Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “scheduling software”

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 1,153 records · Page 64

Flight and Integrated Vehicle Testing: Laying the Groundwork for the Next Generation of Space Exploration Launch Vehicles

Integrated vehicle testing will be critical to ensuring proper vehicle integration of the Ares I crew launch vehicle and Ares V cargo launch vehicle. The Ares Projects, based at Marshall Space Flight Center in Alabama, created the Flight and Integrated Test Office (FITO) as a separate team to ensure that testing is an integral part of the vehicle development process. As its name indicates, FITO is responsible for managing flight testing for the Ares vehicles. FITO personnel are well on the way toward assembling and flying the first flight test vehicle of Ares I, th Ares I-X. This suborbital development flight will evaluate the performance of Ares I from liftoff to first stage separation, testing flight control algorithms, vehicle roll control, separation and recovery systems, and ground operations. Ares I-X is now scheduled to fly in summer 2009. The follow-on flight, Ares I-Y, will test a full five-segment first stage booster and will include cryogenic propellants in the upper stage, an upper stage engine simulator, and an active launch abort system. The following flight, Orion 1, will be the first flight of an active upper stage and upper stage engine, as well as the first uncrewed flight of an Orion spacecraft into orbit. The Ares Projects are using an incremental buildup of flight capabilities prior to the first operational crewed flight of Ares I and the Orion crew exploration vehicle in 2015. In addition to flight testing, the FITO team will be responsible for conducting hardware, software, and ground vibration tests of the integrated launch vehicle. These efforts will include verifying hardware, software, and grou handling interfaces. Through flight and integrated testing, the Ares Projects will identify and mitigate risks early the United States prepares to take its next giant leaps to the Moon and beyond.

Taylor, Jim↗

Flight and Integrated Vehicle Testing: Laying the Groundwork for the Next Generation of Space Exploration Launch Vehicles

Integrated vehicle testing will be critical to ensuring proper vehicle integration of the Ares I crew launch vehicle and Ares V cargo launch vehicle. The Ares Projects, based at Marshall Space Flight Center in Alabama, created the Flight and Integrated Test Office (FITO) as a separate team to ensure that testing is an integral part of the vehicle development process. As its name indicates, FITO is responsible for managing flight testing for the Ares vehicles. FITO personnel are well on the way toward assembling and flying the first flight test vehicle of Ares I, the Ares I-X. This suborbital development flight will evaluate the performance of Ares I from liftoff to first stage separation, testing flight control algorithms, vehicle roll control, separation and recovery systems, and ground operations. Ares I-X is now scheduled to fly in summer 2009. The follow-on flight, Ares I-Y, will test a full five-segment first stage booster and will include cryogenic propellants in the upper stage, an upper stage engine simulator, and an active launch abort system. The following flight, Orion 1, will be the first flight of an active upper stage and upper stage engine, as well as the first uncrewed flight of an Orion spacecraft into orbit. The Ares Projects are using an incremental buildup of flight capabilities prior to the first operational crewed flight of Ares I and the Orion crew exploration vehicle in 2015. In addition to flight testing, the FITO team will be responsible for conducting hardware, software, and ground vibration tests of the integrated launch vehicle. These efforts will include verifying hardware, software, and ground handling interfaces. Through flight and integrated testing, the Ares Projects will identify and mitigate risks early as the United States prepares to take its next giant leaps to the Moon and beyond.

Taylor, J. L.↗

Automated Derivation of Complex System Constraints from User Requirements

The Payload Operations Integration Center (POIC) located at the Marshall Space Flight Center has the responsibility of integrating US payload science requirements for the International Space Station (ISS). All payload operations must request ISS system resources so that the resource usage will be included in the ISS on-board execution timelines. The scheduling of resources and building of the timeline is performed using the Consolidated Planning System (CPS). The ISS resources are quite complex due to the large number of components that must be accounted for. The planners at the POIC simplify the process for Payload Developers (PD) by providing the PDs with a application that has the basic functionality PDs need as well as list of simplified resources in the User Requirements Collection (URC) application. The planners maintained a mapping of the URC resources to the CPS resources. The process of manually converting PD's science requirements from a simplified representation to a more complex CPS representation is a time-consuming and tedious process. The goal is to provide a software solution to allow the planners to build a mapping of the complex CPS constraints to the basic URC constraints and automatically convert the PD's requirements into systems requirements during export to CPS.

