[llvm] [LV][VPlan] Implement VPlan-based cost for exit condition. (PR #125640)

[Florian Hahn via llvm-commits]

================
@@ -657,28 +657,58 @@ define void @multiple_exit_conditions(ptr %src, ptr noalias %dst) #1 {
 ; DEFAULT-LABEL: define void @multiple_exit_conditions(
 ; DEFAULT-SAME: ptr [[SRC:%.*]], ptr noalias [[DST:%.*]]) #[[ATTR2:[0-9]+]] {
 ; DEFAULT-NEXT:  [[ENTRY:.*]]:
-; DEFAULT-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; DEFAULT-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
+; DEFAULT-NEXT:    [[TMP9:%.*]] = mul nuw i64 [[TMP7]], 8
+; DEFAULT-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 257, [[TMP9]]
+; DEFAULT-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
 ; DEFAULT:       [[VECTOR_PH]]:
-; DEFAULT-NEXT:    [[IND_END:%.*]] = getelementptr i8, ptr [[DST]], i64 2048
+; DEFAULT-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; DEFAULT-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 8
+; DEFAULT-NEXT:    [[N_MOD_VF:%.*]] = urem i64 257, [[TMP3]]
+; DEFAULT-NEXT:    [[N_VEC:%.*]] = sub i64 257, [[N_MOD_VF]]
+; DEFAULT-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; DEFAULT-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP10]], 8
+; DEFAULT-NEXT:    [[TMP6:%.*]] = mul i64 [[N_VEC]], 8
+; DEFAULT-NEXT:    [[IND_END:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP6]]
+; DEFAULT-NEXT:    [[TMP8:%.*]] = mul i64 [[N_VEC]], 2
 ; DEFAULT-NEXT:    br label %[[VECTOR_BODY:.*]]
 ; DEFAULT:       [[VECTOR_BODY]]:
 ; DEFAULT-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
 ; DEFAULT-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], 8
 ; DEFAULT-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[DST]], i64 [[OFFSET_IDX]]
 ; DEFAULT-NEXT:    [[TMP1:%.*]] = load i16, ptr [[SRC]], align 2
-; DEFAULT-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i16> poison, i16 [[TMP1]], i64 0
-; DEFAULT-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i16> [[BROADCAST_SPLATINSERT]], <8 x i16> poison, <8 x i32> zeroinitializer
-; DEFAULT-NEXT:    [[TMP2:%.*]] = or <8 x i16> [[BROADCAST_SPLAT]], splat (i16 1)
-; DEFAULT-NEXT:    [[TMP3:%.*]] = uitofp <8 x i16> [[TMP2]] to <8 x double>
-; DEFAULT-NEXT:    store <8 x double> [[TMP3]], ptr [[NEXT_GEP]], align 8
-; DEFAULT-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
-; DEFAULT-NEXT:    [[TMP5:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
-; DEFAULT-NEXT:    br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP22:![0-9]+]]
+; DEFAULT-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i16> poison, i16 [[TMP1]], i64 0
+; DEFAULT-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i16> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i16> poison, <vscale x 2 x i32> zeroinitializer
+; DEFAULT-NEXT:    [[TMP28:%.*]] = or <vscale x 2 x i16> [[BROADCAST_SPLAT]], splat (i16 1)
----------------
fhahn wrote:

This also looks like a potential regression, as we only use 1/4 of the available vector width?

https://github.com/llvm/llvm-project/pull/125640