Abstract: A system includes a plurality of bus masters that generate direct memory access requests to access a protected memory device. Before granting the access, the system checks for memory protection information stored in a cache. The cache is shared by the bus masters and allocation of the cache entries is prioritized among the bus masters.

Abstract: A memory allocation method and terminal for supporting Direct Memory Access (DMA) are provided. The terminal includes a memory for storing data used for operations of the terminal, a plurality of devices for executing applications for specific functions, a control unit for defining, when the terminal boots up, a virtual zone dedicated for the DMA in the memory, and a DMA unit for controlling the DMA of the devices.

Abstract: A dual or triple access interface (e.g., hardware and software implementation) allows a CPU and at least one DMA peripheral, e.g., Universal Serial Bus (USB) DMA engine, to transfer data in and/or out of a common single port SRAM by negotiating access requests between the CPU and the DMA peripheral, and then subsequently forms memory cycles to the single port SRAM to satisfy both the CPU's and DMA peripheral's memory access throughput requirements. This allows the CPU and the at least one DMA peripheral to access a shared single port SRAM by time multiplexing granted accesses between, for example, two or three simultaneous memory access requests, thus eliminating the need for a dual port memory.

Abstract: An infrastructure element can receive a first DMA request including a first address and the data, generate a meta request that comprises a resource key value and a doorbell address, and transmit the meta request via the infrastructure using the doorbell address. A remote DMA adapter can receive the meta request at the doorbell address and generate a remote direct memory access request message using the resource key, the first address and the data from the received meta request.

Abstract: The image processing apparatus (data processing apparatus) stores data in a storing unit (storing means), inputs and outputs the data to and from the storing unit via a storage control unit (input-output means) and processes the data outputted from the storing unit with a control unit (processing means). The storage control unit inputs and outputs image data to and from the storing unit by the DMA method through a path via a DMA control unit and inputs and outputs other data such as a control instruction to and from the storing unit by the PIO method through a path via a PIO control unit. Image data to be inputted and outputted to and from the storing unit by the DMA method is encrypted in an input operation and decrypted in an output operation by an encryption/decryption unit provided on the input-output path for DMA method.

Abstract: A direct memory access system utilizing a local memory that stores a plurality of DMA command lists, each comprising at least one DMA command. A command queue can hold a plurality of entries, each entry comprising a pointer field and a sequence field. The pointer field points to one of the DMA command lists. The sequence field holds a sequence value. A DMA engine accesses an entry in the command queue and then accesses the DMA commands of the DMA command list pointed to by the pointer field of the accessed entry. The DMA engine performs the DMA operations specified by the accessed DMA commands. The DMA engine makes available the sequence value held in the sequence field of the accessed entry when all of the DMA commands in the accessed command list have been performed. In one embodiment, the command queue is part of the DMA engine.

Abstract: A control machine which uses a data amount stored in an FIFO as a trigger and allows a DMA transfer to be started according to a capacity of the FIFO allows a control machine for preparing for the DMA transfer to start to prepare a command and the like for the DMA transfer. The control machine for preparing for the DMA transfer issues the prepared command to a control machine for transferring DMA data, so that a process according to the command is started. At the time of the DMA transfer, a burden on a host CPU is reduced.

Abstract: An inkjet print control apparatus connected with a processor and a memory through a bus. The memory stores print image data. The inkjet print control apparatus fetches the print image data stored in the memory for further data operation in order to drive one or more inkjet heads. The inkjet print control apparatus includes a DMA controller, an instruction RAM and a capture processor. The instruction RAM stores a capture instruction for the print image data fetched. The capture processor is connected to the instruction RAM and the DMA controller for computing an address accessed by the DMA controller to the memory according to the capture instruction. The DMA controller accesses the print image data according to the address.

Abstract: A Multi-Media Card/Secure Digital (MMC/SD) single-chip flash device contains a MMC/SD flash microcontroller and flash mass storage blocks containing flash memory arrays that are block-addressable rather than randomly-addressable. MMC/SD transactions from a host MMC/SD bus are read by a bus transceiver on the MMC/SD flash microcontroller. Various routines that execute on a CPU in the MMC/SD flash microcontroller are activated in response to commands in the MMC/SD transactions. A flash-memory controller in the MMC/SD flash microcontroller transfers data from the bus transceiver to the flash mass storage blocks for storage. Rather than boot from an internal ROM coupled to the CPU, a boot loader is transferred by DMA from the first page of the flash mass storage block to an internal RAM. The flash memory is automatically read from the first page at power-on. The CPU then executes the boot loader from the internal RAM to load the control program.

