Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel computer architecture”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,675 records · Page 93

Scalable Bayesian optimization with randomized prior networks

Several fundamental problems in science and engineering consist of global optimization tasks involving unknown high-dimensional (black-box) functions that map a set of controllable variables to the outcomes of an expensive experiment. Bayesian Optimization (BO) techniques are known to be effective in tackling global optimization problems using a relatively small number objective function evaluations, but their performance suffers when dealing with high-dimensional outputs. To overcome the major challenge of dimensionality, here we propose a deep learning framework for BO and sequential decision making based on bootstrapped ensembles of neural architectures with randomized priors. Using appropriate architecture choices, we show that the proposed framework can approximate functional relationships between design variables and quantities of interest, even in cases where the latter take values in high-dimensional vector spaces or even infinite-dimensional function spaces. In the context of BO, we augmented the proposed probabilistic surrogates with re-parameterized Monte Carlo approximations of multiple-point (parallel) acquisition functions, as well as methodological extensions for accommodating black-box constraints and multi-fidelity information sources. We test the proposed framework against state-of-the-art methods for BO and demonstrate superior performance across several challenging tasks with high-dimensional outputs, including a constrained multi-fidelity optimization task involving shape optimization of rotor blades in turbo-machinery.

97 MATHEMATICS AND COMPUTING↗

Better, Cheaper, Faster Molecular Dynamics

Recent, revolutionary progress in genomics and structural, molecular and cellular biology has created new opportunities for molecular-level computer simulations of biological systems by providing vast amounts of data that require interpretation. These opportunities are further enhanced by the increasing availability of massively parallel computers. For many problems, the method of choice is classical molecular dynamics (iterative solving of Newton's equations of motion). It focuses on two main objectives. One is to calculate the relative stability of different states of the system. A typical problem that has' such an objective is computer-aided drug design. Another common objective is to describe evolution of the system towards a low energy (possibly the global minimum energy), "native" state. Perhaps the best example of such a problem is protein folding. Both types of problems share the same difficulty. Often, different states of the system are separated by high energy barriers, which implies that transitions between these states are rare events. This, in turn, can greatly impede exploration of phase space. In some instances this can lead to "quasi non-ergodicity", whereby a part of phase space is inaccessible on time scales of the simulation. To overcome this difficulty and to extend molecular dynamics to "biological" time scales (millisecond or longer) new physical formulations and new algorithmic developments are required. To be efficient they should account for natural limitations of multi-processor computer architecture. I will present work along these lines done in my group. In particular, I will focus on a new approach to calculating the free energies (stability) of different states and to overcoming "the curse of rare events". I will also discuss algorithmic improvements to multiple time step methods and to the treatment of slowly decaying, log-ranged, electrostatic effects.

Pohorille, Andrew↗

NASA Earth Systems Digital Twins (ESDT)

