J. Greathouse, Zhiqiang Ma, M. Frank, R. Peri, T. Austin
Dynamic data race detectors are an important mechanism for creating robust parallel programs. Software race detectors instrument the program under test, observe each memory access, and watch for inter-thread data sharing that could lead to concurrency errors. While this method of bug hunting can find races that are normally difficult to observe, it also suffers from high runtime overheads. It is not uncommon for commercial race detectors to experience 300× slowdowns, limiting their usage. This paper presents a hardware-assisted demand-driven race detector. We are able to observe cache events that are indicative of data sharing between threads by taking advantage of hardware available on modern commercial microprocessors. We use these to build a race detector that is only enabled when it is likely that inter-thread data sharing is occurring. When little sharing takes place, this demand-driven analysis is much faster than contemporary continuous-analysis tools without a large loss of detection accuracy. We modified the race detector in Intel® Inspector XE to utilize our hardware-based sharing indicator and were able to achieve performance increases of 3× and 10× in two parallel benchmark suites and 51× for one particular program.
{"title":"Demand-driven software race detection using hardware performance counters","authors":"J. Greathouse, Zhiqiang Ma, M. Frank, R. Peri, T. Austin","doi":"10.1145/2000064.2000084","DOIUrl":"https://doi.org/10.1145/2000064.2000084","url":null,"abstract":"Dynamic data race detectors are an important mechanism for creating robust parallel programs. Software race detectors instrument the program under test, observe each memory access, and watch for inter-thread data sharing that could lead to concurrency errors. While this method of bug hunting can find races that are normally difficult to observe, it also suffers from high runtime overheads. It is not uncommon for commercial race detectors to experience 300× slowdowns, limiting their usage. This paper presents a hardware-assisted demand-driven race detector. We are able to observe cache events that are indicative of data sharing between threads by taking advantage of hardware available on modern commercial microprocessors. We use these to build a race detector that is only enabled when it is likely that inter-thread data sharing is occurring. When little sharing takes place, this demand-driven analysis is much faster than contemporary continuous-analysis tools without a large loss of detection accuracy. We modified the race detector in Intel® Inspector XE to utilize our hardware-based sharing indicator and were able to achieve performance increases of 3× and 10× in two parallel benchmark suites and 51× for one particular program.","PeriodicalId":340732,"journal":{"name":"2011 38th Annual International Symposium on Computer Architecture (ISCA)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121040306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recent advances in the neuroscientific understanding of the brain are bringing about a tantalizing opportunity for building synthetic machines that perform computation in ways that differ radically from traditional Von Neumann machines. These brain-like architectures, which are premised on our understanding of how the human neocortex computes, are highly fault-tolerant, averaging results over large numbers of potentially faulty components, yet manage to solve very difficult problems more reliably than traditional algorithms. A key principle of operation for these architectures is that of automatic abstraction: independent features are extracted from highly disordered inputs and are used to create abstract invariant representations of the external entities. This feature extraction is applied hierarchically, leading to increasing levels of abstraction at higher levels in the hierarchy. This paper describes and evaluates a biologically plausible computational model for this process, and highlights the inherent fault tolerance of the biologically-inspired algorithm. We introduce a stuck-at fault model for such cortical networks, and describe how this model maps to hardware faults that can occur on commodity GPGPU cores used to realize the model in software. We show experimentally that the model software implementation can intrinsically preserve its functionality in the presence of faulty hardware, without requiring any reprogramming or recompilation. This model is a first step towards developing a comprehensive and biologically plausible understanding of the computational algorithms and microarchitecture of computing systems that mimic the human cortex, and to applying them to the robust implementation of tasks on future computing systems built of faulty components.
