Traditional software transactional memory designs are targeted towards performance and therefore little is known about their impact on energy consumption. We provide, in this paper, a comprehensive energy analysis of a standard STM design and propose novel scratchpad-based energy-aware STM design strategies. Experimental results collected through a state-of-the-art MPSoC simulation infrastructure show that our approach can achieve an energy improvement of up to 36% with regard to the base STM for applications characterized by short-lived transactions and relatively high abort rate. Copyright 2009 ACM.ACM SIGDA,Sociedade Brasileira de Computacao, SBC,IEEE Circuits and Systems Society, CAS,IEEE,ifipBanakar, R., Steinke, S., Lee, B.-S., Balakr...
Power has emerged as a first-order design constraint in modern processors and has energized microarc...
In VLSI systems-on-chips (SoC), leakage is expected to override 50% of the total power consumption, ...
Due to the advent of multi-core processors and the consequent need for better concurrent programming...
Abstract—The well-known drawbacks imposed by lock-based synchronization have forced researchers to d...
Transactional memory (TM) is a new synchronization mechanism devised to simplify parallel programmin...
Energy efficiency is becoming a pressing issue, especially in large data centers where it entails, a...
Hardware vendors make an important effort creating low-power CPUs that keep battery duration and dur...
[Abstract] On-chip power consumption is one of the fundamental challenges of current technology scal...
Transactional Memory (TM) is an emerging programming paradigm that drastically simplifies the develo...
One important way in which multiprocessors differ from uniprocessors is in the need to provide progr...
We investigate how transactional memory can be adapted for embedded systems. We consider energy cons...
Transactional memory (TM) is emerging as an attractive synchronization mechanism for concurrent comp...
Orientador: Rodolfo Jardim de AzevedoDissertação (mestrado) - Universidade Estadual de Campinas, Ins...
The design of future high-performance embedded systems is hampered by two problems: First, the requi...
Abstract—Transactional memory (TM) is emerging as an attractive synchronization mechanism for concur...
Power has emerged as a first-order design constraint in modern processors and has energized microarc...
In VLSI systems-on-chips (SoC), leakage is expected to override 50% of the total power consumption, ...
Due to the advent of multi-core processors and the consequent need for better concurrent programming...
Abstract—The well-known drawbacks imposed by lock-based synchronization have forced researchers to d...
Transactional memory (TM) is a new synchronization mechanism devised to simplify parallel programmin...
Energy efficiency is becoming a pressing issue, especially in large data centers where it entails, a...
Hardware vendors make an important effort creating low-power CPUs that keep battery duration and dur...
[Abstract] On-chip power consumption is one of the fundamental challenges of current technology scal...
Transactional Memory (TM) is an emerging programming paradigm that drastically simplifies the develo...
One important way in which multiprocessors differ from uniprocessors is in the need to provide progr...
We investigate how transactional memory can be adapted for embedded systems. We consider energy cons...
Transactional memory (TM) is emerging as an attractive synchronization mechanism for concurrent comp...
Orientador: Rodolfo Jardim de AzevedoDissertação (mestrado) - Universidade Estadual de Campinas, Ins...
The design of future high-performance embedded systems is hampered by two problems: First, the requi...
Abstract—Transactional memory (TM) is emerging as an attractive synchronization mechanism for concur...
Power has emerged as a first-order design constraint in modern processors and has energized microarc...
In VLSI systems-on-chips (SoC), leakage is expected to override 50% of the total power consumption, ...
Due to the advent of multi-core processors and the consequent need for better concurrent programming...