Making STMs Cache Friendly with Compiler Transformations

Software transactional memory (STM) is a promising programming paradigm for shared memory multithreaded programs. In order for STMs to be adopted widely for performance critical software, understanding and improving the cache performance of applications running on STM becomes increasingly crucial, as the performance gap between processor and memory continues to grow. In this paper, we present the most detailed experimental evaluation to date, of the cache behavior of STM applications and quantify the impact of the different STM factors on the cache misses experienced by the applications. We find that STMs are not cache friendly, with the data cache stall cycles contributing to more than 50% of the execution cycles in a majority of the benchmarks. We find that on an average, misses occurring inside the STM account for 62% of total data cache miss latency cycles experienced by the applications and the cache performance is impacted adversely due to certain inherent characteristics of the STM itself. The above observations motivate us to propose a set of specific compiler transformations targeted at making the STMs cache friendly. We find that STM's fine grained and application unaware locking is a major contributor to its poor cache behavior. Hence we propose selective Lock Data co-location (LDC) and Redundant Lock Access Removal (RLAR) to address the lock access misses. We find that even transactions that are completely disjoint access parallel, suffer from costly coherence misses caused by the centralized global time stamp updates and hence we propose the Selective Per-Partition Time Stamp (SPTS) transformation to address this. We show that our transformations are effective in improving the cache behavior of STM applications by reducing the data cache miss latency by 20.15% to 37.14% and improving execution time by 18.32% to 33.12% in five of the 8 STAMP applications.

Probabilistic Shared Cache Management (PriSM)

Effective sharing of the last level cache has a significant influence on the overall performance of a multicore system. We observe that existing solutions control cache occupancy at a coarser granularity, do not scale well to large core counts and in some cases lack the flexibility to support a variety of performance goals. In this paper, we propose Probabilistic Shared Cache Management (PriSM), a framework to manage the cache occupancy of different cores at cache block granularity by controlling their eviction probabilities. The proposed framework requires only simple hardware changes to implement, can scale to larger core count and is flexible enough to support a variety of performance goals. We demonstrate the flexibility of PriSM, by computing the eviction probabilities needed to achieve goals like hit-maximization, fairness and QOS. PriSM-HitMax improves performance by 18.7% over LRU and 11.8% over previously proposed schemes in a sixteen core machine. PriSM-Fairness improves fairness over existing solutions by 23.3% along with a performance improvement of 19.0%. PriSM-QOS successfully achieves the desired QOS targets.

NUcache: an efficient multicore cache organization based on next-use distance

The effectiveness of the last-level shared cache is crucial to the performance of a multi-core system. In this paper, we observe and make use of the DelinquentPC - Next-Use characteristic to improve shared cache performance. We propose a new PC-centric cache organization, NUcache, for the shared last level cache of multi-cores. NUcache logically partitions the associative ways of a cache set into MainWays and DeliWays. While all lines have access to the MainWays, only lines brought in by a subset of delinquent PCs, selected by a PC selection mechanism, are allowed to enter the DeliWays. The PC selection mechanism is an intelligent cost-benefit analysis based algorithm that utilizes Next-Use information to select the set of PCs that can maximize the hits experienced in DeliWays. Performance evaluation reveals that NUcache improves the performance over a baseline design by 9.6%, 30% and 33% respectively for dual, quad and eight core workloads comprised of SPEC benchmarks. We also show that NUcache is more effective than other well-known cache-partitioning algorithms.

Adaptive power optimization of on-chip SNUCA cache on tiled chip multicore architecture using remap policy

Advances in technology have increased the number of cores and size of caches present on chip multicore platforms(CMPs). As a result, leakage power consumption of on-chip caches has already become a major power consuming component of the memory subsystem. We propose to reduce leakage power consumption in static nonuniform cache architecture(SNUCA) on a tiled CMP by dynamically varying the number of cache slices used and switching off unused cache slices. A cache slice in a tile includes all cache banks present in that tile. Switched-off cache slices are remapped considering the communication costs to reduce cache usage with minimal impact on execution time. This saves leakage power consumption in switched-off L2 cache slices. On an average, there map policy achieves 41% and 49% higher EDP savings compared to static and dynamic NUCA (DNUCA) cache policies on a scalable tiled CMP, respectively.

