| 1. |
- Hansson, Erik, 1983-, et al.
(författare)
-
A Quantitative Comparison of PRAM based Emulated Shared Memory Architectures to Current Multicore CPUs and GPUs
- 2014
-
Ingår i: 27th International Conference on Architecture of Computing Systems (ARCS), 2014, ARCS Workshops: Proc. PASA-2014 11th Workshop on Parallel Systems and Algorithms, Lübeck, Germany. - Lübeck, Germany : VDE Verlag GmbH. - 9783800735792 ; , s. 27-33
-
Konferensbidrag (refereegranskat)abstract
- The performance of current multicore CPUs and GPUs is limited in computations making frequent use of communication/synchronization between the subtasks executed in parallel. This is because the directory-based cache systems scale weakly and/or the cost of synchronization is high. The Emulated Shared Memory (ESM) architectures relying on multithreading and efficient synchronization mechanisms have been developed to solve these problems affecting both performance and programmability of current machines. In this paper, we compare preliminarily the performance of three hardware implemented ESM architectures with state-of-the-art multicore CPUs and GPUs. The benchmarks are selected to cover different patterns of parallel computation and therefore reveal the performance potential of ESM architectures with respect to current multicores.
|
|
| 2. |
- Dahlström, Märta, et al.
(författare)
-
Development of a fluorescent intensity assay amenable for high-throughput screening for determining 15-lipoxygenase activity.
- 2010
-
Ingår i: Journal of Biomolecular Screening. - : Elsevier BV. - 1087-0571 .- 1552-454X. ; 15:6, s. 671-9
-
Tidskriftsartikel (refereegranskat)abstract
- 15-Lipoxygenase-1 catalyzes the introduction of molecular oxygen into polyunsaturated fatty acids to form a lipid hydroperoxide. The authors have developed an assay for the detection of lipid hydroperoxides formed by human 15-lipoxygenase (15-LO) in enzyme or cellular assays using either a 96-well or a 384-well format. The assays described take advantage of the ability of lipid hydroperoxides to oxidize nonfluorescent diphenyl-1-pyrenylphosphine (DPPP) to a fluorescent phosphine oxide. Oxidation of DPPP yields a fluorescent compound, which is not sensitive to temperature and is stable for more than 2 h. The assay is sensitive toward inhibition and robust with a Z' value of 0.79 and 0.4 in a 96- and 384-well format, respectively, and thus amenable for high-throughput screening. The utility of DPPP as a marker for 15-lipoxygenase activity was demonstrated with both enzyme- and cell-based assays for the identification of hits and to determine potency by IC(50) determinations.
|
|
| 3. |
- Forsell, Martti, et al.
(författare)
-
Hardware and Software Support for NUMA Computing on Configurable Emulated Shared Memory Architectures
- 2013
-
Ingår i: 2013 IEEE 27th International Parallel and Distributed Processing Symposium Workshops & PhD Forum (IPDPSW). - : IEEE conference proceedings. - 9780769549798 ; , s. 640-647
-
Konferensbidrag (refereegranskat)abstract
- The emulated shared memory (ESM) architectures are good candidates for future general purpose parallel computers due to their ability to provide easy-to-use explicitly parallel synchronous model of computation to programmers as well as avoid most performance bottlenecks present in current multicore architectures. In order to achieve full performance the applications must, however, have enough thread-level parallelism (TLP). To solve this problem, in our earlier work we have introduced a class of configurable emulated shared memory (CESM) machines that provides a special non-uniform memory access (NUMA) mode for situations where TLP is limited or for direct compatibility for legacy code sequential computing or NUMA mechanism. Unfortunately the earlier proposed CESM architecture does not integrate the different modes of the architecture well together e.g. by leaving the memories for different modes isolated and therefore the programming interface is non-integrated. In this paper we propose a number of hardware and software techniques to support NUMA computing in CESM architectures in a seamless way. The hardware techniques include three different NUMA-shared memory access mechanisms and the software ones provide a mechanism to integrate NUMA computation into the standard parallel random access machine (PRAM) operation of the CESM. The hardware techniques are evaluated on our REPLICA CESM architecture and compared to an ideal CESM machine making use of the proposed software techniques.
|
|
| 4. |
- Forsell, Martti, et al.