{"title":"Automatic abstraction and fault tolerance in cortical microachitectures","authors":"Atif Hashmi, H. Berry, O. Temam, Mikko H. Lipasti","doi":"10.1145/2000064.2000066","DOIUrl":"https://doi.org/10.1145/2000064.2000066","url":null,"abstract":"Recent advances in the neuroscientific understanding of the brain are bringing about a tantalizing opportunity for building synthetic machines that perform computation in ways that differ radically from traditional Von Neumann machines. These brain-like architectures, which are premised on our understanding of how the human neocortex computes, are highly fault-tolerant, averaging results over large numbers of potentially faulty components, yet manage to solve very difficult problems more reliably than traditional algorithms. A key principle of operation for these architectures is that of automatic abstraction: independent features are extracted from highly disordered inputs and are used to create abstract invariant representations of the external entities. This feature extraction is applied hierarchically, leading to increasing levels of abstraction at higher levels in the hierarchy. This paper describes and evaluates a biologically plausible computational model for this process, and highlights the inherent fault tolerance of the biologically-inspired algorithm. We introduce a stuck-at fault model for such cortical networks, and describe how this model maps to hardware faults that can occur on commodity GPGPU cores used to realize the model in software. We show experimentally that the model software implementation can intrinsically preserve its functionality in the presence of faulty hardware, without requiring any reprogramming or recompilation. This model is a first step towards developing a comprehensive and biologically plausible understanding of the computational algorithms and microarchitecture of computing systems that mimic the human cortex, and to applying them to the robust implementation of tasks on future computing systems built of faulty components.","PeriodicalId":340732,"journal":{"name":"2011 38th Annual International Symposium on Computer Architecture (ISCA)","volume":"02 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127429571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alaa R. Alameldeen, I. Wagner, Zeshan A. Chishti, Wei Wu, C. Wilkerson, Shih-Lien Lu
Voltage scaling is one of the most effective mechanisms to improve microprocessors' energy efficiency. However, processors cannot operate reliably below a minimum voltage, Vccmin, since hardware structures may fail. Cell failures in large memory arrays (e.g., caches) typically determine Vccmin for the whole processor. We observe that most cache lines exhibit zero or one failures at low voltages. However, a few lines, especially in large caches, exhibit multi-bit failures and increase Vccmin. Previous solutions either significantly reduce cache capacity to enable uniform error correction across all lines, or significantly increase latency and bandwidth overheads when amortizing the cost of error-correcting codes (ECC) over large lines. In this paper, we propose a novel cache architecture that uses variable-strength error-correcting codes (VS-ECC). In the common case, lines with zero or one failures use a simple and fast ECC. A small number of lines with multi-bit failures use a strong multi-bit ECC that requires some additional area and latency. We present a novel dynamic cache characterization mechanism to determine which lines will exhibit multi-bit failures. In particular, we use multi-bit correction to protect a fraction of the cache after switching to low voltage, while dynamically testing the remaining lines for multi-bit failures. Compared to prior multi-bit-correcting proposals, VS-ECC significantly reduces power and energy, avoids significant reductions in cache capacity, incurs little area overhead, and avoids large increases in latency and bandwidth.
{"title":"Energy-efficient cache design using variable-strength error-correcting codes","authors":"Alaa R. Alameldeen, I. Wagner, Zeshan A. Chishti, Wei Wu, C. Wilkerson, Shih-Lien Lu","doi":"10.1145/2000064.2000118","DOIUrl":"https://doi.org/10.1145/2000064.2000118","url":null,"abstract":"Voltage scaling is one of the most effective mechanisms to improve microprocessors' energy efficiency. However, processors cannot operate reliably below a minimum voltage, Vccmin, since hardware structures may fail. Cell failures in large memory arrays (e.g., caches) typically determine Vccmin for the whole processor. We observe that most cache lines exhibit zero or one failures at low voltages. However, a few lines, especially in large caches, exhibit multi-bit failures and increase Vccmin. Previous solutions either significantly reduce cache capacity to enable uniform error correction across all lines, or significantly increase latency and bandwidth overheads when amortizing the cost of error-correcting codes (ECC) over large lines. In this paper, we propose a novel cache architecture that uses variable-strength error-correcting codes (VS-ECC). In the common case, lines with zero or one failures use a simple and fast ECC. A small number of lines with multi-bit failures use a strong multi-bit ECC that requires some additional area and latency. We present a novel dynamic cache characterization mechanism to determine which lines will exhibit multi-bit failures. In particular, we use multi-bit correction to protect a fraction of the cache after switching to low voltage, while dynamically testing the remaining lines for multi-bit failures. Compared to prior multi-bit-correcting proposals, VS-ECC significantly reduces power and energy, avoids significant reductions in cache capacity, incurs little area overhead, and avoids large increases in latency and bandwidth.","PeriodicalId":340732,"journal":{"name":"2011 38th Annual International Symposium on Computer Architecture (ISCA)","volume":"30 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128190373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
