专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09131899B2 Efficient handling of misaligned loads and stores 有权
标题翻译：高效处理不对齐的负载和商店
公开(公告)号：US09131899B2
公开(公告)日：2015-09-15
申请号：US13177192
申请日：2011-07-06
申请人： Hari S. Kannan , Pradeep Kanapathipillai , Greg M. Hess
发明人： Hari S. Kannan , Pradeep Kanapathipillai , Greg M. Hess
IPC分类号： G06F12/00 , A61B5/00 , A61B5/053 , A61N1/05 , A61N1/362 , G06F12/08
CPC分类号： A61B5/686 , A61B5/0538 , A61B5/4836 , A61B5/7275 , A61N1/05 , A61N1/362 , G06F12/0802 , G06F12/0862 , G06F12/0877
摘要： A system and method for efficiently handling misaligned memory accesses within a processor. A processor comprises a load-store unit (LSU) with a banked data cache (d-cache) and a banked store queue. The processor generates a first address corresponding to a memory access instruction identifying a first cache line. The processor determines the memory access is misaligned which crosses over a cache line boundary. The processor generates a second address identifying a second cache line logically adjacent to the first cache line. If the instruction is a load instruction, the LSU simultaneously accesses the d-cache and store queue with the first and the second addresses. If there are two hits, the data from the two cache lines are simultaneously read out. If the access is a store instruction, the LSU separates associated write data into two subsets and simultaneously stores these subsets in separate cache lines in separate banks of the store queue.
摘要翻译：一种用于有效地处理处理器内的未对准存储器访问的系统和方法。处理器包括具有分组数据高速缓存（d-cache）和分组存储队列的加载存储单元（LSU）。处理器产生对应于识别第一高速缓存行的存储器访问指令的第一地址。处理器确定在高速缓存线边界上跨越的存储器访问未对准。处理器生成标识逻辑上与第一高速缓存线相邻的第二高速缓存线的第二地址。如果指令是加载指令，则LSU同时访问d-cache并存储具有第一和第二地址的队列。如果有两个命中，则同时读出来自两条缓存行的数据。如果访问是存储指令，则LSU将相关联的写入数据分成两个子集，并且将这些子集同时存储在存储队列的单独的存储区中的单独的高速缓存行中。

2. 发明申请

US20130013862A1 EFFICIENT HANDLING OF MISALIGNED LOADS AND STORES 有权
标题翻译：有效处理缺陷货物和仓库
公开(公告)号：US20130013862A1
公开(公告)日：2013-01-10
申请号：US13177192
申请日：2011-07-06
申请人： Hari S. Kannan , Pradeep Kanapathipillai , Greg M. Hess
发明人： Hari S. Kannan , Pradeep Kanapathipillai , Greg M. Hess
IPC分类号： G06F12/08
CPC分类号： A61B5/686 , A61B5/0538 , A61B5/4836 , A61B5/7275 , A61N1/05 , A61N1/362 , G06F12/0802 , G06F12/0862 , G06F12/0877
摘要： A system and method for efficiently handling misaligned memory accesses within a processor. A processor comprises a load-store unit (LSU) with a banked data cache (d-cache) and a banked store queue. The processor generates a first address corresponding to a memory access instruction identifying a first cache line. The processor determines the memory access is misaligned which crosses over a cache line boundary. The processor generates a second address identifying a second cache line logically adjacent to the first cache line. If the instruction is a load instruction, the LSU simultaneously accesses the d-cache and store queue with the first and the second addresses. If there are two hits, the data from the two cache lines are simultaneously read out. If the access is a store instruction, the LSU separates associated write data into two subsets and simultaneously stores these subsets in separate cache lines in separate banks of the store queue.
摘要翻译：一种用于有效地处理处理器内的未对准存储器访问的系统和方法。处理器包括具有分组数据高速缓存（d-cache）和分组存储队列的加载存储单元（LSU）。处理器产生对应于识别第一高速缓存行的存储器访问指令的第一地址。处理器确定在高速缓存线边界上跨越的存储器访问未对准。处理器生成标识逻辑上与第一高速缓存线相邻的第二高速缓存线的第二地址。如果指令是加载指令，则LSU同时访问d-cache并存储具有第一和第二地址的队列。如果有两个命中，则同时读出来自两条缓存行的数据。如果访问是存储指令，则LSU将相关联的写入数据分成两个子集，并且将这些子集同时存储在存储队列的单独的存储区中的单独的高速缓存行中。

