Xilinx, Inc.

Triscend Corporation

James J Murray

Jean-Didier Allegrucci

Nishit Patel

Sagheer Ahmad

Ahmad R Ansari

Ygal Arbel

Ting Lu

Kam-Wing Li

Jeffery H Appelbaum

Jerry A Case

Alex Scott Warshofsky

Kathryn Story Purcell

Hyun Kwon

Methods and systems are disclosed for transferring data using descriptors to reference memory locations at which data is to be written to or read from. Each descriptor references a respective linked list of descriptor blocks. Each of the descriptor blocks includes a contiguous portion of the memory that stores a plurality of addresses, at which data is to be written to or read from. In response to receiving the data transfer request, a set of data is transferred from a first set of addresses specified in a first descriptor to a second set of addresses specified in a second descriptor by traversing the linked lists of descriptor blocks in the first and second descriptors.

Direct memory access descriptor

In an example, a circuit to manage memory between a first and second microprocessors each of which is coupled to a control circuit, includes: first and second memory circuits; and a switch circuit coupled to the first and second memory circuits, and memory interfaces of the first and second microprocessors, the switch circuit having a mode signal as input. The switch is configured to selectively operate in one of a first mode or a second mode based on the mode signal such that, in the first mode, the switch circuit couples the first memory circuit to the memory interface of the first microprocessor and the second memory circuit to the memory interface of the second microprocessor and, in the second mode, the switch circuit selectively couples the first or second memory circuits to the memory interface of either the first or second microprocessor.

Managing memory in a multiprocessor system

Circuits and methods are disclosed that allow devices to control the flow of DMA transfers to or from the devices using a token based protocol. In one example implementation, a DMA circuit includes a transfer control circuit that performs data transfers over a first data channel of a device, when transactions on the first data channel are enabled. The DMA circuit includes a flow control circuit that increments a token count for a data channel of a device when a token for the data channel is received and decrements the token count for each data transfer on the data channel performed by the DMA circuit. The flow control circuit enables data transfers on the data channel when the token count is greater than 0, and otherwise, disables data transfers on the data channel.

Flow control for direct memory access transfers

In approaches for correction of errors introduced in an interconnect circuit, an ECC proxy circuit is coupled between a first interconnect and the second interconnect, and generates for each of the write transactions from a bus master circuit, a first ECC from and associated with data of the write transaction, and transmits the write transaction and associated first ECC on the second interconnect. The ECC proxy circuit also supplements each of the read transactions from the bus master circuit with a reference to a second ECC associated with data referenced by the read transaction. The ECC proxy circuit transmits the read transaction that references the second ECC on the second interconnect. At least one random access memory (RAM) is coupled to the ECC proxy circuit through the second interconnect. The RAM stores data of each write transaction and the first ECC.

Error correction for interconnect circuits

A circuit for enabling access to data is described. The circuit comprises a memory device storing data blocks having a first predetermined size; and a direct memory access circuit coupled to the memory device, the direct memory circuit accessing a data payload having a second predetermined size which is greater than the first predetermined size; wherein the direct memory access circuit accesses the data payload in response to a descriptor having a plurality of addresses corresponding to a predetermined number of the data blocks stored in the memory device. A method of enabling the access to data is also disclosed.

Circuits for and methods of enabling the access to data

In one embodiment, a method for implementing quality of service (QOS) processing in a data bus interface. Each input read/write command is stored in a first-in-first-out queue. Each input read/write command includes a respective QOS value. In response to an input first read/write command having a QOS value higher than the QOS value of the read/write command at a head of the first-in-first-out queue, the QOS value of each of a first number of read/write commands is increased as each read/write command is removed from the head of the first-in-first-out queue.

Method and apparatus for implementing quality of service in a data bus interface

A data bus interface channel controller circuit for an N-bit data bus is described. A FIFO command queue is coupled to receive and buffer one or more commands formatted for M-bit transactions. A FIFO data queue is coupled to receive and buffer N-bit formatted data packets. A first translation circuit is coupled to the FIFO command queue and configured to translate the each commands into a selected one of a plurality of transaction formats. A transmission control circuit is coupled and configured to receive and transmit commands removed from the FIFO command queue. The transmission control circuit is configured to track a number of outstanding transmitted commands and, in response to receiving a command having a transaction format different from the previously received command, delay transmission of commands on the N-bit data bus until the number of outstanding transmitted commands equals zero.

