diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst
index 7e3320b2fe2e..ff89e0d77448 100644
--- a/llvm/docs/LangRef.rst
+++ b/llvm/docs/LangRef.rst
@@ -15680,12 +15680,15 @@ The first argument to this intrinsic is a scalar start value for the reduction.
 The type of the start value matches the element-type of the vector input.
 The second argument must be a vector of floating-point values.
 
+To ignore the start value, negative zero (``-0.0``) can be used, as it is
+the neutral value of floating point addition.
+
 Examples:
 """""""""
 
 ::
 
-      %unord = call reassoc float @llvm.vector.reduce.fadd.v4f32(float 0.0, <4 x float> %input) ; relaxed reduction
+      %unord = call reassoc float @llvm.vector.reduce.fadd.v4f32(float -0.0, <4 x float> %input) ; relaxed reduction
       %ord = call float @llvm.vector.reduce.fadd.v4f32(float %start_value, <4 x float> %input) ; sequential reduction
 
 
@@ -15751,6 +15754,9 @@ The first argument to this intrinsic is a scalar start value for the reduction.
 The type of the start value matches the element-type of the vector input.
 The second argument must be a vector of floating-point values.
 
+To ignore the start value, one (``1.0``) can be used, as it is the neutral
+value of floating point multiplication.
+
 Examples:
 """""""""
 
diff --git a/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization-strict.ll b/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization-strict.ll
index 12c166490e87..7b957cb11b6e 100644
--- a/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization-strict.ll
+++ b/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization-strict.ll
@@ -9,76 +9,145 @@ declare double @llvm.vector.reduce.fadd.f64.v1f64(double, <1 x double>)
 declare fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128, <1 x fp128>)
 
 declare float @llvm.vector.reduce.fadd.f32.v3f32(float, <3 x float>)
+declare float @llvm.vector.reduce.fadd.f32.v5f32(float, <5 x float>)
 declare fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128, <2 x fp128>)
 declare float @llvm.vector.reduce.fadd.f32.v16f32(float, <16 x float>)
 
-define half @test_v1f16(<1 x half> %a) nounwind {
+define half @test_v1f16(<1 x half> %a, half %s) nounwind {
 ; CHECK-LABEL: test_v1f16:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    fcvt s0, h0
-; CHECK-NEXT:    fmov s1, wzr
-; CHECK-NEXT:    fadd s0, s0, s1
+; CHECK-NEXT:    fcvt s1, h1
+; CHECK-NEXT:    fadd s0, s1, s0
 ; CHECK-NEXT:    fcvt h0, s0
 ; CHECK-NEXT:    ret
-  %b = call half @llvm.vector.reduce.fadd.f16.v1f16(half 0.0, <1 x half> %a)
+  %b = call half @llvm.vector.reduce.fadd.f16.v1f16(half %s, <1 x half> %a)
   ret half %b
 }
 
-define float @test_v1f32(<1 x float> %a) nounwind {
+define half @test_v1f16_neutral(<1 x half> %a) nounwind {
+; CHECK-LABEL: test_v1f16_neutral:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ret
+  %b = call half @llvm.vector.reduce.fadd.f16.v1f16(half -0.0, <1 x half> %a)
+  ret half %b
+}
+
+define float @test_v1f32(<1 x float> %a, float %s) nounwind {
 ; CHECK-LABEL: test_v1f32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
-; CHECK-NEXT:    fmov s1, wzr
-; CHECK-NEXT:    fadd s0, s0, s1
+; CHECK-NEXT:    fadd s0, s1, s0
 ; CHECK-NEXT:    ret
-  %b = call float @llvm.vector.reduce.fadd.f32.v1f32(float 0.0, <1 x float> %a)
+  %b = call float @llvm.vector.reduce.fadd.f32.v1f32(float %s, <1 x float> %a)
   ret float %b
 }
 
-define double @test_v1f64(<1 x double> %a) nounwind {
+define float @test_v1f32_neutral(<1 x float> %a) nounwind {
+; CHECK-LABEL: test_v1f32_neutral:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    // kill: def $s0 killed $s0 killed $q0
+; CHECK-NEXT:    ret
+  %b = call float @llvm.vector.reduce.fadd.f32.v1f32(float -0.0, <1 x float> %a)
+  ret float %b
+}
+
+define double @test_v1f64(<1 x double> %a, double %s) nounwind {
 ; CHECK-LABEL: test_v1f64:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    fmov d1, xzr
-; CHECK-NEXT:    fadd d0, d0, d1
+; CHECK-NEXT:    fadd d0, d1, d0
 ; CHECK-NEXT:    ret
-  %b = call double @llvm.vector.reduce.fadd.f64.v1f64(double 0.0, <1 x double> %a)
+  %b = call double @llvm.vector.reduce.fadd.f64.v1f64(double %s, <1 x double> %a)
   ret double %b
 }
 
-define fp128 @test_v1f128(<1 x fp128> %a) nounwind {
+define double @test_v1f64_neutral(<1 x double> %a) nounwind {
+; CHECK-LABEL: test_v1f64_neutral:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ret
+  %b = call double @llvm.vector.reduce.fadd.f64.v1f64(double -0.0, <1 x double> %a)
+  ret double %b
+}
+
+define fp128 @test_v1f128(<1 x fp128> %a, fp128 %s) nounwind {
 ; CHECK-LABEL: test_v1f128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    adrp x8, .LCPI3_0
-; CHECK-NEXT:    ldr q1, [x8, :lo12:.LCPI3_0]
+; CHECK-NEXT:    mov v2.16b, v0.16b
+; CHECK-NEXT:    mov v0.16b, v1.16b
+; CHECK-NEXT:    mov v1.16b, v2.16b
 ; CHECK-NEXT:    bl __addtf3
 ; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
-  %b = call fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 zeroinitializer, <1 x fp128> %a)
+  %b = call fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 %s, <1 x fp128> %a)
   ret fp128 %b
 }
 
-define float @test_v3f32(<3 x float> %a) nounwind {
+define fp128 @test_v1f128_neutral(<1 x fp128> %a) nounwind {
+; CHECK-LABEL: test_v1f128_neutral:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ret
+  %b = call fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 0xL00000000000000008000000000000000, <1 x fp128> %a)
+  ret fp128 %b
+}
+
+define float @test_v3f32(<3 x float> %a, float %s) nounwind {
 ; CHECK-LABEL: test_v3f32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    fmov s1, wzr
+; CHECK-NEXT:    fadd s1, s1, s0
 ; CHECK-NEXT:    mov s2, v0.s[1]
-; CHECK-NEXT:    fadd s1, s0, s1
 ; CHECK-NEXT:    fadd s1, s1, s2
 ; CHECK-NEXT:    mov s0, v0.s[2]
 ; CHECK-NEXT:    fadd s0, s1, s0
 ; CHECK-NEXT:    ret
-  %b = call float @llvm.vector.reduce.fadd.f32.v3f32(float 0.0, <3 x float> %a)
+  %b = call float @llvm.vector.reduce.fadd.f32.v3f32(float %s, <3 x float> %a)
   ret float %b
 }
 
-define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
+define float @test_v3f32_neutral(<3 x float> %a) nounwind {
+; CHECK-LABEL: test_v3f32_neutral:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    faddp s1, v0.2s
+; CHECK-NEXT:    mov s0, v0.s[2]
+; CHECK-NEXT:    fadd s0, s1, s0
+; CHECK-NEXT:    ret
+  %b = call float @llvm.vector.reduce.fadd.f32.v3f32(float -0.0, <3 x float> %a)
+  ret float %b
+}
+
+define float @test_v5f32(<5 x float> %a, float %s) nounwind {
+; CHECK-LABEL: test_v5f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fadd s0, s5, s0
+; CHECK-NEXT:    fadd s0, s0, s1
+; CHECK-NEXT:    fadd s0, s0, s2
+; CHECK-NEXT:    fadd s0, s0, s3
+; CHECK-NEXT:    fadd s0, s0, s4
+; CHECK-NEXT:    ret
+  %b = call float @llvm.vector.reduce.fadd.f32.v5f32(float %s, <5 x float> %a)
+  ret float %b
+}
+
+define float @test_v5f32_neutral(<5 x float> %a) nounwind {
+; CHECK-LABEL: test_v5f32_neutral:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fadd s0, s0, s1
+; CHECK-NEXT:    fadd s0, s0, s2
+; CHECK-NEXT:    fadd s0, s0, s3
+; CHECK-NEXT:    fadd s0, s0, s4
+; CHECK-NEXT:    ret
+  %b = call float @llvm.vector.reduce.fadd.f32.v5f32(float -0.0, <5 x float> %a)
+  ret float %b
+}
+
+define fp128 @test_v2f128(<2 x fp128> %a, fp128 %s) nounwind {
 ; CHECK-LABEL: test_v2f128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32 // =32
-; CHECK-NEXT:    adrp x8, .LCPI5_0
 ; CHECK-NEXT:    str q1, [sp] // 16-byte Folded Spill
-; CHECK-NEXT:    ldr q1, [x8, :lo12:.LCPI5_0]
+; CHECK-NEXT:    mov v1.16b, v0.16b
+; CHECK-NEXT:    mov v0.16b, v2.16b
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    bl __addtf3
 ; CHECK-NEXT:    ldr q1, [sp] // 16-byte Folded Reload
@@ -86,16 +155,26 @@ define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
 ; CHECK-NEXT:    ldr x30, [sp, #16] // 8-byte Folded Reload
 ; CHECK-NEXT:    add sp, sp, #32 // =32
 ; CHECK-NEXT:    ret
-  %b = call fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 zeroinitializer, <2 x fp128> %a)
+  %b = call fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 %s, <2 x fp128> %a)
   ret fp128 %b
 }
 
