摘要:
Method and apparatus for allowing a direct memory access unit to have access to a virtual address space is accomplished by receiving a request for memory access from the direct memory access device; determining a device identifier according to the received request for memory access; determining a memory protection schema according to the determined device identifier; and granting the direct memory access unit access to memory in accordance with the determined memory protection schema.
摘要:
A PC bus architecture that is compatible with an industry standard bus architecture and allows devices to transfer data at higher data rates that the bus clock speed. By transferring data more than once per clock cycle, the data transfer rate is multiplied. Another feature of the present invention is a protocol allowing a data transaction in which a data transfer request can be made by a bus master device and then queued so that the transaction occurs at a later time allowing the bus to be free for other transactions until the responding device has prepared the data.
摘要:
A method and apparatus to improve computer bus access time. A bus is described which has sequential control states and fixed transaction times. Without the invention, arbitration may be delayed as the bus sequences through control states. With the invention, arbitration is immediate if the bus is idle. When any transaction is initiated, a counter is initialized to the number of control states in the standard transaction time. If the counter reaches zero, the bus is idle. If the bus is not idle, a sequence of bus control states is repeated. If the bus is idle, the bus is forced to remain in an arbitration state, thereby enabling any subsequent arbitration to take place immediately.
摘要:
A system and method for achieving one or more protected regions within a computer system having multiple partitions are disclosed. In at least some embodiments, the system includes an intermediary device for use within the computer system having the multiple partitions. The intermediary device includes a fabric device, and a first firewall device capable of limiting communication of a signal based upon at least one of a source of the signal and an intended destination of the signal, the first firewall device being at least indirectly coupled to the fabric device. The intermediary device further includes a first conversion device that is one of integrated with the first firewall device and distinct from the first firewall device, and that is capable of converting between a processor address and a fabric address for use by the fabric device. In some embodiments, the various devices each include Control and Status Registers (CSRs).
摘要:
An output resistance (R.sub.O) is situated at each output of a plurality of drivers communicating to a plurality of receivers via an interconnect network which is biased by a terminal supply voltage (V.sub.T). The output resistance R.sub.O eliminates the need for a wait period in a cycle, which wait period is usually required when mastership of the interconnect network changes over from one driver to another driver. The drivers and receivers are two-state devices. For a logic high, the drivers exhibit a virtually infinite resistance. Consequently, the interconnect network exhibits a high voltage V.sub.INT, which is approximately equal to the terminal supply voltage V.sub.T. Whereas for a logic low, the drivers sink current from the interconnect network, thereby pulling the interconnect network voltage V.sub.INT towards ground. Any signal below about (7/8)*V.sub.T is recognized by the receivers as a logic low, while any signal above this threshold is recognized as a logic high. In the case of a logic low, the voltage V.sub.INT is prevented from being pulled to ground by the output resistance (R.sub.O). The driver sinks enough current so that the voltage V.sub.INT is approximately equal to V.sub.T /2. Accordingly, if a change over occurs in a cycle after a logic low, the newly active driver can immediately drive a logic high or low onto the interconnect network, because the voltage V.sub.T /2 is readily available on the interconnect network. If the newly active driver wishes to drive a logic high, the driver exhibits infinite resistance, and the voltage V.sub.INT increases to V.sub.T. If the newly active driver wishes to drive a logic low, the driver sinks current, and the voltage V.sub.INT increases to only about (3/4)*(V.sub.T), which is recognized as a logic low. The voltage V.sub.INT will ultimately decrease to V.sub.T /2, thereby enhancing its disposition as a logic low.
摘要:
A system and method for achieving one or more protected regions within a computer system having multiple partitions are disclosed. In at least some embodiments, the system includes an intermediary device for use within the computer system having the multiple partitions. The intermediary device includes a fabric device, and a first firewall device capable of limiting communication of a signal based upon at least one of a source of the signal and an intended destination of the signal, the first firewall device being at least indirectly coupled to the fabric device. The intermediary device further includes a first conversion device that is one of integrated with the first firewall device and distinct from the first firewall device, and that is capable of converting between a processor address and a fabric address for use by the fabric device. In some embodiments, the various devices each include Control and Status Registers (CSRs).
摘要:
A directory cache is provided with a plurality of directory entries configured to store information regarding copies of memory lines stored in a plurality of caches. The entries are divided into sets of N entries, with each set of N entries being addressable via an index. The directory cache is also provided with a cache controller. The cache controller retrieves a set of N entries associated with an index corresponding to a memory line, and if a tag portion of one of the retrieved entries corresponds to the memory line, the cache controller determines whether the one of the retrieved entries contains an indication that information regarding the memory line is stored in at least a second one of the retrieved entries.
摘要:
A method and apparatus to improve memory performance in a computer bus system. Memory is divided into interleaved blocks and memory addresses are mapped into block identification numbers. Master devices keep track of which parts of memory are busy by storing memory block identification numbers in local queues whenever memory is accessed. Block identification numbers are removed from local queues when the memory transaction is complete. Master devices arbitrate for access to the bus for memory transactions only if the target memory block identification number is not in the local queue.
摘要:
A double data rate memory controller is provided with a plurality of data and strobe pads, means for receiving data and strobe signals via said pads at 1x double data rate memory speed, and means for receiving data and strobe signals via said pads at Mx double data rate memory speed (M2).
摘要:
Methods and apparatus for receiving data from memory, the data being associated with a strobe, are disclosed herein. In general, the methods and apparatus provide a memory controller with a means for receiving data at different rates. Data may be received by a memory controller at different rates because, for example, the memory controller is used in environments where it attaches directly to a number of memory modules, and/or in environments where it attaches to a number of memory modules via an intermediary chip. The intermediary chip may, for example, include multiplexers which receive data from two or more banks of memory modules and then multiplex the data into one or more data streams which are then transmitted to the memory controller at twice the rate which the memory modules in either bank could transmit data to the memory controller.