[all-commits] [llvm/llvm-project] 72925d: [riscv] Canonicalize vsetvli (vsetvli avl, vtype1)...

[Philip Reames via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 72925d98bf928431e430a49a0504bda8d7d0d184
      https://github.com/llvm/llvm-project/commit/72925d98bf928431e430a49a0504bda8d7d0d184
  Author: Philip Reames <preames at rivosinc.com>
  Date:   2022-05-11 (Wed, 11 May 2022)

  Changed paths:
    M llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
    M llvm/test/CodeGen/RISCV/rvv/vsetvli-insert.ll

  Log Message:
  -----------
  [riscv] Canonicalize vsetvli (vsetvli avl, vtype1) vtype2 transitionsas reviewed

This patch is an alternative to a piece of D125270. If we have one vsetvli which is using as AVL the output of another, and the prior AVL can be proven to produce the same VL value as that defining one, we can use the AVL from the prior instruction. This has the effect of removing a state transition on AVL, and will let us use the cheaper 'vsetvli x0, x0, vtype1' form or possible even skip emitting it entirely.

This builds on the same infrastructure as D125337, and does the analogous extension to working on abstract states instead of only prior explicit vsetvli instructions. This is where the (relatively minor) code improvements come from.

More importantly, this fixes the last case where the state computed in phase 1 and 2 of the algorithm differs from the state computed during phase 3. Note that such differences can cause miscompiles by creating disagreements about contents of the VL and VTYPE registers at block boundaries.

Doing this transform inside the dataflow can cause the compatibility of a later store to change with regards to the current state. test15 in the diff illustrates this case well. What we have is a vsetvli which is mutated by one following vector op, but whose GPR result is used by another. The compatibility logic walks back to the def in this case, and checks to see if it matches the immediate prior state. In phase 1 and 2, it doesn't, and in phase 3 (after mutation) it does because we remove a transition which caused it to differ.

Differential Revision: https://reviews.llvm.org/D125392