Abstract: A programmable device may have logic circuitry formed in a top die and memory and specialized processing blocks formed in a bottom die, where the top die is stacked directly on top of the bottom die in a face-to-face configuration. The logic circuitry may include logic sectors, logic array blocks, logic elements, and other types of logic regions. The memory blocks may include large banks of multiport memory for storing data. The specialized processing blocks may include multipliers, adders, and other arithmetic components. The logic circuitry may access the memory and specialized processing blocks via an address encoded scheme. Configured in this way, the maximum operating frequency of the programmable device can be optimized such that critical paths will no longer need to traverse any unused memory and specialized processing blocks.

Abstract: An IC includes first, second, and third IOs, and a multiplexer that includes first and second inputs, and an output. The IC includes first and second transmitters respectively having an output coupled to the first IO and an output coupled to the second IO. A clock generator is coupled between the output and an input of the first transmitter and between the output and an input of the second transmitter. The first input may receive a clock signal generated by the first clock generator and the second clock input is coupled to the third IO and may receive a clock signal via the third IO element from another IC. An IC includes a programmable fabric, k*n wires coupled to and extending from the fabric, n TDMs, and n IO blocks. Each TDM includes k inputs coupled to k wires and an output coupled to one of the IO blocks.

Abstract: An integrated circuit package may include a semiconductor die on a first side of the integrated circuit package, a first ball grid array (BGA) connection on the first side of the integrated circuit package, and a second BGA connection on a second side of the integrated circuit package. The integrated circuit package may include one or more traces that route data from the first BGA connection and the second BGA connection.

Abstract: Techniques described herein may relate to providing a programmable interconnect network (e.g., a programmable network-on-chip (NOC)). A method may include determining a transmission parameter, bonding one or more channels of an interconnect network based at least in part on the transmission parameter, and power-gating any unused channels after the bonding.

Abstract: An integrated circuit package may be formed comprising an interposer with a center die and a plurality of identical integrated circuit dice positioned around the center die and attached to the interposer, wherein the center die is the switch/router for the plurality of identical integrated circuit dice. The interposer comprises a substrate, a central pattern of bond pads formed in or on the substrate for attaching the center die, and substantially identical satellite patterns formed in or on the substrate for attaching identical integrated circuit dice. The central pattern of bond pads has repeating sets of a specific geometric pattern and wherein the identical satellite patterns of bond pads are positioned to form the same geometric pattern as the specific geometric pattern of the central pattern of bond pads. Thus, substantially identical conductive routes may be formed between the center die and each of the identical integrated circuit dice.

Abstract: An integrated circuit structure that includes a first integrated circuit package and a second integrated circuit package is described. The two packages can be stacked above, for example, a printed circuit board. The top package is inverted, such that a first die of that top package is facing a second die of the bottom package. A cooling arrangement is in a gap between the first and second integrated circuit packages, and is thermally coupled to the first and second die. The cooling arrangement is to transfer heat generated by a first die of the first integrated circuit package and a second die of the second integrated circuit package. In some cases, structures comprising electrically conductive material (e.g., metal) are encapsulated by a molding compound or insulator, and extend between a first substrate of the first integrated circuit package and a second substrate of the second integrated circuit package.

Abstract: Systems and methods related to multi-die integrated circuits that may include dies having high-speed core interconnects. The high-speed core interconnects may be used to directly connect two adjacent dies.

Abstract: Techniques described herein may relate to providing a programmable interconnect network (e.g., a programmable network-on-chip (NOC)). A method may include determining a transmission parameter, bonding one or more channels of an interconnect network based at least in part on the transmission parameter, and power-gating any unused channels after the bonding.

Abstract: Systems or methods of the present disclosure may improve scalability (e.g., component scalability, product variation scalability) of integrated circuit systems by disaggregating periphery intellectual property (IP) circuitry into modular periphery IP tiles that can be installed as modules. Such an integrated circuit system may include a first die that includes programmable fabric circuitry and a second die that that includes a periphery IP tile. The periphery IP tile may be disaggregated from the programmable fabric die and may be communicatively coupled to the first die via a modular interface.

Abstract: Embodiments disclosed herein include electronic packages. In an embodiment, the electronic package comprises, a package substrate, an interposer on the package substrate, a first die cube and a second die cube on the interposer, wherein the interposer includes conductive traces for electrically coupling the first die cube to the second die cube, a die on the package substrate, and an embedded multi-die interconnect bridge (EMIB) in the package substrate, wherein the EMIB electrically couples the interposer to the die.

Abstract: A programmable device may have logic circuitry formed in a top die and memory and specialized processing blocks formed in a bottom die, where the top die is stacked directly on top of the bottom die in a face-to-face configuration. The logic circuitry may include logic sectors, logic array blocks, logic elements, and other types of logic regions. The memory blocks may include large banks of multiport memory for storing data. The specialized processing blocks may include multipliers, adders, and other arithmetic components. The logic circuitry may access the memory and specialized processing blocks via an address encoded scheme. Configured in this way, the maximum operating frequency of the programmable device can be optimized such that critical paths will no longer need to traverse any unused memory and specialized processing blocks.

