为了在数据密集型工作流下有效降低缓存碎片整理开销并提高缓存命中率,提出一种持久性分布式文件系统客户端缓存DFS-Cache(Distributed File System Cache)。DFS-Cache基于非易失性内存(NVM)设计实现,能够保证数据的持久性和崩溃一致性...为了在数据密集型工作流下有效降低缓存碎片整理开销并提高缓存命中率,提出一种持久性分布式文件系统客户端缓存DFS-Cache(Distributed File System Cache)。DFS-Cache基于非易失性内存(NVM)设计实现,能够保证数据的持久性和崩溃一致性,并大幅减少冷启动时间。DFS-Cache包括基于虚拟内存重映射的缓存碎片整理机制和基于生存时间(TTL)的缓存空间管理策略。前者基于NVM可被内存控制器直接寻址的特性,动态修改虚拟地址和物理地址之间的映射关系,实现零拷贝的内存碎片整理;后者是一种冷热分离的分组管理策略,借助重映射的缓存碎片整理机制,提升缓存空间的管理效率。实验采用真实的Intel傲腾持久性内存设备,对比商用的分布式文件系统MooseFS和GlusterFS,采用Fio和Filebench等标准测试程序,DFS-Cache最高能提升5.73倍和1.89倍的系统吞吐量。展开更多
A notable portion of cachelines in real-world workloads exhibits inner non-uniform access behaviors.However,modern cache management rarely considers this fine-grained feature,which impacts the effective cache capacity...A notable portion of cachelines in real-world workloads exhibits inner non-uniform access behaviors.However,modern cache management rarely considers this fine-grained feature,which impacts the effective cache capacity of contemporary high-performance spacecraft processors.To harness these non-uniform access behaviors,an efficient cache replacement framework featuring an auxiliary cache specifically designed to retain evicted hot data was proposed.This framework reconstructs the cache replacement policy,facilitating data migration between the main cache and the auxiliary cache.Unlike traditional cacheline-granularity policies,the approach excels at identifying and evicting infrequently used data,thereby optimizing cache utilization.The evaluation shows impressive performance improvement,especially on workloads with irregular access patterns.Benefiting from fine granularity,the proposal achieves superior storage efficiency compared with commonly used cache management schemes,providing a potential optimization opportunity for modern resource-constrained processors,such as spacecraft processors.Furthermore,the framework complements existing modern cache replacement policies and can be seamlessly integrated with minimal modifications,enhancing their overall efficacy.展开更多
稀疏线性方程组求解等高性能计算应用常常涉及稀疏矩阵向量乘(SpMV)序列Ax,A2x,…,Asx的计算.上述SpMV序列操作又称为稀疏矩阵幂函数(matrix power kernel,MPK).由于MPK执行多次SpMV且稀疏矩阵保持不变,在缓存(cache)中重用稀疏矩阵,可...稀疏线性方程组求解等高性能计算应用常常涉及稀疏矩阵向量乘(SpMV)序列Ax,A2x,…,Asx的计算.上述SpMV序列操作又称为稀疏矩阵幂函数(matrix power kernel,MPK).由于MPK执行多次SpMV且稀疏矩阵保持不变,在缓存(cache)中重用稀疏矩阵,可避免每次执行SpMV均从主存加载A,从而缓解SpMV访存受限问题,提升MPK性能.但缓存数据重用会导致相邻SpMV操作之间的数据依赖,现有MPK优化多针对单次SpMV调用,或在实现数据重用时引入过多额外开销.提出了缓存感知的MPK(cache-awareMPK,Ca-MPK),基于稀疏矩阵的依赖图,设计了体系结构感知的递归划分方法,将依赖图划分为适合缓存大小的子图/子矩阵,通过构建分割子图解耦数据依赖,根据特定顺序在子矩阵上调度执行SpMV,实现缓存数据重用.测试结果表明,Ca-MPK相对于Intel OneMKL库和最新MPK实现,平均性能提升分别多达约1.57倍和1.40倍.展开更多
文摘为了在数据密集型工作流下有效降低缓存碎片整理开销并提高缓存命中率,提出一种持久性分布式文件系统客户端缓存DFS-Cache(Distributed File System Cache)。DFS-Cache基于非易失性内存(NVM)设计实现,能够保证数据的持久性和崩溃一致性,并大幅减少冷启动时间。DFS-Cache包括基于虚拟内存重映射的缓存碎片整理机制和基于生存时间(TTL)的缓存空间管理策略。前者基于NVM可被内存控制器直接寻址的特性,动态修改虚拟地址和物理地址之间的映射关系,实现零拷贝的内存碎片整理;后者是一种冷热分离的分组管理策略,借助重映射的缓存碎片整理机制,提升缓存空间的管理效率。实验采用真实的Intel傲腾持久性内存设备,对比商用的分布式文件系统MooseFS和GlusterFS,采用Fio和Filebench等标准测试程序,DFS-Cache最高能提升5.73倍和1.89倍的系统吞吐量。
文摘A notable portion of cachelines in real-world workloads exhibits inner non-uniform access behaviors.However,modern cache management rarely considers this fine-grained feature,which impacts the effective cache capacity of contemporary high-performance spacecraft processors.To harness these non-uniform access behaviors,an efficient cache replacement framework featuring an auxiliary cache specifically designed to retain evicted hot data was proposed.This framework reconstructs the cache replacement policy,facilitating data migration between the main cache and the auxiliary cache.Unlike traditional cacheline-granularity policies,the approach excels at identifying and evicting infrequently used data,thereby optimizing cache utilization.The evaluation shows impressive performance improvement,especially on workloads with irregular access patterns.Benefiting from fine granularity,the proposal achieves superior storage efficiency compared with commonly used cache management schemes,providing a potential optimization opportunity for modern resource-constrained processors,such as spacecraft processors.Furthermore,the framework complements existing modern cache replacement policies and can be seamlessly integrated with minimal modifications,enhancing their overall efficacy.
文摘稀疏线性方程组求解等高性能计算应用常常涉及稀疏矩阵向量乘(SpMV)序列Ax,A2x,…,Asx的计算.上述SpMV序列操作又称为稀疏矩阵幂函数(matrix power kernel,MPK).由于MPK执行多次SpMV且稀疏矩阵保持不变,在缓存(cache)中重用稀疏矩阵,可避免每次执行SpMV均从主存加载A,从而缓解SpMV访存受限问题,提升MPK性能.但缓存数据重用会导致相邻SpMV操作之间的数据依赖,现有MPK优化多针对单次SpMV调用,或在实现数据重用时引入过多额外开销.提出了缓存感知的MPK(cache-awareMPK,Ca-MPK),基于稀疏矩阵的依赖图,设计了体系结构感知的递归划分方法,将依赖图划分为适合缓存大小的子图/子矩阵,通过构建分割子图解耦数据依赖,根据特定顺序在子矩阵上调度执行SpMV,实现缓存数据重用.测试结果表明,Ca-MPK相对于Intel OneMKL库和最新MPK实现,平均性能提升分别多达约1.57倍和1.40倍.
