Search NASA⌕ Search

SEARCH · Search NASA

Results for “Runtime Scheduling”

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.

141 records · Page 8

ATD-2 Benefits Mechanism

NASA has been developing and demonstrating a suite of decision support capabilities for integrated arrival, departure, and surface (IADS) operations in a metroplex environment. The effort is being made in three phases, under NASA’s Airspace Technology Demonstration 2 (ATD-2) sub-project, through a close partnership with the Federal Aviation Administration (FAA), air carriers, airport, and general aviation community. The Phase 1 Baseline IADS capabilities provide enhanced operational efficiency and predictability of flight operations through data exchange and integration, tactical surface metering, and automated coordination of release time of controlled flights for overhead stream insertion. The Phase 2 Fused IADS capabilities include the fusion of strategic and tactical surface metering, Atlanta Center airspace tactical scheduling, Electronic Flight Data (EFD) integration, Terminal Flight Data Manager (TFDM) Terminal Publication (TTP) prototype, and Mobile App for General Aviation (GA) community. In the Phase 2 field evaluation, strategic surface metering provides advance notice of metering and additional stability to the assigned gate holds. The users of the IADS system in Phases 1 and 2 include the personnel at Charlotte Douglas International Airport (CLT) air traffic control tower, American Airlines ramp tower, CLT terminal radar approach control (TRACON), and Washington and Atlanta Center. This document describes the ATD-2 benefits mechanism used to assess the Phases 1 and 2 IADS capabilities and field evaluation conducted at CLT since September 2017. The ATD-2 benefits mechanism mainly consists of surface metering and overhead stream insertion. This document provides detailed calculation methods of major benefit metrics, such as fuel savings, gas emissions savings, and engine runtime reduction, which can be obtained through surface metering, gate hold of Approval Request (APREQ) flights prior to pushback, and the renegotiation of release time while taxiing. As of April 30, 2020, it is estimated that 5,097,173 pounds of fuel savings and 15,699,292 pounds of CO2 emission reduction have been achieved so far, with a reduction of 3,831 hours in total engine runtime. The amount of CO2 savings is estimated to be equivalent to planting 116,739 urban trees. The pre- and post-metering comparison results using FAA’s Aviation System Performance Metrics (ASPM) data have also shown that the surface metering had no negative impact on the on-time arrival performance of both outbound and inbound flights at CLT.

ATD-2↗

Argobots: A Lightweight Low-Level Threading and Tasking Framework

In the past few decades, a number of user-level threading and tasking models have been proposed in the literature to address the shortcomings of OS-level threads, primarily with respect to cost and flexibility. Current state-of-the-art user-level threading and tasking models, however, are either too specific to applications or architectures or are not as powerful or flexible. In this paper, we present Argobots, a lightweight, low-level threading and tasking framework that is designed as a portable and performant substrate for high-level programming models or runtime systems. Argobots offers a carefully designed execution model that balances generality of functionality with providing a rich set of controls to allow specialization by the user or high-level programming model. We describe the design, implementation, and optimization of Argobots and present integrations with three example high-level models: OpenMP, MPI, and co-located I/O service. Evaluations show that (1) Argobots outperforms existing generic threading runtimes; (2) our OpenMP runtime offers more efficient interoperability capabilities than production OpenMP runtimes do; (3) when MPI interoperates with Argobots instead of Pthreads, it enjoys reduced synchronization costs and better latency hiding capabilities; and (4) I/O service with Argobots reduces interference with co-located applications, achieving performance competitive with that of the Pthreads version.

Seo, Sangmin (ORCID:0000000295159836)↗

High-Level Synthesis of Parallel Specifications Coupling Static and Dynamic Controllers

The increased need for efficient ways to implement domain-specific accelerators is driving design methodologies towards the use of abstractions higher than the Register Transfer Level (RTL). In this scenario, High Level Synthesis (HLS) plays a significant role by enabling the automatic generation of custom hardware accelerators starting from high level descriptions (e.g., C code). Conventional HLS tools exploit parallelism mostly at the Instruction Level (ILP). They statically schedule the input specifications, and build centralized Finite State Machine (FSM) controllers. However, aggressive exploitation of ILP in many applications has diminishing returns and, usually, centralized approaches do not efficiently exploit coarser parallelism because FSMs are inherently serial. In this paper we present a HLS framework able to synthesize applications that, beside ILP, also expose Task Level Parallelism (TLP). An application can expose TLP through annotations that identify the parallel functions (i.e., tasks). To generate accelerators that efficiently execute concur- rent tasks, we need to solve several issues: devise a mechanism to support concurrent execution flows, exploit memory parallelism, and manage synchronization. To support concurrent execution flows, we introduce a novel adaptive controller. The adaptive controller is composed of a set of interacting control elements that independently manage the execution of a single operation or function call. These control elements check dependencies and resource constraints at runtime, enabling as soon as possible execution. To support parallel access to shared memories and synchronization, we introduce a novel Hierarchical Memory Interface (HMI). With respect to previous solutions, the proposed interface supports multi-ported memories and atomic memory operations, which commonly occur in parallel programming. Our framework can generate the hardware implementation of C functions by employing two different approaches, depending on its characteristics. If a function exposes TLP, then the framework generates hardware implementations based on the adaptive controller. Otherwise, the framework implements the function by exploiting a more conventional FSM approach, which is optimized for ILP exploitation. We evaluate our framework on a set of parallel applications, and show substantial performance improvements (average speedup of 4.7) with limited area over- heads (average area increase of 5.48 times).

