Asymmetric Chip Multiprocessors (ACMPs) are becoming a reality. ACMPs can speed up parallel applications if they can identify and accelerate code segments that are critical for performance. Proposals already exist for using coarse-grained thread scheduling and fine-grained bottleneck acceleration. Unfortunately, there have been no proposals offered thus far to decide which code segments to accelerate in cases where both coarse-grained thread scheduling and fine-grained bottleneck acceleration could have value. This paper proposes Utility-Based Acceleration of Multithreaded Applications on Asymmetric CMPs (UBA), a cooperative software/hardware mechanism for identifying and accelerating the most likely critical code segments from a set of multithreaded applications running on an ACMP. The key idea is a new Utility of Acceleration metric that quantifies the performance benefit of accelerating a bottleneck or a thread by taking into account both the criticality and the expected speedup. UBA outperforms the best of two state-of-the-art mechanisms by 11% for single application workloads and by 7% for two-application workloads on an ACMP with 52 small cores and 3 large cores.
非对称芯片多处理器(acmp)正在成为现实。如果acmp能够识别和加速对性能至关重要的代码段，则可以加快并行应用程序的速度。已经有使用粗粒度线程调度和细粒度瓶颈加速的建议。不幸的是，到目前为止还没有提出建议来决定在粗粒度线程调度和细粒度瓶颈加速都有价值的情况下加速哪些代码段。本文提出了基于实用程序的多线程应用在非对称cmp (UBA)上的加速，这是一种协作的软件/硬件机制，用于识别和加速在ACMP上运行的一组多线程应用中最可能的关键代码段。关键思想是一个新的Utility of Acceleration度量，它通过考虑临界性和预期加速来量化加速瓶颈或线程的性能收益。在具有52个小核和3个大核的ACMP上，对于单个应用程序工作负载，UBA的性能比两种最先进机制中的最佳机制高出11%，对于两个应用程序工作负载，UBA的性能高出7%。
{"title":"Utility-based acceleration of multithreaded applications on asymmetric CMPs","authors":"José A. Joao, M. A. Suleman, O. Mutlu, Y. Patt","doi":"10.1145/2485922.2485936","DOIUrl":"https://doi.org/10.1145/2485922.2485936","url":null,"abstract":"Asymmetric Chip Multiprocessors (ACMPs) are becoming a reality. ACMPs can speed up parallel applications if they can identify and accelerate code segments that are critical for performance. Proposals already exist for using coarse-grained thread scheduling and fine-grained bottleneck acceleration. Unfortunately, there have been no proposals offered thus far to decide which code segments to accelerate in cases where both coarse-grained thread scheduling and fine-grained bottleneck acceleration could have value. This paper proposes Utility-Based Acceleration of Multithreaded Applications on Asymmetric CMPs (UBA), a cooperative software/hardware mechanism for identifying and accelerating the most likely critical code segments from a set of multithreaded applications running on an ACMP. The key idea is a new Utility of Acceleration metric that quantifies the performance benefit of accelerating a bottleneck or a thread by taking into account both the criticality and the expected speedup. UBA outperforms the best of two state-of-the-art mechanisms by 11% for single application workloads and by 7% for two-application workloads on an ACMP with 52 small cores and 3 large cores.","PeriodicalId":20555,"journal":{"name":"Proceedings of the 40th Annual International Symposium on Computer Architecture","volume":"44 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82549380","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}
The global pool of data is growing at 2.5 quintillion bytes per day, with 90% of it produced in the last two years alone [24]. There is no doubt the era of big data has arrived. This paper explores targeted deployment of hardware accelerators to improve the throughput and energy efficiency of large-scale data processing. In particular, data partitioning is a critical operation for manipulating large data sets. It is often the limiting factor in database performance and represents a significant fraction of the overall runtime of large data queries. To accelerate partitioning, this paper describes a hardware accelerator for range partitioning, or HARP, and a hardware-software data streaming framework. The streaming framework offers a seamless execution environment for streaming accelerators such as HARP. Together, HARP and the streaming framework provide an order of magnitude improvement in partitioning performance and energy. A detailed analysis of a 32nm physical design shows 7.8 times the throughput of a highly optimized and optimistic software implementation, while consuming just 6.9% of the area and 4.3% of the power of a single Xeon core in the same technology generation.
