Automerge: Revert "[SLP]Improved reduction cost/codegen"

This reverts commit 2ad8166 to fix
bug/miscompiles, reported in
llvm/llvm-project#118293 (comment)
and llvm/llvm-project#118293 (comment).

Author: alexey-bataev

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -19,8 +19,9 @@ define void @foo(ptr %0) {
 ; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <4 x ptr> [[TMP7]], <4 x ptr> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
 ; CHECK-NEXT:    [[TMP9:%.*]] = icmp ult <4 x ptr> [[TMP8]], zeroinitializer
 ; CHECK-NEXT:    [[TMP10:%.*]] = and <4 x i1> [[TMP9]], zeroinitializer
-; CHECK-NEXT:    [[RDX_OP:%.*]] = or <4 x i1> [[TMP5]], [[TMP10]]
-; CHECK-NEXT:    [[OP_RDX:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[RDX_OP]])
+; CHECK-NEXT:    [[TMP11:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[TMP5]])
+; CHECK-NEXT:    [[TMP12:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[TMP10]])
+; CHECK-NEXT:    [[OP_RDX:%.*]] = or i1 [[TMP11]], [[TMP12]]
 ; CHECK-NEXT:    br i1 [[OP_RDX]], label [[DOTLR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    ret void

llvm/test/Transforms/SLPVectorizer/AArch64/InstructionsState-is-invalid-0.ll

@@ -81,9 +81,10 @@ define half @reduce_fast_half8(<8 x half> %vec8) {
 ; NOFP16-SAME: <8 x half> [[VEC8:%.*]]) #[[ATTR0]] {
 ; NOFP16-NEXT:  [[ENTRY:.*:]]
 ; NOFP16-NEXT:    [[TMP0:%.*]] = shufflevector <8 x half> [[VEC8]], <8 x half> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; NOFP16-NEXT:    [[TMP1:%.*]] = call fast half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> [[TMP0]])
 ; NOFP16-NEXT:    [[TMP2:%.*]] = shufflevector <8 x half> [[VEC8]], <8 x half> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; NOFP16-NEXT:    [[RDX_OP:%.*]] = fadd fast <4 x half> [[TMP0]], [[TMP2]]
-; NOFP16-NEXT:    [[OP_RDX3:%.*]] = call fast half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> [[RDX_OP]])
+; NOFP16-NEXT:    [[TMP3:%.*]] = call fast half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> [[TMP2]])
+; NOFP16-NEXT:    [[OP_RDX3:%.*]] = fadd fast half [[TMP1]], [[TMP3]]
 ; NOFP16-NEXT:    ret half [[OP_RDX3]]
 ;
 ; FULLFP16-LABEL: define half @reduce_fast_half8(

llvm/test/Transforms/SLPVectorizer/AArch64/reduce-fadd.ll

@@ -57,9 +57,10 @@ define half @reduction_half16(<16 x half> %vec16) {
 ; VI-LABEL: @reduction_half16(
 ; VI-NEXT:  entry:
 ; VI-NEXT:    [[TMP0:%.*]] = shufflevector <16 x half> [[VEC16:%.*]], <16 x half> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; VI-NEXT:    [[TMP1:%.*]] = call fast half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> [[TMP0]])
 ; VI-NEXT:    [[TMP2:%.*]] = shufflevector <16 x half> [[VEC16]], <16 x half> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; VI-NEXT:    [[RDX_OP:%.*]] = fadd fast <8 x half> [[TMP0]], [[TMP2]]
-; VI-NEXT:    [[OP_RDX:%.*]] = call fast half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> [[RDX_OP]])
+; VI-NEXT:    [[TMP3:%.*]] = call fast half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> [[TMP2]])
+; VI-NEXT:    [[OP_RDX:%.*]] = fadd fast half [[TMP1]], [[TMP3]]
 ; VI-NEXT:    ret half [[OP_RDX]]
 ;
 entry:

