发明名称 Information processing apparatus, cache apparatus, and data processing method
摘要 A more efficient technique is provided in an information processing apparatus which executes processing using pipelines. An information processing apparatus according to this invention includes a first pipeline, second pipeline, processing unit, and reorder unit. The first pipeline has a plurality of first nodes, and shifts first data held in a first node to a first node. The second pipeline has a plurality of second nodes respectively corresponding to the first nodes of the first pipeline, and shifts second data held in a second node to a second node. The processing unit executes data processing using the first data and the second data. The reorder unit holds one of the output second data based on attribute information of the second data output from the second pipeline, and outputs the held second data to the second pipeline.
申请公布号 US8819360(B2) 申请公布日期 2014.08.26
申请号 US201113173970 申请日期 2011.06.30
申请人 Canon Kabushiki Kaisha 发明人 Ito Tadayuki
分类号 G06F13/00;G06F13/28 主分类号 G06F13/00
代理机构 Fitzpatrick, Cella, Harper & Scinto 代理人 Fitzpatrick, Cella, Harper & Scinto
主权项 1. An information processing apparatus comprising: a first pipeline which has a plurality of first nodes, and shifts first data held in a first node of interest to a first node which is located in a first direction with respect to the first node of interest; a second pipeline which has a plurality of second nodes respectively corresponding to the first nodes of said first pipeline, and shifts second data held in a second node of interest to a second node which is located in a second direction opposite to the first direction with respect to the second node of interest; a processing unit configured to execute data processing using the first data and the second data; and a determination unit configured to hold second data output from the second pipeline, and decide priority order of the second data held by the determination unit based on attribute information of the second data held by the determination unit, the attribute information being used for determining whether the second data held by the determination unit is to be discarded or to be returned to the second pipeline, wherein the second data held by the determination unit and the second data held by the second pipeline are exchanged in accordance with the priority order.
地址 Tokyo JP