Improving GPGPU Concurrency with Elastic Kernels

Each new generation of GPUs vastly increases the resources available to GPGPU programs. GPU programming models (like CUDA) were designed to scale to use these resources. However, we find that CUDA programs actually do not scale to utilize all available resources, with over 30% of resources going unused on average for programs of the Parboil2 suite that we used in our work. Current GPUs therefore allow concurrent execution of kernels to improve utilization. In this work, we study concurrent execution of GPU kernels using multiprogram workloads on current NVIDIA Fermi GPUs. On two-program workloads from the Parboil2 benchmark suite we find concurrent execution is often no better than serialized execution. We identify that the lack of control over resource allocation to kernels is a major serialization bottleneck. We propose transformations that convert CUDA kernels into elastic kernels which permit fine-grained control over their resource usage. We then propose several elastic-kernel aware concurrency policies that offer significantly better performance and concurrency compared to the current CUDA policy. We evaluate our proposals on real hardware using multiprogrammed workloads constructed from benchmarks in the Parboil 2 suite. On average, our proposals increase system throughput (STP) by 1.21x and improve the average normalized turnaround time (ANTT) by 3.73x for two-program workloads when compared to the current CUDA concurrency implementation.

Estimation of Probabilistic Bounds on Phase CPI and Relevance in WCET Analysis

Estimating program worst case execution time(WCET) accurately and efficiently is a challenging task. Several programs exhibit phase behavior wherein cycles per instruction (CPI) varies in phases during execution. Recent work has suggested the use of phases in such programs to estimate WCET with minimal instrumentation. However the suggested model uses a function of mean CPI that has no probabilistic guarantees. We propose to use Chebyshev's inequality that can be applied to any arbitrary distribution of CPI samples, to probabilistically bound CPI of a phase. Applying Chebyshev's inequality to phases that exhibit high CPI variation leads to pessimistic upper bounds. We propose a mechanism that refines such phases into sub-phases based on program counter(PC) signatures collected using profiling and also allows the user to control variance of CPI within a sub-phase. We describe a WCET analyzer built on these lines and evaluate it with standard WCET and embedded benchmark suites on two different architectures for three chosen probabilities, p={0.9, 0.95 and 0.99}. For p= 0.99, refinement based on PC signatures alone, reduces average pessimism of WCET estimate by 36%(77%) on Arch1 (Arch2). Compared to Chronos, an open source static WCET analyzer, the average improvement in estimates obtained by refinement is 5%(125%) on Arch1 (Arch2). On limiting variance of CPI within a sub-phase to {50%, 10%, 5% and 1%} of its original value, average accuracy of WCET estimate improves further to {9%, 11%, 12% and 13%} respectively, on Arch1. On Arch2, average accuracy of WCET improves to 159% when CPI variance is limited to 50% of its original value and improvement is marginal beyond that point.

Does lean imply green?: a study of the power performance implications of Java runtime bloat

The presence of software bloat in large flexible software systems can hurt energy efficiency. However, identifying and mitigating bloat is fairly effort intensive. To enable such efforts to be directed where there is a substantial potential for energy savings, we investigate the impact of bloat on power consumption under different situations. We conduct the first systematic experimental study of the joint power-performance implications of bloat across a range of hardware and software configurations on modern server platforms. The study employs controlled experiments to expose different effects of a common type of Java runtime bloat, excess temporary objects, in the context of the SPECPower_ssj2008 workload. We introduce the notion of equi-performance power reduction to characterize the impact, in addition to peak power comparisons. The results show a wide variation in energy savings from bloat reduction across these configurations. Energy efficiency benefits at peak performance tend to be most pronounced when bloat affects a performance bottleneck and non-bloated resources have low energy-proportionality. Equi-performance power savings are highest when bloated resources have a high degree of energy proportionality. We develop an analytical model that establishes a general relation between resource pressure caused by bloat and its energy efficiency impact under different conditions of resource bottlenecks and energy proportionality. Applying the model to different "what-if" scenarios, we predict the impact of bloat reduction and corroborate these predictions with empirical observations. Our work shows that the prevalent software-only view of bloat is inadequate for assessing its power-performance impact and instead provides a full systems approach for reasoning about its implications.