"Similarly to artificial intelligence, which is now revolutionizing many aspects of our daily lives, Earth system digital twin technologies have the potential to revolutionize the way Earth Science research will be conducted in the future, and how results and knowledge from this research will provide information to support decision making and yield impactful societal benefits. An Earth System Digital Twin or ESDT is a dynamic and interactive information system that first provides a digital replica of the past and current states of the Earth or Earth system as accurately and timely as possible; second, allows for computing forecasts of future states under nominal assumptions and based on the current replica; and third, offers the capability to investigate many hypothetical scenarios under varying impact assumptions. In other words, an ESDT provides the integrated What-Now, What-Next, and What-If pictures of the Earth or Earth system, by continuously ingesting newly observed data and by leveraging multiple interconnected models, machine learning as well advanced computing and visualization capabilities. Digital twins have been developed in engineering since 2002, but the interest in digital twins for the Earth domain is more recent and stems from the convergence of several developments: - The huge amount of diverse data that has now been collected continuously for more than 50 years, and that is becoming more and more difficult to access, understand, and utilize. - At the same time, because of climate change and its impacts the information produced by all of this data is becoming of interest to many new non-traditional users for analyzing and predicting various phenomena. - Because of advances in computational and visualization capabilities and the parallel unprecedented development of machine learning (ML), extracting relevant information from these large amounts of data and running complex models faster has become possible. As a result, it is becoming necessary and possible to build intuitive and interactive frameworks that will enable users with various skill levels and/or organizational hierarchy levels to easily access large amounts of targeted information along with the relevant tools and models (Earth system and human activity models), to support them in analyzing and visualizing this information, to help them understand interactions among models, to visualize the potential outcomes of various impacts, and to support decision or policy making. The full power of digital twins is that, through an integrated representation and standardized tools and software technologies, the same digital replica can address the needs of multiple users at various resolutions (spatial and temporal) and for various applications (science, economic, policy, etc.) – “from farmer to scientist”. With all these interests at stake, the challenges of building optimal digital twins are many and complex. The first challenge is to determine if a Digital Twin should be global or local, and multi-domain or thematic. For example, some domains such as Climate or Weather will require a global Digital Twin or Digital Twin capabilities while science areas such as Biodiversity might be more local. We can also envision that multiple thematic ESDTs, e.g., Air Quality, Wildfires, Hydrology could be federated or provide input to other ESDTs, either on a regional level or to a more global ESDT. Overall, we can imagine a future “web” of Digital Twins co-existing in a hierarchy or in a network, and capable of being connected or federated depending on the needs. This last point brings up the very important challenge of interoperability, including standards and protocols that will need to be built into these systems from the beginning. Each individual digital twin would have full flexibility in internal construction but would need standards-based interfaces (input and output) or hooks to make it compatible with others. Another challenge when building digital twins will be to decide how to organize each digital replica. Based on the applications targeted by the DT under implementation, various amounts and types of raw data, Analysis Ready Data (ARD) and information will need to be incorporated. Depending on the required latencies and needs of the users, various solutions can be considered, including Data Cubes, Data Lakes, pointers, or computing information on demand. We envision that each ESDT will choose a solution adapted to its specific objectives. Another important challenge is the type(s) of visualization that will be used, as well as the level of interactivity and refresh rate that will be required. Again, this will depend on the objectives of the ESDT, but also on the various users’ needs. In most cases, several types of visualizations and human interfaces will need to be offered depending on the projected users of that system. In parallel to the challenges highlighted above, there are also many tools and technologies that will need to be developed or improved for all types of digital twins. Among those are improved machine learning technologies, for example providing explainability, but also ML techniques for causality and providing a better integration of physics models. Additionally, reliable uncertainty quantification methods will be needed for all ESDT components, from validating data fusion and assimilation to assessing the accuracy of ML models and weighing the values of decisions supported by those systems. This presentation introduces the ESDT concept, presents several ESDT use cases, and a proposed ESDT architecture framework, as well as various technologies being developed by the Advanced Information Systems Technology (AIST) Program."

Earth Science Remote Sensing; Information Systems↗

Accelerating DCA++ (Dynamical Cluster Approximation) Scientific Application on the Summit supercomputer

Optimizing scientific applications on today’s accelerator-based high performance computing systems can be challenging, especially when multiple GPUs and CPUs with heterogeneous memories and persistent non-volatile memories are present. An example is Summit, an accelerator-based system at the Oak Ridge Leadership Computing Facility (OLCF) that is rated as the world’s fastest supercomputer to-date. New strategies are thus needed to expose the parallelism in legacy applications, while being amenable to efficient mapping to the underlying architecture.In this paper we discuss our experiences and strategies to port a scientific application, DCA++, to Summit. DCA++ is a highperformance research application that solves quantum manybody problems with a cutting edge quantum cluster algorithm, the dynamical cluster approximation.Our strategies aim to synergize the strengths of the different programming models in the code. These include: (a) streamlining the interactions between the CPU threads and the GPUs, (b) implementing computing kernels on the GPUs and decreasing CPU-GPU memory transfers, (c) allowing asynchronous GPU communications, and (d) increasing compute intensity by combining linear algebraic operations.Full-scale production runs using all 4600 Summit nodes attained a peak performance of 73.5 PFLOPS with a mixed precision implementation.We observed a perfect strong and weak scaling for the quantum Monte Carlo solver in DCA++, while encountering about 2× input/output (I/O) and MPI communication overhead on the time-to-solution for the full machine run. Our hardware agnostic optimizations are designed to alleviate the communication and I/O challenges observed, while improving the compute intensity and obtaining optimal performance on a complex, hybrid architecture like Summit.