(författare)
-
NUMA Computing with Hardware and Software Co-Support on Configurable Emulated Shared Memory Architectures
- 2014
-
Ingår i: International Journal of Networking and Computing. - 2185-2839 .- 2185-2847. ; 4:1, s. 189-206
-
Tidskriftsartikel (refereegranskat)abstract
- The emulated shared memory (ESM) architectures are good candidates for future general purpose parallel computers due to their ability to provide an easy-to-use explicitly parallel synchronous model of computation to programmers as well as avoid most performance bottlenecks present in current multicore architectures. In order to achieve full performance the applications must, however, have enough thread-level parallelism (TLP). To solve this problem, in our earlier work we have introduced a class of configurable emulated shared memory (CESM) machines that provides a special non-uniform memory access (NUMA) mode for situations where TLP is limited or for direct compatibility for legacy code sequential computing and NUMA mechanism. Unfortunately the earlier proposed CESM architecture does not integrate the different modes of the architecture well together e.g. by leaving the memories for different modes isolated and therefore the programming interface is non-integrated. In this paper we propose a number of hardware and software techniques to support NUMA computing in CESM architectures in a seamless way. The hardware techniques include three different NUMA shared memory access mechanisms and the software ones provide a mechanism to integrate and optimize NUMA computation into the standard parallel random access machine (PRAM) operation of the CESM. The hardware techniques are evaluated on our REPLICA CESM architecture and compared to an ideal CESM machine making use of the proposed software techniques.
|
|
| 5. |
- Mäkelä, Jari-Matti, et al.
(författare)
-
Design of the Language Replica for Hybrid PRAM-NUMA Many-core Architectures
- 2012
-
Ingår i: Parallel and Distributed Processing with Applications (ISPA), 2012. - : IEEE conference proceedings. - 9781467316316 ; , s. 697-704
-
Konferensbidrag (refereegranskat)abstract
- Parallel programming is widely considered very demanding for an average programmer due to inherent asynchrony of underlying parallel architectures. In this paper we describe the main design principles and core features of Replica -- a parallel language aimed for high-level programming of a new paradigm of reconfigurable, scalable and powerful synchronous shared memory architectures that promise to make parallel programming radically easier with the help of strict memory consistency and deterministic synchronous execution of hardware threads and multi-operations.
|
|
| 6. |
- Rozental, Alexander, et al.
(författare)
-
Psychometric evaluation of the Swedish version of the pure procrastination scale, the irrational procrastination scale, and the susceptibility to temptation scale in a clinical population
- 2014
-
Ingår i: BMC Psychology. - : Springer Science and Business Media LLC. - 2050-7283. ; 2
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Procrastination is a prevalent self-regulatory failure associated with stress and anxiety, decreased well-being, and poorer performance in school as well as work. One-fifth of the adult population and half of the student population describe themselves as chronic and severe procrastinators. However, despite the fact that it can become a debilitating condition, valid and reliable self-report measures for assessing the occurrence and severity of procrastination are lacking, particularly for use in a clinical context. The current study explored the usefulness of the Swedish version of three Internet-administered self-report measures for evaluating procrastination; the Pure Procrastination Scale, the Irrational Procrastination Scale, and the Susceptibility to Temptation Scale, all having good psychometric properties in English.Methods: In total, 710 participants were recruited for a clinical trial of Internet-based cognitive behavior therapy for procrastination. All of the participants completed the scales as well as self-report measures of depression, anxiety, and quality of life. Principal Component Analysis was performed to assess the factor validity of the scales, and internal consistency and correlations between the scales were also determined. Intraclass Correlation Coefficient, Minimal Detectable Change, and Standard Error of Measurement were calculated for the Irrational Procrastination Scale.Results: The Swedish version of the scales have a similar factor structure as the English version, generated good internal consistencies, with Cronbach’s α ranging between .76 to .87, and were moderately to highly intercorrelated. The Irrational Procrastination Scale had an Intraclass Correlation Coefficient of .83, indicating excellent reliability. Furthermore, Standard Error of Measurement was 1.61, and Minimal Detectable Change was 4.47, suggesting that a change of almost five points on the scale is necessary to determine a reliable change in self-reported procrastination severity.Conclusions: The current study revealed that the Pure Procrastination Scale, the Irrational Procrastination Scale, and the Susceptibility to Temptation Scale are both valid and reliable from a psychometric perspective, and that they might be used for assessing the occurrence and severity of procrastination via the Internet.
|
|
