Search

Transient faults continue to be a critical concern in a range of computing domains including: High-Performance Computing (HPC), scientific computing, and the automotive industry. While radiation-induced faults have been well studied and understood in microprocessors, their impact on computations on Graphic Processing Units (GPU) has received less attention. GPUs are now being used in a large number of HPC and automotive markets. Mitigating the effects of transient faults requires a thorough understanding of the interaction between applications, system software, and the underlying hardware. Developing this understanding is quite challenging mainly due to our limited ability to capture and study cross-layer reliability interactions. In this paper, we consider the combination of neutron beam testing experiments with architectural fault injection experiments to gain a deeper understanding of the relationship between the vulnerability of GPUs and the underlying workload characteristics of applications targeted for GPU devices.

Asphalt binder modification is one of the approaches taken to improve pavement performance. In addition it may also be improved through the addition of fibers to Asphalt mix that enhances material strength and fatigue characteristics while adding ductility. Due to their inherent compatibility with Asphalt concrete and excellent mechanical properties, fibers offer an excellent potential for modification of Asphalt concrete mix. To investigate the behavior of Fiber Modified Asphalt Concrete Mixes (FMACM), a preliminary study has been done to determine the feasibility of modifying the behavior of a Asphalt Concrete (AC) mixture through the use of Glass fiber and Polyester fiber. The purpose of this study was to identify and understand the factor that is responsible for improving the behavior of FMACM. Asphalt concrete samples were prepared and tested in the laboratory to evaluate the various mixture characteristics. The conclusions drawn from the study on testing of fiber-modified mixes are that fiber modified Asphalt mixtures have shown increased stiffness and resistance to permanent deformation. Fatigue characteristics of the mixtures were also improved. Fibers used in the study were of high tensile strength therefore test results of FMACM have shown higher indirect tensile strength and improved skid resistance for paving applications.

This study was designed to determine the effects of dietary supplementation of black cumin (Nigella sativa), garlic (Allium sativa) and turmeric (Curcuma longa) on the production performance and egg quality in laying hens. A total of 180, 26-weeks old White Leghorn layers were randomly assigned into nine dietary treatments each with four replicates having 5 birds in each, and reared for 12 weeks from 28 to 39 weeks of age. The experimental diets were prepared by supplementing basal diet (T1) with an antibiotic (Enramycin @ 2.5 g per quintal of feed) feed additive (T2), 1% black cumin powder (T3), 1% garlic powder (T4), 1% turmeric powder (T5), 1% mixture of black cumin and turmeric in equal proportion (T6), 1% mixture of black cumin and garlic in equal proportion (T7), 1% mixture of garlic and turmeric in equal proportion (T8) and 1% mixture of black cumin seed, garlic and turmeric in equal proportion (T9). Results indicated a significantly (P

Introduction: Porcelain fused to metal is the most common restoration. The success of the prosthesis greatly depends on the mechanical bonding between the metal alloy and the ceramic. Newer techniques such as selective laser sintering (SLS) and computer-aided design are fast replacing the lost-wax technique due to ease of fabrication. This study was carried out to ascertain the best possible technique to ensure success. Materials and Methods: Forty strips of cobalt–chromium (Co–Cr) metal were fabricated and divided into two groups (lost-wax technique vs. SLS technology), which were then bonded with ceramic and compared for bond strength and fracture toughness. Results: SLS group showed higher bond strength than conventional lost-wax technique (CAST) group but lowered fracture toughness. This difference was also found to be statistically significant. Conclusion: The lost-wax technique is a time-tested method that needs not be abandoned until successful evolution of emerging technologies is firmly established.