Balduzzi, Giovanni↗

Exascale models of stellar explosions: Quintessential multi-physics simulation

The ExaStar project aims to deliver an efficient, versatile, and portable software ecosystem for multi-physics astrophysics simulations run on exascale machines. The code suite is a component-based multi-physics toolkit, built on the capabilities of current simulation codes (in particular Flash-X and Castro), and based on the massively parallel adaptive mesh refinement framework AMReX. It includes modules for hydrodynamics, advanced radiation transport, thermonuclear kinetics, and nuclear microphysics. The code will reach exascale efficiency by building upon current multi- and many-core packages integrated into an orchestration system that uses a combination of configuration tools, code translators, and a domain-specific asynchronous runtime to manage performance across a range of platform architectures. The target science includes multi-physics simulations of astrophysical explosions (such as supernovae and neutron star mergers) to understand the cosmic origin of the elements and the fundamental physics of matter and neutrinos under extreme conditions.

79 ASTRONOMY AND ASTROPHYSICS↗

Observability of fidelity decay at the Lyapunov rate in few-qubit quantum simulations

In certain regimes, the fidelity of quantum states will decay at a rate set by the classical Lyapunov exponent. This serves both as one of the most important examples of the quantum-classical correspondence principle and as an accurate test for the presence of chaos. While detecting this phenomenon is one of the first useful calculations that noisy quantum computers without error correction can perform, a thorough study of the quantum sawtooth map reveals that observing the Lyapunov regime is just beyond the reach of present-day devices. We prove that there are three bounds on the ability of any device to observe the Lyapunov regime and give the first quantitatively accurate description of these bounds: (1) the Fermi golden rule decay rate must be larger than the Lyapunov rate, (2) the quantum dynamics must be diffusive rather than localized, and (3) the initial decay rate must be slow enough for Lyapunov decay to be observable. This last bound, which has not been recognized previously, places a limit on the maximum amount of noise that can be tolerated. The theory implies that an absolute minimum of 6 qubits is required. Recent experiments on IBM-Q and IonQ imply that some combination of a noise reduction by up to 100x per gate and large increases in connectivity and gate parallelization are also necessary. Finally, scaling arguments are given that quantify the ability of future devices to observe the Lyapunov regime based on trade-offs between hardware architecture and performance.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Neural Networks for Nuclear Reactions in MAESTROeX

We demonstrate the use of neural networks to accelerate the reaction steps in the MAESTROeX stellar hydrodynamics code. A traditional MAESTROeX simulation uses a stiff ODE integrator for the reactions; here, we employ a ResNet architecture and describe details relating to the architecture, training, and validation of our networks. Our customized approach includes options for the form of the loss functions, a demonstration that the use of parallel neural networks leads to increased accuracy, and a description of a perturbational approach in the training step that robustifies the model. We test our approach on millimeter-scale flames using a single-step, 3-isotope network describing the first stages of carbon fusion occurring in Type Ia supernovae. We train the neural networks using simulation data from a standard MAESTROeX simulation, and show that the resulting model can be effectively applied to different flame configurations. This work lays the groundwork for more complex networks, and iterative time-integration strategies that can leverage the efficiency of the neural networks.

