[SLP] add another bailout for load-combine patterns (2nd try)

[SLP] add another bailout for load-combine patterns (2nd try)

The original patch (rG86dfbc676ebe) exposed an existing bug:
we could wrongly cast a constant expression to BinaryOperator
because the pattern matching allows that. This adds a check
for that case, and there's a reduced test case to verify no
crashing.

Original commit message:

This builds on the or-reduction bailout that was added with D67841.
We still do not have IR-level load combining, although that could
be a target-specific enhancement for -vector-combiner.

The heuristic is narrowly defined to catch the motivating case from
PR39538:
https://bugs.llvm.org/show_bug.cgi?id=39538
...while preserving existing functionality.

That is, there's an unmodified test of pure load/zext/store that is
not seen in this patch at llvm/test/Transforms/SLPVectorizer/X86/cast.ll.
That's the reason for the logic difference to require the 'or'
instructions. The chances that vectorization would actually help a
memory-bound sequence like that seem small, but it looks nicer with:

  vpmovzxwd     (%rsi), %xmm0
  vmovdqu       %xmm0, (%rdi)

rather than:

  movzwl        (%rsi), %eax
  movl  %eax, (%rdi)
  ...

In the motivating test, we avoid creating a vector mess that is
unrecoverable in the backend, and SDAG forms the expected bswap
instructions after load combining:

  movzbl (%rdi), %eax
  vmovd %eax, %xmm0
  movzbl 1(%rdi), %eax
  vmovd %eax, %xmm1
  movzbl 2(%rdi), %eax
  vpinsrb $4, 4(%rdi), %xmm0, %xmm0
  vpinsrb $8, 8(%rdi), %xmm0, %xmm0
  vpinsrb $12, 12(%rdi), %xmm0, %xmm0
  vmovd %eax, %xmm2
  movzbl 3(%rdi), %eax
  vpinsrb $1, 5(%rdi), %xmm1, %xmm1
  vpinsrb $2, 9(%rdi), %xmm1, %xmm1
  vpinsrb $3, 13(%rdi), %xmm1, %xmm1
  vpslld $24, %xmm0, %xmm0
  vpmovzxbd %xmm1, %xmm1 # xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero
  vpslld $16, %xmm1, %xmm1
  vpor %xmm0, %xmm1, %xmm0
  vpinsrb $1, 6(%rdi), %xmm2, %xmm1
  vmovd %eax, %xmm2
  vpinsrb $2, 10(%rdi), %xmm1, %xmm1
  vpinsrb $3, 14(%rdi), %xmm1, %xmm1
  vpinsrb $1, 7(%rdi), %xmm2, %xmm2
  vpinsrb $2, 11(%rdi), %xmm2, %xmm2
  vpmovzxbd %xmm1, %xmm1 # xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero
  vpinsrb $3, 15(%rdi), %xmm2, %xmm2
  vpslld $8, %xmm1, %xmm1
  vpmovzxbd %xmm2, %xmm2 # xmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero
  vpor %xmm2, %xmm1, %xmm1
  vpor %xmm1, %xmm0, %xmm0
  vmovdqu %xmm0, (%rsi)

  movl  (%rdi), %eax
  movl  4(%rdi), %ecx
  movl  8(%rdi), %edx
  movbel        %eax, (%rsi)
  movbel        %ecx, 4(%rsi)
  movl  12(%rdi), %ecx
  movbel        %edx, 8(%rsi)
  movbel        %ecx, 12(%rsi)

Differential Revision: https://reviews.llvm.org/D78997