{"title":"Navigating big data with high-throughput, energy-efficient data partitioning","authors":"Lisa Wu, R. J. Barker, Martha A. Kim, K. A. Ross","doi":"10.1145/2485922.2485944","DOIUrl":"https://doi.org/10.1145/2485922.2485944","url":null,"abstract":"The global pool of data is growing at 2.5 quintillion bytes per day, with 90% of it produced in the last two years alone [24]. There is no doubt the era of big data has arrived. This paper explores targeted deployment of hardware accelerators to improve the throughput and energy efficiency of large-scale data processing. In particular, data partitioning is a critical operation for manipulating large data sets. It is often the limiting factor in database performance and represents a significant fraction of the overall runtime of large data queries. To accelerate partitioning, this paper describes a hardware accelerator for range partitioning, or HARP, and a hardware-software data streaming framework. The streaming framework offers a seamless execution environment for streaming accelerators such as HARP. Together, HARP and the streaming framework provide an order of magnitude improvement in partitioning performance and energy. A detailed analysis of a 32nm physical design shows 7.8 times the throughput of a highly optimized and optimistic software implementation, while consuming just 6.9% of the area and 4.3% of the power of a single Xeon core in the same technology generation.","PeriodicalId":20555,"journal":{"name":"Proceedings of the 40th Annual International Symposium on Computer Architecture","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87038341","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}
There are several emerging memory technologies looming on the horizon to compensate the physical scaling challenges of DRAM. Phase change memory (PCM) is one such candidate proposed for being part of the main memory in computing systems. One salient feature of PCM is its multi-level-cell (MLC) property, which can be used to multiply the memory capacity at the cell level. However, due to the nature of PCM that the value written to the cell can drift over time, PCM is prone to a unique type of soft errors, posing a great challenge for their practical deployment. This paper first quantitatively studied the current art for MLC PCM in dealing with the resistance drift problem and showed that the previously proposed techniques such as scrubbing or error correction mechanisms have significant reliability challenges to overcome. We then propose tri-level-cell PCM and demonstrate its ability to achieving 105 x lower soft error rate than four-level-cell PCM and 1.33 x higher information density than single-level-cell PCM. According to our findings, the tri-level-cell PCM shows 36.4% performance improvement over the four-level-cell PCM while achieving the soft error rate of DRAM.
{"title":"Tri-level-cell phase change memory: toward an efficient and reliable memory system","authors":"N. Seong, Sungkap Yeo, H. Lee","doi":"10.1145/2485922.2485960","DOIUrl":"https://doi.org/10.1145/2485922.2485960","url":null,"abstract":"There are several emerging memory technologies looming on the horizon to compensate the physical scaling challenges of DRAM. Phase change memory (PCM) is one such candidate proposed for being part of the main memory in computing systems. One salient feature of PCM is its multi-level-cell (MLC) property, which can be used to multiply the memory capacity at the cell level. However, due to the nature of PCM that the value written to the cell can drift over time, PCM is prone to a unique type of soft errors, posing a great challenge for their practical deployment. This paper first quantitatively studied the current art for MLC PCM in dealing with the resistance drift problem and showed that the previously proposed techniques such as scrubbing or error correction mechanisms have significant reliability challenges to overcome. We then propose tri-level-cell PCM and demonstrate its ability to achieving 105 x lower soft error rate than four-level-cell PCM and 1.33 x higher information density than single-level-cell PCM. According to our findings, the tri-level-cell PCM shows 36.4% performance improvement over the four-level-cell PCM while achieving the soft error rate of DRAM.","PeriodicalId":20555,"journal":{"name":"Proceedings of the 40th Annual International Symposium on Computer Architecture","volume":"48 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91401271","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}
Arkaprava Basu, Jayneel Gandhi, Jichuan Chang, M. Hill, M. Swift
Our analysis shows that many "big-memory" server workloads, such as databases, in-memory caches, and graph analytics, pay a high cost for page-based virtual memory. They consume as much as 10% of execution cycles on TLB misses, even using large pages. On the other hand, we find that these workloads use read-write permission on most pages, are provisioned not to swap, and rarely benefit from the full flexibility of page-based virtual memory. To remove the TLB miss overhead for big-memory workloads, we propose mapping part of a process's linear virtual address space with a direct segment, while page mapping the rest of the virtual address space. Direct segments use minimal hardware---base, limit and offset registers per core---to map contiguous virtual memory regions directly to contiguous physical memory. They eliminate the possibility of TLB misses for key data structures such as database buffer pools and in-memory key-value stores. Memory mapped by a direct segment may be converted back to paging when needed. We prototype direct-segment software support for x86-64 in Linux and emulate direct-segment hardware. For our workloads, direct segments eliminate almost all TLB misses and reduce the execution time wasted on TLB misses to less than 0.5%.
