RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2024-11-24 20:29:53 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

This converts a signed remainder instruction to unsigned remainder, which

Browse Source 
enables the code size optimisation to fold a rem and div into a single
aeabi_uidivmod call. This was not happening before because sdiv was converted
but srem not, and instructions with different signedness are not combined.

Differential Revision: http://reviews.llvm.org/D22214


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@275403 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sjoerd Meijer 2016-07-14 12:23:48 +00:00
parent 2bb340ccad
commit 4fab1d4f07
2 changed files with 62 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
lib/Transforms/Scalar/CorrelatedValuePropagation.cpp
View File

@ -37,6 +37,7 @@ STATISTIC(NumCmps, "Number of comparisons propagated");
STATISTIC(NumReturns, "Number of return values propagated");
STATISTIC(NumDeadCases, "Number of switch cases removed");
STATISTIC(NumSDivs, "Number of sdiv converted to udiv");
STATISTIC(NumSRems, "Number of srem converted to urem");
namespace {
class CorrelatedValuePropagation : public FunctionPass {
@ -325,32 +326,51 @@ static bool processCallSite(CallSite CS, LazyValueInfo *LVI) {
return true;
}
// Helper function to rewrite srem and sdiv. As a policy choice, we choose not
// to waste compile time on anything where the operands are local defs. While
// LVI can sometimes reason about such cases, it's not its primary purpose.
static bool hasLocalDefs(BinaryOperator *SDI) {
for (Value *O : SDI->operands()) {
auto *I = dyn_cast<Instruction>(O);
if (I && I->getParent() == SDI->getParent())
return true;
}
return false;
}
static bool hasPositiveOperands(BinaryOperator *SDI, LazyValueInfo *LVI) {
Constant *Zero = ConstantInt::get(SDI->getType(), 0);
for (Value *O : SDI->operands()) {
auto Result = LVI->getPredicateAt(ICmpInst::ICMP_SGE, O, Zero, SDI);
if (Result != LazyValueInfo::True)
return false;
}
return true;
}
static bool processSRem(BinaryOperator *SDI, LazyValueInfo *LVI) {
if (SDI->getType()->isVectorTy() || hasLocalDefs(SDI) ||
!hasPositiveOperands(SDI, LVI))
return false;
++NumSRems;
auto *BO = BinaryOperator::CreateURem(SDI->getOperand(0), SDI->getOperand(1),
SDI->getName(), SDI);
SDI->replaceAllUsesWith(BO);
SDI->eraseFromParent();
return true;
}
/// See if LazyValueInfo's ability to exploit edge conditions or range
/// information is sufficient to prove the both operands of this SDiv are
/// positive. If this is the case, replace the SDiv with a UDiv. Even for local
/// conditions, this can sometimes prove conditions instcombine can't by
/// exploiting range information.
static bool processSDiv(BinaryOperator *SDI, LazyValueInfo *LVI) {
if (SDI->getType()->isVectorTy())
if (SDI->getType()->isVectorTy() || hasLocalDefs(SDI) ||
!hasPositiveOperands(SDI, LVI))
return false;
for (Value *O : SDI->operands()) {
// As a policy choice, we choose not to waste compile time on anything where
// the operands are local defs. While LVI can sometimes reason about such
// cases, it's not its primary purpose.
auto *I = dyn_cast<Instruction>(O);
if (I && I->getParent() == SDI->getParent())
return false;
}
Constant *Zero = ConstantInt::get(SDI->getType(), 0);
for (Value *O : SDI->operands()) {
LazyValueInfo::Tristate Result =
LVI->getPredicateAt(ICmpInst::ICMP_SGE, O, Zero, SDI);
if (Result != LazyValueInfo::True)
return false;
}
++NumSDivs;
auto *BO = BinaryOperator::CreateUDiv(SDI->getOperand(0), SDI->getOperand(1),
SDI->getName(), SDI);
@ -410,6 +430,9 @@ static bool runImpl(Function &F, LazyValueInfo *LVI) {
case Instruction::Invoke:
BBChanged |= processCallSite(CallSite(II), LVI);
break;
case Instruction::SRem:
BBChanged |= processSRem(cast<BinaryOperator>(II), LVI);
break;
case Instruction::SDiv:
BBChanged |= processSDiv(cast<BinaryOperator>(II), LVI);
break;

21
test/Transforms/CorrelatedValuePropagation/srem.ll Normal file
View File

@ -0,0 +1,21 @@
; RUN: opt < %s -correlated-propagation -S | FileCheck %s
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv7m-arm-none-eabi"
define void @h(i32* nocapture %p, i32 %x) local_unnamed_addr #0 {
entry:
; CHECK-LABEL: @h(
; CHECK: urem
%cmp = icmp sgt i32 %x, 0
br i1 %cmp, label %if.then, label %if.end
if.then:
%rem2 = srem i32 %x, 10
store i32 %rem2, i32* %p, align 4
br label %if.end
if.end:
ret void
}