The Experts below are selected from a list of 263142 Experts worldwide ranked by ideXlab platform
Vulloji Raja - One of the best experts on this subject based on the ideXlab platform.
-
A Novel Key Aggregate Searchable Encryption for Group Data Sharing Using Cloud Data Storage
International Journal of Research, 2016Co-Authors: P. Ashok Kumar, Vulloji RajaAbstract:The capacity of preferentially sharing encrypted data with in contrast to clients by means of public cloud storage would quite ease safety depression, by means of likelihood data expose within the cloud. A Key experiment to design such encryption notion lies within the good-organized management encryption Keys. The preferred flexibility of allocating any group records with any group of clients by way of achieving weightage exclusive encryption Keys to be used for exclusive files. However, this involves the need of securely distributing to clients through a large quantity of Keys for both encryption and search, and people users have got to development to store the received Keys. The indirect want for comfortable communique, storage, and complexity obviously purpose the unreasonable procedure. In this paper, we pay attention to this useful problem, through suggesting the novel thought of Key Combination searchable encryption (KASE) and instantiating the inspiration through an actual KASE scheme, where a knowledge proprietor desires to share out a single Key to a consumer for distributing a massive number of records, and the person wants to reward a single trapdoor to the cloud for questioning the shared files.
Paolo Romano - One of the best experts on this subject based on the ideXlab platform.
-
Extending hardware transactional memory capacity via rollback-only transactions and suspend/resume
Distributed Computing, 2019Co-Authors: Shady Issa, Alexander Matveev, Pascal Felber, Paolo RomanoAbstract:Transactional memory (TM) aims at simplifying concurrent programming via the familiar abstraction of atomic transactions. Recently, Intel and IBM have integrated hardware based TM (HTM) implementations in commodity processors, paving the way for the mainstream adoption of the TM paradigm. Yet, existing HTM implementations suffer from a crucial limitation, which hampers the adoption of HTM as a general technique for regulating concurrent access to shared memory: the inability to execute transactions whose working sets exceed the capacity of CPU caches. In this article we propose P8TM, a novel approach that mitigates this limitation on IBM’s POWER8 architecture by leveraging a Key Combination of hardware and software techniques to support different execution paths. P8TM also relies on self-tuning mechanisms aimed at dynamically switching between different execution modes to best adapt to the workload characteristics. In-depth evaluation with several benchmarks indicates that P8TM can achieve striking performance gains in workloads that stress the capacity limitations of HTM, while achieving performance on par with HTM even in unfavourable workloads.
-
DISC - Extending Hardware Transactional Memory Capacity via Rollback-Only Transactions and Suspend/Resume.
Distributed Computing, 2019Co-Authors: Shady Issa, Alexander Matveev, Pascal Felber, Paolo RomanoAbstract:Transactional memory (TM) aims at simplifying concurrent programming via the familiar abstraction of atomic transactions. Recently, Intel and IBM have integrated hardware based TM (HTM) implementations in commodity processors, paving the way for the mainstream adoption of the TM paradigm. Yet, existing HTM implementations suffer from a crucial limitation, which hampers the adoption of HTM as a general technique for regulating concurrent access to shared memory: the inability to execute transactions whose working sets exceed the capacity of CPU caches. In this article we propose P8TM, a novel approach that mitigates this limitation on IBM’s POWER8 architecture by leveraging a Key Combination of hardware and software techniques to support different execution paths. P8TM also relies on self-tuning mechanisms aimed at dynamically switching between different execution modes to best adapt to the workload characteristics. In-depth evaluation with several benchmarks indicates that P8TM can achieve striking performance gains in workloads that stress the capacity limitations of HTM, while achieving performance on par with HTM even in unfavourable workloads.
P. Ashok Kumar - One of the best experts on this subject based on the ideXlab platform.
-
A Novel Key Aggregate Searchable Encryption for Group Data Sharing Using Cloud Data Storage
International Journal of Research, 2016Co-Authors: P. Ashok Kumar, Vulloji RajaAbstract:The capacity of preferentially sharing encrypted data with in contrast to clients by means of public cloud storage would quite ease safety depression, by means of likelihood data expose within the cloud. A Key experiment to design such encryption notion lies within the good-organized management encryption Keys. The preferred flexibility of allocating any group records with any group of clients by way of achieving weightage exclusive encryption Keys to be used for exclusive files. However, this involves the need of securely distributing to clients through a large quantity of Keys for both encryption and search, and people users have got to development to store the received Keys. The indirect want for comfortable communique, storage, and complexity obviously purpose the unreasonable procedure. In this paper, we pay attention to this useful problem, through suggesting the novel thought of Key Combination searchable encryption (KASE) and instantiating the inspiration through an actual KASE scheme, where a knowledge proprietor desires to share out a single Key to a consumer for distributing a massive number of records, and the person wants to reward a single trapdoor to the cloud for questioning the shared files.
