Integrated: 8300256: C2: vectorization is sometimes skipped on loops where it would succeed

Roland Westrelin roland at openjdk.org
Wed Feb 1 09:52:08 UTC 2023


On Fri, 20 Jan 2023 15:15:40 GMT, Roland Westrelin <roland at openjdk.org> wrote:

> Vectorization for a counted loop cl only proceeds if
> cl->range_checks_present() returns true. The result of that method is
> computed lazily and its result cached in the CountedLoopNode and never
> re-computed. If PhaseIdealLoop::do_range_check() returns 0 then the
> result of that computation is overwritten (no range checks
> present). PhaseIdealLoop::do_range_check() counts the number of tests
> present in the loop body (which is really what range_checks_present()
> is about) and decrements that count for every check it eliminates
> except if it's not a comparison with a LoadRange (for a reason that I
> don't understand). In the case of the test (a pattern from a
> ByteBuffer benchmark), not all tests are with a LoadRange. As a
> result, PhaseIdealLoop::do_range_check() returns non zero even though
> it eliminates all tests. As a result, vectorization is never
> attempted.
> 
> There doesn't seem to be a value in caching the result of
> range_checks_present() in CountedLoopNode. It's not that expensive to
> compute, it's only used during loop opts and it's really hard to keep
> in sync with whether the loop has still tests: several different
> transformations could remove a test. What I propose instead is to keep
> roughly the same approach (compute the result lazily and cache it so
> it doesn't have to be re-computed) but to store it on the
> IdealLoopTree instead (so it's recomputed on every loop opts pass and
> there's no risk that it becomes out of sync).

This pull request has now been integrated.

Changeset: 2a8ae2ff
Author:    Roland Westrelin <roland at openjdk.org>
URL:       https://git.openjdk.org/jdk/commit/2a8ae2ff1c95cb75f315eb5340bff2b46409d1ae
Stats:     155 lines in 5 files changed: 83 ins; 40 del; 32 mod

8300256: C2: vectorization is sometimes skipped on loops where it would succeed

Reviewed-by: kvn, thartmann

-------------

PR: https://git.openjdk.org/jdk/pull/12116


More information about the hotspot-compiler-dev mailing list