SCI Publications

Modeling thermal radiation is computationally challenging in parallel due to its all-to-all physical and resulting computational connectivity, and is also the dominant mode of heat transfer in practical applications such as next-generation clean coal boilers, being modeled by the Uintah framework. However, a direct all-to-all treatment of radiation is prohibitively expensive on large computers systems whether homogeneous or heterogeneous. DOE Titan and the planned DOE Summit and Sierra machines are examples of current and emerging GPUbased heterogeneous systems where the increased processing capability of GPUs over CPUs exacerbates this problem. These systems require that computational frameworks like Uintah leverage an arbitrary number of on-node GPUs, while simultaneously utilizing thousands of GPUs within a single simulation. We show that radiative heat transfer problems can be made to scale within Uintah on heterogeneous systems through a combination of reverse Monte Carlo ray tracing (RMCRT) techniques combined with AMR, to reduce the amount of global communication. In particular, significant Uintah infrastructure changes, including a novel lock and contention-free, thread-scalable data structure for managing MPI communication requests and improved memory allocation strategies were necessary to achieve excellent strong scaling results to 16384 GPUs on Titan.

The current diversity in nodal parallel computer architectures is seen in machines based upon multicore CPUs, GPUs and the Intel Xeon Phi's. A class of approaches for enabling scalability of complex applications on such architectures is based upon Asynchronous Many Task software architectures such as that in the Uintah framework used for the parallel solution of solid and fluid mechanics problems. Uintah has both an applications layer with its own programming model and a separate runtime system. While Uintah scales well today, it is necessary to address nodal performance portability in order for it to continue to do. Incrementally modifying Uintah to use the Kokkos performance portability library through prototyping experiments results in improved kernel performance by more than a factor of two.

The current diversity in nodal parallel computer architectures is seen in machines based upon multicore CPUs, GPUs and the Intel Xeon Phi's. A class of approaches for enabling scalability of complex applications on such architectures is based upon Asynchronous Many Task software architectures such as that in the Uintah framework used for the parallel solution of solid and fluid mechanics problems. Uintah has both an applications layer with its own programming model and a separate runtime system. While Uintah scales well today, it is necessary to address nodal performance portability in order for it to continue to do. Incrementally modifying Uintah to use the Kokkos performance portability library through prototyping experiments results in improved kernel performance by more than a factor of two.

This report provides in-depth information and analysis to help create a technical road map for developing nextgeneration programming models and runtime systems that support Advanced Simulation and Computing (ASC) workload requirements. The focus herein is on asynchronous many-task (AMT) model and runtime systems, which are of great interest in the context of "exascale" computing, as they hold the promise to address key issues associated with future extreme-scale computer architectures. This report includes a thorough qualitative and quantitative examination of three best-of-class AMT runtime systems—Charm++, Legion, and Uintah, all of which are in use as part of the ASC Predictive Science Academic Alliance Program II (PSAAP-II) Centers. The studies focus on each of the runtimes' programmability, performance, and mutability. Through the experiments and analysis presented, several overarching findings emerge. From a performance perspective, AMT runtimes show tremendous potential for addressing extremescale challenges. Empirical studies show an AMT runtime can mitigate performance heterogeneity inherent to the machine itself and that Message Passing Interface (MPI) and AMT runtimes perform comparably under balanced conditions. From a programmability and mutability perspective however, none of the runtimes in this study are currently ready for use in developing production-ready Sandia ASC applications. The report concludes by recommending a codesign path forward, wherein application, programming model, and runtime system developers work together to define requirements and solutions. Such a requirements-driven co-design approach benefits the high-performance computing (HPC) community as a whole, with widespread community engagement mitigating risk for both application developers and runtime system developers.

While particle-in-cell type methods, such as MPM, have been very successful in providing solutions to many challenging problems there are some important issues that remain to be resolved with regard to their analysis. One such challenge relates to the difference in dimensionality between the particles and the grid points to which they are mapped. There exists a non-trivial null space of the linear operator that maps particles values onto nodal values. In other words, there are non-zero particle values values that when mapped to the nodes are zero there. Given positive mapping weights such null space values are oscillatory in nature. The null space may be viewed as a more general form of the ringing instability identified by Brackbill for PIC methods. It will be shown that it is possible to remove these null-space values from the solution and so to improve the accuracy of PIC methods, using a matrix SVD approach. The expense of doing this is prohibitive for real problems and so a local method is developed for doing this.

