[PATCH] D22216: [ARM] Prefer indirect calls in minsize mode

[James Molloy via llvm-commits]

jmolloy created this revision.
jmolloy added reviewers: t.p.northover, mcrosier.
jmolloy added a subscriber: llvm-commits.
jmolloy set the repository for this revision to rL LLVM.
Herald added subscribers: rengolin, aemerson.

... When we emit several calls to the same function in the same basic block.

An indirect call uses a "BLX r0" instruction which has a 16-bit encoding. If many calls are made to the same target, this can enable significant code size reductions.

Repository:
  rL LLVM

http://reviews.llvm.org/D22216

Files:
  lib/Target/ARM/ARMISelLowering.cpp
  test/CodeGen/ARM/minsize-call-cse.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D22216.63496.patch
Type: text/x-patch
Size: 4919 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160711/eeecb125/attachment.bin>