Alexey Bataev b6c9077a19 [SLP] Improve horizontal vectorization for non-power-of-2 number of ...

instructions.

If number of instructions in horizontal reduction list is not power of 2
then only PowerOf2Floor(NumberOfInstructions) last elements are actually
vectorized, other instructions remain scalar. Patch tries to vectorize
the remaining elements either.

Differential Revision: https://reviews.llvm.org/D28959

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@293042 91177308-0d34-0410-b5e6-96231b3b80d8

2017-01-25 09:54:38 +00:00

..

AArch64

[SLP] Avoid signed integer overflow

2016-08-23 20:48:50 +00:00

AMDGPU

[SLPVectorizer] Try different vectorization factors for store chains

2015-07-08 23:40:55 +00:00

ARM

[opaque pointer type] Add textual IR support for explicit type parameter to load instruction

2015-02-27 21:17:42 +00:00

PowerPC

[SLP] Pass in correct alignment when query memory access cost

2016-05-31 20:41:19 +00:00

X86

[SLP] Improve horizontal vectorization for non-power-of-2 number of

2017-01-25 09:54:38 +00:00

XCore

[opaque pointer type] Add textual IR support for explicit type parameter to load instruction

2015-02-27 21:17:42 +00:00