prefetchedA prefetch was inserted

Reported by --explain after a verdict.

mettle explain prefetched

The loop walks memory with a stride the compiler can see ahead of, so it asks for the line some iterations early. This hides part of the memory latency on a loop whose limit is bandwidth rather than arithmetic.

Related

• vectorizedThe loop became a SIMD kernel
• vectorized-innerThe inner loop of a nest became a kernel
• outer-of-nestThe outer loop of a nest, reported for context
• eliminatedThe loop was removed
• inlinedThe call was inlined
• unrolledThe loop was unrolled
• hoistedA call was lifted out of the loop
• if-convertedA branch became branchless arithmetic