Arbitrating among portions of multiple transactions and transmitting a winning portion over one of a multiplicity of virtual channels associated with an interconnect on a clock cycle-by-clock cycle basis. By repeatedly performing the above each clock cycle, winning portions are interleaved and transmitted over the multiplicity of virtual channels over multiple clock cycles respectively.

Arbitrating among portions of multiple transactions and transmitting a winning portion over one of a multiplicity of virtual channels associated with an interconnect on a clock cycle-by-clock cycle basis. By repeatedly performing the above each clock cycle, winning portions are interleaved and transmitted over the multiplicity of virtual channels over multiple clock cycles respectively.

Techniques in electronic systems, such as in systems comprising a CPU die and one or more external mixed-mode (analog) chips, may provide improvements advantages in one or more of system design, performance, cost, efficiency and programmability. In one embodiment, the CPU die comprises at least one microcontroller CPU and circuitry enabling the at least one CPU to have a full and transparent connectivity to an analog chip as if they are designed as a single chip microcontroller, while the interface design between the two is extremely efficient and with limited in number of wires, yet may provide improved performance without impact to functionality or the software model.

The technology disclosed relates to interconnect-based resource allocation for reconfigurable processors. In particular, the technology disclosed relates to a runtime logic that is configured to receive target interconnect bandwidth and target interconnect latency, and rated interconnect bandwidth and rated interconnect latency. The runtime logic is further configured to respond by allocating, to configuration files defining an application graph, processing elements in a plurality of processing elements, and interconnects between the processing elements, and executing the configuration files using the allocated processing elements and the allocated interconnects.

A storage system includes a NAND storage media and a nonvolatile storage media as a write buffer for the NAND storage media. The write buffer is partitioned, where the partitions are to buffer write data based on a classification of a received write request. Write requests are placed in the write buffer partition with other write requests of the same classification. The partitions have a size at least equal to the size of an erase unit of the NAND storage media. The write buffer flushes a partition once it has an amount of write data equal to the size of the erase unit.

A high bandwidth non-volatile memory (NVM) is described suitable for providing neural network weight data to an AI accelerator processing core or cores. An artificial intelligence (AI) inference memory device employing the high bandwidth NVM technology as described herein can comprise a logic layer die including channel logic implementing connections between a plurality of channels for conducting data to and from an accelerator core via a bus and a plurality of non-volatile memory (NVM) dies stacked vertically one above another, forming a layered vertical stack of NVM dies, each of the NVM dies including at least one memory chip and a plurality of direct vertical connections to a corresponding channel in the logic layer.

The disclosed technology relates to link-based resource allocation for a pool of reconfigurable processors. Resource allocation is provided for reconfigurable processors based on link bandwidths and link latencies. Runtime logic receives target link bandwidth and target link latency and rated link bandwidth and rated link latency. In response, the runtime logic allocates configuration files for an application, reconfigurable processors, and links between the processors. The runtime logic executes the allocated configuration files using the allocated processors and the allocated links. In another embodiment, the pool of reconfigurable processors comprise a cluster of processing nodes connected through a network.

Described herein are embodiments of an apparatus configured for dynamic link width modulation, a system including an apparatus configured for dynamic link width modulation, a method for dynamic link width modulation, and computer-readable media having instructions that, if executed by one or more processors, cause an apparatus to perform a dynamic link width modulation method. An apparatus configured for dynamic link width modulation may include a first counter for determining a length of a queue of packets at a source of a link, a second counter for determining a rate of utilization of the link, and a power control unit configured to modify a width of the link based at least in part on the length of the queue and the rate of utilization. Other embodiments may be described and/or claimed.

Techniques in electronic systems, such as in systems comprising a CPU die and one or more external mixed-mode (analog) chips, may provide improvements advantages in one or more of system design, performance, cost, efficiency and programmability. In one embodiment, the CPU die comprises at least one microcontroller CPU and circuitry enabling the at least one CPU to have a full and transparent connectivity to an analog chip as if they are designed as a single chip microcontroller, while the interface design between the two is extremely efficient and with limited in number of wires, yet may provide improved performance without impact to functionality or the software model.

A storage system includes a NAND storage media and a nonvolatile storage media as a write buffer for the NAND storage media. The write buffer is partitioned, where the partitions are to buffer write data based on a classification of a received write request. Write requests are placed in the write buffer partition with other write requests of the same classification. The partitions have a size at least equal to the size of an erase unit of the NAND storage media. The write buffer flushes a partition once it has an amount of write data equal to the size of the erase unit.