The majority of roads in India are constructed of flexible pavements, wherein, the bulk of distress is in the form of either cracking (fatigue) or rutting (permanent deformation). Rutting is the longitudinal depression in the wheel path in bituminous pavements, which can be attributed to excessive consolidation, formed by an accumulation of permanent deformations caused by repeated heavy loads, or lateral movement of the material, caused by shear failure of the bituminous concrete layer, or a combination of both mechanisms. There are countries facing functional constraints on their flexible road pavements due to rutting and trying to resolve this failure. Rutting in pavement is a serious mode of distress beside fatigue in bituminous pavement in high temperature areas, including India, and may lead to premature failure in pavements and result in early and costly rehabilitation. In addition, rutting in pavements causes hydroplaning and severe physiological and safety concern for users. Premature distress and associated problems in pavement result in an economic burden on the tax payer. Hence, this problems needs to be properly addressed through evaluation and mitigation measures so that the occurrence and resulting impacts are minimized. In order to study the pavement failure modes and to minimize them so as to get good serviceability from the huge road assets the country is having, the actual response of pavement structure needs to be monitored. This necessitates a systematic assessment and performance evaluation of pavement with known design and influencing factors. An array of response measuring instruments, under measurable loading conditions is required to accrue objective indicators. Evaluation strategies use performance monitoring through laboratory and field evaluation, while the field evaluation itself can be accomplished by monitoring in-service pavements or smaller replicated test strips using an "Accelerated Pavement Testing" protocol. CSIR-CRRI (Central Road Research Institute) has recently procured and established a national facility of Accelerated Pavement Testing. Through this, tire pressure can be simulated on the in-field loading on pavements, and design traffic. A systematic study was initiated on the permanent deformation development involving a flexible pavement designed as per Indian practice. The paper brings out the details of this evaluation study and also features the capabilities and applications of Indian APTF in the issue.

Variety of road based transport modes catering to the transport demand ply in large number on the road system of urban India. As a result, the traffic and transportation problems are aggravating day by day. These problems manifest in the form of increased traffic congestion, increased air and noise pollution, accidents, delays etc. The consumption of fuel is on the increase due to enhanced trip lengths, shift of modal share towards personalized modes of travel and at signalized intersections due to idling of vehicles during stoppage phases. The results of a study conducted by CRRI in 2005 estimated that fuel worth of Indian Rupees. 1, 0000 Million is wasted every year in Delhi by vehicles idling at 600 signalized traffic signals and was around 15% of the total fuel consumed annually in Delhi. In addition, the time loss to the commuters is also associated with the delays. The running engines during idling also generate emissions, which are harmful both for human health and ecology. One of the ways to conserve fuels is to minimize its wastage. It is necessary to understand the amount of fuel loss and emissions generated at signalized intersections in the country. By applying various engineering / management measures the fuel wastage and associated emissions can be reduced. Presently there is no model that can give the amount of fuel loss and emissions in relation to the type of vehicle and delays. In this paper a review of the study for exploring suitable mitigation measures to improve the signalized intersections are presented. 

Checkpoint and restart mechanisms have been widely used in large scientific simulation applications to make forward progress in case of failures. However, none of the prior works have considered the interaction of power-constraint with temperature, reliability, performance, and checkpointing interval. It is not clear how power-capping may affect optimal checkpointing interval. What are the involved reliability, performance, and energy trade-offs? In this paper, we develop a deep understanding about the interaction between power-capping and scientific applications using checkpoint/restart as resilience mechanism, and propose a new model for the optimal checkpointing interval (OCI) under power-capping. Our study reveals several interesting, and previously unknown, insights about how power-capping affects the reliability, energy consumption, performance.

Resilience is an important challenge for extreme-scale supercomputers. Today, failures in supercomputers are assumed to be uniformly distributed in time. However, recent studies show that failures in high-performance computing systems are partially correlated in time, generating periods of higher failure density. Our study of the failure logs of multiple supercomputers show that periods of higher failure density occur with up to three times more than the average. We design a monitoring system that listens to hardware events and forwards important events to the runtime to detect those regime changes. We implement a runtime capable of receiving notifications and adapt dynamically. In addition, we build an analytical model to predict the gains that such dynamic approach could achieve. We demonstrate that in some systems, our approach can reduce the wasted time by over 30%.

More than 95 % of road network in India is made up of flexible pavement, especially due to the relative lesser initial cost, ease of construction and maintenance. The design of flexible pavement in India is done with criteria of load associated fatigue cracking and permanent deformation (rutting). While design methods try to consider these failure modes, more rational inputs based on intrinsic evaluations are required for better and improved designs. The Accelerated Pavement Testing Facility (APTF) is regarded as a versatile tool all over the world in pavement evaluation and performance monitoring due to its advance evaluation capabilities within a short time. This paper presents the rutting performance characteristics of a typical flexible pavement built as per Indian design practice, evaluated using APTF. APTF is capable of evaluation with regard to total structural ability of a pavement based on number of standard axle load passes which represents time period and load sustainability of a pavement with respect to defined failure criteria. The pavement was instrumented with interfacial response monitoring, wherein deflections were effectively measured using state of art instrumentation technique. The study result and possible rutting mechanism under the operational capabilities of APTF and test condition have been discussed in the paper.