N. Choudhary, Salil V. Wadhavkar, Tanmay A. Shah, Hiran Mayukh, Jayneel Gandhi, Brandon H. Dwiel, Sandeep Navada, H. H. Najaf-abadi, E. Rotenberg
A growing body of work has compiled a strong case for the single-ISA heterogeneous multi-core paradigm. A single-ISA heterogeneous multi-core provides multiple, differently-designed superscalar core types that can streamline the execution of diverse programs and program phases. No prior research has addressed the “Achilles' heel” of this paradigm: design and verification effort is multiplied by the number of different core types. This work frames superscalar processors in a canonical form, so that it becomes feasible to quickly design many cores that differ in the three major superscalar dimensions: superscalar width, pipeline depth, and sizes of structures for extracting instruction-level parallelism (ILP). From this idea, we develop a toolset, called FabScalar, for automatically composing the synthesizable register-transfer-level (RTL) designs of arbitrary cores within a canonical superscalar template. The template defines canonical pipeline stages and interfaces among them. A Canonical Pipeline Stage Library (CPSL) provides many implementations of each canonical pipeline stage, that differ in their superscalar width and depth of sub-pipelining. An RTL generation tool uses the template and CPSL to automatically generate an overall core of desired configuration. Validation experiments are performed along three fronts to evaluate the quality of RTL designs generated by FabScalar: functional and performance (instructions-per-cycle (IPC)) validation, timing validation (cycle time), and confirmation of suitability for standard ASIC flows. With FabScalar, a chip with many different superscalar core types is conceivable.
{"title":"FabScalar: Composing synthesizable RTL designs of arbitrary cores within a canonical superscalar template","authors":"N. Choudhary, Salil V. Wadhavkar, Tanmay A. Shah, Hiran Mayukh, Jayneel Gandhi, Brandon H. Dwiel, Sandeep Navada, H. H. Najaf-abadi, E. Rotenberg","doi":"10.1145/2000064.2000067","DOIUrl":"https://doi.org/10.1145/2000064.2000067","url":null,"abstract":"A growing body of work has compiled a strong case for the single-ISA heterogeneous multi-core paradigm. A single-ISA heterogeneous multi-core provides multiple, differently-designed superscalar core types that can streamline the execution of diverse programs and program phases. No prior research has addressed the “Achilles' heel” of this paradigm: design and verification effort is multiplied by the number of different core types. This work frames superscalar processors in a canonical form, so that it becomes feasible to quickly design many cores that differ in the three major superscalar dimensions: superscalar width, pipeline depth, and sizes of structures for extracting instruction-level parallelism (ILP). From this idea, we develop a toolset, called FabScalar, for automatically composing the synthesizable register-transfer-level (RTL) designs of arbitrary cores within a canonical superscalar template. The template defines canonical pipeline stages and interfaces among them. A Canonical Pipeline Stage Library (CPSL) provides many implementations of each canonical pipeline stage, that differ in their superscalar width and depth of sub-pipelining. An RTL generation tool uses the template and CPSL to automatically generate an overall core of desired configuration. Validation experiments are performed along three fronts to evaluate the quality of RTL designs generated by FabScalar: functional and performance (instructions-per-cycle (IPC)) validation, timing validation (cycle time), and confirmation of suitability for standard ASIC flows. With FabScalar, a chip with many different superscalar core types is conceivable.","PeriodicalId":340732,"journal":{"name":"2011 38th Annual International Symposium on Computer Architecture (ISCA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124628840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Conventional high-performance processors utilize register renaming and complex broadcast-based scheduling logic to steer instructions into a small number of heavily-pipelined execution lanes. This requires multiple complex structures and repeated dependency resolution, imposing a significant dynamic power overhead. This paper advocates in-place execution of instructions, a power-saving, pipeline-free approach that consolidates rename, issue, and bypass logic into one structure - the CRIB - while simultaneously eliminating the need for a multiported register file, instead storing architected state in a simple rank of latches. CRIB achieves the high IPC of an out-of-order machine while keeping the execution core clean, simple, and low power. The datapath within a CRIB structure is purely combinational, eliminating most of the clocked elements in the core while keeping a fully synchronous yet high-frequency design. Experimental results match the IPC and cycle time of a baseline outof- order design while reducing dynamic energy consumption by more than 60% in affected structures.