79 ASTRONOMY AND ASTROPHYSICS↗

A High Performance Sparse Tensor Algebra Compiler in MLIR

Sparse tensor algebra is widely used in many applications, including scientific computing, machine learning, and data analytics. The performance of sparse tensor algebra kernels strongly depends on the intrinsic characteristics of the input tensors, hence many storage formats are designed for tensors to achieve optimal performance for particular applications/architectures, which makes it challenging to implement and optimize every tensor operation of interest on a given architecture. We propose a tensor algebra domain-specific language (DSL) and compiler framework to automatically generate kernels for mixed sparse-dense tensor algebra operations. The proposed DSL provides high-level programming abstractions that resemble the familiar Einstein notation to represent tensor algebra operations. The compiler introduces a new Sparse Tensor Algebra dialect built on top of LLVM's extensible MLIR compiler infrastructure for efficient code generation while covering a wide range of tensor storage formats. Our compiler also leverages input-dependent code optimization to enhance data locality for better performance. Our results show that the performance of automatically generated kernels outperforms the state-of-the-art sparse tensor algebra compiler, with up to 20.92x, 6.39x, and 13.9x performance improvement over state-of-the-art tensor algebra compilers, for parallel SpMV, SpMM, and TTM, respectively.

Tian, Ruiqin↗

Deploy Nalu/Kokkos algorithmic infrastructure with performance benchmarking.

The former Nalu interior heterogeneous algorithm design, which was originally designed to manage matrix assembly operations over all elemental topology types, has been modified to operate over homogeneous collections of mesh entities. This newly templated kernel design allows for removal of workset variable resize operations that were formerly required at each loop over a Sierra ToolKit (STK) bucket (nominally, 512 entities in size). Extensive usage of the Standard Template Library (STL) std::vector has been removed in favor of intrinsic Kokkos memory views. In this milestone effort, the transition to Kokkos as the underlying infrastructure to support performance and portability on many-core architectures has been deployed for key matrix algorithmic kernels. A unit-test driven design effort has developed a homogeneous entity algorithm that employs a team-based thread parallelism construct. The STK Single Instruction Multiple Data (SIMD) infrastructure is used to interleave data for improved vectorization. The collective algorithm design, which allows for concurrent threading and SIMD management, has been deployed for the core low-Mach element- based algorithm. Several tests to ascertain SIMD performance on Intel KNL and Haswell architectures have been carried out. The performance test matrix includes evaluation of both low- and higher-order methods. The higher-order low-Mach methodology builds on polynomial promotion of the core low-order control volume nite element method (CVFEM). Performance testing of the Kokkos-view/SIMD design indicates low-order matrix assembly kernel speed-up ranging between two and four times depending on mesh loading and node count. Better speedups are observed for higher-order meshes (currently only P=2 has been tested) especially on KNL. The increased workload per element on higher-order meshes bene ts from the wide SIMD width on KNL machines. Combining multiple threads with SIMD on KNL achieves a 4.6x speedup over the baseline, with assembly timings faster than that observed on Haswell architecture. The computational workload of higher-order meshes, therefore, seems ideally suited for the many-core architecture and justi es further exploration of higher-order on NGP platforms. A Trilinos/Tpetra-based multi-threaded GMRES preconditioned by symmetric Gauss Seidel (SGS) represents the core solver infrastructure for the low-Mach advection/diffusion implicit solves. The threaded solver stack has been tested on small problems on NREL's Peregrine system using the newly developed and deployed Kokkos-view/SIMD kernels. fforts are underway to deploy the Tpetra-based solver stack on NERSC Cori system to benchmark its performance at scale on KNL machines.

97 MATHEMATICS AND COMPUTING↗

Normal Tissue Complication Probability Modeling of Radiation-Induced Hypothyroidism After Head-and-Neck Radiation Therapy

