Results 1 - 10
of
76
Cooperative caching for chip multiprocessors
- In Proceedings of the 33nd Annual International Symposium on Computer Architecture
, 2006
"... Chip multiprocessor (CMP) systems have made the on-chip caches a critical resource shared among co-scheduled threads. Limited off-chip bandwidth, increasing on-chip wire delay, destructive inter-thread interference, and diverse workload characteristics pose key design challenges. To address these ch ..."
Abstract
-
Cited by 140 (1 self)
- Add to MetaCart
(Show Context)
Chip multiprocessor (CMP) systems have made the on-chip caches a critical resource shared among co-scheduled threads. Limited off-chip bandwidth, increasing on-chip wire delay, destructive inter-thread interference, and diverse workload characteristics pose key design challenges. To address these challenge, we propose CMP cooperative caching (CC), a unified framework to efficiently organize and manage on-chip cache resources. By forming a globally managed, shared cache using cooperative private caches. CC can effectively support two important caching applications: (1) reduction of average memory access latency and (2) isolation of destructive inter-thread interference. CC reduces the average memory access latency by balancing between cache latency and capacity opti-mizations. Based private caches, CC naturally exploits their access latency benefits. To improve the effective cache capacity, CC forms a “shared ” cache using replication control and LRU-based global replacement policies. Via cooperation throttling, CC provides a spectrum of caching behaviors between the two extremes of private and shared caches, thus enabling dynamic adaptation to suit workload requirements. We show that CC can achieve a robust performance advantage over private and shared cache schemes across different processor, cache and memory configurations, and a wide selection of multithreaded and multiprogrammed
Parallelism-Aware Batch Scheduling: Enhancing both Performance and Fairness of Shared DRAM Systems
, 2008
"... In a chip-multiprocessor (CMP) system, the DRAM system is shared among cores. In a shared DRAM system, requests from a thread can not only delay requests from other threads by causing bank/bus/row-buffer conflicts but they can also destroy other threads’ DRAM-bank-level parallelism. Requests whose l ..."
Abstract
-
Cited by 127 (45 self)
- Add to MetaCart
(Show Context)
In a chip-multiprocessor (CMP) system, the DRAM system is shared among cores. In a shared DRAM system, requests from a thread can not only delay requests from other threads by causing bank/bus/row-buffer conflicts but they can also destroy other threads’ DRAM-bank-level parallelism. Requests whose latencies would otherwise have been overlapped could effectively become serialized. As a result both fairness and system throughput degrade, and some threads can starve for long time periods. This paper proposes a fundamentally new approach to designing a shared DRAM controller that provides quality of service to threads, while also improving system throughput. Our parallelism-aware batch scheduler (PAR-BS) design is based on two key ideas. First, PAR-BS processes DRAM requests in batches to provide fairness and to avoid starvation of requests. Second, to optimize system throughput, PAR-BS employs a parallelism-aware DRAM scheduling policy that aims to process requests from a thread in parallel in the DRAM banks, thereby reducing the memory-related stall-time experienced by the thread. PAR-BS seamlessly incorporates support for system-level thread priorities and can provide different service levels, including purely opportunistic service, to threads with different priorities. We evaluate the design trade-offs involved in PAR-BS and compare it to four previously proposed DRAM scheduler designs on 4-, 8-, and 16-core systems. Our evaluations show that, averaged over 100 4-core workloads, PAR-BS improves fairness by 1.11X and system throughput by 8.3 % compared to the best previous scheduling technique, Stall-Time Fair Memory (STFM) scheduling. Based on simple request prioritization rules, PAR-BS is also simpler to implement than STFM.
Adaptive insertion policies for high performance caching
- In Proceedings of the 35th International Symposium on Computer Architecture
, 2007
"... The commonly used LRU replacement policy is susceptible to thrashing for memory-intensive workloads that have a working set greater than the available cache size. For such applications, the majority of lines traverse from the MRU position to the LRU position without receiving any cache hits, resulti ..."
Abstract
-
Cited by 109 (4 self)
- Add to MetaCart
The commonly used LRU replacement policy is susceptible to thrashing for memory-intensive workloads that have a working set greater than the available cache size. For such applications, the majority of lines traverse from the MRU position to the LRU position without receiving any cache hits, resulting in inefficient use of cache space. Cache performance can be improved if some fraction of the working set is retained in the cache so that at least that fraction of the working set can contribute to cache hits. We show that simple changes to the insertion policy can significantly reduce cache misses for memory-intensive workloads. We propose the LRU Insertion Policy (LIP) which places the incoming line in the LRU position instead of the MRU position. LIP protects the cache from thrashing and results in close to optimal hitrate for applications that have a cyclic reference pattern. We also propose the Bimodal Insertion Policy (BIP) as an enhancement of LIP that adapts to changes in the working set while maintaining the thrashing protection of LIP. We finally propose a Dynamic Insertion Policy (DIP) to choose between BIP and the traditional LRU policy depending on which policy incurs fewer misses. The proposed insertion policies do not require any change to the existing cache structure, are trivial to implement, and have a storage requirement of less than two bytes. We show that DIP reduces the average MPKI of the baseline 1MB 16-way L2 cache by 21%, bridging two-thirds of the gap between LRU and OPT.
PIPP: Promotion/Insertion Pseudo-Partitioning of Multi-core Shared Caches
- In Proc. of the 36th Intl. Symp. on Computer Architecture
, 2009
"... Many multi-core processors employ a large last-level cache (LLC) shared among the multiple cores. Past research has demonstrated that sharing-oblivious cache management policies (e.g., LRU) can lead to poor performance and fairness when the multiple cores compete for the limited LLC capacity. Differ ..."
Abstract
-
Cited by 62 (1 self)
- Add to MetaCart
(Show Context)
Many multi-core processors employ a large last-level cache (LLC) shared among the multiple cores. Past research has demonstrated that sharing-oblivious cache management policies (e.g., LRU) can lead to poor performance and fairness when the multiple cores compete for the limited LLC capacity. Different memory access patterns can cause cache contention in different ways, and various techniques have been proposed to target some of these behaviors. In this work, we propose a new cache management approach that combines dynamic insertion and promotion policies to provide the benefits of cache partitioning, adaptive insertion, and capacity stealing all with a single mechanism. By handling multiple types of memory behaviors, our proposed technique outperforms techniques that target only either capacity partitioning or adaptive insertion.
Dynamic Warp Subdivision for Integrated Branch and Memory Divergence Tolerance: Extended Tradeoff Analysis ∗
, 2010
"... SIMD organizations amortize the area and power of fetch, decode, and issue logic across multiple processing units in order to maximize throughput for a given area and power budget. However, throughput is reduced when a set of threads operating in lockstep (a warp) are stalled due to long latency mem ..."
Abstract
-
Cited by 47 (6 self)
- Add to MetaCart
(Show Context)
SIMD organizations amortize the area and power of fetch, decode, and issue logic across multiple processing units in order to maximize throughput for a given area and power budget. However, throughput is reduced when a set of threads operating in lockstep (a warp) are stalled due to long latency memory accesses. The resulting idle cycles are extremely costly. Multi-threading can hide latencies by interleaving the execution of multiple warps, but deep multi-threading using many warps dramatically increases the cost of the register files (multi-threading depth × SIMD width), and cache contention can make performance worse. Instead, intra-warp latency hiding should first be exploited. This allows threads that are ready but stalled by SIMD restrictions to use these idle cycles and reduces the need for multi-threading among warps. This paper introduces dynamic warp subdivision (DWS), which allows a single warp to occupy more than one slot in the scheduler without requiring extra register file space. Independent scheduling entities allow divergent branch paths to interleave their execution, and allow threads that hit to run ahead. The result is improved latency hiding and memory level parallelism (MLP). We evaluate the technique on a coherent cache hierarchy with private L1 caches and a shared L2 cache. With an area overhead of less than 1%, experiments with eight data-parallel benchmarks show our technique improves performance on average by 1.7X with energy savings of 30%. We further study the performance sensitivity of DWS to various D-cache sizes and associativities. The performance benefit of DWS is also demonstrated with various SIMD widths and multi-threading depths. While DWS may increase the number of scheduling entities, we propose ways to limit this side effect. The effectiveness of such technique is also analyzed quantitatively. 1
A Framework for Providing Quality of Service in Chip Multi-Processors
- In Proc. of the 40th Intl. Symp. on Microarchitecture (MICRO
, 2007
"... The trends in enterprise IT toward service-oriented computing, server consolidation, and virtual computing point to a future in which workloads are becoming increasingly diverse in terms of performance, reliability, and availability requirements. It can be expected that more and more applications wi ..."
Abstract
-
Cited by 43 (0 self)
- Add to MetaCart
(Show Context)
The trends in enterprise IT toward service-oriented computing, server consolidation, and virtual computing point to a future in which workloads are becoming increasingly diverse in terms of performance, reliability, and availability requirements. It can be expected that more and more applications with diverse requirements will run on a CMP and share platform resources such as the lowest level cache and off-chip bandwidth. In this environment, it is desirable to have microarchitecture and software support that can provide a guarantee of a certain level of performance, which we refer to as performance Quality of Service. In this paper, we investigate a framework that would be needed for a CMP to fully provide QoS. We found that the ability of a CMP to partition platform resources alone is not sufficient for fully providing QoS. We also need an appropriate way to specify a QoS target, and an admission control policy that accepts jobs only when their QoS targets can be satisfied. We also found that providing strict QoS often leads to a significant reduction in throughput due to resource fragmentation. We propose novel throughput optimization techniques that include: (1) exploiting various QoS execution modes, and (2) a microarchitecture technique that steals excess resources from a job while still meeting its QoS target. We evaluated our QoS framework with a full system simulation of a 4-core CMP and a recent version of the Linux Operating System. We found that compared to an unoptimized scheme, the throughput can be improved by up to 47%, making the throughput significantly closer to a non-QoS CMP. 1
Application-Aware Prioritization Mechanisms for On-Chip Networks
"... Network-on-Chips (NoCs) are likely to become a critical shared resource in future many-core processors. The challenge is to develop policies and mechanisms that enable multiple applications to efficiently and fairly share the network, to improve system performance. Existing local packet scheduling p ..."
Abstract
-
Cited by 29 (12 self)
- Add to MetaCart
(Show Context)
Network-on-Chips (NoCs) are likely to become a critical shared resource in future many-core processors. The challenge is to develop policies and mechanisms that enable multiple applications to efficiently and fairly share the network, to improve system performance. Existing local packet scheduling policies in the routers fail to fully achieve this goal, because they treat every packet equally, regardless of which application issued the packet. This paper proposes prioritization policies and architectural extensions to NoC routers that improve the overall application-level throughput, while ensuring fairness in the network. Our prioritization policies are application-aware, distinguishing applications based on the stall-time criticality of their packets. The idea is to divide processor execution time into phases, rank applications within a phase based on stall-time criticality, and have all routers in the network prioritize packets based on their applications ’ ranks. Our scheme also includes techniques that ensure starvation freedom and enable the enforcement of system-level application priorities. We evaluate the proposed prioritization policies on a 64-core CMP with an 8x8 mesh NoC, using a suite of 35 diverse applications. For a representative set of case studies, our proposed policy increases average system throughput by 25.6 % over age-based arbitration and 18.4 % over round-robin arbitration. Averaged over 96 randomlygenerated multiprogrammed workload mixes, the proposed policy improves system throughput by 9.1 % over the best existing prioritization policy, while also reducing application-level unfairness.
A memory-level parallelism aware fetch policy for SMT processors
- In HPCA
, 2007
"... A thread executing on a simultaneous multithreading (SMT) processor that experiences a long-latency load will eventually stall while holding execution resources. Existing long-latency load aware SMT fetch policies limit the amount of resources allocated by a stalled thread by identifying long-latenc ..."
Abstract
-
Cited by 24 (7 self)
- Add to MetaCart
(Show Context)
A thread executing on a simultaneous multithreading (SMT) processor that experiences a long-latency load will eventually stall while holding execution resources. Existing long-latency load aware SMT fetch policies limit the amount of resources allocated by a stalled thread by identifying long-latency loads and preventing the given thread from fetching more instructions — and in some implementations, instructions beyond the long-latency load may even be flushed which frees allocated resources. This paper proposes an SMT fetch policy that takes into account the available memory-level parallelism (MLP) in a thread. The key idea proposed in this paper is that in case of an isolated long-latency load, i.e., there is no MLP, the thread should be prevented from allocating additional resources. However, in case multiple independent long-latency loads overlap, i.e., there is MLP, the thread should allocate as many resources as needed in order to fully expose the available MLP. The proposed MLP-aware fetch policy achieves better performance for MLP-intensive threads on an SMT processor and achieves a better overall balance between performance and fairness than previously proposed fetch policies. 1
Line Distillation: Increasing Cache Capacity by Filtering Unused Words in Cache Lines
"... Caches are organized at a line-size granularity to exploit spatial locality. However, when spatial locality is low, many words in the cache line are not used. Unused words occupy cache space but do not contribute to cache hits. Filtering these words can allow the cache to store more cache lines. We ..."
Abstract
-
Cited by 22 (1 self)
- Add to MetaCart
(Show Context)
Caches are organized at a line-size granularity to exploit spatial locality. However, when spatial locality is low, many words in the cache line are not used. Unused words occupy cache space but do not contribute to cache hits. Filtering these words can allow the cache to store more cache lines. We show that unused words in a cache line are unlikely to be accessed in the less recent part of the LRU stack. We propose Line Distillation (LDIS), a technique that retains only the used words and evicts the unused words in a cache line. We also propose Distill Cache, a cache organization to utilize the capacity created by LDIS. Our experiments with 16 memory-intensive benchmarks show that LDIS reduces the average misses for a 1MB 8-way L2 cache by 30 % and improves the average IPC by 12%. 1.
Multicore-aware reuse distance analysis
, 2009
"... Abstract—This paper presents and validates methods to extend reuse distance analysis of application locality characteristics to shared-memory multicore platforms by accounting for invalidation-based cache-coherence and inter-core cache sharing. Existing reuse distance analysis methods track the numb ..."
Abstract
-
Cited by 19 (2 self)
- Add to MetaCart
(Show Context)
Abstract—This paper presents and validates methods to extend reuse distance analysis of application locality characteristics to shared-memory multicore platforms by accounting for invalidation-based cache-coherence and inter-core cache sharing. Existing reuse distance analysis methods track the number of distinct addresses referenced between reuses of the same address by a given thread, but do not model the effects of data references by other threads. This paper shows several methods to keep reuse stacks consistent so that they account for invalidations and cache sharing, either as references arise in a simulated execution or at synchronization points. These methods are evaluated against a Simics-based coherent cache simulator running several OpenMP and transactionbased benchmarks. The results show that adding multicoreawareness substantially improves the ability of reuse distance analysis to model cache behavior, reducing the error in miss ratio prediction (relative to cache simulation for a specific cache size) by an average of 70 % for per-core caches and an average of 90 % for shared caches. I.
