In one embodiment, an apparatus comprises a fabric controller of a first computing node. The fabric controller is to receive, from a second computing node via a network fabric that couples the first computing node to the second computing node, a request to execute a kernel on a field-programmable gate array (FPGA) of the first computing node; instruct the FPGA to execute the kernel; and send a result of the execution of the kernel to the second computing node via the network fabric.

In one embodiment, an apparatus comprises a fabric controller of a first computing node. The fabric controller is to receive, from a second computing node via a network fabric that couples the first computing node to the second computing node, a request to execute a kernel on a field-programmable gate array (FPGA) of the first computing node; instruct the FPGA to execute the kernel; and send a result of the execution of the kernel to the second computing node via the network fabric.

In one embodiment, an apparatus comprises a fabric controller of a first computing node. The fabric controller is to receive, from a second computing node via a network fabric that couples the first computing node to the second computing node, a request to execute a kernel on a field-programmable gate array (FPGA) of the first computing node; instruct the FPGA to execute the kernel; and send a result of the execution of the kernel to the second computing node via the network fabric.

In one embodiment, an apparatus comprises a fabric controller of a first computing node. The fabric controller is to receive, from a second computing node via a network fabric that couples the first computing node to the second computing node, a request to execute a kernel on a field-programmable gate array (FPGA) of the first computing node; instruct the FPGA to execute the kernel; and send a result of the execution of the kernel to the second computing node via the network fabric.

A logic device includes a compare unit at one level of a plurality of levels of a hierarchical structure to be used in sorting of records. The compare unit includes a buffer pair in which one or more buffers of the buffer pair are adapted to store at least one record. The logic device further includes another compare unit on another level of the plurality of levels of the hierarchical structure. The other compare unit includes another buffer pair in which one or more other buffers of the other buffer pair are adapted to store a portion of a record. A size of the one or more other buffers of the other buffer pair is insufficient to store the entire record. The one compare unit and the other compare unit are adapted to sort a plurality of records.

A logic device includes a compare unit at one level of a plurality of levels of a hierarchical structure to be used in sorting of records. The compare unit includes a buffer pair in which one or more buffers of the buffer pair are adapted to store at least one record. The logic device further includes another compare unit on another level of the plurality of levels of the hierarchical structure. The other compare unit includes another buffer pair in which one or more other buffers of the other buffer pair are adapted to store a portion of a record. A size of the one or more other buffers of the other buffer pair is insufficient to store the entire record. The one compare unit and the other compare unit are adapted to sort a plurality of records.

A multichip package may include at least a main die mounted on a substrate. The main die may be coupled to one or more transceiver dies also mounted on the substrate. The main die may include one or more universal interface blocks configured to interface with an on-package memory device or an on-package expansion die, both of which can be mounted on the substrate. The expansion die may include external memory interface (EMIF) components for communicating with off-package memory devices and/or bulk random-access memory (RAM) components for storing large amounts of data for the main die. Smaller input-output blocks such as GPIO (general purpose input-output) or LVDS (low-voltage differential signaling) interfaces may be formed within the core fabric of the main die without causing routing congestion while providing the necessary clock source.

A method of routing interconnects of a field programmable gate array including: a plurality of logic tiles, and a tile-to-tile interconnect network, having a plurality of tile-to-tile interconnects to interconnect logic tile networks of the logic tiles, the method comprises: routing a first plurality of tile-to-tile interconnects in a first plurality of logic tiles. After routing the first plurality of tile-to-tile interconnects, routing a second plurality of tile-to-tile interconnects in a second plurality of logic tiles. The start/end point of each tile-to-tile interconnect in the first plurality and the second plurality of tiles is independent of the start/end point of the other tile-to-tile interconnects in the first and second plurality, respectively. Routing the second plurality of tile-to-tile interconnects includes connecting at least one start/end point of each tile-to-tile interconnect in the second plurality of tiles to at least one start/end point of each interconnect in the first plurality of tiles.

A method of routing interconnects of a field programmable gate array including: a plurality of logic tiles, and a tile-to-tile interconnect network, having a plurality of tile-to-tile interconnects to interconnect logic tile networks of the logic tiles, the method comprises: routing a first plurality of tile-to-tile interconnects in a first plurality of logic tiles. After routing the first plurality of tile-to-tile interconnects, routing a second plurality of tile-to-tile interconnects in a second plurality of logic tiles. The start/end point of each tile-to-tile interconnect in the first plurality and the second plurality of tiles is independent of the start/end point of the other tile-to-tile interconnects in the first and second plurality, respectively. Routing the second plurality of tile-to-tile interconnects includes connecting at least one start/end point of each tile-to-tile interconnect in the second plurality of tiles to at least one start/end point of each interconnect in the first plurality of tiles.

Methods, systems, and apparatus, including a system that includes a first integrated circuit chip configured to store application logic for one or more executable applications; and a second integrated circuit chip communicatively coupled to the first integrated circuit chip, the second integrated circuit chip including an instruction decoder configured to decode instructions for executing the one or more executable applications; and a communication interface configured to transmit the decoded instructions to the first integrated circuit chip to execute the one or more executable applications on the first integrated circuit chip.