\nu$ with respect to $\nu$. While closed form expressions of these derivatives do exist, they are prohibitively difficult and expensive to compute. For this reason, many software packages require fixing $\nu$ as opposed to estimating it, and all existing software packages that attempt to offer the functionality of estimating $\nu$ use finite difference estimates for $\partial$ $\nu$ $K$ $\nu$ . In this work, we introduce a new implementation of $K$$\nu$ that has been designed to provide derivatives via automatic differentiation (AD), and whose resulting derivatives are significantly faster and more accurate than those computed using finite differences. Here, we provide comprehensive testing for both speed and accuracy and show that our AD solution can be used to build accurate Hessian matrices for second-order maximum likelihood estimation in settings where Hessians built with finite difference approximations completely fail.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

A Scalable Mixed-Integer Decomposition Method for Security-Constrained Optimal Power Flow with Complementarity Constraints

This project aimed to develop a scalable algorithm for security-constrained optimal power flow (SCOPF) under contingency scenarios. In particular, the SCOPF problem targeted in the GO Competition is challenging because of the nonconvexity, its nonsmoothness, and the problem size, which increases with the number of contingency events. Complementarity constraints imposed in post-contingency variables are particularly challenging because they lead to a violation of constraint qualifications at any feasible point.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Toward a scalable robust security-constrained optimal power flow using a proximal projection bundle method

Robust security-constrained optimal power flow (rSCOPF) aims to find the worst-case contingencies of alternating current optimal power flow (ACOPF) in power systems. With the rise of GPU architectures on the upcoming supercomputer architectures, optimization algorithms that rely on sparse linear algebra and indefinite linear systems are becoming increasingly hard to solve efficiently (e.g. interior-point method). To address this we revisit a maximin optimization formulation of the rSCOPF and the single-level mixed-integer semidefinite programming (MISDP) reformulation, which is obtained by taking the Lagrangian relaxation of the inner minimization ACOPF problem. In this paper, we focus on the development of a proximal projection bundle method (PPBM) for solving continuous relaxation node subproblems of the MISDP problem, based primarily on the well-known alternating direction method of multipliers. Cutting planes reminiscent of bundle method ideas are also applied in coordination with updates of the proximal parameter. The cutting-plane method can generate a large number of linear inequalities, leading to a large scale but decomposable quadratic programming (QP) subproblem that is amenable to GPUs. We present the numerical results on the IEEE 30, 57, 118, and 300-bus systems by using our PBMM method. We discuss the main computational bottleneck of our method, which is the time taken to solve each iteration of a QP subproblem instance of the PPBM, and how GPU architectures can accelerate this solution process.

bundle method↗

DOE OSTI2019

A Framework for Distributed Approximation of Moments with Higher-Order Derivatives through Automatic Differentiation

We present a framework for the distributed approximation of moments, enabling the evaluation of the uncertainty in a dynamical system. The first and second moment, mean, and variance are computed with up to third-order Taylor series expansion. The required derivatives for the expansion are generated automatically by automatic differentiation and propagated through an implicit time stepper. The computational kernels are the accumulation of the derivatives (Jacobian, Hessian, tensor) and the covariance matrix. We apply distributed parallelism to the Hessian or third-order tensor, and the user merely has to provide a function for the differential equation, thus achieving similar ease of use as Monte Carlo-based methods. We demonstrate our approach using with benchmarks on Theta, a KNL-based system at the Argonne Leadership Computing Facility.

Automatic Differentiation↗

DOE OSTI2016

Asynchronous Two-Level Checkpointing Scheme for Large-Scale Adjoints in the Spectral-Element Solver Nek5000

Adjoints are an important computational tool for large-scale sensitivity evaluation, uncertainty quantification, and derivative-based optimization. An essential component of their performance is the storage/recomputation balance in which efficient checkpointing methods play a key role. We introduce a novel asynchronous two-level adjoint checkpointing scheme for multistep numerical time discretizations targeted at large-scale numerical simulations. The checkpointing scheme combines bandwidth-limited disk checkpointing and binomial memory checkpointing. Based on assumptions about the target petascale systems, which we later demonstrate to be realistic on the IBM Blue Gene/Q system Mira, we create a model of the expected performance of our checkpointing approach and validate it using the highly scalable Navier-Stokes spectralelement solver Nek5000 on small to moderate subsystems of the Mira supercomputer. In turn, this allows us to predict optimal algorithmic choices when using all of Mira. We also demonstrate that two-level checkpointing is significantly superior to single-level checkpointing when adjoining a large number of time integration steps. To our knowledge, this is the first time two-level checkpointing had been designed, implemented, tuned, and demonstrated on fluid dynamics codes at large scale of 50k+ cores.

Adjoints↗

DOE OSTI2016

On the Strong Scaling of the Spectral Element Solver Nek5000 on Petascale Systems. In: EASC '16 Proceedings of the Exascale Applications and Software Conference 2016, Article No. 5

The present work is targeted at performing a strong scaling study of the high-order spectral element fluid dynamics solver Nek5000. Prior studies such as [5] indicated a recommendable metric for strong scalability from a theoretical viewpoint, which we test here extensively on three parallel machines with different performance characteristics and interconnect networks, namely Mira (IBM Blue Gene/Q), Beskow (Cray XC40) and Titan (Cray XK7). The test cases considered for the simulations correspond to a turbulent flow in a straight pipe at four different friction Reynolds numbers Reτ = 180, 360, 550 and 1000. Considering the linear model for parallel communication we quantify the machine characteristics in order to better assess the scaling behaviors of the code. Subsequently sampling and profiling tools are used to measure the computation and communication times over a large range of compute cores. We also study the effect of the two coarse grid solvers XXT and AMG on the computational time. Super-linear scaling due to a reduction in cache misses is observed on each computer. The strong scaling limit is attained for roughly 5000-10,000 degrees of freedom per core on Mira, 30,000 - 50,0000 on Beskow, with only a small impact of the problem size for both machines, and ranges between 10,000 and 220,000 depending on the problem size on Titan. This work aims at being a reference for Nek5000 users and also serves as a basis for potential issues to address as the community heads towards exascale supercomputers.

Offermans, Nicolas↗