[llvm] [LV] Adding/modifying pre-commit tests for changing loop interleaving count computation (PR #74689)

[Florian Hahn via llvm-commits]

================
@@ -53,9 +53,104 @@ for.end:
   ret void
 }
 
-; For a loop with unknown trip count but a profile showing an approx TC estimate of 32, when the
-; auto-vectorizer chooses VF 16, it should choose IC 2 since chances are high that the remainder loop
-; won't need to run
+; For this loop with known TC of 39, when the auto-vectorizer chooses VF 16, it should choose
+; IC 2 since there is a small remainder loop that needs to run after the vector loop.
+; CHECK: remark: <unknown>:0:0: vectorized loop (vectorization width: 16, interleaved count: 2)
+define void @loop_with_tc_39(ptr noalias %p, ptr noalias %q) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
+  %tmp0 = getelementptr %pair, ptr %p, i64 %i, i32 0
+  %tmp1 = load i8, ptr %tmp0, align 1
+  %tmp2 = getelementptr %pair, ptr %p, i64 %i, i32 1
+  %tmp3 = load i8, ptr %tmp2, align 1
+  %add = add i8 %tmp1, %tmp3
+  %qi = getelementptr i8, ptr %q, i64 %i
+  store i8 %add, ptr %qi, align 1
+  %i.next = add nuw nsw i64 %i, 1
+  %cond = icmp eq i64 %i.next, 39
+  br i1 %cond, label %for.end, label %for.body
+
+for.end:
+  ret void
+}
+
+; TODO: For this loop with known TC of 48, when the auto-vectorizer chooses VF 16, it should choose
+; IC 1 since there will be no remainder loop that needs to run after the vector loop.
+; CHECK: remark: <unknown>:0:0: vectorized loop (vectorization width: 16, interleaved count: 2)
+define void @loop_with_tc_48(ptr noalias %p, ptr noalias %q) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
+  %tmp0 = getelementptr %pair, ptr %p, i64 %i, i32 0
+  %tmp1 = load i8, ptr %tmp0, align 1
+  %tmp2 = getelementptr %pair, ptr %p, i64 %i, i32 1
+  %tmp3 = load i8, ptr %tmp2, align 1
+  %add = add i8 %tmp1, %tmp3
+  %qi = getelementptr i8, ptr %q, i64 %i
+  store i8 %add, ptr %qi, align 1
+  %i.next = add nuw nsw i64 %i, 1
+  %cond = icmp eq i64 %i.next, 48
+  br i1 %cond, label %for.end, label %for.body
+
+for.end:
+  ret void
+}
+
+; TODO: For this loop with known TC of 49, when the auto-vectorizer chooses VF 16, it should choose
+; IC 1 since a remainder loop TC of 1 is more efficient than remainder loop TC of 17 with IC 2
+; CHECK: remark: <unknown>:0:0: vectorized loop (vectorization width: 16, interleaved count: 2)
+define void @loop_with_tc_49(ptr noalias %p, ptr noalias %q) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
+  %tmp0 = getelementptr %pair, ptr %p, i64 %i, i32 0
+  %tmp1 = load i8, ptr %tmp0, align 1
+  %tmp2 = getelementptr %pair, ptr %p, i64 %i, i32 1
+  %tmp3 = load i8, ptr %tmp2, align 1
+  %add = add i8 %tmp1, %tmp3
+  %qi = getelementptr i8, ptr %q, i64 %i
+  store i8 %add, ptr %qi, align 1
+  %i.next = add nuw nsw i64 %i, 1
+  %cond = icmp eq i64 %i.next, 49
+  br i1 %cond, label %for.end, label %for.body
+
+for.end:
+  ret void
+}
+
+; TODO: For this loop with known TC of 55, when the auto-vectorizer chooses VF 16, it should choose
----------------
fhahn wrote:

Do we have test cases for larger trip counts? If the number of vector iterations is high enough the cost of the additional epilogue should become negligible, and avoiding an epilogue in favor of a smaller IC should not apply any longer, correct?

https://github.com/llvm/llvm-project/pull/74689