diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -3690,6 +3690,9 @@
              TTI->getShuffleCost(TargetTransformInfo::SK_Broadcast, VecTy, None,
                                  0);
     }
+    // No cost for "gathering" already vector value
+    if (isa<FixedVectorType>(VL[0]->getType()))
+      return 0;
     if (E->getOpcode() == Instruction::ExtractElement &&
         allSameType(VL) && allSameBlock(VL)) {
       SmallVector<int> Mask;
@@ -4591,6 +4594,9 @@
 Value *BoUpSLP::gather(ArrayRef<Value *> VL) {
   Value *Val0 =
       isa<StoreInst>(VL[0]) ? cast<StoreInst>(VL[0])->getValueOperand() : VL[0];
+  // "Gathering" of vector values is already done
+  if (isa<FixedVectorType>(Val0->getType()))
+    return Val0;
   FixedVectorType *VecTy = FixedVectorType::get(Val0->getType(), VL.size());
   Value *Vec = PoisonValue::get(VecTy);
   unsigned InsIndex = 0;
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector-inseltpoison.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector-inseltpoison.ll
@@ -1,6 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -S -slp-vectorizer -slp-threshold=-10000 < %s | FileCheck %s
 ; RUN: opt -S -slp-vectorizer -slp-threshold=0 < %s | FileCheck %s
+; RUN: opt -S -slp-vectorizer -slp-threshold=-10000 -slp-min-tree-size=0 < %s | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.8.0"
@@ -42,42 +43,6 @@
 
 ; This entire tree is ephemeral, don't vectorize any of it.
 define <4 x float> @simple_select_eph(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
-; CHECK-LABEL: @simple_select_eph(
-; CHECK-NEXT:    [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
-; CHECK-NEXT:    [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
-; CHECK-NEXT:    [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
-; CHECK-NEXT:    [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
-; CHECK-NEXT:    [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
-; CHECK-NEXT:    [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
-; CHECK-NEXT:    [[A2:%.*]] = extractelement <4 x float> [[A]], i32 2
-; CHECK-NEXT:    [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3
-; CHECK-NEXT:    [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
-; CHECK-NEXT:    [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
-; CHECK-NEXT:    [[B2:%.*]] = extractelement <4 x float> [[B]], i32 2
-; CHECK-NEXT:    [[B3:%.*]] = extractelement <4 x float> [[B]], i32 3
-; CHECK-NEXT:    [[CMP0:%.*]] = icmp ne i32 [[C0]], 0
-; CHECK-NEXT:    [[CMP1:%.*]] = icmp ne i32 [[C1]], 0
-; CHECK-NEXT:    [[CMP2:%.*]] = icmp ne i32 [[C2]], 0
-; CHECK-NEXT:    [[CMP3:%.*]] = icmp ne i32 [[C3]], 0
-; CHECK-NEXT:    [[S0:%.*]] = select i1 [[CMP0]], float [[A0]], float [[B0]]
-; CHECK-NEXT:    [[S1:%.*]] = select i1 [[CMP1]], float [[A1]], float [[B1]]
-; CHECK-NEXT:    [[S2:%.*]] = select i1 [[CMP2]], float [[A2]], float [[B2]]
-; CHECK-NEXT:    [[S3:%.*]] = select i1 [[CMP3]], float [[A3]], float [[B3]]
-; CHECK-NEXT:    [[RA:%.*]] = insertelement <4 x float> poison, float [[S0]], i32 0
-; CHECK-NEXT:    [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[S1]], i32 1
-; CHECK-NEXT:    [[RC:%.*]] = insertelement <4 x float> [[RB]], float [[S2]], i32 2
-; CHECK-NEXT:    [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[S3]], i32 3
-; CHECK-NEXT:    [[Q0:%.*]] = extractelement <4 x float> [[RD]], i32 0
-; CHECK-NEXT:    [[Q1:%.*]] = extractelement <4 x float> [[RD]], i32 1
-; CHECK-NEXT:    [[Q2:%.*]] = extractelement <4 x float> [[RD]], i32 2
-; CHECK-NEXT:    [[Q3:%.*]] = extractelement <4 x float> [[RD]], i32 3
-; CHECK-NEXT:    [[Q4:%.*]] = fadd float [[Q0]], [[Q1]]
-; CHECK-NEXT:    [[Q5:%.*]] = fadd float [[Q2]], [[Q3]]
-; CHECK-NEXT:    [[Q6:%.*]] = fadd float [[Q4]], [[Q5]]
-; CHECK-NEXT:    [[QI:%.*]] = fcmp olt float [[Q6]], [[Q5]]
-; CHECK-NEXT:    call void @llvm.assume(i1 [[QI]])
-; CHECK-NEXT:    ret <4 x float> undef
-;
   %c0 = extractelement <4 x i32> %c, i32 0
   %c1 = extractelement <4 x i32> %c, i32 1
   %c2 = extractelement <4 x i32> %c, i32 2
@@ -350,10 +315,6 @@
 ; Make sure that vectorization happens even if insertelements operations
 ; must be rescheduled. The case here is from compiling Julia.
 define <4 x float> @reschedule_extract(<4 x float> %a, <4 x float> %b) {
-; CHECK-LABEL: @reschedule_extract(
-; CHECK-NEXT:    [[TMP1:%.*]] = fadd <4 x float> [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT:    ret <4 x float> [[TMP1]]
-;
   %a0 = extractelement <4 x float> %a, i32 0
   %b0 = extractelement <4 x float> %b, i32 0
   %c0 = fadd float %a0, %b0
@@ -376,10 +337,6 @@
 ; Check that cost model for vectorization takes credit for
 ; instructions that are erased.
 define <4 x float> @take_credit(<4 x float> %a, <4 x float> %b) {
-; CHECK-LABEL: @take_credit(
-; CHECK-NEXT:    [[TMP1:%.*]] = fadd <4 x float> [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT:    ret <4 x float> [[TMP1]]
-;
   %a0 = extractelement <4 x float> %a, i32 0
   %b0 = extractelement <4 x float> %b, i32 0
   %c0 = fadd float %a0, %b0
@@ -426,10 +383,6 @@
 }
 
 define <8 x float> @_vadd256(<8 x float> %a, <8 x float> %b) local_unnamed_addr #0 {
-; CHECK-LABEL: @_vadd256(
-; CHECK-NEXT:    [[TMP1:%.*]] = fadd <8 x float> [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT:    ret <8 x float> [[TMP1]]
-;
   %vecext = extractelement <8 x float> %a, i32 0
   %vecext1 = extractelement <8 x float> %b, i32 0
   %add = fadd float %vecext, %vecext1