RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2025-02-04 11:27:34 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Generate FSQRT from calls to the sqrt function, which

Browse Source 
allows appropriate backends to generate a sqrt instruction.

On x86, this isn't done at -O0 because we go through
FastISel instead.  This is a behavior change from before
this series of sqrt patches started.  I think this is OK
considering that compile speed is most important at -O0, but
could be convinced otherwise.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82778 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Dale Johannesen 2009-09-25 17:23:22 +00:00
parent 2702e6aa53
commit 52fb79b7f9
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
lib/CodeGen/SelectionDAG/SelectionDAGBuild.cpp
View File

@ -4576,6 +4576,15 @@ void SelectionDAGLowering::visitCall(CallInst &I) {
Tmp.getValueType(), Tmp));
return;
}
} else if (Name == "sqrt" || Name == "sqrtf" || Name == "sqrtl") {
if (I.getNumOperands() == 2 && // Basic sanity checks.
I.getOperand(1)->getType()->isFloatingPoint() &&
I.getType() == I.getOperand(1)->getType()) {
SDValue Tmp = getValue(I.getOperand(1));
setValue(&I, DAG.getNode(ISD::FSQRT, getCurDebugLoc(),
Tmp.getValueType(), Tmp));
return;
}
}
}
} else if (isa<InlineAsm>(I.getOperand(0))) {