Abstract: In one embodiment, an input/output (I/O) node comprises an I/O memory management unit (IOMMU) configured to translate memory requests. The I/O node is configured to couple to an interconnect and to operate as a tunnel on the interconnect, and wherein the IOMMU is configured translate memory requests passing through the tunnel in the upstream direction. In another embodiment, a system comprises another I/O node configured to bridge another interconnect to the interconnect, wherein the I/O node is the tunnel for the other I/O node.

Abstract: Methods and apparatus are disclosed for managing configuration data for a system. In various embodiments, a chain description data set is generated to specify an order in a configuration chain of configurable devices in the system and identify configuration data sets associated with the configurable devices. A system identifier value is generated and associated with the chain description data set. An archive is generated including the configuration data sets, chain description data set, and system identifier value.

Abstract: A method, computer program product, and distributed data processing system that allows a single physical I/O adapter, such as a PCI, PCI-X, or PCI-E adapter, to validate that a direct memory access address referenced by an incoming I/O transaction that was initiated through a memory mapped I/O operation are associated with a virtual adapter or virtual resource that is referenced by the incoming memory mapped I/O operation is provided. Specifically, the present invention is directed to a mechanism for sharing conventional PCI (Peripheral Component Interconnect) I/O adapters, PCI-X I/O Adapters, PCI-Express I/O Adapters, and, in general, any I/O adapter that uses a memory mapped I/O interface for communications. A single physical I/O adapter validates that one or more direct memory access addresses referenced by an incoming I/O transaction initiated through a memory mapped I/O operation are associated with a virtual adapter or virtual resource that is referenced by the incoming memory mapped I/O operation.

Abstract: Systems and methods of addressing two or more banks of memory utilizing a single-bank serial peripheral interface and an at least three-byte address protocol are provided. In one embodiment, a serial peripheral interface comprises a serial processing component configured to address one of the memory banks using the three-byte addressing scheme, and to write data to or read data from the addressed bank, and a bank register pointer component coupled to the serial processing component, the pointer component comprising two or more bank register pointers associated with respective memory banks, and configured to select one of the memory banks based on the two or more bank register pointers, wherein the bank register pointer component selects one of the two or more memory banks, and the serial processing component writes data to or reads data from the selected bank of memory according to the three-byte addressing scheme.

Abstract: A device driver includes a kernel stub and a user-mode module. The device driver may access device registers while operating in user-mode to promote system stability while providing a low-latency software response from the system upon interrupts. Upon receipt of an interrupt, the kernel stub may run an interrupt service routine and write information to shared memory. Control is passed to the user-mode module by a reflector. The user-mode module may then read the information from the shared memory to continue servicing the interrupt.

Abstract: To communicate over a SCSI protocol, a first device allocates buffers for a dummy SCSI read command and sends the dummy SCSI read command to a second device. This dummy SCSI read command is not a request by the first device to read data from the second device but instead is an indication that the first device is ready to receive data from the second device. In response, the second device stores the dummy SCSI read command to a command queue until the second device wishes to send data to the first device. At that time, the second device removes the dummy SCSI read command from the command queue and sends a response to the dummy SCSI read command to the first device. This response includes data that the second device wishes to send to the first device. The first device then delivers the received data to a higher layer process.

Abstract: A multi-node computer system with a plurality of interconnected processing nodes, including a method of using DMA engines without page locking by the operating system. The method includes a sending node with a first virtual address space and a receiving node with a second virtual address space. Performing a DMA data transfer operation between the first virtual address space on the sending node and the second virtual address space on the receiving node via a DMA engine, and if the DMA operation refers to a virtual address within the second virtual address space that is not in physical memory, causing the DMA operation to fail. The method includes causing the receiving node to map the referenced virtual address within the second virtual address space to a physical address, and causing the sending node to retry the DMA operation, wherein the retried DMA operation is performed without page locking.

Abstract: A DMA controller includes at least one peripheral DMA channel for handling DMA transfers on a peripheral access bus; at least one memory DMA stream, including a memory destination channel and a memory source channel, for handling DMA transfers on first and second memory access buses; first and second address computation units for computing updated memory addresses for DMA transfers; first and second memory pipelines for supplying memory addresses to the first and second memory access buses, respectively, and for transferring data on the first and second memory access buses; and a multiplexer configured to supply first and second current memory addresses to selected ones of the first and second memory pipelines in response to a control signal.