Foshee, Mark↗

Preliminary Modeling of Accident Tolerant Fuel Concepts under Accident Conditions

The catastrophic events that occurred at the Fukushima-Daiichi nuclear power plant in 2011 have led to widespread interest in research of alternative fuels and claddings that are proposed to be accident tolerant. Thus, the United States Department of Energy through its NEAMS (Nuclear Energy Advanced Modeling and Simulation) program has funded an Accident Tolerant Fuel (ATF) High Impact Problem (HIP). The ATF HIP is funded for a three-year period. The purpose of the HIP is to perform research into two potential accident tolerant concepts and provide an in-depth report to the Advanced Fuels Campaign (AFC) describing the behavior of the concepts, both of which are being considered for inclusion in a lead test assembly scheduled for placement into a commercial reactor in 2022. The initial focus of the HIP is on uranium silicide fuel and iron-chromium-aluminum (FeCrAl) alloy cladding. Utilizing the expertise of three national laboratory participants (INL, LANL, and ANL) a comprehensive mulitscale approach to modeling is being used including atomistic modeling, molecular dynamics, rate theory, phase-field, and fuel performance simulations. In this paper, we present simulations of two proposed accident tolerant fuel systems: U3Si2 fuel with Zircaloy-4 cladding, and UO2 fuel with FeCrAl cladding. The simulations investigate the fuel performance response of the proposed ATF systems under Loss of Coolant and Station Blackout conditions using the BISON code. Sensitivity analyses are completed using Sandia National Laboratories’ DAKOTA software to determine which input parameters (e.g., fuel specific heat) have the greatest influence on the output metrics of interest (e.g., fuel centerline temperature). Early results indicate that each concept has significant advantages as well as areas of concern. Further work is required prior to formulating the proposition report for the Advanced Fuels Campaign.

36 MATERIALS SCIENCE↗

TT and C - First TDRSS, Then Commercial GEO and Big LEO and Now through LEO

The advent of low earth orbit (LEO) commercial communications satellites provides an opportunity to dramatically reduce Telemetry Tracking and Control (TT&C) costs of launch vehicles and Unpiloted Aerial Vehicles (UAVs) by reducing or eliminating ground infrastructure. Personnel from the Goddard Space Flight Center Wallops Flight Facility (GSFC/WFF) in Virginia have successfully used commercial GEO & Big LEO communications satellites for Long Duration Balloon flight TT&C. In addition, TDRSS capability for these balloons has been developed by WFF for the Ultra Long Duration Balloons with the first test flight launch in January 2001 for one global circumnavigation at 120,000 feet altitude launched from Alice Springs. Australia. Numerous other low cost applications can new utilize the commercial LEO satellites for TT&C. The Flight Modern became a GSFC/WFF Advanced Range Technology Initiative (ARTI) in an effort to streamline TT&C capability to the user community at low cost. Phase I ground tests of The Flight Modem verified downlink communications quality of service and measured transmission latencies. These tests were completed last year, Phase II consisting of aircraft flight tests provide much of the data presented in this paper. Phase III of the Flight Modern baseline test program is a demonstration of the ruggedized version of the WFF Flight Modem flown on one sounding rocket launched from Sweden. Flights of opportunity have been and are being actively pursued with other centers, ranges and users at universities. The WFF goal is to reduce TT&C costs by providing a low cost COTS Flight Modem with a User Handbook containing system capability and limitation descriptions. Additionally, since data transmission is by packetized Internet Protocol (IP), data can be received and commands initialed from practically any location with no infrastructure. The WFF, like most ranges, has been using GPS receivers on sounding rockets and long duration balloons for several years, The WFF Flight Modem contains a GPS receiver to provide vehicle position for tracking and vehicle recovery. The system architecture which integrates antennas, GPS receiver, commercial satellite packet data modem. and a single board computer with custom software is described and a number of technical challenges are discussed along with the plan for their resolution. These include antenna development, high Doppler rates, reliability, environmental ruggedness, hand over between satellites and data security. An aggressive test plan is included which in addition to environmental Testing measures bit error rate latency and antenna patterns. Additional flight tests are planned far the near future on aircraft, long duration balloons and sounding rockets and these results as well as the current status of the project arc reported. Use of the WFF Flight Modem on small satellites is also being pursued. The LEO satellite constellation altitude above 1400 km is not an obstacle because most spacecraft do not require continuous Communications. The challenge is scheduling where store and forward techniques for command are required and downlink when the communications link allows connection (above 60 percent of the time depending on the satellite altitude). Sophisticated scheduling techniques utilizing 2-line orbital element sets available on the NASA/NORAD Internet site could be implemented for rare special cases. The current 9600 baud rate of the LEO communications link may be increased With special techniques that are planned for development in the WFF Flight Modem project.

