-
公开(公告)号：US09021206B2
公开(公告)日：2015-04-28
申请号：US13218173
申请日：2011-08-25
CPC分类号： G06F12/0888 , G06F12/0842 , G06F12/0897 , G06F12/128 , G06F2212/1021
摘要： A method, system and program are provided for controlling access to a specified cache level in a cache hierarchy in a multiprocessor system by evaluating cache statistics for a specified application at the specified cache level against predefined criteria to prevent the specified application from accessing the specified cache level if the specified application does not meeting the predefined criteria.
摘要翻译： 提供了一种方法，系统和程序，用于通过针对预定义的标准评估针对指定高速缓存级别的指定应用程序的高速缓存统计信息来控制对多处理器系统中的高速缓存层级中的指定缓存级别的访问，以防止指定的应用程序访问指定的缓存 级别，如果指定的应用程序不符合预定义的标准。
-
公开(公告)号：US08935478B2
公开(公告)日：2015-01-13
申请号：US13286507
申请日：2011-11-01
申请人： Robert H. Bell, Jr. , Wen-Tzer T. Chen , Diane G. Flemming , Hong L. Hua , William A. Maron , Mysore S. Srinivas
发明人： Robert H. Bell, Jr. , Wen-Tzer T. Chen , Diane G. Flemming , Hong L. Hua , William A. Maron , Mysore S. Srinivas
CPC分类号： G06F12/08 , G06F12/0811 , G06F12/0897
摘要： According to one aspect of the present disclosure, a system and technique for variable cache line size management is disclosed. The system includes a processor and a cache hierarchy, where the cache hierarchy includes a sectored upper level cache and an unsectored lower level cache, and wherein the upper level cache includes a plurality of sub-sectors, each sub-sector having a cache line size corresponding to a cache line size of the lower level cache. The system also includes logic executable to, responsive to determining that a cache line from the upper level cache is to be evicted to the lower level cache: identify referenced sub-sectors of the cache line to be evicted; invalidate unreferenced sub-sectors of the cache line to be evicted; and store the referenced sub-sectors in the lower level cache.
摘要翻译： 根据本公开的一个方面，公开了一种用于可变高速缓存行大小管理的系统和技术。 该系统包括处理器和高速缓存层级，其中高速缓存分层结构包括扇区高级缓存和未被覆盖的较低级高速缓存，并且其中高级高速缓存包括多个子扇区，每个子扇区具有高速缓存行大小 对应于较低级别缓存的高速缓存行大小。 该系统还包括可执行的逻辑，用于响应于确定来自较高级别高速缓存的高速缓存线将被驱逐到较低级高速缓存：识别要驱逐的高速缓存行的参考子扇区; 使缓存行的未引用子扇区无效; 并将参考的子扇区存储在较低级别的高速缓存中。
-
公开(公告)号：US08677371B2
公开(公告)日：2014-03-18
申请号：US12650909
申请日：2009-12-31
申请人： Diane G. Flemming , William A. Maron , Ram Raghavan , Satya Prakash Sharma , Mysore S. Srinivas
发明人： Diane G. Flemming , William A. Maron , Ram Raghavan , Satya Prakash Sharma , Mysore S. Srinivas
CPC分类号： G06F9/5077
摘要： Functionality is implemented to determine that a plurality of multi-core processing units of a system are configured in accordance with a plurality of operating performance modes. It is determined that a first of the plurality of operating performance modes satisfies a first performance criterion that corresponds to a first workload of a first logical partition of the system. Accordingly, the first logical partition is associated with a first set of the plurality of multi-core processing units that are configured in accordance with the first operating performance mode. It is determined that a second of the plurality of operating performance modes satisfies a second performance criterion that corresponds to a second workload of a second logical partition of the system. Accordingly, the second logical partition is associated with a second set of the plurality of multi-core processing units that are configured in accordance with the second operating performance mode.
