HomePhabricator

[DAGCombine] Fix bug in load scalarization

Authored by frasercrmck on Apr 21 2020, 8:23 AM.

Description

[DAGCombine] Fix bug in load scalarization

Summary:
For vector element types which are not byte-sized, we would generate
incorrect scalar offsets and produce incorrect codegen.

This optimization could potentially be supported in the future, e.g. by
loading in bytes, then shifting and masking out the remaining bits of
the vector element. However, without an upstream target to test against
it's best to avoid the bad codegen in the simplest possible way.

Related to this bug:

https://bugs.llvm.org/show_bug.cgi?id=27600

Reviewed by: foad

Differential Revision: https://reviews.llvm.org/D78568

Details

Committed
frasercrmckNov 4 2020, 11:02 AM
Reviewer
foad
Differential Revision
D78568: [DAGCombine] Fix bug in load scalarization
Parents
rG0df0d0fe2d1f: [libc++] NFC: Remove trailing whitespace
Branches
Unknown
Tags
Unknown