Castellana, Vito G.↗

High-Level Synthesis of Parallel Specifications Coupling Static and Dynamic Controllers

The increased need for efficient ways to implement domain-specific accelerators is driving design methodologies towards the use of abstractions higher than the Register Transfer Level (RTL). In this scenario, High Level Synthesis (HLS) plays a significant role by enabling the automatic generation of custom hardware accelerators starting from high level descriptions (e.g., C code). Conventional HLS tools exploit parallelism mostly at the Instruction Level (ILP). They statically schedule the input specifications, and build centralized Finite State Machine (FSM) controllers. However, aggressive exploitation of ILP in many applications has diminishing returns and, usually, centralized approaches do not efficiently exploit coarser parallelism because FSMs are inherently serial. In this paper we present a HLS framework able to synthesize applications that, beside ILP, also expose Task Level Parallelism (TLP). An application can expose TLP through annotations that identify the parallel functions (i.e., tasks). To generate accelerators that efficiently execute concur- rent tasks, we need to solve several issues: devise a mechanism to support concurrent execution flows, exploit memory parallelism, and manage synchronization. To support concurrent execution flows, we introduce a novel adaptive controller. The adaptive controller is composed of a set of interacting control elements that independently manage the execution of a single operation or function call. These control elements check dependencies and resource constraints at runtime, enabling as soon as possible execution. To support parallel access to shared memories and synchronization, we introduce a novel Hierarchical Memory Interface (HMI). With respect to previous solutions, the proposed interface supports multi-ported memories and atomic memory operations, which commonly occur in parallel programming. Our framework can generate the hardware implementation of C functions by employing two different approaches, depending on its characteristics. If a function exposes TLP, then the framework generates hardware implementations based on the adaptive controller. Otherwise, the framework implements the function by exploiting a more conventional FSM approach, which is optimized for ILP exploitation. We evaluate our framework on a set of parallel applications, and show substantial performance improvements (average speedup of 4.7) with limited area over- heads (average area increase of 5.48 times).

Castellana, Vito G.↗

IRIS: A Performance-Portable Framework for Cross-Platform Heterogeneous Computing

From edge to exascale, computer architectures are becoming more heterogeneous and complex. The systems typically have fat nodes, with multicore CPUs and multiple hardware accelerators such as GPUs, FPGAs, and DSPs. This complexity is causing a crisis in programming systems and performance portability. Several programming systems are working to address these challenges, but the increasing architectural diversity is forcing software stacks and applications to be specialized for each architecture. As we show, all of these approaches critically depend on their software framework for discovery, execution, scheduling, and data orchestration. To address this challenge, we believe that a more agile and proactive software framework is essential to increase performance portability and improve user productivity. To this end, we have designed and implemented IRIS: a performance-portable framework for cross-platform heterogeneous computing. IRIS can discover available resources, manage multiple diverse programming platforms (e.g., CUDA, Hexagon, HIP, Level Zero, OpenCL, OpenMP) simultaneously in the same execution, respect data dependencies, orchestrate data movement proactively, and provide for user-configurable scheduling. To simplify data movement, IRIS introduces a shared virtual device memory with relaxed consistency among different heterogeneous devices. IRIS also adds an automatic kernel workload partitioning technique using the polyhedral model so that it can resize kernels for a wide range of devices. Our evaluation on three architectures, ranging from Qualcomm Snapdragon to a Summit supercomputer node, shows that IRIS improves portability across a wide range of diverse heterogeneous architectures with negligible overhead.

