Abstract: The present invention relates a network-on-chip (NoC) system for optimizing data transfer, the system comprising a plurality of nodes including a source node and a destination node; characterized by a plurality of routers attached to the plurality of nodes that route a plurality of data packets from the source node to the destination node; wherein each of the plurality of packets is tagged with a routing information (RINFO), each node is assigned with a node unique identifier (ID) and each router is assigned with a router unique identifier (RID) for each horizontal and vertical routing direction for 2D and 3D interconnect topologies; wherein each of the router comprising at least a pair of ingress port and egress port, a route decoder and an arbiter to support a synchronous, an asynchronous and a source-synchronous operations. The present invention also relates to a method of optimizing data transfer using the NoC system.

Abstract: A device and method of clock synchronization for external memory interface. The device, and method, generating a clock output from a phase lock loop block via a sub-module clocking component; multiplexing the clock output through a global clock into different clock domains; clocking the data and an address or a command path by each clock domain; clocking the phase compensation FIFO by clock domain and clock phase alignment clock; generating the pointer for the phase compensation FIFO from central pointer generator block; and synchronizing the pointer of the adjacent intellectual property module with a parent intellectual property module.

Abstract: An apparatus and a method for synchronizing output clock signals across a plurality of phase-locked loops (PLLs). The apparatus coupled within each PLL comprises: a local counter configured to provide a count when receiving a reference clock signal; a comparator configured to compare the count from the local counter with a predetermined or preconfigured value; wherein a multiplexor connected to the local counter and counters of adjacent PLLs, configured to select the count from the local counter or a count from the counters of the adjacent PLLs; wherein the selected count from the multiplexor is incremented and directed to the local counter; wherein an output clock divider enable is asserted to the PLL to start an output clock divider to generate the output clock signal when the count from the local counter reaches the predetermined or preconfigured value.

Abstract: A circuit system includes an interposer that has a first clock network and first and second integrated circuit dies that are mounted on the interposer. The first integrated circuit die includes a phase detector circuit, an adjustable delay circuit that generates a second clock signal in response to a first clock signal received from the first clock network, and a second clock network that generates a third clock signal in response to the second clock signal. The second integrated circuit die comprises a third clock network that generates a fourth clock signal in response to the first clock signal received from the first clock network. The phase detector circuit controls a delay provided by the adjustable delay circuit to the second clock signal based on a phase comparison between phases of the third and fourth clock signals.

Abstract: 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.

Abstract: A memory sequencer system for external memory protocols including a control center and a microcontroller; a control center network-on-chip having nodes connected point-to-point to synchronize and co-ordinate communication; whereby a command and address sequencer to generate command, control and address commands for specific memory protocols; and at least one data sequencer to generate pseudo-random or deterministic data patterns for each byte lane of a memory interface; wherein said command and address sequencer and said data sequencer are chained to form complex address and data sequences for memory interface training, calibrating and debugging; wherein said control center network-on-chip interconnecting the control center with said command and address sequencer and data sequencer to provide firmware controllability.

Abstract: A memory controller for improving data integrity and providing data security. The memory controller including a transmit data path to transmit write data to a memory device, the transmit data path comprising a scrambling component, wherein the scrambling component includes a scrambling logic and an exclusive OR logic, wherein the write data is divided into a first portion and a second portion, wherein input of the scrambling logic comprises the first portion of the write data and an address associated with the write data to generate a pseudo-random output, and wherein input of the exclusive OR logic comprises the second portion of the write data, the pseudo-random output and a fixed seed corresponding to the first portion of the write data to generate a scrambled data.

Abstract: A generic physical layer providing a unified architecture for interfacing with an external memory device. The physical layer comprises a transmit data path for transmitting a parallel data to the external memory device and a receive data path for receiving a serial data from the external memory device. The generic physical layer is characterized by a receive enable logic for masking strobe of the serial data, wherein the transmit data path and the receive data path each comprising a FIFO circuit, a data rotator and an adjustable-delay logic for delay tuning and a per-bit-deskew for multi-lane support.

Abstract: A generic physical layer providing a unified architecture for interfacing with an external memory device. The physical layer comprises a transmit data path for transmitting a parallel data to the external memory device and a receive data path for receiving a serial data from the external memory device. The generic physical layer is characterized by a receive enable logic for masking strobe of the serial data, wherein the transmit data path and the receive data path each comprising a FIFO circuit, a data rotator and an adjustable-delay logic for delay tuning and a per-bit-deskew for multi-lane support.

Abstract: Systems and methods described herein may relate to data transactions involving a microsector architecture. Control circuitry may organize transactions to and from the microsector architecture to, for example, enable direct addressing transactions as well as batch transactions across multiple microsectors. A data path disposed between programmable logic circuitry of a column of microsectors and a column of row controllers may form a micro-network-on-chip used by a network-on-chip to interface with the programmable logic circuitry.

