Abstract: A method and computer system for reducing the wiring congestion, required real estate, and access latency in a cache subsystem with a sectored and sliced lower cache by re-configuring sector-to-slice allocation and the lower cache addressing scheme. With this allocation, sectors having discontiguous addresses are placed within the same slice, and a reduced-wiring scheme is possible between two levels of lower caches based on this re-assignment of the addressable sectors within the cache slices. Additionally, the lower cache effective address tag is re-configured such that the address fields previously allocated to identifying the sector and the slice are switched relative to each other's location within the address tag. This re-allocation of the address bits enables direct slice addressing based on the indicated sector.

Abstract: A cache memory logically partitions a cache array having a single access/command port into at least two slices, and uses a first directory to access the first array slice while using a second directory to access the second array slice, but accesses from the cache directories are managed using a single cache arbiter which controls the single access/command port. In one embodiment, each cache directory has its own directory arbiter to handle conflicting internal requests, and the directory arbiters communicate with the cache arbiter. The cache array is arranged with rows and columns of cache sectors wherein a cache line is spread across sectors in different rows and columns, with a portion of the given cache line being located in a first column having a first latency and another portion of the given cache line being located in a second column having a second latency greater than the first latency.

Abstract: A method, system, and device for enabling intervention across same-level cache memories. In a preferred embodiment, responsive to a cache miss in a first cache memory a direct intervention request is sent from the first cache memory to a second cache memory requesting a direct intervention that satisfies the cache miss. In an alternate embodiment, direct intervention is utilized to access a same-level victim cache.

Abstract: A cache memory logically associates a cache line with at least two cache sectors of a cache array wherein different sectors have different output latencies and, for a load hit, selectively enables the cache sectors based on their latency to output the cache line over successive clock cycles. Larger wires having a higher transmission speed are preferably used to output the cache line corresponding to the requested memory block. In the illustrative embodiment the cache is arranged with rows and columns of the cache sectors, and a given cache line is spread across sectors in different columns, with at least one portion of the given cache line being located in a first column having a first latency, and another portion of the given cache line being located in a second column having a second latency greater than the first latency.

Abstract: A cache memory logically partitions a cache array having a single access/command port into at least two slices, and uses a first directory to access the first array slice while using a second directory to access the second array slice, but accesses from the cache directories are managed using a single cache arbiter which controls the single access/command port. In one embodiment, each cache directory has its own directory arbiter to handle conflicting internal requests, and the directory arbiters communicate with the cache arbiter. The cache array is arranged with rows and columns of cache sectors wherein a cache line is spread across sectors in different rows and columns, with a portion of the given cache line being located in a first column having a first latency and another portion of the given cache line being located in a second column having a second latency greater than the first latency.

Abstract: A method and computer system for reducing the wiring congestion, required real estate, and access latency in a cache subsystem with a sectored and sliced lower cache by re-configuring sector-to-slice allocation and the lower cache addressing scheme. With this allocation, sectors having discontiguous addresses are placed within the same slice, and a reduced-wiring scheme is possible between two levels of lower caches based on this re-assignment of the addressable sectors within the cache slices. Additionally, the lower cache effective address tag is re-configured such that the address fields previously allocated to identifying the sector and the slice are switched relative to each other's location within the address tag. This re-allocation of the address bits enables direct slice addressing based on the indicated sector.

Abstract: A cache memory logically partitions a cache array having a single access/command port into at least two slices, and uses a first cache directory to access the first cache array slice while using a second cache directory to access the second cache array slice, but accesses from the cache directories are managed using a single cache arbiter which controls the single access/command port. In the illustrative embodiment, each cache directory has its own directory arbiter to handle conflicting internal requests, and the directory arbiters communicate with the cache arbiter. An address tag associated with a load request is transmitted from the processor core with a designated bit that associates the address tag with only one of the cache array slices whose corresponding directory determines whether the address tag matches a currently valid cache entry.

Abstract: A cache memory logically associates a cache line with at least two cache sectors of a cache array wherein different sectors have different output latencies and, for a load hit, selectively enables the cache sectors based on their latency to output the cache line over successive clock cycles. Larger wires having a higher transmission speed are preferably used to output the cache line corresponding to the requested memory block. In the illustrative embodiment the cache is arranged with rows and columns of the cache sectors, and a given cache line is spread across sectors in different columns, with at least one portion of the given cache line being located in a first column having a first latency, and another portion of the given cache line being located in a second column having a second latency greater than the first latency.

Abstract: A method, system, and device for enabling intervention across same-level cache memories. In a preferred embodiment, responsive to a cache miss in a first cache memory a direct intervention request is sent from the first cache memory to a second cache memory requesting a direct intervention that satisfies the cache miss. In an alternate embodiment, direct intervention is utilized to access a same-level victim 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 (Li) 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 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 a respective one of a plurality of data streams. If an error is detected in a particular hardware partition, the data stream assigned to that hardware partition is reassigned to another of the plurality of hardware partitions, thus preventing an error in one of the hardware partitions from resulting in a catastrophic failure.

