Stop asking the Go compiler to reorder struct fields for zero-padding. The layout reflects access patterns, not just byte sizes. As rsc reasoned: the compiler is blind to the hot path, and trashing CPU cache lines just to squeeze memory is missing the forest for the trees.
github.com/golang/go/issu…
TIL: you can increase hot loop performance by 20x by properly exploiting store forwarding property on modern CPUs. And Go better fits than Rust for achieving this performance boost, since it doesn't automatically reorder struct fields.