Optimal incentive timing strategies for product marketing on social networks

We consider the problem of devising incentive strategies for viral marketing of a product. In particular, we assume that the seller can influence penetration of the product by offering two incentive programs: a) direct incentives to potential buyers (influence) and b) referral rewards for customers who influence potential buyers to make the purchase (exploit connections). The problem is to determine the optimal timing of these programs over a finite time horizon. In contrast to algorithmic perspective popular in the literature, we take a mean-field approach and formulate the problem as a continuous-time deterministic optimal control problem. We show that the optimal strategy for the seller has a simple structure and can take both forms, namely, influence-and-exploit and exploit-and-influence. We also show that in some cases it may optimal for the seller to deploy incentive programs mostly for low degree nodes. We support our theoretical results through numerical studies and provide practical insights by analyzing various scenarios.

Identifying services from Legacy batch applications

Transaction processing is a key constituent of the IT workload of commercial enterprises (e.g., banks, insurance companies). Even today, in many large enterprises, transaction processing is done by legacy "batch" applications, which run offline and process accumulated transactions. Developers acknowledge the presence of multiple loosely coupled pieces of functionality within individual applications. Identifying such pieces of functionality (which we call "services") is desirable for the maintenance and evolution of these legacy applications. This is a hard problem, which enterprises grapple with, and one without satisfactory automated solutions. In this paper, we propose a novel static-analysis-based solution to the problem of identifying services within transaction-processing programs. We provide a formal characterization of services in terms of control-flow and data-flow properties, which is well-suited to the idioms commonly exhibited by business applications. Our technique combines program slicing with the detection of conditional code regions to identify services in accordance with our characterization. A preliminary evaluation, based on a manual analysis of three real business programs, indicates that our approach can be effective in identifying useful services from batch applications.

Packet flow analysis in IP networks using data-flow analysis

Static analysis (aka offline analysis) of a model of an IP network is useful for understanding, debugging, and verifying packet flow properties of the network. Data-flow analysis is a method that has typically been applied to static analysis of programs. We propose a new, data-flow based approach for static analysis of packet flows in networks. We also investigate an application of our analysis to the problem of inferring a high-level policy from the network, which has been addressed in the past only for a single router.

Regulation of transcription initiation in mycobacteria

The success of Mycobacterium tuberculosis as a deadly pathogen lies in its ability to survive under adverse conditions during pre- and post-infectious stages. The transcription process and the regulation of gene expression are central to the survival of the pathogen through the harsh conditions. Multiple sigma factors, transcription regulators, diverse two-component systems contribute in tailoring the events to meet the challenges faced by the pathogen. Although the machinery is conserved, many aspects of transcription and its regulation seem to be different in mycobacteria when compared to the other well-studied organisms. Here, we discuss salient aspects of transcription and its regulation in the context of distinct physiology of mycobacteria.

Fast and efficient automatic memory management for GPUs using compiler-assisted runtime coherence scheme

Exploiting the performance potential of GPUs requires managing the data transfers to and from them efficiently which is an error-prone and tedious task. In this paper, we develop a software coherence mechanism to fully automate all data transfers between the CPU and GPU without any assistance from the programmer. Our mechanism uses compiler analysis to identify potential stale accesses and uses a runtime to initiate transfers as necessary. This allows us to avoid redundant transfers that are exhibited by all other existing automatic memory management proposals. We integrate our automatic memory manager into the X10 compiler and runtime, and find that it not only results in smaller and simpler programs, but also eliminates redundant memory transfers. Tested on eight programs ported from the Rodinia benchmark suite it achieves (i) a 1.06x speedup over hand-tuned manual memory management, and (ii) a 1.29x speedup over another recently proposed compiler--runtime automatic memory management system. Compared to other existing runtime-only and compiler-only proposals, it also transfers 2.2x to 13.3x less data on average.