{"title":"CRIB: Consolidated rename, issue, and bypass","authors":"Erika Gunadi, Mikko H. Lipasti","doi":"10.1145/2000064.2000068","DOIUrl":"https://doi.org/10.1145/2000064.2000068","url":null,"abstract":"Conventional high-performance processors utilize register renaming and complex broadcast-based scheduling logic to steer instructions into a small number of heavily-pipelined execution lanes. This requires multiple complex structures and repeated dependency resolution, imposing a significant dynamic power overhead. This paper advocates in-place execution of instructions, a power-saving, pipeline-free approach that consolidates rename, issue, and bypass logic into one structure - the CRIB - while simultaneously eliminating the need for a multiported register file, instead storing architected state in a simple rank of latches. CRIB achieves the high IPC of an out-of-order machine while keeping the execution core clean, simple, and low power. The datapath within a CRIB structure is purely combinational, eliminating most of the clocked elements in the core while keeping a fully synchronous yet high-frequency design. Experimental results match the IPC and cycle time of a baseline outof- order design while reducing dynamic energy consumption by more than 60% in affected structures.","PeriodicalId":340732,"journal":{"name":"2011 38th Annual International Symposium on Computer Architecture (ISCA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121993835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Guangyu Sun, C. Hughes, Changkyu Kim, Jishen Zhao, Cong Xu, Yuan Xie, Yen-kuang Chen
In recent years, the increasing number of processor cores and limited increases in main memory bandwidth have led to the problem of the bandwidth wall, where memory bandwidth is becoming a performance bottleneck. This is especially true for emerging latency-insensitive, bandwidth-sensitive applications. Designing the memory hierarchy for a platform with an emphasis on maximizing bandwidth within a fixed power budget becomes one of the key challenges. To facilitate architects to quickly explore the design space of memory hierarchies, we propose an analytical performance model called Moguls. The Moguls model estimates the performance of an application on a system, using the bandwidth demand of the application for a range of cache capacities and the bandwidth provided by the system with those capacities. We show how to extend this model with appropriate approximations to optimize a cache hierarchy under a power constraint. The results show how many levels of cache should be designed, and what the capacity, bandwidth, and technology of each level should be. In addition, we study memory hierarchy design with hybrid memory technologies, which shows the benefits of using multiple technologies for future computing systems.
