Chris Wilkerson

Runahead execution: an alternative to very large instruction windows for out-of-order processors

Todays high performance processors tolerate long latency operations by means of out-of-order execution. However, as latencies increase, the size of the instruction window must increase even faster if we are to continue to tolerate these latencies. We have already reached the point where the size of an instruction window that can handle these latencies is prohibitively large in terms of both design complexity and power consumption. And, the problem is getting worse. This paper proposes runahead execution as an effective way to increase memory latency tolerance in an out-of-order processor without requiring an unreasonably large instruction window. Runahead execution unblocks the instruction window blocked by long latency operations allowing the processor to execute far ahead in the program path. This results in data being prefetched into caches long before it is needed. On a machine model based on the Intel/spl reg/ Pentium/spl reg/ processor, having a 128-entry instruction window, adding runahead execution improves the IPC (instructions per cycle) by 22% across a wide range of memory intensive applications. Also, for the same machine model, runahead execution combined with a 128-entry window performs within 1% of a machine with no runahead execution and a 384-entry instruction window.

Flipping bits in memory without accessing them: an experimental study of DRAM disturbance errors

Memory isolation is a key property of a reliable and secure computing system-an access to one memory address should not have unintended side effects on data stored in other addresses. However, as DRAM process technology scales down to smaller dimensions, it becomes more difficult to prevent DRAM cells from electrically interacting with each other. In this paper, we expose the vulnerability of commodity DRAM chips to disturbance errors. By reading from the same address in DRAM, we show that it is possible to corrupt data in nearby addresses. More specifically, activating the same row in DRAM corrupts data in nearby rows. We demonstrate this phenomenon on Intel and AMD systems using a malicious program that generates many DRAM accesses. We induce errors in most DRAM modules (110 out of 129) from three major DRAM manufacturers. From this we conclude that many deployed systems are likely to be at risk. We identify the root cause of disturbance errors as the repeated toggling of a DRAM rows wordline, which stresses inter-cell coupling effects that accelerate charge leakage from nearby rows. We provide an extensive characterization study of disturbance errors and their behavior using an FPGA-based testing platform. Among our key findings, we show that (i) it takes as few as 139K accesses to induce an error and (ii) up to one in every 1.7K cells is susceptible to errors. After examining various potential ways of addressing the problem, we propose a low-overhead solution to prevent the errors.

A 45 nm Resilient Microprocessor Core for Dynamic Variation Tolerance

A 45 nm microprocessor core integrates resilient error-detection and recovery circuits to mitigate the clock frequency (FCLK) guardbands for dynamic parameter variations to improve throughput and energy efficiency. The core supports two distinct error-detection designs, allowing a direct comparison of the relative trade-offs. The first design embeds error-detection sequential (EDS) circuits in critical paths to detect late timing transitions. In addition to reducing the Fclk guardbands for dynamic variations, the embedded EDS design can exploit path-activation rates to operate the microprocessor faster than infrequently-activated critical paths. The second error-detection design offers a less-intrusive approach for dynamic timing-error detection by placing a tunable replica circuit (TRC) per pipeline stage to monitor worst-case delays. Although the TRCs require a delay guardband to ensure the TRC delay is always slower than critical-path delays, the TRC design captures most of the benefits from the embedded EDS design with less implementation overhead. Furthermore, while core min-delay constraints limit the potential benefits of the embedded EDS design, a salient advantage of the TRC design is the ability to detect a wider range of dynamic delay variation, as demonstrated through low supply voltage (VCC) measurements. Both error-detection designs interface with error-recovery techniques, enabling the detection and correction of timing errors from fast-changing variations such as high-frequency VCC droops. The microprocessor core also supports two separate error-recovery techniques to guarantee correct execution even if dynamic variations persist. The first technique requires clock control to replay errant instructions at 1/2FCLK. In comparison, the second technique is a new multiple-issue instruction replay design that corrects errant instructions with a lower performance penalty and without requiring clock control. Silicon measurements demonstrate that resilient circuits enable a 41% throughput gain at equal energy or a 22% energy reduction at equal throughput, as compared to a conventional design when executing a benchmark program with a 10% VCC droop. In addition, the microprocessor includes a new adaptive clock control circuit that interfaces with the resilient circuits and a phase-locked loop (PLL) to track recovery cycles and adapt to persistent errors by dynamically changing Fclk f°Γ maximum efficiency.

Reducing cache power with low-cost, multi-bit error-correcting codes

Technology advancements have enabled the integration of large on-die embedded DRAM (eDRAM) caches. eDRAM is significantly denser than traditional SRAMs, but must be periodically refreshed to retain data. Like SRAM, eDRAM is susceptible to device variations, which play a role in determining refresh time for eDRAM cells. Refresh power potentially represents a large fraction of overall system power, particularly during low-power states when the CPU is idle. Future designs need to reduce cache power without incurring the high cost of flushing cache data when entering low-power states. In this paper, we show the significant impact of variations on refresh time and cache power consumption for large eDRAM caches. We propose Hi-ECC, a technique that incorporates multi-bit error-correcting codes to significantly reduce refresh rate. Multi-bit error-correcting codes usually have a complex decoder design and high storage cost. Hi-ECC avoids the decoder complexity by using strong ECC codes to identify and disable sections of the cache with multi-bit failures, while providing efficient single-bit error correction for the common case. Hi-ECC includes additional optimizations that allow us to amortize the storage cost of the code over large data words, providing the benefit of multi-bit correction at same storage cost as a single-bit error-correcting (SECDED) code (2% overhead). Our proposal achieves a 93% reduction in refresh power vs. a baseline eDRAM cache without error correcting capability, and a 66% reduction in refresh power vs. a system using SECDED codes.

Scheduling threads for constructive cache sharing on CMPs

In chip multiprocessors (CMPs), limiting the number of offchip cache misses is crucial for good performance. Many multithreaded programs provide opportunities for constructive cache sharing, in which concurrently scheduled threads share a largely overlapping working set. In this paper, we compare the performance of two state-of-the-art schedulers proposed for fine-grained multithreaded programs: Parallel Depth First (PDF), which is specifically designed for constructive cache sharing, and Work Stealing (WS), which is a more traditional design. Our experimental results indicate that PDF scheduling yields a 1.3--1.6X performance improvement relative to WS for several fine-grain parallel benchmarks on projected future CMP configurations; we also report several issues that may limit the advantage of PDF in certain applications. These results also indicate that PDF more effectively utilizes off-chip bandwidth, making it possible to trade-off on-chip cache for a larger number of cores. Moreover, we find that task granularity plays a key role in cache performance. Therefore, we present an automatic approach for selecting effective grain sizes, based on a new working set profiling algorithm that is an order of magnitude faster than previous approaches. This is the first paper demonstrating the effectiveness of PDF on real benchmarks, providing a direct comparison between PDF and WS, revealing the limiting factors for PDF in practice, and presenting an approach for overcoming these factors.

An experimental study of data retention behavior in modern DRAM devices: implications for retention time profiling mechanisms

DRAM cells store data in the form of charge on a capacitor. This charge leaks off over time, eventually causing data to be lost. To prevent this data loss from occurring, DRAM cells must be periodically refreshed. Unfortunately, DRAM refresh operations waste energy and also degrade system performance by interfering with memory requests. These problems are expected to worsen as DRAM density increases. The amount of time that a DRAM cell can safely retain data without being refreshed is called the cells retention time. In current systems, all DRAM cells are refreshed at the rate required to guarantee the integrity of the cell with the shortest retention time, resulting in unnecessary refreshes for cells with longer retention times. Prior work has proposed to reduce unnecessary refreshes by exploiting differences in retention time among DRAM cells; however, such mechanisms require knowledge of each cells retention time. In this paper, we present a comprehensive quantitative study of retention behavior in modern DRAMs. Using a temperature-controlled FPGA-based testing platform, we collect retention time information from 248 commodity DDR3 DRAM chips from five major DRAM vendors. We observe two significant phenomena: data pattern dependence, where the retention time of each DRAM cell is significantly affected by the data stored in other DRAM cells, and variable retention time, where the retention time of some DRAM cells changes unpredictably over time. We discuss possible physical explanations for these phenomena, how their magnitude may be affected by DRAM technology scaling, and their ramifications for DRAM retention time profiling mechanisms.