Purpose: To determine the dose-response relationship of the thyroid for radiation-induced hypothyroidism in head-and-neck radiation therapy, according to 6 normal tissue complication probability models, and to find the best-fit parameters of the models. Methods and Materials: Sixty-five patients treated with primary or postoperative radiation therapy for various cancers in the head-and-neck region were prospectively evaluated. Patient serum samples (tri-iodothyronine, thyroxine, thyroid-stimulating hormone [TSH], free tri-iodothyronine, and free thyroxine) were measured before and at regular time intervals until 1 year after the completion of radiation therapy. Dose-volume histograms (DVHs) of the patients' thyroid gland were derived from their computed tomography (CT)-based treatment planning data. Hypothyroidism was defined as increased TSH (subclinical hypothyroidism) or increased TSH in combination with decreased free thyroxine and thyroxine (clinical hypothyroidism). Thyroid DVHs were converted to 2 Gy/fraction equivalent doses using the linear-quadratic formula with {alpha}/{beta} = 3 Gy. The evaluated models included the following: Lyman with the DVH reduced to the equivalent uniform dose (EUD), known as LEUD; Logit-EUD; mean dose; relative seriality; individual critical volume; and population critical volume models. The parameters of the models were obtained by fitting the patients' data using a maximum likelihood analysis method. The goodness of fit of the models was determined by the 2-sample Kolmogorov-Smirnov test. Ranking of the models was made according to Akaike's information criterion. Results: Twenty-nine patients (44.6%) experienced hypothyroidism. None of the models was rejected according to the evaluation of the goodness of fit. The mean dose model was ranked as the best model on the basis of its Akaike's information criterion value. The D{sub 50} estimated from the models was approximately 44 Gy. Conclusions: The implemented normal tissue complication probability models showed a parallel architecture for the thyroid. The mean dose model can be used as the best model to describe the dose-response relationship for hypothyroidism complication.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

A simple modern correctness condition for a space-based high-performance multiprocessor

A number of U.S. national programs, including space-based detection of ballistic missile launches, envisage putting significant computing power into space. Given sufficient progress in low-power VLSI, multichip-module packaging and liquid-cooling technologies, we will see design of high-performance multiprocessors for individual satellites. In very high speed implementations, performance depends critically on tolerating large latencies in interprocessor communication; without latency tolerance, performance is limited by the vastly differing time scales in processor and data-memory modules, including interconnect times. The modern approach to tolerating remote-communication cost in scalable, shared-memory multiprocessors is to use a multithreaded architecture, and alter the semantics of shared memory slightly, at the price of forcing the programmer either to reason about program correctness in a relaxed consistency model or to agree to program in a constrained style. The literature on multiprocessor correctness conditions has become increasingly complex, and sometimes confusing, which may hinder its practical application. We propose a simple modern correctness condition for a high-performance, shared-memory multiprocessor; the correctness condition is based on a simple interface between the multiprocessor architecture and a high-performance, shared-memory multiprocessor; the correctness condition is based on a simple interface between the multiprocessor architecture and the parallel programming system.

Probst, David K.↗

A Novel Algorithm for Solving the Multidimensional Neutron Transport Equation on Massively Parallel Architectures

We employ the Integral Transport Matrix Method (ITMM) as the kernel of new parallel solution methods for the discrete ordinates approximation of the within-group neutron transport equation. The ITMM abandons the repetitive mesh sweeps of the traditional source iterations (SI) scheme in favor of constructing stored operators that account for the direct coupling factors among all the cells' fluxes and between the cells' and boundary surfaces' fluxes. The main goals of this work are to develop the algorithms that construct these operators and employ them in the solution process, determine the most suitable way to parallelize the entire procedure, and evaluate the behavior and parallel performance of the developed methods with increasing number of processes, P. The fastest observed parallel solution method, Parallel Gauss-Seidel (PGS), was used in a weak scaling comparison with the PARTISN transport code, which uses the source iteration (SI) scheme parallelized with the Koch-baker-Alcouffe (KBA) method. Compared to the state-of-the-art SI-KBA with diffusion synthetic acceleration (DSA), this new method- even without acceleration/preconditioning-is completitive for optically thick problems as P is increased to the tens of thousands range. For the most optically thick cells tested, PGS reduced execution time by an approximate factor of three for problems with more than 130 million computational cells on P = 32,768. Moreover, the SI-DSA execution times's trend rises generally more steeply with increasing P than the PGS trend. Furthermore, the PGS method outperforms SI for the periodic heterogeneous layers (PHL) configuration problems. The PGS method outperforms SI and SI-DSA on as few as P = 16 for PHL problems and reduces execution time by a factor of ten or more for all problems considered with more than 2 million computational cells on P = 4.096.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Petascale direct numerical simulation of blood flow on 200K cores and heterogeneous architectures