In this chapter, we illustrate benefits of thinking in terms of thread management techniques when using a centralized scheduler model along with interoperability of MPI and PThreads. This is facilitated through an exploration of thread placement strategies for an algorithm modeling radiative heat transfer with special attention to the 61^st core. This algorithm plays a key role within the Uintah Computational Framework (UCF) and current efforts taking place at the University of Utah to model next-generation, large-scale clean coal boilers. In such simulations, this algorithm models the dominant form of heat transfer and consumes a large portion of compute time. Exemplified by a real-world example, this chapter presents our early efforts in porting a key portion of a scalability-centric codebase to the Intel ® Xeon Phi^TM coprocessor. Specifically, this chapter presents results from our experiments profiling the native execution of a reverse Monte-Carlo ray tracing-based radiation model on a single coprocessor. These results demonstrate that our fastest run confiurations utilized the 61st core and that performance was not profoundly impacted when explicitly over-subscribing the coprocessor operating system thread. Additionally, this chapter presents a portion of radiation model source code, a MIC-centric UCF cross-compilation example, and less conventional thread management techniques for developers utilizing the PThreads threading model.

Radiative heat transfer is an important mechanism in a class of challenging engineering and research problems. A direct all-to-all treatment of these problems is prohibitively expensive on large core counts due to pervasive all-to-all MPI communication. The massive heat transfer problem arising from the next generation of clean coal boilers being modeled by the Uintah framework has radiation as a dominant heat transfer mode. Reverse Monte Carlo ray tracing (RMCRT) can be used to solve for the radiative-flux divergence while accounting for the effects of participating media. The ray tracing approach used here replicates the geometry of the boiler on a multi-core node and then uses an all-to-all communication phase to distribute the results globally. The cost of this all-to-all is reduced by using an adaptive mesh approach in which a fine mesh is only used locally, and a coarse mesh is used elsewhere. A model for communication and computation complexity is used to predict performance of this new method. We show this model is consistent with observed results and demonstrate excellent strong scaling to 262K cores on the DOE Titan system on problem sizes that were previously computationally intractable.

Keywords: Uintah; Radiation modeling; Parallel; Scalability; Adaptive mesh refinement; Simulation science; Titan

Over the last decade block-structured adaptive mesh refinement (SAMR) has found increasing use in large, publicly available codes and frameworks. SAMR frameworks have evolved along different paths. Some have stayed focused on specific domain areas, others have pursued a more general functionality, providing the building blocks for a larger variety of applications. In this survey paper we examine a representative set of SAMR packages and SAMR-based codes that have been in existence for half a decade or more, have a reasonably sized and active user base outside of their home institutions, and are publicly available. The set consists of a mix of SAMR packages and application codes that cover a broad range of scientific domains. We look at their high-level frameworks, their design trade-offs and their approach to dealing with the advent of radical changes in hardware architecture. The codes included in this survey are BoxLib, Cactus, Chombo, Enzo, FLASH, and Uintah.

Keywords: SAMR, BoxLib, Chombo, FLASH, Cactus, Enzo, Uintah

Fast, scalable, low-cost, and low-power execution of parallel graph algorithms is important for a wide variety of commercial and public sector applications. Breadth First Search (BFS) imposes an extreme burden on memory bandwidth and network communications and has been proposed as a benchmark that may be used to evaluate current and future parallel computers. Hardware trends and manufacturing limits strongly imply that many core devices, such as NVIDIA® GPUs and the Intel® Xeon Phi®, will become central components of such future systems. GPUs are well known to deliver the highest FLOPS/watt and enjoy a very significant memory bandwidth advantage over CPU architectures. Recent work has demonstrated that GPUs can deliver high performance for parallel graph algorithms and, further, that it is possible to encapsulate that capability in a manner that hides the low level details of the GPU architecture and the CUDA language but preserves the high throughput of the GPU. We extend previous research on GPUs and on scalable graph processing on super-computers and demonstrate that a high-performance parallel graph machine can be created using commodity GPUs and networking hardware.