-define float @test_v16f32(<16 x float> %a) nounwind {
+define fp128 @test_v2f128_neutral(<2 x fp128> %a) nounwind {
+; CHECK-LABEL: test_v2f128_neutral:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT:    bl __addtf3
+; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
+; CHECK-NEXT:    ret
+  %b = call fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 0xL00000000000000008000000000000000, <2 x fp128> %a)
+  ret fp128 %b
+}
+
+define float @test_v16f32(<16 x float> %a, float %s) nounwind {
 ; CHECK-LABEL: test_v16f32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    fmov s4, wzr
+; CHECK-NEXT:    fadd s4, s4, s0
 ; CHECK-NEXT:    mov s5, v0.s[1]
-; CHECK-NEXT:    fadd s4, s0, s4
 ; CHECK-NEXT:    fadd s4, s4, s5
 ; CHECK-NEXT:    mov s5, v0.s[2]
 ; CHECK-NEXT:    mov s0, v0.s[3]
@@ -123,6 +202,40 @@ define float @test_v16f32(<16 x float> %a) nounwind {
 ; CHECK-NEXT:    mov s1, v3.s[3]
 ; CHECK-NEXT:    fadd s0, s0, s1
 ; CHECK-NEXT:    ret
-  %b = call float @llvm.vector.reduce.fadd.f32.v16f32(float 0.0, <16 x float> %a)
+  %b = call float @llvm.vector.reduce.fadd.f32.v16f32(float %s, <16 x float> %a)
+  ret float %b
+}
+
+define float @test_v16f32_neutral(<16 x float> %a) nounwind {
+; CHECK-LABEL: test_v16f32_neutral:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    faddp s4, v0.2s
+; CHECK-NEXT:    mov s5, v0.s[2]
+; CHECK-NEXT:    mov s0, v0.s[3]
+; CHECK-NEXT:    fadd s4, s4, s5
+; CHECK-NEXT:    fadd s0, s4, s0
+; CHECK-NEXT:    mov s5, v1.s[1]
+; CHECK-NEXT:    fadd s0, s0, s1
+; CHECK-NEXT:    mov s4, v1.s[2]
+; CHECK-NEXT:    fadd s0, s0, s5
+; CHECK-NEXT:    mov s1, v1.s[3]
+; CHECK-NEXT:    fadd s0, s0, s4
+; CHECK-NEXT:    fadd s0, s0, s1
+; CHECK-NEXT:    mov s5, v2.s[1]
+; CHECK-NEXT:    fadd s0, s0, s2
+; CHECK-NEXT:    mov s4, v2.s[2]
+; CHECK-NEXT:    fadd s0, s0, s5
+; CHECK-NEXT:    mov s1, v2.s[3]
+; CHECK-NEXT:    fadd s0, s0, s4
+; CHECK-NEXT:    fadd s0, s0, s1
+; CHECK-NEXT:    mov s2, v3.s[1]
+; CHECK-NEXT:    fadd s0, s0, s3
+; CHECK-NEXT:    mov s5, v3.s[2]
+; CHECK-NEXT:    fadd s0, s0, s2
+; CHECK-NEXT:    fadd s0, s0, s5
+; CHECK-NEXT:    mov s1, v3.s[3]
+; CHECK-NEXT:    fadd s0, s0, s1
+; CHECK-NEXT:    ret
+  %b = call float @llvm.vector.reduce.fadd.f32.v16f32(float -0.0, <16 x float> %a)
   ret float %b
 }
diff --git a/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll b/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll
index 950995f739c4..8bbea08cccb6 100644
--- a/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll
+++ b/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll
@@ -7,6 +7,7 @@ declare double @llvm.vector.reduce.fadd.f64.v1f64(double, <1 x double>)
 declare fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128, <1 x fp128>)
 
 declare float @llvm.vector.reduce.fadd.f32.v3f32(float, <3 x float>)
+declare float @llvm.vector.reduce.fadd.f32.v5f32(float, <5 x float>)
 declare fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128, <2 x fp128>)
 declare float @llvm.vector.reduce.fadd.f32.v16f32(float, <16 x float>)
 
@@ -14,7 +15,7 @@ define half @test_v1f16(<1 x half> %a) nounwind {
 ; CHECK-LABEL: test_v1f16:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    ret
-  %b = call fast nnan half @llvm.vector.reduce.fadd.f16.v1f16(half 0.0, <1 x half> %a)
+  %b = call reassoc half @llvm.vector.reduce.fadd.f16.v1f16(half -0.0, <1 x half> %a)
   ret half %b
 }
 
@@ -24,7 +25,7 @@ define float @test_v1f32(<1 x float> %a) nounwind {
 ; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
 ; CHECK-NEXT:    // kill: def $s0 killed $s0 killed $q0
 ; CHECK-NEXT:    ret
-  %b = call fast nnan float @llvm.vector.reduce.fadd.f32.v1f32(float 0.0, <1 x float> %a)
+  %b = call reassoc float @llvm.vector.reduce.fadd.f32.v1f32(float -0.0, <1 x float> %a)
   ret float %b
 }
 
@@ -32,7 +33,7 @@ define double @test_v1f64(<1 x double> %a) nounwind {
 ; CHECK-LABEL: test_v1f64:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    ret
-  %b = call fast nnan double @llvm.vector.reduce.fadd.f64.v1f64(double 0.0, <1 x double> %a)
+  %b = call reassoc double @llvm.vector.reduce.fadd.f64.v1f64(double -0.0, <1 x double> %a)
   ret double %b
 }
 
@@ -40,7 +41,7 @@ define fp128 @test_v1f128(<1 x fp128> %a) nounwind {
 ; CHECK-LABEL: test_v1f128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    ret
-  %b = call fast nnan fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 zeroinitializer, <1 x fp128> %a)
+  %b = call reassoc fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 0xL00000000000000008000000000000000, <1 x fp128> %a)
   ret fp128 %b
 }
 
@@ -52,7 +53,29 @@ define float @test_v3f32(<3 x float> %a) nounwind {
 ; CHECK-NEXT:    fadd v0.2s, v0.2s, v1.2s
 ; CHECK-NEXT:    faddp s0, v0.2s
 ; CHECK-NEXT:    ret
-  %b = call fast nnan float @llvm.vector.reduce.fadd.f32.v3f32(float 0.0, <3 x float> %a)
+  %b = call reassoc float @llvm.vector.reduce.fadd.f32.v3f32(float -0.0, <3 x float> %a)
+  ret float %b
+}
+
+define float @test_v5f32(<5 x float> %a) nounwind {
+; CHECK-LABEL: test_v5f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $s0 killed $s0 def $q0
+; CHECK-NEXT:    // kill: def $s1 killed $s1 def $q1
+; CHECK-NEXT:    // kill: def $s2 killed $s2 def $q2
+; CHECK-NEXT:    movi v5.2d, #0000000000000000
+; CHECK-NEXT:    mov v0.s[1], v1.s[0]
+; CHECK-NEXT:    mov v0.s[2], v2.s[0]
+; CHECK-NEXT:    // kill: def $s4 killed $s4 def $q4
+; CHECK-NEXT:    // kill: def $s3 killed $s3 def $q3
+; CHECK-NEXT:    mov v0.s[3], v3.s[0]
+; CHECK-NEXT:    mov v5.s[0], v4.s[0]
+; CHECK-NEXT:    fadd v0.4s, v0.4s, v5.4s
+; CHECK-NEXT:    ext v1.16b, v0.16b, v0.16b, #8
+; CHECK-NEXT:    fadd v0.2s, v0.2s, v1.2s
+; CHECK-NEXT:    faddp s0, v0.2s
+; CHECK-NEXT:    ret
+  %b = call reassoc float @llvm.vector.reduce.fadd.f32.v5f32(float -0.0, <5 x float> %a)
   ret float %b
 }
 
@@ -63,7 +86,7 @@ define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
 ; CHECK-NEXT:    bl __addtf3
 ; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
-  %b = call fast nnan fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 zeroinitializer, <2 x fp128> %a)
+  %b = call reassoc fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 0xL00000000000000008000000000000000, <2 x fp128> %a)
   ret fp128 %b
 }
 
@@ -77,6 +100,6 @@ define float @test_v16f32(<16 x float> %a) nounwind {
 ; CHECK-NEXT:    fadd v0.2s, v0.2s, v1.2s
 ; CHECK-NEXT:    faddp s0, v0.2s
 ; CHECK-NEXT:    ret
-  %b = call fast nnan float @llvm.vector.reduce.fadd.f32.v16f32(float 0.0, <16 x float> %a)
+  %b = call reassoc float @llvm.vector.reduce.fadd.f32.v16f32(float -0.0, <16 x float> %a)
   ret float %b
 }
diff --git a/llvm/test/CodeGen/AArch64/vecreduce-fadd.ll b/llvm/test/CodeGen/AArch64/vecreduce-fadd.ll
index 7c5e50a6ef11..12e8be962f79 100644
--- a/llvm/test/CodeGen/AArch64/vecreduce-fadd.ll
+++ b/llvm/test/CodeGen/AArch64/vecreduce-fadd.ll
@@ -14,7 +14,7 @@ define float @add_HalfS(<2 x float> %bin.rdx)  {
 ; CHECKNOFP16-NEXT:    // kill: def $d0 killed $d0 def $q0
 ; CHECKNOFP16-NEXT:    faddp s0, v0.2s
 ; CHECKNOFP16-NEXT:    ret
-  %r = call fast float @llvm.vector.reduce.fadd.f32.v2f32(float 0.0, <2 x float> %bin.rdx)
+  %r = call fast float @llvm.vector.reduce.fadd.f32.v2f32(float -0.0, <2 x float> %bin.rdx)
   ret float %r
 }
 
@@ -48,7 +48,7 @@ define half @add_HalfH(<4 x half> %bin.rdx)  {
 ; CHECKNOFP16-NEXT:    fadd s0, s0, s1
 ; CHECKNOFP16-NEXT:    fcvt h0, s0
 ; CHECKNOFP16-NEXT:    ret
-  %r = call fast half @llvm.vector.reduce.fadd.f16.v4f16(half 0.0, <4 x half> %bin.rdx)
+  %r = call fast half @llvm.vector.reduce.fadd.f16.v4f16(half -0.0, <4 x half> %bin.rdx)
   ret half %r
 }
 
@@ -103,7 +103,7 @@ define half @add_H(<8 x half> %bin.rdx)  {
 ; CHECKNOFP16-NEXT:    fadd s0, s0, s1
 ; CHECKNOFP16-NEXT:    fcvt h0, s0
 ; CHECKNOFP16-NEXT:    ret
-  %r = call fast half @llvm.vector.reduce.fadd.f16.v8f16(half 0.0, <8 x half> %bin.rdx)
+  %r = call fast half @llvm.vector.reduce.fadd.f16.v8f16(half -0.0, <8 x half> %bin.rdx)
   ret half %r
 }
 
@@ -121,7 +121,7 @@ define float @add_S(<4 x float> %bin.rdx)  {
 ; CHECKNOFP16-NEXT:    fadd v0.2s, v0.2s, v1.2s
 ; CHECKNOFP16-NEXT:    faddp s0, v0.2s
 ; CHECKNOFP16-NEXT:    ret
-  %r = call fast float @llvm.vector.reduce.fadd.f32.v4f32(float 0.0, <4 x float> %bin.rdx)
+  %r = call fast float @llvm.vector.reduce.fadd.f32.v4f32(float -0.0, <4 x float> %bin.rdx)
   ret float %r
 }
 
@@ -135,7 +135,7 @@ define double @add_D(<2 x double> %bin.rdx)  {
 ; CHECKNOFP16:       // %bb.0:
 ; CHECKNOFP16-NEXT:    faddp d0, v0.2d
 ; CHECKNOFP16-NEXT:    ret
-  %r = call fast double @llvm.vector.reduce.fadd.f64.v2f64(double 0.0, <2 x double> %bin.rdx)
+  %r = call fast double @llvm.vector.reduce.fadd.f64.v2f64(double -0.0, <2 x double> %bin.rdx)
   ret double %r
 }
 
@@ -229,7 +229,7 @@ define half @add_2H(<16 x half> %bin.rdx)  {
 ; CHECKNOFP16-NEXT:    fadd s0, s1, s0
 ; CHECKNOFP16-NEXT:    fcvt h0, s0
 ; CHECKNOFP16-NEXT:    ret
-  %r = call fast half @llvm.vector.reduce.fadd.f16.v16f16(half 0.0, <16 x half> %bin.rdx)
+  %r = call fast half @llvm.vector.reduce.fadd.f16.v16f16(half -0.0, <16 x half> %bin.rdx)
   ret half %r
 }
 