{"title":"Moguls: A model to explore the memory hierarchy for bandwidth improvements","authors":"Guangyu Sun, C. Hughes, Changkyu Kim, Jishen Zhao, Cong Xu, Yuan Xie, Yen-kuang Chen","doi":"10.1145/2000064.2000109","DOIUrl":"https://doi.org/10.1145/2000064.2000109","url":null,"abstract":"In recent years, the increasing number of processor cores and limited increases in main memory bandwidth have led to the problem of the bandwidth wall, where memory bandwidth is becoming a performance bottleneck. This is especially true for emerging latency-insensitive, bandwidth-sensitive applications. Designing the memory hierarchy for a platform with an emphasis on maximizing bandwidth within a fixed power budget becomes one of the key challenges. To facilitate architects to quickly explore the design space of memory hierarchies, we propose an analytical performance model called Moguls. The Moguls model estimates the performance of an application on a system, using the bandwidth demand of the application for a range of cache capacities and the bandwidth provided by the system with those capacities. We show how to extend this model with appropriate approximations to optimize a cache hierarchy under a power constraint. The results show how many levels of cache should be designed, and what the capacity, bandwidth, and technology of each level should be. In addition, we study memory hierarchy design with hybrid memory technologies, which shows the benefits of using multiple technologies for future computing systems.","PeriodicalId":340732,"journal":{"name":"2011 38th Annual International Symposium on Computer Architecture (ISCA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125137865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
N. Binkert, A. Davis, N. Jouppi, M. McLaren, Naveen Muralimanohar, R. Schreiber, Jung Ho Ahn
For large-scale networks, high-radix switches reduce hop and switch count, which decreases latency and power. The ITRS projections for signal-pin count and per-pin bandwidth are nearly flat over the next decade, so increased radix in electronic switches will come at the cost of less per-port bandwidth. Silicon nanophotonic technology provides a long-term solution to this problem. We first compare the use of photonic I/O against an all-electrical, Cray YARC inspired baseline. We compare the power and performance of switches of radix 64, 100, and 144 in the 45, 32, and 22 nm technology steps. In addition with the greater off-chip bandwidth enabled by photonics, the high power of electrical components inside the switch becomes a problem beyond radix 64. We propose an optical switch architecture that exploits high-speed optical interconnects to build a flat crossbar with multiple-writer, single-reader links. Unlike YARC, which uses small buffers at various stages, the proposed design buffers only at input and output ports. This simplifies the design and enables large buffers, capable of handling ethernet-size packets. To mitigate head-of-line blocking and maximize switch throughput, we use an arbitration scheme that allows each port to make eight requests and use two grants. The bandwidth of the optical crossbar is also doubled to to provide a 2x internal speedup. Since optical interconnects have high static power, we show that it is critical to balance the use of optical and electrical components to get the best energy efficiency. Overall, the adoption of photonic I/O allows 100,000 port networks to be constructed with less than one third the power of equivalent all-electronic networks. A further 50% reduction in power can be achieved by using photonics within the switch components. Our best optical design performs similarly to YARC for small packets while consuming less than half the power, and handles 80% more load for large message traffic.
{"title":"The role of optics in future high radix switch design","authors":"N. Binkert, A. Davis, N. Jouppi, M. McLaren, Naveen Muralimanohar, R. Schreiber, Jung Ho Ahn","doi":"10.1145/2000064.2000116","DOIUrl":"https://doi.org/10.1145/2000064.2000116","url":null,"abstract":"For large-scale networks, high-radix switches reduce hop and switch count, which decreases latency and power. The ITRS projections for signal-pin count and per-pin bandwidth are nearly flat over the next decade, so increased radix in electronic switches will come at the cost of less per-port bandwidth. Silicon nanophotonic technology provides a long-term solution to this problem. We first compare the use of photonic I/O against an all-electrical, Cray YARC inspired baseline. We compare the power and performance of switches of radix 64, 100, and 144 in the 45, 32, and 22 nm technology steps. In addition with the greater off-chip bandwidth enabled by photonics, the high power of electrical components inside the switch becomes a problem beyond radix 64. We propose an optical switch architecture that exploits high-speed optical interconnects to build a flat crossbar with multiple-writer, single-reader links. Unlike YARC, which uses small buffers at various stages, the proposed design buffers only at input and output ports. This simplifies the design and enables large buffers, capable of handling ethernet-size packets. To mitigate head-of-line blocking and maximize switch throughput, we use an arbitration scheme that allows each port to make eight requests and use two grants. The bandwidth of the optical crossbar is also doubled to to provide a 2x internal speedup. Since optical interconnects have high static power, we show that it is critical to balance the use of optical and electrical components to get the best energy efficiency. Overall, the adoption of photonic I/O allows 100,000 port networks to be constructed with less than one third the power of equivalent all-electronic networks. A further 50% reduction in power can be achieved by using photonics within the switch components. Our best optical design performs similarly to YARC for small packets while consuming less than half the power, and handles 80% more load for large message traffic.","PeriodicalId":340732,"journal":{"name":"2011 38th Annual International Symposium on Computer Architecture (ISCA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128138430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shuou Nomura, Matthew D. Sinclair, C. Ho, Venkatraman Govindaraju, M. Kruijf, K. Sankaralingam
With technology scaling, manufacture-time and in-field permanent faults are becoming a fundamental problem. Multi-core architectures with spares can tolerate them by detecting and isolating faulty cores, but the required fault detection coverage becomes effectively 100% as the number of permanent faults increases. Dual-modular redundancy(DMR) can provide 100% coverage without assuming device-level fault models, but its overhead is excessive. In this paper, we explore a simple and low-overhead mechanism we call Sampling-DMR: run in DMR mode for a small percentage (1% of the time for example) of each periodic execution window (5 million cycles for example). Although Sampling-DMR can leave some errors undetected, we argue the permanent fault coverage is 100% because it can detect all faults eventually. SamplingDMR thus introduces a system paradigm of restricting all permanent faults' effects to small finite windows of error occurrence. We prove an ultimate upper bound exists on total missed errors and develop a probabilistic model to analyze the distribution of the number of undetected errors and detection latency. The model is validated using full gate-level fault injection experiments for an actual processor running full application software. Sampling-DMR outperforms conventional techniques in terms of fault coverage, sustains similar detection latency guarantees, and limits energy and performance overheads to less than 2%.
