[llvm-bugs] [Bug 238712] [AArch64] vectorToScalarBitmask without NEON (streaming-compatible SVE): `bitcast <16 x i1> to i16` drops lanes 8..15 because their mask bits 1<<8..1<<15 are truncated to i8

LLVM Bugs via llvm-bugs llvm-bugs at lists.llvm.org
Tue Nov 3 23:58:39 PST 2026

Previous message: [llvm-bugs] [Bug 238711] [DAGCombiner] visitVECTOR_DEINTERLEAVE folds the whole deinterleave to undef when only its first operand is undef
Next message: [llvm-bugs] [Bug 238713] [SystemZ] lowerSIGN_EXTEND_VECTOR_INREG folds a shuffle whose sign-extended lanes come from the second operand into UNPACKs of the first operand: `__builtin_convertvector(__builtin_shufflevector(a, b, 22, 23, ...), long16)` extends a[14], a[15]
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20261104/71ca8405/attachment-0001.html>

More information about the llvm-bugs mailing list