@@ -249,7 +249,7 @@ define float @add_2S(<8 x float> %bin.rdx)  {
 ; CHECKNOFP16-NEXT:    fadd v0.2s, v0.2s, v1.2s
 ; CHECKNOFP16-NEXT:    faddp s0, v0.2s
 ; CHECKNOFP16-NEXT:    ret
-  %r = call fast float @llvm.vector.reduce.fadd.f32.v8f32(float 0.0, <8 x float> %bin.rdx)
+  %r = call fast float @llvm.vector.reduce.fadd.f32.v8f32(float -0.0, <8 x float> %bin.rdx)
   ret float %r
 }
 
@@ -265,7 +265,7 @@ define double @add_2D(<4 x double> %bin.rdx)  {
 ; CHECKNOFP16-NEXT:    fadd v0.2d, v0.2d, v1.2d
 ; CHECKNOFP16-NEXT:    faddp d0, v0.2d
 ; CHECKNOFP16-NEXT:    ret
-  %r = call fast double @llvm.vector.reduce.fadd.f64.v4f64(double 0.0, <4 x double> %bin.rdx)
+  %r = call fast double @llvm.vector.reduce.fadd.f64.v4f64(double -0.0, <4 x double> %bin.rdx)
   ret double %r
 }
 
diff --git a/llvm/test/CodeGen/ARM/vecreduce-fadd-legalization-soft-float.ll b/llvm/test/CodeGen/ARM/vecreduce-fadd-legalization-soft-float.ll
index 9e3d7e7775b4..e52b78ca0ea2 100644
--- a/llvm/test/CodeGen/ARM/vecreduce-fadd-legalization-soft-float.ll
+++ b/llvm/test/CodeGen/ARM/vecreduce-fadd-legalization-soft-float.ll
@@ -6,8 +6,8 @@ declare float @llvm.vector.reduce.fadd.f32.v4f32(float, <4 x float>)
 declare double @llvm.vector.reduce.fadd.f64.v2f64(double, <2 x double>)
 declare fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128, <2 x fp128>)
 
-define half @test_v4f16(<4 x half> %a) nounwind {
-; CHECK-LABEL: test_v4f16:
+define half @test_v4f16_reassoc(<4 x half> %a) nounwind {
+; CHECK-LABEL: test_v4f16_reassoc:
 ; CHECK:       @ %bb.0:
 ; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, lr}
 ; CHECK-NEXT:    push {r4, r5, r6, r7, r8, lr}
@@ -37,12 +37,47 @@ define half @test_v4f16(<4 x half> %a) nounwind {
 ; CHECK-NEXT:    bl __aeabi_f2h
 ; CHECK-NEXT:    pop {r4, r5, r6, r7, r8, lr}
 ; CHECK-NEXT:    mov pc, lr
-  %b = call fast half @llvm.vector.reduce.fadd.f16.v4f16(half 0.0, <4 x half> %a)
+  %b = call reassoc half @llvm.vector.reduce.fadd.f16.v4f16(half -0.0, <4 x half> %a)
   ret half %b
 }
 
-define float @test_v4f32(<4 x float> %a) nounwind {
-; CHECK-LABEL: test_v4f32:
+define half @test_v4f16_seq(<4 x half> %a) nounwind {
+; CHECK-LABEL: test_v4f16_seq:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, lr}
+; CHECK-NEXT:    push {r4, r5, r6, r7, r8, lr}
+; CHECK-NEXT:    mov r4, #255
+; CHECK-NEXT:    mov r7, r0
+; CHECK-NEXT:    orr r4, r4, #65280
+; CHECK-NEXT:    mov r5, r2
+; CHECK-NEXT:    and r0, r3, r4
+; CHECK-NEXT:    mov r6, r1
+; CHECK-NEXT:    bl __aeabi_h2f
+; CHECK-NEXT:    mov r8, r0
+; CHECK-NEXT:    and r0, r5, r4
+; CHECK-NEXT:    bl __aeabi_h2f
+; CHECK-NEXT:    mov r5, r0
+; CHECK-NEXT:    and r0, r7, r4
+; CHECK-NEXT:    bl __aeabi_h2f
+; CHECK-NEXT:    mov r7, r0
+; CHECK-NEXT:    and r0, r6, r4
+; CHECK-NEXT:    bl __aeabi_h2f
+; CHECK-NEXT:    mov r1, r0
+; CHECK-NEXT:    mov r0, r7
+; CHECK-NEXT:    bl __aeabi_fadd
+; CHECK-NEXT:    mov r1, r5
+; CHECK-NEXT:    bl __aeabi_fadd
+; CHECK-NEXT:    mov r1, r8
+; CHECK-NEXT:    bl __aeabi_fadd
+; CHECK-NEXT:    bl __aeabi_f2h
+; CHECK-NEXT:    pop {r4, r5, r6, r7, r8, lr}
+; CHECK-NEXT:    mov pc, lr
+  %b = call half @llvm.vector.reduce.fadd.f16.v4f16(half -0.0, <4 x half> %a)
+  ret half %b
+}
+
+define float @test_v4f32_reassoc(<4 x float> %a) nounwind {
+; CHECK-LABEL: test_v4f32_reassoc:
 ; CHECK:       @ %bb.0:
 ; CHECK-NEXT:    .save {r4, r5, r11, lr}
 ; CHECK-NEXT:    push {r4, r5, r11, lr}
@@ -55,24 +90,54 @@ define float @test_v4f32(<4 x float> %a) nounwind {
 ; CHECK-NEXT:    bl __aeabi_fadd
 ; CHECK-NEXT:    pop {r4, r5, r11, lr}
 ; CHECK-NEXT:    mov pc, lr
-  %b = call fast float @llvm.vector.reduce.fadd.f32.v4f32(float 0.0, <4 x float> %a)
+  %b = call reassoc float @llvm.vector.reduce.fadd.f32.v4f32(float -0.0, <4 x float> %a)
   ret float %b
 }
 
-define double @test_v2f64(<2 x double> %a) nounwind {
-; CHECK-LABEL: test_v2f64:
+define float @test_v4f32_seq(<4 x float> %a) nounwind {
+; CHECK-LABEL: test_v4f32_seq:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    .save {r4, r5, r11, lr}
+; CHECK-NEXT:    push {r4, r5, r11, lr}
+; CHECK-NEXT:    mov r4, r3
+; CHECK-NEXT:    mov r5, r2
+; CHECK-NEXT:    bl __aeabi_fadd
+; CHECK-NEXT:    mov r1, r5
+; CHECK-NEXT:    bl __aeabi_fadd
+; CHECK-NEXT:    mov r1, r4
+; CHECK-NEXT:    bl __aeabi_fadd
+; CHECK-NEXT:    pop {r4, r5, r11, lr}
+; CHECK-NEXT:    mov pc, lr
+  %b = call float @llvm.vector.reduce.fadd.f32.v4f32(float -0.0, <4 x float> %a)
+  ret float %b
+}
+
+define double @test_v2f64_reassoc(<2 x double> %a) nounwind {
+; CHECK-LABEL: test_v2f64_reassoc:
 ; CHECK:       @ %bb.0:
 ; CHECK-NEXT:    .save {r11, lr}
 ; CHECK-NEXT:    push {r11, lr}
 ; CHECK-NEXT:    bl __aeabi_dadd
 ; CHECK-NEXT:    pop {r11, lr}
 ; CHECK-NEXT:    mov pc, lr
-  %b = call fast double @llvm.vector.reduce.fadd.f64.v2f64(double zeroinitializer, <2 x double> %a)
+  %b = call reassoc double @llvm.vector.reduce.fadd.f64.v2f64(double -0.0, <2 x double> %a)
   ret double %b
 }
 
-define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
-; CHECK-LABEL: test_v2f128:
+define double @test_v2f64_seq(<2 x double> %a) nounwind {
+; CHECK-LABEL: test_v2f64_seq:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    .save {r11, lr}
+; CHECK-NEXT:    push {r11, lr}
+; CHECK-NEXT:    bl __aeabi_dadd
+; CHECK-NEXT:    pop {r11, lr}
+; CHECK-NEXT:    mov pc, lr
+  %b = call double @llvm.vector.reduce.fadd.f64.v2f64(double -0.0, <2 x double> %a)
+  ret double %b
+}
+
+define fp128 @test_v2f128_reassoc(<2 x fp128> %a) nounwind {
+; CHECK-LABEL: test_v2f128_reassoc:
 ; CHECK:       @ %bb.0:
 ; CHECK-NEXT:    .save {r11, lr}
 ; CHECK-NEXT:    push {r11, lr}
@@ -90,6 +155,29 @@ define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
 ; CHECK-NEXT:    add sp, sp, #16
 ; CHECK-NEXT:    pop {r11, lr}
 ; CHECK-NEXT:    mov pc, lr
-  %b = call fast fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 zeroinitializer, <2 x fp128> %a)
+  %b = call reassoc fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 0xL00000000000000008000000000000000, <2 x fp128> %a)
+  ret fp128 %b
+}
+
+define fp128 @test_v2f128_seq(<2 x fp128> %a) nounwind {
+; CHECK-LABEL: test_v2f128_seq:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    .save {r11, lr}
+; CHECK-NEXT:    push {r11, lr}
+; CHECK-NEXT:    .pad #16
+; CHECK-NEXT:    sub sp, sp, #16
+; CHECK-NEXT:    ldr r12, [sp, #36]
+; CHECK-NEXT:    str r12, [sp, #12]
+; CHECK-NEXT:    ldr r12, [sp, #32]
+; CHECK-NEXT:    str r12, [sp, #8]
+; CHECK-NEXT:    ldr r12, [sp, #28]
+; CHECK-NEXT:    str r12, [sp, #4]
+; CHECK-NEXT:    ldr r12, [sp, #24]
+; CHECK-NEXT:    str r12, [sp]
+; CHECK-NEXT:    bl __addtf3
+; CHECK-NEXT:    add sp, sp, #16
+; CHECK-NEXT:    pop {r11, lr}
+; CHECK-NEXT:    mov pc, lr
+  %b = call fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 0xL00000000000000008000000000000000, <2 x fp128> %a)
   ret fp128 %b
 }
diff --git a/llvm/test/CodeGen/ARM/vecreduce-fadd-legalization-strict.ll b/llvm/test/CodeGen/ARM/vecreduce-fadd-legalization-strict.ll
index 83073b895b2c..3541df933d07 100644
--- a/llvm/test/CodeGen/ARM/vecreduce-fadd-legalization-strict.ll
+++ b/llvm/test/CodeGen/ARM/vecreduce-fadd-legalization-strict.ll
@@ -7,111 +7,228 @@ declare double @llvm.vector.reduce.fadd.f64.v1f64(double, <1 x double>)
 declare fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128, <1 x fp128>)
 
 declare float @llvm.vector.reduce.fadd.f32.v3f32(float, <3 x float>)
+declare float @llvm.vector.reduce.fadd.f32.v5f32(float, <5 x float>)
 declare fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128, <2 x fp128>)
 declare float @llvm.vector.reduce.fadd.f32.v16f32(float, <16 x float>)
 