To reduce the energy consumption and CO2 emissions during asphalt production, several environmentally friendly technologies have been developed during the last years. One of these technologies is the cold recycling by using foamed bitumen. Foaming the bitumen reduces the binder viscosity temporarily and increases the volume as well. Homogenous foams are produced by injection of cold water into hot bitumen. The paper presents the results of laboratory testing of the physical and mechanical parameters of the recycled mixes using the foamed bitumen and resistance to the action of water. The aim of the tests was to evaluate the properties of the mixes in terms of the RAP Content and Foam Binder Content. To evaluate the significance of impact of both factors i.e., Foam Binder Content and RAP Content on the distribution of the analyzed parameters, two-way Analysis of Variance (ANOVA) was performed. ANOVA Analysis results suggest that the RAP in cold mixes is not completely acting as black rock implying that some portion of the residual aged binder is possibly rejuvenated or softened by adding new binders.

An experiment was conducted to discern the comparative effects of dietary supplementation of herbal methionine and synthetic DL-methionine on growth performance and nutrient utilization in broiler chicks during summer season. A total of 180, day-old commercial broiler chicks were divided into 6 treatments with 3 replicates each and 10 broiler chicks per replicate. There were 6 dietary treatments viz., treatments T1 to T6. The treatment T1 served as control, basal diet (maize-soyabean meal based) without methionine supplementation, whereas in treatments T2 to T6, the basal diet contained herbal methionine at 0, 25, 50, 75 and 100% levels by replacing synthetic DL-methionine, respectively. The total supplemental level of methionine in the diets was 0.20%. The feeding trial lasted for 42 days viz., 0–21 days (starter phase) and 21–42 days (finisher phase). During starter phase (0–21 days), the body weight gains were 576.20, 611.33, 598.13, 606.93, 596.10 and 636.09 g, respectively, in treatments T1, T2, T3, T4, T5 and T6 and there was higher (P

Day old commercial broiler chicks (No.=150) were distributed equally into five groups of 30 chicks each which were further replicated to three groups of ten each. The chicks were placed on one of the dietary treatments i.e. basal diet without any supplement (CON) or 0.125% antibiotic growth promoter (AGP) or 3 levels of turmeric powder i.e 0.5% (TP5), 1.0% TP (TP10) and 1.5% TP (TP15). At the end of of the experiment, the birds of antibiotic growth promoter group had highest (P 0.05) by treatments. Carcass traits like dressing yield, giblet weight, cooking loss, pH, shear force and proximate composition was not affected by treatments whereas separable fat and meat cholesterol level reduced (P

Finite element simulations have been conducted to determine the temperature distribution (both in radial and axial direction), heat and electric flux-field in the powder compact/die/punch assembly during the spark plasma sintering (SPS) process. A thermal–electrical coupled model with temperature dependent thermal and electrical properties is implemented. The simulation studies were conducted using both ABAQUS and MATLAB and a range of power input, varying thermal conductivity of powder compact were considered. Also, the effect of time variation on both thermal and electric field evolution was assessed. During SPS, the heat transmission pattern and the temperature difference between the specimen center and the die surface depend on thermal conductivity of the powder compact, time of sintering and power input. The simulation results also revealed that the temperature gradient across the powder compact/graphite die wall is higher for conditions of higher power input and/or powder compact with lower thermal conductivity.

Strength reliability, one of the critical factors restricting wider use of brittle materials in various structural applications, is commonly characterized by Weibull strength distribution function. In the present work, the detailed statistical analysis of the strength data is carried out using a larger class of probability models including Weibull, normal, log-normal, gamma and generalized exponential distributions. Our analysis is validated using the strength data, measured with a number of structural ceramic materials and a glass material. An important implication of the present study is that the gamma or log-normal distribution function, in contrast to Weibull distribution, may describe more appropriately, in certain cases, the experimentally measured strength data.