摘要翻译： 实现功能以确定系统的多个多核处理单元根据多个操作性能模式来配置。 确定多个操作性能模式中的第一个满足与系统的第一逻辑分区的第一工作负载相对应的第一性能标准。 因此，第一逻辑分区与根据第一操作性能模式配置的多个多核处理单元的第一组相关联。 确定多个操作性能模式中的第二个满足与系统的第二逻辑分区的第二工作负载相对应的第二性能标准。 因此，第二逻辑分区与根据第二操作性能模式配置的多个多核处理单元的第二组关联。
-
公开(公告)号：US20130111136A1
公开(公告)日：2013-05-02
申请号：US13451742
申请日：2012-04-20
申请人： Robert H. Bell, JR. , Wen-Tzer T. Chen , Diane G. Flemming , Hong L. Hua , William A. Maron , Mysore S. Srinivas
发明人： Robert H. Bell, JR. , Wen-Tzer T. Chen , Diane G. Flemming , Hong L. Hua , William A. Maron , Mysore S. Srinivas
IPC分类号： G06F12/08
CPC分类号： G06F12/08 , G06F12/0811 , G06F12/0897
摘要： According to one aspect of the present disclosure, a method and technique for variable cache line size management is disclosed. The method includes: determining whether an eviction of a cache line from an upper level sectored cache to an unsectored lower level cache is to be performed, wherein the upper level cache includes a plurality of sub-sectors, each sub-sector having a cache line size corresponding to a cache line size of the lower level cache; responsive to determining that an eviction is to be performed, identifying referenced sub-sectors of the cache line to be evicted; invalidating unreferenced sub-sectors of the cache line to be evicted; and storing the referenced sub-sectors in the lower level cache.
摘要翻译： 根据本公开的一个方面，公开了一种用于可变高速缓存行大小管理的方法和技术。 该方法包括：确定是否执行将高速缓存行从高级扇区高速缓存驱逐到未故障的较低级高速缓存，其中高级缓存包括多个子扇区，每个子扇区具有高速缓存行 对应于较低级缓存的高速缓存行大小的大小; 响应于确定要执行驱逐，识别要被驱逐的高速缓存行的参考子扇区; 使要删除的缓存行的未引用子扇区无效; 并将所引用的子扇区存储在下级缓存中。
-
公开(公告)号：US20120216214A1
公开(公告)日：2012-08-23
申请号：US13458769
申请日：2012-04-27
申请人： Diane G. Flemming , William A. Maron , Ram Raghavan , Satya Prakash Sharma , Mysore S. Srinivas
发明人： Diane G. Flemming , William A. Maron , Ram Raghavan , Satya Prakash Sharma , Mysore S. Srinivas
IPC分类号： G06F9/46
CPC分类号： G06F9/5077
摘要： Functionality is implemented to determine that a plurality of multi-core processing units of a system are configured in accordance with a plurality of operating performance modes. It is determined that a first of the plurality of operating performance modes satisfies a first performance criterion that corresponds to a first workload of a first logical partition of the system. Accordingly, the first logical partition is associated with a first set of the plurality of multi-core processing units that are configured in accordance with the first operating performance mode. It is determined that a second of the plurality of operating performance modes satisfies a second performance criterion that corresponds to a second workload of a second logical partition of the system. Accordingly, the second logical partition is associated with a second set of the plurality of multi-core processing units that are configured in accordance with the second operating performance mode.
摘要翻译： 实现功能以确定系统的多个多核处理单元根据多个操作性能模式来配置。 确定多个操作性能模式中的第一个满足与系统的第一逻辑分区的第一工作负载相对应的第一性能标准。 因此，第一逻辑分区与根据第一操作性能模式配置的多个多核处理单元的第一组相关联。 确定多个操作性能模式中的第二个满足与系统的第二逻辑分区的第二工作负载相对应的第二性能标准。 因此，第二逻辑分区与根据第二操作性能模式配置的多个多核处理单元的第二组相关联。
-
6.发明申请公开(公告)号：US20120216212A1
公开(公告)日：2012-08-23
申请号：US13460448
申请日：2012-04-30
IPC分类号： G06F9/46
CPC分类号： G06F9/5011 , G06F9/45516 , G06F9/45558 , G06F9/4881 , G06F9/5088 , G06F2009/4557 , G06F2009/45579
摘要： A computer implemented method includes determining first characteristics of a first logical partition, the first characteristics including a memory footprint characteristic. The method includes assigning a first portion of a first set of physical computing resources to the first logical partition. The first set of physical computing resources includes a plurality of processors that includes a first processor having a first processor type and a second processor having a second processor type. The first portion includes the second processor. The method includes dispatching the first logical partition to execute using the first portion. The method includes creating a second logical partition that includes the second processor and assigning a second portion of the first set of physical computing resources to the second logical partition. The method includes dispatching the second logical partition to execute using the second portion.
