-; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=2 -S | FileCheck %s
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 -S | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
; CHECK-LABEL: @multi_int_induction(
; CHECK: vector.body:
; CHECK: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
-; CHECK: %normalized.idx = sub i64 %index, 0
-; CHECK: %[[VAR:.*]] = trunc i64 %normalized.idx to i32
+; CHECK: %[[VAR:.*]] = trunc i64 %index to i32
; CHECK: %offset.idx = add i32 190, %[[VAR]]
define void @multi_int_induction(i32* %A, i32 %N) {
for.body.lr.ph:
for.body:
%indvars.iv = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
%count.09 = phi i32 [ 190, %for.body.lr.ph ], [ %inc, %for.body ]
- %arrayidx2 = getelementptr inbounds i32* %A, i64 %indvars.iv
+ %arrayidx2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
store i32 %count.09, i32* %arrayidx2, align 4
%inc = add nsw i32 %count.09, 1
%indvars.iv.next = add i64 %indvars.iv, 1
ret void
}
-; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=2 -instcombine -S | FileCheck %s --check-prefix=IND
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 -instcombine -S | FileCheck %s --check-prefix=IND
; Make sure we remove unneeded vectorization of induction variables.
; In order for instcombine to cleanup the vectorized induction variables that we
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%ind.sum = add i64 %iv, %offset
- %arr.idx = getelementptr inbounds float* %a, i64 %ind.sum
- %l1 = load float* %arr.idx, align 4
+ %arr.idx = getelementptr inbounds float, float* %a, i64 %ind.sum
+ %l1 = load float, float* %arr.idx, align 4
%ind.sum2 = add i64 %iv, %offset2
- %arr.idx2 = getelementptr inbounds float* %a, i64 %ind.sum2
- %l2 = load float* %arr.idx2, align 4
+ %arr.idx2 = getelementptr inbounds float, float* %a, i64 %ind.sum2
+ %l2 = load float, float* %arr.idx2, align 4
%m = fmul fast float %b, %l2
%ad = fadd fast float %l1, %m
store float %ad, float* %arr.idx, align 4
; condition and branch directly to the scalar loop.
; CHECK-LABEL: max_i32_backedgetaken
-; CHECK: %backedge.overflow = icmp eq i32 -1, -1
-; CHECK: br i1 %backedge.overflow, label %scalar.ph, label %overflow.checked
+; CHECK: br i1 true, label %scalar.ph, label %min.iters.checked
; CHECK: scalar.ph:
-; CHECK: %bc.resume.val = phi i32 [ %resume.val, %middle.block ], [ 0, %0 ]
-; CHECK: %bc.merge.rdx = phi i32 [ 1, %0 ], [ %5, %middle.block ]
+; CHECK: %bc.resume.val = phi i32 [ 0, %middle.block ], [ 0, %0 ]
+; CHECK: %bc.merge.rdx = phi i32 [ 1, %0 ], [ 1, %min.iters.checked ], [ %5, %middle.block ]
define i32 @max_i32_backedgetaken() nounwind readnone ssp uwtable {
; <label>:5 ; preds = %1
ret i32 %2
}
+
+; When generating the overflow check we must sure that the induction start value
+; is defined before the branch to the scalar preheader.
+
+; CHECK-LABEL: testoverflowcheck
+; CHECK: entry
+; CHECK: %[[LOAD:.*]] = load i8
+; CHECK: br
+
+; CHECK: scalar.ph
+; CHECK: phi i8 [ %{{.*}}, %middle.block ], [ %[[LOAD]], %entry ]
+
+@e = global i8 1, align 1
+@d = common global i32 0, align 4
+@c = common global i32 0, align 4
+define i32 @testoverflowcheck() {
+entry:
+ %.pr.i = load i8, i8* @e, align 1
+ %0 = load i32, i32* @d, align 4
+ %c.promoted.i = load i32, i32* @c, align 4
+ br label %cond.end.i
+
+cond.end.i:
+ %inc4.i = phi i8 [ %.pr.i, %entry ], [ %inc.i, %cond.end.i ]
+ %and3.i = phi i32 [ %c.promoted.i, %entry ], [ %and.i, %cond.end.i ]
+ %and.i = and i32 %0, %and3.i
+ %inc.i = add i8 %inc4.i, 1
+ %tobool.i = icmp eq i8 %inc.i, 0
+ br i1 %tobool.i, label %loopexit, label %cond.end.i
+
+loopexit:
+ ret i32 %and.i
+}