Current Search:  hierarchy (x)

View All Items

  • CSV Spreadsheet
(1 - 8 of 8)
ANALYZING INSTRUCTTION BASED CACHE REPLACEMENT POLICIES
Title
ANALYZING INSTRUCTTION BASED CACHE REPLACEMENT POLICIES.
Creator
Xiang, Ping, Zhou, Huiyang, University of Central Florida
Abstract / Description
The increasing speed gap between microprocessors and off-chip DRAM makes last-level caches (LLCs) a critical component for computer performance. Multi core processors aggravate the problem since multiple processor cores compete for the LLC. As a result, LLCs typically consume a significant amount of the die area and effective utilization of LLCs is mandatory for both performance and power efficiency. We present a novel replacement policy for last-level caches (LLCs). The fundamental...
Show moreThe increasing speed gap between microprocessors and off-chip DRAM makes last-level caches (LLCs) a critical component for computer performance. Multi core processors aggravate the problem since multiple processor cores compete for the LLC. As a result, LLCs typically consume a significant amount of the die area and effective utilization of LLCs is mandatory for both performance and power efficiency. We present a novel replacement policy for last-level caches (LLCs). The fundamental observation is to view LLCs as a shared resource among multiple address streams with each stream being generated by a static memory access instruction. The management of LLCs in both single-core and multi-core processors can then be modeled as a competition among multiple instructions. In our proposed scheme, we prioritize those instructions based on the number of LLC accesses and reuses and only allow cache lines having high instruction priorities to replace those of low priorities. The hardware support for our proposed replacement policy is light-weighted. Our experimental results based on a set of SPEC 2006 benchmarks show that it achieves significant performance improvement upon the least-recently used (LRU) replacement policy for benchmarks with high numbers of LLC misses. To handle LRU-friendly workloads, the set sampling technique is adopted to retain the benefits from the LRU replacement policy.
Show less
Date Issued
2010
Identifier
CFE0003377, ucf:48481
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0003377
Energy-Aware Data Movement In Non-Volatile Memory Hierarchies
Title
Energy-Aware Data Movement In Non-Volatile Memory Hierarchies.
Creator
Khoshavi Najafabadi, Navid, DeMara, Ronald, Yuan, Jiann-Shiun, Song, Zixia, University of Central Florida
Abstract / Description
While technology scaling enables increased density for memory cells, the intrinsic high leakagepower of conventional CMOS technology and the demand for reduced energy consumption inspiresthe use of emerging technology alternatives such as eDRAM and Non-Volatile Memory (NVM) including STT-MRAM, PCM, and RRAM. The utilization of emerging technology in Last Level Cache (LLC) designs which occupies a signi?cant fraction of total die area in Chip Multi Processors (CMPs) introduces new dimensions...
Show moreWhile technology scaling enables increased density for memory cells, the intrinsic high leakagepower of conventional CMOS technology and the demand for reduced energy consumption inspiresthe use of emerging technology alternatives such as eDRAM and Non-Volatile Memory (NVM) including STT-MRAM, PCM, and RRAM. The utilization of emerging technology in Last Level Cache (LLC) designs which occupies a signi?cant fraction of total die area in Chip Multi Processors (CMPs) introduces new dimensions of vulnerability, energy consumption, and performance delivery. To be speci?c, a part of this research focuses on eDRAM Bit Upset Vulnerability Factor (BUVF) to assess vulnerable portion of the eDRAM refresh cycle where the critical charge varies depending on the write voltage, storage and bit-line capacitance. This dissertation broaden the study on vulnerability assessment of LLC through investigating the impact of Process Variations (PV) on narrow resistive sensing margins in high-density NVM arrays, including on-chip cache and primary memory. Large-latency and power-hungry Sense Ampli?ers (SAs) have been adapted to combat PV in the past. Herein, a novel approach is proposed to leverage the PV in NVM arrays using Self-Organized Sub-bank (SOS) design. SOS engages the preferred SA alternative based on the intrinsic as-built behavior of the resistive sensing timing margin to reduce the