llvm/test/Transforms/SLPVectorizer/AMDGPU/reduction.ll

@@ -18,7 +18,7 @@
 ; YAML-NEXT: Function:        test
 ; YAML-NEXT: Args:
 ; YAML-NEXT:   - String:          'Vectorized horizontal reduction with cost '
-; YAML-NEXT:   - Cost:            '-15'
+; YAML-NEXT:   - Cost:            '-14'
 ; YAML-NEXT:   - String:          ' and with tree size '
 ; YAML-NEXT:   - TreeSize:        '1'
 ; YAML-NEXT: ...
@@ -28,7 +28,7 @@
 ; YAML-NEXT: Function:        test
 ; YAML-NEXT: Args:
 ; YAML-NEXT:   - String:          'Vectorized horizontal reduction with cost '
-; YAML-NEXT:   - Cost:            '-6'
+; YAML-NEXT:   - Cost:            '-4'
 ; YAML-NEXT:   - String:          ' and with tree size '
 ; YAML-NEXT:   - TreeSize:        '1'
 ; YAML-NEXT:...
@@ -45,13 +45,11 @@ define float @test(ptr %x) {
 ; CHECK-NEXT:    [[TMP3:%.*]] = load float, ptr [[ARRAYIDX_28]], align 4
 ; CHECK-NEXT:    [[ARRAYIDX_29:%.*]] = getelementptr inbounds float, ptr [[X]], i64 30
 ; CHECK-NEXT:    [[TMP4:%.*]] = load float, ptr [[ARRAYIDX_29]], align 4
-; CHECK-NEXT:    [[TMP5:%.*]] = call fast <8 x float> @llvm.vector.extract.v8f32.v16f32(<16 x float> [[TMP0]], i64 0)
-; CHECK-NEXT:    [[RDX_OP:%.*]] = fadd fast <8 x float> [[TMP5]], [[TMP1]]
-; CHECK-NEXT:    [[TMP6:%.*]] = call fast <16 x float> @llvm.vector.insert.v16f32.v8f32(<16 x float> [[TMP0]], <8 x float> [[RDX_OP]], i64 0)
-; CHECK-NEXT:    [[RDX_OP4:%.*]] = call fast <4 x float> @llvm.vector.extract.v4f32.v16f32(<16 x float> [[TMP6]], i64 0)
-; CHECK-NEXT:    [[RDX_OP5:%.*]] = fadd fast <4 x float> [[RDX_OP4]], [[TMP2]]
-; CHECK-NEXT:    [[TMP8:%.*]] = call fast <16 x float> @llvm.vector.insert.v16f32.v4f32(<16 x float> [[TMP6]], <4 x float> [[RDX_OP5]], i64 0)
-; CHECK-NEXT:    [[OP_RDX1:%.*]] = call fast float @llvm.vector.reduce.fadd.v16f32(float 0.000000e+00, <16 x float> [[TMP8]])
+; CHECK-NEXT:    [[TMP5:%.*]] = call fast float @llvm.vector.reduce.fadd.v16f32(float 0.000000e+00, <16 x float> [[TMP0]])
+; CHECK-NEXT:    [[TMP6:%.*]] = call fast float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> [[TMP1]])
+; CHECK-NEXT:    [[OP_RDX:%.*]] = fadd fast float [[TMP5]], [[TMP6]]
+; CHECK-NEXT:    [[TMP7:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> [[TMP2]])
+; CHECK-NEXT:    [[OP_RDX1:%.*]] = fadd fast float [[OP_RDX]], [[TMP7]]
 ; CHECK-NEXT:    [[OP_RDX2:%.*]] = fadd fast float [[OP_RDX1]], [[TMP3]]
 ; CHECK-NEXT:    [[OP_RDX3:%.*]] = fadd fast float [[OP_RDX2]], [[TMP4]]
 ; CHECK-NEXT:    ret float [[OP_RDX3]]

