Subhasish Mitra

Robust system design with built-in soft-error resilience

Transient errors caused by terrestrial radiation pose a major barrier to robust system design. A systems susceptibility to such errors increases in advanced technologies, making the incorporation of effective protection mechanisms into chip designs essential. A new design paradigm reuses design-for-testability and debug resources to eliminate such errors.

Carbon nanotube computer

The miniaturization of electronic devices has been the principal driving force behind the semiconductor industry, and has brought about major improvements in computational power and energy efficiency. Although advances with silicon-based electronics continue to be made, alternative technologies are being explored. Digital circuits based on transistors fabricated from carbon nanotubes (CNTs) have the potential to outperform silicon by improving the energy–delay product, a metric of energy efficiency, by more than an order of magnitude. Hence, CNTs are an exciting complement to existing semiconductor technologies. Owing to substantial fundamental imperfections inherent in CNTs, however, only very basic circuit blocks have been demonstrated. Here we show how these imperfections can be overcome, and demonstrate the first computer built entirely using CNT-based transistors. The CNT computer runs an operating system that is capable of multitasking: as a demonstration, we perform counting and integer-sorting simultaneously. In addition, we implement 20 different instructions from the commercial MIPS instruction set to demonstrate the generality of our CNT computer. This experimental demonstration is the most complex carbon-based electronic system yet realized. It is a considerable advance because CNTs are prominent among a variety of emerging technologies that are being considered for the next generation of highly energy-efficient electronic systems.

Circuit Failure Prediction and Its Application to Transistor Aging

Circuit failure prediction predicts the occurrence of a circuit failure before errors actually appear in system data and states. This is in contrast to classical error detection where a failure is detected after errors appear in system data and states. Circuit failure prediction is performed during system operation by analyzing the data collected by sensors inserted at various locations inside a chip. We demonstrate this concept of circuit failure prediction for a dominant PMOS aging mechanism induced by negative bias temperature instability (NBTI). NBTI-induced PMOS aging slows down PMOS transistors over time. As a result, the speed of a chip can significantly degrade over time and can result in delay faults. The traditional practice is to incorporate worst-case speed margins to prevent delay faults during system operation due to NBTI aging. A new sensor design integrated inside a flip-flop enables efficient circuit failure prediction at a low cost. Simulation results using 90nm and 65nm technologies demonstrate that this technique can significantly improve system performance by enabling close to best-case design instead of traditional worst-case design.

The case for RAMClouds: scalable high-performance storage entirely in DRAM

Disk-oriented approaches to online storage are becoming increasingly problematic: they do not scale gracefully to meet the needs of large-scale Web applications, and improvements in disk capacity have far outstripped improvements in access latency and bandwidth. This paper argues for a new approach to datacenter storage called RAMCloud, where information is kept entirely in DRAM and large-scale systems are created by aggregating the main memories of thousands of commodity servers. We believe that RAMClouds can provide durable and available storage with 100-1000x the throughput of disk-based systems and 100-1000x lower access latency. The combination of low latency and large scale will enable a new breed of dataintensive applications.

X-compact: an efficient response compaction technique for test cost reduction

We present a technique for compacting test response data using combinational logic circuits. Our compaction technique enables up to an exponential reduction in the number of pins required to collect test response from a chip. The combinational circuits require negligible area, do not add any extra delay during normal operation, guarantee detection of defective chips even in the presence of sources of unknown logic values (often referred to as Xs) and preserve diagnosis capabilities for all practical scenarios. The technique has minimum impact on current design and test flows, and can be used to reduce test time, test data volume, test-I/O pins and tester channels, and also to improve test quality.

X-compact: an efficient response compaction technique

X-Compact is an X-tolerant test response compaction technique. It enables up to exponential reduction in the test response data volume and the number of pins required to collect test response from a chip. The compaction hardware requires negligible area, does not add any extra delay during normal operation, guarantees detection of defective chips even in the presence of unknown logic values (often referred to as Xs), and preserves diagnosis capabilities for most practical scenarios. The technique has minimum impact on current design and test flows, and can be used to reduce test time, test-data volume, test-input/output pins and tester channels, and also to improve test quality.

