[PATCH] [SDAG] Optimize unordered comparison in soft-float mode

[Anton Nadolskiy]

Hi resistor,

Current implementation handles unordered comparison poorly. 
Consider (a ULE b) which is a <= b. It is lowered to  (__ledf2(a, b) <= 0 || __unorddf2(a, b) != 0) (in general). We can do better job by lowering it to (__gtdf2(a, b) <= 0). 
Such replacement is true for other CMP's (ult, ugt, uge). In general, we just call same function as for ordered case but negate comparison against zero.

REPOSITORY
  rL LLVM

http://reviews.llvm.org/D10804

Files:
  lib/CodeGen/SelectionDAG/TargetLowering.cpp
  test/CodeGen/AArch64/arm64-fp128.ll
  test/CodeGen/Mips/mips16fpe.ll
  test/CodeGen/Thumb2/float-cmp.ll
  test/CodeGen/Thumb2/float-intrinsics-double.ll

EMAIL PREFERENCES
  http://reviews.llvm.org/settings/panel/emailpreferences/
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D10804.28671.patch
Type: text/x-patch
Size: 9754 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20150629/061173ff/attachment.bin>