[llvm-bugs] [Bug 235368] [NVPTX] "Cannot select: v2bf16 = scalar_to_vector" for a byte-wise copy of an unaligned bfloat through a local array (regression in LLVM 23)

LLVM Bugs via llvm-bugs llvm-bugs at lists.llvm.org
Sat Oct 24 16:17:54 PDT 2026

Previous message: [llvm-bugs] [Bug 235366] [NVPTX] "Cannot select: v2i32 = and" when storing `trunc <2 x i32> to <2 x i1>` on sm_100 and newer
Next message: [llvm-bugs] [Bug 235399] [LoopStrengthReduce] Use-list order picks between two equal-cost solutions, and one of them costs an extra instruction (`d - 1` in a counted loop)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20261024/cddd063a/attachment-0001.html>

Previous message: [llvm-bugs] [Bug 235366] [NVPTX] "Cannot select: v2i32 = and" when storing `trunc <2 x i32> to <2 x i1>` on sm_100 and newer
Next message: [llvm-bugs] [Bug 235399] [LoopStrengthReduce] Use-list order picks between two equal-cost solutions, and one of them costs an extra instruction (`d - 1` in a counted loop)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-bugs mailing list