Reconciling transactional conflicts with compiler's help

Software transactional memory(STM) is a promising programming paradigm for shared memory multithreaded programs. While STM offers the promise of being less error-prone and more programmer friendly compared to traditional lock-based synchronization, it also needs to be competitive in performance in order for it to be adopted in mainstream software. A major source of performance overheads in STM is transactional aborts. Conflict resolution and aborting a transaction typically happens at the transaction level which has the advantage that it is automatic and application agnostic. However it has a substantial disadvantage in that STM declares the entire transaction as conflicting and hence aborts it and re-executes it fully, instead of partially re-executing only those part(s) of the transaction, which have been affected due to the conflict. This "Re-execute Everything" approach has a significant adverse impact on STM performance. In order to mitigate the abort overheads, we propose a compiler aided Selective Reconciliation STM (SR-STM) scheme, wherein certain transactional conflicts can be reconciled by performing partial re-execution of the transaction. Ours is a selective hybrid approach which uses compiler analysis to identify those data accesses which are legal and profitable candidates for reconciliation and applies partial re-execution only to these candidates selectively while other conflicting data accesses are handled by the default STM approach of abort and full re-execution. We describe the compiler analysis and code transformations required for supporting selective reconciliation. We find that SR-STM is effective in reducing the transactional abort overheads by improving the performance for a set of five STAMP benchmarks by 12.58% on an average and up to 22.34%.

Multiple sub-row buffers in DRAM: unlocking performance and energy improvement opportunities

The twin demands of energy-efficiency and higher performance on DRAM are highly emphasized in multicore architectures. A variety of schemes have been proposed to address either the latency or the energy consumption of DRAMs. These schemes typically require non-trivial hardware changes and end up improving latency at the cost of energy or vice-versa. One specific DRAM performance problem in multicores is that interleaved accesses from different cores can potentially degrade row-buffer locality. In this paper, based on the temporal and spatial locality characteristics of memory accesses, we propose a reorganization of the existing single large row-buffer in a DRAM bank into multiple sub-row buffers (MSRB). This re-organization not only improves row hit rates, and hence the average memory latency, but also brings down the energy consumed by the DRAM. The first major contribution of this work is proposing such a reorganization without requiring any significant changes to the existing widely accepted DRAM specifications. Our proposed reorganization improves weighted speedup by 35.8%, 14.5% and 21.6% in quad, eight and sixteen core workloads along with a 42%, 28% and 31% reduction in DRAM energy. The proposed MSRB organization enables opportunities for the management of multiple row-buffers at the memory controller level. As the memory controller is aware of the behaviour of individual cores it allows us to implement coordinated buffer allocation schemes for different cores that take into account program behaviour. We demonstrate two such schemes, namely Fairness Oriented Allocation and Performance Oriented Allocation, which show the flexibility that memory controllers can now exploit in our MSRB organization to improve overall performance and/or fairness. Further, the MSRB organization enables additional opportunities for DRAM intra-bank parallelism and selective early precharging of the LRU row-buffer to further improve memory access latencies. These two optimizations together provide an additional 5.9% performance improvement.

Sustaining cooperation on networks: an analytical study based on evolutionary game theory

We analytically study the role played by the network topology in sustaining cooperation in a society of myopic agents in an evolutionary setting. In our model, each agent plays the Prisoner's Dilemma (PD) game with its neighbors, as specified by a network. Cooperation is the incumbent strategy, whereas defectors are the mutants. Starting with a population of cooperators, some agents are switched to defection. The agents then play the PD game with their neighbors and compute their fitness. After this, an evolutionary rule, or imitation dynamic is used to update the agent strategy. A defector switches back to cooperation if it has a cooperator neighbor with higher fitness. The network is said to sustain cooperation if almost all defectors switch to cooperation. Earlier work on the sustenance of cooperation has largely consisted of simulation studies, and we seek to complement this body of work by providing analytical insight for the same. We find that in order to sustain cooperation, a network should satisfy some properties such as small average diameter, densification, and irregularity. Real-world networks have been empirically shown to exhibit these properties, and are thus candidates for the sustenance of cooperation. We also analyze some specific graphs to determine whether or not they sustain cooperation. In particular, we find that scale-free graphs belonging to a certain family sustain cooperation, whereas Erdos-Renyi random graphs do not. To the best of our knowledge, ours is the first analytical attempt to determine which networks sustain cooperation in a population of myopic agents in an evolutionary setting.

