[PATCH] D64193: [PowerPC] Add exception constraint to FP rounding operations

[Qiu Chaofan via Phabricator via llvm-commits]

qiucf marked an inline comment as done.
qiucf added inline comments.


================
Comment at: llvm/test/CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll:6246
+; PC64LE-NEXT:    addis 4, 2, .LCPI103_1 at toc@ha
 ; PC64LE-NEXT:    addis 3, 2, .LCPI103_0 at toc@ha
+; PC64LE-NEXT:    addi 4, 4, .LCPI103_1 at toc@l
----------------
steven.zhang wrote:
> This looks like a deg. Please explain more about how this happens.
This is a reasonable result (for this case). Since arguments to `ceil` is constant `1.5`, result as `2.0` is provided even before DAG built.

Without this patch, these unused node (`frip`) would be dropped after isel, before list scheduling. However, every strict-fp node will have another operand for its chain. So they won't be dropped before list scheduling.

Maybe using variable as operand hits more about what we intend to test.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D64193/new/

https://reviews.llvm.org/D64193