Abstract: Embodiments of the invention include a stacked die system and methods for forming such systems. In an embodiment, the stacked die system may include a first die. The first die may include a device layer and a plurality of routing layers formed over the device layer. The plurality of routing layers may be segmented into a plurality of sub regions. In an embodiment no conductive traces in the plurality of routing layers pass over a boundary between any of the plurality of sub regions. In an embodiment, the stacked die system may also include a plurality of second dies stacked over the first die. According to an embodiment, at least a two of the second dies are communicatively coupled to each other by a die to die interconnect formed entirely within a single sub region in the first die.

Abstract: Systems and methods related to multi-die integrated circuits that may include dies having high-speed core interconnects. The high-speed core interconnects may be used to directly connect two adjacent dies.

Abstract: A central processing unit (CPU) may be directly coupled to an accelerator dual in-line memory module (DIMM) card that is plugged into a DIMM slot. The CPU may include a master memory controller that sends requests or offloads tasks to the accelerator DIMM card via a low-latency double data rate (DDR) interface. The acceleration DIMM card may include a slave memory controller for translating the received requests, a decoder for decoding the translated requests, control circuitry for orchestrating the data flow within the DIMM card, hardware acceleration resources that can be dynamically programmed to support a wide variety of custom functions, and input-output components for interfacing with various types of non-volatile and/or volatile memory and for connecting with other types of storage and processing devices.

Abstract: A package substrate and a package assembly including a package substrate including a substrate body including a plurality of first contact points on a surface thereof configured for electrical connection to a first die and a plurality of second contact points on the surface configured for electrical connection to a second die; and a bridge coupled to the substrate body, the bridge including active device circuitry that is coupled to ones of the plurality of first contact points and ones of the plurality of second contact points. A method of forming a package assembly including coupling a first die to a package substrate, the package substrate including a bridge substrate including active device circuitry; and coupling a second die to the package substrate, wherein coupling the first die and the second die to the package substrate includes coupling the first die and the second die to the active circuitry.

Abstract: Systems or methods of the present disclosure may improve scalability (e.g., component scalability, product variation scalability) of integrated circuit systems by disaggregating periphery intellectual property (IP) circuitry into modular periphery IP tiles that can be installed as modules. Such an integrated circuit system may include a first die that includes programmable fabric circuitry and a second die that that includes a periphery IP tile. The periphery IP tile may be disaggregated from the programmable fabric die and may be communicatively coupled to the first die via a modular interface.

Abstract: Systems and method include one or more die coupled to an interposer. The interposer includes interconnection circuitry configured to electrically connect the one or more die together via the interposer. The interposer also includes translation circuitry configured to translate communications as they pass through the interposer. For instance, in the interposer, the translation circuitry translates communications, in the interposer, from a first protocol of a first die of the one or more die to a second protocol of a second die of the one or more die.

Abstract: A programmable device may have logic circuitry formed in a top die and memory and specialized processing blocks formed in a bottom die, where the top die is stacked directly on top of the bottom die in a face-to-face configuration. The logic circuitry may include logic sectors, logic array blocks, logic elements, and other types of logic regions. The memory blocks may include large banks of multiport memory for storing data. The specialized processing blocks may include multipliers, adders, and other arithmetic components. The logic circuitry may access the memory and specialized processing blocks via an address encoded scheme. Configured in this way, the maximum operating frequency of the programmable device can be optimized such that critical paths will no longer need to traverse any unused memory and specialized processing blocks.

Abstract: A programmable device may have logic circuitry formed in a top die and memory and specialized processing blocks formed in a bottom die, where the top die is stacked directly on top of the bottom die in a face-to-face configuration. The logic circuitry may include logic sectors, logic array blocks, logic elements, and other types of logic regions. The memory blocks may include large banks of multiport memory for storing data. The specialized processing blocks may include multipliers, adders, and other arithmetic components. The logic circuitry may access the memory and specialized processing blocks via an address encoded scheme. Configured in this way, the maximum operating frequency of the programmable device can be optimized such that critical paths will no longer need to traverse any unused memory and specialized processing blocks.

Abstract: A multi-chip packaged device may include a first integrated circuit die with a first integrated circuit, such that the first integrated circuit may include a first plurality of ports disposed on a first side and a second plurality of ports disposed on a second side of the first integrated circuit die. The multi-chip packaged device may also include a second integrated circuit die, such that the second integrated circuit may include a third plurality of ports disposed on a third side of the second integrated circuit die. The first integrated circuit may communicate with the first side of the second integrated circuit when placed adjacent to the first side and communicate with the second side of the first integrated circuit die when placed adjacent to the second side.