摘要翻译： 计算机实现的方法包括确定第一逻辑分区的第一特征，所述第一特征包括存储器占用特征。 该方法包括将第一组物理计算资源的第一部分分配给第一逻辑分区。 第一组物理计算资源包括多个处理器，其包括具有第一处理器类型的第一处理器和具有第二处理器类型的第二处理器。 第一部分包括第二处理器。 该方法包括使用第一部分调度第一逻辑分区以执行。 该方法包括创建包括第二处理器并将第一组物理计算资源的第二部分分配给第二逻辑分区的第二逻辑分区。 该方法包括使用第二部分调度第二逻辑分区以执行。
-
7.发明申请Assigning Cache Priorities to Virtual/Logical Processors and Partitioning a Cache According to Such Priorities 失效根据这种优先级，将虚拟/逻辑处理器的缓存优先级分配给缓存公开(公告)号：US20110145505A1
公开(公告)日：2011-06-16
申请号：US12637891
申请日：2009-12-15
CPC分类号： G06F12/0895 , G06F9/5022 , G06F9/5077 , G06F12/126 , G06F2209/5021
摘要： Mechanisms are provided, for implementation in a data processing system having at least one physical processor and at least one associated cache memory, for allocating cache resources of the at least one cache memory to virtual processors of the data processing system. The mechanisms identify a plurality of high priority virtual processors in the data processing system. The mechanisms further determine a percentage of cache lines of the at least one cache memory to be assigned to high priority virtual processors. Moreover, the mechanisms mark a portion of the cache lines in the at least one cache memory as being evictable by only high priority virtual processors based on the determined percentage of cache lines to be assigned to high priority virtual processors. The marked portion of the cache lines cannot be evicted by lower priority virtual processors having a priority lower than the high priority virtual processors.
摘要翻译： 提供了用于在具有至少一个物理处理器和至少一个相关联的高速缓冲存储器的数据处理系统中实现的机制，用于将至少一个高速缓冲存储器的高速缓存资源分配给数据处理系统的虚拟处理器。 该机制识别数据处理系统中的多个高优先级虚拟处理器。 这些机制进一步确定要分配给高优先级虚拟处理器的至少一个高速缓冲存储器的高速缓存行的百分比。 此外，机制将所述至少一个高速缓冲存储器中的高速缓存行的一部分标记为仅基于所分配给高优先级虚拟处理器的高速缓存行的确定百分比仅被高优先级的虚拟处理器驱逐。 高速缓存行的标记部分不能被优先级低于高优先级虚拟处理器的较低优先级的虚拟处理器驱逐。
-
8.发明申请公开(公告)号：US20110093861A1
公开(公告)日：2011-04-21
申请号：US12582813
申请日：2009-10-21
CPC分类号： G06F9/5011 , G06F9/45516 , G06F9/45558 , G06F9/4881 , G06F9/5088 , G06F2009/4557 , G06F2009/45579
摘要： A data processing system includes physical computing resources that include a plurality of processors. The plurality of processors include a first processor having a first processor type and a second processor having a second processor type that is different than the first processor type. The data processing system also includes a resource manager to assign portions of the physical computing resources to be used when executing logical partitions. The resource manager is configured to assign a first portion of the physical computing resources to a logical partition, to determine characteristics of the logical partition, the characteristics including a memory footprint characteristic, to assign a second portion of the physical computing resources based on the characteristics of the logical partition, and to dispatch the logical partition to execute using the second portion of the physical computing resources.
