摘要:
A mechanism is provided for generating a checkpoint for a speculatively executed portion of code. The mechanisms identify, during a speculative execution of a portion of code, a register renaming operation occurring to an entry in a register renaming table of the processor. In response to the register renaming operation occurring to the register renaming table, a determination is made as to whether an update to an entry in a hardware-implemented recovery renaming table is to be performed. If so, the entry in the hardware-implemented recovery renaming table is updated. The entry in the recovery renaming table is part of the checkpoint for the speculative execution of the portion of code.
摘要:
A scheme referred to as a “Region-based cache restoration prefetcher” (RECAP) is employed for cache preloading on a partition or a context switch. The RECAP exploits spatial locality to provide a bandwidth-efficient prefetcher to reduce the “cold” cache effect caused by multiprogrammed virtualization. The RECAP groups cache blocks into coarse-grain regions of memory, and predicts which regions contain useful blocks that should be prefetched the next time the current virtual machine executes. Based on these predictions, and using a simple compression technique that also exploits spatial locality, the RECAP provides a robust prefetcher that improves performance without excessive bandwidth overhead or slowdown.
摘要:
A scheme referred to as a “Region-based cache restoration prefetcher” (RECAP) is employed for cache preloading on a partition or a context switch. The RECAP exploits spatial locality to provide a bandwidth-efficient prefetcher to reduce the “cold” cache effect caused by multiprogrammed virtualization. The RECAP groups cache blocks into coarse-grain regions of memory, and predicts which regions contain useful blocks that should be prefetched the next time the current virtual machine executes. Based on these predictions, and using a simple compression technique that also exploits spatial locality, the RECAP provides a robust prefetcher that improves performance without excessive bandwidth overhead or slowdown.
摘要:
A computer-implemented method of cache replacement includes steps of: determining whether each cache block in a cache memory is a read or a write block; augmenting metadata associated with each cache block with an indicator of the type of access; receiving an access request resulting in a cache miss, the cache miss indicating that a cache block will need to be replaced; examining the indicator in the metadata of each cache block for determining a probability that said cache block will be replaced; and selecting for replacement the cache block with the highest probability of replacement.