摘要:
A data processing system 2 utilizes a register renaming mechanism 10, 26 to rename architectural register specifiers to physical register specifiers to facilitate out-of-order processing. The register renaming mechanism 10, 26 includes a renaming recovery unit 26 which enables recovery from incorrectly executed speculative instructions by restoring the register mapping to the state prior to those incorrect instructions with the physical registers restored to containing the data values which were current at the time prior to that incorrect instruction. In the case of load instructions, these are treated as speculative but the data value returned in response to the load instruction and stored within a physical register is released for use as soon as it is returned and prior to a determination result being available as to whether or not that data value is corrupt. Corruption checking an take the form of ECC checking, parity checking and the like, and when a late error signal is generated then this indicates whether or not the data value has been properly released for use. If corruption is detected, then the renaming recovery unit 26 is used to recover the state of the system 2 in a precise way to that preceding the failing load instruction.
摘要:
A data processing system 2 utilises a register renaming mechanism 10, 26 to rename architectural register specifiers to physical register specifiers to facilitate out-of-order processing. The register renaming mechanism 10, 26 includes a renaming recovery unit 26 which enables recovery from incorrectly executed speculative instructions by restoring the register mapping to the state prior to those incorrect instructions with the physical registers restored to containing the data values which were current at the time prior to that incorrect instruction. In the case of load instructions, these are treated as speculative but the data value returned in response to the load instruction and stored within a physical register is released for use as soon as it is returned and prior to a determination result being available as to whether or not that data value is corrupt. Corruption checking an take the form of ECC checking, parity checking and the like, and when a late error signal is generated then this indicates whether or not the data value has been properly released for use. If corruption is detected, then the renaming recovery unit 26 is used to recover the state of the system 2 in a precise way to that preceding the failing load instruction.
摘要:
The present application discloses register renaming circuitry for mapping registers from an architectural set of registers to registers within a physical set of registers, said architectural set of registers being registers specified by instructions within an instruction set and said physical set of registers being registers within a processor for processing instructions of said instruction set, said instruction set comprising exception instructions and non-exception instructions, exception instructions being instructions that may generate an exception and non-exception instructions being instructions that execute in a statically determinable way, said register renaming circuitry comprising: a first data store for storing a future renaming table, said future renaming table comprising renaming values for mapping registers from said architectural set of registers to registers in said physical set of registers for instructions that are to be executed or are currently being executed by said processor; a second data store for storing a recovery renaming table, said recovery renaming table comprising a most recently committed mapping of said processor; wherein said register renaming circuitry is responsive to detection of a predetermined condition to mark said physical registers not mapped in said recovery renaming table as available for renaming.
摘要:
Within a data processing system 2 including a register renaming mechanism 8, 22, register renaming for some conditional instructions which are predicted as not-executed is suppressed. The conditional instructions which are subject to such suppression of renaming may not be all conditional instructions, but may be those which are known to consume a particularly large number of physical registers 24 if they are subject to renaming A conditional load multiple instruction in which multiple registers are loaded with new data values taken from memory in response to signal instruction is an example where the present technique may be used, particularly when one of the registers loaded is the program counter and accordingly the instruction is a conditional branch.
摘要:
A data processing apparatus and method are provided for converting data values from a first endian format to a second endian format. Swizzle circuitry is provided within the data processing apparatus for receiving a block of data containing at least one data value, and for converting each data value in the block from the first endian format to the second endian format. The swizzle circuitry comprises first swizzle circuitry for performing a re-ordering operation on the block of data assuming the at least one data value contained therein is of a first predetermined size, in order to produce re-ordered data. Further, second swizzle circuitry is provided which is responsive to an indication that the at least one data value is of a size different to the first predetermined size to perform an additional re-ordering operation on the re-ordered data having regard to the size of the at least one data value in order to convert each data value to the second endian format. The swizzle circuitry is responsive to an indication that the at least one data value is of the first predetermined size to output the re-ordered data produced by the first swizzle circuitry, whereas otherwise the swizzle circuitry outputs the data produced by the second swizzle circuitry. This can reduce the complexity of swizzle circuitry provided on a critical path, by optimising the swizzle circuitry to handle endian conversion for data values of the first predetermined size, at the expense of data values that are of other sizes requiring more time for the endian conversion operation to be completed.