Twenty lactating crossbred cows yielding 10 to 15 litres of milk daily during mid lactation were selected and divided into four groups of five animals to assess the effect of feeding calcium soaps of palm oil fatty acids (bypass fat) on milk yield, milk composition and nutrient utilization in lactating crossbred cows. The animals in groups 1 (control), 2, 3 and 4 were fed concentrate mixture containing 0 (no bypass fat), 2, 4 and 6% bypass fat, respectively. The average daily dry matter consumption in the various groups ranged from 13.1 to 13.6 kg and showed no significant difference among treatment groups. There was no significant difference among different groups in digestibility of DM, OM, CP and CF, however, ether extract digestibility in cows of groups 2 and 4 was significantly (p

The increasing data demands from high-performance computing applications significantly accelerate the capacity, capability and reliability requirements of storage systems. As systems scale, component failures and repair times increase, significantly impacting data availability. A wide array of decision points must be balanced in designing such systems. We propose a systematic approach that balances and optimizes both initial and continuous spare provisioning based on a detailed investigation of the anatomy and field failure data analysis of extreme-scale storage systems. We consider the component failure characteristics and its cost and impact at the system level simultaneously. We build a tool to evaluate different provisioning schemes, and the results demonstrate that our optimized provisioning can reduce the duration of data unavailability by as much as 52% under a fixed budget. We also observe that non-disk components have much higher failure rates than disks, and warrant careful considerations in the overall provisioning process.

Online data-intensive services parallelize query execution across distributed software components. Interactive response time is a priority, so online query executions return answers without waiting for slow running components to finish. However, data from these slow components could lead to better answers. We propose Ubora, an approach to measure the effect of slow running components on the quality of answers. Ubora randomly samples online queries and executes them twice. The first execution elides data from slow components and provides fast online answers; the second execution waits for all components to complete. Ubora uses memoization to speed up mature executions by replaying network messages exchanged between components. Our systems-level implementation works for a wide range of platforms, including Hadoop/Yarn, Apache Lucene, the EasyRec Recommendation Engine, and the OpenEphyra question answering system. Ubora computes answer quality much faster than competing approaches that do not use memoization. With Ubora, we show that answer quality can and should be used to guide online admission control. Our adaptive controller processed 37% more queries than a competing controller guided by the rate of timeouts., Comment: Technical Report

As we approach exascale, the scientific simulations are expected to experience more interruptions due to increased system failures. Designing better HPC resilience techniques requires understanding the key characteristics of system failures on these systems. While temporal properties of system failures on HPC systems have been well-investigated, there is limited understanding about the spatial characteristics of system failures and its impact on the resilience mechanisms. Therefore, we examine the spatial characteristics and behavior of system failures. We investigate the interaction between spatial and temporal characteristics of failures and its implications for system operations and resilience mechanisms on large-scale HPC systems. We show that system failures have "spatial locality" at different granularity in the system, study impact of different failure-types, and investigate the correlation among different failure-types. Finally, we propose a novel scheme that exploits the spatial locality in failures to improve application and system performance. Our evaluation shows that the proposed scheme significantly improves the system performance in a dynamic and production-level HPC system.

Increase in graphics hardware performance and improvements in programmability has enabled GPUs to evolve from a graphics-specific accelerator to a general-purpose computing device. Titan, the world's second fastest supercomputer for open science in 2014, consists of more dum 18,000 GPUs that scientists from various domains such as astrophysics, fusion, climate, and combustion use routinely to run large-scale simulations. Unfortunately, while the performance efficiency of GPUs is well understood, their resilience characteristics in a large-scale computing system have not been fully evaluated. We present a detailed study to provide a thorough understanding of GPU errors on a large-scale GPU-enabled system. Our data was collected from the Titan supercomputer at the Oak Ridge Leadership Computing Facility and a GPU cluster at the Los Alamos National Laboratory. We also present results from our extensive neutron-beam tests, conducted at Los Alamos Neutron Science Center (LANSCE) and at ISIS (Rutherford Appleron Laboratories, UK), to measure the resilience of different generations of GPUs. We present several findings from our field data and neutron-beam experiments, and discuss the implications of our results for future GPU architects, current and future HPC computing facilities, and researchers focusing on GPU resilience.

