Design and Development of an FPGA-based Distributed Computing Processing Platform

This thesis presents two frameworks- a software framework and a hardware core manager framework- which, together, can be used to develop a processing platform using a distributed system of field-programmable gate array (FPGA) boards. The software framework providesusers with the ability to easily develop applications that exploit the processing power of FPGAs while the hardware core manager framework gives users the ability to configure and interact with multiple FPGA boards and/or hardware cores. This thesis describes the design and development of these frameworks and analyzes the performance of a system that was constructed using the frameworks. The performance analysis included measuring the effect of incorporating additional hardware components into the system and comparing the system to a software-only implementation. This work draws conclusions based on the provided results of the performance analysis and offers suggestions for future work.

HIV treatment response and prognosis in Europe and North America in the first decade of highly active antiretroviral therapy: a collaborative analysis

BACKGROUND: Highly active antiretroviral therapy (HAART) for the treatment of HIV infection was introduced a decade ago. We aimed to examine trends in the characteristics of patients starting HAART in Europe and North America, and their treatment response and short-term prognosis. METHODS: We analysed data from 22,217 treatment-naive HIV-1-infected adults who had started HAART and were followed up in one of 12 cohort studies. The probability of reaching 500 or less HIV-1 RNA copies per mL by 6 months, and the change in CD4 cell counts, were analysed for patients starting HAART in 1995-96, 1997, 1998, 1999, 2000, 2001, and 2002-03. The primary endpoints were the hazard ratios for AIDS and for death from all causes in the first year of HAART, which were estimated using Cox regression. RESULTS: The proportion of heterosexually infected patients increased from 20% in 1995-96 to 47% in 2002-03, and the proportion of women from 16% to 32%. The median CD4 cell count when starting HAART increased from 170 cells per muL in 1995-96 to 269 cells per muL in 1998 but then decreased to around 200 cells per muL. In 1995-96, 58% achieved HIV-1 RNA of 500 copies per mL or less by 6 months compared with 83% in 2002-03. Compared with 1998, adjusted hazard ratios for AIDS were 1.07 (95% CI 0.84-1.36) in 1995-96 and 1.35 (1.06-1.71) in 2002-03. Corresponding figures for death were 0.87 (0.56-1.36) and 0.96 (0.61-1.51). INTERPRETATION: Virological response after starting HAART improved over calendar years, but such improvement has not translated into a decrease in mortality.

Rates of disease progression according to initial highly active antiretroviral therapy regimen: a collaborative analysis of 12 prospective cohort studies

BACKGROUND: No large clinical end-point trials have been conducted comparing regimens among human immunodeficiency virus type 1-positive persons starting antiretroviral therapy. We examined clinical progression according to initial regimen in the Antiretroviral Therapy Cohort Collaboration, which is based on 12 European and North American cohort studies. METHODS: We analyzed progression to death from any cause and to AIDS or death (AIDS/death), comparing efavirenz (EFV), nevirapine (NVP), nelfinavir, idinavir, ritonavir (RTV), RTV-boosted protease inhibitors (PIs), saquinavir, and abacavir. We also compared nucleoside reverse-transcriptase inhibitor pairs: zidovudine/lamivudine (AZT/3TC), stavudine (D4T)/3TC, D4T/didanosine (DDI), and others. RESULTS: A total of 17,666 treatment-naive patients, 55,622 person-years at risk, 1,617 new AIDS events, and 895 deaths were analyzed. Compared with EFV, the adjusted hazard ratio (HR) for AIDS/death was 1.28 (95% confidence interval [CI], 1.03-1.60) for NVP, 1.31 (95% CI, 1.01-1.71) for RTV, and 1.45 (95% CI, 1.15-1.81) for RTV-boosted PIs. For death, the adjusted HR for NVP was 1.65 (95% CI, 1.16-2.36). The adjusted HR for death for D4T/3TC was 1.35 (95% CI, 1.14-1.59), compared with AZT/3TC. CONCLUSIONS: Outcomes may vary across initial regimens. Results are observational and may have been affected by bias due to unmeasured or residual confounding. There is a need for large, randomized, clinical end-point trials.

Outcomes associated with drug-eluting and bare-metal stents: a collaborative network meta-analysis

Whether the two drug-eluting stents approved by the US Food and Drug Administration-a sirolimus-eluting stent and a paclitaxel-eluting stent-are associated with increased risks of death, myocardial infarction, or stent thrombosis compared with bare-metal stents is uncertain. Our aim was to compare the safety and effectiveness of these stents.

Prognosis of HIV-1-infected patients up to 5 years after initiation of HAART: collaborative analysis of prospective studies

OBJECTIVE: To estimate the prognosis over 5 years of HIV-1-infected, treatment-naive patients starting HAART, taking into account the immunological and virological response to therapy. DESIGN: A collaborative analysis of data from 12 cohorts in Europe and North America on 20,379 adults who started HAART between 1995 and 2003. METHODS: Parametric survival models were used to predict the cumulative incidence at 5 years of a new AIDS-defining event or death, and death alone, first from the start of HAART and second from 6 months after the start of HAART. Data were analysed by intention-to-continue-treatment, ignoring treatment changes and interruptions. RESULTS: During 61 798 person-years of follow-up, 1005 patients died and an additional 1303 developed AIDS. A total of 10 046 (49%) patients started HAART either with a CD4 cell count of less than 200 cells/microl or with a diagnosis of AIDS. The 5-year risk of AIDS or death (death alone) from the start of HAART ranged from 5.6 to 77% (1.8-65%), depending on age, CD4 cell count, HIV-1-RNA level, clinical stage, and history of injection drug use. From 6 months the corresponding figures were 4.1-99% for AIDS or death and 1.3-96% for death alone. CONCLUSION: On the basis of data collected routinely in HIV care, prognostic models with high discriminatory power over 5 years were developed for patients starting HAART in industrialized countries. A risk calculator that produces estimates for progression rates at years 1 to 5 after starting HAART is available from www.art-cohort-collaboration.org.

