会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 8. 发明授权
    • Method and system for efficient miss sequence cache line allocation
utilizing an allocation control cell state to enable a selected match
line
    • 用于利用分配控制单元状态来启用所选择的匹配行的有效未命中序列高速缓存行分配的方法和系统
    • US5668972A
    • 1997-09-16
    • US319202
    • 1994-10-05
    • Peichun Peter LiuBrian David Branson
    • Peichun Peter LiuBrian David Branson
    • G06F12/08G06F12/12
    • G06F12/0893G06F12/123
    • A data cache array which includes a plurality of cache lines wherein each cache line includes a selected block of data, a parity field, a content addressable field containing at least a portion of an address for that block of information and a data status field for providing an indication of data validity within that cache line. An allocation control cell is associated with each cache line and a pseudo least recently utilized (PLRU) logic circuit is provided within the data cache array for each group of cache lines. The pseudo least recently utilized (PLRU) logic circuit is then utilized to select and set a particular allocation control cell within each group of cache lines in response to utilization of those cache lines. The cache line allocation process is then utilized to select a particular cache line within a group of cache lines for replacement in response to either an indication of invalidity of the block of information within that cache line or in response to the state of the pseudo least recently utilized (PLRU) logic circuit for that group of cache lines, if the block of information within every cache line within the group is indicated as valid.
    • 一种数据高速缓存阵列,其包括多条高速缓存行,其中每条高速缓存行包括所选择的数据块,奇偶校验字段,内容可寻址字段,其包含用于该信息块的地址的至少一部分,以及数据状态字段,用于提供 该缓存行内的数据有效性的指示。 分配控制单元与每个高速缓存行相关联,并且在数据高速缓存阵列内为每组高速缓存行提供伪最近最少利用的(PLRU)逻辑电路。 然后利用伪最近最少使用的(PLRU)逻辑电路来响应于这些高速缓存行的使用来选择并设置每组高速缓存行内的特定分配控制单元。 然后,高速缓存行分配过程用于响应于该高速缓存行内的信息块的无效指示或响应于伪最近的状态来选择一组高速缓存行中的特定高速缓存行进行替换 如果组内的每个高速缓存行内的信息块被表示为有效,则对该组高速缓存行使用(PLRU)逻辑电路。
    • 10. 发明授权
    • Method and system for offset miss sequence handling in a data cache
array having multiple content addressable field per cache line
utilizing an MRU bit
    • 利用MRU位,每个高速缓存线具有多个内容可寻址字段的数据高速缓存阵列中的偏移未命中序列处理方法和系统
    • US5890221A
    • 1999-03-30
    • US319201
    • 1994-10-05
    • Peichun Peter LiuBrian David Branson
    • Peichun Peter LiuBrian David Branson
    • G06F12/10G06F12/08
    • G06F12/1045
    • An interleaved data cache array which is divided into two sub arrays is provided for utilization within a data processing system. Each subarray includes a plurality of cache lines wherein each cache line includes a selected block of data, a parity field, a first content addressable field containing a portion of an effective address for the selected block of data, a second content addressable field contains a portion of the real address for the selected block of data and a data status field. By utilizing two separate content addresssable fields for the effective address and real address offset and alias problems may be efficiently resolved. A virtual address aliasing condition is identified by searching each cache line for a match between a portion of a desired effective address and the content of the first content addressable field. The desired effective address is translated into a desired real address and a portion of the desired real address is then utilized to search each cache line for a match with the content of the second content addressable field if no match was found within the first content addressable field during the previous cycle. An offset condition is identified by comparing the translated real address to the content of the second content addressable field in a cache line when a match has occurred between the desired effective address and the content of the first content addressable field within that cache line.
    • 提供分割成两个子阵列的交错数据高速缓存阵列用于数据处理系统内的利用。 每个子阵列包括多条高速缓存线,其中每条高速缓存线包括所选择的数据块,奇偶校验字段,包含所选择的数据块的有效地址的一部分的第一内容可寻址字段,第二内容可寻址字段包含部分 的所选数据块的真实地址和数据状态字段。 通过利用两个单独的内容可寻址字段来实现有效地址和实际地址偏移,并且可以有效地解决别名问题。 通过搜索每个高速缓存行来确定虚拟地址混叠条件,以获得期望的有效地址的一部分与第一内容可寻址字段的内容之间的匹配。 将期望的有效地址转换成所需的实际地址,然后如果在第一内容可寻址字段内没有找到匹配,则利用所需实际地址的一部分来搜索每个高速缓存线与第二内容可寻址字段的内容的匹配 在上一个周期。 当在期望的有效地址与该高速缓存行内的第一内容可寻址字段的内容之间发生匹配时,通过比较翻译的实际地址与高速缓存行中的第二内容可寻址字段的内容来识别偏移条件。