latency and power consumption while maintaining acceptable access time.On the other hand, this dissertation investigates a novel technique to prioritize the service to 1)Extensive Read Reused Accessed blocks of the LLC that are silently dropped from higher levelsof cache, and 2) the portion of the working set that may exhibit distant re-reference interval in L2. In particular, we develop a lightweight Multi-level Access History Pro?ler to ef?ciently identifyERRA blocks through aggregating the LLC block addresses tagged with identical Most Signi?cantBits into a single entry. Experimental results indicate that the proposed technique can reduce theL2 read miss ratio by 51.7% on average across PARSEC and SPEC2006 workloads.In addition, this dissertation will broaden and apply advancements in theories of subspace recoveryto pioneer computationally-aware in-situ operand reconstruction via the novel Logic In Intercon-nect (LI2) scheme. LI2 will be developed, validated, and re?ned both theoretically and experimentally to realize a radically different approach to post-Moore's Law computing by leveraginglow-rank matrices features offering data reconstruction instead of fetching data from main memory to reduce energy/latency cost per data movement. We propose LI2 enhancement to attain highperformance delivery in the post-Moore's Law era through equipping the contemporary micro-architecture design with a customized memory controller which orchestrates the memory requestfor fetching low-rank matrices to customized Fine Grain Recon?gurable Accelerator (FGRA) forreconstruction while the other memory requests are serviced as before. The goal of LI2 is to conquer the high latency/energy required to traverse main memory arrays in the case of LLC miss, by using in-situ construction of the requested data dealing with low-rank matrices. Thus, LI2 exchanges a high volume of data transfers with a novel lightweight reconstruction method under speci?c conditions using a cross-layer hardware/algorithm approach.
Show less
Date Issued
2017
Identifier
CFE0006754, ucf:51859
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0006754
COLLOQUIA EDUCATION: AN EXAMINATION OF ROMAN SECOND LANGUAGE EDUCATION FOR SOCIAL IMPLICATIONS
Title
COLLOQUIA EDUCATION: AN EXAMINATION OF ROMAN SECOND LANGUAGE EDUCATION FOR SOCIAL IMPLICATIONS.
Creator
Newton, Jennifer, Dandrow, Edward, University of Central Florida
Abstract / Description
The expansion of the Roman Empire had compelled disparate cultures to mingle and assimilate. In relation to education this fact meant that teachers used a variety of curricula to convey an amalgamation of cultural dynamics. Evidence for this phenomenon is found in the content Colloquia, a fourth-century elementary language textbook, which displays aspects Greek and Roman culture through the explicit and implicit instruction of the text. The existence of this mixture education displays the...
Show moreThe expansion of the Roman Empire had compelled disparate cultures to mingle and assimilate. In relation to education this fact meant that teachers used a variety of curricula to convey an amalgamation of cultural dynamics. Evidence for this phenomenon is found in the content Colloquia, a fourth-century elementary language textbook, which displays aspects Greek and Roman culture through the explicit and implicit instruction of the text. The existence of this mixture education displays the motivations of the author, as well as information about the values of the contemporary culture.
Show less
Date Issued
2015
Identifier
CFH0004904, ucf:45499
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFH0004904
Towards High-Efficiency Data Management In the Next-Generation Persistent Memory System
Title
Towards High-Efficiency Data Management In the Next-Generation Persistent Memory System.
Creator
Chen, Xunchao, Wang, Jun, Fan, Deliang, Lin, Mingjie, Ewetz, Rickard, Zhang, Shaojie, University of Central Florida
Abstract / Description
For the sake of higher cell density while achieving near-zero standby power, recent research progress in Magnetic Tunneling Junction (MTJ) devices has leveraged Multi-Level Cell (MLC) configurations of Spin-Transfer Torque Random Access Memory (STT-RAM). However, in order to mitigate the write disturbance in an MLC strategy, data stored in the soft bit must be restored back immediately after the hard bit switching is completed. Furthermore, as the result of MTJ feature size scaling, the soft...
