Abstract: A pipelined microprocessor having a branch prediction unit implemented in an instruction pointer generation stage of the microprocessor. The branch prediction unit includes a memory device having at least a first entry configured to hold at least a part of a memory address of a pre-selected branch instruction and at least a part of a memory address of a branch target corresponding to the pre-selected branch instruction. The branch prediction unit compares an instruction pointer of an instruction to be executed with the memory address of the pre-selected branch instruction. In response to a match between the instruction pointer and the memory address of pre-selected branch instruction, the unit causes the microprocessor to fetch an instruction corresponding to the branch target. In one embodiment, the instruction pointer generation stage of the microprocessor is implemented as a first stage of the pipelined microprocessor.

Abstract: A memory device including an array of memory cells and a method for copying information within the memory device. Each memory cell includes a first memory sub-cell and a second memory sub-cell. Each memory cell also includes a device that copies information from the first memory sub-cell into the second memory sub-cell. Each memory cell may include a static random access memory (SRAM) cell and may utilize tri-state inverters to make overwriting information easier and reduce power consumption. Each memory cell may also include a second copy device that allows information to be copied from the second memory sub-cell to the first memory sub-cell. The memory device may be provided in a register file of a microprocessor to copy information from an architectural branch register (ABR) file to a speculative branch register (SBR) file.

Abstract: A method and apparatus for dynamically predicting the outcome and the tar address of a multiple-target branch instruction, where the multiple-target branch instruction contains at least two potential target addresses, not including the fall through address. In addition, this method and apparatus can also be used to predict multiple single-target branches simultaneously. The apparatus stores information indicating the outcome of previous executions and predictions of the multiple-target branch instruction in a branch prediction table. In addition, multiple target addresses (at least two) are associated with the multiple-target branch instruction. Using the information indicating the outcome of the previous execution of the multiple-target branch instruction, the apparatus predicts the outcome of a next execution of the multiple-target branch instruction, and predicts which, if any, of the target addresses associated with the multiple-target branch instruction, will be taken.

Abstract: A branch prediction system is described for use within a microprocessor having an instruction cache capable of storing two or more instructions per cache line. Each entry of a branch prediction table (BPT) includes a value identifying whether at least one other instruction within a common cache line contains a branch. The value is referred to herein as a multiple-B bit value. The multiple-B bit value is examined by branch prediction logic while one branch prediction is being performed to determine whether a second branch prediction can be initiated for another branch within the same cache line. In one implementation, the multiple-B bit of one BPT entry is examined following a hit. A branch prediction for the entry generating a hit is initiated. Simultaneously, the BPT is reaccessed to search for an entry corresponding to another instruction within the same cache line if the multiple-B bit for the first entry was set. If the second entry is found, a secondary branch prediction is initiated.

Abstract: Allocation circuitry for allocating entries within a set-associative cache memory is disclosed. The set-associative cache memory comprises N ways, each way having M entries and corresponding entries in each of the N ways constituting a set of entries. The allocation circuitry has a first circuit which identifies related data units by identifying a probability that the related data units may be successively read from the cache memory. A second circuit within the allocation circuitry allocates the corresponding entries in each of the ways to the related data units, so that related data units are stored in a common set of entries. Accordingly, the related data units will be simultaneously outputted from the set-associative cache memory, and are thus concurrently available for processing. The invention may find application in allocating entries of a common set in a branch prediction table (BPT) to branch prediction information for related branch instructions.