[VPlan] Run VPlan optimizations on plans in native path. Update buildVPlans (used in native path) to also run general VPlan optimizations in another small step to align both codepaths.

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index fdf8f70..58ef665 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -7843,7 +7843,9 @@
   auto MaxVFTimes2 = MaxVF * 2;
   for (ElementCount VF = MinVF; ElementCount::isKnownLT(VF, MaxVFTimes2);) {
     VFRange SubRange = {VF, MaxVFTimes2};
-    VPlans.push_back(buildVPlan(SubRange));
+    auto Plan = buildVPlan(SubRange);
+    VPlanTransforms::optimize(*Plan, *PSE.getSE());
+    VPlans.push_back(std::move(Plan));
     VF = SubRange.End;
   }
 }

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll b/llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll
index 933b467..736be49 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/outer_loop_prefer_scalable.ll

@@ -49,8 +49,6 @@
 ; CHECK:       vector.latch:
 ; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <vscale x 4 x float> [ [[TMP12]], [[INNER_LOOP1]] ]
 ; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4f32.nxv4p0(<vscale x 4 x float> [[VEC_PHI5]], <vscale x 4 x ptr> [[TMP10]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
-; CHECK-NEXT:    [[TMP16:%.*]] = add nuw nsw <vscale x 4 x i64> [[VEC_IND]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq <vscale x 4 x i64> [[TMP16]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1024, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP19]]
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
 ; CHECK-NEXT:    [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]

diff --git a/llvm/test/Transforms/LoopVectorize/dbg-outer-loop-vect.ll b/llvm/test/Transforms/LoopVectorize/dbg-outer-loop-vect.ll
index 3f56361..3bf2591 100644
--- a/llvm/test/Transforms/LoopVectorize/dbg-outer-loop-vect.ll
+++ b/llvm/test/Transforms/LoopVectorize/dbg-outer-loop-vect.ll

@@ -13,7 +13,6 @@
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]], !dbg [[DBG21]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[FOR_COND_CLEANUP32:%.*]] ]
-; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[FOR_COND_CLEANUP32]] ]
 ; CHECK-NEXT:    br label [[FOR_COND5_PREHEADER1:%.*]], !dbg [[DBG21]]
 ; CHECK:       for.cond5.preheader1:
 ; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i64> [ zeroinitializer, [[VECTOR_BODY]] ], [ [[TMP4:%.*]], [[FOR_COND5_PREHEADER1]] ], !dbg [[DBG21]]
@@ -30,10 +29,7 @@
 ; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x i1> [[TMP5]], i32 0, !dbg [[DBG26:![0-9]+]]
 ; CHECK-NEXT:    br i1 [[TMP6]], label [[FOR_COND_CLEANUP32]], label [[FOR_COND5_PREHEADER1]], !dbg [[DBG26]]
 ; CHECK:       vector.latch:
-; CHECK-NEXT:    [[TMP7:%.*]] = add nuw nsw <4 x i64> [[VEC_IND]], <i64 1, i64 1, i64 1, i64 1>, !dbg [[DBG27:![0-9]+]]
-; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq <4 x i64> [[TMP7]], <i64 23, i64 23, i64 23, i64 23>, !dbg [[DBG28:![0-9]+]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], 20
 ; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP29:![0-9]+]]
 ; CHECK:       middle.block:
@@ -59,9 +55,9 @@
 ; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC10]], 5, !dbg [[DBG25]]
 ; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP3]], label [[FOR_COND5_PREHEADER]], !dbg [[DBG26]]
 ; CHECK:       for.cond.cleanup3:
-; CHECK-NEXT:    [[INC13]] = add nuw nsw i64 [[I_023]], 1, !dbg [[DBG27]]
+; CHECK-NEXT:    [[INC13]] = add nuw nsw i64 [[I_023]], 1, !dbg [[DBG27:![0-9]+]]
 ; CHECK-NEXT:      #dbg_value(i64 [[INC13]], [[META11]], !DIExpression(), [[META20]])
-; CHECK-NEXT:    [[EXITCOND24_NOT:%.*]] = icmp eq i64 [[INC13]], 23, !dbg [[DBG28]]
+; CHECK-NEXT:    [[EXITCOND24_NOT:%.*]] = icmp eq i64 [[INC13]], 23, !dbg [[DBG28:![0-9]+]]
 ; CHECK-NEXT:    br i1 [[EXITCOND24_NOT]], label [[EXIT]], label [[FOR_COND1_PREHEADER]], !dbg [[DBG21]], !llvm.loop [[LOOP34:![0-9]+]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void, !dbg [[DBG35:![0-9]+]]
@@ -164,13 +160,13 @@
 ; CHECK: [[DBG24]] = !DILocation(line: 11, column: 32, scope: [[META19]])
 ; CHECK: [[DBG25]] = !DILocation(line: 11, column: 26, scope: [[META19]])
 ; CHECK: [[DBG26]] = !DILocation(line: 11, column: 5, scope: [[META15]])
-; CHECK: [[DBG27]] = !DILocation(line: 10, column: 30, scope: [[META16]])
-; CHECK: [[DBG28]] = !DILocation(line: 10, column: 24, scope: [[META16]])
 ; CHECK: [[LOOP29]] = distinct !{[[LOOP29]], [[DBG21]], [[META30:![0-9]+]], [[META31:![0-9]+]], [[META32:![0-9]+]]}
 ; CHECK: [[META30]] = !DILocation(line: 13, column: 13, scope: [[META12]])
 ; CHECK: [[META31]] = !{!"llvm.loop.isvectorized", i32 1}
 ; CHECK: [[META32]] = !{!"llvm.loop.unroll.runtime.disable"}
 ; CHECK: [[DBG33]] = !DILocation(line: 13, column: 2, scope: [[META23]])
+; CHECK: [[DBG27]] = !DILocation(line: 10, column: 30, scope: [[META16]])
+; CHECK: [[DBG28]] = !DILocation(line: 10, column: 24, scope: [[META16]])
 ; CHECK: [[LOOP34]] = distinct !{[[LOOP34]], [[DBG21]], [[META30]], [[META31]]}
 ; CHECK: [[DBG35]] = !DILocation(line: 14, column: 1, scope: [[DBG4]])
 ;.

