[llvm] [LoopVectorize] Vectorize fixed-order recurrence with vscale x 1. (PR #142772)

[David Sherwood via llvm-commits]

================
@@ -43,17 +77,51 @@ define void @pr97452_scalable_vf1_for_no_live_out(ptr %src, ptr noalias %dst) {
 ; CHECK-LABEL: define void @pr97452_scalable_vf1_for_no_live_out(
 ; CHECK-SAME: ptr [[SRC:%.*]], ptr noalias [[DST:%.*]]) {
 ; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 23, [[TMP0]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 23, [[TMP1]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 23, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT:    [[TMP4:%.*]] = sub i32 [[TMP3]], 1
+; CHECK-NEXT:    [[VECTOR_RECUR_INIT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 0, i32 [[TMP4]]
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VECTOR_RECUR:%.*]] = phi <vscale x 1 x i64> [ [[VECTOR_RECUR_INIT]], %[[VECTOR_PH]] ], [ [[WIDE_LOAD:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[SRC]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i64, ptr [[TMP5]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD]] = load <vscale x 1 x i64>, ptr [[TMP6]], align 8
+; CHECK-NEXT:    [[TMP7:%.*]] = call <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64> [[VECTOR_RECUR]], <vscale x 1 x i64> [[WIDE_LOAD]], i32 -1)
+; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[DST]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i32 0
+; CHECK-NEXT:    store <vscale x 1 x i64> [[TMP7]], ptr [[TMP9]], align 8
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
+; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP10]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    [[TMP11:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT:    [[TMP12:%.*]] = sub i32 [[TMP11]], 1
+; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <vscale x 1 x i64> [[WIDE_LOAD]], i32 [[TMP12]]
----------------
david-arm wrote:

This is just an observation really, but it seems a shame we generate this code despite there being no users of `VECTOR_RECUR_EXTRACT`

https://github.com/llvm/llvm-project/pull/142772