Craig Topper af156f2d96 [AVX-512] Remove patterns that select vmovdqu8/16 for unmasked loads. Prefer vmovdqa64/vmovdqu64 instead. ...

These were taking priority over the aligned load instructions since there is no vmovda8/16. I don't think there is really a difference between aligned and unaligned on newer cpus so I don't think it matters which instructions we use.

But with this change we reduce the size of the isel table a little and we allow the aligned information to pass through to the evex->vec pass and produce the same output has avx/avx2 in some cases.

I also generally dislike patterns rooted in a bitcast which these were.

Differential Revision: https://reviews.llvm.org/D35977

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@309589 91177308-0d34-0410-b5e6-96231b3b80d8

2017-07-31 17:35:44 +00:00

..

AArch64

[GISel]: Support Widening G_ICMP's destination operand.

2017-07-31 17:00:16 +00:00

AMDGPU

AMDGPU: Make areMemAccessesTriviallyDisjoint more aware of segment flat

2017-07-29 01:26:21 +00:00

ARM

Remove the obsolete offset parameter from @llvm.dbg.value

2017-07-28 20:21:02 +00:00

AVR

[AVR] Remove the instrumentation pass

2017-07-23 23:39:11 +00:00

BPF

[DAG] Fix typo preventing some stores merges to truncated stores.

2017-07-23 02:06:28 +00:00

Generic

[AVR] Add/remove XFAILs to get the backend passing Generic CodeGen tests

2017-07-16 23:33:50 +00:00

Hexagon

[Hexagon] Recognize C4_cmpneqi, C4_cmpltei and C4_cmplteui in NewValueJump

2017-07-24 19:35:48 +00:00

Inputs

…

Lanai

CodeGen: Rename DEBUG_TYPE to match passnames

2017-05-25 21:26:32 +00:00

Mips

[SelectionDAG][mips] Fix PR33883

2017-07-31 14:06:58 +00:00

MIR

AMDGPU: Implement memory model

2017-07-21 21:19:23 +00:00

MSP430

[DAG] Improve Aliasing of operations to static alloca

2017-07-18 20:06:24 +00:00

Nios2

[Nios2] Target registration

2017-05-29 09:48:30 +00:00

NVPTX

[NVPTX] Add lowering of i128 params.

2017-07-20 21:16:03 +00:00

PowerPC

[PowerPC] enable optimizeCompareInstr for branch with static branch hint

2017-07-27 08:14:48 +00:00

SPARC

[SPARC] Clean up the support for disabling fsmuld and fmuls instructions.

2017-07-20 20:09:11 +00:00

SystemZ

[SystemZ] test update

2017-07-21 13:14:17 +00:00

Thumb

[ARM] Allow rematerialization of ARM Thumb literal pool loads

2017-07-14 08:23:56 +00:00

Thumb2

[ARM] Adjust ifcvt heuristic for the diamond ifcvt case

2017-07-12 13:23:10 +00:00

WebAssembly

Revert r308273 to reinstate part of r308100.

2017-07-19 04:15:30 +00:00

WinEH

Avoid infinite loops in branch folding

2016-12-12 23:05:38 +00:00

X86

[AVX-512] Remove patterns that select vmovdqu8/16 for unmasked loads. Prefer vmovdqa64/vmovdqu64 instead.

2017-07-31 17:35:44 +00:00

XCore

[DAG] Improve Aliasing of operations to static alloca

2017-07-18 20:06:24 +00:00