Microsemi Solutions (us), Inc.

Texas Instruments Corporation

Pmc-sierra Us, Inc.

Janardan Prasad

David Joseph Clinton

Cheng Yi

Amrendra Kumar

Robert J Nychka

Anil B Dongare

Nilesh Acharya

Aditya Rawal

Ambar Nawaz

Lijish Remani Bal

A power-saving method and circuit in a data processing device comprising a data buffer. Data transfer commands associated with a data source and a data destination are received at the data processing device. The data transfer commands are accumulated until an amount of data associated with the read commands is greater than a predefined threshold. When the amount of data is less than the predefined threshold and the data buffer is empty, the data buffer is signaled to enter or to maintain a power saving mode. When the amount of data is at least the predefined threshold, the data buffer is signaled to exit the power saving mode following a predetermined delay. Processing of the commands and data in respective pipelines is monitored to time exiting of the buffer from the power saving mode for arrival of the data. Power saving mode use and thus power saving are optimized.

Power saving in multi-directional data transfer

The present disclosure provides a method of scheduling data processing at a pipelined data processing engine, and a command scheduler for scheduling data processing at the pipelined data processing engine. The command scheduler determines whether a first data stream is locked to the pipelined data processing engine based on a status of a current data frame of the first data stream in the pipelined data processing engine. The command scheduler will schedule a next data frame of the first data stream to the data processing engine if the first data stream is not locked to the pipelined data processing engine, or it will postpone the scheduling of the next data frame of the first data stream if the first data stream is locked to the pipelined data processing engine.

Method and apparatus for scheduling processing tasks in a pipelined engine

A method and apparatus for handling SGLs for out of order systems is disclosed. The method involves generating multiple Child IOs from an original IO, each Child IO being at the granularity of a storage side memory; generating separate SG lists for each Child IO; and processing each Child IO independently of other Child IOs and in order with each Child IO for data transfer. As each Child IO is generated at the granularity of the storage side memory, the Child IOs can be processed independently of each other and in-order within each Child IO. Thus, an out-of order IO transfer is transformed into an in-order IO transfer.

Apparatus and method for scatter gather list handling for an out of order system

A power-saving method for a first-in-first-out (FIFO) buffer implemented in a memory. The memory is segmented into a plurality of logical segments. For each logical segment, for each power saving mode, a recovery time and recovery overhead to an operational mode, and a transition overhead for transitioning the logical segment into the power saving mode, are determined. During each clock cycle, a determination is made as to whether a net power saving will result by entering each logical segment into a power saving mode based on a minimum time before a read or write pointer will enter the logical segment as well as the recovery time, the recovery overhead, and the transition overhead. The logical segment is transitioned to the power saving mode only if a net power saving will result, and is returned to the operational mode when the minimum time is no longer greater than the recovery time.

Power saving for FIFO buffer without performance degradation

A digital system is provided with a hierarchical memory system having at least a first and second level cache and a higher level memory. If a requested data item misses in both the first cache level and in the second cache level, a line of data containing the requested data is obtained from a higher level of the hierarchical memory system. The line of data is allocated to both the first cache level and to the second cache level simultaneously.

Growing community of inventors

Bengaluru, India

Janardan Prasad