Method and apparatus for implementing a data bus interface

A hardwired core is embedded in an integrated circuit having programmable circuitry. The hardwired core has a microprocessor; a crossbar interconnect coupled to processor local buses of the microprocessor; and a memory controller interface coupled to the crossbar interconnect. The crossbar interconnect provides pipelines for coupling the hardwired core to the programmable circuitry. The microprocessor, the crossbar interconnect, and the memory controller interface are all capable of operating at a first frequency of operation, and the memory controller interface is further capable of being set to operate at a second frequency of operation having an integer ratio with respect to the first frequency of operation. The crossbar interconnect is configured to direct transactions initiated by the microprocessor to the memory controller interface for accessing one or more memory devices coupled to the memory controller interface via a memory controller. Additional or other interfaces may be coupled to the crossbar interconnect.

Processor block ASIC core for embedding in an integrated circuit

A direct memory access engine is described. The direct memory access engine has a transmit channel coupled to a transmit interface, a receive channel coupled to a receive interface, an arbiter coupled to both the transmit channel and the receive channel, and a set of queues coupled to the arbiter. The set of queues has command buffers, transmit buffers, and receive buffers. A direct memory access-to-processor bus interface is coupled to the set of queues. The transmit buffers are for first separate read and write requests. The receive buffers are for second separate read and write requests which are independent of the first separate read and write requests.

Direct memory access engine

Command translation of burst commands is described. A slave processor local bus ('PLB') bridge, part of a processor block core embedded in a host IC, has a data size threshold to allow access to a crossbar switch device. A master device, coupled to the slave PLB bridge, has any of a plurality of command bus widths. A burst command is issued via a command bus, having a command bus width of the plurality, from the master device for the slave PLB bridge. The burst command is converted to a native bus width of the slave processor logic block if the command bus width is not equal to the native bus width. The burst command is translated if execution of the burst command will exceed the data size threshold and passed without the translating if the execution of the burst command will not exceed the data size threshold.

Translation of commands in an interconnection of an embedded processor block core in an integrated circuit

According to one embodiment a system is described. The system includes a direct memory access (DMA) controller and an input/output (I/O) device coupled to the DMA controller. The DMA controller is adaptable to operate in a normal mode and a descriptor mode.

DMA protocol extension for packet-based transfer

A method for ensuring data coherency in buffered direct memory access (DMA) data transfers. The DMA controller realizes the last piece of data is being transferred to the write buffer. The DMA controller then sends a &ldquo;Last Write Data&rdquo; signal to the external memory access arbitration unit. The external memory access arbitration unit then allows completion of all pending memory operations. If a memory request occurs, a wait line is asserted such that memory operations (i.e., reading from, or writing to, the memory) are prevented for all sources other than the DMA channel associated with the &ldquo;Last Write Data&rdquo; signal. The external memory access arbitration unit also grants priority to the DMA channel associated with the &ldquo;Last Write Data&rdquo; signal. This effectively flushes the write buffer and completes the buffered DMA data transfer. The external memory access arbitration unit then deasserts any asserted wait lines and memory operations are no longer prevented.

Methods and apparatuses for guaranteed coherency of buffered direct-memory-access data

The present invention provides a method for breakpoint stepping a multi-bus device. The multi-bus device includes a breakpoint unit capable of detecting bus events on multiple busses. The breakpoint unit is originally programmed to break on the detection of a specified bus event on a bus selected from multiple busses. After the specified bus event has been detected and the device has entered one of several possible frozen states, the breakpoint unit may be programmed to detect a new bus event on a bus selected from multiple busses. The method is repeated as needed to achieve breakpoint stepping, including single stepping.

Method and apparatus for multi-bus breakpoint stepping

The present invention provides a hardware breakpoint unit for a multibus, processor-based, configurable circuit. The multi-bus breakpoint unit connects to and allows tracing of multiple busses and includes the ability to break on the occurrence of a pre-determined bus event on any one of the multiple busses. The multi-bus breakpoint unit can be connected to and programmed by a host debugging system via a port on the target chip.

Universal multi-bus breakpoint unit for a configurable system-on-chip

An integrated circuit including a processor, a processor bus coupled to the processor, a system bus and a trace buffer. The trace buffer may capture activity on either the processor bus or the system bus.

Growing community of inventors

Los Gatos, CA, United States of America

James J Murray