[Bug c++/114921] Optimization flags cause _Float16 to __bf16 casting to do nothing

2024-05-02 Thread cvs-commit at gcc dot gnu.org via Gcc-bugs 
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114921

--- Comment #2 from GCC Commits  ---
The master branch has been updated by Richard Biener :

https://gcc.gnu.org/g:87e35da16df74cd1c4729a55d94e7bc592487f48

commit r15-124-g87e35da16df74cd1c4729a55d94e7bc592487f48
Author: Richard Biener 
Date:   Thu May 2 13:55:15 2024 +0200

tree-optimization/114921 - _Float16 -> __bf16 isn't noop

The vectorizer handles a _Float16 to __bf16 conversion through
vectorizable_assignment, thinking it's a noop.  The following
fixes this by requiring the same vector component mode when
checking for CONVERT_EXPR_CODE_P, being stricter than for
VIEW_CONVERT_EXPR.

PR tree-optimization/114921
* tree-vect-stmts.cc (vectorizable_assignment): Require
same vector component modes for input and output for
CONVERT_EXPR_CODE_P.

[Bug c++/114921] Optimization flags cause _Float16 to __bf16 casting to do nothing

2024-05-02 Thread rguenth at gcc dot gnu.org via Gcc-bugs 
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114921

Richard Biener  changed:

   What|Removed |Added

   Assignee|unassigned at gcc dot gnu.org  |rguenth at gcc dot 
gnu.org
   Keywords||wrong-code
 Ever confirmed|0   |1
   Last reconfirmed||2024-05-02
 Status|UNCONFIRMED |ASSIGNED

--- Comment #1 from Richard Biener  ---
Confirmed.  We vectorize the loop to

   [local count: 119292720]:
  vect_temp_9.6_3 = MEM  [(_Float16 *)f_7(D)];
  vect__4.7_9 = VIEW_CONVERT_EXPR(vect_temp_9.6_3);
  MEM  [(__bf16 *)f_7(D)] = vect__4.7_9;
  vect_temp_9.6_17 = MEM  [(_Float16 *)f_7(D) + 8B];
  vect__4.7_18 = VIEW_CONVERT_EXPR(vect_temp_9.6_17);
  MEM  [(__bf16 *)f_7(D) + 8B] = vect__4.7_18;

likely because the vectorizer thinks this is a noop conversion, it handles
it via vectorizable_assignment.