On secrecy above secrecy capacity

We consider secrecy obtained when one transmits on a Gaussian Wiretap channel above the secrecy capacity. Instead of equivocation, we consider probability of error as the criterion of secrecy. The usual channel codes are considered for transmission. The rates obtained can reach the channel capacity. We show that the “confusion” caused to the Eve when the rate of transmission is above capacity of the Eve's channel is similar to the confusion caused by using the wiretap channel codes used below the secrecy capacity.

Game theoretic analysis of collusions in nonneutral networks

This paper studies the impact of exclusive contracts between a content provider (CP) and an internet service provider (ISP) in a nonneutral network. We consider a simple linear demand function for the CPs. We studywhen an exclusive contract is benefcial to the colluding pair and evaluate its impact on the noncolluding players at equilibrium. For the case of two CPs and one ISP we show that collusion may not always be benefcial. We derive an explicit condition in terms of the advertisement revenues of the CPs that tells when a collusion is proftable to the colluding entities.

Endoplasmic Reticulum Stress-Mediated Activation of p38 MAPK, Caspase-2 and Caspase-8 Leads to Abrin-Induced Apoptosis

Abrin from Abrus precatorius plant is a potent protein synthesis inhibitor and induces apoptosis in cells. However, the relationship between inhibition of protein synthesis and apoptosis is not well understood. Inhibition of protein synthesis by abrin can lead to accumulation of unfolded protein in the endoplasmic reticulum causing ER stress. The observation of phosphorylation of eukaryotic initiation factor 2 alpha and upregulation of CHOP (CAAT/enhancer binding protein (C/EBP) homologous protein), important players involved in ER stress signaling by abrin, suggested activation of ER stress in the cells. ER stress is also known to induce apoptosis via stress kinases such as p38 MAPK and JNK. Activation of both the pathways was observed upon abrin treatment and found to be upstream of the activation of caspases. Moreover, abrin-induced apoptosis was found to be dependent on p38 MAPK but not JNK. We also observed that abrin induced the activation of caspase-2 and caspase-8 and triggered Bid cleavage leading to mitochondrial membrane potential loss and thus connecting the signaling events from ER stress to mitochondrial death machinery.

Chaperoning mitochondrial permeability transition: regulation of transition pore complex by a J-protein, DnaJC15

Mitochondria have a central role in the intrinsic pathway of apoptosis and involve activation of several transmembrane channels leading to release of death factors. Reduced expression of a mitochondrial J-protein DnaJC15 was associated with the development of chemoresistance in ovarian cancer cells. DnaJC15 was found to be a part of mitochondrial protein-transport machinery, though its connection with cell death mechanisms is still unclear. In the present study, we have provided evidence towards a novel function of DnaJC15 in regulation of mitochondrial permeability transition pore (MPTP) complex in normal and cancer cells. Overexpression of DnaJC15 resulted in MPTP opening and induction of apoptosis, whereas reduced amount of protein suppressed MPTP activation, upon cisplatin treatment. DnaJC15 was found to exert its proapoptotic function through the essential component of MPTP, cyclophilin D (CypD). Our results reveal a specific role of DnaJC15 in recruitment and coupling of CypD with mitochondrial permeability transition. In summary, our analysis provides first-time insights on the functional connection between mitochondrial inner membrane protein translocation machinery-associated J-protein DnaJC15 and regulation of cell death pathways.