Morgan, Dwayne↗

NASA Platform for Autonomous Systems (NPAS)

NASA Platform for Autonomous Systems (NPAS) is a disruptive software platform and processes being developed by the NASA Stennis Space Center (SSC) Autonomous Systems Laboratory (ASL). Autonomous operations are critical for the success, safety and crew survival of NASA deep space missions beyond low Earth orbit, including the Gateway, and for the future of cost-effective ground mission operations. NPAS represents the embodiment of an innovative paradigm for “thinking” autonomy in contrast to brute-force autonomy. NPAS uniquely addresses the requirements and integrates the primary functionalities for autonomous operations, in one platform that includes: (1) Integrated System Health Management (ISHM); (2) autonomy strategies, guided by system health and concepts of operations; (3) domain objects (system elements) and infrastructure to create complete application domain knowledge models (4) infrastructure to create, schedule, and execute mission plans; (5) infrastructure to develop user interfaces for comprehensive awareness; and (6) infrastructure to integrate distributed autonomous applications across networks. NPAS is a single platform that can be used to make any system operate with any desirable degree of autonomy, as well as provide comprehensive system awareness to operators and users.

Figueroa, Fernando↗

The Berkeley Serendip Project

An automated system was designed to perform a real time search for narrow band radio signals in the spectra of sources in a regularly scheduled, non-SETI astronomical observing program. The system will compute the power spectrum using a 65,536 channel fast Fourier transform processor with a real time bandwidth of 128 KHz and 2 Hz per channel resolution. After search for peaks in a 100 KHz portion of the IF band of the radio telescope, the system will move to the next 100 KHz portion using a programmable frequency synthesizer. When the whole IF band is scanned, the process will start again. Unidentified peaks in the power spectra are candidates for further study and their celestial coordinates will be recorded along with the time and power, IF and RF frequency, and bandwidth of the peak. Most of the hardware was developed and the machine software is in the process of being finalized. A number of means for identifying and rejecting power spectra peaks which have a high likelihood of being nonuseful are being investigated.

Bowyer, S.↗

Optimizing CMS build infrastructure via Apache Mesos

The Offline Software of the CMS Experiment at the Large Hadron Collider (LHC) at CERN consists of 6M lines of in-house code, developed over a decade by nearly 1000 physicists, as well as a comparable amount of general use open-source code. A critical ingredient to the success of the construction and early operation of the WLCG was the convergence, around the year 2000, on the use of a homogeneous environment of commodity x86-64 processors and Linux.Apache Mesos is a cluster manager that provides efficient resource isolation and sharing across distributed applications, or frameworks. It can run Hadoop, Jenkins, Spark, Aurora, and other applications on a dynamically shared pool of nodes. Lastly, we present how we migrated our continuous integration system to schedule jobs on a relatively small Apache Mesos enabled cluster and how this resulted in better resource usage, higher peak performance and lower latency thanks to the dynamic scheduling capabilities of Mesos.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Automatic Command Sequence Generation

