[SLP] Don't vectorize loads of non-packed types (like i1, i2).

Summary:
Given an array of i2 elements, 4 consecutive scalar loads will be lowered to
i8-sized loads and thus will access 4 consecutive bytes in memory. If we
vectorize these loads into a single <4 x i2> load, it'll access only 1 byte in
memory. Hence, we should prohibit vectorization in such cases.

PS: Initial patch was proposed by Arnold.

Reviewers: aschwaighofer, nadav, hfinkel

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D13277

llvm-svn: 248943

1 files changed, 26 insertions, 0 deletions

diff --git a/llvm/test/Transforms/SLPVectorizer/X86/bad_types.ll b/llvm/test/Transforms/SLPVectorizer/X86/bad_types.ll
index 2d8f3832ee2..98c29068bb9 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/bad_types.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/bad_types.ll
@@ -47,4 +47,30 @@ exit:
   ret void
 }
 
+define i8 @test3(i8 *%addr) {
+; Check that we do not vectorize types that are padded to a bigger ones.
+;
+; CHECK-LABEL: @test3
+; CHECK-NOT:   <4 x i2>
+; CHECK:       ret i8
+entry:
+  %a = bitcast i8* %addr to i2*
+  %a0 = getelementptr inbounds i2, i2* %a, i64 0
+  %a1 = getelementptr inbounds i2, i2* %a, i64 1
+  %a2 = getelementptr inbounds i2, i2* %a, i64 2
+  %a3 = getelementptr inbounds i2, i2* %a, i64 3
+  %l0 = load i2, i2* %a0, align 1
+  %l1 = load i2, i2* %a1, align 1
+  %l2 = load i2, i2* %a2, align 1
+  %l3 = load i2, i2* %a3, align 1
+  br label %bb1
+bb1:                                              ; preds = %entry
+  %p0 = phi i2 [ %l0, %entry ]
+  %p1 = phi i2 [ %l1, %entry ]
+  %p2 = phi i2 [ %l2, %entry ]
+  %p3 = phi i2 [ %l3, %entry ]
+  %r  = zext i2 %p2 to i8
+  ret i8 %r
+}
+
 declare void @f(i64, i64)