Adaptive Channel Buffers in On-Chip Interconnection Networks - A Power and Performance Analysis
نویسندگان
چکیده
On-chip interconnection networks (OCINs) have emerged as a modular and scalable solution for wire delay constraints in deep submicron VLSI design. OCIN research has shown that the design of buffers in the router influences the energy consumption, area overhead, and overall performance of the network. In this paper, we propose a low-power low-area OCIN architecture by reducing the number of buffers within the router. To minimize the performance degradation due to the reduced buffer size, we use the already existing repeaters along the inter-router channels to double as buffers along the channel when required. At low network loads, the proposed adaptive channel buffers function as conventional repeaters, propagating the signals. At high network loads, the adaptive channel buffers function as storage elements in addition to the router buffers. The router buffers can be assigned either statically or dynamically to the incoming packets. Static allocation reserves equal buffer space partitioned among all of the incoming packets, whereas dynamic allocation reserves buffer space on a per-flit basis, enabling higher buffer occupancy. We evaluate the proposed adaptive channel buffers with both static and dynamic buffer allocation policies in the 90-nm technology node, using 8 8 mesh and folded torus network topologies. Simulation results using the SPLASH-2 suite benchmarks and synthetic traffic patterns show that, by reducing the router buffer size, our proposed architecture achieves nearly 40 percent savings in router buffer power, 30 percent savings in overall network power, and 41 percent savings in area, with only a marginal 1-5 percent drop in throughput under dynamic buffer allocation and about 10-20 percent drop in throughput for statically assigned buffers.
منابع مشابه
Networks on Chip, router architectures and performance challenges
With the continuous technology scaling, System On Chips (SoCs) have evolved considerably and can integrate an important number of Intellectual Property (IP) cores in the same chip. However, global interconnects are become the main performance limitation of SoCs. The Network on Chip (NoC) paradigm has emerged as an efficient interconnection structure addressing the global wire delay problem. Thi...
متن کاملCost-aware Topology Customization of Mesh-based Networks-on-Chip
Nowadays, the growing demand for supporting multiple applications causes to use multiple IPs onto the chip. In fact, finding truly scalable communication architecture will be a critical concern. To this end, the Networks-on-Chip (NoC) paradigm has emerged as a promising solution to on-chip communication challenges within the silicon-based electronics. Many of today’s NoC architectures are based...
متن کاملDesign of a performance enhanced and power reduced dual-crossbar Network-on-Chip (NoC) architecture
The input buffers of the current packet-switched Network-on-Chip (NoC) architectures consume a significant portion of the total power of the interconnection network. Reducing the size of input buffers would result in degraded performance, while eliminating all buffers would result in increased power at high network load. In this article, we propose DXbar: an innovative dual-crossbar design. By ...
متن کاملTwo-Level FIFO Buffer Design for Routers in On-Chip Interconnection Networks
The on-chip interconnection network (OCIN) is an integrated solution for system-on-chip (SoC) designs. The buffer architecture and size, however, dominate the performance of OCINs and affect the design of routers. This work analyzes different buffer architectures and uses a data-link two-level FIFO (first-in first-out) buffer architecture to implement high-performance routers. The concepts of s...
متن کاملPerformance Analysis of a New Neural Network for Routing in Mesh Interconnection Networks
Routing is one of the basic parts of a message passing multiprocessor system. The routing procedure has a great impact on the efficiency of a system. Neural algorithms that are currently in use for computer networks require a large number of neurons. If a specific topology of a multiprocessor network is considered, the number of neurons can be reduced. In this paper a new recurrent neural ne...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- IEEE Trans. Computers
دوره 57 شماره
صفحات -
تاریخ انتشار 2008