Automatic Sequence Generator (Autogen) Version 3.0 software automatically generates command sequences for the Mars Reconnaissance Orbiter (MRO) and several other JPL spacecraft operated by the multi-mission support team. Autogen uses standard JPL sequencing tools like APGEN, ASP, SEQGEN, and the DOM database to automate the generation of uplink command products, Spacecraft Command Message Format (SCMF) files, and the corresponding ground command products, DSN Keywords Files (DKF). Autogen supports all the major multi-mission mission phases including the cruise, aerobraking, mapping/science, and relay mission phases. Autogen is a Perl script, which functions within the mission operations UNIX environment. It consists of two parts: a set of model files and the autogen Perl script. Autogen encodes the behaviors of the system into a model and encodes algorithms for context sensitive customizations of the modeled behaviors. The model includes knowledge of different mission phases and how the resultant command products must differ for these phases. The executable software portion of Autogen, automates the setup and use of APGEN for constructing a spacecraft activity sequence file (SASF). The setup includes file retrieval through the DOM (Distributed Object Manager), an object database used to store project files. This step retrieves all the needed input files for generating the command products. Depending on the mission phase, Autogen also uses the ASP (Automated Sequence Processor) and SEQGEN to generate the command product sent to the spacecraft. Autogen also provides the means for customizing sequences through the use of configuration files. By automating the majority of the sequencing generation process, Autogen eliminates many sequence generation errors commonly introduced by manually constructing spacecraft command sequences. Through the layering of commands into the sequence by a series of scheduling algorithms, users are able to rapidly and reliably construct the desired uplink command products. With the aid of Autogen, sequences may be produced in a matter of hours instead of weeks, with a significant reduction in the number of people on the sequence team. As a result, the uplink product generation process is significantly streamlined and mission risk is significantly reduced. Autogen is used for operations of MRO, Mars Global Surveyor (MGS), Mars Exploration Rover (MER), Mars Odyssey, and will be used for operations of Phoenix. Autogen Version 3.0 is the operational version of Autogen including the MRO adaptation for the cruise mission phase, and was also used for development of the aerobraking and mapping mission phases for MRO.

Fisher, Forest↗

Exploration Exercise System (EES) Development

Exploration class missions will be required to have an exercise device that is lightweight, has a small footprint, and is capable of providing enough physical stimulus and exercise variability to be an effective countermeasure against muscle and bone loss that results from the microgravity environment. Exploration exercise device prototypes should be evaluated on the ground and in-orbit for feasibility of use in microgravity for long and short duration exploration missions and efficacy of the device to maintain multi-system health and performance. The European Enhanced Exploration Exercise Device (E4D) was selected as the exploration prototype device to be evaluated on ISS for efficacy and feasibility of use as a single multi-modality device for the exercise system for exploration missions. This effort supports the continued development, testing, and verification of E4D hardware and software, internal NASA integration (Human Health and Performance, ISS Vehicle Office, Engineering, and Flight Operations), and external integration across NASA, ESA, and the Danish Aerospace Company (DAC). Providing a feasibility and acceptability assessment from a physiological efficacy and hardware durability standpoint are critical for informing use and risk associated with use on exploration missions. Clearly defined objectives from end users, stakeholders, and Subject Matter Experts (SMEs) will be tested by crewmembers during acute use sessions and long duration use of the exercise device while on ISS. This effort will include a flight study where crewmembers will be asked to exercise using only the E4D during the duration of their mission and participate in a battery of physiological testing to evaluate the efficacy. Hardware is scheduled to launch in FY25 followed by 2 years of operational use after activation and checkout. A final recommendation will be provided to the Artemis program on acceptability of the device for exploration missions. The E4D needs a vibration isolation stabilization (VIS) system that serves as a platform for the exercise hardware to protect the vehicle from loads imparted during exercise. Exploration forward VIS systems will need to protect the vehicle and provide sufficient stabilization for the exerciser during performance of all critical exercises. These enabling capabilities need to be achieved within exploration vehicle power, thermal, mass, and volume limitations.

Kent Lawrence Kalogera↗

Sensor Placement Optimization using Chama

Continuous or regularly scheduled monitoring has the potential to quickly identify changes in the environment. However, even with low - cost sensors, only a limited number of sensors can be deployed. The physical placement of these sensors, along with the sensor technology and operating conditions, can have a large impact on the performance of a monitoring strategy. Chama is an open source Python package which includes mixed - integer, stochastic programming formulations to determine sensor locations and technology that maximize monitoring effectiveness. The methods in Chama are general and can be applied to a wide range of applications. Chama is currently being used to design sensor networks to monitor airborne pollutants and to monitor water quality in water distribution systems. The following documentation includes installation instructions and examples, description of software features, and software license. The software is intended to be used by regulatory agencies, industry, and the research community. It is assumed that the reader is familiar with the Python Programming Language. References are included for addit ional background on software components. Online documentation, hosted at http://chama.readthedocs.io/, will be updated as new features are added. The online version includes API documentation .

