Target independent DAG transform to use truncate for field extraction + sign extend on targets where this is profitable. Passes nightly on x86-64.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48491 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Christopher Lamb 2008-03-18 16:46:39 +00:00
parent 3c88d742d4
commit 981576c818
2 changed files with 65 additions and 0 deletions

View File

@ -2374,6 +2374,32 @@ SDOperand DAGCombiner::visitSRA(SDNode *N) {
DAG.getValueType(EVT));
}
// fold sra (shl X, m), result_size - n
// -> (sign_extend (trunc (shl X, result_size - n - m))) for
// result_size - n != m. If truncate is free for the target sext(shl) is
// likely to result in better code.
if (N0.getOpcode() == ISD::SHL) {
// Get the two constanst of the shifts, CN0 = m, CN = n.
const ConstantSDNode *N01C = dyn_cast<ConstantSDNode>(N0.getOperand(1));
if (N01C && N1C) {
// Determine if the truncate type's bitsize would correspond to
// an integer type for this target.
unsigned VTValSize = MVT::getSizeInBits(VT);
MVT::ValueType TruncVT = MVT::getIntegerType(VTValSize - N1C->getValue());
unsigned ShiftAmt = N1C->getValue() - N01C->getValue();
// If the shift wouldn't be a noop, the truncated type is an actual type,
// and the truncate is free, then proceed with the transform.
if (ShiftAmt != 0 &&
!MVT::isExtendedVT(TruncVT) && TLI.isTruncateFree(VT, TruncVT)) {
SDOperand Amt = DAG.getConstant(ShiftAmt, TLI.getShiftAmountTy());
SDOperand Shift = DAG.getNode(ISD::SRL, VT, N0.getOperand(0), Amt);
SDOperand Trunc = DAG.getNode(ISD::TRUNCATE, TruncVT, Shift);
return DAG.getNode(ISD::SIGN_EXTEND, N->getValueType(0), Trunc);
}
}
}
// fold (sra (sra x, c1), c2) -> (sra x, c1+c2)
if (N1C && N0.getOpcode() == ISD::SRA) {
if (ConstantSDNode *C1 = dyn_cast<ConstantSDNode>(N0.getOperand(1))) {

View File

@ -0,0 +1,39 @@
; RUN: llvm-as < %s | llc -march=x86 | grep sar | count 1
; RUN: llvm-as < %s | llc -march=x86-64 | not grep sar
define i32 @test(i32 %f12) {
%tmp7.25 = lshr i32 %f12, 16
%tmp7.26 = trunc i32 %tmp7.25 to i8
%tmp78.2 = sext i8 %tmp7.26 to i32
ret i32 %tmp78.2
}
define i32 @test2(i32 %f12) {
%f11 = shl i32 %f12, 8
%tmp7.25 = ashr i32 %f11, 24
ret i32 %tmp7.25
}
define i32 @test3(i32 %f12) {
%f11 = shl i32 %f12, 13
%tmp7.25 = ashr i32 %f11, 24
ret i32 %tmp7.25
}
define i64 @test4(i64 %f12) {
%f11 = shl i64 %f12, 32
%tmp7.25 = ashr i64 %f11, 32
ret i64 %tmp7.25
}
define i16 @test5(i16 %f12) {
%f11 = shl i16 %f12, 2
%tmp7.25 = ashr i16 %f11, 8
ret i16 %tmp7.25
}
define i16 @test6(i16 %f12) {
%f11 = shl i16 %f12, 8
%tmp7.25 = ashr i16 %f11, 8
ret i16 %tmp7.25
}