97 MATHEMATICS AND COMPUTING↗

Extending I/O through High Performance Data Services

The complexity of HPC systems has increased the burden on the developer as applications scale to hundreds of thousands of processing cores. Moreover, additional efforts are required to achieve acceptable I/O performance, where it is important how I/O is performed, which resources are used, and where I/O functionality is deployed. Specifically, by scheduling I/O data movement and by effectively placing operators affecting data volumes or information about the data, tremendous gains can be achieved both in the performance of simulation output and in the usability of output data. Previous studies have shown the value of using asynchronous I/O, of employing a staging area, and of performing select operations on data before it is written to disk. Leveraging such insights, this paper develops and experiments with higher level I/O abstractions, termed 'data services', that manage output data from 'source to sink': where/when it is captured, transported towards storage, and filtered or manipulated by service functions to improve its information content. Useful services include data reduction, data indexing, and those that manage how I/O is performed, i.e., the control aspects of data movement. Our data services implementation distinguishes control aspects - the control plane - from data movement - the data plane, so that both may be changed separably. This results in runtime flexibility not only in which services to employ, but also in where to deploy them and how they use I/O resources. The outcome is consistently high levels of I/O performance at large scale, without requiring application change.

97 MATHEMATICS AND COMPUTING↗

Components Refurbishment and Chemical Analysis Facility, Hot Spot 1 Solid Waste Management Unit #041 Year 4 Annual Performance Monitoring Report Kennedy Space Center, Florida

This Year 4 Annual Performance Monitoring Report (PMR) presents the operations, maintenance, and monitoring activities for the Hydraulic Containment System (HCS) Interim Measure (IM) at the Components Refurbishment and Chemical Analysis (CRCA) facility located at John F. Kennedy Space Center (KSC), Florida. The primary objective of the HCS is to attain hydraulic control of the dissolved-phase chlorinated volatile organic compound (CVOC) plume, with the secondary objective to reduce concentrations of CVOCs in the high-concentration plume to support transition to monitored natural attenuation (MNA). CRCA has been designated Solid Waste Management Unit 041 under the KSC Resource Conservation and Recovery Act Corrective Action Program. The timeframe for activities documented in this Year 4 PMR extends from November 2022 through September 2023. Baseline sampling activities were completed in June 2019, and full-scale startup of the HCS IM was completed in July-August 2019. The operational runtime of the HCS for the Year 4 reporting period was approximately 94%, with the majority of downtime attributed to associated groundwater sampling events, maintenance, and Hurricane Nicole. Almost five million gallons of groundwater were treated during Year 4 of HCS operations, and concentrations of the site’s contaminants of concern (trans-1,2-dichloroethene and vinyl chloride) have been reduced by over 99%. This PMR describes the activities that were performed during Year 4 to operate and monitor the HCS IM, which includes three extraction wells, seven injection wells, and conveyance piping to a modular structure containing the control panel and an air stripper. Influent and effluent sampling results from the air stripper show that the system is operating as designed and is reducing concentrations of contaminants of concern to below detection limits. In addition to HCS operation, this PMR also discusses performance monitoring that has been implemented to assess progress of the HCS IM and overall plume conditions through scheduled groundwater (quarterly and semi-annual) and sub-slab soil gas (quarterly) sampling and analysis. Two ambient air samples were also collected on a quarterly basis in the vicinity of the modular structure and the paved driveway east of the Solvent Reclamation Area during routine operation and maintenance (O&M) activities to ensure safe breathing zone air quality for on-site personnel. All sub-slab soil gas and ambient air sampling conducted during the Year 4 operational period showed results below applicable regulatory air screening limits. Predictions made during the Year 2 groundwater model updates were in close correlation to post Year 4 plume conditions. A supplemental DPT study conducted in 2022 and 2023. This study indicated that low-concentration plume conditions, where concentrations exceed State of Florida Groundwater Cleanup Target Levels, expanded westward to Kennedy Parkway North and northward to the vicinity of the railroad tracks. Based on these results, recommendations were made to install 14 wells to monitor the downgradient and boundary conditions of the expanded LCP. The contents of this Year 4 PMR were presented during the November 2023 KSC Remediation Team meeting, where Team consensus was reached on several items including continued O&M of the HCS, and continued monitoring of groundwater, ambient air, and sub-slab soil gas. Sampling for per- and polyfluoroalkyl substances at CRCA is ongoing and will be submitted under separate cover.

K. Alex Murphy↗

Components Refurbishment and Chemical Analysis Facility, Hot Spot 1 SWMU #041 Year 3 Annual Performance Monitoring Report Kennedy Space Center, Florida

