Three-dimensional (3-D) integration promises continuous system-level functional scaling beyond the traditional 2-D device-level geometric scaling. It allows stacking memory dies on top of a logic die using through-silicon vias (TSVs) to realize high bandwidth by deploying the vertical connections between functional blocks. In this paper, we present a design strategy using ESL virtual platform to explore 3-D memory architecture for a heterogeneous multi-core system and base on exploration results, we propose the reconfigurable stacking memory architecture for three-dimension IC. Based on the virtual platform, designers can rapidly obtain the 3-D stacking interface for better system performance and TSV utilization. A feasible stacking archite...
Abstract—Specialized hardware acceleration is an effective technique to mitigate the dark silicon pr...
none4siEnergy efficiency is the major optimization criterion for systems-on-chip (SoCs) for mobile d...
Memory bandwidth has become a major performance bottleneck as more and more cores are integrated ont...
Three-dimensional (3D) on-chip memory stacking has been proposed as a promising solution to the &apo...
The main aim of this thesis is to examine the advantages of 3D stacking applied to microprocessors a...
Recently, stereo matching processors have been adopted in real-time embedded systems such as intelli...
Three-Dimensional (3D) silicon integration is an emerging technology that vertically stacks multiple...
Abstract—This paper demonstrates a fully functional hard-ware and software design for a 3D stacked m...
To address the 'memory wall' challenge, on-chip memory stacking has been proposed as a pro...
Several recent works have demonstrated the benefits of through-silicon-via (TSV) based 3D integratio...
[[abstract]]To address the “memory wall” challenge, on-chip memory stacking has been proposed as a p...
Convergence of communication, consumer applications and computing within mobile systems pushes memor...
none43D integration based on TSV (through silicon via) technology enables stacking of multiple memor...
A novel modular, cost e ffective 3D multi-processor architecture is presented. Auto-configurable and...
Historically, processor performance has increased at a much faster rate than that of main memory and...
Abstract—Specialized hardware acceleration is an effective technique to mitigate the dark silicon pr...
none4siEnergy efficiency is the major optimization criterion for systems-on-chip (SoCs) for mobile d...
Memory bandwidth has become a major performance bottleneck as more and more cores are integrated ont...
Three-dimensional (3D) on-chip memory stacking has been proposed as a promising solution to the &apo...
The main aim of this thesis is to examine the advantages of 3D stacking applied to microprocessors a...
Recently, stereo matching processors have been adopted in real-time embedded systems such as intelli...
Three-Dimensional (3D) silicon integration is an emerging technology that vertically stacks multiple...
Abstract—This paper demonstrates a fully functional hard-ware and software design for a 3D stacked m...
To address the 'memory wall' challenge, on-chip memory stacking has been proposed as a pro...
Several recent works have demonstrated the benefits of through-silicon-via (TSV) based 3D integratio...
[[abstract]]To address the “memory wall” challenge, on-chip memory stacking has been proposed as a p...
Convergence of communication, consumer applications and computing within mobile systems pushes memor...
none43D integration based on TSV (through silicon via) technology enables stacking of multiple memor...
A novel modular, cost e ffective 3D multi-processor architecture is presented. Auto-configurable and...
Historically, processor performance has increased at a much faster rate than that of main memory and...
Abstract—Specialized hardware acceleration is an effective technique to mitigate the dark silicon pr...
none4siEnergy efficiency is the major optimization criterion for systems-on-chip (SoCs) for mobile d...
Memory bandwidth has become a major performance bottleneck as more and more cores are integrated ont...