Abstract: A non-uniform memory access (NUMA) computer system includes a remote node coupled by a node interconnect to a home node including a home system memory. The remote node includes a plurality of snoopers coupled to a local interconnect. The plurality of snoopers includes a cache that caches a cache line corresponding to but modified with respect to data resident in the home system memory. The cache has a cache controller that issues a deallocate operation on the local interconnect in response to deallocating the modified cache line. The remote node further includes a node controller, coupled between the local interconnect and the node interconnect, that transmits the deallocate operation to the home node with an indication of whether or not a copy of the cache line remains in the remote node following the deallocation. In this manner, the local memory directory associated with the home system memory can be updated to precisely reflect which nodes hold a copy of the cache line.

Abstract: System bus snoopers within a multiprocessor system in which dynamic application sequence behavior information is maintained within cache directories append the dynamic application sequence behavior information for the target cache line to their snoop responses. The system controller, which may also maintain dynamic application sequence behavior information in a history directory, employs the available dynamic application sequence behavior information to append “hints” to the combined response, appends the concatenated dynamic application sequence behavior information to the combined response, or both. Either the hints or the dynamic application sequence behavior information may be employed by the bus master and other snoopers in cache management.

Abstract: An apparatus for allocating data usage in an embedded dynamic random access memory (DRAM) device is disclosed. The apparatus for allocating data usages within an embedded dynamic random access memory (DRAM) device comprises a control analysis circuit, a data/command flow circuit, and a partition management control. The control analysis circuit generates an allocation signal in response to processing performances of a processor. Coupled to an embedded DRAM device, the data/command flow circuit controls data flow from the processor to the embedded DRAM device. The partition management control, coupled to the control analysis circuit, partitions the embedded DRAM device into a first partition and a second partition. The data stored in the first partition are different from the data stored in the second partition according to their respective usage. The allocation percentages of the first and second partitions are dynamically allocated by the allocation signal from the control analysis circuit.

Abstract: A data processing system includes a plurality of nodes, which each contain at least one agent, and data storage accessible to agents within the nodes. The plurality of nodes are coupled by a non-hierarchical interconnect including multiple non-blocking uni-directional address channels and at least one uni-directional data channel. The agents, which are each coupled to and snoop transactions on all of the plurality of address channels, can only issue transactions on an associated address channel. The uni-directional channels employed by the present non-hierarchical interconnect architecture permit high frequency pumped operation not possible with conventional bi-directional shared system buses. In addition, access latencies to remote (cache or main) memory incurred following local cache misses are greatly reduced as compared with conventional hierarchical systems because of the absence of inter-level (e.g., bus acquisition) communication latency.

Abstract: A non-uniform memory access (NUMA) data processing system includes a plurality of nodes coupled to a node interconnect. The plurality of nodes contain a plurality of processing units and at least one system memory having a table (e.g., a page table) resident therein. The table includes at least one entry for translating a group of non-physical addresses to physical addresses that individually specifies control information pertaining to the group of non-physical addresses for each of the plurality of nodes. The control information may include one or more data storage control fields, which may include a plurality of write through indicators that are each associated with a respective one of the plurality of nodes. When a write through indicator is set, processing units in the associated node write modified data back to system memory in a home node rather than caching the data.

Abstract: A computer system includes a home node and one or more remote nodes coupled by a node interconnect. The home node includes a local interconnect, a node controller coupled between the local interconnect and the node interconnect, a home system memory, and a memory controller coupled to the local interconnect and the home system memory. In response to receipt of a data request from the remote node, the memory controller transmits requested data from the home system memory to the remote node and, in a separate transfer, conveys responsibility for global coherency management for the requested data from the home node to the remote node. By decoupling responsibility for global coherency management from delivery of the requested data in this manner, the memory controller queue allocated to the data request can be deallocated earlier, thus improving performance.

