HomePhabricator

[SLP] Vectorize jumbled memory loads.

Authored by ashahid on Oct 3 2017, 8:28 AM.

Description

[SLP] Vectorize jumbled memory loads.

Summary:
This patch tries to vectorize loads of consecutive memory accesses, accessed
in non-consecutive or jumbled way. An earlier attempt was made with patch D26905
which was reverted back due to some basic issue with representing the 'use mask' of
jumbled accesses.

This patch fixes the mask representation by recording the 'use mask' in the usertree entry.

Change-Id: I9fe7f5045f065d84c126fa307ef6ebe0787296df

Reviewers: mkuper, loladiro, Ayal, zvi, danielcdh

Reviewed By: Ayal

Subscribers: hans, mzolotukhin

Differential Revision: https://reviews.llvm.org/D36130

llvm-svn: 314806

Details

Committed
ashahidOct 3 2017, 8:28 AM
Reviewer
Ayal
Differential Revision
D36130: [SLP] Vectorize jumbled memory loads.
Parents
rG5f081b1c0b2d: [Dominators] Don't use default parameter in lambda
Branches
Unknown
Tags
Unknown