Abstract: A device and method of clock synchronization for external memory interface. The device, and method, generating a clock output from a phase lock loop block via a sub-module clocking component; multiplexing the clock output through a global clock into different clock domains; clocking the data and an address or a command path by each clock domain; clocking the phase compensation FIFO by clock domain and clock phase alignment clock; generating the pointer for the phase compensation FIFO from central pointer generator block; and synchronizing the pointer of the adjacent intellectual property module with a parent intellectual property module.

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: A I/O transmitter circuitry for supporting multi-modes serialization comprising a serializer, wherein said serializer comprising a multiple FIFO buffers, a multiple flip-flops including a first latch, a second latch, a third flop and a fourth flop, to hold data ready and stage the data for subsequent muxing, a 0-degree shifted clock and a 90-degree shifted clock and a multiplexer, wherein a read pointer reads one bit of data from each of the FIFO buffers, wherein the data is sampled into the respective flip-flops according to frequency of the 0-degree shifted clock and 90-degree shifted clock, wherein the data is outputted by the 0-degree shifted clock and 90-degree shifted clock via the multiplexer.

Abstract: A memory sequencer system for external memory protocols including a control center and a microcontroller; a control center network-on-chip having nodes connected point-to-point to synchronize and co-ordinate communication; whereby a command and address sequencer to generate command, control and address commands for specific memory protocols; and at least one data sequencer to generate pseudo-random or deterministic data patterns for each byte lane of a memory interface; wherein said command and address sequencer and said data sequencer are chained to form complex address and data sequences for memory interface training, calibrating and debugging; wherein said control center network-on-chip interconnecting the control center with said command and address sequencer and data sequencer to provide firmware controllability.

Abstract: A method for dynamically configuring multiple processors based on needs of applications includes receiving, from an application, an acceleration request message including a task to be accelerated. The method further includes determining a type of the task and searching a database of available accelerators to dynamically select a first accelerator based on the type of the task. The method further includes sending the acceleration request message to a first acceleration interface located at a configurable processing circuit. The first acceleration interface sends the acceleration request message to a first accelerator, and the first accelerator accelerates the task upon receipt of the acceleration request message.

Abstract: A multichip package having a main die coupled to one or more daughter dies is provided. The main die may include embedded universal interface blocks (UIB) each of which can be used to interface with a corresponding daughter die to support high bandwidth parallel or serial communications. Each UIB may include an integrated processor subsystem and associated pattern sequencing logic to perform interface initialization and margining operations. Each UIB may perform simultaneous accesses to a daughter die across one or more channels. Each UIB may also include multiple phase-locked loop circuits for providing different clock signals to different portions of the UIB and a 2x clock phase generation logic. Each UIB may include multiple IO modules, each of which may optionally include its own duty cycle correction circuit. Each IO module may include buffer circuits, each of which may have a de-emphasis control logic for adjusting buffer drive strength.

Abstract: Systems and methods for an interface with a widened interface-to-fabric shoreline between semiconductor circuits and a narrower interface-to-memory controller shoreline. The interface providing transitions from a first clock of a first circuit (e.g., field-programmable gate array (FPGA)), a second clock of a second circuit (e.g., high-bandwidth memory generation 2 (HBM2) stack, and a third clock of a physical layer of the second circuit. A first transfer between the first clock and the second clock may use a first set of first-in first-outs (FIFO) buffers, such as rate-matching FIFO buffers. A second transfer between the second clock and the third clock may use a second set of FIFO buffers, such as phase compensation FIFOs.

Abstract: A memory controller system comprising a scheduling module; wherein a data buffer module; a global order buffer module; and a linked-list controlling module to receive and process a first command comprising a write command or a read command; wherein the linked-list controlling module constructs at least one linked-list head based on scheduling dependencies and determines whether the first command is dependency-hit by comparing the first command with the existing commands buffered in the global order buffer module; whereby in a case that the first command is dependency-hit, the linked-list controlling module is configured to trigger a write merging process or a read snarfing process.

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 multichip package having a main die coupled to one or more daughter dies is provided. The main die may include embedded universal interface blocks (UIB) each of which can be used to interface with a corresponding daughter die to support high bandwidth parallel or serial communications. Each UIB may include an integrated processor subsystem and associated pattern sequencing logic to perform interface initialization and margining operations. Each UIB may perform simultaneous accesses to a daughter die across one or more channels. Each UIB may also include multiple phase-locked loop circuits for providing different clock signals to different portions of the UIB and a 2× clock phase generation logic. Each UIB may include multiple IO modules, each of which may optionally include its own duty cycle correction circuit. Each IO module may include buffer circuits, each of which may have a de-emphasis control logic for adjusting buffer drive strength.