Abstract: A non-uniform memory access (NUMA) computer system includes a node interconnect to which a remote node and a home node are coupled. The home node contains a home system memory, and the remote node includes at least one processing unit and a cache. In response to the cache deallocating an unmodified cache line that corresponds to data resident in the home system memory, a cache controller of the cache issues a deallocate operation on a local interconnect of the remote node. In one embodiment, the deallocate operation is further transmitted to the home node via the node interconnect only in response to an indication, such as a combined response, that no other cache in the remote node caches the cache line. In response to receipt of the deallocate operation, a memory controller in the home node updates a local memory directory associated with the home system memory to indicate that the remote node does not hold a copy of the cache line.

Abstract: System bus masters within a multiprocessor system in which dynamic application sequence behavior information is maintained within cache directories append the historical access information for the target cache line to their requests. Snoopers and/or the system controller, which may also maintain dynamic application sequence behavior information in a history directory, employ the appended access information for cache management.

Abstract: In addition to an address tag, a coherency state and an LRU position, each cache directory entry includes historical processor access information for the corresponding cache line. The historical processor access information includes different subentries for each different processor which has accessed the corresponding cache line, with subentries being “pushed” along the stack when a new processor accesses the subject cache line. Each subentries contains the processor identifier for the corresponding processor which accessed the cache line, one or more opcodes identifying the operations which were performed by the processor, and timestamps associated with each opcode.

Abstract: Disclosed is a method and memory subsystem that allows for speculative issuance of reads to a DRAM array to provide efficient utilization of the data out bus and faster read response for accesses to a single DRAM array. Two read requests are issued simultaneously to a first and second DRAM in the memory subsystem, respectively. Data issued from the first DRAM is immediately placed on the data out bus, while data issued from the second DRAM is held in an associated buffer. The processor or memory controller then generates a release signal if the second read is not speculative or is correctly speculated. The release signal is sent to the second DRAM after the first issued data is placed on the bus. The release signal releases the data held in the buffer associated with the second DRAM from the buffer to the data out bus.

Abstract: A non-uniform memory access (NUMA) computer system includes a remote node coupled by a node interconnect to a home node having a home system memory. The remote node includes a local interconnect, a processing unit and at least one cache coupled to the local interconnect, and a node controller coupled between the local interconnect and the node interconnect. The processing unit first issues, on the local interconnect, a read-type request targeting data resident in the home system memory with a flag in the read-type request set to a first state to indicate only local servicing of the read-type request. In response to inability to service the read-type request locally in the remote node, the processing unit reissues the read-type request with the flag set to a second state to instruct the node controller to transmit the read-type request to the home node.

Abstract: An apparatus for accessing a banked embedded dynamic random access memory device is disclosed. The apparatus for accessing a banked embedded dynamic random access memory (DRAM) device comprises a general functional control logic and a bank RAS controller. The general functional control logic is coupled to each bank of the banked embedded DRAM device. Coupled to the general functional control logic, the bank RAS controller includes a rotating shift register having multiple bits. Each bit within the rotating shift register corresponds to each bank of the banked embedded DRAM device. As such, a first value within a bit of the rotating shift register allows accesses to an associated bank of the banked embedded DRAM device, and a second value within a bit of the rotating shift register denies accesses to an associated bank of the banked embedded DRAM device.

Abstract: The present invention provides an improved method, an system, and a set of computer implemented instructions for handling a cache containing multiple single-bit hard errors on multiple addresses within a data processing system. Such handles will prevent any down time by logging in the parts to be replaced by an operator when certain level of bit errors is reached. When a hard error exists on a cache address for the first time, serviceable first hard error, that cache line is deleted. Thus the damaged memory device is no longer used by the system. As a result, the system is running with “N−x” lines wherein “N” constitutes the total number of existing lines and “x” is less than “N”. An alternative method is to exchange the damaged memory device to a spare memory device. In order to provide such services, the system must first differentiate whether an error is a soft or hard error.

