Add DAG-combines for aggressive FMA formation.

This patch adds DAG combines to form FMAs from pairs of FADD + FMUL or
FSUB + FMUL. The combines are performed when:
(a) Either
      AllowExcessFPPrecision option (-enable-excess-fp-precision for llc)
        OR
      UnsafeFPMath option (-enable-unsafe-fp-math)
    are set, and
(b) TargetLoweringInfo::isFMAFasterThanMulAndAdd(VT) is true for the type of
    the FADD/FSUB, and
(c) The FMUL only has one user (the FADD/FSUB).

If your target has fast FMA instructions you can make use of these combines by
overriding TargetLoweringInfo::isFMAFasterThanMulAndAdd(VT) to return true for
types supported by your FMA instruction, and adding patterns to match ISD::FMA
to your FMA instructions.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158757 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 8 insertions, 8 deletions

diff --git a/include/llvm/Target/TargetOptions.h b/include/llvm/Target/TargetOptions.h
index bc60673..84287fb 100644
--- a/include/llvm/Target/TargetOptions.h
+++ b/include/llvm/Target/TargetOptions.h
@@ -35,7 +35,7 @@ namespace llvm {
     TargetOptions()
         : PrintMachineCode(false), NoFramePointerElim(false),
           NoFramePointerElimNonLeaf(false), LessPreciseFPMADOption(false),
-          NoExcessFPPrecision(false), UnsafeFPMath(false), NoInfsFPMath(false),
+          AllowExcessFPPrecision(false), UnsafeFPMath(false), NoInfsFPMath(false),
           NoNaNsFPMath(false), HonorSignDependentRoundingFPMathOption(false),
           UseSoftFloat(false), NoZerosInBSS(false), JITExceptionHandling(false),
           JITEmitDebugInfo(false), JITEmitDebugInfoToDisk(false),
@@ -74,13 +74,13 @@ namespace llvm {
     unsigned LessPreciseFPMADOption : 1;
     bool LessPreciseFPMAD() const;
 
-    /// NoExcessFPPrecision - This flag is enabled when the
-    /// -disable-excess-fp-precision flag is specified on the command line.
-    /// When this flag is off (the default), the code generator is allowed to
-    /// produce results that are "more precise" than IEEE allows.  This includes
-    /// use of FMA-like operations and use of the X86 FP registers without
-    /// rounding all over the place.
-    unsigned NoExcessFPPrecision : 1;
+    /// AllowExcessFPPrecision - This flag is enabled when the
+    /// -enable-excess-fp-precision flag is specified on the command line. This
+    /// flag is OFF by default. When it is turned on, the code generator is
+    /// allowed to produce results that are "more precise" than IEEE allows.
+    /// This includes use of FMA-like operations and use of the X86 FP registers
+    /// without rounding all over the place.
+    unsigned AllowExcessFPPrecision : 1;
 
     /// UnsafeFPMath - This flag is enabled when the
     /// -enable-unsafe-fp-math flag is specified on the command line.  When