AS DEVICES SHRINK toward the nanometer scale, on-chip interconnects are becoming a critical bottleneck in meeting performance and power consumption requirements of chip designs. Industry and academia recognize the interconnect problem as an important design constraint, and, consequently, researchers have proposed packet-based on-chip communication networks, known as networks on chips (NoCs), to address the challenges of increasing interconnect complexity. [1][2][3][4][5] NoC designs promise to deliver fast, reliable, energy-efficient communication between on-chip components. Because most application traffic is bursty in nature, packet-switched networks are suitable for NoCs. 2,4,5 Another effect of shrinking feature size is that power supply voltage and device V t decrease, and wires become unreliable because they are increasingly susceptible to noise sources such as crosstalk, coupling noise, soft errors, and process variation.6 Using aggressive voltage-scaling techniques to reduce a system's power consumption further increases the system's susceptibility to various noise sources. Providing resilience from such transient delay and logic errors is critical for proper system operation.Error detection or correction mechanisms can protect the system from transient errors that occur in the communication subsystem. These schemes can use end-to-end flow control (network level) or switch-to-switch flow control (link level). In a simple retransmission scheme, the sender adds error detection codes (parity or cyclic redundancy check codes) to the original data, and the receiver checks the received data for correctness. If it detects an error, it requests the sender to retransmit the data. Alternatively, the sender can add error-correcting codes (such as Hamming codes) to the data, and the receiver can correct errors. Hybrid schemes with combined retransmission and error correction capabilities are also possible. Because the error detection/correction capability, area-power overhead, and performance of the various schemes differ, the choice of error recovery scheme for an application requires exploring multiple power-performance-reliability trade-offs.In this article, we relate these three major design constraints to characterize efficient error recovery mechanisms for the NoC design environment. We explore error control mechanisms at the data link and network layers and present the schemes' architectural details. We investigate the energy efficiency, error protection efficiency, and performance impact of various error recovery mechanisms.Our objective is twofold: First, we want to identify the major power overhead issues of various error recovery schemes, so that designers can create efficient mechanisms to address them. Second, we want to provide the Analysis of Error Recovery Schemes for Networks on ChipsEditor's note: Error resiliency is a must for NoCs, but it must not incur undue costsparticularly in terms of energy consumption. Here, the authors present an authoritative discussion of the trade-offs involved in va...

No abstract

The anticipated explosive growth of pervasive and mobile computing devices that are typically constrained by energy has brought hardware and software techniques for energy conservation into the spotlight. While there have been several studies and proposals for energy conservation for CPUs and peripherals, energy optimization techniques for selective operating mode control of DRAMs have not been fully explored. It has been shown that for some systems as much as 90% of overall system energy (excluding I/O) is consumed by the DRAM modules; thus they serve as a good candidate for energy optimizations. Further, DRAM technology has also matured to provide several low energy operating modes (power modes), making it an opportunistic moment to conduct studies exploring the potential benefits of mode control techniques. This paper conducts an in-depth investigation of software and hardware techniques to take advantage of the DRAM mode control capabilities at a module granularity for energy savings. Using a memory system architecture capturing five different energy modes and corresponding resynchronization times, this paper presents several novel compilation techniques to both cluster the data across memory banks as well as to detect module idleness and perform energy mode transitions. In addition, hardware-assisted approaches (called self-monitoring) based on predictions of module inter-access times are proposed. These techniques are extensively evaluated using a set of a dozen benchmarks. It is shown that we get an average of 61% savings in DRAM energy using compiler-directed mode control. One of the self-monitored approaches gives as much as 89% savings (72% on the average), coming as close as 8.8% to the optimal energy savings that one can expect with DRAM module mode control. The optimization techniques are demonstrated to be invaluable for energy savings as memory technologies continue to evolve.

A new approximation heuristic for finding a rectilinear Steiner tree of a set of nodes is presented. It starts with a rectilinear minimum spanning tree of the nodes and repeatedly connects a node to the nearest point on the rectangular layout of an edge, removing the longest edge of the loop thus formed. A simple implementation of the heuristic using conventional data structures is compared with previously existing algorithms. The performance (i.e., quality of the route produced) of our algorithm is as good as the hest reported algorithm, while the running time is an order of magnitude better than that of this hest algorithm. It is also shown that the asymptotic time complexity for the algorithm can he improved to O(n log n), where n is the number of points in the set.

Interconnects are becoming an increasing problem from both performance and power consumption perspective in future technology nodes. The introduction of 3D chip architectures, with their intrinsic capability of reducing wire length, is one of the promising solutions to mitigate the interconnect problem. While interconnect power consumption reduces due to the adoption of 3D designs, the stacking of multiple active layers leads to higher power densities. Thus, high peak temperatures are of major concern in 3D designs. Consequently, we present a thermal-aware floorplanner for 3D architectures. In contrast to most prior work, our floorplanner considers the interconnect power consumption in exploring a thermal-aware floorplan. Our results show that excluding interconnect power can result in peak temperatures being underestimated by as much as 15 o C in 90nm technology. Finally, we demonstrate that our floorplanner is effective in lowering peak temperatures using a microprocessor design and four MCNC designs as benchmarks.