[llvm] [NFC][VPlan] Test showing that unit-stride-mv should be done later in pipeline (PR #180292)

Andrei Elovikov via llvm-commits llvm-commits at lists.llvm.org
Mon Feb 9 08:06:26 PST 2026

Previous message: [llvm] [NFC][VPlan] Test showing that unit-stride-mv should be done later in pipeline (PR #180292)
Next message: [llvm] [AMDGPU] Add legalization rules for G_ATOMICRMW_FADD (PR #175257)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

eas wrote:

> Wrong as in not optimal, not a miscompile right?

Yes.

https://github.com/llvm/llvm-project/pull/180292

Previous message: [llvm] [NFC][VPlan] Test showing that unit-stride-mv should be done later in pipeline (PR #180292)
Next message: [llvm] [AMDGPU] Add legalization rules for G_ATOMICRMW_FADD (PR #175257)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list