Patents Assigned to Applied Micro Circuits Corporation
-
SYSTEMS AND METHODS FACILITATING MULTI-WORD ATOMIC OPERATION SUPPORT FOR SYSTEM ON CHIP ENVIRONMENTS
Publication number: 20150324133Abstract: Systems and methods that facilitate multi-word atomic operation support for systems on chip are described. One method involves: receiving an instruction associated with a calling process, and determining a first memory width associated with execution of the instruction based on an operator of the instruction and a width of at least one operand of the instruction. The instruction can be associated with an atomic operation. In some embodiments, the instruction contains a message having a first field identifying the operator and a second field identifying the operand.Type: ApplicationFiled: April 29, 2014Publication date: November 12, 2015Applicant: APPLIED MICRO CIRCUITS CORPORATIONInventor: Millind Mittal -
Publication number: 20150323956Abstract: Various aspects provide for generating a timeout signal based on a clock counter associated with a data request. An interface component is configured for receiving a data request from a master device and forwarding the data request to a slave device. A timeout component is configured for maintaining a clock counter associated with the data request and generating a timeout signal in response to a determination that a threshold level associated with the clock counter is reached before receiving a data response associated with the data request from the slave device.Type: ApplicationFiled: February 27, 2014Publication date: November 12, 2015Applicant: APPLIED MICRO CIRCUITS CORPORATIONInventors: Ayush Goyal, Phil Mitchell
-
Publication number: 20150317158Abstract: A system and method are provided for simplifying load acquire and store release semantics that are used in reduced instruction set computing (RISC). Translating the semantics into micro-operations, or low-level instructions used to implement complex machine instructions, can avoid having to implement complicated new memory operations. Using one or more data memory barrier operations in conjunction with load and store operations can provide sufficient ordering as a data memory barrier ensures that prior instructions are performed and completed before subsequent instructions are executed.Type: ApplicationFiled: April 3, 2014Publication date: November 5, 2015Applicant: APPLIED MICRO CIRCUITS CORPORATIONInventors: Matthew Ashcraft, Christopher Nelson
-
Patent number: 9170642Abstract: Systems and methods are provided that facilitate power management in a processing device. The system contains a power management component and a coupled to the processing device. The power management component determines and input rate and target voltages and/or frequency. The power management component can scale voltages and/or frequencies based on target voltages and/or frequencies. Accordingly, power consumption can be reduced and processing devices can be more efficient.Type: GrantFiled: March 21, 2013Date of Patent: October 27, 2015Assignee: Applied Micro Circuits CorporationInventors: Kjeld P. Svendsen, Arun Jangity
-
Patent number: 9172578Abstract: A transceiver architectures can comprises an encoder and a decoder for communicating high speed transmissions. The encoder can modulate signal data for being mapped in a constellation that is generated based on a leech lattice. The data can be transmitted at a high speed according to the constellation with an embedded leech lattice configuration in order to generate a coding gain. A decoder operates to decode the received input signal data with a decreased latency or a minimal latency with a high spectral efficiency.Type: GrantFiled: August 22, 2014Date of Patent: October 27, 2015Assignee: Applied Micro Circuits CorporationInventor: Dariush Dabiri
-
Patent number: 9158713Abstract: A system and method are provided for evenly distributing central processing unit (CPU) packet processing workloads. The method accepts packets for processing at a port hardware module port interface. The port hardware module supplies the packets to a direct memory access (DMA) engine for storage in system memory. The port hardware module also supplies descriptors to a mailbox. Each descriptor identifies a corresponding packet. The mailbox has a plurality of slots, and loads the descriptors into empty slots. There is a plurality of CPUs, and each CPU fetches descriptors from assigned slots in the mailbox. Then, each CPU processes packets in the system memory in the order in which the associated descriptors are fetched. A load balancing module estimates each CPU workload and reassigns mailbox slots to CPUs in response to unequal CPU workloads.Type: GrantFiled: May 3, 2010Date of Patent: October 13, 2015Assignee: Applied Micro Circuits CorporationInventors: Keyur Chudgar, Vinay Ravuri, Loc Nhin Ho
-
Patent number: 9152661Abstract: System and method for searching a data structure are disclosed. The method includes providing a data structure that includes a plurality of data entries stored in an external random access memory (RAM) and a portion of the data structure is stored in an internal cache memory, performing one or more hash functions on each entry of the data structure to generate an encoding that maps to a location in the external RAM, maintaining a count of encodings that map to the location in the external RAM, receiving a search string, performing the one or more hash functions on the search string to generate an index to the count of encodings, and searching the data structure in accordance with the count of encodings stored in the internal cache memory and in the external RAM.Type: GrantFiled: October 21, 2011Date of Patent: October 6, 2015Assignee: Applied Micro Circuits CorporationInventors: Satish Sathe, Rajendra Marulkar, Sagar Vaishampayan
