Hal Finkel c404e8208c Optionally enable more-aggressive FMA formation in DAGCombine ... The heuristic used by DAGCombine to form FMAs checks that the FMUL has only one use, but this is overly-conservative on some systems. Specifically, if the FMA and the FADD have the same latency (and the FMA does not compete for resources with the FMUL any more than the FADD does), there is no need for the restriction, and furthermore, forming the FMA leaving the FMUL can still allow for higher overall throughput and decreased critical-path length. Here we add a new TLI callback, enableAggressiveFMAFusion, false by default, to elide the hasOneUse check. This is enabled for PowerPC by default, as most PowerPC systems will benefit. Patch by Olivier Sallenave, thanks! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218120 91177308-0d34-0410-b5e6-96231b3b80d8		2014-09-19 11:42:56 +00:00
..
AArch64	Optimize sext/zext insertion algorithm in back-end.	2014-09-19 05:30:35 +00:00
ARM	[ARM] Do not perform a tail call when the caller returns several values.	2014-09-18 21:17:50 +00:00
CPP
Generic
Hexagon
Inputs
Mips
MSP430
NVPTX
PowerPC	Optionally enable more-aggressive FMA formation in DAGCombine	2014-09-19 11:42:56 +00:00
R600	R600: Better fix for bug 20982	2014-09-19 00:42:06 +00:00
SPARC
SystemZ
Thumb
Thumb2
X86	[x86] Recognize that we can use duplication to widen v16i8 shuffles due	2014-09-19 09:45:21 +00:00
XCore