Search

As various graphics processing unit architectures are deployed across broad computing spectrum from a hand-held or embedded device to a high-performance computing server, OpenCL becomes the de facto standard programming environment for general-purpose computing on graphics processing units. Unlike its CPU counterpart, OpenCL has several distinct features such as its disciplined memory model, which is partially inherited from conventional 3D graphics programming models. On the other hand, due to ever increasing memory bandwidth pressure and low power requirement, the capacity of on-chip caches in GPUs keeps increasing over time. Given such trends, we believe that we have interesting programming model/architecture co-optimization opportunities, in particular, how to energy-efficiently utilize large on-chip caches for GPUs. In this paper, as a showcase, we study the characteristics of the OpenCL memory model and propose a technique called GPU Region-aware energy-efficient non-inclusive cache hierarchy, or GREEN cache hierarchy. With the GREEN cache, our simulation results show that we can save 56 percent of dynamic energy in the L1 cache, 39 percent of dynamic energy in the L2 cache, and 50 percent of leakage energy in the L2 cache with practically no performance degradation and off-chip access increases.

This paper describes the architecture, design, analysis, and simulation and measurement results of the 3D-MAPS (3D massively parallel processor with stacked memory) chip built with a 1.5 V, 130 nm process technology and a two-tier 3D stacking technology using 1.2 \microm-diameter, 6 \micro m-height through-silicon vias (TSVs) and 3.4\nbsp\microm-diameter face-to-face bond pads. 3D-MAPS consists of a core tier containing 64 cores and a memory tier containing 64 memory blocks. Each core communicates with its dedicated 4KB SRAM block using face-to-face bond pads, which provide negligible data transfer delay between the core and the memory tiers. The maximum operating frequency is 277 MHz and the maximum memory bandwidth is 70.9 GB/s at 277 MHz. The peak measured memory bandwidth usage is 63.8 GB/s and the peak measured power is approximately 4 W based on eight parallel benchmarks.

Arabidopsis AtERF71/HRE2, a transcription activator, is located in the nucleus and is involved in the signal transduction of low oxygen and osmotic stresses. In this study, microarray analysis using AtERF71/HRE2-overexpressing transgenic plants was performed to identify genes downstream of AtERF71/HRE2. A total of 161 different genes as well as AtERF71/HRE2 showed more than a twofold higher expression in AtERF71/HRE2-overexpressing transgenic plants compared with wild-type plants. Among the 161 genes, 24 genes were transcriptional regulators, such as transcription factors and DNA-binding proteins, based on gene ontology annotations, suggesting that AtERF71/HRE2 is an upstream transcription factor that regulates the activities of various downstream genes via these transcription regulators. RT-PCR analysis of 15 genes selected out of the 161 genes showed higher expression in AtERF71/HRE2-overexpressing transgenic plants, validating the microarray data. On the basis of Genevestigator database analysis, 51 genes among the 161 genes were highly expressed under low oxygen and/or osmotic stresses. RT-PCR analysis showed that the expression levels of three genes among the selected 15 genes increased under low oxygen stress and another three genes increased under high salt stress, suggesting that these genes might be downstream genes of AtERF71/HRE2 in low oxygen or high salt stress signal transduction. Microarray analysis results indicated that AtERF71/HRE2 might also be involved in the responses to other abiotic stresses and also in the regulation of plant developmental processes.

As dynamic RAM scaling approaches its physical limit, phase-change memory is the most mature and well-studied option for potential DRAM replacement. However, malicious wear-out attacks can exploit PCM's limited write endurance. To address this, a low-cost wear-leveling scheme can dynamically randomize the data addresses across the entire address space and obfuscate their actual locations from users and system software.

Plants adapt to abiotic stresses by complex mechanisms involving various stress-responsive genes. Here, we identified a DEAD-box RNA helicase (RH) gene, AtRH17, in Arabidopsis, involved in salt-stress responses using activation tagging, a useful technique for isolating novel stress-responsive genes. AT895, an activation tagging line, was more tolerant than wild type (WT) under NaCl treatment during germination and seedling development, and AtRH17 was activated in AT895. AtRH17 possesses nine well-conserved motifs of DEAD-box RHs, consisting of motifs Q, I, Ia, Ib, and II-VI. Although at least 12 orthologs of AtRH17 have been found in various plant species, no paralog occurs in Arabidopsis. AtRH17 protein is subcellularily localized in the nucleus. AtRH17-overexpressing transgenic plants (OXs) were more tolerant to high concentrations of NaCl and LiCl compared with WT, but no differences from WT were detected among seedlings exposed to mannitol and freezing treatments. Moreover, in the mature plant stage, AtRH17 OXs were also more tolerant to NaCl than WT, but not to drought, suggesting that AtRH17 is involved specifically in the salt-stress response. Notably, transcriptions of well-known abscisic acid (ABA)-dependent and ABA-independent stress-response genes were similar or lower in AtRH17 OXs than WT under salt-stress treatments. Taken together, our findings suggest that AtRH17, a nuclear DEAD-box RH protein, is involved in salt-stress tolerance, and that its overexpression confers salt-stress tolerance via a pathway other than the well-known ABA-dependent and ABA-independent pathways.

