Abstract: A method of operating a processing unit of a computer system, by issuing an instruction having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the prefetch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit (the latter feature is particularly useful for caches which are shared by a processing unit cluster).

Abstract: A processor having a hashed and partitioned register file includes at least one execution unit, an instruction sequencing unit coupled to the execution unit, and a plurality of registers coupled to the execution unit. The plurality of registers are partitioned into a plurality of groups, such that registers within each group can store only data having associated addresses within a respective one of a plurality of subsets of an address space.

Abstract: A method of operating a processing unit of a computer system, by issuing an instruction having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the pref etch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit.

Abstract: A method of operating a processing unit of a computer system, by issuing an instruction having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the prefetch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit (the latter feature is particularly useful for caches which are shared by a processing unit cluster).

Abstract: A method of operating a multi-level memory hierarchy of a computer system and apparatus embodying the method, wherein instructions issue having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. These prefetch requests can be demand load requests, where the processing unit will need the operand data or instructions, or speculative load requests, where the processing unit may or may not need the operand data or instructions, but a branch prediction or stream association predicts that they might be needed. Further branch predictions or stream associations that were made based on an earlier speculative choice are linked by using a tag pool which assigns a bit fields in the tag pool entries to the level of speculation depth. Each entry shares in common the bit field values associated with earlier branches or stream associations.

Abstract: A method of operating a multi-level memory hierarchy of a computer system and an apparatus embodying the method, wherein multiple levels of storage subsystems are used to improve the performance of the computer system, each next higher level generally having a faster access time, but a smaller amount of storage. Values within a level are indexed by a directory that provides an indexing of information relating the values in that level to the next lower level. In a preferred embodiment of the invention, the directories for the various levels of storage are contained within the next higher level, providing a faster access to the directory information. Cache memories used as the highest levels of storage, and one or more sets are allocated out of that cache memory for containing a directory of the next lower level of storage.

Abstract: A processor includes execution resources, data storage, and an instruction sequencing unit, coupled to the execution resources and the data storage, that supplies instructions within the data storage to the execution resources. At least one of the execution resources, the data storage, and the instruction sequencing unit is implemented with a plurality of hardware partitions of like function for processing data. The data processed by each hardware partition is assigned according to a selectable hash of addresses associated as with the data. In a preferred embodiment, the selectable hash can be altered dynamically during the operation of the processor, for example, in response to detection of an error or a load imbalance between the hardware partitions.

Abstract: A method of improving memory access for a computer system, by sending load requests to a lower level storage subsystem along with associated information pertaining to intended use of the requested information by the requesting processor, without using a high level load queue. Returning the requested information to the processor along with the associated use information allows the information to be placed immediately without using reload buffers. A register load bus separate from the cache load bus (and having a smaller granularity) is used to return the information. An upper level (L1) cache may then be imprecisely reloaded (the upper level cache can also be imprecisely reloaded with store instructions). The lower level (L2) cache can monitor L1 and L2 cache activity, which can be used to select a victim cache block in the L1 cache (based on the additional L2 information), or to select a victim cache block in the L2 cache (based on the additional L1 information).

Abstract: A signal is transmitted from a sending chip to a first receiving chip in a communications ring via a first i/o set of the sending chip. A signal from the sending chip to a second receiving chip in the communications ring is transmitted via a second i/o set of the sending chip. The first i/o set corresponds to a first direction for the sending chip transmitting around the ring, and the second i/o set corresponds to a second direction for the sending chip transmitting around the ring. The transmitting via the first i/o set is for a circumstance where a number of chips interposed in the ring between the sending and receiving chips in the first direction is not greater than the number of chips interposed in the second direction. The transmitting via the second i/o set is for a circumstance where the number is greater.

Abstract: A processor includes at least one execution unit, an instruction sequencing unit coupled to the execution unit, and a plurality of caches at a same level. The caches, which store data utilized by the execution unit, have diverse cache hardware and each preferably store only data having associated addresses within a respective one of a plurality of subsets of an address space. The diverse cache hardware can include, for example, differing cache sizes, differing associativities, differing sectoring, and differing inclusivities.