Abstract: A memory controller for a wireless communication system comprises a packet buffer write system and a packet buffer read system. The packet buffer write system places packets including packet header and packet data into a packet buffer. The packet buffer read system removes packets including a packet header and packet data from a packet buffer. The packet buffer is arranged into a plurality of packet buffer memory slots, each slot comprising a descriptor status array location including an availability bit set to “used” or “free”, and a packet buffer memory location comprising a descriptor memory slot and a data segment memory slot. The descriptor memory slot includes header information for each packet, and the data segment memory slot includes packet data. The memory controller operates on one or more queues of data, and data is placed into a particular queue in packet memory determined by priority information derived from incoming packet header or packet data.

Abstract: An I/O controller to which an I/O device is connected includes a DMA controller (DMAC) and an access control unit (ACU). The DMAC executes DMA transfer in accordance with data transfer control information set in a control/status register by a user process. The ACU limits execution of DMA transfer by the DMAC based on access control information set in a control/status register by a privileged process, and disables the DMAC from accessing any memory area other than the memory area that can be accessed by the user process.

Abstract: A storage system controller (302) includes a plurality of media controllers (301), a local microprocessor (306), and a host interface logic (310), operably coupled by a multi-drop parallel bus. The multi-drop parallel bus includes a control bus (324), a payload data bus (320), a real-time ready-status (data ready) signaling bus (322) and a general microprocessor bus (330). Each media controller has a storage media (311) operably coupled thereto. Each media controller includes a parameter storage (404), a media interface circuit (406), a control data state machine (408), a command sequencer state machine (410), a media-side multi-mode transfer state machine (412), a dual-port memory (402), a memory controller (420), and a host-side transfer state machine (430). The host interface logic and the media controllers are implemented in one or more Field Programmable Gate Arrays.

Abstract: Processor resources are partitioned based on memory usage. A compiler determines the extent to which a process is memory-bound and accordingly divides the process into a number of threads. When a first thread encounters a prolonged instruction, the compiler inserts a conditional branch to a second thread. When the second thread encounters a prolonged instruction, a conditional branch to a third thread is executed. This continues until the last thread conditionally branches back to the first thread. An indirect segmented register file is used so that the “return to” and “branch to” logical registers within each thread are the same (e.g., R1 and R2)for each thread. These logical registers are mapped to hardware registers that store actual addresses. The indirect mapping is altered to bypass completed threads. When the last thread completes it may signal an external process.

Abstract: A background memory manager (BMM) for managing a memory in a data processing system has circuitry for transferring data to and from an outside device and to and from a memory, a memory state map associated with the memory, and a communication link to a processor. The BMM manages the memory, determining if each data structure fits into the memory, deciding exactly where to place the data structure in memory, performing all data transfers between the outside device and the memory, and maintaining the memory state map according to memory transactions made, and informing the processor of new data and its location. In preferred embodiments the BMM, in the process of storing data structures into the memory, provides an identifier for each structure to the processor. The system is particularly applicable to Internet packet processing in packet routers.

Abstract: Methods and systems for customizing information in a memory associated with a SAS host bus adapter (“HBA”). A SAS HBA typically includes a memory component that stores information common to all SAS HBA's manufactured by a particular vendor (e.g., common instructions and data). In addition, each HBA memory component typically includes some information unique to each HBA (e.g., board trace number, SAS address, configuration page, boot record, etc.). Features and aspects hereof permit pre-programmed memory components to be integrated with a SAS HBA to eliminate a step to program an assembled HBA through a specialized, one-time interaction to add required unique information. Thus a manufacturer may simply integrate a pre-programmed memory component to an otherwise completed HBA assembly to complete the product manufacturing without need for a special programming step. Or a design or test engineer may simply replace a memory component to change unique information on the HBA.

Abstract: This invention is a method allowing for interfacing high speed hard disk drives (ATA-HDD) in high throughput PIO modes to currently available digital media processors (DMP). The prescribed interface programs signals available in the DMP external memory interface (EMIF) functions to match the requirements of ATA-HDD PIO functions. Selected signal redefinition and minimal glue logic is employed to form a seamless link between the EMIF I/O of the digital media processor DMP and the ATA-HDD hard drive.

