Variable Granularity Access Tracking Scheme for Improving the Performance of Software Transactional Memory

Software transactional memory (STM) has been proposed as a promising programming paradigm for shared memory multi-threaded programs as an alternative to conventional lock based synchronization primitives. Typical STM implementations employ a conflict detection scheme, which works with uniform access granularity, tracking shared data accesses either at word/cache line or at object level. It is well known that a single fixed access tracking granularity cannot meet the conflicting goals of reducing false conflicts without impacting concurrency adversely. A fine grained granularity while improving concurrency can have an adverse impact on performance due to lock aliasing, lock validation overheads, and additional cache pressure. On the other hand, a coarse grained granularity can impact performance due to reduced concurrency. Thus, in general, a fixed or uniform granularity access tracking (UGAT) scheme is application-unaware and rarely matches the access patterns of individual application or parts of an application, leading to sub-optimal performance for different parts of the application(s). In order to mitigate the disadvantages associated with UGAT scheme, we propose a Variable Granularity Access Tracking (VGAT) scheme in this paper. We propose a compiler based approach wherein the compiler uses inter-procedural whole program static analysis to select the access tracking granularity for different shared data structures of the application based on the application's data access pattern. We describe our prototype VGAT scheme, using TL2 as our STM implementation. Our experimental results reveal that VGAT-STM scheme can improve the application performance of STAMP benchmarks from 1.87% to up to 21.2%.

Neurochemistry of the afferents to the rat cochlear root nucleus: Possible synaptic modulation of the acoustic startle

Afferents to the primary startle circuit are essential for the elicitation and modulation of the acoustic startle reflex (ASR). In the rat, cochlear root neurons (CRNs) comprise the first component of the acoustic startle circuit and play a crucial role in mediating the ASR. Nevertheless, the neurochemical pattern of their afferents remains unclear. To determine the distribution of excitatory and inhibitory inputs, we used confocal microscopy to analyze the immunostaining for vesicular glutamate and GABA transporter proteins (VGLUT1 and VGAT) on retrogradely labeled CRNs. We also used reverse transcription-polymerase chain reaction (RT-PCR) and immunohistochemistry to detect and localize specific neurotransmitter receptor subunits in the cochlear root. Our results show differential distributions of VGLUT1- and VGAT-immunoreactive endings around cell bodies and dendrites. The RT-PCR data showed a positive band for several ionotropic glutamate receptor subunits, M1-M5 muscarinic receptor subtypes, the glycine receptor alpha 1 subunit (GlyR alpha 1), GABA(A), GABA(B), and subunits of alpha 2 and beta-noradrenergic receptors. By immunohistochemistry, we confirmed that CRN cell bodies exhibit positive immunoreaction for the glutamate receptor (GluR) 3 and NR1 GluR subunits. Cell bodies and dendrites were also positive for M2 and M4, and GlyR alpha 1. Other subunits, such as GluR1 and GluR4 of the AMPA GluRs, were observed in glial cells neighboring unlabeled CRN cell bodies. We further confirmed the existence of nor-adrenergic afferents onto CRNs from the locus coeruleus by combining tyrosine hydroxylase immunohistochemistry and tract-tracing experiments. Our results provide valuable information toward understanding how CRNs might integrate excitatory and inhibitory inputs, and hence how they could elicit and modulate the ASR. (C) 2008 IBRO. Published by Elsevier Ltd. All rights reserved.