Commit Graph

4 Commits

Author SHA1 Message Date
Krzysztof Parzyszek c8bfed05e2 Reland 7691790dfd with a MSAN fix
In some cases when HexagonTargetLowering::allowsMemoryAccess returned
true, it did not set the "Fast" argument, leaving it uninitialized.

[Hexagon] Improve casting of boolean HVX vectors to scalars

- Mark memory access for bool vectors as disallowed in target lowering.
  This will prevent combining bitcasts of bool vectors with stores.
- Replace the actual bitcasting code with a faster version.
- Handle casting of v16i1 to i16.
2020-02-28 08:32:58 -06:00
Kirill Bobyrev 014728413f Revert "[Hexagon] Improve casting of boolean HVX vectors to scalars"
This reverts commit 7691790dfd.

The patch is failing tests with MSAN:
http://lab.llvm.org:8011/builders/sanitizer-x86_64-linux-fast/builds/39054/steps/check-llvm%20msan/logs/stdio
2020-02-27 11:58:32 +01:00
Krzysztof Parzyszek 7691790dfd [Hexagon] Improve casting of boolean HVX vectors to scalars
- Mark memory access for bool vectors as disallowed in target lowering.
  This will prevent combining bitcasts of bool vectors with stores.
- Replace the actual bitcasting code with a faster version.
- Handle casting of v16i1 to i16.
2020-02-26 12:46:52 -06:00
Ikhlas Ajbar a8a4f99afb [Hexagon] Lower bitcast of a vector predicate
This patch lowers bitcast of vector predicate of type v32i1/v64i1
to i32/i64 type.
2020-02-24 15:25:51 -06:00