Georg Goldenberg - One of the best experts on this subject based on the ideXlab platform.
-
A program for measuring timing and accuracy in a complex motor reaction task
Computer methods and programs in biomedicine, 1994Co-Authors: Mates J, Georg GoldenbergAbstract:A program was developed to explore a subject's accuracy and response timing in a reaction-time paradigm, which involves a multiple choice along with a complex response. The program can be run on an IBM-PC or compatible computers. The subject's task is: (1) to react to a stimulus (task) pattern by releasing a go-Key (release time); the pattern is displayed on a Keyboard as a Combination of up to five light-emitting diodes associated with five answer Keys; (2) then to press correctly the Key Combination indicated (response completion time). The Keys are located at positions corresponding to finger tips. The response is complete at the moment all Keys of the required Combination are held down simultaneously, the order in response completion is not important. Responses are classified according to possible errors: whenever a Key is pressed that does not belong to the required Combination or the full Key Combination is not held until a (preset) waiting time period, the response is classified as incorrect. Various task patterns representing the required response Combination of any subset of the five Keys can be designed. Both the left and the right hand can be tested separately. In this way, possible distortions in performance caused, for instance, by apraxia can be analyzed. Basic statistical characteristics of the release times and completion times for correct responses are computed from the data and stored. The program is written in MODULA-2, the output files are in the ASCII format, which enables further processing of the data by standard statistical packages.
Shady Issa - One of the best experts on this subject based on the ideXlab platform.
-
Extending hardware transactional memory capacity via rollback-only transactions and suspend/resume
Distributed Computing, 2019Co-Authors: Shady Issa, Alexander Matveev, Pascal Felber, Paolo RomanoAbstract:Transactional memory (TM) aims at simplifying concurrent programming via the familiar abstraction of atomic transactions. Recently, Intel and IBM have integrated hardware based TM (HTM) implementations in commodity processors, paving the way for the mainstream adoption of the TM paradigm. Yet, existing HTM implementations suffer from a crucial limitation, which hampers the adoption of HTM as a general technique for regulating concurrent access to shared memory: the inability to execute transactions whose working sets exceed the capacity of CPU caches. In this article we propose P8TM, a novel approach that mitigates this limitation on IBM’s POWER8 architecture by leveraging a Key Combination of hardware and software techniques to support different execution paths. P8TM also relies on self-tuning mechanisms aimed at dynamically switching between different execution modes to best adapt to the workload characteristics. In-depth evaluation with several benchmarks indicates that P8TM can achieve striking performance gains in workloads that stress the capacity limitations of HTM, while achieving performance on par with HTM even in unfavourable workloads.
-
DISC - Extending Hardware Transactional Memory Capacity via Rollback-Only Transactions and Suspend/Resume.
Distributed Computing, 2019Co-Authors: Shady Issa, Alexander Matveev, Pascal Felber, Paolo RomanoAbstract:Transactional memory (TM) aims at simplifying concurrent programming via the familiar abstraction of atomic transactions. Recently, Intel and IBM have integrated hardware based TM (HTM) implementations in commodity processors, paving the way for the mainstream adoption of the TM paradigm. Yet, existing HTM implementations suffer from a crucial limitation, which hampers the adoption of HTM as a general technique for regulating concurrent access to shared memory: the inability to execute transactions whose working sets exceed the capacity of CPU caches. In this article we propose P8TM, a novel approach that mitigates this limitation on IBM’s POWER8 architecture by leveraging a Key Combination of hardware and software techniques to support different execution paths. P8TM also relies on self-tuning mechanisms aimed at dynamically switching between different execution modes to best adapt to the workload characteristics. In-depth evaluation with several benchmarks indicates that P8TM can achieve striking performance gains in workloads that stress the capacity limitations of HTM, while achieving performance on par with HTM even in unfavourable workloads.
