[all-commits] [llvm/llvm-project] e47fd0: [RISCV] Use shNadd for scalable stack offsets (#88...

[Philip Reames via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: e47fd09f8eece712707f9611992cf6cfcd66605e
      https://github.com/llvm/llvm-project/commit/e47fd09f8eece712707f9611992cf6cfcd66605e
  Author: Philip Reames <preames at rivosinc.com>
  Date:   2024-04-09 (Tue, 09 Apr 2024)

  Changed paths:
    M llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp
    M llvm/test/CodeGen/RISCV/rvv/allocate-lmul-2-4-8.ll

  Log Message:
  -----------
  [RISCV] Use shNadd for scalable stack offsets (#88062)

If we need to multiply VLENB by 2, 4, or 8 and add it to the stack
pointer, we can do so with a shNadd instead of separate shift and add
instructions.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications