Abstract: The invention performs an extra read from a register of a register file prior to writing to that register. The data from the extra read is stored in a buffer (e.g., another register file). After a “checkpoint” period, a check is made as to whether any data errors have occurred; if there are no errors, the buffer is flushed and processing continues per normal; if there are errors, the register file is rewritten with contents from the buffer and the program counter is reset to the prior checkpoint, wherein after processing re-executes program instructions from the last checkpoint. The checkpointing period may be defined by the memory size of the buffer; typically that buffer has a fraction of the memory capacity of the register file, since a flush occurs at every checkpoint. The register file of the invention may utilize an extra read port with the register file to perform the extra read.

Abstract: A system is disclosed for generating a plurality of timeout event triggers in response to a plurality of kinds of timeout events. The system includes an overflow generator, which generates a plurality of overflow signals having a plurality of periods. The system also includes a plurality of trigger generators corresponding to the plurality of kinds of timeout events. Each of the plurality of trigger generators is associated with a corresponding timeout threshold value representing the minimum amount of time that must elapse for the trigger generator to generate a timeout event trigger. For each of the plurality of timeout triggers, a corresponding selection signal selects one of the plurality of periodic overflow signals. The timeout threshold corresponding to each timeout trigger is equal to the period of the corresponding selected overflow signal multiplied by the value of the corresponding control signal.

Abstract: A processing system including a plurality of processors, a cache data array, and a crossbar interface connecting the processors with the cache data array. Each processor includes a tag array mapped to the cache data array. In another embodiment, the cache data array includes a plurality of sub-arrays accessible via a plurality of ports of the crossbar interface. The system allows an upper-level cache data array to be shared among processors while cache latency is reduced.

Abstract: Microprocessor that includes a mechanism for detecting soft errors. The processor includes an instruction fetch unit for fetching an instruction and an instruction decoder for decoding the instruction. The mechanism for detecting soft errors includes duplication hardware for duplicating the instruction and comparison hardware. The processor further includes a first execution unit for executing the instruction in a first execution cycle and the duplicated instruction in a second execution cycle. The comparison hardware compares the results of the first execution cycle and the results of the second execution cycle. The comparison hardware can include an exception unit for generating an exception (e.g., raising a fault) when the results are not the same. The processor also includes a commit unit for committing one of the results when the results are the same.

Abstract: A processor that includes an in-order execution architecture for executing at least two instructions per cycle (e.g., 2n instructions are processed per cycle, where n is an integer greater than or equal to one) and at least two symmetric execution units. The processor includes an instruction fetch unit for fetching n instructions (where n is an integer greater than or equal to one) and an instruction decoder for decoding the n instruction. The error detection mechanism includes duplication hardware for duplicating the n instructions into a first bundle of n instructions and a second bundle of n instructions. A first execution unit for executing the first bundle of instructions in a first execution cycle, and a second symmetric execution unit for executing the second bundle of instructions in the first execution cycle are provided. The error detection mechanism also includes comparison hardware for comparing the results of the first execution unit and the results of the second execution unit.

Abstract: A multiple dispatch processor has several instruction fetch units, each for providing a stream of instructions to an instruction decode and dispatch unit. The processor also has an resource allocation unit, and multiple resources such as combined integer and address execution pipelines and floating point execution pipelines. Each instruction decode and dispatch unit requests resources needed to perform an instruction of the resource allocation unit, which arbitrates among the multiple instruction decode and dispatch units.

Abstract: Virtual-machine-monitor operation and implementation is facilitated by number of easily implemented features and extensions added to the features of a processor architecture. These features, one or more of which are used in various embodiments of the present invention, include a vmsw instruction that provides a means for transitioning between virtualization mode and non-virtualization mode without an interruption, a virtualization fault that faults on an attempt by a priority-0 routine in virtualization mode attempting to execute a privileged instruction, and a flexible highest-implemented-address mechanism to partition virtual address space into a virtualization address space and a non-virtualization address space.

Abstract: A processing system crossbar includes control sub-ports and mini-ports selectively configurable as connection points. Each control sub-port has a domain of mini-ports that the control sub-port is configured to selectively control. Each mini-port is configurable to select a control sub-port from those having domains that include the selecting mini-port. Each connection point includes a corresponding control sub-port and each mini-port selecting the corresponding control sub-port. The crossbar provides bandwidth tailored for various system agents. Thus crossbar bottlenecks are eliminated or reduced.

Abstract: A processing system includes a processor on a die, a cache memory external to the die, and a high-bandwidth interconnection between the processor and the cache memory. Where the cache is dynamic random access memory (DRAM), shorter latencies are generated than in traditional DRAM cache/processor configurations, yet higher density can be provided than available using SRAM caches.