Improving cache lifetime reliability at ultra-low voltages

Voltage scaling is one of the most effective mechanisms to reduce microprocessor power consumption. However, the increased severity of manufacturing-induced parameter variations at lower voltages limits voltage scaling to a minimum voltage, Vccmin, below which a processor cannot operate reliably. Memory cell failures in large memory structures (e.g., caches) typically determine the Vccmin for the whole processor. Memory failures can be persistent (i.e., failures at time zero which cause yield loss) or non-persistent (e.g., soft errors or erratic bit failures). Both types of failures increase as supply voltage decreases and both need to be addressed to achieve reliable operation at low voltages. In this paper, we propose a novel adaptive technique to improve cache lifetime reliability and enable low voltage operation. This technique, multi-bit segmented ECC (MS-ECC) addresses both persistent and non-persistent failures. Like previous work on mitigating persistent failures, MS-ECC trades off cache capacity for lower voltages. However, unlike previous schemes, MS-ECC does not rely on testing to identify and isolate defective bits, and therefore enables error tolerance for non-persistent failures like erratic bits and soft errors at low voltages. Furthermore, MS-ECCs design can allow the operating system to adaptively change the cache size and ECC capability to adjust to system operating conditions. Compared to current designs with single-bit correction, the most aggressive implementation for MS-ECC enables a 30% reduction in supply voltage, reducing power by 71% and energy per instruction by 42%.

Circuit techniques for dynamic variation tolerance

Three circuit techniques for dynamic variation tolerance are presented: (i) Sensors with adaptive voltage and frequency circuits, (ii) Tunable replica circuits for timing-error prediction with error recovery, and (iii) Embedded error-detection sequential circuits with error recovery. These circuits mitigate the clock frequency guardbands for dynamic variations, thus improving microprocessor performance and energy-efficiency. These circuits are described with a focus on the different trade-offs in guardband reduction and design overhead. Opportunities for CAD to further enhance microprocessor performance and energy efficiency are offered.

Hierarchical scheduling windows

Large scheduling windows are an effective mechanism for increasing microprocessor performance through the extraction of instruction level parallelism. Current techniques do not scale effectively for very large windows, leading to slow wakeup and select logic as well as large complicated bypass networks. This paper introduces a new instruction scheduler implementation, referred to as Hierarchical Scheduling Windows or HSW, which exploits latency tolerant instructions in order to reduce implementation complexity. HSW yields a very large instruction window that tolerates wakeup, select, and bypass latency, while extracting significant far flung ILP. Results: It is shown that HSW loses <0.5% performance per additional cycle of bypass/select/wakeup latency as compared to a monolithic window that loses /spl sim/5% per additional cycle. Also, HSW achieves the performance of traditional implementations with only 1/3 to 1/2 the number of entries in the critical timing path.

Energy-Efficient and Metastability-Immune Timing-Error Detection and Instruction-Replay-Based Recovery Circuits for Dynamic-Variation Tolerance

Microprocessor clock frequency (FCLK) is traditionally determined based on maximum supply voltage (Vcc) droop and temperature specifications. Since typical usage patterns usually run at nominal Vcc and temperature, these infrequent dynamic variations severely limit FCLK. The concept of timing-error detection and correction in previous work by Ernst, D., et al, (2003) is extended and implemented in a test-chip in 65nm CMOS in Bai, P., et al, (2004) to explore the effectiveness of resilient circuits in eliminating Vcc and temperature FCLK guardbands as well as exploiting path-activation probabilities to maximize throughput (TP).