片上多核共享緩存管理策略研究
發(fā)布時(shí)間：2018-11-09 16:46
【摘要】：片上多核處理器(Chip Multi-Processor, CMP)已經(jīng)成為高性能微處理器的發(fā)展潮流。高速緩存作為處理器與主存之間的重要橋梁，在計(jì)算機(jī)系統(tǒng)的性能優(yōu)化中發(fā)揮著重要作用。一種能夠有效管理CMP共享高速緩存的策略對于當(dāng)今高性能微處理器而言，有著重要的意義。 目前學(xué)術(shù)界對CMP的緩存優(yōu)化主要是面向多道程序的，對于多線程應(yīng)用程序，已有的Cache優(yōu)化技術(shù)如何提高性能，依然是開放的問題。本文圍繞多線程應(yīng)用程序的負(fù)載均衡，混合多線程應(yīng)用程序的服務(wù)質(zhì)量(QoS)等問題，針對CMP系統(tǒng)上運(yùn)行單個(gè)或混合多線程應(yīng)用程序時(shí)，共享高速緩存優(yōu)化策略進(jìn)行了研究，本文的主要研究內(nèi)容與貢獻(xiàn)包括： 1．針對在fork-join模式下運(yùn)行的并行應(yīng)用程序，各線程之間存在的負(fù)載不均衡現(xiàn)象。本文設(shè)計(jì)了一種關(guān)鍵線程指導(dǎo)的細(xì)粒度緩存管理策略，通過在源程序中插入檢查點(diǎn)，由各處理器統(tǒng)計(jì)并行循環(huán)區(qū)域的迭代次數(shù)，準(zhǔn)確地找到并行程序的關(guān)鍵線程；通過給關(guān)鍵線程分配更多的緩存空間，平衡并行程序各線程之間的負(fù)載和加速關(guān)鍵線程的執(zhí)行，從而提升并行程序的整體性能。實(shí)驗(yàn)表明關(guān)鍵線程指導(dǎo)的細(xì)粒度CMP共享緩存管理策略能對于計(jì)算機(jī)視覺、數(shù)據(jù)挖掘等并行程序的加速比分別達(dá)到1-6%。 2．提出關(guān)鍵線程感知的共享緩存管理策略(CASCM)，針對當(dāng)前系統(tǒng)不能基于進(jìn)程的優(yōu)先級進(jìn)行有效的進(jìn)行緩存空間的分配的問題，不僅考慮了進(jìn)程之間的優(yōu)先級，，還考慮了并行程序的線程之間的優(yōu)先級，基于進(jìn)程和線程的不同優(yōu)先級來分配緩存空間，在保證高優(yōu)先級程序服務(wù)質(zhì)量水平的前提下，盡量提升其它進(jìn)程的性能，且無需對現(xiàn)有的緩存結(jié)構(gòu)進(jìn)行較大的改動(dòng)，硬件代價(jià)��；實(shí)驗(yàn)表明，關(guān)鍵線程感知的共享緩存管理策略更有效地利用了緩存空間，相對于ATR緩存管理策略，CASCM在保證了高優(yōu)先級程序服務(wù)質(zhì)量水平的前提下，低優(yōu)先級進(jìn)程的性能可獲得更多地提升。
[Abstract]:Multi-core processor (Chip Multi-Processor, CMP) on-chip has become the trend of high-performance microprocessors. Cache, as an important bridge between processor and main memory, plays an important role in the performance optimization of computer systems. A strategy to effectively manage CMP shared cache is of great significance to today's high-performance microprocessors. At present, CMP cache optimization is mainly oriented to multiprogramming in academic circles. For multithreaded applications, how existing Cache optimization technology can improve performance is still an open problem. This paper focuses on the problems of load balancing of multithreaded applications and quality of service (QoS) of hybrid multithreaded applications. This paper studies the optimization strategy of shared cache when running single or mixed multithreaded applications on CMP system. The main contents and contributions of this paper are as follows: 1. For parallel applications running in fork-join mode, there is a load imbalance between threads. In this paper, a fine-grained cache management strategy guided by critical threads is designed. By inserting checkpoints into source programs, the number of iterations in the parallel loop region is counted by each processor, and the key threads of parallel programs are found accurately. By allocating more cache space to critical threads, balancing the load between threads of parallel programs and accelerating the execution of critical threads, the overall performance of parallel programs can be improved. Experiments show that the fine-grained CMP shared cache management strategy guided by critical threads can accelerate the speed of parallel programs such as computer vision and data mining to 1-6 respectively. 2. A key thread-aware shared cache management strategy, (CASCM), is proposed to solve the problem that the current system cannot allocate cache space effectively based on the priority of the process. It also considers the priority between threads of parallel programs, allocates cache space based on different priorities of processes and threads, and improves the performance of other processes under the premise of ensuring the quality of service of high priority programs. Moreover, there is no need to change the existing cache structure, and the hardware cost is low. The experiments show that the shared cache management strategy of critical thread is more efficient than the ATR cache management strategy. Compared with the ATR cache management strategy, CASCM ensures the quality of service of high priority programs. The performance of low-priority processes can be improved more.
