Skip to content

[X86] Use shift+add/sub for vXi8 splat multiplies #174110

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
RKSimon merged 8 commits into from
Mar 11, 2026
Merged

[X86] Use shift+add/sub for vXi8 splat multiplies #174110

Show file tree
Hide file tree
Changes from 6 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
bb437eb
[X86] lit tests for vXi8 shift+add/sub without width extension
grodranlorth Nov 22, 2025
e418ad1
[X86] Use shift+add/sub for vXi8 splat multiply
grodranlorth Nov 18, 2025
625a6f2
fixup! [X86] Use shift+add/sub for vXi8 splat multiply
Jan 7, 2026
ce38724
fixup! [X86] Use shift+add/sub for vXi8 splat multiply
grodranlorth Feb 1, 2026
d645d4e
fixup! [X86] Use shift+add/sub for vXi8 splat multiply
grodranlorth Feb 7, 2026
4d22476
Move vXi8 tests into a single file
grodranlorth Feb 7, 2026
0b4d080
RKSimon's test feedback
grodranlorth Mar 8, 2026
3e483de
Merge branch 'main' into shiftopt
RKSimon Mar 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions llvm/lib/Target/X86/X86ISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3389,6 +3389,18 @@ bool X86TargetLowering::decomposeMulByConstant(LLVMContext &Context, EVT VT,
if (!ISD::isConstantSplatVector(C.getNode(), MulC))
return false;

if (VT.isVector() && VT.getScalarSizeInBits() == 8) {
// Check whether a vXi8 multiply can be decomposed into two shifts
// (decomposing 2^m ± 2^n as 2^(a+b) ± 2^b). Similar to
// DAGCombiner::visitMUL, consider the constant `2` decomposable as
Comment thread
grodranlorth marked this conversation as resolved.
// (2^0 + 1).
APInt ShiftedMulC = MulC.abs();
unsigned TZeros = ShiftedMulC == 2 ? 0 : ShiftedMulC.countr_zero();
ShiftedMulC.lshrInPlace(TZeros);
if ((ShiftedMulC - 1).isPowerOf2() || (ShiftedMulC + 1).isPowerOf2())
return true;
}

// Find the type this will be legalized too. Otherwise we might prematurely
// convert this to shl+add/sub and then still have to type legalize those ops.
// Another choice would be to defer the decision for illegal types until
Expand Down
Loading