-
Patent number: 9146677Abstract: The described systems and methods can facilitate efficient and effective information storage. In one embodiment a system includes a hash component, a queue request order component and a request queue component. The hash component is operable to hash a request indication. The queue request order component is operable to track a queue request order. The request queue component is operable to queue and forward requests in accordance with direction from the queue request order component. In one embodiment, the storage component maintains a request without stalling a request in an aliasing condition.Type: GrantFiled: January 28, 2013Date of Patent: September 29, 2015Assignee: Applied Micro Circuits CorporationInventor: Kjeld Svendsen
-
Patent number: 9142286Abstract: A device (e.g., an integrated circuit memory device such as a static random access memory device) includes word line drivers. Each of the word line drivers includes a pull-up device that is coupled to a node via a shared line. A precharge device is coupled between a power supply and the node. The precharge device and a pull-up device for a selected word line driver are controlled to allow the power supply to charge the node and then to allow the charge stored in the node to flow into a word line corresponding to the selected word line driver.Type: GrantFiled: April 15, 2013Date of Patent: September 22, 2015Assignee: Applied Micro Circuits CorporationInventors: Jason T Su, Jitendra Khare
-
Patent number: 9088357Abstract: Methods and systems for facilitating alignment of optical systems and optoelectronic systems are disclosed here. The methods and systems include passively detecting images, determining relative positions of components and aligning components. An imaging component can detect images and determine relative positions and repositioning instructions.Type: GrantFiled: October 26, 2012Date of Patent: July 21, 2015Assignees: APPLIED MICRO CIRCUITS CORPORATION, VOLEX PLCInventors: Benoit Sevigny, Ezra Gold
-
Patent number: 9071262Abstract: Techniques for calibration of high-speed interleaved analog-to-digital converter (ADC) arrays are presented. A transceiver comprises an ADC component that comprises an array of sub-ADCs that can be interleaved to facilitate high-speed data communications. The ADC component processes signals received from a remote transmitter to facilitate recovering the received data. The transceiver can comprise a calibration component that determines transfer characteristics of the communication channel or medium between the transceiver and the remote transmitter, and the transfer characteristics of the remote transmitter to each of the sub-ADCs of the array, based on the recovered data.Type: GrantFiled: January 24, 2014Date of Patent: June 30, 2015Assignee: Applied Micro Circuits CorporationInventor: Moshe Malkin
-
Patent number: 9065610Abstract: Systems and methods for smoothing jitter generated by byte stuffing. A frequency synthesizer comprises a smoothing logic coupled with a PLL. The smoothing logic is configured to modify a phase error signal generated by a phase frequency detector into a distributed phase error signal that spread over multiple clock cycles. The distributed phase error signal is used to drive a DCO. The smoothing logic may comprise a ramping logic operable to generate a series of ramping values to substitute a phase difference in the phase error signal. The phase difference may correspond to a stuffing byte.Type: GrantFiled: April 18, 2013Date of Patent: June 23, 2015Assignee: Applied Micro Circuits CorporationInventors: Yehuda Azenkot, Timothy P. Walker
-
Patent number: 9059723Abstract: Provided is a digital-to-analog converter configured to mitigate data dependent jitter of switch driver signals. The digital-to-analog converter is configured to produce data patterns of “0001000”. The digital-to-analog converter includes a digital portion that includes a digital data input component, an analog portion, and a conversion component. The conversion component includes a decoder configured to split a first data stream comprising a set of digital data into a first data sub-stream and a second data sub-stream, and a second data stream comprising another set of digital data into a third data sub-stream and a fourth data sub-stream. The conversion component also includes a first pair of drivers, a second pair of drivers, a third pair of drivers, and a fourth pair of drivers, wherein respective drivers of the first, second, third, and fourth pairs of drivers are configured to output respective data patterns comprising at least three consecutive identical bits.Type: GrantFiled: August 22, 2014Date of Patent: June 16, 2015Assignee: Applied Micro Circuits CorporationInventors: Ramesh Kumar Singh, Tarun Gupta
-