We present a fast, petaflop-scalable algorithm for Stokesian particulate flows. Our goal is the direct simulation of blood, which we model as a mixture of a Stokesian fluid (plasma) and red blood cells (RBCs). Directly simulating blood is a challenging multiscale, multiphysics problem. We report simulations with up to 260 million deformable RBCs. The largest simulation amounts to 90 billion unknowns in space. In terms of the number of cells, we improve the state-of-the art by several orders of magnitude: the previous largest simulation, at the same physical fidelity as ours, resolved the flow of O(1,000-10,000) RBCs. Our approach has three distinct characteristics: (1) we faithfully represent the physics of RBCs by using nonlinear solid mechanics to capture the deformations of each cell; (2) we accurately resolve the long-range, N-body, hydrodynamic interactions between RBCs (which are caused by the surrounding plasma); and (3) we allow for highly non-uniform spatial distributions of RBCs. The new method has been implemented in the software library MOBO (for 'Moving Boundaries'). We designed MOBO to support parallelism at all levels, including inter-node distributed memory parallelism, intra-node shared memory parallelism, data parallelism (vectorization), and fine-grained multithreading for GPUs. We have implemented and optimized the majority of the computation kernels on both Intel/AMD x86 and NVidia's Tesla/Fermi platforms for single and double floating point precision. Overall, the code has scaled on 256 CPU-GPUs on the Teragrid's Lincoln cluster and on 200,000 AMD cores of the Oak Ridge National Laboratory's Jaguar PF system. In our largest simulation, we have achieved 0.7 Petaflops/s of sustained performance on Jaguar.

59 BASIC BIOLOGICAL SCIENCES↗

Symmetric Indefinite Linear Solver Using OpenMP Task on Multicore Architectures

Recently, the Open Multi-Processing (OpenMP) standard has incorporated task-based programming, where a function call with input and output data is treated as a task. At run time, OpenMP's superscalar scheduler tracks the data dependencies among the tasks and executes the tasks as their dependencies are resolved. On a shared-memory architecture with multiple cores, the independent tasks are executed on different cores in parallel, thereby enabling parallel execution of a seemingly sequential code. With the emergence of many-core architectures, this type of programming paradigm is gaining attention-not only because of its simplicity, but also because it breaks the artificial synchronization points of the program and improves its thread-level parallelization. In this paper, we use these new OpenMP features to develop a portable high-performance implementation of a dense symmetric indefinite linear solver. Obtaining high performance from this kind of solver is a challenge because the symmetric pivoting, which is required to maintain numerical stability, leads to data dependencies that prevent us from using some common performance-improving techniques. To fully utilize a large number of cores through tasking, while conforming to the OpenMP standard, we describe several techniques. Our performance results on current many-core architectures-including Intel's Broadwell, Intel's Knights Landing, IBM's Power8, and Arm's ARMv8-demonstrate the portable and superior performance of our implementation compared with the Linear Algebra PACKage (LAPACK). The resulting solver is now available as a part of the PLASMA software package.

Computer Science↗

End-to-end I/O portfolio for the summit supercomputing ecosystem

The I/O subsystem for the Summit supercomputer, No. 1 on the Top500 list, and its ecosystem of analysis platforms is composed of two distinct layers, namely the in-system layer and the center-wide parallel file system layer (PFS), Spider 3. The in-system layer uses node-local SSDs and provides 26.7 TB/s for reads, 9.7 TB/s for writes, and 4.6 billion IOPS to Summit. The Spider 3 PFS layer uses IBM's Spectrum Scale™ and provides 2.5 TB/s and 2.6 million IOPS to Summit and other systems. While deploying them as two distinct layers was operationally efficient, it also presented usability challenges in terms of multiple mount points and lack of transparency in data movement. To address these challenges, we have developed novel end-to-end I/O solutions for the concerted use of the two storage layers. We present the I/O subsystem architecture, the end-to-end I/O solution space, their design considerations and our deployment experience.