This Year 3 Annual Performance Monitoring Report (PMR) presents the operations, maintenance, and monitoring activities for the Hydraulic Containment System (HCS) Interim Measure (IM) at the Components Refurbishment and Chemical Analysis (CRCA) facility located at John F. Kennedy Space Center (KSC), Florida. The primary objective of the HCS is to attain hydraulic control of the dissolved-phase chlorinated volatile organic compound (CVOC) plume, with the secondary objective to reduce concentrations of CVOCs in the high-concentration plume to support transition to monitored natural attenuation (MNA). CRCA has been designated Solid Waste Management Unit 041 under the KSC Resource Conservation and Recovery Act Corrective Action Program. The timeframe for activities documented in this Year 3 PMR extends from September 2021 through October 2022. Baseline sampling activities were completed in June 2019, and full-scale startup of the HCS IM was completed in July-August 2019. The operational runtime of the HCS for the Year 3 reporting period was approximately 91%, with the majority of downtime attributed to system maintenance and repair. This is generally consistent with Year 1 and Year 2 runtimes of 85% and 92%, respectively. To help reduce downtime, an anti-scaling amendment, Redux 390, has been used to reduce scaling and help maintain system design parameters. Over nine million gallons of groundwater were treated during Year 3 of HCS operations, and concentrations of the site’s contaminants of concern (trans-1,2-dichloroethene and vinyl chloride) have been reduced by over 97%. This PMR describes the activities that were performed during Year 3 to operate and monitor the HCS IM, which includes three extraction wells, seven injection wells, and conveyance piping to a modular structure containing the control panel and an air stripper. Influent and effluent sampling results from the air stripper show that the system is operating as designed and is reducing concentrations of contaminants of concern to below detection limits. In addition to HCS operation, this PMR also discusses performance monitoring that has been implemented to assess progress of the HCS IM and overall plume conditions through scheduled groundwater (quarterly and semi-annual) and sub-slab soil gas (quarterly) sampling and analysis. Two ambient air samples were also collected on a quarterly basis in the vicinity of the modular structure and the paved driveway east of the Solvent Reclamation Area during routine operation and maintenance (O&M) activities to ensure safe breathing zone air quality for on-site personnel. All sub-slab soil gas and ambient air sampling conducted during the Year 3 operational period showed results below applicable regulatory air screening limits. Predictions made during the Year 2 groundwater model updates were in close correlation to post Year 3 plume conditions. Therefore, it can be assumed that the projected path remains valid for transition to MNA in one to two years of continuous HCS operation. The contents of this Year 3 PMR were presented during the February 2023 KSC Remediation Team meeting, where Team consensus was reached on several items including continued O&M of the HCS, and continued monitoring of groundwater, ambient air, and sub-slab soil gas. Replacement of MW0019 and VMP04 was also recommended, as well as additional direct-push technology sampling to further delineate the downgradient plume and confirm overall site-wide low-concentration plume boundaries. Sampling for per- and polyfluoroalkyl substances at CRCA is ongoing and will be submitted under separate cover.

K. Alex Murphy↗

Principles for Integrating Mars Analog Science, Operations, and Technology Research

During the Apollo program, the scientific community and NASA used terrestrial analog sites for understanding planetary features and for training astronauts to be scientists. Human factors studies (Harrison, Clearwater, & McKay 1991; Stuster 1996) have focused on the effects of isolation in extreme environments. More recently, with the advent of wireless computing, we have prototyped advanced EVA technologies for navigation, scheduling, and science data logging (Clancey 2002b; Clancey et al., in press). Combining these interests in a single expedition enables tremendous synergy and authenticity, as pioneered by Pascal Lee's Haughton-Mars Project (Lee 2001; Clancey 2000a) and the Mars Society s research stations on a crater rim on Devon Island in the High Canadian Arctic (Clancey 2000b; 2001b) and the Morrison Formation of southeast Utah (Clancey 2002a). Based on this experience, the following principles are proposed for conducting an integrated science, operations, and technology research program at analog sites: 1) Authentic work; 2) PI-based projects; 3) Unencumbered baseline studies; 4) Closed simulations; and 5) Observation and documentation. Following these principles, we have been integrating field science, operations research, and technology development at analog sites on Devon Island and in Utah over the past five years. Analytic methods include work practice simulation (Clancey 2002c; Sierhuis et a]., 2000a;b), by which the interaction of human behavior, facilities, geography, tools, and procedures are formalized in computer models. These models are then converted into the runtime EVA system we call mobile agents (Clancey 2002b; Clancey et al., in press). Furthermore, we have found that the Apollo Lunar Surface Journal (Jones, 1999) provides a vast repository or understanding astronaut and CapCom interactions, serving as a baseline for Mars operations and quickly highlighting opportunities for computer automation (Clancey, in press).