{"title":"Efficient virtual memory for big memory servers","authors":"Arkaprava Basu, Jayneel Gandhi, Jichuan Chang, M. Hill, M. Swift","doi":"10.1145/2485922.2485943","DOIUrl":"https://doi.org/10.1145/2485922.2485943","url":null,"abstract":"Our analysis shows that many \"big-memory\" server workloads, such as databases, in-memory caches, and graph analytics, pay a high cost for page-based virtual memory. They consume as much as 10% of execution cycles on TLB misses, even using large pages. On the other hand, we find that these workloads use read-write permission on most pages, are provisioned not to swap, and rarely benefit from the full flexibility of page-based virtual memory. To remove the TLB miss overhead for big-memory workloads, we propose mapping part of a process's linear virtual address space with a direct segment, while page mapping the rest of the virtual address space. Direct segments use minimal hardware---base, limit and offset registers per core---to map contiguous virtual memory regions directly to contiguous physical memory. They eliminate the possibility of TLB misses for key data structures such as database buffer pools and in-memory key-value stores. Memory mapped by a direct segment may be converted back to paging when needed. We prototype direct-segment software support for x86-64 in Linux and emulate direct-segment hardware. For our workloads, direct segments eliminate almost all TLB misses and reduce the execution time wasted on TLB misses to less than 0.5%.","PeriodicalId":20555,"journal":{"name":"Proceedings of the 40th Annual International Symposium on Computer Architecture","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84078818","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}
Ling Ren, Xiangyao Yu, Christopher W. Fletcher, Marten van Dijk, S. Devadas
Keeping user data private is a huge problem both in cloud computing and computation outsourcing. One paradigm to achieve data privacy is to use tamper-resistant processors, inside which users' private data is decrypted and computed upon. These processors need to interact with untrusted external memory. Even if we encrypt all data that leaves the trusted processor, however, the address sequence that goes off-chip may still leak information. To prevent this address leakage, the security community has proposed ORAM (Oblivious RAM). ORAM has mainly been explored in server/file settings which assume a vastly different computation model than secure processors. Not surprisingly, naïvely applying ORAM to a secure processor setting incurs large performance overheads. In this paper, a recent proposal called Path ORAM is studied. We demonstrate techniques to make Path ORAM practical in a secure processor setting. We introduce background eviction schemes to prevent Path ORAM failure and allow for a performance-driven design space exploration. We propose a concept called super blocks to further improve Path ORAM's performance, and also show an efficient integrity verification scheme for Path ORAM. With our optimizations, Path ORAM overhead drops by 41.8%, and SPEC benchmark execution time improves by 52.4% in relation to a baseline configuration. Our work can be used to improve the security level of previous secure processors.
{"title":"Design space exploration and optimization of path oblivious RAM in secure processors","authors":"Ling Ren, Xiangyao Yu, Christopher W. Fletcher, Marten van Dijk, S. Devadas","doi":"10.1145/2485922.2485971","DOIUrl":"https://doi.org/10.1145/2485922.2485971","url":null,"abstract":"Keeping user data private is a huge problem both in cloud computing and computation outsourcing. One paradigm to achieve data privacy is to use tamper-resistant processors, inside which users' private data is decrypted and computed upon. These processors need to interact with untrusted external memory. Even if we encrypt all data that leaves the trusted processor, however, the address sequence that goes off-chip may still leak information. To prevent this address leakage, the security community has proposed ORAM (Oblivious RAM). ORAM has mainly been explored in server/file settings which assume a vastly different computation model than secure processors. Not surprisingly, naïvely applying ORAM to a secure processor setting incurs large performance overheads. In this paper, a recent proposal called Path ORAM is studied. We demonstrate techniques to make Path ORAM practical in a secure processor setting. We introduce background eviction schemes to prevent Path ORAM failure and allow for a performance-driven design space exploration. We propose a concept called super blocks to further improve Path ORAM's performance, and also show an efficient integrity verification scheme for Path ORAM. With our optimizations, Path ORAM overhead drops by 41.8%, and SPEC benchmark execution time improves by 52.4% in relation to a baseline configuration. Our work can be used to improve the security level of previous secure processors.","PeriodicalId":20555,"journal":{"name":"Proceedings of the 40th Annual International Symposium on Computer Architecture","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2013-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80237822","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}
Next generation multicore applications will process massive amounts of data with significant sharing. Data movement and management impacts memory access latency and consumes power. Therefore, harnessing data locality is of fundamental importance in future processors. We propose a scalable, efficient shared memory cache coherence protocol that enables seamless adaptation between private and logically shared caching of on-chip data at the fine granularity of cache lines. Our data-centric approach relies on in-hardware yet low-overhead runtime profiling of the locality of each cache line and only allows private caching for data blocks with high spatio-temporal locality. This allows us to better exploit the private caches and enable low-latency, low-energy memory access, while retaining the convenience of shared memory. On a set of parallel benchmarks, our low-overhead locality-aware mechanisms reduce the overall energy by 25% and completion time by 15% in an NoC-based multicore with the Reactive-NUCA on-chip cache organization and the ACKwise limited directory-based coherence protocol.