Keywords: GPU cluster, MPI, BFS, graph, parallel graph algorithm

Fast, scalable, low-cost, and low-power execution of parallel graph algorithms is important for a wide variety of commercial and public sector applications. Breadth First Search (BFS) imposes an extreme burden on memory bandwidth and network communications and has been proposed as a benchmark that may be used to evaluate current and future parallel computers. Hardware trends and manufacturing limits strongly imply that many core devices, such as NVIDIA® GPUs and the Intel® Xeon Phi®, will become central components of such future systems. GPUs are well known to deliver the highest FLOPS/watt and enjoy a very significant memory bandwidth advantage over CPU architectures. Recent work has demonstrated that GPUs can deliver high performance for parallel graph algorithms and, further, that it is possible to encapsulate that capability in a manner that hides the low level details of the GPU architecture and the CUDA language but preserves the high throughput of the GPU. We extend previous research on GPUs and on scalable graph processing on super-computers and demonstrate that a high-performance parallel graph machine can be created using commodity GPUs and networking hardware.

Keywords: GPU cluster, MPI, BFS, graph, parallel graph algorithm

Parallel computational frameworks for high performance computing (HPC) are central to the advancement of simulation based studies in science and engineering. Unfortunately, finding and fixing bugs in these frameworks can be extremely time consuming. Left unchecked, these bugs can drastically diminish the amount of new science that can be performed. This paper presents our systematic study of the Uintah Computational Framework, and our approaches to debug it more incisively. Our key insight is to leverage the modular structure of Uintah which lends itself to systematic debugging. In particular, we have developed a new approach based on Coalesced Stack Trace Graphs (CSTGs) that summarize the system behavior in terms of key control flows manifested through function invocation chains. We illustrate several scenarios how CSTGs could help efficiently localize bugs, and present a case study of how we found and fixed a real Uintah bug using CSTGs.

Keywords: Computational Modeling and Frameworks, Parallel Programming, Reliability, Debugging Aids

Today's massively parallel simulation code can produce output ranging up to many terabytes of data. Utilizing this data to support scientific inquiry requires analysis and visualization, yet the sheer size of the data makes it cumbersome or impossible to read without computational resources similar to the original simulation. We identify two broad classes of problems for reading data and present effective solutions for both. The first class of data reads depends on user requirements and available resources. Tasks such as visualization and user-guided analysis may be accomplished using only a subset of variables with restricted spatial extents at a reduced resolution. The other class of reads require full resolution multi-variate data to be loaded, for example to restart a simulation. We show that utilizing the hierarchical multi-resolution IDX data format enables scalable and efficient serial and parallel read access on a variety of hardware from supercomputers down to portable devices. We demonstrate interactive view-dependent visualization and analysis of massive scientific datasets using low-power commodity hardware, and we compare read performance with other parallel file formats for both full and partial resolution data.

Uintah is a software framework that provides an environment for solving fluid–structure interaction problems on structured adaptive grids for large-scale science and engineering problems involving the solution of partial differential equations. Uintah uses a combination of fluid flow solvers and particle-based methods for solids, together with adaptive meshing and a novel asynchronous task-based approach with fully automated load balancing. When applying Uintah to fluid–structure interaction problems, the combination of adaptive mesh- ing and the movement of structures through space present a formidable challenge in terms of achieving scalability on large-scale parallel computers. The Uintah approach to the growth of the number of core counts per socket together with the prospect of less memory per core is to adopt a model that uses MPI to communicate between nodes and a shared memory model on-node so as to achieve scalability on large-scale systems. For this approach to be successful, it is necessary to design data structures that large numbers of cores can simultaneously access without contention. This scalability challenge is addressed here for Uintah, by the development of new hybrid runtime and scheduling algorithms combined with novel lock-free data structures, making it possible for Uintah to achieve excellent scalability for a challenging fluid–structure problem with mesh refinement on as many as 260K cores.