【學(xué)位授予單位】：湖南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP333
本文編號(hào)：2320996
[Abstract]:Multi-core processor (Chip Multi-Processor, CMP) on-chip has become the trend of high-performance microprocessors. Cache, as an important bridge between processor and main memory, plays an important role in the performance optimization of computer systems. A strategy to effectively manage CMP shared cache is of great significance to today's high-performance microprocessors. At present, CMP cache optimization is mainly oriented to multiprogramming in academic circles. For multithreaded applications, how existing Cache optimization technology can improve performance is still an open problem. This paper focuses on the problems of load balancing of multithreaded applications and quality of service (QoS) of hybrid multithreaded applications. This paper studies the optimization strategy of shared cache when running single or mixed multithreaded applications on CMP system. The main contents and contributions of this paper are as follows: 1. For parallel applications running in fork-join mode, there is a load imbalance between threads. In this paper, a fine-grained cache management strategy guided by critical threads is designed. By inserting checkpoints into source programs, the number of iterations in the parallel loop region is counted by each processor, and the key threads of parallel programs are found accurately. By allocating more cache space to critical threads, balancing the load between threads of parallel programs and accelerating the execution of critical threads, the overall performance of parallel programs can be improved. Experiments show that the fine-grained CMP shared cache management strategy guided by critical threads can accelerate the speed of parallel programs such as computer vision and data mining to 1-6 respectively. 2. A key thread-aware shared cache management strategy, (CASCM), is proposed to solve the problem that the current system cannot allocate cache space effectively based on the priority of the process. It also considers the priority between threads of parallel programs, allocates cache space based on different priorities of processes and threads, and improves the performance of other processes under the premise of ensuring the quality of service of high priority programs. Moreover, there is no need to change the existing cache structure, and the hardware cost is low. The experiments show that the shared cache management strategy of critical thread is more efficient than the ATR cache management strategy. Compared with the ATR cache management strategy, CASCM ensures the quality of service of high priority programs. The performance of low-priority processes can be improved more.
【學(xué)位授予單位】：湖南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP333
【參考文獻(xiàn)】
相關(guān)期刊論文 前4條
1 王紹剛;徐煒遐;龐征斌;吳丹;戴藝;陸平靜;;PMESI:一種優(yōu)化進(jìn)程私有數(shù)據(jù)訪問的緩存一致性協(xié)議[J];國防科技大學(xué)學(xué)報(bào);2013年01期
2 彭蔓蔓;李仁發(fā);王宇明;;一種基于程序段的動(dòng)態(tài)電壓縮放算法[J];計(jì)算機(jī)研究與發(fā)展;2008年06期
3 唐軼軒;吳俊敏;陳國良;隋秀峰;黃景;;面向多線程程序基于效用的Cache優(yōu)化策略[J];計(jì)算機(jī)研究與發(fā)展;2013年01期
4 尹巍;吳俊敏;朱小東;;消除低重用塊和預(yù)測訪問間隔的Cache管理策略[J];小型微型計(jì)算機(jī)系統(tǒng);2012年06期
本文編號(hào)：2320996
本文鏈接：http://sikaile.net/kejilunwen/jisuanjikexuelunwen/2320996.html
最近更新
教材專著