Show moreFor the sake of higher cell density while achieving near-zero standby power, recent research progress in Magnetic Tunneling Junction (MTJ) devices has leveraged Multi-Level Cell (MLC) configurations of Spin-Transfer Torque Random Access Memory (STT-RAM). However, in order to mitigate the write disturbance in an MLC strategy, data stored in the soft bit must be restored back immediately after the hard bit switching is completed. Furthermore, as the result of MTJ feature size scaling, the soft bit can be expected to become disturbed by the read sensing current, thus requiring an immediate restore operation to ensure the data reliability. In this paper, we design and analyze a novel Adaptive Restore Scheme for Write Disturbance (ARS-WD) and Read Disturbance (ARS-RD), respectively. ARS-WD alleviates restoration overhead by intentionally overwriting soft bit lines which are less likely to be read. ARS-RD, on the other hand, aggregates the potential writes and restore the soft bit line at the time of its eviction from higher level cache. Both of these two schemes are based on a lightweight forecasting approach for the future read behavior of the cache block. Our experimental results show substantial reduction in soft bit line restore operations. Moreover, ARS promotes advantages of MLC to provide a preferable L2 design alternative in terms of energy, area and latency product compared to SLC STT-RAM alternatives. Whereas the popular Cell Split Mapping (CSM) for MLC STT-RAM leverages the inter-block nonuniform access frequency, the intra-block data access features remain untapped in the MLC design. Aiming to minimize the energy-hungry write request to Hard-Bit Line (HBL) and maximize the dynamic range in the advantageous Soft-Bit Line (SBL), an hybrid mapping strategy for MLC STT-RAM cache (Double-S) is advocated in the paper. Double-S couples the contemporary Cell-Split-Mapping with the novel Word-Split-Mapping (WSM). Sparse cache block detector and read depth based data allocation/ migration policy are proposed to release the full potential of Double-S.
Show less
Date Issued
2017
Identifier
CFE0006865, ucf:51751
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0006865
A Decision Support Model for Autonomous Trucks Strategies
Title
A Decision Support Model for Autonomous Trucks Strategies.
Creator
Mohamed, Ahmad Saeid Ammar, Yun, Hae-Bum, Chopra, Manoj, Sallam, Amr, University of Central Florida
Abstract / Description
We examined the potential to improve the movement of freight using Truck PlatooningLane strategies on limited access highways in the State of Florida. In the First part of thisresearch, we investigated the potential benefits from dedicating one lane from existinglanes for autonomous trucks only. In this regard, a general framework tool was developedto evaluate and compare different measurements (e.g., travel tim and emissions) to betterassist decision makers to determine the most effective...
Show moreWe examined the potential to improve the movement of freight using Truck PlatooningLane strategies on limited access highways in the State of Florida. In the First part of thisresearch, we investigated the potential benefits from dedicating one lane from existinglanes for autonomous trucks only. In this regard, a general framework tool was developedto evaluate and compare different measurements (e.g., travel tim and emissions) to betterassist decision makers to determine the most effective freight transportation strategy.Additionally, the travel time, level of service and emissions on Florida Strategic IntermodalSystem (SIS) were systematically analyzed using a VISSIM and MOVES simulation todetermine if it can be improved. For the scenarios simulated in this investigation, the inputincluded different patterns with a variety of peak hour volumes, truck percentages, speeds,and number of lanes. Additionally, the various total values of the resultant travel time,emissions and level of service for each SIS corridor were determined and calculated usinga General Linear Model and then tabulated to reveal input patterns. The results showed thata truck platooning lane can significantly reduce the travel time and emissions of trucks. Inthe second part, we proposed using a The Analytic Hierarchy Process (AHP) method toevaluate the potential benefits of building a new lane for autonomous trucks. The AHPmethod was developed to include all possible measurements that can assist decision makersto select the best autonomous truck policy. The results of the AHP model showed that thesafety criterion was significantly the most influential perspective per experts' opinions. Theresults showed that experts were more concerned about safety and environmentalconsiderations than the initial cost associated with building a new lane.
