HomePhabricator

[SLP] Vectorize jumbled memory loads.

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: mgrang, dcaballe, hans, mzolotukhin

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

Details

Committed
ashahidDec 12 2017, 7:08 PM
Reviewer
Ayal
Differential Revision
D36130: [SLP] Vectorize jumbled memory loads.
Parents
rL320547: [CallSiteSplitting] Refactor creating callsites.
Branches
Unknown
Tags
Unknown