Efficient Cache Exploration Method for a Tiled Chip Multiprocessor

Past studies use deterministic models to evaluate optimal cache configuration or to explore its design space. However, with the increasing number of components present on a chip multiprocessor (CMP), deterministic approaches do not scale well. Hence, we apply probabilistic genetic algorithms (GA) to determine a near-optimal cache configuration for a sixteen tiled CMP. We propose and implement a faster trace based approach to estimate fitness of a chromosome. It shows up-to 218x simulation speedup over the cycle-accurate architectural simulation. Our methodology can be applied to solve other cache optimization problems such as design space exploration of cache and its partitioning among applications/ virtual machines.

Interdependent cache analyses for better precision and safety

One of the challenges for accurately estimating Worst Case Execu-tion Time(WCET) of executables is to accurately predict their cache behaviour. Various techniques have been developed to predict the cache contents at different program points to estimate the execution time of memory-accessing instructions. One of the most widely used techniques is Abstract Interpretation based Must Analysis, which de-termines the cache blocks guaranteed to be present in the cache, and hence provides safe estimation of cache hits and misses. However,Must Analysis is highly imprecise, and platforms using Must Analysis have been known to produce blown-up WCET estimates. In our work, we propose to use May Analysis to assist the Must Analysis cache up-date and make it more precise. We prove the safety of our approach as well as provide examples where our Improved Must Analysis provides better precision. Further, we also detect a serious flaw in the original Persistence Analysis, and use Must and May Analysis to assist the Persistence Analysis cache update, to make it safe and more precise than the known solutions to the problem.

Path Sensitive Cache Analysis Using Cache Miss Paths

Cache analysis plays a very important role in obtaining precise Worst Case Execution Time (WCET) estimates of programs for real-time systems. While Abstract Interpretation based approaches are almost universally used for cache analysis, they fail to take advantage of its unique requirement: it is not necessary to find the guaranteed cache behavior that holds across all executions of a program. We only need the cache behavior along one particular program path, which is the path with the maximum execution time. In this work, we introduce the concept of cache miss paths, which allows us to use the worst-case path information to improve the precision of AI-based cache analysis. We use Abstract Interpretation to determine the cache miss paths, and then integrate them in the IPET formulation. An added advantage is that this further allows us to use infeasible path information for cache analysis. Experimentally, our approach gives more precise WCETs as compared to AI-based cache analysis, and we also provide techniques to trade-off analysis time with precision to provide scalability.

Bi-Modal DRAM Cache: Improving Hit Rate, Hit Latency and Bandwidth

In this paper, we present Bi-Modal Cache - a flexible stacked DRAM cache organization which simultaneously achieves several objectives: (i) improved cache hit ratio, (ii) moving the tag storage overhead to DRAM, (iii) lower cache hit latency than tags-in-SRAM, and (iv) reduction in off-chip bandwidth wastage. The Bi-Modal Cache addresses the miss rate versus off-chip bandwidth dilemma by organizing the data in a bi-modal fashion - blocks with high spatial locality are organized as large blocks and those with little spatial locality as small blocks. By adaptively selecting the right granularity of storage for individual blocks at run-time, the proposed DRAM cache organization is able to make judicious use of the available DRAM cache capacity as well as reduce the off-chip memory bandwidth consumption. The Bi-Modal Cache improves cache hit latency despite moving the metadata to DRAM by means of a small SRAM based Way Locator. Further by leveraging the tremendous internal bandwidth and capacity that stacked DRAM organizations provide, the Bi-Modal Cache enables efficient concurrent accesses to tags and data to reduce hit time. Through detailed simulations, we demonstrate that the Bi-Modal Cache achieves overall performance improvement (in terms of Average Normalized Turnaround Time (ANTT)) of 10.8%, 13.8% and 14.0% in 4-core, 8-core and 16-core workloads respectively.

