mirror of
https://github.com/intel/llvm.git
synced 2026-01-17 14:48:27 +08:00
memory cache subsystem so we're reading only the 4 bytes needed to check for the magic word at the start of a mach-o binary instead of the default 512 block. It can be a small performance help to reduce the size of memory reads from possibly unmapped memory. <rdar://problem/29256385> llvm-svn: 286926