-define half @test_v1f16(<1 x half> %a) nounwind {
+define half @test_v1f16(<1 x half> %a, half %s) nounwind {
 ; CHECK-LABEL: test_v1f16:
 ; CHECK:       @ %bb.0:
-; CHECK-NEXT:    .save {r11, lr}
-; CHECK-NEXT:    push {r11, lr}
-; CHECK-NEXT:    bl __aeabi_f2h
+; CHECK-NEXT:    .save {r4, r5, r11, lr}
+; CHECK-NEXT:    push {r4, r5, r11, lr}
+; CHECK-NEXT:    .vsave {d8}
+; CHECK-NEXT:    vpush {d8}
+; CHECK-NEXT:    mov r4, r0
+; CHECK-NEXT:    mov r0, r1
 ; CHECK-NEXT:    bl __aeabi_h2f
-; CHECK-NEXT:    vldr s0, .LCPI0_0
-; CHECK-NEXT:    vmov s2, r0
-; CHECK-NEXT:    vadd.f32 s0, s2, s0
+; CHECK-NEXT:    mov r5, r0
+; CHECK-NEXT:    mov r0, r4
+; CHECK-NEXT:    bl __aeabi_f2h
+; CHECK-NEXT:    vmov s16, r5
+; CHECK-NEXT:    bl __aeabi_h2f
+; CHECK-NEXT:    vmov s0, r0
+; CHECK-NEXT:    vadd.f32 s0, s16, s0
 ; CHECK-NEXT:    vmov r0, s0
 ; CHECK-NEXT:    bl __aeabi_f2h
-; CHECK-NEXT:    pop {r11, lr}
+; CHECK-NEXT:    vpop {d8}
+; CHECK-NEXT:    pop {r4, r5, r11, lr}
 ; CHECK-NEXT:    mov pc, lr
-; CHECK-NEXT:    .p2align 2
-; CHECK-NEXT:  @ %bb.1:
-; CHECK-NEXT:  .LCPI0_0:
-; CHECK-NEXT:    .long 0x00000000 @ float 0
-  %b = call half @llvm.vector.reduce.fadd.f16.v1f16(half 0.0, <1 x half> %a)
+  %b = call half @llvm.vector.reduce.fadd.f16.v1f16(half %s, <1 x half> %a)
   ret half %b
 }
 
-define float @test_v1f32(<1 x float> %a) nounwind {
-; CHECK-LABEL: test_v1f32:
-; CHECK:       @ %bb.0:
-; CHECK-NEXT:    vldr s0, .LCPI1_0
-; CHECK-NEXT:    vmov s2, r0
-; CHECK-NEXT:    vadd.f32 s0, s2, s0
-; CHECK-NEXT:    vmov r0, s0
-; CHECK-NEXT:    mov pc, lr
-; CHECK-NEXT:    .p2align 2
-; CHECK-NEXT:  @ %bb.1:
-; CHECK-NEXT:  .LCPI1_0:
-; CHECK-NEXT:    .long 0x00000000 @ float 0
-  %b = call float @llvm.vector.reduce.fadd.f32.v1f32(float 0.0, <1 x float> %a)
-  ret float %b
-}
-
-define double @test_v1f64(<1 x double> %a) nounwind {
-; CHECK-LABEL: test_v1f64:
-; CHECK:       @ %bb.0:
-; CHECK-NEXT:    vmov.i32 d16, #0x0
-; CHECK-NEXT:    vmov d17, r0, r1
-; CHECK-NEXT:    vadd.f64 d16, d17, d16
-; CHECK-NEXT:    vmov r0, r1, d16
-; CHECK-NEXT:    mov pc, lr
-  %b = call double @llvm.vector.reduce.fadd.f64.v1f64(double 0.0, <1 x double> %a)
-  ret double %b
-}
-
-define fp128 @test_v1f128(<1 x fp128> %a) nounwind {
-; CHECK-LABEL: test_v1f128:
+define half @test_v1f16_neutral(<1 x half> %a) nounwind {
+; CHECK-LABEL: test_v1f16_neutral:
 ; CHECK:       @ %bb.0:
 ; CHECK-NEXT:    .save {r11, lr}
 ; CHECK-NEXT:    push {r11, lr}
-; CHECK-NEXT:    .pad #16
-; CHECK-NEXT:    sub sp, sp, #16
-; CHECK-NEXT:    mov r12, #0
-; CHECK-NEXT:    str r12, [sp]
-; CHECK-NEXT:    str r12, [sp, #4]
-; CHECK-NEXT:    str r12, [sp, #8]
-; CHECK-NEXT:    str r12, [sp, #12]
-; CHECK-NEXT:    bl __addtf3
-; CHECK-NEXT:    add sp, sp, #16
+; CHECK-NEXT:    bl __aeabi_f2h
+; CHECK-NEXT:    mov r1, #255
+; CHECK-NEXT:    orr r1, r1, #65280
+; CHECK-NEXT:    and r0, r0, r1
 ; CHECK-NEXT:    pop {r11, lr}
 ; CHECK-NEXT:    mov pc, lr
-  %b = call fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 zeroinitializer, <1 x fp128> %a)
+  %b = call half @llvm.vector.reduce.fadd.f16.v1f16(half -0.0, <1 x half> %a)
+  ret half %b
+}
+
+define float @test_v1f32(<1 x float> %a, float %s) nounwind {
+; CHECK-LABEL: test_v1f32:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    vmov s0, r0
+; CHECK-NEXT:    vmov s2, r1
+; CHECK-NEXT:    vadd.f32 s0, s2, s0
+; CHECK-NEXT:    vmov r0, s0
+; CHECK-NEXT:    mov pc, lr
+  %b = call float @llvm.vector.reduce.fadd.f32.v1f32(float %s, <1 x float> %a)
+  ret float %b
+}
+
+define float @test_v1f32_neutral(<1 x float> %a) nounwind {
+; CHECK-LABEL: test_v1f32_neutral:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    mov pc, lr
+  %b = call float @llvm.vector.reduce.fadd.f32.v1f32(float -0.0, <1 x float> %a)
+  ret float %b
+}
+
+define double @test_v1f64(<1 x double> %a, double %s) nounwind {
+; CHECK-LABEL: test_v1f64:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    vmov d16, r0, r1
+; CHECK-NEXT:    vmov d17, r2, r3
+; CHECK-NEXT:    vadd.f64 d16, d17, d16
+; CHECK-NEXT:    vmov r0, r1, d16
+; CHECK-NEXT:    mov pc, lr
+  %b = call double @llvm.vector.reduce.fadd.f64.v1f64(double %s, <1 x double> %a)
+  ret double %b
+}
+
+define double @test_v1f64_neutral(<1 x double> %a) nounwind {
+; CHECK-LABEL: test_v1f64_neutral:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    mov pc, lr
+  %b = call double @llvm.vector.reduce.fadd.f64.v1f64(double -0.0, <1 x double> %a)
+  ret double %b
+}
+
+define fp128 @test_v1f128(<1 x fp128> %a, fp128 %s) nounwind {
+; CHECK-LABEL: test_v1f128:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    .save {r4, r5, r11, lr}
+; CHECK-NEXT:    push {r4, r5, r11, lr}
+; CHECK-NEXT:    .pad #16
+; CHECK-NEXT:    sub sp, sp, #16
+; CHECK-NEXT:    ldr r12, [sp, #32]
+; CHECK-NEXT:    ldr lr, [sp, #36]
+; CHECK-NEXT:    ldr r4, [sp, #40]
+; CHECK-NEXT:    ldr r5, [sp, #44]
+; CHECK-NEXT:    stm sp, {r0, r1, r2, r3}
+; CHECK-NEXT:    mov r0, r12
+; CHECK-NEXT:    mov r1, lr
+; CHECK-NEXT:    mov r2, r4
+; CHECK-NEXT:    mov r3, r5
+; CHECK-NEXT:    bl __addtf3
+; CHECK-NEXT:    add sp, sp, #16
+; CHECK-NEXT:    pop {r4, r5, r11, lr}
+; CHECK-NEXT:    mov pc, lr
+  %b = call fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 %s, <1 x fp128> %a)
   ret fp128 %b
 }
 
-define float @test_v3f32(<3 x float> %a) nounwind {
+define fp128 @test_v1f128_neutral(<1 x fp128> %a) nounwind {
+; CHECK-LABEL: test_v1f128_neutral:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    mov pc, lr
+  %b = call fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 0xL00000000000000008000000000000000, <1 x fp128> %a)
+  ret fp128 %b
+}
+
+define float @test_v3f32(<3 x float> %a, float %s) nounwind {
 ; CHECK-LABEL: test_v3f32:
 ; CHECK:       @ %bb.0:
 ; CHECK-NEXT:    vmov d3, r2, r3
-; CHECK-NEXT:    vldr s0, .LCPI4_0
+; CHECK-NEXT:    vldr s0, [sp]
 ; CHECK-NEXT:    vmov d2, r0, r1
-; CHECK-NEXT:    vadd.f32 s0, s4, s0
+; CHECK-NEXT:    vadd.f32 s0, s0, s4
 ; CHECK-NEXT:    vadd.f32 s0, s0, s5
 ; CHECK-NEXT:    vadd.f32 s0, s0, s6
 ; CHECK-NEXT:    vmov r0, s0
 ; CHECK-NEXT:    mov pc, lr
-; CHECK-NEXT:    .p2align 2
-; CHECK-NEXT:  @ %bb.1:
-; CHECK-NEXT:  .LCPI4_0:
-; CHECK-NEXT:    .long 0x00000000 @ float 0
-  %b = call float @llvm.vector.reduce.fadd.f32.v3f32(float 0.0, <3 x float> %a)
+  %b = call float @llvm.vector.reduce.fadd.f32.v3f32(float %s, <3 x float> %a)
   ret float %b
 }
 