An experiment was conducted to investigate the effect of feeding transgenic cottonseed (Bt.) vis-a-vis non-transgenic (non-Bt.) cottonseed on blood biochemical constituents in lactating Murrah buffaloes. Twenty Murrah buffaloes in mid-lactation were divided into 2 groups of 10 each. Animals of group I were fed with 39.5% non-transgenic cottonseed in concentrate mixture while the same percentage of transgenic (Bt.) cottonseed was included in the concentrate mixture fed to the animals of group II. Animals of both groups were fed with concentrate mixture to support their milk production requirements. Each buffalo was also offered 20 kg mixed green fodder (oats and berseem) and wheat straw ad libitum. The experimental feeding trial lasted for 35 days. There was no significant difference in the dry matter intake between the two groups of buffaloes. All the buffaloes gained body weight, however, the differences were non significant. Total erythrocyte count, hemoglobin content and packed cell volume were 9.27±0.70×10 6 /µl, 13.01±0.60 g/dl and 34.87±1.47%, respectively in group I with the corresponding figures of 8.88±0.33, 12.99±0.52 and 31.08±1.52 in group II. The values of total erythrocyte count, haemoglobin content and packed cell volume did not differ significantly between the two groups of buffaloes. The concentration of plasma glucose, serum total proteins, albumin, globulin, triglycerides and high density lipoprotein were non significantly higher in buffaloes fed non-transgenic cottonseed than in buffaloes fed transgenic cottonseed. The cholesterol concentration was significantly (p

With the advent of big data, the I/O subsystems of large-scale compute clusters are becoming a center of focus. More applications are putting greater demands on end-to-end I/O performance. These subsystems are often complex in design. They comprise of multiple hardware and software layers to cope with the increasing capacity, capability, and scalability requirements of data intensive applications. However, the sharing nature of storage resources and the intrinsic interactions across these layers make it a great challenge to realize end-to-end performance gains. This paper proposes a topology-aware strategy to balance the load across resources, to improve the per-application I/O performance. We demonstrate the effectiveness of our algorithm on an extreme-scale compute cluster, Titan, at the Oak Ridge Leadership Computing Facility (OLCF). Our experiments with both synthetic benchmarks and a real-world application show that, even under congestion, our proposed algorithm can improve large-scale application I/O performance significantly, resulting in both a reduction in application run time as well as a higher resolution of simulation run.

The Oak Ridge Leadership Computing Facility (OLCF) has deployed multiple large-scale parallel file systems (PFS) to support its operations. During this process, OLCF acquired significant expertise in large-scale storage system design, file system software development, technology evaluation, benchmarking, procurement, deployment, and operational practices. Based on the lessons learned from each new PFS deployment, OLCF improved its operating procedures, and strategies. This paper provides an account of our experience and lessons learned in acquiring, deploying, and operating large-scale parallel file systems. We believe that these lessons will be useful to the wider HPC community.

Continuing increase in the computational power of supercomputers has enabled large-scale scientific applications in the areas of astrophysics, fusion, climate and combustion to run larger and longer-running simulations, facilitating deeper scientific insights. However, these long-running simulations are often interrupted by multiple system failures. Therefore, these applications rely on "check pointing'" as a resilience mechanism to store application state to permanent storage and recover from failures. Unfortunately, check pointing incurs excessive I/O overhead on supercomputers due to large size of checkpoints, resulting in a sub-optimal performance and resource utilization. In this paper, we devise novel mechanisms to show how check pointing overhead can be mitigated significantly by exploiting the temporal characteristics of system failures. We provide new insights and detailed quantitative understanding of the check pointing overheads and trade-offs on large-scale machines. Our prototype implementation shows the viability of our approach on extreme-scale machines.

Serviceability is an indicator that represents the level of service a pavement provides to the users. This subjective opinion is closely related to objective aspects, which can be measured on the pavement’s surface. Modelling the present serviceability index is very important in pavement management system. In the present study, the present serviceability index (PSI) has been analyzed using artificial neural networks (ANN) for the flexible pavements of urban roads. The study area considered constitutes of 21 urban road sections for the Noida city in the NCR of New Delhi, capital of India. Field data collected includes slope variance, rut depth, patches, cracking and longitudinal cracking for two consecutive years on the selected road network. The developed ANN model has also been compared with model developed using multi-linear regression analysis.