{"title":"The locality-aware adaptive cache coherence protocol","authors":"George Kurian, O. Khan, S. Devadas","doi":"10.1145/2485922.2485967","DOIUrl":"https://doi.org/10.1145/2485922.2485967","url":null,"abstract":"Next generation multicore applications will process massive amounts of data with significant sharing. Data movement and management impacts memory access latency and consumes power. Therefore, harnessing data locality is of fundamental importance in future processors. We propose a scalable, efficient shared memory cache coherence protocol that enables seamless adaptation between private and logically shared caching of on-chip data at the fine granularity of cache lines. Our data-centric approach relies on in-hardware yet low-overhead runtime profiling of the locality of each cache line and only allows private caching for data blocks with high spatio-temporal locality. This allows us to better exploit the private caches and enable low-latency, low-energy memory access, while retaining the convenience of shared memory. On a set of parallel benchmarks, our low-overhead locality-aware mechanisms reduce the overall energy by 25% and completion time by 15% in an NoC-based multicore with the Reactive-NUCA on-chip cache organization and the ACKwise limited directory-based coherence protocol.","PeriodicalId":20555,"journal":{"name":"Proceedings of the 40th Annual International Symposium on Computer Architecture","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2013-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91109004","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}
R. Azevedo, John D. Davis, K. Strauss, Parikshit Gopalan, M. Manasse, S. Yekhanin
Zombie is an endurance management framework that enables a variety of error correction mechanisms to extend the lifetimes of memories that suffer from bit failures caused by wearout, such as phase-change memory (PCM). Zombie supports both single-level cell (SLC) and multi-level cell (MLC) variants. It extends the lifetime of blocks in working memory pages (primary blocks) by pairing them with spare blocks, i.e., working blocks in pages that have been disabled due to exhaustion of a single block's error correction resources, which would be 'dead' otherwise. Spare blocks adaptively provide error correction resources to primary blocks as failures accumulate over time. This reduces the waste caused by early block failures, making working blocks in discarded pages a useful resource. Even though we use PCM as the target technology, Zombie applies to any memory technology that suffers stuck-at cell failures. This paper describes the Zombie framework, a combination of two new error correction mechanisms (ZombieXOR for SLC and ZombieMLC for MLC) and the extension of two previously proposed SLC mechanisms (ZombieECP and ZombieERC). The result is a 58% to 92% improvement in endurance for Zombie SLC memory and an even more impressive 11x to 17x improvement for ZombieMLC, both with performance overheads of only 0.1% when memories using prior error correction mechanisms reach end of life.
{"title":"Zombie memory: Extending memory lifetime by reviving dead blocks","authors":"R. Azevedo, John D. Davis, K. Strauss, Parikshit Gopalan, M. Manasse, S. Yekhanin","doi":"10.1145/2485922.2485961","DOIUrl":"https://doi.org/10.1145/2485922.2485961","url":null,"abstract":"Zombie is an endurance management framework that enables a variety of error correction mechanisms to extend the lifetimes of memories that suffer from bit failures caused by wearout, such as phase-change memory (PCM). Zombie supports both single-level cell (SLC) and multi-level cell (MLC) variants. It extends the lifetime of blocks in working memory pages (primary blocks) by pairing them with spare blocks, i.e., working blocks in pages that have been disabled due to exhaustion of a single block's error correction resources, which would be 'dead' otherwise. Spare blocks adaptively provide error correction resources to primary blocks as failures accumulate over time. This reduces the waste caused by early block failures, making working blocks in discarded pages a useful resource. Even though we use PCM as the target technology, Zombie applies to any memory technology that suffers stuck-at cell failures. This paper describes the Zombie framework, a combination of two new error correction mechanisms (ZombieXOR for SLC and ZombieMLC for MLC) and the extension of two previously proposed SLC mechanisms (ZombieECP and ZombieERC). The result is a 58% to 92% improvement in endurance for Zombie SLC memory and an even more impressive 11x to 17x improvement for ZombieMLC, both with performance overheads of only 0.1% when memories using prior error correction mechanisms reach end of life.","PeriodicalId":20555,"journal":{"name":"Proceedings of the 40th Annual International Symposium on Computer Architecture","volume":"142 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2013-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77428969","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：