-define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
+define float @test_v3f32_neutral(<3 x float> %a) nounwind {
+; CHECK-LABEL: test_v3f32_neutral:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    vmov d1, r2, r3
+; CHECK-NEXT:    vmov d0, r0, r1
+; CHECK-NEXT:    vadd.f32 s4, s0, s1
+; CHECK-NEXT:    vadd.f32 s0, s4, s2
+; CHECK-NEXT:    vmov r0, s0
+; CHECK-NEXT:    mov pc, lr
+  %b = call float @llvm.vector.reduce.fadd.f32.v3f32(float -0.0, <3 x float> %a)
+  ret float %b
+}
+
+define float @test_v5f32(<5 x float> %a, float %s) nounwind {
+; CHECK-LABEL: test_v5f32:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    vldr s0, [sp, #4]
+; CHECK-NEXT:    vmov s2, r0
+; CHECK-NEXT:    vadd.f32 s0, s0, s2
+; CHECK-NEXT:    vmov s2, r1
+; CHECK-NEXT:    vadd.f32 s0, s0, s2
+; CHECK-NEXT:    vmov s2, r2
+; CHECK-NEXT:    vadd.f32 s0, s0, s2
+; CHECK-NEXT:    vmov s2, r3
+; CHECK-NEXT:    vadd.f32 s0, s0, s2
+; CHECK-NEXT:    vldr s2, [sp]
+; CHECK-NEXT:    vadd.f32 s0, s0, s2
+; CHECK-NEXT:    vmov r0, s0
+; CHECK-NEXT:    mov pc, lr
+  %b = call float @llvm.vector.reduce.fadd.f32.v5f32(float %s, <5 x float> %a)
+  ret float %b
+}
+
+define float @test_v5f32_neutral(<5 x float> %a) nounwind {
+; CHECK-LABEL: test_v5f32_neutral:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    vmov s0, r1
+; CHECK-NEXT:    vmov s2, r0
+; CHECK-NEXT:    vadd.f32 s0, s2, s0
+; CHECK-NEXT:    vmov s2, r2
+; CHECK-NEXT:    vadd.f32 s0, s0, s2
+; CHECK-NEXT:    vmov s2, r3
+; CHECK-NEXT:    vadd.f32 s0, s0, s2
+; CHECK-NEXT:    vldr s2, [sp]
+; CHECK-NEXT:    vadd.f32 s0, s0, s2
+; CHECK-NEXT:    vmov r0, s0
+; CHECK-NEXT:    mov pc, lr
+  %b = call float @llvm.vector.reduce.fadd.f32.v5f32(float -0.0, <5 x float> %a)
+  ret float %b
+}
+
+define fp128 @test_v2f128(<2 x fp128> %a, fp128 %s) nounwind {
 ; CHECK-LABEL: test_v2f128:
 ; CHECK:       @ %bb.0:
 ; CHECK-NEXT:    .save {r4, r5, r11, lr}
 ; CHECK-NEXT:    push {r4, r5, r11, lr}
 ; CHECK-NEXT:    .pad #16
 ; CHECK-NEXT:    sub sp, sp, #16
-; CHECK-NEXT:    mov r12, #0
-; CHECK-NEXT:    str r12, [sp]
-; CHECK-NEXT:    str r12, [sp, #4]
-; CHECK-NEXT:    str r12, [sp, #8]
-; CHECK-NEXT:    str r12, [sp, #12]
+; CHECK-NEXT:    ldr r12, [sp, #48]
+; CHECK-NEXT:    ldr lr, [sp, #52]
+; CHECK-NEXT:    ldr r4, [sp, #56]
+; CHECK-NEXT:    ldr r5, [sp, #60]
+; CHECK-NEXT:    stm sp, {r0, r1, r2, r3}
+; CHECK-NEXT:    mov r0, r12
+; CHECK-NEXT:    mov r1, lr
+; CHECK-NEXT:    mov r2, r4
+; CHECK-NEXT:    mov r3, r5
 ; CHECK-NEXT:    bl __addtf3
+; CHECK-NEXT:    ldr r4, [sp, #32]
+; CHECK-NEXT:    ldr r5, [sp, #40]
+; CHECK-NEXT:    ldr lr, [sp, #44]
+; CHECK-NEXT:    ldr r12, [sp, #36]
+; CHECK-NEXT:    stm sp, {r4, r12}
+; CHECK-NEXT:    str r5, [sp, #8]
+; CHECK-NEXT:    str lr, [sp, #12]
+; CHECK-NEXT:    bl __addtf3
+; CHECK-NEXT:    add sp, sp, #16
+; CHECK-NEXT:    pop {r4, r5, r11, lr}
+; CHECK-NEXT:    mov pc, lr
+  %b = call fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 %s, <2 x fp128> %a)
+  ret fp128 %b
+}
+
+define fp128 @test_v2f128_neutral(<2 x fp128> %a) nounwind {
+; CHECK-LABEL: test_v2f128_neutral:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    .save {r4, r5, r11, lr}
+; CHECK-NEXT:    push {r4, r5, r11, lr}
+; CHECK-NEXT:    .pad #16
+; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    ldr r12, [sp, #36]
 ; CHECK-NEXT:    ldr lr, [sp, #32]
 ; CHECK-NEXT:    ldr r4, [sp, #40]
@@ -124,18 +241,18 @@ define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
 ; CHECK-NEXT:    add sp, sp, #16
 ; CHECK-NEXT:    pop {r4, r5, r11, lr}
 ; CHECK-NEXT:    mov pc, lr
-  %b = call fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 zeroinitializer, <2 x fp128> %a)
+  %b = call fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 0xL00000000000000008000000000000000, <2 x fp128> %a)
   ret fp128 %b
 }
 
-define float @test_v16f32(<16 x float> %a) nounwind {
+define float @test_v16f32(<16 x float> %a, float %s) nounwind {
 ; CHECK-LABEL: test_v16f32:
 ; CHECK:       @ %bb.0:
 ; CHECK-NEXT:    vmov d3, r2, r3
-; CHECK-NEXT:    vldr s0, .LCPI6_0
+; CHECK-NEXT:    vldr s0, [sp, #48]
 ; CHECK-NEXT:    vmov d2, r0, r1
 ; CHECK-NEXT:    mov r0, sp
-; CHECK-NEXT:    vadd.f32 s0, s4, s0
+; CHECK-NEXT:    vadd.f32 s0, s0, s4
 ; CHECK-NEXT:    vadd.f32 s0, s0, s5
 ; CHECK-NEXT:    vadd.f32 s0, s0, s6
 ; CHECK-NEXT:    vadd.f32 s0, s0, s7
@@ -158,10 +275,38 @@ define float @test_v16f32(<16 x float> %a) nounwind {
 ; CHECK-NEXT:    vadd.f32 s0, s0, s7
 ; CHECK-NEXT:    vmov r0, s0
 ; CHECK-NEXT:    mov pc, lr
-; CHECK-NEXT:    .p2align 2
-; CHECK-NEXT:  @ %bb.1:
-; CHECK-NEXT:  .LCPI6_0:
-; CHECK-NEXT:    .long 0x00000000 @ float 0
-  %b = call float @llvm.vector.reduce.fadd.f32.v16f32(float 0.0, <16 x float> %a)
+  %b = call float @llvm.vector.reduce.fadd.f32.v16f32(float %s, <16 x float> %a)
+  ret float %b
+}
+
+define float @test_v16f32_neutral(<16 x float> %a) nounwind {
+; CHECK-LABEL: test_v16f32_neutral:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    vmov d1, r2, r3
+; CHECK-NEXT:    vmov d0, r0, r1
+; CHECK-NEXT:    mov r0, sp
+; CHECK-NEXT:    vadd.f32 s4, s0, s1
+; CHECK-NEXT:    vadd.f32 s4, s4, s2
+; CHECK-NEXT:    vadd.f32 s0, s4, s3
+; CHECK-NEXT:    vld1.64 {d2, d3}, [r0]
+; CHECK-NEXT:    add r0, sp, #16
+; CHECK-NEXT:    vadd.f32 s0, s0, s4
+; CHECK-NEXT:    vadd.f32 s0, s0, s5
+; CHECK-NEXT:    vadd.f32 s0, s0, s6
+; CHECK-NEXT:    vadd.f32 s0, s0, s7
+; CHECK-NEXT:    vld1.64 {d2, d3}, [r0]
+; CHECK-NEXT:    add r0, sp, #32
+; CHECK-NEXT:    vadd.f32 s0, s0, s4
+; CHECK-NEXT:    vadd.f32 s0, s0, s5
+; CHECK-NEXT:    vadd.f32 s0, s0, s6
+; CHECK-NEXT:    vadd.f32 s0, s0, s7
+; CHECK-NEXT:    vld1.64 {d2, d3}, [r0]
+; CHECK-NEXT:    vadd.f32 s0, s0, s4
+; CHECK-NEXT:    vadd.f32 s0, s0, s5
+; CHECK-NEXT:    vadd.f32 s0, s0, s6
+; CHECK-NEXT:    vadd.f32 s0, s0, s7
+; CHECK-NEXT:    vmov r0, s0
+; CHECK-NEXT:    mov pc, lr
+  %b = call float @llvm.vector.reduce.fadd.f32.v16f32(float -0.0, <16 x float> %a)
   ret float %b
 }
diff --git a/llvm/test/CodeGen/X86/vector-reduce-fadd.ll b/llvm/test/CodeGen/X86/vector-reduce-fadd.ll
index ebcf1d38e23b..74213c015769 100644
--- a/llvm/test/CodeGen/X86/vector-reduce-fadd.ll
+++ b/llvm/test/CodeGen/X86/vector-reduce-fadd.ll
@@ -338,107 +338,121 @@ define float @test_v16f32(float %a0, <16 x float> %a1) {
 define float @test_v2f32_zero(<2 x float> %a0) {
 ; SSE2-LABEL: test_v2f32_zero:
 ; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorps %xmm1, %xmm1
+; SSE2-NEXT:    movaps %xmm0, %xmm1
+; SSE2-NEXT:    shufps {{.*#+}} xmm1 = xmm1[1,1],xmm0[1,1]
 ; SSE2-NEXT:    addss %xmm0, %xmm1
-; SSE2-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,1,1,1]
-; SSE2-NEXT:    addss %xmm1, %xmm0
+; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSE41-LABEL: test_v2f32_zero:
 ; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorps %xmm1, %xmm1
-; SSE41-NEXT:    addss %xmm0, %xmm1
-; SSE41-NEXT:    movshdup {{.*#+}} xmm0 = xmm0[1,1,3,3]
+; SSE41-NEXT:    movshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
 ; SSE41-NEXT:    addss %xmm1, %xmm0
 ; SSE41-NEXT:    retq
 ;
-; AVX-LABEL: test_v2f32_zero:
-; AVX:       # %bb.0:
-; AVX-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    vaddss %xmm1, %xmm0, %xmm1
-; AVX-NEXT:    vmovshdup {{.*#+}} xmm0 = xmm0[1,1,3,3]
-; AVX-NEXT:    vaddss %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    retq
+; AVX1-SLOW-LABEL: test_v2f32_zero:
+; AVX1-SLOW:       # %bb.0:
+; AVX1-SLOW-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    retq
+;
+; AVX1-FAST-LABEL: test_v2f32_zero:
+; AVX1-FAST:       # %bb.0:
+; AVX1-FAST-NEXT:    vhaddps %xmm0, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    retq
+;
+; AVX2-LABEL: test_v2f32_zero:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; AVX2-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: test_v2f32_zero:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; AVX512-NEXT:    vaddss %xmm1, %xmm0, %xmm1
-; AVX512-NEXT:    vmovshdup {{.*#+}} xmm0 = xmm0[1,1,3,3]
-; AVX512-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; AVX512-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; AVX512-NEXT:    vaddss %xmm1, %xmm0, %xmm0
 ; AVX512-NEXT:    retq
-  %1 = call float @llvm.vector.reduce.fadd.f32.v2f32(float 0.0, <2 x float> %a0)
+  %1 = call float @llvm.vector.reduce.fadd.f32.v2f32(float -0.0, <2 x float> %a0)
   ret float %1
 }
 