diff --git a/llvm/test/Transforms/LoopVectorize/outer-loop-vec-phi-predecessor-order.ll b/llvm/test/Transforms/LoopVectorize/outer-loop-vec-phi-predecessor-order.ll
index 260f59c..b6f2ae3 100644
--- a/llvm/test/Transforms/LoopVectorize/outer-loop-vec-phi-predecessor-order.ll
+++ b/llvm/test/Transforms/LoopVectorize/outer-loop-vec-phi-predecessor-order.ll

@@ -41,8 +41,6 @@
 ; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x i1> [[TMP6]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP7]], label [[LOOP_1_LATCH5]], label [[LOOP_2_HEADER1]]
 ; CHECK:       vector.latch:
-; CHECK-NEXT:    [[TMP8:%.*]] = add nuw nsw <4 x i64> [[VEC_IND]], <i64 1, i64 1, i64 1, i64 1>
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq <4 x i64> [[TMP8]], [[BROADCAST_SPLAT]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
 ; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]

diff --git a/llvm/test/Transforms/LoopVectorize/outer_loop_hcfg_construction.ll b/llvm/test/Transforms/LoopVectorize/outer_loop_hcfg_construction.ll
index 986a608..5df4fce 100644
--- a/llvm/test/Transforms/LoopVectorize/outer_loop_hcfg_construction.ll
+++ b/llvm/test/Transforms/LoopVectorize/outer_loop_hcfg_construction.ll

@@ -52,8 +52,6 @@
 ; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x i1> [[TMP6]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_LOOP_LATCH4]], label [[INNERMOST_LOOP1]]
 ; CHECK:       vector.latch:
-; CHECK-NEXT:    [[TMP8:%.*]] = add nuw nsw <4 x i64> [[VEC_IND]], <i64 1, i64 1, i64 1, i64 1>
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq <4 x i64> [[TMP8]], [[BROADCAST_SPLAT3]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
 ; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
@@ -197,8 +195,6 @@
 ; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x i1> [[TMP6]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_LOOP_J0_CLEANUP4]], label [[INNERMOST_LOOP1]]
 ; CHECK:       vector.latch:
-; CHECK-NEXT:    [[TMP8:%.*]] = add nuw nsw <4 x i64> [[VEC_IND]], <i64 1, i64 1, i64 1, i64 1>
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq <4 x i64> [[TMP8]], [[BROADCAST_SPLAT3]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
 ; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]

diff --git a/llvm/test/Transforms/LoopVectorize/outer_loop_scalable.ll b/llvm/test/Transforms/LoopVectorize/outer_loop_scalable.ll
index 6cd7e37..08f2b82 100644
--- a/llvm/test/Transforms/LoopVectorize/outer_loop_scalable.ll
+++ b/llvm/test/Transforms/LoopVectorize/outer_loop_scalable.ll

