Patents by Inventor Mihai Pricopi

Mihai Pricopi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 9977741
    Abstract: A reconfigurable cache architecture is provided. In processor design, as the density of on-chip components increases, a quantity and complexity of processing cores will increase as well. In order to take advantage of increased processing capabilities, many applications will take advantage of instruction level parallelism. The reconfigurable cache architecture provides a cache memory that in capable of being configured in a private mode and a fused mode for an associated multi-core processor. In the fused mode, individual cores of the multi-core processor can write and read data from certain cache banks of the cache memory with greater control over address routing. The cache architecture further includes control and configurability of the memory size and associativity of the cache memory itself.
    Type: Grant
    Filed: July 12, 2016
    Date of Patent: May 22, 2018
    Assignees: Huawei Technologies Co., Ltd., National University of Singapore
    Inventors: Mihai Pricopi, Zhiguo Ge, Yuan Yao, Tulika Mitra, Naxin Zhang
  • Patent number: 9690620
    Abstract: Methods and architecture for dynamic polymorphic heterogeneous multi-core processor operation are provided. The method for dynamic heterogeneous polymorphic processing includes the steps of receiving a processing task comprising a plurality of serial threads. The method is performed in a processor including a plurality of processing cores, each of the plurality of processing cores being assigned to one of a plurality of core clusters and each of the plurality of core clusters capable of dynamically forming a coalition comprising two or more of its processing cores. The method further includes determining whether each of the plurality of serial threads requires more than one processing core, and sending a go-into-coalition-mode-now instruction to ones of the plurality of core clusters for handling ones of the plurality of serial threads that require more than one processing core.
    Type: Grant
    Filed: December 3, 2012
    Date of Patent: June 27, 2017
    Assignee: National University of Singapore
    Inventors: Tulika Mitra, Mihai Pricopi
  • Publication number: 20160321177
    Abstract: A reconfigurable cache architecture is provided. In processor design, as the density of on-chip components increases, a quantity and complexity of processing cores will increase as well. In order to take advantage of increased processing capabilities, many applications will take advantage of instruction level parallelism. The reconfigurable cache architecture provides a cache memory that in capable of being configured in a private mode and a fused mode for an associated multi-core processor. In the fused mode, individual cores of the multi-core processor can write and read data from certain cache banks of the cache memory with greater control over address routing. The cache architecture further includes control and configurability of the memory size and associativity of the cache memory itself.
    Type: Application
    Filed: July 12, 2016
    Publication date: November 3, 2016
    Inventors: Mihai PRICOPI, Zhiguo GE, Yuan YAO, Tulika MITRA, Naxin ZHANG
  • Patent number: 9460012
    Abstract: A reconfigurable cache architecture is provided. In processor design, as the density of on-chip components increases, a quantity and complexity of processing cores will increase as well. In order to take advantage of increased processing capabilities, many applications will take advantage of instruction level parallelism. The reconfigurable cache architecture provides a cache memory that in capable of being configured in a private mode and a fused mode for an associated multi-core processor. In the fused mode, individual cores of the multi-core processor can write and read data from certain cache banks of the cache memory with greater control over address routing. The cache architecture further includes control and configurability of the memory size and associativity of the cache memory itself.
    Type: Grant
    Filed: February 18, 2014
    Date of Patent: October 4, 2016
    Assignees: National University of Singapore, Huawei Technologies Co., Ltd.
    Inventors: Mihai Pricopi, Zhiguo Ge, Yuan Yao, Tulika Mitra, Naxin Zhang
  • Publication number: 20150234744
    Abstract: A reconfigurable cache architecture is provided. In processor design, as the density of on-chip components increases, a quantity and complexity of processing cores will increase as well. In order to take advantage of increased processing capabilities, many applications will take advantage of instruction level parallelism. The reconfigurable cache architecture provides a cache memory that in capable of being configured in a private mode and a fused mode for an associated multi-core processor. In the fused mode, individual cores of the multi-core processor can write and read data from certain cache banks of the cache memory with greater control over address routing. The cache architecture further includes control and configurability of the memory size and associativity of the cache memory itself.
    Type: Application
    Filed: February 18, 2014
    Publication date: August 20, 2015
    Applicants: National University of Singapore, Huawei Technologies Co., Ltd.
    Inventors: Mihai PRICOPI, Zhiguo GE, Yuan YAO, Tulika MITRA, Naxin ZHANG
  • Publication number: 20140331236
    Abstract: Methods and architecture for dynamic polymorphic heterogeneous multi-core processor operation are provided. The method for dynamic heterogeneous polymorphic processing includes the steps of receiving a processing task comprising a plurality of serial threads. The method is performed in a processor including a plurality of processing cores, each of the plurality of processing cores being assigned to one of a plurality of core clusters and each of the plurality of core clusters capable of dynamically forming a coalition comprising two or more of its processing cores. The method further includes determining whether each of the plurality of serial threads requires more than one processing core, and sending a go-into-coalition-mode-now instruction to ones of the plurality of core clusters for handling ones of the plurality of serial threads that require more than one processing core.
    Type: Application
    Filed: December 3, 2012
    Publication date: November 6, 2014
    Inventors: Tulika Mitra, Mihai Pricopi