maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

This Patch corrects a problem whereby the optimization to use a faster divide 

instruction (for Intel Atom) was not being done by Clang, because
the type context used by Clang is not the default context.

It fixes the problem by getting the global context types for each div/rem
instruction in order to compare them against the types in the BypassTypeMap.

Tests for this will be done as a separate patch to Clang.

Patch by Tyler Nowicki.

llvm-svn: 165126
This commit is contained in:
Preston Gurd 2012-10-03 16:11:44 +00:00
parent 7cbc12a41d
commit 5509e3d727
1 changed files with 16 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
llvm/lib/Transforms/Utils/BypassSlowDivision.cpp
View File

@ -238,14 +238,24 @@ bool llvm::bypassSlowDivision(Function &F,
if (!UseDivOp && !UseRemOp)
continue;
// Continue if div/rem type is not bypassed
DenseMap<Type *, Type *>::const_iterator BT =
BypassTypeMap.find(J->getType());
if (BT == BypassTypeMap.end())
// Skip division on vector types, only optimize integer instructions
if (!J->getType()->isIntegerTy())
continue;
IntegerType *BypassType = cast<IntegerType>(BT->second);
MadeChange |= reuseOrInsertFastDiv(F, I, J, BypassType, UseDivOp,
// Get same type in global context
IntegerType *T = cast<IntegerType>(J->getType());
IntegerType *GT = IntegerType::get(getGlobalContext(), T->getBitWidth());
// Continue if div/rem type is not bypassed
DenseMap<Type *, Type *>::const_iterator BI = BypassTypeMap.find(GT);
if (BI == BypassTypeMap.end())
continue;
// Get the bypass type in the original context
IntegerType *GBT = cast<IntegerType>(BI->second);
IntegerType *BT = IntegerType::get(J->getContext(), GBT->getBitWidth());
MadeChange |= reuseOrInsertFastDiv(F, I, J, BT, UseDivOp,
UseSignedOp, DivCache);
}