llvm/test/Transforms/SLPVectorizer/RISCV/horizontal-list.ll

@@ -341,41 +341,44 @@ define void @reduce_or_2() {
 ; ZVFHMIN-NEXT:    [[TMP3:%.*]] = icmp ult <16 x i64> [[TMP2]], zeroinitializer
 ; ZVFHMIN-NEXT:    [[TMP4:%.*]] = insertelement <16 x i64> <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 poison, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>, i64 [[TMP1]], i32 6
 ; ZVFHMIN-NEXT:    [[TMP5:%.*]] = icmp ult <16 x i64> [[TMP4]], zeroinitializer
-; ZVFHMIN-NEXT:    [[RDX_OP:%.*]] = or <16 x i1> [[TMP3]], [[TMP5]]
-; ZVFHMIN-NEXT:    [[OP_RDX:%.*]] = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> [[RDX_OP]])
+; ZVFHMIN-NEXT:    [[TMP6:%.*]] = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> [[TMP3]])
+; ZVFHMIN-NEXT:    [[TMP7:%.*]] = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> [[TMP5]])
+; ZVFHMIN-NEXT:    [[OP_RDX:%.*]] = or i1 [[TMP6]], [[TMP7]]
 ; ZVFHMIN-NEXT:    br i1 [[OP_RDX]], label [[TMP9:%.*]], label [[TMP8:%.*]]
-; ZVFHMIN:       7:
-; ZVFHMIN-NEXT:    ret void
 ; ZVFHMIN:       8:
 ; ZVFHMIN-NEXT:    ret void
+; ZVFHMIN:       9:
+; ZVFHMIN-NEXT:    ret void
 ;
 ; ZVL128-LABEL: @reduce_or_2(
 ; ZVL128-NEXT:    [[TMP1:%.*]] = shl i64 0, 0
 ; ZVL128-NEXT:    [[TMP2:%.*]] = insertelement <16 x i64> <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 poison>, i64 [[TMP1]], i32 15
 ; ZVL128-NEXT:    [[TMP3:%.*]] = icmp ult <16 x i64> [[TMP2]], zeroinitializer
 ; ZVL128-NEXT:    [[TMP4:%.*]] = insertelement <16 x i64> <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 poison, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>, i64 [[TMP1]], i32 6
 ; ZVL128-NEXT:    [[TMP5:%.*]] = icmp ult <16 x i64> [[TMP4]], zeroinitializer
-; ZVL128-NEXT:    [[RDX_OP:%.*]] = or <16 x i1> [[TMP3]], [[TMP5]]
-; ZVL128-NEXT:    [[OP_RDX:%.*]] = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> [[RDX_OP]])
+; ZVL128-NEXT:    [[TMP6:%.*]] = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> [[TMP3]])
+; ZVL128-NEXT:    [[TMP7:%.*]] = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> [[TMP5]])
+; ZVL128-NEXT:    [[OP_RDX:%.*]] = or i1 [[TMP6]], [[TMP7]]
 ; ZVL128-NEXT:    br i1 [[OP_RDX]], label [[TMP9:%.*]], label [[TMP8:%.*]]
-; ZVL128:       7:
-; ZVL128-NEXT:    ret void
 ; ZVL128:       8:
 ; ZVL128-NEXT:    ret void
+; ZVL128:       9:
+; ZVL128-NEXT:    ret void
 ;
 ; ZVL256-LABEL: @reduce_or_2(
 ; ZVL256-NEXT:    [[TMP1:%.*]] = shl i64 0, 0
 ; ZVL256-NEXT:    [[TMP2:%.*]] = insertelement <16 x i64> <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 poison>, i64 [[TMP1]], i32 15
 ; ZVL256-NEXT:    [[TMP3:%.*]] = icmp ult <16 x i64> [[TMP2]], zeroinitializer
 ; ZVL256-NEXT:    [[TMP4:%.*]] = insertelement <16 x i64> <i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 poison, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>, i64 [[TMP1]], i32 6
 ; ZVL256-NEXT:    [[TMP5:%.*]] = icmp ult <16 x i64> [[TMP4]], zeroinitializer
-; ZVL256-NEXT:    [[RDX_OP:%.*]] = or <16 x i1> [[TMP3]], [[TMP5]]
-; ZVL256-NEXT:    [[OP_RDX:%.*]] = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> [[RDX_OP]])
+; ZVL256-NEXT:    [[TMP6:%.*]] = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> [[TMP3]])
+; ZVL256-NEXT:    [[TMP7:%.*]] = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> [[TMP5]])
+; ZVL256-NEXT:    [[OP_RDX:%.*]] = or i1 [[TMP6]], [[TMP7]]
 ; ZVL256-NEXT:    br i1 [[OP_RDX]], label [[TMP9:%.*]], label [[TMP8:%.*]]
-; ZVL256:       7:
-; ZVL256-NEXT:    ret void
 ; ZVL256:       8:
 ; ZVL256-NEXT:    ret void
+; ZVL256:       9:
+; ZVL256-NEXT:    ret void
 ;
 ; ZVL512-LABEL: @reduce_or_2(
 ; ZVL512-NEXT:    [[TMP1:%.*]] = shl i64 0, 0