Keywords: MPI, threads, Uintah, many core, lock free, fluid-structure interaction, c-safe

A central need during software development of large-scale parallel systems is tools that help help to identify the root causes of bugs quickly. Given the massive scale of these systems, tools that highlight changes--say introduced across software versions or their operating conditions (e.g., inputs, schedules)--can prove to be highly effective in practice. Conventional debuggers, while good at presenting details at the problem-site (e.g., crash), often omit contextual information to identify the root causes of the bug. We present a new approach to collect and coalesce stack traces, leading to an efficient summary display of salient system control flow differences in a graphical form called Coalesced Stack Trace Graphs (CSTG). CSTGs have helped us understand and debug situations within a computational framework called Uintah that has been deployed at large scale, and undergoes frequent version updates. In this paper, we detail CSTGs through case studies in the context of Uintah where unexpected behaviors caused by different vesions of software or occurring across different time-steps of a system (e.g., due to non-determinism) are debugged. We show that CSTG also gives conventional debuggers a far more productive and guided role to play.

Accidental explosions are exceptionally dangerous and costly, both in lives and money. Regarding world-wide conflict with small arms and light weapons, the Small Arms Survey has recorded over 297 accidental explosions in munitions depots across the world that have resulted in thousands of deaths and billions of dollars in damage in the past decade alone [45]. As the recent fertilizer plant explosion that killed 15 people in West, Texas demonstrates, accidental explosions are not limited to military operations. Transportation accidents also pose risks, as illustrated by the occasional train derailment/explosion in the nightly news, or the semi-truck explosion detailed in the following section. Unlike other industrial accident scenarios, explosions can easily affect the general public, a dramatic example being the PEPCON disaster in 1988, where windows were shattered, doors blown off their hinges, and flying glass and debris caused injuries up to 10 miles away.

While the relative rarity of accidental explosions speaks well of our understanding to date, their violence rightly gives us pause. A better understanding of these materials is clearly still needed, but a significant barrier is the complexity of these materials and the various length scales involved. In typical military applications, explosives are known to be ignited by the coalescence of hot spots which occur on micrometer scales. Whether this reaction remains a deflagration (burning) or builds to a detonation depends both on the stimulus and the boundary conditions or level of confinement. Boundary conditions are typically on the scale of engineered parts, approximately meters. Additional dangers are present at the scale of trucks and factories. The interaction of various entities, such as barrels of fertilizer or crates of detonators, admits the possibility of a sympathetic detonation, i.e. the unintended detonation of one entity by the explosion of another, generally caused by an explosive shock wave or blast fragments.

While experimental work has been and will continue to be critical to developing our fundamental understanding of explosive initiation, de agration and detonation, there is no practical way to comprehensively assess safety on the scale of trucks and factories experimentally. The scenarios are too diverse and the costs too great. Numerical simulation provides a complementary tool that, with the steadily increasing computational power of the past decades, makes simulations at this scale begin to look plausible. Simulations at both the micrometer scale, the "mesoscale", and at the scale of engineered parts, the "macro-scale", have been contributing increasingly to our understanding of these materials. Still, simulations on this scale require both massively parallel computational infrastructure and selective sampling of mesoscale response, i.e. advanced computational tools and modeling. The computational framework Uintah [1] has been developed for exactly this purpose.

Keywords: uintah, c-safe, accidents, explosions, military computing, risk analysis

The past, present and future scalability of the Uintah Software framework is considered with the intention of describing a successful approach to large scale parallelism and also considering how this approach may need to be extended for future architectures. Uintah allows the solution of large scale fluid-structure interaction problems through the use of fluid flow solvers coupled with particle-based solids methods. In addition Uintah uses a combustion solver to tackle a broad and challenging class of turbulent combustion problems. A unique feature of Uintah is that it uses an asynchronous task-based approach with automatic load balancing to solve complex problems using techniques such as adaptive mesh refinement. At present, Uintah is able to make full use of present-day massively parallel machines as the result of three phases of development over the past dozen years. These development phases have led to an adaptive scalable run-time system that is capable of independently scheduling tasks to multiple CPUs cores and GPUs on a node. In the case of solving incompressible low-mach number applications it is also necessary to use linear solvers and to consider the challenges of radiation problems. The approaches adopted to achieve present scalability are described and their extensions to possible future architectures is considered.

Keywords: netl, Uintah, parallelism, scalability, adaptive mesh refinement, linear equations