 define float @test_v4f32_zero(<4 x float> %a0) {
 ; SSE2-LABEL: test_v4f32_zero:
 ; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorps %xmm1, %xmm1
+; SSE2-NEXT:    movaps %xmm0, %xmm1
+; SSE2-NEXT:    shufps {{.*#+}} xmm1 = xmm1[1,1],xmm0[1,1]
 ; SSE2-NEXT:    addss %xmm0, %xmm1
 ; SSE2-NEXT:    movaps %xmm0, %xmm2
-; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[1,1],xmm0[1,1]
+; SSE2-NEXT:    unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
 ; SSE2-NEXT:    addss %xmm1, %xmm2
-; SSE2-NEXT:    movaps %xmm0, %xmm1
-; SSE2-NEXT:    unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
-; SSE2-NEXT:    addss %xmm2, %xmm1
 ; SSE2-NEXT:    shufps {{.*#+}} xmm0 = xmm0[3,3,3,3]
-; SSE2-NEXT:    addss %xmm1, %xmm0
+; SSE2-NEXT:    addss %xmm2, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSE41-LABEL: test_v4f32_zero:
 ; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorps %xmm1, %xmm1
+; SSE41-NEXT:    movshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
 ; SSE41-NEXT:    addss %xmm0, %xmm1
-; SSE41-NEXT:    movshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; SSE41-NEXT:    movaps %xmm0, %xmm2
+; SSE41-NEXT:    unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
 ; SSE41-NEXT:    addss %xmm1, %xmm2
-; SSE41-NEXT:    movaps %xmm0, %xmm1
-; SSE41-NEXT:    unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
-; SSE41-NEXT:    addss %xmm2, %xmm1
 ; SSE41-NEXT:    shufps {{.*#+}} xmm0 = xmm0[3,3,3,3]
-; SSE41-NEXT:    addss %xmm1, %xmm0
+; SSE41-NEXT:    addss %xmm2, %xmm0
 ; SSE41-NEXT:    retq
 ;
-; AVX-LABEL: test_v4f32_zero:
-; AVX:       # %bb.0:
-; AVX-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    vaddss %xmm1, %xmm0, %xmm1
-; AVX-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
-; AVX-NEXT:    vaddss %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
-; AVX-NEXT:    vaddss %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
-; AVX-NEXT:    vaddss %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    retq
+; AVX1-SLOW-LABEL: test_v4f32_zero:
+; AVX1-SLOW:       # %bb.0:
+; AVX1-SLOW-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm1, %xmm0, %xmm1
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX1-SLOW-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; AVX1-SLOW-NEXT:    retq
+;
+; AVX1-FAST-LABEL: test_v4f32_zero:
+; AVX1-FAST:       # %bb.0:
+; AVX1-FAST-NEXT:    vhaddps %xmm0, %xmm0, %xmm1
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
+; AVX1-FAST-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX1-FAST-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
+; AVX1-FAST-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; AVX1-FAST-NEXT:    retq
+;
+; AVX2-LABEL: test_v4f32_zero:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; AVX2-NEXT:    vaddss %xmm1, %xmm0, %xmm1
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
+; AVX2-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX2-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
+; AVX2-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: test_v4f32_zero:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vxorps %xmm1, %xmm1, %xmm1
+; AVX512-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
 ; AVX512-NEXT:    vaddss %xmm1, %xmm0, %xmm1
-; AVX512-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
-; AVX512-NEXT:    vaddss %xmm2, %xmm1, %xmm1
 ; AVX512-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
 ; AVX512-NEXT:    vaddss %xmm2, %xmm1, %xmm1
 ; AVX512-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
 ; AVX512-NEXT:    vaddss %xmm0, %xmm1, %xmm0
 ; AVX512-NEXT:    retq
-  %1 = call float @llvm.vector.reduce.fadd.f32.v4f32(float 0.0, <4 x float> %a0)
+  %1 = call float @llvm.vector.reduce.fadd.f32.v4f32(float -0.0, <4 x float> %a0)
   ret float %1
 }
 
 define float @test_v8f32_zero(<8 x float> %a0) {
 ; SSE2-LABEL: test_v8f32_zero:
 ; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorps %xmm2, %xmm2
+; SSE2-NEXT:    movaps %xmm0, %xmm2
+; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[1,1],xmm0[1,1]
 ; SSE2-NEXT:    addss %xmm0, %xmm2
 ; SSE2-NEXT:    movaps %xmm0, %xmm3
-; SSE2-NEXT:    shufps {{.*#+}} xmm3 = xmm3[1,1],xmm0[1,1]
+; SSE2-NEXT:    unpckhpd {{.*#+}} xmm3 = xmm3[1],xmm0[1]
 ; SSE2-NEXT:    addss %xmm2, %xmm3
-; SSE2-NEXT:    movaps %xmm0, %xmm2
-; SSE2-NEXT:    unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
-; SSE2-NEXT:    addss %xmm3, %xmm2
 ; SSE2-NEXT:    shufps {{.*#+}} xmm0 = xmm0[3,3,3,3]
-; SSE2-NEXT:    addss %xmm2, %xmm0
+; SSE2-NEXT:    addss %xmm3, %xmm0
 ; SSE2-NEXT:    addss %xmm1, %xmm0
 ; SSE2-NEXT:    movaps %xmm1, %xmm2
 ; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[1,1],xmm1[1,1]
@@ -452,15 +466,13 @@ define float @test_v8f32_zero(<8 x float> %a0) {
 ;
 ; SSE41-LABEL: test_v8f32_zero:
 ; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorps %xmm2, %xmm2
+; SSE41-NEXT:    movshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
 ; SSE41-NEXT:    addss %xmm0, %xmm2
-; SSE41-NEXT:    movshdup {{.*#+}} xmm3 = xmm0[1,1,3,3]
+; SSE41-NEXT:    movaps %xmm0, %xmm3
+; SSE41-NEXT:    unpckhpd {{.*#+}} xmm3 = xmm3[1],xmm0[1]
 ; SSE41-NEXT:    addss %xmm2, %xmm3
-; SSE41-NEXT:    movaps %xmm0, %xmm2
-; SSE41-NEXT:    unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
-; SSE41-NEXT:    addss %xmm3, %xmm2
 ; SSE41-NEXT:    shufps {{.*#+}} xmm0 = xmm0[3,3,3,3]
-; SSE41-NEXT:    addss %xmm2, %xmm0
+; SSE41-NEXT:    addss %xmm3, %xmm0
 ; SSE41-NEXT:    addss %xmm1, %xmm0
 ; SSE41-NEXT:    movshdup {{.*#+}} xmm2 = xmm1[1,1,3,3]
 ; SSE41-NEXT:    addss %xmm2, %xmm0
@@ -471,33 +483,66 @@ define float @test_v8f32_zero(<8 x float> %a0) {
 ; SSE41-NEXT:    addss %xmm1, %xmm0
 ; SSE41-NEXT:    retq
 ;
-; AVX-LABEL: test_v8f32_zero:
-; AVX:       # %bb.0:
-; AVX-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    vaddss %xmm1, %xmm0, %xmm1
-; AVX-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
-; AVX-NEXT:    vaddss %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
-; AVX-NEXT:    vaddss %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[3,3,3,3]
-; AVX-NEXT:    vaddss %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX-NEXT:    vaddss %xmm0, %xmm1, %xmm1
-; AVX-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
-; AVX-NEXT:    vaddss %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
-; AVX-NEXT:    vaddss %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
-; AVX-NEXT:    vaddss %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-SLOW-LABEL: test_v8f32_zero:
+; AVX1-SLOW:       # %bb.0:
+; AVX1-SLOW-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm1, %xmm0, %xmm1
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX1-SLOW-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[3,3,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX1-SLOW-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-SLOW-NEXT:    vaddss %xmm0, %xmm1, %xmm1
+; AVX1-SLOW-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX1-SLOW-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; AVX1-SLOW-NEXT:    vzeroupper
+; AVX1-SLOW-NEXT:    retq
+;
+; AVX1-FAST-LABEL: test_v8f32_zero:
+; AVX1-FAST:       # %bb.0:
+; AVX1-FAST-NEXT:    vhaddps %xmm0, %xmm0, %xmm1
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
+; AVX1-FAST-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX1-FAST-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[3,3,3,3]
+; AVX1-FAST-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX1-FAST-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-FAST-NEXT:    vaddss %xmm0, %xmm1, %xmm1
+; AVX1-FAST-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; AVX1-FAST-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
+; AVX1-FAST-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX1-FAST-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
+; AVX1-FAST-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; AVX1-FAST-NEXT:    vzeroupper
+; AVX1-FAST-NEXT:    retq
+;
+; AVX2-LABEL: test_v8f32_zero:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; AVX2-NEXT:    vaddss %xmm1, %xmm0, %xmm1
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
+; AVX2-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX2-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[3,3,3,3]
+; AVX2-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX2-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX2-NEXT:    vaddss %xmm0, %xmm1, %xmm1
+; AVX2-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; AVX2-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
+; AVX2-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX2-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
+; AVX2-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: test_v8f32_zero:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vxorps %xmm1, %xmm1, %xmm1
+; AVX512-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
 ; AVX512-NEXT:    vaddss %xmm1, %xmm0, %xmm1
-; AVX512-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
-; AVX512-NEXT:    vaddss %xmm2, %xmm1, %xmm1
 ; AVX512-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
 ; AVX512-NEXT:    vaddss %xmm2, %xmm1, %xmm1
 ; AVX512-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[3,3,3,3]
@@ -512,23 +557,21 @@ define float @test_v8f32_zero(<8 x float> %a0) {
 ; AVX512-NEXT:    vaddss %xmm0, %xmm1, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
-  %1 = call float @llvm.vector.reduce.fadd.f32.v8f32(float 0.0, <8 x float> %a0)
+  %1 = call float @llvm.vector.reduce.fadd.f32.v8f32(float -0.0, <8 x float> %a0)
   ret float %1
 }
 
