KERNEL MAPPING TO NODES IN COMPUTE FABRIC

    公开(公告)号:US20250094365A1

    公开(公告)日:2025-03-20

    申请号:US18970417

    申请日:2024-12-05

    Abstract: A reconfigurable compute fabric can include multiple nodes, and each node can include multiple tiles with respective processing and storage elements. Compute kernels can be parsed into directed graphs and mapped to particular node or tile resources for execution. In an example, a branch-and-bound search algorithm can be used to perform the mapping. The algorithm can use a cost function to evaluate the resources based on capability, occupancy, or power consumption of the various node or tile resources.

    Kernel mapping to nodes in compute fabric

    公开(公告)号:US12174760B2

    公开(公告)日:2024-12-24

    申请号:US18211473

    申请日:2023-06-19

    Abstract: A reconfigurable compute fabric can include multiple nodes, and each node can include multiple tiles with respective processing and storage elements. Compute kernels can be parsed into directed graphs and mapped to particular node or tile resources for execution. In an example, a branch-and-bound search algorithm can be used to perform the mapping. The algorithm can use a cost function to evaluate the resources based on capability, occupancy, or power consumption of the various node or tile resources.

    TILE-BASED RESULT BUFFERING IN MEMORY-COMPUTE SYSTEMS

    公开(公告)号:US20230067771A1

    公开(公告)日:2023-03-02

    申请号:US17407502

    申请日:2021-08-20

    Abstract: A reconfigurable compute fabric can include multiple nodes, and each node can include multiple tiles with respective processing and storage elements. A first tile in a first node can include a processor with a processor output and a first register network configured to receive information from the processor output and information from one or more of the multiple other tiles in the first node. In response to an output instruction and a delay instruction, the register network can provide an output signal to one of the multiple other tiles in the first node. Based on the output instruction, the output signal can include one or the other of the information from the processor output and the information from one or more of the multiple other tiles in the first node. A timing characteristic of the output signal can depend on the delay instruction.

    KERNEL MAPPING TO NODES IN COMPUTE FABRIC

    公开(公告)号:US20230059948A1

    公开(公告)日:2023-02-23

    申请号:US17407486

    申请日:2021-08-20

    Abstract: A reconfigurable compute fabric can include multiple nodes, and each node can include multiple tiles with respective processing and storage elements. Compute kernels can be parsed into directed graphs and mapped to particular node or tile resources for execution. In an example, a branch-and-bound search algorithm can be used to perform the mapping. The algorithm can use a cost function to evaluate the resources based on capability, occupancy, or power consumption of the various node or tile resources.

    PACKING CONDITIONAL BRANCH OPERATIONS

    公开(公告)号:US20230052450A1

    公开(公告)日:2023-02-16

    申请号:US17399878

    申请日:2021-08-11

    Abstract: Disclosed in some examples, are systems, methods, devices, and machine readable mediums which use improved dynamic programming algorithms to pack conditional branch instructions. Conditional code branches may be modeled as directed acyclic graphs (DAGs) which have a topological ordering. These DAGs may be used to construct a dynamic programming table to find a partial mapping of one path onto the other path using dynamic programming algorithms.

    Tile-based result buffering in memory-compute systems

    公开(公告)号:US11675588B2

    公开(公告)日:2023-06-13

    申请号:US17407502

    申请日:2021-08-20

    Abstract: A reconfigurable compute fabric can include multiple nodes, and each node can include multiple tiles with respective processing and storage elements. A first tile in a first node can include a processor with a processor output and a first register network configured to receive information from the processor output and information from one or more of the multiple other tiles in the first node. In response to an output instruction and a delay instruction, the register network can provide an output signal to one of the multiple other tiles in the first node. Based on the output instruction, the output signal can include one or the other of the information from the processor output and the information from one or more of the multiple other tiles in the first node. A timing characteristic of the output signal can depend on the delay instruction.

Patent Agency Ranking