Oral, Sarp↗

A two-level GPU-accelerated incomplete LU preconditioner for general sparse linear systems

This paper presents a parallel preconditioning approach based on incomplete LU (ILU) factorizations in the framework of Domain Decomposition (DD) for general sparse linear systems. We focus on distributed memory parallel architectures, specifically, those that are equipped with graphic processing units (GPUs). In addition to block-Jacobi, we present general purpose two-level ILU Schur complement-based approaches, where different strategies are presented to solve the coarse-level reduced system. These strategies are combined with modified ILU methods in the construction of the coarse-level operator, in order to effectively remove smooth errors by targeting an algebraically smooth vector. We leverage available GPU-based sparse matrix kernels to accelerate the setup and the solve phases of the proposed ILU preconditioner. We evaluate the efficiency of the proposed methods as a smoother for algebraic multigrid (AMG) and as a preconditioner for Krylov subspace methods on challenging anisotropic diffusion problems and a collection of general sparse matrices.

97 MATHEMATICS AND COMPUTING↗

Virtual Machine Language 2.1

VML (Virtual Machine Language) is an advanced computing environment that allows spacecraft to operate using mechanisms ranging from simple, time-oriented sequencing to advanced, multicomponent reactive systems. VML has developed in four evolutionary stages. VML 0 is a core execution capability providing multi-threaded command execution, integer data types, and rudimentary branching. VML 1 added named parameterized procedures, extensive polymorphism, data typing, branching, looping issuance of commands using run-time parameters, and named global variables. VML 2 added for loops, data verification, telemetry reaction, and an open flight adaptation architecture. VML 2.1 contains major advances in control flow capabilities for executable state machines. On the resource requirements front, VML 2.1 features a reduced memory footprint in order to fit more capability into modestly sized flight processors, and endian-neutral data access for compatibility with Intel little-endian processors. Sequence packaging has been improved with object-oriented programming constructs and the use of implicit (rather than explicit) time tags on statements. Sequence event detection has been significantly enhanced with multi-variable waiting, which allows a sequence to detect and react to conditions defined by complex expressions with multiple global variables. This multi-variable waiting serves as the basis for implementing parallel rule checking, which in turn, makes possible executable state machines. The new state machine feature in VML 2.1 allows the creation of sophisticated autonomous reactive systems without the need to develop expensive flight software. Users specify named states and transitions, along with the truth conditions required, before taking transitions. Transitions with the same signal name allow separate state machines to coordinate actions: the conditions distributed across all state machines necessary to arm a particular signal are evaluated, and once found true, that signal is raised. The selected signal then causes all identically named transitions in all present state machines to be taken simultaneously. VML 2.1 has relevance to all potential space missions, both manned and unmanned. It was under consideration for use on Orion.

Riedel, Joseph E.↗

Operating System Support for Fine-Grained Task Migration

With the end of clock scaling and the limited power budget available (20-30MW), future supercomputers will meet exascale performance primarily through a higher level of parallelism. Current operating (OS) and runtime (RT) systems are designed for the classical SMP model and based on the static and coarse-grained process/thread paradigm. They do not provide the required level of flexibility, especially within a single compute node, to meet the requirements imposed by exascale systems in terms of power/energy efficiency, resilience, managing concurrency and performance portability. The high level of concurrency poses new challenges specific to exascale systems that need to be addressed by novel solutions. In particular, requiring the user to manage billions of concurrent threads could easily result in poor data locality, clogged interconnection networks, unchecked propagation of soft errors, and lack of control over power/energy consumption. Equally important, managing such level of concurrency interferes with the user’s focus on the application and the algorithm. We envision that the computation will be encapsulated into fine-grained tasks that can be isolated and protected from the other tasks running in the system. Whenever a task needs to work on some data that is not stored on the local node, the OS/RT allows the task to be migrated to the node that owns the data. Each task is associated with a contained state (set or architectural registers, stack frame, running node, etc.) that describes the progress of the task and that should be moved together with the task’s code. We believe system support for task migration is a fundamental function that can ease the job of tackling several of the exascale challenges.

Gioiosa, Roberto↗