Abstract:Abstract-In many of today's system-on-chip (SoC) designs, the cores are partitioned into multiple voltage and frequency islands (VFIs), and the global interconnect is implemented using a packetswitched network on chip (NoC). In such VFI-based designs, the benefits of 3-D integration in reducing the NoC power or delay are unclear, as a significant fraction of power is spent in link-level synchronization, and stacked designs may impose many synchronization boundaries. In this brief, we show the quantitative bene… Show more
“…However, most of the existing VFI methodologies for TSV-based 3D NoC ignores the performance-thermal tradeoffs (Seiculescu et al 2010;Rahmani et al 2013). For VFI-based system, a group of cores with similar communication and computation characteristics are clustered together.…”
Section: Performance and Thermal-efficient 3d Noc Incorporating Vfimentioning
Three-dimensional (3D) integration enables the design of high-performance and energy-efficient network on chip (NoC) architectures as communication backbones for manycore chips. To exploit the benefits of the vertical dimension of 3D integration, through-silicon-via (TSV) has been predominantly used in state-of-the-art manycore chip design. However, for TSV-based systems, high power density and the resultant thermal hotspot remain major concerns from the perspectives of chip functionality and overall reliability. The power consumption and thermal profiles of 3D NoCs can be improved by incorporating a Voltage-Frequency-Island (VFI)-based power management strategy. However, due to inherent thermal constraints of a TSV-based 3D system, we are unable to fully exploit the benefits offered by the power management methodology. In this context, emergence of monolithic 3D (M3D) integration has opened up new possibility of designing ultra-low-power and high-performance circuits and systems. The smaller dimensions of the inter-layer dielectric (ILD) and monolithic inter-tier vias (MIVs) offer high-density integration, flexibility of partitioning logic blocks across multiple tiers, and significant reduction of total wire-length. In this work, we present the first-ever study of the performance-thermal tradeoffs for energy efficient monolithic 3D manycore chips. In particular, we present a comparative performance evaluation of M3D NoCs with respect to their conventional TSV-based counterparts. We demonstrate that the proposed M3D-based NoC architecture incorporating VFI-based power management achieves a maximum of 29.4% lower energy-delay-product (EDP) compared to the TSV-based designs for a large set of benchmarks. We also demonstrate that the M3D-based NoC shows up to 29.1% lower maximum temperature than the TSV-based counterpart for these benchmarks.
“…However, most of the existing VFI methodologies for TSV-based 3D NoC ignores the performance-thermal tradeoffs (Seiculescu et al 2010;Rahmani et al 2013). For VFI-based system, a group of cores with similar communication and computation characteristics are clustered together.…”
Section: Performance and Thermal-efficient 3d Noc Incorporating Vfimentioning
Three-dimensional (3D) integration enables the design of high-performance and energy-efficient network on chip (NoC) architectures as communication backbones for manycore chips. To exploit the benefits of the vertical dimension of 3D integration, through-silicon-via (TSV) has been predominantly used in state-of-the-art manycore chip design. However, for TSV-based systems, high power density and the resultant thermal hotspot remain major concerns from the perspectives of chip functionality and overall reliability. The power consumption and thermal profiles of 3D NoCs can be improved by incorporating a Voltage-Frequency-Island (VFI)-based power management strategy. However, due to inherent thermal constraints of a TSV-based 3D system, we are unable to fully exploit the benefits offered by the power management methodology. In this context, emergence of monolithic 3D (M3D) integration has opened up new possibility of designing ultra-low-power and high-performance circuits and systems. The smaller dimensions of the inter-layer dielectric (ILD) and monolithic inter-tier vias (MIVs) offer high-density integration, flexibility of partitioning logic blocks across multiple tiers, and significant reduction of total wire-length. In this work, we present the first-ever study of the performance-thermal tradeoffs for energy efficient monolithic 3D manycore chips. In particular, we present a comparative performance evaluation of M3D NoCs with respect to their conventional TSV-based counterparts. We demonstrate that the proposed M3D-based NoC architecture incorporating VFI-based power management achieves a maximum of 29.4% lower energy-delay-product (EDP) compared to the TSV-based designs for a large set of benchmarks. We also demonstrate that the M3D-based NoC shows up to 29.1% lower maximum temperature than the TSV-based counterpart for these benchmarks.
“…First, for voltage and frequency islands NoC-based systems, network partitioning techniques were used to divide the whole systems into partitions that were implemented as separate islands [28,29]. The use of partitioning with voltage and frequency island NoC-based systems was evaluated in [30]. Second, for multicast 2D NoCs routing, network partitioning techniques were used to enhance the bandwidth efficiency and the overall performance of NoC-based systems in [31,32].…”
Networks-on-Chip (NoC) design is a trade-off between cost and performance. To realize the best trade-off between these factors, researchers have recently proposed using network partitioning techniques to customize the NoC architecture according to the application requirements. In this paper, the impact of using partitioning on different NoC metrics; namely, power, area, and delay, is analyzed. We present a system-level methodology to evaluate the performance of using partitioning-based architecture customization techniques with NoC. Our methodology is applied onto synthetic traffic as well as a number of real NoC benchmarks with different number of cores. Finally, we mathematically formulate evaluation factors that could be used as measures of the enhancements achieved by using partitioning.
“…Impacts of single and multiple VFIs on system performance was analyzed in [19]. VFI partitioning scheme was proposed in [20]. Huang et al [21] proposed task allocation and scheduling algorithm for energy optimization targeting MPSoCs.…”
Technology scaling dramatically increases transistor integration capacity, enabling more and more cores to be integrated into a single chip. Parameter variability, however, leads to performance asymmetry among the cores, degrading the energy efficiency of the system. Recently, voltage/frequency island (VFI) based designs are widely exploited on a multi-core platform for system energy optimization under variations. In this paper, a post-silicon energy optimization scheme is proposed targeting VFI-based 3-D multi-core SoCs. Design constraints on VFI, difference of communication energies between horizontal and vertical directions and unique thermal feature of the 3-D chip are totally considered. An energy efficient task mapping and scheduling algorithm is proposed, which seamlessly combines with dynamic voltage/frequency scaling to minimize the system energy under deadline and thermal constraints. Experimental results demonstrate that the effectiveness of the proposed scheme.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.