Abstract: A processor includes at least one execution unit, an instruction sequencing unit coupled to the execution unit, and a plurality of caches at a same level. The caches, which store data utilized by the execution unit, each store only data having associated addresses within a respective one of a plurality of subsets of an address space and implement diverse caching behaviors. The diverse caching behaviors can include differing memory update policies, differing coherence protocols, differing prefetch behaviors, and differing cache line replacement policies.

Abstract: A method of improving memory access for a computer system, by sending load requests to a lower level storage subsystem along with associated information pertaining to intended use of the requested information by the requesting processor, without using a high level load queue. Returning the requested information to the processor along with the associated use information allows the information to be placed immediately without using reload buffers. A register load bus separate from the cache load bus (and having a smaller granularity) is used to return the information. An upper level (L1) cache may then be imprecisely reloaded (the upper level cache can also be imprecisely reloaded with store instructions). The lower level (L2) cache can monitor L1 and L2 cache activity, which can be used to select a victim cache block in the L1 cache (based on the additional L2 information), or to select a victim cache block in the L2 cache (based on the additional L1 information).

Abstract: A method of operating a multi-level memory hierarchy of a computer system and apparatus embodying the method, wherein instructions issue having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the prefetch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit.

Abstract: A method of improving memory access for a computer system, by sending load requests to a lower level storage subsystem along with associated information pertaining to intended use of the requested information by the requesting processor, without using a high level load queue. Returning the requested information to the processor along with the associated use information allows the information to be placed immediately without using reload buffers. A register load bus separate from the cache load bus (and having a smaller granularity) is used to return the information. An upper level (L1) cache may then be imprecisely reloaded (the upper level cache can also be imprecisely reloaded with store instructions). The lower level (L2) cache can monitor L1 and L2 cache activity, which can be used to select a victim cache block in the L1 cache (based on the additional L2 information), or to select a victim cache block in the L2 cache (based on the additional L1 information).

Abstract: A method and apparatus for efficiently managing caches with non-power-of-two congruence classes allows for increasing the number of congruence classes in a cache when not enough area is available to double the cache size. One or more congruence classes within the cache have their associative sets split so that a number of congruence classes are created with reduced associativity. The management method and apparatus allow access to the congruence classes without introducing any additional cycles of delay or complex logic.

Abstract: A method of operating a processing unit of a computer system, by issuing an instruction having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the prefetch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit (the latter feature is particularly useful for caches which are shared by a processing unit cluster).

Abstract: A method of operating a processing unit of a computer system, by issuing an instruction having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the prefetch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit (the latter feature is particularly useful for caches which are shared by a processing unit cluster).

Abstract: A method of operating a multi-level memory hierarchy of a computer system and apparatus embodying the method, wherein instructions issue having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions and treats instructions in a different manner when they are loaded speculatively. These prefetch requests can be demand load requests, where the processing unit will need the operand data or instructions, or speculative load requests, where the processing unit may or may not need the operand data or instructions, but a branch prediction or stream association predicts that they might be needed. The load requests are sent to the lower level cache when the upper level cache does not contain the value required by the load.

Abstract: A method of improving memory access for a computer system, by sending load requests to a lower level storage subsystem along with associated information pertaining to intended use of the requested information by the requesting processor, without using a high level load queue. Returning the requested information to the processor along with the associated use information allows the information to be placed immediately without using reload buffers. A register load bus separate from the cache load bus (and having a smaller granularity) is used to return the information. An upper level (L1) cache may then be imprecisely reloaded (the upper level cache can also be imprecisely reloaded with store instructions). The lower level (L2) cache can monitor L1 and L2 cache activity, which can be used to select a victim cache block in the L1 cache (based on the additional L2 information), or to select a victim cache block in the L2 cache (based on the additional L1 information).

Abstract: A data processing system having a modified processor chip and external components to the processor chip. The processor chip is interconnected to the external components via point-to-point bus connections controlled by an integrated distributed switch (IDS) controller. The IDS controller is placed, during chip design, in the upper layer metals of the processor chip. When the data processing system is a multi-chip multiprocessor data processing system, the IDS controller operates to provide a pseudo switching effect whereby the processor is directly connected to each external component. The IDS controller permits the processor to have greater communication bandwidth and reduced latencies with the external components. It also allows for a connection to distributed external components such as memory and I/O, etc. with overall reduced system components.