A performance trap: when store forwarding fails

A store does not go straight into the cache. Waiting for that write would stall the processor. It sits in a store buffer, and a later load can take its bytes from that buffer. That is store forwarding. Forwarding works when the load is the same size as the store, or smaller and completely inside Continue reading A performance trap: when store forwarding fails

Reproduced from the Daniel Lemire feed. No model was used to write this entry — follow the link for the full article.