In this study, we constructed various kinds of binary vectors with the pPZP backbone for co-overexpression, tissue- or development-specific expression and stress-inducible expression, and validated them for ectopic expression of target genes. Using a modified CaMV 35S promoter, a binary vector was generated for co-overexpression of two different genes and was confirmed to be efficient for overexpressing two different target genes at the same time and place. Binary vectors containing At2S3, KNAT1 or LFY promoters were constructed for tissue-specific or development-specific gene expression, and the binary vectors were suited for embryo/young seedling stage-, shoot apical meristem- or leaf primordia-specific expressions. Furthermore, the binary vectors containing RD29A or AtNCED3 promoters were validated as suitable vectors for gene expression induced by abiotic stresses such as high salt, ABA, MV and low temperature. Taken together, the binary vectors constructed in this study would be very useful for analyzing the biological functions of target genes and molecular mechanisms through ectopic expression.

Heterogeneous multicore processors have emerged as an energy- and area-efficient architectural solution to improving performance for domain-specific applications such as those with a plethora of data-level parallelism. These processors typically contain a large number of small, compute-centric cores for acceleration while keeping one or two high-performance ILP cores on the die to guarantee single-thread performance. Although a major portion of the transistors are occupied by the acceleration cores, these resources will sit idle when running unparallelized legacy codes or the sequential part of an application. To address this underutilization issue, in this article, we introduce Chameleon, a flexible heterogeneous multicore architecture to virtualize these resources for enhancing memory performance when running sequential programs. The Chameleon architecture can dynamically virtualize the idle acceleration cores into a last-level cache, a data prefetcher, or a hybrid between these two techniques. In addition, Chameleon can operate in an adaptive mode that dynamically configures the acceleration cores between the hybrid mode and the prefetch-only mode by monitoring the effectiveness of the Chameleon cache mode. In our evaluation with SPEC2006 benchmark suite, different levels of performance improvements were achieved in different modes for different applications. In the case of the adaptive mode, Chameleon improves the performance of SPECint06 and SPECfp06 by 31% and 15%, on average. When considering only memory-intensive applications, Chameleon improves the system performance by 50% and 26% for SPECint06 and SPECfp06, respectively.

An updated take on Amdahl's analytical model uses modern design constraints to analyze many-core design alternatives. The revised models provide computer architects with a better understanding of many-core design types, enabling them to make more informed tradeoffs.

Despite increasing reports that CCCH zinc finger proteins function in plant development and stress responses, the functions and molecular aspects of many CCCH zinc finger proteins remain uncharacterized. Here, we characterized the biological and molecular functions of AtC3H17, a unique Arabidopsis gene encoding a non-tandem CCCH zinc finger protein. AtC3H17 was ubiquitously expressed throughout the life cycle of Arabidopsis plants and their organs. The rate and ratio of seed germination of atc3h17 mutants were slightly slower and lower, respectively, than those of the wild type (WT), whereas AtC3H17-overexpressing transgenic plants (OXs) showed an enhanced germination rate. atc3h17 mutant seedlings were smaller and lighter than WT seedlings while AtC3H17 OX seedlings were larger and heavier. In regulation of flowering time, atc3h17 mutants showed delayed flowering, whereas AtC3H17 OXs showed early flowering compared with the WT. In addition, overexpression of AtC3H17 affected seed development, displaying abnormalities compared with the WT. AtC3H17 protein was localized to the nucleus and showed transcriptional activation activity in yeast and Arabidopsis protoplasts. The N-terminal region of AtC3H17, containing a conserved EELR-like motif, was necessary for transcriptional activation activity, and the two conserved glutamate residues in the EELR-like motif played an important role in transcriptional activation activity. Real-time PCR and transactivation analyses showed that AtC3H17 might be involved in seed development via transcriptional activation of OLEO1, OLEO2 and CRU3. Our results suggest that AtC3H17 has pleiotropic effects on vegetative development such as seed germination and seedling growth, flowering and seed development, and functions as a nuclear transcriptional activator in Arabidopsis.

Aurora A kinase has drawn considerable attention as a therapeutic target for cancer therapy. However, the underlying molecular and cellular mechanisms of the anticancer effects of Aurora A kinase inhibition are still not fully understood. Herein, we show that depletion of Aurora A kinase by RNA interference (RNAi) in hepatocellular carcinoma (HCC) cells upregulated FoxO1 in a p53-dependent manner, which induces cell cycle arrest. Introduction of an RNAi-resistant Aurora A kinase into Aurora A-knockdown cells resulted in downregulation of FoxO1 expression and rescued proliferation. In addition, silencing of FoxO1 in Aurora A-knockdown cells allowed the cells to exit cytostatic arrest, which, in turn, led to massive cell death. Our results suggest that FoxO1 is responsible for growth arrest at the G2/M phase that is induced by Aurora A kinase inhibition.