@@ -55,8 +55,6 @@
 ; CHECK:       vector.latch:
 ; CHECK-NEXT:    [[VEC_PHI5:%.*]] = phi <vscale x 4 x float> [ [[TMP12]], [[INNER_LOOP1]] ]
 ; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4f32.nxv4p0(<vscale x 4 x float> [[VEC_PHI5]], <vscale x 4 x ptr> [[TMP10]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
-; CHECK-NEXT:    [[TMP16:%.*]] = add nuw nsw <vscale x 4 x i64> [[VEC_IND]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq <vscale x 4 x i64> [[TMP16]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1024, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP19]]
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
 ; CHECK-NEXT:    [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]

diff --git a/llvm/test/Transforms/LoopVectorize/vplan-vectorize-inner-loop-reduction.ll b/llvm/test/Transforms/LoopVectorize/vplan-vectorize-inner-loop-reduction.ll
index fdf7396..1552af3 100644
--- a/llvm/test/Transforms/LoopVectorize/vplan-vectorize-inner-loop-reduction.ll
+++ b/llvm/test/Transforms/LoopVectorize/vplan-vectorize-inner-loop-reduction.ll

@@ -40,8 +40,6 @@
 ; CHECK-NEXT: %[[REDUCTION:.*]] = phi <4 x double> [ %[[REDUCTION_NEXT]], %[[FOR2_HEADER]] ]
 ; CHECK-NEXT: %[[C_PTR:.*]] = getelementptr inbounds double, ptr %c.out, <4 x i64> %[[VEC_INDEX]]
 ; CHECK-NEXT: call void @llvm.masked.scatter.v4f64.v4p0(<4 x double> %[[REDUCTION]], <4 x ptr> %[[C_PTR]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
-; CHECK-NEXT: %[[VEC_INDEX_NEXT:.*]] = add nuw nsw <4 x i64> %[[VEC_INDEX]], <i64 1, i64 1, i64 1, i64 1>
-; CHECK-NEXT: %[[VEC_PTR:.*]] = icmp eq <4 x i64> %[[VEC_INDEX_NEXT]], <i64 1000, i64 1000, i64 1000, i64 1000>
 ; CHECK-NEXT: %[[FOR1_INDEX_NEXT:.*]] = add nuw i64 %[[FOR1_INDEX]], 4
 ; CHECK-NEXT: %{{.*}} = add <4 x i64> %[[VEC_INDEX]], <i64 4, i64 4, i64 4, i64 4>
 ; CHECK-NEXT: %[[EXIT_COND:.*]] = icmp eq i64 %[[FOR1_INDEX_NEXT]], 1000

diff --git a/llvm/test/Transforms/LoopVectorize/vplan-widen-call-instruction.ll b/llvm/test/Transforms/LoopVectorize/vplan-widen-call-instruction.ll
index 3335c21..4241409d 100644
--- a/llvm/test/Transforms/LoopVectorize/vplan-widen-call-instruction.ll
+++ b/llvm/test/Transforms/LoopVectorize/vplan-widen-call-instruction.ll

@@ -30,8 +30,6 @@
 ; CHECK-NEXT: %[[REDUCTION:.*]] = phi <4 x double> [ %[[REDUCTION_NEXT]], %[[FOR2_HEADER]] ]
 ; CHECK-NEXT: %[[C_PTR:.*]] = getelementptr inbounds double, ptr %c.out, <4 x i64> %[[VEC_INDEX]]
 ; CHECK-NEXT: call void @llvm.masked.scatter.v4f64.v4p0(<4 x double> %[[REDUCTION]], <4 x ptr> %[[C_PTR]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
-; CHECK-NEXT: %[[VEC_INDEX_NEXT:.*]] = add nuw nsw <4 x i64> %[[VEC_INDEX]], <i64 1, i64 1, i64 1, i64 1>
-; CHECK-NEXT: %[[VEC_PTR:.*]] = icmp eq <4 x i64> %[[VEC_INDEX_NEXT]], <i64 1000, i64 1000, i64 1000, i64 1000>
 ; CHECK-NEXT: %[[FOR1_INDEX_NEXT:.*]] = add nuw i64 %[[FOR1_INDEX]], 4
 ; CHECK-NEXT: %{{.*}} = add <4 x i64> %[[VEC_INDEX]], <i64 4, i64 4, i64 4, i64 4>
 ; CHECK-NEXT: %[[EXIT_COND:.*]] = icmp eq i64 %[[FOR1_INDEX_NEXT]], 1000