Abstract: Methods, systems, and products are disclosed for DMA transfer completion notification that include: inserting, by an origin DMA on an origin node in an origin injection FIFO, a data descriptor for an application message; inserting, by the origin DMA, a reflection descriptor in the origin injection FIFO, the reflection descriptor specifying a remote get operation for injecting a completion notification descriptor in a reflection injection FIFO on a reflection node; transferring, by the origin DMA to a target node, the message in dependence upon the data descriptor; in response to completing the message transfer, transferring, by the origin DMA to the reflection node, the completion notification descriptor in dependence upon the reflection descriptor; receiving, by the origin DMA from the reflection node, a completion packet; and notifying, by the origin DMA in response to receiving the completion packet, the origin node's processing core that the message transfer is complete.

Abstract: Circuits, apparatus, and methods for avoiding deadlock conditions in a bus fabric. One exemplary embodiment provides an address decoder for determining whether a received posted request is a peer-to-peer request. If it is, the posted request is sent as a non-posted request. A limit on the number of pending non-posted requests is maintained and not exceed, such that deadlock is avoided. Another exemplary embodiment provides an arbiter that tracks a number of pending posted requests. When the number pending posted requests reaches a predetermined or programmable level, a Block Peer-to-Peer signal is sent to the arbiter's clients, again avoiding deadlock.

Abstract: A method, computer program product, and distributed data processing system that allows a single physical I/O adapter, such as a PCI, PCI-X, or PCI-E adapter, to validate that a direct memory access address referenced by an incoming I/O transaction that was initiated through a memory mapped I/O operation are associated with a virtual adapter or virtual resource that is referenced by the incoming memory mapped I/O operation is provided. Specifically, the present invention is directed to a mechanism for sharing conventional PCI (Peripheral Component Interconnect) I/O adapters, PCI-X I/O Adapters, PCI-Express I/O Adapters, and, in general, any I/O adapter that uses a memory mapped I/O interface for communications. A single physical I/O adapter validates that one or more direct memory access addresses referenced by an incoming I/O transaction initiated through a memory mapped I/O operation are associated with a virtual adapter or virtual resource that is referenced by the incoming memory mapped I/O operation.

Abstract: A parallel computer system is constructed as a network of interconnected compute nodes. Each of the compute nodes includes at least one processor, a memory and a DMA engine. The DMA engine includes a processor interface for interfacing with the at least one processor, DMA logic, a memory interface for interfacing with the memory, a DMA network interface for interfacing with the network, injection and reception byte counters, injection and reception FIFO metadata, and status registers and control registers. The injection FIFOs maintain memory locations of the injection FIFO metadata memory locations including its current head and tail, and the reception FIFOs maintain the reception FIFO metadata memory locations including its current head and tail. The injection byte counters and reception byte counters may be shared between messages.

Abstract: A method and apparatus for using a 2:1 MUX to control read access, data bypass, and page size bypass in a memory array. The mechanism of the present invention reduces the 3:1 MUX normally required to manage these three functions to a 2:1 MUX.

Abstract: A disk controller has a channel adapter having a connection interface to a host computer or a disk drive; a memory adapter for temporarily storing data to be transferred between the host computer and disk drive; a processor adapter for controlling operations of the channel adapter and memory adapter; and a switch adapter for configuring an inner network by interconnecting the channel adapter, memory adapter and processor adapter, wherein the channel adapter, memory adapter, processor adapter and switch adapter each include a DMA controller for performing a communication protocol control of the inner network; and packet multiplex communication is performed among the DMA controllers provided in the adapters. The disk controller can realize a high transfer efficiency and a low cost while retaining a high reliability. A storage system includes an interface unit having an interface with a server or hard drives, a memory unit, a processor unit, and an interconnection.

Abstract: A hardware-based offload engine is disclosed for mapping protected data into frames. For a write operation, the HBA determines host addresses and the size of data to be read from those addresses. The HBA also determines the frame size and protection scheme for data to be written. A frame transmit engine reads each host descriptor in the host data descriptor list to determine the location and byte count of the data to be read. A DMA engine reads the protection information/scratch area to determine the exact data size used to fill each frame and the protection scheme, and retrieves one or more free frame buffers. Check bytes are inserted alongside the data and stored in free frame buffers. After each frame is filled, the frame transmit engine also generates and stores header information for that frame, and then combines header, data and check bytes for transmission over the network.