Lactating crossbred cows (15) in mid lactation were assessed for their performance after feeding mineral mixture containing diammonium phosphate (DAP) in replacement of dicalcium phosphate (DCP) at different levels. Cows were divided into three groups of five each in such a way that the average milk yield in all the groups was similar. The animals in group 1 were fed ration containing mineral mixture with 0% DAP while those in groups 2 and 3 were fed ration with mineral mixture containing 50 and 100% DAP, respectively by replacing DCP on P content basis. There was no significant effect on the milk yield, milk composition in terms of total solids, fat, protein, lactose, ash, SNF, calcium, phosphorus and gross energy content, gross and net energetic efficiencies and gross and net efficiency of nitrogen utilization for milk production, body weight changes, feed intake and digestibility of nutrients. The values of blood biochemical parameters viz., serum total protein, albumin and globulin contents, serum alkaline phosphatase, alanine amino transferase and aspartate amino transferase, Ca and P were similar in all the groups. However, the digestibility of ether extract was lower (P

Map Reduce parallel programming model has seen wide adoption in data center applications. Recently, lightweight, fast, in-memory Map Reduce runtime systems have been proposed for shared memory systems. However, what factors affect performance and what performance bottlenecks exist for a given program, are not well understood. This paper builds an analytical model to capture key performance factors of shared memory Map Reduce and investigates important performance trends and behavior. Our study discovers several important findings and implications for system designers, performance tuners, and programmers. Our model quantifies relative contribution of different key performance factors for both map and reduce phases, and shows that performance of Map Reduce programs are highly input-content dependent. Our model reveals that performance is heavily affected by the order in which distinct keys are encountered during the Map phase, and the frequency of these distinct keys. Our model points out cases in which reduce phase time dominates the total execution time. We also show that data-structure and algorithm design choices affect map and reduce phases differently and sometimes affecting map phase positively while affecting reduce phase negatively. Finally, we propose an application classification framework that can be used to reason about performance bottlenecks for a given application.

Today, more than 99% of web-browsers are enabled with Javascript capabilities, and Javascript's popularity is only going to increase in the future. However, due to bytecode interpretation, Javascript codes suffer from severe performance penalty (up to 50x slower) compared to the corresponding native C/C++ code. We recognize that the first step to bridge this performance gap is to understand the the architectural execution characteristics of Javascript benchmarks. Therefore, this paper presents an in-depth architectural characterization of widely used V8 and Sunspider Javascript benchmarks using Google's V8 javascript engine. Using statistical data analysis techniques, our characterization study discovers and explains correlation among different execution characteristics in microarchitecture dependent as well as microarchitecture independent fashion. Furthermore, our study measures (dis)similarity among 33 different Javascript benchmarks and discusses its implications. Given the widespread use of Javascripts, we believe our findings are useful for both performance analysis and benchmarking communities.

Queues are commonly used in multithreaded programs for synchronization and communication. However, because software queues tend to be too expensive to support finegrained parallelism, hardware queues have been proposed to reduce overhead of communication between cores. Hardware queues require modifications to the processor core and need a custom interconnect. They also pose difficulties for the operating system because their state must be preserved across context switches. To solve these problems, we propose a hardware-accelerated queue, or HAQu. HAQu adds hardware to a CMP that accelerates operations on software queues. Our design implements fast queueing through an application's address space with operations that are compatible with a fully software queue. Our design provides accelerated and OS-transparent performance in three general ways: (1) it provides a single instruction for enqueueing and dequeueing which significantly reduces the overhead when used in fine-grained threading; (2) operations on the queue are designed to leverage low-level details of the coherence protocol; and (3) hardware ensures that the full state of the queue is stored in the application's address space, thereby ensuring virtualization. We have evaluated our design in the context of application domains: offloading fine-grained checks for improved software reliability, and automatic, fine-grained parallelization using decoupled software pipelining.

Dynamic memory management is one of the most expensive but ubiquitous operations in many operations in many C/C++ applications. Additional features such as security checks, while desirable, further worsen memory management overheads. With advent of multicore architecture, it is important to investigate how dynamic memory management overheads for sequential applications can be reduced. In this paper, we propose a new approach for accelerating dynamic memory management on multicore architecture, by offloading dynamic management functions to a separate thread that we refer to as memory management thread (MMT). We show that an efficient MMT design can give significant performance improvement by extracting parallelism while being agnostic to the underlying memory management library algorithms and data structures. We also show how parallelism provided by MMT can be beneficial for high overhead memory management tasks, for example, security checks related to memory management. We evaluate MMT on heap allocation-intensive benchmarks running on an Intel core 2 quad platform for two widely-used memory allocators: Doug Lea's and PHKmalloc allocators. On average, MMT achieves a speedup ratio of 1.19× for both allocators, while both the application and memory management libraries are unmodified and are oblivious to the parallelization scheme. For PHKmalloc with security checks turned on, MMT reduces the security check overheads from 21% to only 1% on average.