3. 发明授权

US09098418B2 Coordinated prefetching based on training in hierarchically cached processors 有权
标题翻译：基于分级缓存处理器的训练进行协调预取
公开(公告)号：US09098418B2
公开(公告)日：2015-08-04
申请号：US13425123
申请日：2012-03-20
申请人： Hari S. Kannan , Brian P. Lilly , Gerard R. Williams, III , Mahnaz Sadoughi-Yarandi , Perumal R. Subramoniam , Pradeep Kanapathipillai
发明人： Hari S. Kannan , Brian P. Lilly , Gerard R. Williams, III , Mahnaz Sadoughi-Yarandi , Perumal R. Subramoniam , Pradeep Kanapathipillai
IPC分类号： G06F13/00 , G06F12/08 , G06F9/30 , G06F9/45
CPC分类号： G06F12/0862 , G06F8/4442 , G06F9/30047 , G06F12/0897 , G06F2212/1016 , G06F2212/6024 , G06F2212/6026 , G06F2212/6028
摘要： Processors and methods for coordinating prefetch units at multiple cache levels. A single, unified training mechanism is utilized for training on streams generated by a processor core. Prefetch requests are sent from the core to lower level caches, and a packet is sent with each prefetch request. The packet identifies the stream ID of the prefetch request and includes relevant training information for the particular stream ID. The lower level caches generate prefetch requests based on the received training information.
摘要翻译：用于在多个高速缓存级别协调预取单元的处理器和方法。一个统一的统一训练机制被用于对处理器核心生成的流进行训练。预取请求从核心发送到较低级别的高速缓存，并且每个预取请求都发送数据包。分组识别预取请求的流ID，并且包括用于特定流ID的相关训练信息。较低级别的缓存基于接收到的训练信息生成预取请求。

4. 发明申请

US20130254485A1 COORDINATED PREFETCHING IN HIERARCHICALLY CACHED PROCESSORS 有权
标题翻译：高性能缓存处理器协调预处理
公开(公告)号：US20130254485A1
公开(公告)日：2013-09-26
申请号：US13425123
申请日：2012-03-20
申请人： Hari S. Kannan , Brian P. Lilly , Gerard R. Williams, III , Mahnaz Sadoughi-Yarandi , Perumal R. Subramoniam , Pradeep Kanapathipillai
发明人： Hari S. Kannan , Brian P. Lilly , Gerard R. Williams, III , Mahnaz Sadoughi-Yarandi , Perumal R. Subramoniam , Pradeep Kanapathipillai
IPC分类号： G06F12/08
CPC分类号： G06F12/0862 , G06F8/4442 , G06F9/30047 , G06F12/0897 , G06F2212/1016 , G06F2212/6024 , G06F2212/6026 , G06F2212/6028
摘要： Processors and methods for coordinating prefetch units at multiple cache levels. A single, unified training mechanism is utilized for training on streams generated by a processor core. Prefetch requests are sent from the core to lower level caches, and a packet is sent with each prefetch request. The packet identifies the stream ID of the prefetch request and includes relevant training information for the particular stream ID. The lower level caches generate prefetch requests based on the received training information.
摘要翻译：用于在多个高速缓存级别协调预取单元的处理器和方法。一个统一的统一训练机制被用于对处理器核心生成的流进行训练。预取请求从核心发送到较低级别的高速缓存，并且每个预取请求都发送数据包。分组识别预取请求的流ID，并且包括用于特定流ID的相关训练信息。较低级别的缓存基于接收到的训练信息生成预取请求。

5. 发明授权

US09009369B2 Lookahead scheme for prioritized reads 有权
标题翻译：优先阅读的前瞻方案
公开(公告)号：US09009369B2
公开(公告)日：2015-04-14
申请号：US13282873
申请日：2011-10-27
申请人： Rajat Goel , Hari S. Kannan , Khurram Z. Malik
发明人： Rajat Goel , Hari S. Kannan , Khurram Z. Malik
IPC分类号： G06F3/06 , G11C8/06 , G11C8/16 , G06F13/00
CPC分类号： G06F12/0215 , G06F5/16 , G06F13/1673 , G06F2212/301 , G11C8/06 , G11C8/16
摘要： A circular queue implementing a scheme for prioritized reads is disclosed. In one embodiment, a circular queue (or buffer) includes a number of storage locations each configured to store a data value. A multiplexer tree is coupled between the storage locations and a read port. A priority circuit is configured to generate and provide selection signals to each multiplexer of the multiplexer tree, based on a priority scheme. Based on the states of the selection signals, one of the storage locations is coupled to the read port via the multiplexers of the multiplexer tree.
摘要翻译：公开了实现优先读取方案的循环队列。在一个实施例中，循环队列（或缓冲器）包括多个存储位置，每个存储位置被配置为存储数据值。复用器树耦合在存储位置和读端口之间。优先级电路被配置为基于优先级方案来生成并提供对多路复用器树的每个多路复用器的选择信号。基于选择信号的状态，其中一个存储位置经由复用器树的多路复用器耦合到读端口。

6. 发明申请

US20130107655A1 Lookahead Scheme for Prioritized Reads 有权
公开(公告)号：US20130107655A1
公开(公告)日：2013-05-02
申请号：US13282873
申请日：2011-10-27
申请人： Rajat Goel , Hari S. Kannan , Khurram Z. Malik
发明人： Rajat Goel , Hari S. Kannan , Khurram Z. Malik
IPC分类号： G11C8/06 , G11C8/00
CPC分类号： G06F12/0215 , G06F5/16 , G06F13/1673 , G06F2212/301 , G11C8/06 , G11C8/16
摘要： A circular queue implementing a scheme for prioritized reads is disclosed. In one embodiment, a circular queue (or buffer) includes a number of storage locations each configured to store a data value. A multiplexer tree is coupled between the storage locations and a read port. A priority circuit is configured to generate and provide selection signals to each multiplexer of the multiplexer tree, based on a priority scheme. Based on the states of the selection signals, one of the storage locations is coupled to the read port via the multiplexers of the multiplexer tree.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式