Fix a HUGE pessimization on X86. The indvars pass was taking this

(familiar) function:

int _strlen(const char *str) {
    int len = 0;
    while (*str++) len++;
    return len;
}

And transforming it to use a ulong induction variable, because the type of
the pointer index was left as a constant long.  This is obviously very bad.

The fix is to shrink long constants in getelementptr instructions to intptr_t,
making the indvars pass insert a uint induction variable, which is much more
efficient.

Here's the before code for this function:

int %_strlen(sbyte* %str) {
entry:
        %tmp.13 = load sbyte* %str              ; <sbyte> [#uses=1]
        %tmp.24 = seteq sbyte %tmp.13, 0                ; <bool> [#uses=1]
        br bool %tmp.24, label %loopexit, label %no_exit

no_exit:                ; preds = %entry, %no_exit
***     %indvar = phi uint [ %indvar.next, %no_exit ], [ 0, %entry ]            ; <uint> [#uses=2]
***     %indvar = phi ulong [ %indvar.next, %no_exit ], [ 0, %entry ]           ; <ulong> [#uses=2]
        %indvar1 = cast ulong %indvar to uint           ; <uint> [#uses=1]
        %inc.02.sum = add uint %indvar1, 1              ; <uint> [#uses=1]
        %inc.0.0 = getelementptr sbyte* %str, uint %inc.02.sum          ; <sbyte*> [#uses=1]
        %tmp.1 = load sbyte* %inc.0.0           ; <sbyte> [#uses=1]
        %tmp.2 = seteq sbyte %tmp.1, 0          ; <bool> [#uses=1]
        %indvar.next = add ulong %indvar, 1             ; <ulong> [#uses=1]
        %indvar.next = add uint %indvar, 1              ; <uint> [#uses=1]
        br bool %tmp.2, label %loopexit.loopexit, label %no_exit

loopexit.loopexit:              ; preds = %no_exit
        %indvar = cast uint %indvar to int              ; <int> [#uses=1]
        %inc.1 = add int %indvar, 1             ; <int> [#uses=1]
        ret int %inc.1

loopexit:               ; preds = %entry
        ret int 0
}

Here's the after code:

int %_strlen(sbyte* %str) {
entry:
        %inc.02 = getelementptr sbyte* %str, uint 1             ; <sbyte*> [#uses=1]
        %tmp.13 = load sbyte* %str              ; <sbyte> [#uses=1]
        %tmp.24 = seteq sbyte %tmp.13, 0                ; <bool> [#uses=1]
        br bool %tmp.24, label %loopexit, label %no_exit

no_exit:                ; preds = %entry, %no_exit
***     %indvar = phi uint [ %indvar.next, %no_exit ], [ 0, %entry ]            ; <uint> [#uses=3]
        %indvar = cast uint %indvar to int              ; <int> [#uses=1]
        %inc.0.0 = getelementptr sbyte* %inc.02, uint %indvar           ; <sbyte*> [#uses=1]
        %inc.1 = add int %indvar, 1             ; <int> [#uses=1]
        %tmp.1 = load sbyte* %inc.0.0           ; <sbyte> [#uses=1]
        %tmp.2 = seteq sbyte %tmp.1, 0          ; <bool> [#uses=1]
        %indvar.next = add uint %indvar, 1              ; <uint> [#uses=1]
        br bool %tmp.2, label %loopexit, label %no_exit

loopexit:               ; preds = %entry, %no_exit
        %len.0.1 = phi int [ 0, %entry ], [ %inc.1, %no_exit ]          ; <int> [#uses=1]
        ret int %len.0.1
}

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@13016 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Scalar/InstructionCombining.cpp b/lib/Transforms/Scalar/InstructionCombining.cpp
index 6b7f20a73cf0dcec496e5556e164c5e05b08f37d..52b861da15665b347a9a5a040d20314f7112afb6 100644 (file)
--- a/lib/Transforms/Scalar/InstructionCombining.cpp
+++ b/lib/Transforms/Scalar/InstructionCombining.cpp
@@ -2580,7 +2580,10 @@ Instruction *InstCombiner::visitGetElementPtrInst(GetElementPtrInst &GEP) {
       // obvious.
       Value *Op = GEP.getOperand(i);
       if (Op->getType()->getPrimitiveSize() > TD->getPointerSize())
-        if (!isa<Constant>(Op)) {
+        if (Constant *C = dyn_cast<Constant>(Op)) {
+          GEP.setOperand(i, ConstantExpr::getCast(C, TD->getIntPtrType()));
+          MadeChange = true;
+        } else {
           Op = InsertNewInstBefore(new CastInst(Op, TD->getIntPtrType(),
                                                 Op->getName()), GEP);
           GEP.setOperand(i, Op);