3 files changed, 125 insertions, 26 deletions
diff --git a/test/Transforms/LoopVectorize/AMDGPU/packed-math.ll b/test/Transforms/LoopVectorize/AMDGPU/packed-math.ll
new file mode 100644
index 000000000000..832843983ebf
--- /dev/null
+++ b/test/Transforms/LoopVectorize/AMDGPU/packed-math.ll
@@ -0,0 +1,34 @@
+; RUN: opt -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s  -loop-vectorize -dce -instcombine -S | FileCheck -check-prefix=GFX9 -check-prefix=GCN %s
+; RUN: opt -mtriple=amdgcn-amd-amdhsa -mcpu=fiji < %s  -loop-vectorize -dce -instcombine -S | FileCheck -check-prefix=CIVI -check-prefix=GCN %s
+; RUN: opt -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii < %s  -loop-vectorize -dce -instcombine -S | FileCheck -check-prefix=CIVI -check-prefix=GCN %s
+
+; GCN-LABEL: @vectorize_v2f16_loop(
+; GFX9: vector.body:
+; GFX9: phi <2 x half>
+; GFX9: load <2 x half>
+; GFX9: fadd fast <2 x half>
+
+; GFX9: middle.block:
+; GFX9: fadd fast <2 x half>
+
+; VI: phi half
+; VI: phi load half
+; VI: fadd fast half
+define half @vectorize_v2f16_loop(half addrspace(1)* noalias %s) {
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %q.04 = phi half [ 0.0, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds half, half addrspace(1)* %s, i64 %indvars.iv
+  %0 = load half, half addrspace(1)* %arrayidx, align 2
+  %add = fadd fast half %q.04, %0
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 256
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:
+  %add.lcssa = phi half [ %add, %for.body ]
+  ret half %add.lcssa
+}
diff --git a/test/Transforms/LoopVectorize/X86/small-size.ll b/test/Transforms/LoopVectorize/X86/small-size.ll
index 47c262b11b46..89d69e232f5b 100644
--- a/test/Transforms/LoopVectorize/X86/small-size.ll
+++ b/test/Transforms/LoopVectorize/X86/small-size.ll
@@ -115,32 +115,6 @@ define void @example3(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture
   ret void
 }
 
-; N is unknown, we need a tail. Can't vectorize because the loop is cold.
-;CHECK-LABEL: @example4(
-;CHECK-NOT: <4 x i32>
-;CHECK: ret void
-define void @example4(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture %q) {
-  %1 = icmp eq i32 %n, 0
-  br i1 %1, label %._crit_edge, label %.lr.ph, !prof !0
-
-.lr.ph:                                           ; preds = %0, %.lr.ph
-  %.05 = phi i32 [ %2, %.lr.ph ], [ %n, %0 ]
-  %.014 = phi i32* [ %5, %.lr.ph ], [ %p, %0 ]
-  %.023 = phi i32* [ %3, %.lr.ph ], [ %q, %0 ]
-  %2 = add nsw i32 %.05, -1
-  %3 = getelementptr inbounds i32, i32* %.023, i64 1
-  %4 = load i32, i32* %.023, align 16
-  %5 = getelementptr inbounds i32, i32* %.014, i64 1
-  store i32 %4, i32* %.014, align 16
-  %6 = icmp eq i32 %2, 0
-  br i1 %6, label %._crit_edge, label %.lr.ph
-
-._crit_edge:                                      ; preds = %.lr.ph, %0
-  ret void
-}
-
-!0 = !{!"branch_weights", i32 64, i32 4}
-
 ; We can't vectorize this one because we need a runtime ptr check.
 ;CHECK-LABEL: @example23(
 ;CHECK-NOT: <4 x i32>
diff --git a/test/Transforms/LoopVectorize/tripcount.ll b/test/Transforms/LoopVectorize/tripcount.ll
new file mode 100644
index 000000000000..03b3aa171d4f
--- /dev/null
+++ b/test/Transforms/LoopVectorize/tripcount.ll
@@ -0,0 +1,91 @@
+; This test verifies that the loop vectorizer will not vectorizes low trip count
+; loops that require runtime checks (Trip count is computed with profile info).
+; REQUIRES: asserts
+; RUN: opt < %s -loop-vectorize -loop-vectorize-with-block-frequency -S | FileCheck %s
+
+target datalayout = "E-m:e-p:32:32-i64:32-f64:32:64-a:0:32-n32-S128"
+
+@tab = common global [32 x i8] zeroinitializer, align 1
+
+define i32 @foo_low_trip_count1(i32 %bound) {
+; Simple loop with low tripcount. Should not be vectorized.
+
+; CHECK-LABEL: @foo_low_trip_count1(
+; CHECK-NOT: <{{[0-9]+}} x i8>
+
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
+  %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 %i.08
+  %0 = load i8, i8* %arrayidx, align 1
+  %cmp1 = icmp eq i8 %0, 0
+  %. = select i1 %cmp1, i8 2, i8 1
+  store i8 %., i8* %arrayidx, align 1
+  %inc = add nsw i32 %i.08, 1
+  %exitcond = icmp eq i32 %i.08, %bound
+  br i1 %exitcond, label %for.end, label %for.body, !prof !1
+
+for.end:                                          ; preds = %for.body
+  ret i32 0
+}
+
+define i32 @foo_low_trip_count2(i32 %bound) !prof !0 {
+; The loop has a same invocation count with the function, but has a low
+; trip_count per invocation and not worth to vectorize.
+
+; CHECK-LABEL: @foo_low_trip_count2(
+; CHECK-NOT: <{{[0-9]+}} x i8>
+
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
+  %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 %i.08
+  %0 = load i8, i8* %arrayidx, align 1
+  %cmp1 = icmp eq i8 %0, 0
+  %. = select i1 %cmp1, i8 2, i8 1
+  store i8 %., i8* %arrayidx, align 1
+  %inc = add nsw i32 %i.08, 1
+  %exitcond = icmp eq i32 %i.08, %bound
+  br i1 %exitcond, label %for.end, label %for.body, !prof !1
+
+for.end:                                          ; preds = %for.body
+  ret i32 0
+}
+
+define i32 @foo_low_trip_count3(i1 %cond, i32 %bound) !prof !0 {
+; The loop has low invocation count compare to the function invocation count, 
+; but has a high trip count per invocation. Vectorize it.
+
+; CHECK-LABEL: @foo_low_trip_count3(
+; CHECK: vector.body:
+
+entry:
+  br i1 %cond, label %for.preheader, label %for.end, !prof !2
+
+for.preheader:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.08 = phi i32 [ 0, %for.preheader ], [ %inc, %for.body ]
+  %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @tab, i32 0, i32 %i.08
+  %0 = load i8, i8* %arrayidx, align 1
+  %cmp1 = icmp eq i8 %0, 0
+  %. = select i1 %cmp1, i8 2, i8 1
+  store i8 %., i8* %arrayidx, align 1
+  %inc = add nsw i32 %i.08, 1
+  %exitcond = icmp eq i32 %i.08, %bound
+  br i1 %exitcond, label %for.end, label %for.body, !prof !3
+
+for.end:                                          ; preds = %for.body
+  ret i32 0
+}
+
+
+!0 = !{!"function_entry_count", i64 100}
+!1 = !{!"branch_weights", i32 100, i32 0}
+!2 = !{!"branch_weights", i32 10, i32 90}
+!3 = !{!"branch_weights", i32 10, i32 10000}