Abstract: A set-associative cache memory having a mechanism for migrating a most recently used set 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 migration means for directing the information from a cache “hit” to a predetermined set of the cache memory.

Abstract: A set-associative cache memory having incremental access latencies 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. In accordance with a preferred embodiment of the present invention, the cache memory further includes a means for accessing each of the sets with an access time dependent on a relative location of each of the sets such that access latency varies incrementally among sets.

Abstract: Only a single snooper queue for global operations within a multiprocessor system is implemented within each bus snooper, controlled by a single token allowing completion of one operation. A bus snooper, upon detecting a combined token and operation request, begins speculatively processing the operation if the snooper is not already busy. The snooper then watches for a combined response acknowledging the combined request or a subsequent token request from the same processor, which indicates that the originating processor has been granted the sole token for completing global operations, before completing the operation. When processing an operation from a combined request and detecting an operation request (only) from a different processor, which indicates that another processor has been granted the token, the snooper suspends processing of the current operation and begins processing the new operation.

Abstract: Serialization of global operations within a multi-processor system is achieved utilizing a plurality of tokens each permitting completion of a single global operation, requiring a bus master to acquire the token for completion of each individual global operation initiated by that bus master. A combined token and operation request, in which a token request and an operation request are transmitted in a single bus transaction, is employed once for a global operation, to initiate the global operation for the first time. A token manager determines whether a token is available or all are checked out and responds to the token portion of the combined request. Snoopers respond to the operation portion of the combined request depending on whether they are busy. If at least the token portion of the combined request is acknowledged or if a token request is acknowledged, the combined response will include a token number for the token granted to the bus master initiating the global operation.

Abstract: Disclosed herein are a data processing system and method of operating a data processing system that arbitrate between conflicting requests to modify data cached in a shared state and that protect ownership of the cache line granted during such arbitration until modification of the data is complete. The data processing system includes a plurality of agents coupled to an interconnect that supports pipelined transactions. While data associated with a target address are cached at a first agent among the plurality of agents in a shared state, the first agent issues a transaction on the interconnect. In response to snooping the transaction, a second agent provides a snoop response indicating that the second agent has a pending conflicting request and a coherency decision point provides a snoop response granting the first agent ownership of the data.

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: Serialization of global operations within a multiprocessor system is achieved utilizing a single token, requiring a bus master to acquire the token for completion of one or more global operations to be initiated by that bus master. A combined token and operation request, in which a token request and an operation request are transmitted in a single bus transaction, is employed once for a global operation, to initiate the global operation for the first time. A token manager determines whether the token is available and released and, if available but not released, whether the token is checked out to the bus master originating the combined token and operation request. If the token is available and released or is available and was last checked out to the bus master originating the combined token and operation request, the token manager acknowledges to the token portion of the combined request; otherwise the token manager retries the token portion of the combined request.

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 handling a write operation in a multiprocessor computer system wherein each processing unit has a respective cache, by determining that a new value for a store instruction is the same as a current value already contained in the memory hierarchy, and discarding the store instruction without issuing any associated cache operation in response to this determination. When a store hit occurs, the current value is retrieved from the local cache. When a store miss occurs, the current value is retrieved from a remote cache by issuing a read request. The comparison may be performed using a portion of the cache line which is less than a granule size of the cache line. A store gathering queue can be use to collect pending store instructions that are directed to different portions of the same cache line.

Abstract: A method of maintaining coherency in a cache hierarchy of a processing unit of a computer system, wherein the upper level (L1) cache includes a split instruction/data cache. In one implementation, the L1 data cache is store-through, and each processing unit has a lower level (L2) cache. When the lower level cache receives a cache operation requiring invalidation of a program instruction in the L1 instruction cache (i.e., a store operation or a snooped kill), the L2 cache sends an invalidation transaction (e.g., icbi) to the instruction cache. The L2 cache is fully inclusive of both instructions and data. In another implementation, the L1 data cache is write-back, and a store address queue in the processor core is used to continually propagate pipelined address sequences to the lower levels of the memory hierarchy, i.e., to an L2 cache or, if there is no L2 cache, then to the system bus. If there is no L2 cache, then the cache operations may be snooped directly against the L1 instruction cache.