Show less
Date Issued
2018
Identifier
CFE0007056, ucf:51983
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0007056
A SYSTEMATIC ANALYSIS TO IDENTIFY, MITIGATE, QUANTIFY, AND MEASURE RISK FACTORS CONTRIBUTING TO FALLS IN NASA GROUND SUPPORT OPERATIONS
Title
A SYSTEMATIC ANALYSIS TO IDENTIFY, MITIGATE, QUANTIFY, AND MEASURE RISK FACTORS CONTRIBUTING TO FALLS IN NASA GROUND SUPPORT OPERATIONS.
Creator
Ware , Joylene, Bush , Pamela, University of Central Florida
Abstract / Description
The objective of the research was to develop and validate a multifaceted model such as a fuzzy Analytical Hierarchy Process (AHP) model that considers both qualitative and quantitative elements with relative significance in assessing the likelihood of falls and aid in the design of NASA Ground Support Operations in aerospace environments. The model represented linguistic variables that quantified significant risk factor levels. Multiple risk factors that contribute to falls in NASA Ground...
Show moreThe objective of the research was to develop and validate a multifaceted model such as a fuzzy Analytical Hierarchy Process (AHP) model that considers both qualitative and quantitative elements with relative significance in assessing the likelihood of falls and aid in the design of NASA Ground Support Operations in aerospace environments. The model represented linguistic variables that quantified significant risk factor levels. Multiple risk factors that contribute to falls in NASA Ground Support Operations are task related, human/personal, environmental, and organizational. Six subject matter experts were asked to participate in a voting system involving a survey where they judge risk factors using the fundamental pairwise comparison scale. The results were analyzed and synthesize using Expert Choice Software, which produced the relative weights for the risk factors. The following are relative weights for these risk factors: Task Related (0.314), Human/Personal (0.307), Environmental (0.248), and Organizational (0.130). The overall inconsistency ratio for all risk factors was 0.07, which indicates the model results were acceptable. The results show that task related risk factors are the highest cause for falls and the organizational risk are the lowest cause for falls in NASA Ground Support Operations. The multiple risk factors weights were validated by having two teams of subject matter experts create priority vectors separately and confirm the weights are valid. The fuzzy AHP model usability was utilizing fifteen subjects in a repeated measures analysis. The subjects were asked to evaluate three scenarios in NASA KSC Ground Support Operations regarding various case studies and historical data. The three scenarios were Shuttle Landing Facility (SLF), Launch Complex Payloads (LCP), and Vehicle Assembly Building (VAB). The Kendall Coefficient of Concordance for assessment agreement between and within the subjects was 1.00. Therefore, the appraisers are applying essentially the same standard when evaluating the scenarios. In addition, a NASA subject matter expert was requested to evaluate the three scenarios also. The predicted value was compared to accepted value. The results from the subject matter expert for the model usability confirmed that the predicted value and accepted value for the likelihood rating were similar. The percentage error for the three scenarios was 0%, 33%, 0% respectively. Multiple descriptive statistics for a 95% confidence interval and t-test are the following: coefficient of variation (21.36), variance (0.251), mean (2.34), and standard deviation (0.501). Model validation was the guarantee of agreement with the NASA standard. Model validation process was partitioned into three components: reliability, objectivity, and consistency. The model was validated by comparing the fuzzy AHP model to NASA accepted model. The results indicate there was minimal variability with fuzzy AHP modeling. As a result, the fuzzy AHP model is confirmed valid. Future research includes developing fall protection guidelines.
Show less
Date Issued
2009
Identifier
CFE0002789, ucf:48094
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0002789
Defining a Stakeholder-Relative Model to Measure Academic Department Efficiency at Achieving Quality in Higher Education
Title
Defining a Stakeholder-Relative Model to Measure Academic Department Efficiency at Achieving Quality in Higher Education.
Creator
Robinson, Federica, Sepulveda, Jose, Reilly, Charles, Nazzal, Dima, Armacost, Robert, Feldheim, Mary, University of Central Florida
Abstract / Description
In a time of strained resources and dynamic environments, the importance of effective and efficient systems is critical. This dissertation was developed to address the need to use feedback from multiple stakeholder groups to define quality and assess an entity's efficiency at achieving such quality.A decision support model with applicability to diverse domains was introduced to outline the approach. Three phases, (1) quality model development, (2) input-output selection and (3) relative...