摘要:
A processor 2 utilising register renaming executes program instructions requiring a large number of architectural register specifiers to be renamed by dividing the renaming tasks into an initial set and a remaining set. The initial set are performed first and the results passed via a main channel 32 for further processing. The remaining set are performed in sequence with the results being passed via a background channel 34 for further processing. This technique is particularly useful for performing renaming operations for load/store multiple LDM instructions.
摘要:
A data processing apparatus 2 supports out-of-order processing register renaming using a renaming stage 8. A set of physical registers 16 is mapped to architectural registers. Available-register identifying logic 26 is used to identify which physical registers 16 are available for use by the renaming stage 8. The available-register identifying logic 26 includes an instruction FIFO 28 storing register mapping data for unresolved instructions and indicating physical registers 16 storing data values which may be required in association with those unresolved speculative instructions. The speculative instructions may be predicted branch instructions, load/store instructions, conditional instructions or other types of instruction.
摘要:
A data processing apparatus 2 supports out-of-order processing register renaming using a renaming stage 8. A set of physical registers 16 is mapped to architectural registers. Available-register identifying logic 26 is used to identify which physical registers 16 are available for use by the renaming stage 8. The available-register identifying logic 26 includes an instruction FIFO 28 storing register mapping data for unresolved instructions and indicating physical registers 16 storing data values which may be required in association with those unresolved speculative instructions. The speculative instructions may be predicted branch instructions, load/store instructions, conditional instructions or other types of instruction.
摘要:
Control logic for storing values relating to unresolved exception instructions within a buffer to enable a register renaming table within a processor to be restored following an exception is disclosed. The processor is operable to process a stream of instructions from an instruction set, the instruction set comprising exception instructions and non-exception instructions, exception instructions being instructions that may generate an exception and non-exception instructions being instructions that execute in a statically determinable way. The processor comprises a physical set of registers operable to store data values being processed by the processor; and register renaming logic operable to receive a stream of decoded instructions and to map for each decoded instruction within the stream of decoded instructions, registers from an architectural set of registers associated with the instruction set to registers within the physical set of registers in dependence upon renaming values stored in the register renaming table; the control logic comprising a buffer and being operable: to identify exception and non-exception instructions within the decoded instruction stream and to group any non-exception instructions with a closest preceding exception instruction; to store in the buffer, register renaming values relating to any registers whose data values are modified by the group of instructions and which are renamed by the register renaming logic as a bundle of register renaming values associated with the exception instruction.
摘要:
A store buffer, method and data processing apparatus is disclosed. The store buffer comprises: reception logic operable to receive a request to write a data value to an address in memory; buffer logic having a plurality of entries, each entry being selectively operable to store request information indicative of a previous request and to maintain associated cache information indicating whether a cache line in a cache is currently allocated for writing data values to an address associated with that request; and entry selection logic operable to determine which one of the plurality entries to allocate to store the request using the request information and the associated cache information of the plurality of entries to determine whether a cache line in the cache is currently allocated for writing the data value to the address in memory. By reviewing the entries in the buffer logic and identifying which entry to store the request based on information currently stored by the buffer logic, the need to obtain cache information indicating whether any cache line in a cache is currently allocated for writing the data value may be obviated. In turn, the need to perform a cache look up to obtain the cache information may also be obviated. It will be appreciated that by obviating the need to perform a cache lookup, the power consumption of the store buffer may be reduced. Also, the amount of cache bandwidth consumed by performing unnecessary cache lookups may also be reduced, thereby significantly improving the performance of the cache.