Abstract: A multiple agent system providing each of a plurality of agents, e.g., processors, to access a shared synchronous or asynchronous memory. In the case of synchronous memory, the clock signal from a super agent selected from among the plurality of agents provides a memory access clock signal to the other agents accessing the same shared memory. The other agents synchronize their respective address, data and control busses to those of the super agent, and output a representation of the same clock signal to the shared memory. In another aspect of the present invention, the shared memory is partitioned for use from among a plurality of groups of agents, each agent group comprising one or more agents. Any one of the agents may update a configuration register to flexibly reconfigure the amount of shared memory available to the agents as necessary.

Abstract: A method and apparatus for controlling a clock of a component of an integrated circuit for testing purposes. The clock is controlled on a hardware level. Specifically, a stepped clocking technique is provided by which a processor can advance the clock signal of a component one bit at a time or in rapid bursts of successive bits. This provides for operation of the accelerator block in increments of half-clock cycles (bit by bit). The accelerator block can be stopped during processing of the dataset. Registers of the accelerator block can then be interrogated by the processor, which continues to operate at full clock speed, to determine how the accelerator block is processing the data.

Abstract: An interrupt mechanism which reduces or eliminates the need for an interrupt status register while at the same time provides suitable information to a host or other processor with respect to the cause and parameters surrounding an interrupt signal. An interrupt queue is maintained in shared memory accessible by both a host and an interrupting agent. The interrupt queue has a capacity or two or more separate interrupt requests, either from a same interrupting agent or from two different interrupting agents. As interrupting agents write to the interrupt queue, an agent current interrupt pointer (ACIP) is incremented to a next position in the interrupt queue. As the host services interrupts, the current host pointer is incremented to clear the serviced interrupt request entry.

Abstract: An on-demand transfer (ODT) engine is located in each peripheral in a host/peripheral system communicating using a burst mode bus, e.g., a PCI bus. Each peripheral transfers blocks by setting, e.g., a starting address and block size of a data block to be transferred. Importantly, the starting location of a data transfer stream is maintained in a common memory area, e.g., in the host, while the length of the data transfer block is maintained in the ODT engine. By maintaining the length of the data block in the ODT engine, the peripheral can change the length of a block in a continual data stream on the fly, without the need to communicate with the host computer or common data transfer device such as a DMA. In the disclosed embodiment, up to 128 data streams may be simultaneously transferred.

Abstract: The present invention provides a PCI Bus Diagnostic Monitor which eliminates the need to hook up a logic analyzer and manually analyze the data passing on the PCI Bus. The present invention provides an accurate analysis of the PCI Bus master's utilization and/or latency time to acquire the PCI Bus by controlling a 12-bit counter and analyzing count values at appropriate times, e.g., between the time the PCI Bus request is output and the time that the data transfer begins, and the time between when the data transfer begins and when the data transfer ends. The data corresponding to a large number of data transfers may be buffered and analyzed to provide performance statistics relating to the PCI Bus. The analysis can be performed in lightly loaded, typically loaded, and heavily loaded PCI bus situations to fully and accurately test real-world capabilities of new peripherals, particular combinations of peripherals, and statistics relating to customized usage of a host system.