Abstract: Provided are a method, system, and program for handling Input/Output (I/O) requests. A bus enables communication with an initiator, target device and device controller, wherein the device controller accesses the target device to execute I/O commands directed to the target device. An I/O request command is received to access the target device. The initiator is configured to transmit at least one data request on the bus to one memory address in a predefined address window of the device controller. The device controller is enabled to claim the data request to the memory address in the predefined address window from the initiator on the bus to execute the data request against the target device.

Abstract: A distributed direct memory access (DMA) method, apparatus, and system is provided within a system on chip (SOC). DMA controller units are distributed to various functional modules desiring direct memory access. The functional modules interface to a systems bus over which the direct memory access occurs. A global buffer memory, to which the direct memory access is desired, is coupled to the system bus. Bus arbitrators are utilized to arbitrate which functional modules have access to the system bus to perform the direct memory access. Once a functional module is selected by the bus arbitrator to have access to the system bus, it can establish a DMA routine with the global buffer memory.

Abstract: Provided are an integrated circuit device having two or more ports and a system for the device, where the device includes a first port for inputting and outputting data and a second port for inputting the data, and either the first port and/or the second port is selected by an external command when the data is input; the second port has ½n the number of pins of the first port, where n is a natural number; the device includes two or more ports that operate independently so that turn around time is reduced and the data bus efficiency of the integrated circuit device and the system are improved.

Abstract: A DMA controller is connected by a bus to a plurality of master devices and a plurality of slave devices, and performs a data transfer between slave devices which are specified as a source and a destination of the data transfer by a transfer condition received from any of the plurality of master devices. Each of the plurality of master devices and the plurality of slave devices has a rank used for judging data transfer permissibility. The DMA controller enables the data transfer if the data transfer is judged to be permitted as a result of a comparison between a rank of the master device and a rank of any of the specified slave devices, and disables the data transfer if the data transfer is judged to be prohibited.

Abstract: In an electronic system, a DMA circuit is supplied with a device selection signal that indicates a processor is accessing or going to access a memory. If the DMA circuit finds that the processor is not accessing or not going to access the memory, the DMA circuit starts its DMA operations. Once the DMA circuit finds that the processor is going to access the memory, the DMA circuit stops its DMA operation and return the use of the memory to the processor.

Abstract: Embodiments include storing graphics instructions at addresses in a memory in an original order, and storing in the memory pointers associated with each instruction pointing to the addresses of the instructions in the original order. A first pointer associated with a first graphics instruction may then be moved from pointing to a first address of the first graphics instruction to point to a second address of a second graphics instruction. Likewise, a second pointer associated with the second graphics instruction may be moved from pointing to the second address to point to the first address by accessing the first pointer before moving the first pointer to determine that the second pointer is to point to the first address (e.g., the address the first instruction points to before being moved). Afterwards, the instructions may be re-ordered into an optimized order for compiling, by switching them to different addresses according to the pointers.

Abstract: A storage system controller (302) includes a plurality of media controllers (301), a local microprocessor (306), and a host interface logic (310), operably coupled by a multi-drop bus. The multi-drop bus includes a control bus (324), a payload data bus (320), a real-time ready-status (data ready) signaling bus (322) and a general microprocessor bus (330). Each media controller has a storage media (311) operably coupled thereto. Each media controller includes a parameter storage (404), a media interface circuit (406), a control data state machine (408), a command sequencer state machine (410), a media-side multi-mode transfer state machine (412), a dual-port memory (402), a memory controller (420), and a host-side transfer state machine (430). The host interface logic and the media controllers are implemented in one or more Field Programmable Gate Arrays.

Abstract: A device for attachment to a host for serial data communication including means for transferring to the host a predetermined data structure indicating whether or not the device supports direct memory access.

Abstract: A storage medium drive is controllable by a storage medium array controller. the storage medium array controller receives a data storage medium drive information and the storage medium array controller sets a data transmission parameter with respect to the storage medium drive based on the data storage medium drive information.

Abstract: A method for using a memory device with a built-in memory array and a connector for a removable memory device is disclosed. In one embodiment, a determination is made regarding whether a removable memory device comprises a memory controller. If the removable memory device does not comprise a memory controller, circuitry in a memory device connected to the removable memory device is used to control read/write operations to a memory array in the removable memory device. In another embodiment, data stored in a built-in memory of a memory device is read, and the read data is stored in a memory array of a removable memory device. In yet another embodiment, a connection of a removable memory device to a memory device is detected. Pre-loaded content is read from a memory array in the removable memory device and stored in the built-in memory array of the memory device.