Clancey, William J.↗

A Scientific Data Provenance Harvester for Distributed Applications

Data provenance provides a way for scientists to observe how experimental data originates, conveys process history, and explains influential factors such as experimental rationale and associated environmental factors from system metrics measured at runtime. The US Department of Energy Office of Science Integrated end-to-end Performance Prediction and Diagnosis for Extreme Scientific Workflows (IPPD) project has developed a provenance harvester that is capable of collecting observations from file based evidence typically produced by distributed applications. To achieve this, file based evidence is extracted and transformed into an intermediate data format inspired in part by W3C CSV on the Web recommendations, called the Harvester Provenance Application Interface (HAPI) syntax. This syntax provides a general means to pre-stage provenance into messages that are both human readable and capable of being written to a provenance store, Provenance Environment (ProvEn). HAPI is being applied to harvest provenance from climate ensemble runs for Accelerated Climate Modeling for Energy (ACME) project funded under the U.S. Department of Energy’s Office of Biological and Environmental Research (BER) Earth System Modeling (ESM) program. ACME informally provides provenance in a native form through configuration files, directory structures, and log files that contain success/failure indicators, code traces, and performance measurements. Because of its generic format, HAPI is also being applied to harvest tabular job management provenance from Belle II DIRAC scheduler relational database tables as well as other scientific applications that log provenance related information.

Stephan, Eric G.↗

Autonomic Management of Application Workflows on Hybrid Computing Infrastructure

In this paper, we present a programming and runtime framework that enables the autonomic management of complex application workflows on hybrid computing infrastructures. The framework is designed to address system and application heterogeneity and dynamics to ensure that application objectives and constraints are satisfied. The need for such autonomic system and application management is becoming critical as computing infrastructures become increasingly heterogeneous, integrating different classes of resources from high-end HPC systems to commodity clusters and clouds. For example, the framework presented in this paper can be used to provision the appropriate mix of resources based on application requirements and constraints. The framework also monitors the system/application state and adapts the application and/or resources to respond to changing requirements or environment. To demonstrate the operation of the framework and to evaluate its ability, we employ a workflow used to characterize an oil reservoir executing on a hybrid infrastructure composed of TeraGrid nodes and Amazon EC2 instances of various types. Specifically, we show how different applications objectives such as acceleration, conservation and resilience can be effectively achieved while satisfying deadline and budget constraints, using an appropriate mix of dynamically provisioned resources. Our evaluations also demonstrate that public clouds can be used to complement and reinforce the scheduling and usage of traditional high performance computing infrastructure.

Kim, Hyunjoo↗

Launch Complex 34, SWMU Cc054 2021 DNAPL Source Zone Operations, Maintenance, and Monitoring, and Hot Spot 6 Air Sparge System Annual Performance Monitoring Report Cape Canaveral Space Force Station, Florida

This Annual Performance Monitoring Report (PMR) for the Dense Non-Aqueous Phase Liquid (DNAPL) Source Zone (DSZ) and Hot Spot 6 (HS 6) Air Sparge (AS) System presents the results of Year 12 operation of the hydraulic containment (HC) Interim Measure (IM), the results of performance monitoring direct-push technology (DPT) sampling and monitoring well sampling conducted in the DSZ, and the results of operations and performance sampling of the HS 6 AS IM at Launch Complex 34 (LC34), located at Cape Canaveral Space Force Station (CCSFS), Florida. Site-wide biennial LTM sampling was not conducted during this reporting period and is scheduled to be conducted in December 2022. The timeframe for activities documented in this PMR extends from April 1, 2021 to March 31, 2022. LC34 has been designated Solid Waste Management Unit CC054 under the Kennedy Space Center (KSC) Resource Conservation and Recovery Act Corrective Action Program. The objective of the HC IM at LC34 is to contain the DSZ and deep dissolved-phase trichloroethene (TCE) high concentration plume via operation of a hydraulic containment system (HCS). The pre-IM design 300 micrograms per liter (μg/L) TCE groundwater contour was used to establish the deep zone capture area for deep recovery wells, and the shallow zone capture area was defined by the DSZ. The system began operating in 2010, and in 2015, the system was expanded to provide HC for areas within the 300 μg/L TCE groundwater isocontours of HS 3 and 4. In 2018 and 2019, an investigation was conducted to re-characterize the DSZ, which included investigating TCE mass in Layer 7. This data was subsequently used to optimize the pumping rates of the HCS to more adequately capture residual contaminant mass. The operational period for Year 12 of the HCS was from April 1, 2021 to March 31, 2022. Operational runtime for the system was 94 percent during Year 12, with downtime events attributed to planned maintenance, system repairs, and power outages. As of March 31, 2022, a total of 285,712,801 gallons of groundwater containing 84,933 pounds of VOCs have been removed by the HCS. Influent concentrations of TCE have decreased since startup from approximately 280,000 µg/L (January 2010) to 12,000 µg/L (March 2022). During the reporting period, all effluent concentrations from the HCS (aqueous and vapor) were below regulatory reporting limits, indicating the system continues to operate as intended. Performance monitoring was conducted in December 2021 within the DSZ to evaluate TCE contamination. Groundwater samples were collected via DPT at nine locations, consistent with previous events in 2017, 2018, 2019, and 2020. Full vertical profile sampling was completed at each DPT from 8 to 98 ft bls, at 5 foot intervals. The DPT performance monitoring results are summarized in this PMR. The results revealed TCE remains at concentrations greater than 11,000 µg/L in the DSZ (1-percent solubility, indicative of DNAPL) at eight of the nine DPT locations at depths ranging from 8 to 98 ft bls. An overall increasing trend of TCE concentrations was observed in DPT samples during this reporting period, which may be due to several recovery wells that were turned off during the AS Pilot Study in the DSZ that operated from July 2021 to February 2022 (documented separately from this report). The maximum TCE concentration in 2021 was 15,400,000 µg/L in the 58 ft bls depth interval at DPT597 (previous maximum result in 2020 was 1,690,000 at 48 ft bls at DPT596). During the 2021 DPT event, the overall majority of TCE contamination was identified in the 58 ft bls interval (below Layer 4), where in the previous year the majority of mass was observed in Layer 4. This trend appears to indicate continued mass discharge from Layer 4 (fine-grained unit). In addition to DPT sampling, monitoring well samples were collected from deep wells in the DSZ area (Layers 7 and 8) to verify vertical delineation. All monitoring well results were non-detect or below cleanup levels, with exception of one well (IW0162, screened 105 to 115 ft bls, which is below the existing recovery well capture zone) where TCE was identified above cleanup target levels. The HS 6 AS system remained operational during the reporting period covered under this report. The HS 6 AS IM was initiated in 2018 with 160 AS wells, and expanded in 2019 with an additional 140 AS wells. Quarterly performance monitoring was reduced to semi-annual prior to this operational period. The results of the HS 6 system operation and semi-annual performance monitoring are summarized in this report. Semi-annual monitoring results collected in April and October 2021 show concentrations of contaminants of concern (cis-1,2-dichloroethene, trans-1,2- dichloroethene, and vinyl chloride) are generally decreasing and not impacting the surface water drainage canal, indicating the HS 6 IM is meeting objectives. Overall, the tasks associated with Year 12 operation of the HC IM and operation of the HS 6 AS IM were performed in accordance with the recommendations of the 2020 LC34 (Year 11) Operations, Maintenance, and Monitoring Report for DNAPL Source Zone, Site Wide LongTerm Monitoring, and Hot Spot 6 Air Sparging System PMR (NASA, 2021c). Evaluation of results from the HC IM and HS 6 IM show that these systems are operating as designed and meeting performance objectives.

