International Business Machines Corporation

Micron Technology Incorporated

Michael Grassi

Kirk D Pospesel

Bernard Charles Drerup

Mark Anthony Check

Raymond Michael Higgs

Clinton E Bubb

Howard M Haynie

Tony M Brewer

Luke M Hopkins

Gabriel Martel Tarr

Sundeep Chadha

Alan Frederic Benner

Douglas James Joseph

Philip Jacob

Marcel Schaal

James P Coghlan

Eric N Lais

Bryan D Hornung

Dean E Walker

Donald R DeSota

David M Patrick

Bruce Michael Gilbert

Steven George Aden

Devices and techniques for packet arbitration for buffered packets in a network device are described herein. A packet can be received at an input of the network device. The packet can be placed in a buffer for the input and a characteristic of the packet can be obtained. A record for the packet, that includes the characteristic, is written into a data structure that is independent of the buffer. Arbitration, based on the characteristic of the packet in the record, can then be performed among multiple packets to select a next packet from the buffer for delivery to an output.

Packet arbitration for buffered packets in a network device

Devices and techniques for asynchronous pipeline merging are described herein. An apparatus, includes a memory controller, which includes merge circuitry; where the memory controller chiplet is configured to perform operations including those to: perform a bitwise logical operation on a first logging bit vector and a second logging bit vector to obtain a result vector, wherein the first logging bit vector is associated with a first pipeline and the second logging bit vector is associated with a second pipeline, and wherein bits in respective index positions of the first and second logging bit vectors represent transactions; select a completed transaction from the result vector using a round-robin technique; and forward the completed transaction from the set of completed transactions to an output pipeline.

Asynchronous pipeline merging using long vector arbitration

A chiplet system comprises an interposer including interconnect and multiple chiplets arranged on the interposer and interconnected using the interconnect of the interposer. The multiple chiplets include a throttle level bus source chiplet including a throttle level bus drive interface configured to place a throttle level value onto the throttle level bus, and one or more throttle level bus receiver chiplets operatively coupled to the throttle level bus. Each chiplet of the multiple chiplets includes throttling logic circuitry configured to set a throttle level of a chiplet according to the throttle level value.

Dynamic power and thermal loading in a chiplet-based system

Devices and techniques for pipeline merging in a circuit are described herein. A parallel pipeline result can be obtained for a transaction index of a parallel pipeline. Here, the parallel pipeline is one of several parallel pipelines that share transaction indices. An element in a vector can be marked. The element corresponds to the transaction index. The vector is one of several vectors respectively assigned to the several parallel pipelines. Further each element in the several vectors corresponds to a possible transaction index with respective elements between vectors corresponding to the same transaction index. Elements between the several vectors that correspond to the same transaction index can be compared to determine when a transaction is complete. In response to the transaction being complete, the result can be released to an output buffer in response to the transaction being complete.

Pipeline merging in a circuit

A computer implemented method and system for managing power in a 3D chip stack formed of multiple memory layers each having a plurality memory banks and a plurality of Through-Silicon-Vias (TSVs) connecting the memory banks. The TSVs are arranged in a plurality of subsets, each subset of TSVs connecting a corresponding vertical stack of memory banks aligned across a plurality of memory layers. The method includes determining a power delivery budget for each subset of TSVs connecting the corresponding vertical stack of memory banks based on memory requests, keeping track of memory requests to the memory banks of each vertical stack of memory banks and scheduling the memory requests to the memory banks of each vertical stack of memory banks based on the power budget. The memory controller is configured with a scorecard scheduler to manage the memory requests based on the power budget.

Power aware scheduling of requests in 3D chip stack

A system for managing one or more queues in a multi-processor environment includes a shared memory configured to be accessed by a plurality of processing elements, and a queue manager configured to control a queue in the shared memory, the queue manager storing dynamically configurable queue parameters including an operation address associated with the queue, a number of queue elements and a size of each queue element. The queue manager is configured to intercept a message from a processing element, the message directed to the shared memory and specifying the operation address, calculate an address of a location in the shared memory corresponding to one or more available queue elements, the calculating performed based on the operation address, the number of queue elements, and the size of each queue element, and perform one or more queuing operations on the queue based on the calculated address.

Configurable hardware queue management and address translation

A system for managing one or more queues in a multi-processor environment includes a memory configured to be accessed by a plurality of processing elements, and a queue manager disposed in communication with a plurality of processors and with the memory, the queue manager configured to control a queue in the memory, the queue including a plurality of queue elements, the queue manager configured to intercept a message from a processing element of the plurality of processing elements and perform one or more queuing operations on the queue based on the message. The system also includes a dynamically configurable queue full value maintained by the queue manager, the queue full value being a threshold value that specifies a maximum number of the queue elements that can be written to before a queue full condition is detected, the maximum number based on a number of processing elements.

Hardware queue manager with water marking

A system for managing one or more queues in a multi-processor environment includes a queue manager disposed in communication with a plurality of processors and a memory shared by the plurality of processors, and a queue configured to be controlled by the queue manager, the queue including independent and discrete queue elements and having a starting location specified by a base address, the queue manager having one or more dynamically configurable parameters, the one or more dynamically configurable parameters including a size of each of the queue elements. The queue manager is configured to perform receiving a message from a processor of the plurality of processors, the message including an operation address specifying a fixed storage location in the memory and a request related to accessing the memory, selecting the queue based on the operation address, and performing a queuing operation on the queue based on the request.

Configurable hardware queue management

A memory controller includes ports and corresponding tables. Each port is receptive to one or more memory modules. Each table includes entries mapping memory addresses to the memory modules. Each entry corresponds to no more than one of the memory modules. The tables support asymmetric population of the memory modules within the ports; each port is capable of having a different number of memory modules relative to the other ports. The tables impose no restrictions on where the memory modules are to be inserted within the ports, both number-wise and position-wise. The tables are independently configurable; the configuration of each table is modifiable independently of the configurations of the other tables. Each table is dynamically configurable. The entries of a table are modifiable to reflect changes in the number and type of the memory modules connected, without restarting or temporarily halting the computer system containing the memory controller.

Growing community of inventors

Shokan, NY, United States of America

Michael Grassi