Implement Transforms/InstCombine/vec_extract_elt.ll, transforming:

define i32 @test(float %f) {
        %tmp7 = insertelement <4 x float> undef, float %f, i32 0
        %tmp17 = bitcast <4 x float> %tmp7 to <4 x i32>
        %tmp19 = extractelement <4 x i32> %tmp17, i32 0
        ret i32 %tmp19
}

into:

define i32 @test(float %f) {
        %tmp19 = bitcast float %f to i32                ; <i32> [#uses=1]
        ret i32 %tmp19
}

On PPC, this is the difference between:

_test:
        mfspr r2, 256
        oris r3, r2, 8192
        mtspr 256, r3
        stfs f1, -16(r1)
        addi r3, r1, -16
        addi r4, r1, -32
        lvx v2, 0, r3
        stvx v2, 0, r4
        lwz r3, -32(r1)
        mtspr 256, r2
        blr

and:

_test:
        stfs f1, -4(r1)
        nop
        nop
        nop
        lwz r3, -4(r1)
        blr


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@36025 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Chris Lattner 2007-04-14 23:02:14 +00:00
parent 32b4c12e6b
commit b7300fa8d2

View File

@ -9109,6 +9109,17 @@ Instruction *InstCombiner::visitExtractElementInst(ExtractElementInst &EI) {
if (Value *Elt = FindScalarElement(EI.getOperand(0), IndexVal))
return ReplaceInstUsesWith(EI, Elt);
// If the this extractelement is directly using a bitcast from a vector of
// the same number of elements, see if we can find the source element from
// it. In this case, we will end up needing to bitcast the scalars.
if (BitCastInst *BCI = dyn_cast<BitCastInst>(EI.getOperand(0))) {
if (const VectorType *VT =
dyn_cast<VectorType>(BCI->getOperand(0)->getType()))
if (VT->getNumElements() == VectorWidth)
if (Value *Elt = FindScalarElement(BCI->getOperand(0), IndexVal))
return new BitCastInst(Elt, EI.getType());
}
}
if (Instruction *I = dyn_cast<Instruction>(EI.getOperand(0))) {