trichloroethene↗

HTMT-class Latency Tolerant Parallel Architecture for Petaflops Scale Computation

Computational Aero Sciences and other numeric intensive computation disciplines demand computing throughputs substantially greater than the Teraflops scale systems only now becoming available. The related fields of fluids, structures, thermal, combustion, and dynamic controls are among the interdisciplinary areas that in combination with sufficient resolution and advanced adaptive techniques may force performance requirements towards Petaflops. This will be especially true for compute intensive models such as Navier-Stokes are or when such system models are only part of a larger design optimization computation involving many design points. Yet recent experience with conventional MPP configurations comprising commodity processing and memory components has shown that larger scale frequently results in higher programming difficulty and lower system efficiency. While important advances in system software and algorithms techniques have had some impact on efficiency and programmability for certain classes of problems, in general it is unlikely that software alone will resolve the challenges to higher scalability. As in the past, future generations of high-end computers may require a combination of hardware architecture and system software advances to enable efficient operation at a Petaflops level. The NASA led HTMT project has engaged the talents of a broad interdisciplinary team to develop a new strategy in high-end system architecture to deliver petaflops scale computing in the 2004/5 timeframe. The Hybrid-Technology, MultiThreaded parallel computer architecture incorporates several advanced technologies in combination with an innovative dynamic adaptive scheduling mechanism to provide unprecedented performance and efficiency within practical constraints of cost, complexity, and power consumption. The emerging superconductor Rapid Single Flux Quantum electronics can operate at 100 GHz (the record is 770 GHz) and one percent of the power required by convention semiconductor logic. Wave Division Multiplexing optical communications can approach a peak per fiber bandwidth of 1 Tbps and the new Data Vortex network topology employing this technology can connect tens of thousands of ports providing a bi-section bandwidth on the order of a Petabyte per second with latencies well below 100 nanoseconds, even under heavy loads. Processor-in-Memory (PIM) technology combines logic and memory on the same chip exposing the internal bandwidth of the memory row buffers at low latency. And holographic storage photorefractive storage technologies provide high-density memory with access a thousand times faster than conventional disk technologies. Together these technologies enable a new class of shared memory system architecture with a peak performance in the range of a Petaflops but size and power requirements comparable to today's largest Teraflops scale systems. To achieve high-sustained performance, HTMT combines an advanced multithreading processor architecture with a memory-driven coarse-grained latency management strategy called "percolation", yielding high efficiency while reducing the much of the parallel programming burden. This paper will present the basic system architecture characteristics made possible through this series of advanced technologies and then give a detailed description of the new percolation approach to runtime latency management.

