Abstract: Memory Access Coloring provides architecture support that allows software to classify memory accesses into different congruence classes by specifying a color for each memory access operation. The color information is received and recorded by the underlying system with appropriate granularity. This allows hardware to monitor color-based cache monitoring information and provide such feedback to the software to enable various runtime optimizations. It also enables enforcement of different memory consistency models for memory regions with different colors at the same time.

Abstract: The present invention relates to a method for processing data entities by a data processing system, wherein: a first and a second set of data entities are stored in a main memory and associated with a respective first and second set of points of a domain; the first set of data entities is loaded into a local storage; one or more first calculations are performed using the first set of data entities to generate first calculated data; the second set of data entities is determined according to at least some of the first calculated data; the determined second set of data entities is loaded into the local storage; and one or more second calculations are performed using the second set of data entities resulting in second calculated data.

Abstract: A method for preserving memory affinity in a computer system is disclosed. The method reduces and sometimes eliminates memory affinity loss due to process migration by restoring the proper memory affinity through dynamic page migration. The memory affinity access patterns of individual pages are tracked continuously. If a particular page is found almost always to be accessed from a particular remote access affinity domain for a certain number of times, and without any intervening requests from other access affinity domain, the page will migrate to that particular remote affinity domain so that the subsequent memory access becomes local memory access. As a result, the proper pages are migrated to increase memory affinity.

Abstract: In a computer system supporting memory compression and wherein data is stored on a disk in a different compressed format, and wherein an IOA (input/output adaptor)/IOP (input/output processor) selectively reads from and writes to a main memory through a direct memory access (DMA) operation, a method for transmitting compressed data from the IOA/IOP to the main memory includes reserving a set of free memory sectors to contain the data in said main memory, sending to the IOA/IOP addresses of said memory sectors, copying the data from the IOA/IOP to said memory sectors using said DMA operation, constructing at the IOA/IOP compressed memory directory information defining how and where the data is stored in memory, sending the memory directory information to a memory controller, and storing the memory directory information in the compressed memory directory structure.

Abstract: A data initiator device designates an initial data tag set for tagging data transfers to thereby attach data tags from the designated set to commands directed to data transfers between the data initiator device and a data target device subsequent to the designation of the initial data tag set. The data transfer commands are issued with the attached data tags from the designated data tag set until an occurrence of a reset error associated with one of the issued data transfer commands. In response to the reset error, the data initiator device designates a different data tag set for tagging data transfers to thereby attach data tags from the newly designated data tag set to commands directed to data transfers between the data initiator device and the data target device subsequent to the designation of the new data tag set.

Abstract: A cache coherence protocol for a multiprocessor system. Each processor in the system has an associated cache capable of storing multiple word data lines. The system also includes a plurality of main memory modules, each having an associated distributed global directory storing directory information for lines stored in the associated main memory module. Each main memory module is connected to each processor by means of a multi-stage interconnection network. When a processor attempts to over-write an individual word in a line stored in its associated cache, a write request signal is sent to the appropriate global directory, and each other processor whose cache stores a copy of the line is notified of the request. When each other processor has responded with an acknowledgement, the first processor is allowed to proceed with the write.

Abstract: An integrated redundancy eDRAM architecture system for an embedded DRAM macro system having a wide data bandwidth and wide internal bus width is disclosed which provides column and row redundancy for defective columns and rows of the eDRAM macro system. Internally generated column and row addresses of defective columns and rows of each micro-cell block are stored in a memory device, such as a fuse bank, during an eDRAM macro test mode in order for the information to be quickly retrieved during each cycle of eDRAM operation to provide an SRAM-like operation. A column steering circuit steers column redundant elements to replace defective column elements. Redundancy information is either supplied from a SRAM fuse data storage device or from a TAG memory device depending on whether a read or write operation, respectively, is being performed.

Abstract: A method, system and program for controlling access to memory areas within a computer are provided. The invention comprises placing a first Bind Work Queue Element (WQE) at the head of a work queue, wherein the first Bind WQE defines parameters associated with a first Memory Window. A set of Work Requests is then placed on the work queue, behind the first Bind WQE wherein the work requests invoke operations that access the first Memory Window. A second Bind WQE is then placed on the work queue, behind the first set of Work Requests. This second Bind WQE defines parameters associated with a second Memory Window. A second set of Work Requests is placed on the work queue behind the second Bind WQE and invoke operations that access the second memory window. The Memory Windows can be associated with a common Memory Region and have different addresses and lengths or different access rights. In another embodiment, the first and second Memory Windows can be associated with different Memory Regions.