Patent number: 9058284Abstract: Method and apparatus for performing table lookup are disclosed. In one embodiment, the method includes providing a lookup table, where the lookup table includes a plurality of translation modes and each translation mode includes a corresponding translation table tree supporting a plurality of page sizes. The method further includes receiving a search request from a requester, determining a translation table tree for conducting the search request, determining a lookup sequence based on the translation table tree, generating a search output using the lookup sequence, and transmitting the search output to the requester. The plurality of translation modes includes a first set of page sizes for 32-bit operating system software and a second set of page sizes for 64-bit operating system software. The plurality of page sizes includes non-global pages, global pages, and both non-global and global pages.Type: GrantFiled: March 16, 2012Date of Patent: June 16, 2015Assignee: Applied Micro Circuits CorporationInventors: Amos Ben-Meir, John Gregory Favor
-
Publication number: 20150160945Abstract: Various aspects provide for detecting ordering violations in a memory system. A system includes a prediction component and an execution component. The prediction component predicts whether a load instruction in the system is associated with an instruction pipeline hazard. The execution component allocates the load instruction to a queue buffer in the system in response to a prediction that the load instruction is not associated with the instruction pipeline hazard.Type: ApplicationFiled: December 9, 2013Publication date: June 11, 2015Applicant: APPLIED MICRO CIRCUITS CORPORATIONInventors: Matthew Ashcraft, Richard W. Thaik
-
Publication number: 20150163024Abstract: Systems and methods for multi-channel signal processing by a series of single processing core logic circuitries in time-slicing. A first logic circuitry is configured to process multiple data streams from multiple channels in a first cycle-based time-sliced schedule. A time slice in the first cycle-based time-sliced schedule comprises a predetermined number of clock cycles allocated to a corresponding data stream. A second logic circuitry is coupled to the first logic circuitry and configured to process the data streams in a first fragment-based time-sliced schedule. A time slice in the first fragment-based time-sliced schedule is determined based on a predetermined boundary associated with the data fragment and is allocated to process a data fragment of the data streams.Type: ApplicationFiled: December 6, 2013Publication date: June 11, 2015Applicant: Applied Micro Circuits CorporationInventor: Dimitri MAVROIDIS
-
Publication number: 20150150009Abstract: Systems and methods for multi-channel signal processing by virtue of packet-based time-slicing with single processing core logic. The processing core logic is configured to receive data streams from the multiple communication channels at a data processing unit, and process data fragments of the data streams in a time-sliced manner. The processing core logic can switch from processing a first data fragment of a first data stream to processing a first data fragment of a second data stream at an end of a time slice, wherein the time slice is determined by a fragment boundary associated with the data fragment of the first data stream.Type: ApplicationFiled: November 26, 2013Publication date: May 28, 2015Applicant: Applied Micro Circuits CorporationInventor: Dimitri MAVROIDIS
-
Patent number: 9032152Abstract: Systems and methods are provided that facilitate cache miss detection in an electronic device. The system contains a probabilistic filter coupled to the processing device. A probing component determines existence of an entry associated with a request. The probing component can communicate a miss token without the need to query a cache. Accordingly, power consumption can be reduced and electronic devices can be more efficient.Type: GrantFiled: March 22, 2013Date of Patent: May 12, 2015Assignee: Applied Micro Circuits CorporationInventors: Kjeld Svendsen, Gaurav Singh
-
Patent number: 9025711Abstract: Techniques for fast filtering for a transceiver are presented. A multidimensional filter processor component (MDFPC) can perform configurations and adaptations of multiple digital filters of a transceiver. The MDFPC can treat multiple, separate filters of a transceiver as a single larger multidimensional filter, and jointly update the multiple filters in a single adaptation operation instead of performing multiple adaptation operations on multiple filters. To facilitate multidimensional filter adaptation, the MDFPC can manage respective cross-correlations associated with the inputs of the filters. The MDFPC can facilitate multidimensional filter adaptation by performing multidimensional filter adaptation in the frequency domain, wherein the adaptation can be performed in parallel for multiple frequency sub-channels.Type: GrantFiled: August 13, 2013Date of Patent: May 5, 2015Assignee: Applied Micro Circuits CorporationInventor: Moshe Malkin
-
Publication number: 20150110233Abstract: Systems and methods for efficient jitter mitigation or removal from a gapped signal. A phase mitigation module is employed to generate discrete correction values for modifying phase error signals detected between a gapped signal and a feedback signal of the PLL. The correction values can be digitally subtracted from the output of a phase frequency detector associated with the PLL. The sequence of correction values can be determined based on phase frequency differences between the input signal and a targeted feedback signal that is free of jitter and has a period equal to an average period of the input signal. An average of the correction values is substantially equal to zero, and an average of the modified phase error signal is substantially equal to zero.Type: ApplicationFiled: October 23, 2013Publication date: April 23, 2015Applicant: Applied Micro Circuits CorporationInventors: Yehuda AZENKOT, Timothy P. Walker