Abstract: A processing system including a plurality of processors, a cache data array, and a crossbar interface connecting the processors with the cache data array. Each processor includes a tag array mapped to the cache data array. In another embodiment, the cache data array includes a plurality of sub-arrays accessible via a plurality of ports of the crossbar interface. The system allows an upper-level cache data array to be shared among processors while cache latency is reduced.

Abstract: A processing system crossbar includes control sub-ports and mini-ports selectively configurable as connection points. Each control sub-port has a domain of mini-ports that the control sub-port is configured to selectively control. Each mini-port is configurable to select a control sub-port from those having domains that include the selecting mini-port. Each connection point includes a corresponding control sub-port and each mini-port selecting the corresponding control sub-port. The crossbar provides bandwidth tailored for various system agents. Thus crossbar bottlenecks are eliminated or reduced.

Abstract: A multiple dispatch processor has several instruction fetch units, each for providing a stream of instructions to an instruction decode and dispatch unit. The processor also has an resource allocation unit, and multiple resources such as combined integer and address execution pipelines and floating point execution pipelines. Each instruction decode and dispatch unit requests resources needed to perform an instruction of the resource allocation unit, which arbitrates among the multiple instruction decode and dispatch units.

Abstract: The invention provides a processor with two or more parallel instruction paths for processing instructions. The instruction paths may be implemented with a plurality of cores on a common die. Instructions of the invention are preferably processed within a bundle of two or more instructions of a common program thread; and each of the instruction paths preferably forms a cluster to process bundled instructions. Each of the instruction paths has an array of pipelined execution units. Initially, two or more of the parallel instruction paths processes the same program thread (one or more bundles) through the execution units, but with different optimization characteristics set for each path. Assessment logic monitors the processing of the initial program thread through the execution units and selects the heuristics defining which path is in the lead.

Abstract: The invention provides a processor that processes bundles of instructions preferentially through clusters or execution units according to thread characteristics. The cluster architectures of the invention preferably include capability to process “multi-threaded” instructions. Selectively, the architecture either (a) processes singly-threaded instructions through a single cluster to avoid bypassing and to increase throughput, or (b) processes singly-threaded instructions through multiple processes to increase “per thread” performance. The architecture may be “configurable” to operate in one of two modes: in a “wide” mode of operation, the processor's internal clusters collectively process bundled instructions of one thread of a program at the same time; in a “throughput” mode of operation, those clusters independently process instruction bundles of separate program threads.

Abstract: The invention performs an extra read from a register of a register file prior to writing to that register. The data from the extra read is stored in a buffer (e.g., another register file). After a “checkpoint” period, a check is made as to whether any data errors have occurred; if there are no errors, the buffer is flushed and processing continues per normal; if there are errors, the register file is rewritten with contents from the buffer and the program counter is reset to the prior checkpoint, whereinafter processing re-executes program instructions from the last checkpoint. The checkpointing period may be defined by the memory size of the buffer; typically that buffer has a fraction of the memory capacity of the register file, since a flush occurs at every checkpoint. The register file of the invention may utilize an extra read port with the register file to perform the extra read.

Abstract: A system and method for reducing the power and the size of a cache memory is implemented by creating a large cache which is subdivided into a smaller cache. One tag controls both the large cache and the smaller, subdivided cache. A second tag controls only the smaller cache. In addition to saving power and area, this system and method may be used to reduce the write-through and write-back effort, improve the latency and the coherency of a cache memory, and improve the ability of multiprocessor system to snoop cache memory.

Abstract: A double cache snoop mechanism in uniprocessor computer systems having a cache and coherent I/O and multiprocessor computer systems reduces the number of cycles that a processor is stalled during a coherency check. The snoop mechanism splits each coherency check, such that a read-only check is first sent to the cache subsystem., and a read-write check is sent thereafter only if there is a cache hit during the read-only check, and there is the need to modify the cache. Average processor pipeline stall time is reduced even though a cache hit results in an additional coherency check because most coherency checks do not result in a cache hit.

Abstract: A cache system buffers data stored in a main memory and utilized by a processor. The cache system includes a first cache, a second cache, a first transfer channel, a second transfer channel and a third transfer channel. The first cache is fully associative. The second cache is directly mapped. The first transfer channel transfers data lines from the main memory to the first cache. The second transfer channel transfers data lines from the first cache to the second cache. The third transfer channel transfers data lines from the second cache to the main memory. Accesses of data lines from the first cache and the second cache are performed in parallel.