Abstract: A method of handling a write operation in a multiprocessor computer system wherein each processing unit has a respective cache, by determining that a new value for a store instruction is the same as a current value already contained in the memory hierarchy, and discarding the store instruction without issuing any associated cache operation in response to this determination. When a store hit occurs, the current value is retrieved from the local cache. When a store miss occurs, the current value is retrieved from a remote cache by issuing a read request. The comparison may be performed using a portion of the cache line which is less than a granule size of the cache line. A store gathering queue can be use to collect pending store instructions that are directed to different portions of the same cache line.

Abstract: A method of maintaining coherency in a cache hierarchy of a processing unit of a computer system, wherein the upper level (L1) cache includes a split instruction/data cache. In one implementation, the L1 data cache is store-through, and each processing unit has a lower level (L2) cache. When the lower level cache receives a cache operation requiring invalidation of a program instruction in the L1 instruction cache (i.e., a store operation or a snooped kill), the L2 cache sends an invalidation transaction (e.g., icbi) to the instruction cache. The L2 cache is fully inclusive of both instructions and data. In another implementation, the L1 data cache is write-back, and a store address queue in the processor core is used to continually propagate pipelined address sequences to the lower levels of the memory hierarchy, i.e., to an L2 cache or, if there is no L2 cache, then to the system bus. If there is no L2 cache, then the cache operations may be snooped directly against the L1 instruction cache.

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 system for time-ordered execution of load instructions. More specifically, the system enables just-in-time delivery of data requested by a load instruction. The system consists of a processor, an L1 data cache with corresponding L1 cache controller, and an instruction processor. The instruction processor manipulates an architected time dependency bit field of a load instruction to create a Distance of Dependency (DoD) bit field. The DoD bit field holds a relative dependency value which is utilized to order the load instruction in a Relative Time-Ordered Queue (RTOQ) of the L1 cache controller. The load instruction is sent from RTOQ to the L1 data cache at a particular time so that the data requested is loaded from the L1 data cache at the time specified by the DoD bit field. In the preferred embodiment, an acknowledgement is sent to the processing unit when the time specified is available in the RTOQ.

Abstract: A system for time-ordered issuance of instruction fetch requests (IFR). More specifically, the system enables just-in-time delivery of instructions requested by an IFR. The system consists of a processor, an L1 instruction cache with corresponding L1 cache controller, and an instruction processor. The instruction processor manipulates an architected time dependency field of an IFR to create a Time of Dependency (ToD) field. The ToD field holds a time dependency value which is utilized to order the IFR in a Relative Time-Ordered Queue (RTOQ) of the L1 cache controller. The IFR is issued from RTOQ to the L1 instruction cache so that the requested instruction is fetched from the L1 instruction cache at the time specified by the ToD value. In an alternate embodiment the ToD is converted to a CoD and the instruction is fetched from a lower level cache at the CoD value.

Abstract: A method for converting a distance of dependency (DoD) value to a cycle of dependency (CoD) value is disclosed. The method comprises the steps of (i) simulating a dependency system timer (DST) on a data processing system, with the DST having a present time measured in cycles and a period, (ii) adding a DoD value of N bits to the present time to yield a resulting time of the least significant N bits of said adding step, and (iii) creating the CoD value by appending a carry over of the adding step to the resulting time, where when the carry over is not equal to zero, the carry over signals a user of the CoD value to wait until a next period before the CoD value should be applied. In one embodiment, the carry-over value is added to the value corresponding to a respective alternating period to yield an even/odd bit which determines the period.

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 avoiding deadlocks in cache coherency protocol for a multi-processor computer system, by loading a memory value into a plurality of cache blocks, assigning a first coherency state having a higher collision priority to only one of the cache blocks, and assigning one or more additional coherency states having lower collision priorities to all of the remaining cache blocks. Different system bus codes can be used to indicate the priority of conflicting requests (e.g., DClaim operations) to modify the memory value. The invention also allows folding or elimination of redundant DClaim operations, and can be applied in a global versus local manner within a multi-processor computer system having processing units grouped into at least two clusters.