{"title":"Sampling + DMR: Practical and low-overhead permanent fault detection","authors":"Shuou Nomura, Matthew D. Sinclair, C. Ho, Venkatraman Govindaraju, M. Kruijf, K. Sankaralingam","doi":"10.1145/2000064.2000089","DOIUrl":"https://doi.org/10.1145/2000064.2000089","url":null,"abstract":"With technology scaling, manufacture-time and in-field permanent faults are becoming a fundamental problem. Multi-core architectures with spares can tolerate them by detecting and isolating faulty cores, but the required fault detection coverage becomes effectively 100% as the number of permanent faults increases. Dual-modular redundancy(DMR) can provide 100% coverage without assuming device-level fault models, but its overhead is excessive. In this paper, we explore a simple and low-overhead mechanism we call Sampling-DMR: run in DMR mode for a small percentage (1% of the time for example) of each periodic execution window (5 million cycles for example). Although Sampling-DMR can leave some errors undetected, we argue the permanent fault coverage is 100% because it can detect all faults eventually. SamplingDMR thus introduces a system paradigm of restricting all permanent faults' effects to small finite windows of error occurrence. We prove an ultimate upper bound exists on total missed errors and develop a probabilistic model to analyze the distribution of the number of undetected errors and detection latency. The model is validated using full gate-level fault injection experiments for an actual processor running full application software. Sampling-DMR outperforms conventional techniques in terms of fault coverage, sustains similar detection latency guarantees, and limits energy and performance overheads to less than 2%.","PeriodicalId":340732,"journal":{"name":"2011 38th Annual International Symposium on Computer Architecture (ISCA)","volume":"239 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125761299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
B. Cuesta, Alberto Ros, M. E. Gómez, A. Robles, J. Duato
To meet the demand for more powerful high-performance shared-memory servers, multiprocessor systems must incorporate efficient and scalable cache coherence protocols, such as those based on directory caches. However, the limited directory cache size of the increasingly larger systems may cause frequent evictions of directory entries and, consequently, invalidations of cached blocks, which severely degrades system performance. A significant percentage of the referred memory blocks are only accessed by one processor (even in parallel applications) and, therefore, do not require coherence maintenance. Taking advantage of techniques that dynamically identify those private blocks, we propose to deactivate the coherence protocol for them and to treat them as uniprocessor systems do. The protocol deactivation allows directory caches to omit the tracking of an appreciable quantity of blocks, which reduces their load and increases their effective size. Since the operating system collaborates on the detection of private blocks, our proposal only requires minor modifications. Simulation results show that, thanks to our proposal, directory caches can avoid the tracking of about 57% of the accessed blocks and their capacity can be better exploited. This contributes either to shorten the runtime of parallel applications by 15% while keeping directory cache size or to maintain system performance while using directory caches 8 times smaller.
