Ahmed Bougacha 9e9bde9b54 [CodeGen] Don't blindly combine (fp_round (fp_round x)) to (fp_round x). ... We used to do this DAG combine, but it's not always correct: If the first fp_round isn't a value preserving truncation, it might introduce a tie in the second fp_round, that wouldn't occur in the single-step fp_round we want to fold to. In other words, double rounding isn't the same as rounding. Differential Revision: http://reviews.llvm.org/D7571 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228911 91177308-0d34-0410-b5e6-96231b3b80d8		2015-02-12 06:15:29 +00:00
..
AArch64	[CodeGen] Don't blindly combine (fp_round (fp_round x)) to (fp_round x).	2015-02-12 06:15:29 +00:00
ARM	[SimplifyCFG] Swap to using TargetTransformInfo for cost	2015-02-11 12:15:41 +00:00
BPF
CPP
Generic
Hexagon	[Hexagon] Factoring classes out of store patterns.	2015-02-09 20:33:46 +00:00
Inputs
Mips	Fix makeLibCall argument (signed) in SoftenFloatRes_XINT_TO_FP function	2015-02-10 23:30:14 +00:00
MSP430
NVPTX
PowerPC	[PowerPC] Mark jumps as expensive (using using CR bits)	2015-02-12 01:02:52 +00:00
R600	R600/SI: Disable subreg liveness	2015-02-11 18:24:53 +00:00
SPARC
SystemZ
Thumb
Thumb2	Make buildbots better.	2015-02-11 12:24:09 +00:00
X86	[CodeGen] Don't blindly combine (fp_round (fp_round x)) to (fp_round x).	2015-02-12 06:15:29 +00:00
XCore