[PATCH] D26905: [SLP] Vectorize loads of consecutive memory accesses, accessed in non-consecutive (jumbled) way.

[Shahid via Phabricator via llvm-commits]

ashahid added inline comments.


================
Comment at: test/Transforms/SLPVectorizer/X86/reduction_loads.ll:35
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <8 x i32> [[BIN_RDX4]], i32 0
+; CHECK-NEXT:    [[ADD_7:%.*]] = add i32 [[TMP4]], [[SUM]]
 ; CHECK-NEXT:    br i1 true, label %for.end, label %for.body
----------------
ashahid wrote:
> RKSimon wrote:
> > This looks suspicious - why the lonely change from TMP3 to TMP4?
> Oh good catch, I will see.
I was surprised initially but later realized that this is because the current patch resolves the regression you pointed out. So if you compare this patch i.e Diff5 with the previous patch i.e Diff4, you will see the expected difference


https://reviews.llvm.org/D26905