47 OTHER INSTRUMENTATION↗

Satellite-Based Stratospheric and Tropospheric Measurements: Determination of Global Ozone and other Trace Species

This report summarizes research done under NASA Grant NAG5-3461 from November 1, 1996 through December 31, 2000. The research performed during this reporting period includes development and maintenance of scientific software for the GOME retrieval algorithms, consultation on operational software development for GOME, sensitivity and instrument studies to help finalize the definition of the SCIAMACHY instrument, leading the development of the SCIAMACHY Scientific Requirements Document for Data and Algorithm Development, consultation and development for SCIAMACHY near-real-time (NRT) and off-line (OL) data products, radiative transfer model development for utilization in GOME, SCIAMACHY and other programs, development of infrared line-by-line atmospheric modeling and retrieval capability for SCIAMACHY, and participation in GOME and SCIAMACHY validation studies. The Global Ozone Monitoring Experiment was successfully launched on the ERS-2 satellite on April 20, 1995, and remains working in normal fashion. SCIAMACHY is currently planned for launch in late 2001 on the ESA Envisat satellite. Three GOME-2 instruments are now scheduled to fly on the Metop series of operational meteorological satellites (Eumetsat). K. Chance is a member of the reconstituted GOME Scientific Advisory Group, which will guide the GOME-2 program as well as the continuing ERS-2 GOME program.

Chance, K. V.↗

GUI for Computational Simulation of a Propellant Mixer

Control Panel is a computer program that generates a graphical user interface (GUI) for computational simulation of a rocket-test-stand propellant mixer in which gaseous hydrogen (GH2) is injected into flowing liquid hydrogen (LH2) to obtain a combined flow having desired thermodynamic properties. The GUI is used in conjunction with software that models the mixer as a system having three inputs (the positions of the GH2 and LH2 inlet valves and an outlet valve) and three outputs (the pressure inside the mixer and the outlet flow temperature and flow rate). The user can specify valve characteristics and thermodynamic properties of the input fluids via userfriendly dialog boxes. The user can enter temporally varying input values or temporally varying desired output values. The GUI provides (1) a set-point calculator function for determining fixed valve positions that yield desired output values and (2) simulation functions that predict the response of the mixer to variations in the properties of the LH2 and GH2 and manual- or feedback-control variations in valve positions. The GUI enables scheduling of a sequence of operations that includes switching from manual to feedback control when a certain event occurs.

Figueroa, Fernando↗

MaROS Strategic Relay Planning and Coordination Interfaces

The Mars Relay Operations Service (MaROS) is designed to provide planning and analysis tools in support of ongoing Mars Network relay operations. Strategic relay planning requires coordination between lander and orbiter mission ground data system (GDS) teams to schedule and execute relay communications passes. MaROS centralizes this process, correlating all data relevant to relay coordination to provide a cohesive picture of the relay state. Service users interact with the system through thin-layer command line and web user interface client applications. Users provide and utilize data such as lander view periods of orbiters, Deep Space Network (DSN) antenna tracks, and reports of relay pass performance. Users upload and download relevant relay data via formally defined and documented file structures including some described in Extensible Markup Language (XML). Clients interface with the system via an http-based Representational State Transfer (ReST) pattern using Javascript Object Notation (JSON) formats. This paper will provide a general overview of the service architecture and detail the software interfaces and considerations for interface design.

Allard, Daniel A.↗

VIPER Lunar Rover Agile Mission Systems

The VIPER Lunar Rover, scheduled for a November, 2024 launch, is a solar powered rover that will search for volatiles at the lunar south pole. VIPER is an operationally complex mission operating in a challenging lighting and communications environment, requiring new design in a number of areas, from mission planning, to real-time waypoint driving. The combination of solar power, limited battery and the dynamic movement of shadows at the south pole gives VIPER small operational margins. The Mission System will be used to operate VIPER during cruise and on the lunar surface. To maximize efficiency and flexibility in Mission System design and thus to improve the performance and reliability of the resulting Mission System, we are tailoring Agile principles that we have used effectively in ground data system software development and applying those principles to the design of elements of the mission system.