摘要翻译： 数据处理系统包括包括多个处理器的物理计算资源。 多个处理器包括具有第一处理器类型的第一处理器和具有不同于第一处理器类型的第二处理器类型的第二处理器。 数据处理系统还包括资源管理器，用于分配在执行逻辑分区时要使用的物理计算资源的部分。 资源管理器被配置为将物理计算资源的第一部分分配给逻辑分区，以确定逻辑分区的特征，包括存储器占用空间特征的特性，以基于特征来分配物理计算资源的第二部分 的逻辑分区，并且使用物理计算资源的第二部分分派逻辑分区来执行。
-
9.发明申请METHOD TO CAPTURE HARDWARE STATISTICS FOR PARTITIONS TO ENABLE DISPATCHING AND SCHEDULING EFFICIENCY 有权收集硬件统计数据的方法，以便能够实现分配和调度效率公开(公告)号：US20080244568A1
公开(公告)日：2008-10-02
申请号：US11692276
申请日：2007-03-28
IPC分类号： G06F9/44
CPC分类号： G06F9/45558 , G06F9/45541 , G06F11/3433 , G06F11/3476 , G06F2009/45591
摘要： A method, system and computer program product enables the granular collection and utilization of hardware statistical samples for the efficient scheduling and allocation of data processing resources. In particular, a Partition Statistics Capture and Analysis (PSCA) utility utilizes special purpose registers to collect statistical samples, such as: (1) instructions completed; (2) Level2 (L2) cache misses; (3) cycles per instruction (CPI); and/or (4) other statistics selected based on the programming of the PSCA utility. Further, these statistical samples are utilized for the several purposes, including: (1) determining how long (time) the footprint of a partition takes to become established during the “cold start” period, i.e., during system instantiation; (2) detecting movement of the CPI curve in order to determine the (shifted) location of the onset of steady state (i.e., the knee) on the CPI curve; and (3) utilizing the statistical samples to guide dispatch decisions and make tuning recommendations.
摘要翻译： 一种方法，系统和计算机程序产品能够对硬件统计样本进行粒度收集和利用，从而有效地调度和分配数据处理资源。 特别地，分区统计捕获和分析（PSCA）实用程序利用专用寄存器来收集统计样本，例如：（1）指令完成; （2）Level2（L2）缓存未命中; （3）每个指令周期（CPI）; 和/或（4）基于PSCA实用程序的编程选择的其他统计信息。 此外，这些统计样本用于多个目的，包括：（1）确定在“冷启动”时段期间，即在系统实例化期间，分区的占用面积需要多长时间（时间）建立; （2）检测CPI曲线的移动，以便确定在CPI曲线上稳定状态（即膝盖）的起始位置（偏移）位置; 和（3）利用统计样本来指导调度决策和调整建议。
-
公开(公告)号：US20080244214A1
公开(公告)日：2008-10-02
申请号：US11692346
申请日：2007-03-28
IPC分类号： G06F12/00
CPC分类号： G06F9/5077 , G06F11/3433 , G06F12/0646 , G06F12/0802 , G06F12/109 , G06F2201/815
摘要： A system, method and computer-readable medium for balancing access among multiple logical partitions to the physical system resources of a computer system employing system virtualization. Each of the logical partitions is classified, initially during a startup period, in accordance with a level of allocated dispatch window utilization. Performance metrics of one or more of the physical system resources are determined in association with one or more of the logical partitions. The performance metrics determination is performed at a hardware level independent of programming interrupts. During a dispatch window in which a given set of the physical system resources are configured for allocation to one of the logical partitions, the given set of physical system resources are re-allocated to a replacement logical partition in accordance with the determined performance metrics associated with the replacement logical partition and the dispatch window utilization classification of the replacement logical partition.
-
-
-
-
-
-
-
-
-
搜索结果
41 条记录 (耗时 0.022 秒)
