diff options
author | Lang Hames <lhames@gmail.com> | 2012-06-19 22:51:23 +0000 |
---|---|---|
committer | Lang Hames <lhames@gmail.com> | 2012-06-19 22:51:23 +0000 |
commit | d693cafcfb9e67ba7040cb810e4409a166421482 (patch) | |
tree | 86a20682e48b7aaf402fc95f6497eae48e8fa89a /tools/llc | |
parent | fa8becb6f9e8aa2cbe3bab79e1fc4cdf2ffbb8e5 (diff) |
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
Diffstat (limited to 'tools/llc')
-rw-r--r-- | tools/llc/llc.cpp | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/tools/llc/llc.cpp b/tools/llc/llc.cpp index d0880913ba..b303cec3b5 100644 --- a/tools/llc/llc.cpp +++ b/tools/llc/llc.cpp @@ -156,8 +156,8 @@ DisableFPElimNonLeaf("disable-non-leaf-fp-elim", cl::init(false)); static cl::opt<bool> -DisableExcessPrecision("disable-excess-fp-precision", - cl::desc("Disable optimizations that may increase FP precision"), +EnableExcessPrecision("enable-excess-fp-precision", + cl::desc("Enable optimizations that may increase FP precision"), cl::init(false)); static cl::opt<bool> @@ -404,7 +404,7 @@ int main(int argc, char **argv) { Options.LessPreciseFPMADOption = EnableFPMAD; Options.NoFramePointerElim = DisableFPElim; Options.NoFramePointerElimNonLeaf = DisableFPElimNonLeaf; - Options.NoExcessFPPrecision = DisableExcessPrecision; + Options.AllowExcessFPPrecision = EnableExcessPrecision; Options.UnsafeFPMath = EnableUnsafeFPMath; Options.NoInfsFPMath = EnableNoInfsFPMath; Options.NoNaNsFPMath = EnableNoNaNsFPMath; |