Abstract: Disclosed is a memory device having Universal Serial Bus (USB) interface and Secure Digital (SD) card interface, including: a plurality of flash memory units; a plurality of flash memory controllers each controlling reading and writing data on the flash memory unit; a Direct Memory Access (DMA) controller including a plurality of DMA channels each transmitting/receiving data to/from the flash memory unit in DMA mode; a Micom dividing a signal received from the USB interface and the SD card interface into data and an address and transmitting the data to the DMA controller; and an address decoder calculating positions of the received data to be written or read on the flash memory unit according to the address.

Abstract: The disclosure is directed to a device including a memory interface. The memory interface includes a data interface, a first state machine and a second state machine. The first state machine includes a first chip select interface and a first ready/busy interface. The first state machine is configured to select and monitor a first memory device via the first chip select interface and the first ready/busy interface, respectively, when the first memory device is coupled to the data interface. The second state machine includes a second chip select interface and a second ready/busy inter-face. The second state machine is configured to select and monitor a second memory device via the second chip select interface and the second ready/busy interface, respectively, when the second memory device is coupled to the data interface.

Abstract: Circuits, apparatus, and methods for avoiding deadlock conditions in a bus fabric. One exemplary embodiment provides an address decoder for determining whether a received posted request is a peer-to-peer request. If it is, the posted request is sent as a non-posted request. A limit on the number of pending non-posted requests is maintained and not exceed, such that deadlock is avoided. Another exemplary embodiment provides an arbiter that tracks a number of pending posted requests. When the number pending posted requests reaches a predetermined or programmable level, a Block Peer-to-Peer signal is sent to the arbiter's clients, again avoiding deadlock.

Abstract: An arrangement of memory devices and a controller is based on an interface with a reduced pin count relative to a known memory device and controller arrangement. Facilitating the reduced pin count interface are some operations performed by the controller. The controller determines a width for a Data bus while assigning a target device address to each of the memory devices.

Abstract: A data transfer control system that can change the way of DMA transfers to meet the requirements of each application. The data transfer control system includes a DMA controller (DMAC) and a DMAC memory dedicated for DMA control purposes. The DMAC performs DMA transfers according to a DMA program stored in the DMAC memory. Each time a new DMA request is received, the DMAC saves its parameters in a DMA request parameter table, and each DMA request parameter table is registered with a DMA request management table. In this way, the received DMA requests are queued in the DMA request management table. They are executed in a first-in first-out fashion. The progress of ongoing DMA transfers are managed in a DMA channel status table disposed for each DMA channel.

Abstract: In a buffering apparatus for digital data for temporarily storing input data and then outputting, a memory apparatus is provided with a plurality of storage areas assigned consecutive identification numbers. A partition designation unit generates an instruction for partitioning the plurality of storage areas. An area partitioning unit partitions the plurality of storage areas in the memory apparatus at least into a first area and a second area in accordance with the generated instruction for partitioning and uses the first area as a buffer area, the first area including storage areas with consecutive identification numbers. A partition designation unit generates an instruction for partitioning that designates a border between the first area and the second area.

Abstract: A method for providing access to a network interface having a plurality of memory access channels is disclosed. The network interface provides access to a plurality of processing entities. The method includes providing a network interface software hierarchy wherein the network interface software hierarchy provides access to the network interface, and associating various memory access channels with corresponding processing entities via the network interface software hierarchy so as to provide a virtualized network interface.

Abstract: A network system having a plurality of processing partitions which includes a network interface unit coupled to a plurality of processing entities is disclosed. The network interface unit includes a plurality of memory access channels. The plurality of memory access channels is virtualized. The network interface unit is shared among the plurality of processing partitions.

Abstract: Methods and apparatus are provided for implementing a programmable device including a processor core, a hardware accelerator, and secondary components such as memory. A portion of a program written in a high-level language is automatically selected for hardware acceleration. Dedicated ports are generated to allow the hardware accelerator to handle pointer referencing and dereferencing. A hardware accelerator is generated to perform pipelined processing of instructions. The number of stages implemented for pipelined processing is at least partially dependent on the latency associated with accessing secondary components.