ERSA: error resilient system architecture for probabilistic applications

There is a growing concern about the increasing vulnerability of future computing systems to errors in the underlying hardware. Traditional redundancy techniques are expensive for designing energy-efficient systems that are resilient to high error rates. We present Error Resilient System Architecture (ERSA), a low-cost robust system architecture for emerging killer probabilistic applications such as Recognition, Mining and Synthesis (RMS) applications. While resilience of such applications to errors in low-order bits of data is well-known, execution of such applications on error-prone hardware significantly degrades output quality (due to high-order bit errors and crashes). ERSA achieves high error resilience to high-order bit errors and control errors (in addition to low-order bit errors) using a judicious combination of 3 key ideas: (1) asymmetric reliability in many-core architectures, (2) error-resilient algorithms at the core of probabilistic applications, and (3) intelligent software optimizations. Error injection experiments on a multi-core ERSA hardware prototype demonstrate that, even at very high error rates of 20,000 errors/second/core or 2×10−4 error/cycle/core (with errors injected in architecturally-visible registers), ERSA maintains 90% or better accuracy of output results, together with minimal impact on execution time, for probabilistic applications such as K-Means clustering, LDPC decoding and Bayesian networks. Moreover, we demonstrate the effectiveness of ERSA in tolerating high rates of static memory errors that are characteristic of emerging challenges such as Vccmin problems and erratic bit errors. Using the concept of configurable reliability, ERSA platforms may also be adapted for general-purpose applications that are less resilient to errors (but at higher costs).

Which concurrent error detection scheme to choose

Concurrent error detection (CED) techniques (based on hardware duplication, parity codes, etc.) are widely used to enhance system dependability. All CED techniques introduce some form of redundancy. Redundant systems we subject to common-mode failures (CMFs). While most of the studies of CED techniques focus on area overhead, few analyze the CMF vulnerability of these techniques. In this paper, we present simulation results to quantitatively compare various CED schemes based on their area overhead and the protection (data integrity) they provide against multiple failures and CMFs. Our results indicate that, for the simulated combinational logic circuits, although diverse duplex systems (with two different implementations of the same logic function) sometimes have marginally higher area overhead, they provide significant protection against multiple failures and CMFs compared to other CED techniques like parity prediction.

Sequential Element Design With Built-In Soft Error Resilience

This paper presents a built-in soft error resilience (BISER) technique for correcting radiation-induced soft errors in latches and flip-flops. The presented error-correcting latch and flip-flop designs are power efficient, introduce minimal speed penalty, and employ reuse of on-chip scan design-for-testability and design-for-debug resources to minimize area overheads. Circuit simulations using a sub-90-nm technology show that the presented designs achieve more than a 20-fold reduction in cell-level soft error rate (SER). Fault injection experiments conducted on a microprocessor model further demonstrate that chip-level SER improvement is tunable by selective placement of the presented error-correcting designs. When coupled with error correction code to protect in-pipeline memories, the BISER flip-flop design improves chip-level SER by 10 times over an unprotected pipeline with the flip-flops contributing an extra 7-10.5% in power. When only soft errors in flips-flops are considered, the BISER technique improves chip-level SER by 10 times with an increased power of 10.3%. The error correction mechanism is configurable (i.e., can be turned on or off) which enables the use of the presented techniques for designs that can target multiple applications with a wide range of reliability requirements

Radiation-Induced Soft Error Rates of Advanced CMOS Bulk Devices

This work provides a comprehensive summary of radiation-induced soft error rate (SER) scaling trends of key CMOS bulk devices. Specifically we analyzed the SER per bit scaling trends of SRAMs, sequentials and static combinational logic. Our results show that for SRAMs the single-bit soft error rate continues to decrease whereas the multi-bit SER increases dramatically. While the total soft error rate of logic devices (sequentials and static combinational devices) has not changed significantly, a substantial increase in the susceptibility to alpha particles is observed. Finally, a novel methodology to extract one-dimensional cross sections of the collected charge distributions from measured multi-bit statistics is introduced