Of plants and pikas: evidence for a climate-mediated decline in forage and cache quality

Background: Animals that hoard food to mediate seasonal deficits in resource availability might be particularly vulnerable to climate-mediated reductions in the quality and accessibility of food during the caching season. Central-place foragers might be additionally impacted by climatic constraints on their already restricted foraging range. Aims: We sought evidence for these patterns in a study of the American pika (Ochotona princeps), a territorial, central-place forager sensitive to climate. Methods: Pika food caches and available forage were re-sampled using historical methods at two long-term study sites, to quantify changes over two decades. Taxa that changed in availability or use were analysed for primary and secondary metabolites. Results: Both sites trended towards warmer summers, and snowmelt trended earlier at the lower latitude site. Graminoid cover increased at each site, and caching trends appeared to reflect available forage rather than primary metabolites. Pikas at the lower latitude site preferred species higher in secondary metabolites, known to provide higher-nutrient winter forage. However, caching of lower-nutrient graminoids increased in proportion with graminoid availability at that site. Conclusions: If our results represent trends in climate, cache quality and available forage, we predict that pikas at the lower latitude site will soon face nutritional deficiencies.

模型检测MESIF Cache一致性协议

在处理器从单核向多核演进的过程中,为了获得更好的性能和可扩展性,适用于多核处理器系统的Cache一致性协议变得越来越复杂。Cache一致性协议的验证一直是模型检测在工业界主要应用之一,被工业界和学术界关注。相对传统方法而言,微结构级的模型检测能够描述和验证更多的协议细节。利用NuSMV工具对Intel公司的MESIF Cache一致性协议进行模型检测在微结构层次上进行了建模,并对该协议进行模型检测,试验结果证明了此方法的有效性。

On the Fractal Nature of WWW and Its Application to Cache Modeling

The World Wide Web (WWW or Web) is growing rapidly on the Internet. Web users want fast response time and easy access to a enormous variety of information across the world. Thus, performance is becoming a main issue in the Web. Fractals have been used to study fluctuating phenomena in many different disciplines, from the distribution of galaxies in astronomy to complex physiological control systems. The Web is also a complex, irregular, and random system. In this paper, we look at the document reference pattern at Internet Web servers and use fractal-based models to understand aspects (e.g. caching schemes) that affect the Web performance.

Basis Token Consistency: A Practical Mechanism for Strong Web Cache Consistency

With web caching and cache-related services like CDNs and edge services playing an increasingly significant role in the modern internet, the problem of the weak consistency and coherence provisions in current web protocols is becoming increasingly significant and drawing the attention of the standards community [LCD01]. Toward this end, we present definitions of consistency and coherence for web-like environments, that is, distributed client-server information systems where the semantics of interactions with resource are more general than the read/write operations found in memory hierarchies and distributed file systems. We then present a brief review of proposed mechanisms which strengthen the consistency of caches in the web, focusing upon their conceptual contributions and their weaknesses in real-world practice. These insights motivate a new mechanism, which we call "Basis Token Consistency" or BTC; when implemented at the server, this mechanism allows any client (independent of the presence and conformity of any intermediaries) to maintain a self-consistent view of the server's state. This is accomplished by annotating responses with additional per-resource application information which allows client caches to recognize the obsolescence of currently cached entities and identify responses from other caches which are already stale in light of what has already been seen. The mechanism requires no deviation from the existing client-server communication model, and does not require servers to maintain any additional per-client state. We discuss how our mechanism could be integrated into a fragment-assembling Content Management System (CMS), and present a simulation-driven performance comparison between the BTC algorithm and the use of the Time-To-Live (TTL) heuristic.

Cache-and-Relay Streaming Media Delivery for Asynchronous Clients

We consider the problem of delivering popular streaming media to a large number of asynchronous clients. We propose and evaluate a cache-and-relay end-system multicast approach, whereby a client joining a multicast session caches the stream, and if needed, relays that stream to neighboring clients which may join the multicast session at some later time. This cache-and-relay approach is fully distributed, scalable, and efficient in terms of network link cost. In this paper we analytically derive bounds on the network link cost of our cache-and-relay approach, and we evaluate its performance under assumptions of limited client bandwidth and limited client cache capacity. When client bandwidth is limited, we show that although finding an optimal solution is NP-hard, a simple greedy algorithm performs surprisingly well in that it incurs network link costs that are very close to a theoretical lower bound. When client cache capacity is limited, we show that our cache-and-relay approach can still significantly reduce network link cost. We have evaluated our cache-and-relay approach using simulations over large, synthetic random networks, power-law degree networks, and small-world networks, as well as over large real router-level Internet maps.