Bypass Slow Divides
* Only apply divide bypass optimization when not optimizing for size.
* Fixed bug caused by constant for 0 value of type Int32,
used dividend type to generate the constant instead.
* For atom x86-64 apply the divide bypass to use 16-bit divides instead of
64-bit divides when operand values are small enough.
* Added lit tests for 64-bit divide bypass.
Patch by Tyler Nowicki!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176442 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Transforms/Scalar/CodeGenPrepare.cpp b/lib/Transforms/Scalar/CodeGenPrepare.cpp
index d71dd5d..015fd2e 100644
--- a/lib/Transforms/Scalar/CodeGenPrepare.cpp
+++ b/lib/Transforms/Scalar/CodeGenPrepare.cpp
@@ -154,7 +154,7 @@
/// This optimization identifies DIV instructions that can be
/// profitably bypassed and carried out with a shorter, faster divide.
- if (TLI && TLI->isSlowDivBypassed()) {
+ if (!OptSize && TLI && TLI->isSlowDivBypassed()) {
const DenseMap<unsigned int, unsigned int> &BypassWidths =
TLI->getBypassSlowDivWidths();
for (Function::iterator I = F.begin(); I != F.end(); I++)
diff --git a/lib/Transforms/Utils/BypassSlowDivision.cpp b/lib/Transforms/Utils/BypassSlowDivision.cpp
index 00cda8e..1f517d0 100644
--- a/lib/Transforms/Utils/BypassSlowDivision.cpp
+++ b/lib/Transforms/Utils/BypassSlowDivision.cpp
@@ -163,7 +163,7 @@
Value *AndV = MainBuilder.CreateAnd(OrV, BitMask);
// Compare operand values and branch
- Value *ZeroV = MainBuilder.getInt32(0);
+ Value *ZeroV = ConstantInt::getSigned(Dividend->getType(), 0);
Value *CmpV = MainBuilder.CreateICmpEQ(AndV, ZeroV);
MainBuilder.CreateCondBr(CmpV, FastBB, SlowBB);
@@ -244,7 +244,7 @@
// Get bitwidth of div/rem instruction
IntegerType *T = cast<IntegerType>(J->getType());
- int bitwidth = T->getBitWidth();
+ unsigned int bitwidth = T->getBitWidth();
// Continue if bitwidth is not bypassed
DenseMap<unsigned int, unsigned int>::const_iterator BI = BypassWidths.find(bitwidth);