Abstract: A processor includes execution resources, data storage, and an instruction sequencing unit, coupled to the data storage and the execution resources, that supplies instructions within the data storage to the execution resources. The execution resources include a plurality of load-store units that each process only instructions that access data having associated addresses within a respective one of a plurality of subsets of an address space. The load-store units can have diverse hardware such that a maximum number of instructions that can be concurrently executed is different for different load-store units or such that some of the load-store units are restricted to executing certain classes of instructions.

Abstract: An information handling system includes a producer that outputs packets, a buffer that receives packets from the producer, buffers the packets, and eventually outputs the packets, and a control unit that controls the flow of packets from the producer to the buffer. The control unit receives as inputs a producer output indication indicating that the producer has output a packet to the buffer and a buffer output indication indicating that the buffer has output a packet. Based upon a capacity of the buffer, a number of the producer output indications, a number of buffer output indications, and a number of grant messages output to the producer within a feedback latency of the control unit, the control unit whether the producer can output a packet without packet loss. In response to a determination that the producer can output a packet without packet loss, the control unit outputs a grant message to the producer indicating that the producer is permitted to output a packet.

Abstract: An information handling system includes a plurality of producers that output packets of information, at least one consumer of the packets, and an information pipeline coupling the consumer and at least a particular producer among the plurality of producers. The information pipeline includes a shared resource having a bandwidth shared by multiple of the plurality of producers. The information handling system further includes a control unit that regulates packet output of the particular producer and that receives as inputs a producer output indication indicating that the particular producer output a packet and a shared resource input indication indicating that a packet output by the particular producer has been accepted by the shared resource for transmission to the consumer.

Abstract: An information handling system includes a producer that outputs packets of information, a plurality of buffers that can each receive packets from the producer and output the packets, and a control unit. The control unit receives at least one producer output indication indicating whether the producer output a packet to one of the plurality of buffers and a plurality of buffer output indications that each indicate whether a respective one of the plurality of buffers has output a packet. Based upon capacities of the plurality of buffers, the producer output indications, the buffer output indications and a number of grant messages output to the producer within a feedback latency of the control unit, the control unit whether the producer can output a packet without packet loss. If so, the control unit provides a grant message to the producer indicating that the producer is permitted to output a packet.

Abstract: A processor having a hashed and partitioned storage subsystem includes at least one execution unit, an instruction sequencing unit coupled to the execution unit, and a cache subsystem including a plurality of caches that store data utilized by the execution unit. Each cache among the plurality of caches stores only data having associated addresses within a respective one of a plurality of subsets of an address space. In one preferred embodiment, the execution units of the processor include a number of load-store units (LSUs) that each process only instructions that access data having associated addresses within a respective one of the plurality of address subsets. The processor may further be incorporated within a data processing system having a number of interconnects and a number of sets of system memory hardware that each have affinity to a respective one of the plurality of address subsets.

Abstract: An information handling system includes a plurality of sequentially connected units including a first unit, a second unit and a third unit. Packets of information flow from the first unit directly to the second unit and then to the third unit, and each of the plurality of units provides a respective dynamic output indication indicating if that unit output a packet. The information handling system further includes a control unit that determines, utilizing all of the plurality of dynamic output indications, packet buffering capacities of the plurality of units, and guaranteed packet flows between adjacent ones of the plurality of units, if the first unit can output a packet directly to the second unit without packet loss. In response to this determination, the control unit outputs a control signal to the first unit.

Abstract: A data processing system with configurable processor chip buses. The processor chip is designed with a plurality of extended buses of which a number are configurable buses (i.e., capable of being allocated to one of several external components, particularly memory and other SMPs). The processor chip allows for the static allocation of these configurable buses to these external components, based primarily on vendor system design preferences.

Abstract: A Fully Interconnected System Architecture (FISA) for an improved data processing system. The data processing system topology has a processor chip and external components to the processor chip, such as memory and input/output (I/O) and other processor chips. The processor chip is interconnected to the external components via a point-to-point bus topology controlled by an intra-chip integrated, distributed switch (IDS) controller. The IDS controller provides the chip with the functionality to provide a single bus to each external component and provides an overall total bandwidth greater than traditional topologies while reducing latencies between the processor and the external components. The design of the processor chip with the intra-chip IDS controller provides a pseudo “distributed switch” which may separately access distributed external components, such as memory and I/Os, etc.

Abstract: A data processing system with configurable processor chip buses. The processor chip is designed with a bus allocation unit and has a plurality of extended buses of which a number are configurable buses (i.e. may be dynamically allocated to any one of several external components, particularly memory and other SMPs). A priority determination of bandwidth requirements of the external components is made during system processing. Then the configurable buses are dynamically allocated to the external components based on their bandwidth requirement and/or the configuration which provides the best overall system efficiency.