Sterling, Thomas↗

Data Locality Enhancement of Dynamic Simulations for Exascale Computing (Final Report)

The development of modern processors exhibits two trends that complicate the optimizations of modern software. The first is the increasing sensitivity of processors' throughput to irregularities in computation. With more processors produced through a massive integration of simple cores, future systems will increasingly favor regular data-level parallel computations, but deviate from the needs of applications with complex patterns. Some evidences are already shown on Graphic Processing Units (GPU): Irregular data accesses (e.g., indirect references A[D[i]]) and conditional branches are limiting many GPU applications' performance at a level an order of magnitude lower than the peak of GPU. The second hardware trend is the growing gap between memory bandwidth and the aggregate speed—that is, the sum of all cores' computing power—of a Chip Multiprocessor (CMP). Despite the capped growth of the peak CPU speed, the aggregate speed of a CMP keeps increasing as more cores get into a single chip. It is expected that by 2018, node concurrency in an exascale system will increase by hundreds of times, whereas, memory bandwidth will expand by only 10 to 20 times. Consequently, data movement and storage is expected to consume more than 70% of the total system power. Bridging this gap is difficult; the complexities of modern CMP memory hierarchy make it even harder: Data cache becomes shared among computing units, and the sharing is often non-uniform—whether two computing units share a cache depends on their proximity and the level of the cache. On the recent IBM Power7 architecture, for instance, four hardware contexts (or SMT threads) in a core share the entire memory hierarchy, all cores in one chip share an on-chip L3 cache, and cores across chips share L3 and main memory through off-chip connections. These two trends complicate the translation of computing power into performance, especially for a program with either intensive data accesses or complex patterns in data accesses or control flow paths. Unfortunately, both attributes present and will persist in a class of important applications. For instance, many scientific simulations deal with a large volume of data. And meanwhile, as most real-world processes are non-uniform and evolving (e.g., the evolution of a galaxy or the process of a drug injection), both the computations and data accesses of these programs tend to be irregular and dynamically changing. Currently, the lack of support to these applications on modern CMP severely limits their performance. On GPU, as our recent study shows and other studies echo, performance enhancement of a factor of integers is possible when memory accesses or control flows are streamlined for a set of GPU applications. On multicore CPU, our studies show that traditional locality enhancement, for being oblivious to the new features of multicore memory hierarchy, may even cause large slowdown to data-intensive dynamic applications. The severity of the issues is expected to worsen as the two hardware trends continue. Some recent studies try to match software with the trends, but in a limited scope or manner. For irregularities on GPU, most studies focus on irregularities analyzable through static analysis (e.g., data accesses in regular loops). Dynamic irregularities are harder to address because the needed analysis and transformations typically have to happen at run time. Some other research resorts to hardware extensions, an actual adoption of which is unclear for the entailed space cost and complexity. For data locality, recent years have seen some exploitations of the new memory hierarchy on multicore for performance, but most of them are on process or thread scheduling, rather than program transformations. Our recent study reveals that program-level transformations may magnify the scheduling benefits by a factor of seven, concluding that program-level transformation should play a central role for data locality enhancement on modern CMP. But research in this direction has been sparse, and most have focused on data layout or cache performance modeling, rather than program transformations to match with the new memory hierarchy features. Overall, it is still an open question how to bridge the gap between dynamic computations and the two prominent properties of modern processors. The goal of this project is to develop a set of techniques and software tools to enhance the matching between memory accesses in dynamic simulations and the prominent features of modern and future CMP, alleviating the memory performance issues for petascale and exascale computing. This report summarizes the discoveries and products produced throughout this project. It includes free launch, a new software approach to overcoming the shortcomings of both methods; coherence-free multiview, an approach that allows multiple views of a single data object to co-exist on GPU memory during a GPU kernel execution; algorithmic optimizations to data analytics problems, especially those that involve lots of distance calculations. Supporting dynamic parallelism is important for GPU to benefit a broad range of applications. There are currently two fundamental ways for programs to exploit dynamic parallelism on GPU: a software-based approach with software-managed worklists, and a hardware-based approach through dynamic subkernel launches. Neither is satisfactory. The former is complicated to program and is often subject to some load imbalance; the latter suffers large runtime overhead. In this work, we propose free launch, a new software approach to overcoming the shortcomings of both methods. It allows programmers to use subkernel launches to express dynamic parallelism. It employs a novel compiler-based code transformation named subkernel launch removal to replace the subkernel launches with the reuse of parent threads. Coupled with an adaptive task assignment mechanism, the transformation reassigns the tasks in the subkernels to the parent threads with a good load balance. The technique requires no hardware extensions, immediately deployable on existing GPUs. It keeps the programming convenience of the subkernel launch-based approach while avoiding its large runtime overhead. Meanwhile, its superior load balancing makes it outperform manual worklist-based techniques by 3X on average. The work was published at the 48th Annual IEEE/ACM International Symposium on Microarchitecture (Micro'2015). A Graphic Processing Unit (GPU) system is typically equipped with many types of memory (e.g., global, constant, texture, shared, cache). Data placement determines what data are placed on which type of memory, essential for GPU memory performance. Prior optimizations of data placement always require a single view of a data object on memory, which limits the optimization effectiveness. In this work, we propose coherence-free multiview, an approach that allows multiple views of a single data object to co-exist on GPU memory during a GPU kernel execution. We demonstrate that under certain conditions, the multiple views can remain incoherent while facilitating enhanced data placement. We present a theorem and some compiler support to ensure the soundness of the usage of coherence-free multiview. We further develop reference-discerning data placement, a new way to enhance data placements on GPU. It enables more flexible data placements by using coherence-free multiview to leverage the slack in coherence requirement of some GPU programs. Experiments on three types of GPU systems show that, with less than 200KB space cost, the new data placement technique can provide a 1.6X average (up to 4.27X) speedup. In addition, we have examined algorithmic optimizations to data analytics problems, especially those that involve lots of distance calculations. Computing distances among data points is an essential part of many important algorithms in data analytics, graph analysis, and other domains. In each of these domains, developers have spent significant manual effort optimizing algorithms, often through novel applications of the triangle equality, in order to minimize the number of distance computations in the algorithms. In this work, we observe that many algorithms across these domains can be generalized as an instance of a generic distance-related abstraction. Based on this abstraction, we derive seven principles for correctly applying the triangular inequality to optimize distance-related algorithms. Guided by the findings, we develop Triangular OPtimizer (TOP), the first software framework that is able to automatically produce optimized algorithms that either matches or outperforms manually designed algorithms for solving distance-related problems. TOP achieves up to 237x speedups and 2.5X on average. The work has been published at the 32nd International Conference on Machine Learning (ICML'15) and the 41st International Conference on Very Large Data Bases (VLDB'15).