Second international collaborative study evaluating performance characteristics of methods measuring the von Willebrand factor cleaving protease (ADAMTS-13)

BACKGROUND: Over the last 4 years ADAMTS-13 measurement underwent dramatic progress with newer and simpler methods. AIMS: Blind evaluation of newer methods for their performance characteristics. DESIGN: The literature was searched for new methods and the authors invited to join the evaluation. Participants were provided with a set of 60 coded frozen plasmas that were prepared centrally by dilutions of one ADAMTS-13-deficient plasma (arbitrarily set at 0%) into one normal-pooled plasma (set at 100%). There were six different test plasmas ranging from 100% to 0%. Each plasma was tested 'blind' 10 times by each method and results expressed as percentage vs. the local and the common standard provided by the organizer. RESULTS: There were eight functional and three antigen assays. Linearity of observed-vs.-expected ADAMTS-13 levels assessed as r2 ranged from 0.931 to 0.998. Between-run reproducibility expressed as the (mean) CV for repeated measurements was below 10% for three methods, 10-15% for five methods and up to 20% for the remaining three. F-values (analysis of variance) calculated to assess the capacity to distinguish between ADAMTS-13 levels (the higher the F-value, the better the capacity) ranged from 3965 to 137. Between-method variability (CV) amounted to 24.8% when calculated vs. the local and to 20.5% when calculated vs. the common standard. Comparative analysis showed that functional assays employing modified von Willebrand factor peptides as substrate for ADAMTS-13 offer the best performance characteristics. CONCLUSIONS: New assays for ADAMTS-13 have the potential to make the investigation/management of patients with thrombotic microangiopathies much easier than in the past.

Drug eluting and bare metal stents in people with and without diabetes: collaborative network meta-analysis

Objective To compare the effectiveness and safety of three types of stents (sirolimus eluting, paclitaxel eluting, and bare metal) in people with and without diabetes mellitus. Design Collaborative network meta-analysis. Data sources Electronic databases (Medline, Embase, the Cochrane Central Register of Controlled Trials), relevant websites, reference lists, conference abstracts, reviews, book chapters, and proceedings of advisory panels for the US Food and Drug Administration. Manufacturers and trialists provided additional data. Review methods Network meta-analysis with a mixed treatment comparison method to combine direct within trial comparisons between stents with indirect evidence from other trials while maintaining randomisation. Overall mortality was the primary safety end point, target lesion revascularisation the effectiveness end point. Results 35 trials in 3852 people with diabetes and 10 947 people without diabetes contributed to the analyses. Inconsistency of the network was substantial for overall mortality in people with diabetes and seemed to be related to the duration of dual antiplatelet therapy (P value for interaction 0.02). Restricting the analysis to trials with a duration of dual antiplatelet therapy of six months or more, inconsistency was reduced considerably and hazard ratios for overall mortality were near one for all comparisons in people with diabetes: sirolimus eluting stents compared with bare metal stents 0.88 (95% credibility interval 0.55 to 1.30), paclitaxel eluting stents compared with bare metal stents 0.91 (0.60 to 1.38), and sirolimus eluting stents compared with paclitaxel eluting stents 0.95 (0.63 to 1.43). In people without diabetes, hazard ratios were unaffected by the restriction. Both drug eluting stents were associated with a decrease in revascularisation rates compared with bare metal stents in people both with and without diabetes. Conclusion In trials that specified a duration of dual antiplatelet therapy of six months or more after stent implantation, drug eluting stents seemed safe and effective in people both with and without diabetes.

Memory resource balancing for virtualized computing

Virtualization has become a common abstraction layer in modern data centers. By multiplexing hardware resources into multiple virtual machines (VMs) and thus enabling several operating systems to run on the same physical platform simultaneously, it can effectively reduce power consumption and building size or improve security by isolating VMs. In a virtualized system, memory resource management plays a critical role in achieving high resource utilization and performance. Insufficient memory allocation to a VM will degrade its performance dramatically. On the contrary, over-allocation causes waste of memory resources. Meanwhile, a VM’s memory demand may vary significantly. As a result, effective memory resource management calls for a dynamic memory balancer, which, ideally, can adjust memory allocation in a timely manner for each VM based on their current memory demand and thus achieve the best memory utilization and the optimal overall performance. In order to estimate the memory demand of each VM and to arbitrate possible memory resource contention, a widely proposed approach is to construct an LRU-based miss ratio curve (MRC), which provides not only the current working set size (WSS) but also the correlation between performance and the target memory allocation size. Unfortunately, the cost of constructing an MRC is nontrivial. In this dissertation, we first present a low overhead LRU-based memory demand tracking scheme, which includes three orthogonal optimizations: AVL-based LRU organization, dynamic hot set sizing and intermittent memory tracking. Our evaluation results show that, for the whole SPEC CPU 2006 benchmark suite, after applying the three optimizing techniques, the mean overhead of MRC construction is lowered from 173% to only 2%. Based on current WSS, we then predict its trend in the near future and take different strategies for different prediction results. When there is a sufficient amount of physical memory on the host, it locally balances its memory resource for the VMs. Once the local memory resource is insufficient and the memory pressure is predicted to sustain for a sufficiently long time, a relatively expensive solution, VM live migration, is used to move one or more VMs from the hot host to other host(s). Finally, for transient memory pressure, a remote cache is used to alleviate the temporary performance penalty. Our experimental results show that this design achieves 49% center-wide speedup.