Abstract: A multiprocessor computer system in which snoop operations of the caches are synchronized to allow the issuance of a cache operation during a cycle which is selected based on the particular manner in which the caches have been synchronized. Each cache controller is aware of when these synchronized snoop tenures occur, and can target these cycles for certain types of requests that are sensitive to snooper retries, such as kill-type operations. The synchronization may set up a priority scheme for systems with multiple interconnect buses, or may synchronize the refresh cycles of the DRAM memory of the snooper's directory. In another aspect of the invention, windows are created during which a directory will not receive write operations (i.e., the directory is reserved for only read-type operations). The invention may be implemented in a cache hierarchy which provides memory arranged in banks, the banks being similarly synchronized.

Abstract: In addition to an address tag, a coherency state and an LRU position, each cache directory entry includes historical processor access and snoop operation information for the corresponding cache line. The historical processor access and snoop operation information includes different subentries for each different processor which has accessed the corresponding cache line, with subentries being “pushed” along the stack when a new processor accesses the subject cache line. Each subentries contains the processor identifier for the corresponding-processor which accessed the cache line, a processor access history segment, and a snoop operation history segment. The processor access history segment contains one or more opcodes identifying the operations which were performed by the processor, and timestamps associated with each opcode.

Abstract: A multiprocessor system bus protocol system and method for processing and handling a processor request within a multiprocessor system having a number of bus accessible memory devices that are snooping on. at least one bus line. Snoop response groups which are groups of different types of snoop responses from the bus accessible memory devices are provided. Different transfer types are provided within each of the snoop response groups. A bus master device that provides a bus master signal is designated. The bus master device receives the processor request. One of the snoop response groups and one of the transfer types are appropriately designated based on the processor request. The bus master signal is formulated from a snoop response group, a transfer type, a valid request signal, and a cache line address. The bus master signal is sent to all of the bus accessible memory devices on the cache bus line and to a combined response logic system.

Abstract: A data processing system includes an interconnect, a plurality of nodes coupled to the interconnect that each include at least one agent, response logic within each node, and a queue. In response to snooping a transaction on the interconnect, each agent outputs a snoop response. In addition, the queue, which has an associated agent, allocates an entry to service the transaction. The response logic within each node accumulates a partial combined response of its node and any preceding node until a complete combined response for all of the plurality of nodes is obtained. However, prior to the associated agent receiving the complete combined response, the queue speculatively deallocates the entry if the partial combined response indicates that an agent other than the associated agent will service the transaction.

Abstract: A set-associative cache memory having asymmetric latency among sets is disclosed. The cache memory has multiple congruence classes of cache lines. Each congruence class includes a number of sets organized in a set-associative manner. The cache memory further includes a means for accessing at least one of the sets faster than the remaining sets having an identical access latency.

Abstract: An apparatus for providing concurrent communications between multiple memory devices and a processor is disclosed. Each of the memory device includes a driver, a phase/cycle adjust sensing circuit, and a bus alignment communication logic. Each phase/cycle adjust sensing circuit detects an occurrence of a cycle adjustment from a corresponding driver within a memory device. If an occurrence of a cycle adjustment has been detected, the bus alignment communication logic communicates the occurrence of a cycle adjustment to the processor. The bus alignment communication logic also communicates the occurrence of a cycle adjustment to the bus alignment communication logic in the other memory devices. There are multiple receivers within the processor, and each of the receivers is designed to receive data from a respective driver in a memory device. Each of the receivers includes a cycle delay block.

Abstract: A method and system for high speed data access of a banked cache memory. In accordance with the method and system of the present invention, during a first cycle, in response to receipt of a request address at an access controller, the request address is speculatively transmitted to a banked cache memory, where the speculative transmission has at least one cycle of latency. Concurrently, the request address is snooped in a directory associated with the banked cache memory. Thereafter, during a second cycle the speculatively transmitted request address is distributed to each of multiple banks of memory within the banked cache memory. In addition, the banked cache memory is provided with a bank indication indicating which bank of memory among the multiple banks of memory contains the request address, in response to a bank hit from snooping the directory.