42 ENGINEERING↗

A Strawman for an HPC PowerStack

The landscape of High-Performance Computing (HPC) is changing as we enter the exascale era and power and energy management are key design points for any next generation of supercomputers. Efficiently utilizing procured power and optimizing performance of scientific applications under power and energy constraints is challenging due to several reasons including dynamic phase behavior, processor manufacturing variability and increasing heterogeneity of node-level components. Extending the scope from the node- and application-level up to the system-level introduces further challenges on top of power-unaware job scheduling, which is known to be NP-hard on its own. While there exists several individual efforts across the community to research automatic techniques for managing power and energy better, the majority of these techniques have been specialized to meet the needs of a specific HPC center or specific optimization goals and provide little support to connect them to each other. Some projects, most notably the PowerAPI efforts [1], discuss interfaces that form a good starting point for full stack integration, but these interfaces still need to be hooked up to the wide range of software components offered by academic partners, developers or vendors. Furthermore, a recent survey conducted by the EE HPC WG concluded that the majority of such techniques have lacked the application-awareness required to achieve the best system performance and throughput. Other observations were that each technique tended to target management of power and energy for a different subset of the site or system hardware and that the different techniques tended to perform management at different (and often conflicting) granularities. Unfortunately, the existing techniques have not been designed to coexist simultaneously on one site and cooperate on management in an integrated manner [2]. The lack of application-awareness, lack of coordinated management across different granularities, and the lack of widely accepted interfaces and consequent limited connectivity between modules, can result in substantially underutilized Watts and FLOPS. To address these gaps, the HPC community needs a holistic stack for power and energy management and none currently exists. In our view, a holistic stack is one that is extensible enough to support the present and anticipated future needs of various different HPC centers, one that achieves best system performance and throughput through application-awareness, one that is designed to coordinate management at different granularities, and one that enables the seamless integration of software components from different developers and vendors. In this seminar, our goal is bring together experts from academia, research laboratories, and industry in order to take stock of existing approaches, design points and power management concepts and requirements at the various participant’s institutions, and to design concepts for a holistic power and energy management stack, which we refer to as the HPC PowerStack. Further, we hope to take steps toward defining the interfaces necessary for providing a complete prototype shared among many groups. The intention is to align development and research efforts across the community so that we may share development resources, avoid duplicating effort, agree on common interfaces and reap the rewards together as a community. The intended final outcome of this collaboration will be a holistic, flexible and extensible concept of a software stack ecosystem that allows us to combine product-grade open-source software components to enable runtime optimization of system power, energy, and performance.

97 MATHEMATICS AND COMPUTING↗