{"title":"Increasing the effectiveness of directory caches by deactivating coherence for private memory blocks","authors":"B. Cuesta, Alberto Ros, M. E. Gómez, A. Robles, J. Duato","doi":"10.1145/2000064.2000076","DOIUrl":"https://doi.org/10.1145/2000064.2000076","url":null,"abstract":"To meet the demand for more powerful high-performance shared-memory servers, multiprocessor systems must incorporate efficient and scalable cache coherence protocols, such as those based on directory caches. However, the limited directory cache size of the increasingly larger systems may cause frequent evictions of directory entries and, consequently, invalidations of cached blocks, which severely degrades system performance. A significant percentage of the referred memory blocks are only accessed by one processor (even in parallel applications) and, therefore, do not require coherence maintenance. Taking advantage of techniques that dynamically identify those private blocks, we propose to deactivate the coherence protocol for them and to treat them as uniprocessor systems do. The protocol deactivation allows directory caches to omit the tracking of an appreciable quantity of blocks, which reduces their load and increases their effective size. Since the operating system collaborates on the detection of private blocks, our proposal only requires minor modifications. Simulation results show that, thanks to our proposal, directory caches can avoid the tracking of about 57% of the accessed blocks and their capacity can be better exploited. This contributes either to shorten the runtime of parallel applications by 15% while keeping directory cache size or to maintain system performance while using directory caches 8 times smaller.","PeriodicalId":340732,"journal":{"name":"2011 38th Annual International Symposium on Computer Architecture (ISCA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130585911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Today's chip-level multiprocessors (CMPs) feature up to a hundred discrete cores, and with increasing levels of integration, CMPs with hundreds of cores, cache tiles, and specialized accelerators are anticipated in the near future. In this paper, we propose and evaluate technologies to enable networks-on-chip (NOCs) to support a thousand connected components (Kilo-NOC) with high area and energy efficiency, good performance, and strong quality-of-service (QOS) guarantees. Our analysis shows that QOS support burdens the network with high area and energy costs. In response, we propose a new lightweight topology-aware QOS architecture that provides service guarantees for applications such as consolidated servers on CMPs and real-time SOCs. Unlike prior NOC quality-of-service proposals which require QOS support at every network node, our scheme restricts the extent of hardware support to portions of the die, reducing router complexity in the rest of the chip. We further improve network area- and energy-efficiency through a novel flow control mechanism that enables a single-network, low-cost elastic buffer implementation. Together, these techniques yield a heterogeneous Kilo-NOC architecture that consumes 45% less area and 29% less power than a state-of-the-art QOS-enabled NOC without these features.
{"title":"Kilo-NOC: A heterogeneous network-on-chip architecture for scalability and service guarantees","authors":"Boris Grot, Joel Hestness, S. Keckler, O. Mutlu","doi":"10.1145/2000064.2000112","DOIUrl":"https://doi.org/10.1145/2000064.2000112","url":null,"abstract":"Today's chip-level multiprocessors (CMPs) feature up to a hundred discrete cores, and with increasing levels of integration, CMPs with hundreds of cores, cache tiles, and specialized accelerators are anticipated in the near future. In this paper, we propose and evaluate technologies to enable networks-on-chip (NOCs) to support a thousand connected components (Kilo-NOC) with high area and energy efficiency, good performance, and strong quality-of-service (QOS) guarantees. Our analysis shows that QOS support burdens the network with high area and energy costs. In response, we propose a new lightweight topology-aware QOS architecture that provides service guarantees for applications such as consolidated servers on CMPs and real-time SOCs. Unlike prior NOC quality-of-service proposals which require QOS support at every network node, our scheme restricts the extent of hardware support to portions of the die, reducing router complexity in the rest of the chip. We further improve network area- and energy-efficiency through a novel flow control mechanism that enables a single-network, low-cost elastic buffer implementation. Together, these techniques yield a heterogeneous Kilo-NOC architecture that consumes 45% less area and 29% less power than a state-of-the-art QOS-enabled NOC without these features.","PeriodicalId":340732,"journal":{"name":"2011 38th Annual International Symposium on Computer Architecture (ISCA)","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131981819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：