RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 03:33:20 +01:00
Code Issues Projects Releases Wiki Activity

Implement shift.ll:test23. If we are shifting right then immediately truncating

Browse Source 
the result, turn signed shift rights into unsigned shift rights if possible.

This leads to later simplification and happens *often* in 176.gcc.  For example,
this testcase:

struct xxx { unsigned int code : 8; };
enum codes { A, B, C, D, E, F };
int foo(struct xxx *P) {
  if ((enum codes)P->code == A)
     bar();
}

used to be compiled to:

int %foo(%struct.xxx* %P) {
        %tmp.1 = getelementptr %struct.xxx* %P, int 0, uint 0           ; <uint*> [#uses=1]
        %tmp.2 = load uint* %tmp.1              ; <uint> [#uses=1]
        %tmp.3 = cast uint %tmp.2 to int                ; <int> [#uses=1]
        %tmp.4 = shl int %tmp.3, ubyte 24               ; <int> [#uses=1]
        %tmp.5 = shr int %tmp.4, ubyte 24               ; <int> [#uses=1]
        %tmp.6 = cast int %tmp.5 to sbyte               ; <sbyte> [#uses=1]
        %tmp.8 = seteq sbyte %tmp.6, 0          ; <bool> [#uses=1]
        br bool %tmp.8, label %then, label %UnifiedReturnBlock

Now it is compiled to:

        %tmp.1 = getelementptr %struct.xxx* %P, int 0, uint 0           ; <uint*> [#uses=1]
        %tmp.2 = load uint* %tmp.1              ; <uint> [#uses=1]
        %tmp.2 = cast uint %tmp.2 to sbyte              ; <sbyte> [#uses=1]
        %tmp.8 = seteq sbyte %tmp.2, 0          ; <bool> [#uses=1]
        br bool %tmp.8, label %then, label %UnifiedReturnBlock

which is the difference between this:

foo:
        subl $4, %esp
        movl 8(%esp), %eax
        movl (%eax), %eax
        shll $24, %eax
        sarl $24, %eax
        testb %al, %al
        jne .LBBfoo_2

and this:

foo:
        subl $4, %esp
        movl 8(%esp), %eax
        movl (%eax), %eax
        testb %al, %al
        jne .LBBfoo_2

This occurs 3243 times total in the External tests, 215x in povray,
6x in each f2c'd program, 1451x in 176.gcc, 7x in crafty, 20x in perl,
25x in gap, 3x in m88ksim, 25x in ijpeg.

Maybe this will cause a little jump on gcc tommorow :)

llvm-svn: 21715
This commit is contained in:
Chris Lattner 2005-05-06 04:18:52 +00:00
parent 8f567bbc2a
commit ead76729cc
1 changed files with 19 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
lib/Transforms/Scalar/InstructionCombining.cpp
View File

@ -3571,6 +3571,25 @@ Instruction *InstCombiner::visitCastInst(CastInst &CI) {
return new ShiftInst(Instruction::Shl, Op0c, Op1);
}
break;
case Instruction::Shr:
// If this is a signed shr, and if all bits shifted in are about to be
// truncated off, turn it into an unsigned shr to allow greater
// simplifications.
if (DestBitSize < SrcBitSize && Src->getType()->isSigned() &&
isa<ConstantInt>(Op1)) {
unsigned ShiftAmt = cast<ConstantUInt>(Op1)->getValue();
if (SrcBitSize > ShiftAmt && SrcBitSize-ShiftAmt >= DestBitSize) {
// Convert to unsigned.
Value *N1 = InsertOperandCastBefore(Op0,
Op0->getType()->getUnsignedVersion(), &CI);
// Insert the new shift, which is now unsigned.
N1 = InsertNewInstBefore(new ShiftInst(Instruction::Shr, N1,
Op1, Src->getName()), CI);
return new CastInst(N1, CI.getType());
}
}
break;
case Instruction::SetNE:
if (ConstantInt *Op1C = dyn_cast<ConstantInt>(Op1)) {
if (Op1C->getRawValue() == 0) {
@ -3601,9 +3620,6 @@ Instruction *InstCombiner::visitCastInst(CastInst &CI) {
In = InsertNewInstBefore(new ShiftInst(Instruction::Shr, In,
ConstantInt::get(Type::UByteTy, ShiftAmt),
In->getName()+".lobit"), CI);
std::cerr << "In1 = " << *Op0;
std::cerr << "In2 = " << *CI.getOperand(0);
std::cerr << "In3 = " << CI;
if (CI.getType() == In->getType())
return ReplaceInstUsesWith(CI, In);
else