 define float @test_v16f32_zero(<16 x float> %a0) {
 ; SSE2-LABEL: test_v16f32_zero:
 ; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorps %xmm4, %xmm4
+; SSE2-NEXT:    movaps %xmm0, %xmm4
+; SSE2-NEXT:    shufps {{.*#+}} xmm4 = xmm4[1,1],xmm0[1,1]
 ; SSE2-NEXT:    addss %xmm0, %xmm4
 ; SSE2-NEXT:    movaps %xmm0, %xmm5
-; SSE2-NEXT:    shufps {{.*#+}} xmm5 = xmm5[1,1],xmm0[1,1]
+; SSE2-NEXT:    unpckhpd {{.*#+}} xmm5 = xmm5[1],xmm0[1]
 ; SSE2-NEXT:    addss %xmm4, %xmm5
-; SSE2-NEXT:    movaps %xmm0, %xmm4
-; SSE2-NEXT:    unpckhpd {{.*#+}} xmm4 = xmm4[1],xmm0[1]
-; SSE2-NEXT:    addss %xmm5, %xmm4
 ; SSE2-NEXT:    shufps {{.*#+}} xmm0 = xmm0[3,3,3,3]
-; SSE2-NEXT:    addss %xmm4, %xmm0
+; SSE2-NEXT:    addss %xmm5, %xmm0
 ; SSE2-NEXT:    addss %xmm1, %xmm0
 ; SSE2-NEXT:    movaps %xmm1, %xmm4
 ; SSE2-NEXT:    shufps {{.*#+}} xmm4 = xmm4[1,1],xmm1[1,1]
@@ -560,15 +603,13 @@ define float @test_v16f32_zero(<16 x float> %a0) {
 ;
 ; SSE41-LABEL: test_v16f32_zero:
 ; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorps %xmm4, %xmm4
+; SSE41-NEXT:    movshdup {{.*#+}} xmm4 = xmm0[1,1,3,3]
 ; SSE41-NEXT:    addss %xmm0, %xmm4
-; SSE41-NEXT:    movshdup {{.*#+}} xmm5 = xmm0[1,1,3,3]
+; SSE41-NEXT:    movaps %xmm0, %xmm5
+; SSE41-NEXT:    unpckhpd {{.*#+}} xmm5 = xmm5[1],xmm0[1]
 ; SSE41-NEXT:    addss %xmm4, %xmm5
-; SSE41-NEXT:    movaps %xmm0, %xmm4
-; SSE41-NEXT:    unpckhpd {{.*#+}} xmm4 = xmm4[1],xmm0[1]
-; SSE41-NEXT:    addss %xmm5, %xmm4
 ; SSE41-NEXT:    shufps {{.*#+}} xmm0 = xmm0[3,3,3,3]
-; SSE41-NEXT:    addss %xmm4, %xmm0
+; SSE41-NEXT:    addss %xmm5, %xmm0
 ; SSE41-NEXT:    addss %xmm1, %xmm0
 ; SSE41-NEXT:    movshdup {{.*#+}} xmm4 = xmm1[1,1,3,3]
 ; SSE41-NEXT:    addss %xmm4, %xmm0
@@ -595,48 +636,111 @@ define float @test_v16f32_zero(<16 x float> %a0) {
 ; SSE41-NEXT:    addss %xmm3, %xmm0
 ; SSE41-NEXT:    retq
 ;
-; AVX-LABEL: test_v16f32_zero:
-; AVX:       # %bb.0:
-; AVX-NEXT:    vxorps %xmm2, %xmm2, %xmm2
-; AVX-NEXT:    vaddss %xmm2, %xmm0, %xmm2
-; AVX-NEXT:    vmovshdup {{.*#+}} xmm3 = xmm0[1,1,3,3]
-; AVX-NEXT:    vaddss %xmm3, %xmm2, %xmm2
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
-; AVX-NEXT:    vaddss %xmm3, %xmm2, %xmm2
-; AVX-NEXT:    vpermilps {{.*#+}} xmm3 = xmm0[3,3,3,3]
-; AVX-NEXT:    vaddss %xmm3, %xmm2, %xmm2
-; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX-NEXT:    vaddss %xmm0, %xmm2, %xmm2
-; AVX-NEXT:    vmovshdup {{.*#+}} xmm3 = xmm0[1,1,3,3]
-; AVX-NEXT:    vaddss %xmm3, %xmm2, %xmm2
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
-; AVX-NEXT:    vaddss %xmm3, %xmm2, %xmm2
-; AVX-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
-; AVX-NEXT:    vaddss %xmm0, %xmm2, %xmm0
-; AVX-NEXT:    vaddss %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm1[1,1,3,3]
-; AVX-NEXT:    vaddss %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
-; AVX-NEXT:    vaddss %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vpermilps {{.*#+}} xmm2 = xmm1[3,3,3,3]
-; AVX-NEXT:    vaddss %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX-NEXT:    vaddss %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm1[1,1,3,3]
-; AVX-NEXT:    vaddss %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
-; AVX-NEXT:    vaddss %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[3,3,3,3]
-; AVX-NEXT:    vaddss %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-SLOW-LABEL: test_v16f32_zero:
+; AVX1-SLOW:       # %bb.0:
+; AVX1-SLOW-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm2, %xmm0, %xmm2
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX1-SLOW-NEXT:    vpermilps {{.*#+}} xmm3 = xmm0[3,3,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX1-SLOW-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-SLOW-NEXT:    vaddss %xmm0, %xmm2, %xmm2
+; AVX1-SLOW-NEXT:    vmovshdup {{.*#+}} xmm3 = xmm0[1,1,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX1-SLOW-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm0, %xmm2, %xmm0
+; AVX1-SLOW-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm1[1,1,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
+; AVX1-SLOW-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilps {{.*#+}} xmm2 = xmm1[3,3,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vextractf128 $1, %ymm1, %xmm1
+; AVX1-SLOW-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm1[1,1,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
+; AVX1-SLOW-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[3,3,3,3]
+; AVX1-SLOW-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vzeroupper
+; AVX1-SLOW-NEXT:    retq
+;
+; AVX1-FAST-LABEL: test_v16f32_zero:
+; AVX1-FAST:       # %bb.0:
+; AVX1-FAST-NEXT:    vhaddps %xmm0, %xmm0, %xmm2
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
+; AVX1-FAST-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX1-FAST-NEXT:    vpermilps {{.*#+}} xmm3 = xmm0[3,3,3,3]
+; AVX1-FAST-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX1-FAST-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-FAST-NEXT:    vaddss %xmm0, %xmm2, %xmm2
+; AVX1-FAST-NEXT:    vmovshdup {{.*#+}} xmm3 = xmm0[1,1,3,3]
+; AVX1-FAST-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
+; AVX1-FAST-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX1-FAST-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
+; AVX1-FAST-NEXT:    vaddss %xmm0, %xmm2, %xmm0
+; AVX1-FAST-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm1[1,1,3,3]
+; AVX1-FAST-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
+; AVX1-FAST-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilps {{.*#+}} xmm2 = xmm1[3,3,3,3]
+; AVX1-FAST-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vextractf128 $1, %ymm1, %xmm1
+; AVX1-FAST-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm1[1,1,3,3]
+; AVX1-FAST-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
+; AVX1-FAST-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[3,3,3,3]
+; AVX1-FAST-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vzeroupper
+; AVX1-FAST-NEXT:    retq
+;
+; AVX2-LABEL: test_v16f32_zero:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; AVX2-NEXT:    vaddss %xmm2, %xmm0, %xmm2
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
+; AVX2-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX2-NEXT:    vpermilps {{.*#+}} xmm3 = xmm0[3,3,3,3]
+; AVX2-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX2-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX2-NEXT:    vaddss %xmm0, %xmm2, %xmm2
+; AVX2-NEXT:    vmovshdup {{.*#+}} xmm3 = xmm0[1,1,3,3]
+; AVX2-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
+; AVX2-NEXT:    vaddss %xmm3, %xmm2, %xmm2
+; AVX2-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,3,3,3]
+; AVX2-NEXT:    vaddss %xmm0, %xmm2, %xmm0
+; AVX2-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm1[1,1,3,3]
+; AVX2-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
+; AVX2-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilps {{.*#+}} xmm2 = xmm1[3,3,3,3]
+; AVX2-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vextractf128 $1, %ymm1, %xmm1
+; AVX2-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm1[1,1,3,3]
+; AVX2-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
+; AVX2-NEXT:    vaddss %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[3,3,3,3]
+; AVX2-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: test_v16f32_zero:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vxorps %xmm1, %xmm1, %xmm1
+; AVX512-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
 ; AVX512-NEXT:    vaddss %xmm1, %xmm0, %xmm1
-; AVX512-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
-; AVX512-NEXT:    vaddss %xmm2, %xmm1, %xmm1
 ; AVX512-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
 ; AVX512-NEXT:    vaddss %xmm2, %xmm1, %xmm1
 ; AVX512-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[3,3,3,3]
@@ -667,7 +771,7 @@ define float @test_v16f32_zero(<16 x float> %a0) {
 ; AVX512-NEXT:    vaddss %xmm0, %xmm1, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
-  %1 = call float @llvm.vector.reduce.fadd.f32.v16f32(float 0.0, <16 x float> %a0)
+  %1 = call float @llvm.vector.reduce.fadd.f32.v16f32(float -0.0, <16 x float> %a0)
   ret float %1
 }
 
@@ -1240,116 +1344,171 @@ define double @test_v16f64(double %a0, <16 x double> %a1) {
 define double @test_v2f64_zero(<2 x double> %a0) {
 ; SSE-LABEL: test_v2f64_zero:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    xorpd %xmm1, %xmm1
+; SSE-NEXT:    movapd %xmm0, %xmm1
+; SSE-NEXT:    unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
 ; SSE-NEXT:    addsd %xmm0, %xmm1
-; SSE-NEXT:    unpckhpd {{.*#+}} xmm0 = xmm0[1,1]
-; SSE-NEXT:    addsd %xmm1, %xmm0
+; SSE-NEXT:    movapd %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: test_v2f64_zero:
-; AVX:       # %bb.0:
-; AVX-NEXT:    vxorpd %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm1
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
-; AVX-NEXT:    vaddsd %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    retq
+; AVX1-SLOW-LABEL: test_v2f64_zero:
+; AVX1-SLOW:       # %bb.0:
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    retq
+;
+; AVX1-FAST-LABEL: test_v2f64_zero:
+; AVX1-FAST:       # %bb.0:
+; AVX1-FAST-NEXT:    vhaddpd %xmm0, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    retq
+;
+; AVX2-LABEL: test_v2f64_zero:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: test_v2f64_zero:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vxorpd %xmm1, %xmm1, %xmm1
-; AVX512-NEXT:    vaddsd %xmm1, %xmm0, %xmm1
-; AVX512-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
-; AVX512-NEXT:    vaddsd %xmm0, %xmm1, %xmm0
+; AVX512-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
+; AVX512-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
 ; AVX512-NEXT:    retq
-  %1 = call double @llvm.vector.reduce.fadd.f64.v2f64(double 0.0, <2 x double> %a0)
+  %1 = call double @llvm.vector.reduce.fadd.f64.v2f64(double -0.0, <2 x double> %a0)
   ret double %1
 }
 
 define double @test_v4f64_zero(<4 x double> %a0) {
 ; SSE-LABEL: test_v4f64_zero:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    xorpd %xmm2, %xmm2
+; SSE-NEXT:    movapd %xmm0, %xmm2
+; SSE-NEXT:    unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
 ; SSE-NEXT:    addsd %xmm0, %xmm2
-; SSE-NEXT:    unpckhpd {{.*#+}} xmm0 = xmm0[1,1]
-; SSE-NEXT:    addsd %xmm2, %xmm0
-; SSE-NEXT:    addsd %xmm1, %xmm0
+; SSE-NEXT:    addsd %xmm1, %xmm2
 ; SSE-NEXT:    unpckhpd {{.*#+}} xmm1 = xmm1[1,1]
-; SSE-NEXT:    addsd %xmm1, %xmm0
+; SSE-NEXT:    addsd %xmm1, %xmm2
+; SSE-NEXT:    movapd %xmm2, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: test_v4f64_zero:
-; AVX:       # %bb.0:
-; AVX-NEXT:    vxorpd %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm1
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
-; AVX-NEXT:    vaddsd %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX-NEXT:    vaddsd %xmm0, %xmm1, %xmm1
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
-; AVX-NEXT:    vaddsd %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-SLOW-LABEL: test_v4f64_zero:
+; AVX1-SLOW:       # %bb.0:
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm1
+; AVX1-SLOW-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-SLOW-NEXT:    vaddsd %xmm0, %xmm1, %xmm1
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm0, %xmm1, %xmm0
+; AVX1-SLOW-NEXT:    vzeroupper
+; AVX1-SLOW-NEXT:    retq
+;
+; AVX1-FAST-LABEL: test_v4f64_zero:
+; AVX1-FAST:       # %bb.0:
+; AVX1-FAST-NEXT:    vhaddpd %xmm0, %xmm0, %xmm1
+; AVX1-FAST-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-FAST-NEXT:    vaddsd %xmm0, %xmm1, %xmm1
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; AVX1-FAST-NEXT:    vaddsd %xmm0, %xmm1, %xmm0
+; AVX1-FAST-NEXT:    vzeroupper
+; AVX1-FAST-NEXT:    retq
+;
+; AVX2-LABEL: test_v4f64_zero:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm1
+; AVX2-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX2-NEXT:    vaddsd %xmm0, %xmm1, %xmm1
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; AVX2-NEXT:    vaddsd %xmm0, %xmm1, %xmm0
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: test_v4f64_zero:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vxorpd %xmm1, %xmm1, %xmm1
+; AVX512-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
 ; AVX512-NEXT:    vaddsd %xmm1, %xmm0, %xmm1
-; AVX512-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
-; AVX512-NEXT:    vaddsd %xmm2, %xmm1, %xmm1
 ; AVX512-NEXT:    vextractf128 $1, %ymm0, %xmm0
 ; AVX512-NEXT:    vaddsd %xmm0, %xmm1, %xmm1
 ; AVX512-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
 ; AVX512-NEXT:    vaddsd %xmm0, %xmm1, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
-  %1 = call double @llvm.vector.reduce.fadd.f64.v4f64(double 0.0, <4 x double> %a0)
+  %1 = call double @llvm.vector.reduce.fadd.f64.v4f64(double -0.0, <4 x double> %a0)
   ret double %1
 }
 
