[llvm] Use (de)interleaving intrinsics for fixed-length vectors (PR #202583)

[via llvm-commits]

github-actions[bot] wrote:

<!--PREMERGE ADVISOR COMMENT: Linux-->
# :penguin: Linux x64 Test Results

* 175291 tests passed
* 3453 tests skipped
* 1 test failed

## Failed Tests
(click on a test name to see its output)

### LLVM
<details>
<summary>LLVM.Transforms/LoopVectorize/AArch64/transform-narrow-interleave-to-widen-memory-with-wide-ops.ll</summary>

```
Exit Code: 1

Command Output (stdout):
--
# RUN: at line 2
/home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/opt -p loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/Transforms/LoopVectorize/AArch64/transform-narrow-interleave-to-widen-memory-with-wide-ops.ll | /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/FileCheck --check-prefixes=VF2 /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/Transforms/LoopVectorize/AArch64/transform-narrow-interleave-to-widen-memory-with-wide-ops.ll
# executed command: /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/opt -p loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/Transforms/LoopVectorize/AArch64/transform-narrow-interleave-to-widen-memory-with-wide-ops.ll
# note: command had no output on stdout or stderr
# executed command: /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/FileCheck --check-prefixes=VF2 /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/Transforms/LoopVectorize/AArch64/transform-narrow-interleave-to-widen-memory-with-wide-ops.ll
# note: command had no output on stdout or stderr
# RUN: at line 3
/home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/opt -p loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/Transforms/LoopVectorize/AArch64/transform-narrow-interleave-to-widen-memory-with-wide-ops.ll | /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/FileCheck --check-prefixes=VF4 /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/Transforms/LoopVectorize/AArch64/transform-narrow-interleave-to-widen-memory-with-wide-ops.ll
# executed command: /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/opt -p loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/Transforms/LoopVectorize/AArch64/transform-narrow-interleave-to-widen-memory-with-wide-ops.ll
# note: command had no output on stdout or stderr
# executed command: /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/FileCheck --check-prefixes=VF4 /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/Transforms/LoopVectorize/AArch64/transform-narrow-interleave-to-widen-memory-with-wide-ops.ll
# .---command stderr------------
# | /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/Transforms/LoopVectorize/AArch64/transform-narrow-interleave-to-widen-memory-with-wide-ops.ll:1300:13: error: VF4-NEXT: expected string not found in input
# | ; VF4-NEXT: [[STRIDED_VEC:%.*]] = shufflevector <8 x i64> [[WIDE_VEC]], <8 x i64> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
# |             ^
# | <stdin>:587:45: note: scanning from here
# |  %wide.vec = load <8 x i64>, ptr %1, align 8
# |                                             ^
# | <stdin>:587:45: note: with "WIDE_VEC" equal to "%wide.vec"
# |  %wide.vec = load <8 x i64>, ptr %1, align 8
# |                                             ^
# | 
# | Input file: <stdin>
# | Check file: /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/Transforms/LoopVectorize/AArch64/transform-narrow-interleave-to-widen-memory-with-wide-ops.ll
# | 
# | -dump-input=help explains the following input dump.
# | 
# | Input was:
# | <<<<<<
# |              .
# |              .
# |              .
# |            582:  
# |            583: vector.body: ; preds = %vector.body, %vector.ph 
# |            584:  %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ] 
# |            585:  %0 = shl nsw i64 %index, 1 
# |            586:  %1 = getelementptr inbounds i64, ptr %src, i64 %0 
# |            587:  %wide.vec = load <8 x i64>, ptr %1, align 8 
# | next:1300'0                                                 X error: no match found
# | next:1300'1                                                   with "WIDE_VEC" equal to "%wide.vec"
# |            588:  %strided.vec = call { <4 x i64>, <4 x i64> } @llvm.vector.deinterleave2.v8i64(<8 x i64> %wide.vec) 
# | next:1300'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |            589:  %2 = extractvalue { <4 x i64>, <4 x i64> } %strided.vec, 0 
# | next:1300'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |            590:  %3 = extractvalue { <4 x i64>, <4 x i64> } %strided.vec, 1 
# | next:1300'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |            591:  %4 = or disjoint <4 x i64> %2, splat (i64 1) 
# | next:1300'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |            592:  %5 = getelementptr inbounds i64, ptr %dst, i64 %0 
# | next:1300'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |              .
# |              .
# |              .
# | >>>>>>
# `-----------------------------
# error: command failed with exit status: 1

--

```
</details>

If these failures are unrelated to your changes (for example tests are broken or flaky at HEAD), please open an issue at https://github.com/llvm/llvm-project/issues and add the `infrastructure` label.

https://github.com/llvm/llvm-project/pull/202583