Design and Analysis of 3D-MAPS (3D Massively Parallel Processor with Stacked Memory)
Citations Over TimeTop 10% of 2013 papers
Abstract
This paper describes the architecture, design, analysis, and simulation and measurement results of the 3D-MAPS (3D massively parallel processor with stacked memory) chip built with a 1.5 V, 130 nm process technology and a two-tier 3D stacking technology using 1.2 $\micro\hbox{m}$ -diameter, 6 $\micro \hbox{m}$ -height through-silicon vias (TSVs) and $3.4\nbsp\micro\hbox{m}$ -diameter face-to-face bond pads. 3D-MAPS consists of a core tier containing 64 cores and a memory tier containing 64 memory blocks. Each core communicates with its dedicated 4KB SRAM block using face-to-face bond pads, which provide negligible data transfer delay between the core and the memory tiers. The maximum operating frequency is 277 MHz and the maximum memory bandwidth is 70.9 GB/s at 277 MHz. The peak measured memory bandwidth usage is 63.8 GB/s and the peak measured power is approximately 4 W based on eight parallel benchmarks.
Related Papers
- → Interprocedural parallelization analysis in SUIF(2005)66 cited
- → Parallelization of a dynamic unstructured algorithm using three leading programming paradigms(2000)27 cited
- → Automatic parallelization for non-cache coherent multiprocessors(1997)4 cited
- Multi-core Parallel Computational Model Based on Horizontal Locality(2012)
- → Speculative parallelization on GPGPUs(2012)