Memory partitioning is an eective approach to memory energy optimization in embedded systems. Spatial local-ity of the memory address prole is the key property that partitioning exploits to determine an eÆcient multi-bank memory architecture. This paper presents an approach, called address clustering, for increasing the locality of a given memory access prole, and thus improving the eÆciency of partitioning. Results obtained on several embedded applications running on an ARM7 core show average energy reductions of 25% (maximum 57%) w.r.t. a partitioned memory architecture synthesized without resorting to address clustering.
Distributed local memories, or scratchpads, have been shown to e#ectively reduce cost and power cons...
International audienceIn order to minimize the energy consumed by the main memory in embedded system...
One of the previously-proposed techniques for reducing memory energy consumption is memory banking. ...
Part 4: Memory System DesignInternational audienceIn the last decades, the increasing amount of reso...
International audiencePower-efficient architectures have become the most important feature required ...
Clustering processors together at a level of the memory hierarchy in shared address space multiproce...
Increasing the locality of a memory access profile is an interesting optimization problem, whose sol...
Main memory in clusters may dominate total system power. The resulting energy consumption increases ...
Power constraints led to the end of exponential growth in single–processor performance, which charac...
Main memory in clusters may dominate total system power. The resulting energy consumption increases ...
Power has become one of the primary design constraints in modern embedded microprocessors. Many embe...
Memory-processor integration offers new opportunities for reducing the energy of a system. In the ca...
Abstract — In many computer systems, a large portion of the execution time and energy consumption is...
Application-Specific Block-Enabled (ASBE) SRAMs represent a viable solution for reducing energy cons...
Memory-processor integration offers new opportunities for reducing the energy of a system. In the ca...
Distributed local memories, or scratchpads, have been shown to e#ectively reduce cost and power cons...
International audienceIn order to minimize the energy consumed by the main memory in embedded system...
One of the previously-proposed techniques for reducing memory energy consumption is memory banking. ...
Part 4: Memory System DesignInternational audienceIn the last decades, the increasing amount of reso...
International audiencePower-efficient architectures have become the most important feature required ...
Clustering processors together at a level of the memory hierarchy in shared address space multiproce...
Increasing the locality of a memory access profile is an interesting optimization problem, whose sol...
Main memory in clusters may dominate total system power. The resulting energy consumption increases ...
Power constraints led to the end of exponential growth in single–processor performance, which charac...
Main memory in clusters may dominate total system power. The resulting energy consumption increases ...
Power has become one of the primary design constraints in modern embedded microprocessors. Many embe...
Memory-processor integration offers new opportunities for reducing the energy of a system. In the ca...
Abstract — In many computer systems, a large portion of the execution time and energy consumption is...
Application-Specific Block-Enabled (ASBE) SRAMs represent a viable solution for reducing energy cons...
Memory-processor integration offers new opportunities for reducing the energy of a system. In the ca...
Distributed local memories, or scratchpads, have been shown to e#ectively reduce cost and power cons...
International audienceIn order to minimize the energy consumed by the main memory in embedded system...
One of the previously-proposed techniques for reducing memory energy consumption is memory banking. ...