Show moreIn a time of strained resources and dynamic environments, the importance of effective and efficient systems is critical. This dissertation was developed to address the need to use feedback from multiple stakeholder groups to define quality and assess an entity's efficiency at achieving such quality.A decision support model with applicability to diverse domains was introduced to outline the approach. Three phases, (1) quality model development, (2) input-output selection and (3) relative efficiency assessment, captured the essence of the process which also delineates the approach per tool applied. This decision support model was adapted in higher education to assess academic departmental efficiency at achieving stakeholder-relative quality. Phase 1 was accomplished through a three round, Delphi-like study which involved user group refinement. Those results were compared to the criteria of an engineering accreditation body (ABET) to support the model's validity to capture quality in the College of Engineering (&) Computer Science, its departments and programs. In Phase 2 the Analytic Hierarchy Process (AHP) was applied to the validated model to quantify the perspective of students, administrators, faculty and employers (SAFE). Using the composite preferences for the collective group (n=74), the model was limited to the top 7 attributes which accounted for about 55% of total preferences. Data corresponding to the resulting variables, referred to as key performance indicators, was collected using various information sources and infused in the data envelopment analysis (DEA) methodology (Phase 3). This process revealed both efficient and inefficient departments while offering transparency of opportunities to maximize quality outputs. Findings validate the potential of the Delphi-like, analytic hierarchical, data envelopment analysis approach for administrative decision-making in higher education. However, the availability of more meaningful metrics and data is required to adapt the model for decision making purposes. Several recommendations were included to improve the usability of the decision support model and future research opportunities were identified to extend the analyses inherent and apply the model to alternative areas.
Show less
Date Issued
2013
Identifier
CFE0004921, ucf:49636
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0004921
Not Woman Enough Harassment: Scale Development and an Integrated Model from Antecedent to Outcome
Title
Not Woman Enough Harassment: Scale Development and an Integrated Model from Antecedent to Outcome.
Creator
Wolcott, Amanda, Jentsch, Kimberly, Jentsch, Florian, Shoss, Mindy, Lopez, Stephanie, University of Central Florida
Abstract / Description
The rise of research on workplace mistreatment in the past twenty years can be attributed to the realization that workplace mistreatment is associated with a host of deleterious outcomes for both the individual targets of the mistreatment and the organizations in which they work. However, the extant literature is failing to capture the full range of sex-based mistreatment that people may experience through a tendency to focus solely on sexual harassment and sex discrimination, which are very...
Show moreThe rise of research on workplace mistreatment in the past twenty years can be attributed to the realization that workplace mistreatment is associated with a host of deleterious outcomes for both the individual targets of the mistreatment and the organizations in which they work. However, the extant literature is failing to capture the full range of sex-based mistreatment that people may experience through a tendency to focus solely on sexual harassment and sex discrimination, which are very specific types of behavior based on one's sex and gender stereotypes. In this dissertation, I introduce the construct of Not Woman Enough Harassment, or the extent to which women perceive that they are treated unfavorably because they do not meet traditionally held stereotypes of femininity. A scale was developed and validated in order to measure this type of harassment, and a model from antecedent to outcome was proposed. Results demonstrated that not woman enough harassment was experienced by approximately 32.5% of the sample. The scale showed good psychometric properties, with two distinct factors of harassment based on physical and non-physical traits. Not woman enough harassment was demonstrated to be distinct from other forms of sexual and workplace harassment. Discomfort with gender norm conformity and masculine physical and non-physical expression were shown to be antecedents of not woman enough harassment, along with a moderating effect of job gender context. In addition, not woman enough harassment significantly predicted decreased job satisfaction, affective organizational commitment, and task performance and increased withdrawal and job stress. Similar patterns were found for males with not man enough harassment.
Show less
Date Issued
2017
Identifier
CFE0006962, ucf:51629
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0006962