 define double @test_v8f64_zero(<8 x double> %a0) {
 ; SSE-LABEL: test_v8f64_zero:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    xorpd %xmm4, %xmm4
+; SSE-NEXT:    movapd %xmm0, %xmm4
+; SSE-NEXT:    unpckhpd {{.*#+}} xmm4 = xmm4[1],xmm0[1]
 ; SSE-NEXT:    addsd %xmm0, %xmm4
-; SSE-NEXT:    unpckhpd {{.*#+}} xmm0 = xmm0[1,1]
-; SSE-NEXT:    addsd %xmm4, %xmm0
-; SSE-NEXT:    addsd %xmm1, %xmm0
+; SSE-NEXT:    addsd %xmm1, %xmm4
 ; SSE-NEXT:    unpckhpd {{.*#+}} xmm1 = xmm1[1,1]
-; SSE-NEXT:    addsd %xmm1, %xmm0
-; SSE-NEXT:    addsd %xmm2, %xmm0
+; SSE-NEXT:    addsd %xmm1, %xmm4
+; SSE-NEXT:    addsd %xmm2, %xmm4
 ; SSE-NEXT:    unpckhpd {{.*#+}} xmm2 = xmm2[1,1]
-; SSE-NEXT:    addsd %xmm2, %xmm0
-; SSE-NEXT:    addsd %xmm3, %xmm0
+; SSE-NEXT:    addsd %xmm2, %xmm4
+; SSE-NEXT:    addsd %xmm3, %xmm4
 ; SSE-NEXT:    unpckhpd {{.*#+}} xmm3 = xmm3[1,1]
-; SSE-NEXT:    addsd %xmm3, %xmm0
+; SSE-NEXT:    addsd %xmm3, %xmm4
+; SSE-NEXT:    movapd %xmm4, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: test_v8f64_zero:
-; AVX:       # %bb.0:
-; AVX-NEXT:    vxorpd %xmm2, %xmm2, %xmm2
-; AVX-NEXT:    vaddsd %xmm2, %xmm0, %xmm2
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
-; AVX-NEXT:    vaddsd %xmm3, %xmm2, %xmm2
-; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX-NEXT:    vaddsd %xmm0, %xmm2, %xmm2
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
-; AVX-NEXT:    vaddsd %xmm0, %xmm2, %xmm0
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
-; AVX-NEXT:    vaddsd %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-SLOW-LABEL: test_v8f64_zero:
+; AVX1-SLOW:       # %bb.0:
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm2, %xmm0, %xmm2
+; AVX1-SLOW-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-SLOW-NEXT:    vaddsd %xmm0, %xmm2, %xmm2
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm0, %xmm2, %xmm0
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm2, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vextractf128 $1, %ymm1, %xmm1
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vzeroupper
+; AVX1-SLOW-NEXT:    retq
+;
+; AVX1-FAST-LABEL: test_v8f64_zero:
+; AVX1-FAST:       # %bb.0:
+; AVX1-FAST-NEXT:    vhaddpd %xmm0, %xmm0, %xmm2
+; AVX1-FAST-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-FAST-NEXT:    vaddsd %xmm0, %xmm2, %xmm2
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; AVX1-FAST-NEXT:    vaddsd %xmm0, %xmm2, %xmm0
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
+; AVX1-FAST-NEXT:    vaddsd %xmm2, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vextractf128 $1, %ymm1, %xmm1
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vzeroupper
+; AVX1-FAST-NEXT:    retq
+;
+; AVX2-LABEL: test_v8f64_zero:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
+; AVX2-NEXT:    vaddsd %xmm2, %xmm0, %xmm2
+; AVX2-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX2-NEXT:    vaddsd %xmm0, %xmm2, %xmm2
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; AVX2-NEXT:    vaddsd %xmm0, %xmm2, %xmm0
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
+; AVX2-NEXT:    vaddsd %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vextractf128 $1, %ymm1, %xmm1
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: test_v8f64_zero:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vxorpd %xmm1, %xmm1, %xmm1
+; AVX512-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
 ; AVX512-NEXT:    vaddsd %xmm1, %xmm0, %xmm1
-; AVX512-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
-; AVX512-NEXT:    vaddsd %xmm2, %xmm1, %xmm1
 ; AVX512-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX512-NEXT:    vaddsd %xmm2, %xmm1, %xmm1
 ; AVX512-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm2[1,0]
@@ -1364,15 +1523,14 @@ define double @test_v8f64_zero(<8 x double> %a0) {
 ; AVX512-NEXT:    vaddsd %xmm0, %xmm1, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
-  %1 = call double @llvm.vector.reduce.fadd.f64.v8f64(double 0.0, <8 x double> %a0)
+  %1 = call double @llvm.vector.reduce.fadd.f64.v8f64(double -0.0, <8 x double> %a0)
   ret double %1
 }
 
 define double @test_v16f64_zero(<16 x double> %a0) {
 ; SSE-LABEL: test_v16f64_zero:
 ; SSE:       # %bb.0:
-; SSE-NEXT:    xorpd %xmm8, %xmm8
-; SSE-NEXT:    addsd %xmm0, %xmm8
+; SSE-NEXT:    movapd %xmm0, %xmm8
 ; SSE-NEXT:    unpckhpd {{.*#+}} xmm0 = xmm0[1,1]
 ; SSE-NEXT:    addsd %xmm8, %xmm0
 ; SSE-NEXT:    addsd %xmm1, %xmm0
@@ -1398,46 +1556,105 @@ define double @test_v16f64_zero(<16 x double> %a0) {
 ; SSE-NEXT:    addsd %xmm7, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: test_v16f64_zero:
-; AVX:       # %bb.0:
-; AVX-NEXT:    vxorpd %xmm4, %xmm4, %xmm4
-; AVX-NEXT:    vaddsd %xmm4, %xmm0, %xmm4
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm5 = xmm0[1,0]
-; AVX-NEXT:    vaddsd %xmm5, %xmm4, %xmm4
-; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX-NEXT:    vaddsd %xmm0, %xmm4, %xmm4
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
-; AVX-NEXT:    vaddsd %xmm0, %xmm4, %xmm0
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm4 = xmm1[1,0]
-; AVX-NEXT:    vaddsd %xmm4, %xmm0, %xmm0
-; AVX-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vaddsd %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm2[1,0]
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vextractf128 $1, %ymm2, %xmm1
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vaddsd %xmm3, %xmm0, %xmm0
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm3[1,0]
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vextractf128 $1, %ymm3, %xmm1
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
-; AVX-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-SLOW-LABEL: test_v16f64_zero:
+; AVX1-SLOW:       # %bb.0:
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm4 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm4, %xmm0, %xmm4
+; AVX1-SLOW-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-SLOW-NEXT:    vaddsd %xmm0, %xmm4, %xmm4
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm0, %xmm4, %xmm0
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm4 = xmm1[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm4, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vextractf128 $1, %ymm1, %xmm1
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vaddsd %xmm2, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm2[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vextractf128 $1, %ymm2, %xmm1
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vaddsd %xmm3, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm3[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vextractf128 $1, %ymm3, %xmm1
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX1-SLOW-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vzeroupper
+; AVX1-SLOW-NEXT:    retq
+;
+; AVX1-FAST-LABEL: test_v16f64_zero:
+; AVX1-FAST:       # %bb.0:
+; AVX1-FAST-NEXT:    vhaddpd %xmm0, %xmm0, %xmm4
+; AVX1-FAST-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-FAST-NEXT:    vaddsd %xmm0, %xmm4, %xmm4
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; AVX1-FAST-NEXT:    vaddsd %xmm0, %xmm4, %xmm0
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm4 = xmm1[1,0]
+; AVX1-FAST-NEXT:    vaddsd %xmm4, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vextractf128 $1, %ymm1, %xmm1
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vaddsd %xmm2, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm2[1,0]
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vextractf128 $1, %ymm2, %xmm1
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vaddsd %xmm3, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm3[1,0]
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vextractf128 $1, %ymm3, %xmm1
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX1-FAST-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX1-FAST-NEXT:    vzeroupper
+; AVX1-FAST-NEXT:    retq
+;
+; AVX2-LABEL: test_v16f64_zero:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm4 = xmm0[1,0]
+; AVX2-NEXT:    vaddsd %xmm4, %xmm0, %xmm4
+; AVX2-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX2-NEXT:    vaddsd %xmm0, %xmm4, %xmm4
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; AVX2-NEXT:    vaddsd %xmm0, %xmm4, %xmm0
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm4 = xmm1[1,0]
+; AVX2-NEXT:    vaddsd %xmm4, %xmm0, %xmm0
+; AVX2-NEXT:    vextractf128 $1, %ymm1, %xmm1
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vaddsd %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm2[1,0]
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vextractf128 $1, %ymm2, %xmm1
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vaddsd %xmm3, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm3[1,0]
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vextractf128 $1, %ymm3, %xmm1
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX2-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: test_v16f64_zero:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vxorpd %xmm2, %xmm2, %xmm2
+; AVX512-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
 ; AVX512-NEXT:    vaddsd %xmm2, %xmm0, %xmm2
-; AVX512-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm0[1,0]
-; AVX512-NEXT:    vaddsd %xmm3, %xmm2, %xmm2
 ; AVX512-NEXT:    vextractf128 $1, %ymm0, %xmm3
 ; AVX512-NEXT:    vaddsd %xmm3, %xmm2, %xmm2
 ; AVX512-NEXT:    vpermilpd {{.*#+}} xmm3 = xmm3[1,0]
@@ -1467,7 +1684,7 @@ define double @test_v16f64_zero(<16 x double> %a0) {
 ; AVX512-NEXT:    vaddsd %xmm1, %xmm0, %xmm0
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
-  %1 = call double @llvm.vector.reduce.fadd.f64.v16f64(double 0.0, <16 x double> %a0)
+  %1 = call double @llvm.vector.reduce.fadd.f64.v16f64(double -0.0, <16 x double> %a0)
   ret double %1
 }