Agile↗

RISK MONITORING CAPABILITES FROM DYNAMIC PRA DATA

Risk Monitors (RMs) are software tools that are employed in nuclear power plants to monitor the safety properties of the plant itself during operation. These safety properties are generated using classical PRA methods which are typically based on static Boolean structures such as Fault-Trees (FTs) and Event-Trees (ETs). The outcomes of these methods are Core Damage Frequency (CDF) and risk importance values of plant components (e.g., valves and pumps). Examples of Risk Importance Measures (RIMs) commonly used are: Risk Achievement Worth (RAW), Risk Reduction Worth (RRW), Birnbaum (B) and Fussell-Vesely (FV) [1,2]. In a RM these values are updated in real time once plant components status is updated (e.g., under maintenance, off-line, testing). In addition, RMs can be used to optimize maintenance schedules so those safety features of the plant are below plant standard values. This paper presents an approach to create temporal profiles of RIMs (i.e., RM capabilities) given a temporal change of the plant configuration. Instead of employing data generated by ETs and FTs, the proposed approach will employ data generated by Dynamic PRA methods. In contrast to classical PRA methods, Dynamic PRA methods couple stochastic methods with safety analysis codes to determine risk associate to complex systems such as nuclear plants. Compared to classical PRA methods, they can evaluate with higher resolution the safety impact of timing and sequencing of events on the accident progression. We will describe how classical RIMs can be generated by Dynamic PRA data and then we will show how the temporal profiles of the RIMs can be generated given a temporal profile of the system configuration.

97 MATHEMATICS AND COMPUTING↗

A simulation‐based integrated virtual testbed for dynamic optimization in smart manufacturing systems

Abstract In a manufacturing system, production control‐related decision‐making activities occur at different levels. At the process level, one of the main control activities is to tune the parameters of individual manufacturing equipment. At the system level, the main activity is to coordinate production resources and to route parts to appropriate workstations based on their processing requirement, priority indices, and control policy. At the factory level, the goal is to plan and schedule the processing of parts at different operations for the entire system in order to optimize certain objectives. Note that the results of such activities at different levels are closely coupled and affect the overall performance of the manufacturing system as a whole. Therefore, it is important to systematically integrate these control and optimization activities into one unified platform to ensure the goal of each individual activity is aligned with the overall performance of the system. In this paper, we develop a simulation‐based virtual testbed that implements dynamic optimization, automatic information exchange, and decision‐making from the process‐level, system‐level, and factory‐level of a manufacturing system into an integrated computation environment. This is demonstrated by connecting a Python‐based numerical computation program, discrete‐event simulation software (Simul8), and an optimization solver (CPLEX) via a third‐party master program. The application of this simulation‐based virtual testbed is illustrated by a case study in a machining shop.

Sun, Yuting↗

Exploring performance and energy tradeoffs for irregular applications: A case study on the Tilera many-core architecture

High performance, parallel applications with irregular data accesses are becoming a critical workload class for modern systems. In particular, the execution of such workloads on emerging many-core systems is expected to be a significant component of applications in data mining, machine learning, scientific computing and graph analytics. However, power and energy constraints limit the capabilities of individual cores, memory hierarchy and on-chip interconnect of such systems, thus leading to architectural and software trade-os that must be understood in the context of the intended application’s behavior. Irregular applications are notoriously hard to optimize given their data-dependent access patterns, lack of structured locality and complex data structures and code patterns. We have ported two irregular applications, graph community detection using the Louvain method (Grappolo) and high-performance conjugate gradient (HPCCG), to the Tilera many-core system and have conducted a detailed study of platform-independent and platform-specific optimizations that improve their performance as well as reduce their overall energy consumption. To conduct this study, we employ an auto-tuning based approach that explores the optimization design space along three dimensions - memory layout schemes, GCC compiler flag choices and OpenMP loop scheduling options. We leverage MIT’s OpenTuner auto-tuning framework to explore and recommend energy optimal choices for different combinations of parameters. We then conduct an in-depth architectural characterization to understand the memory behavior of the selected workloads. Finally, we perform a correlation study to demonstrate the interplay between the hardware behavior and application characteristics. Using auto-tuning, we demonstrate whole-node energy savings and performance improvements of up to 49:6% and 60% relative to a baseline instantiation, and up to 31% and 45:4% relative to manually optimized variants.

auto tuning↗