[SLP] Avoid -passes=instcombine stages in SLP tests (#146257)

Fixes #145511

Note that there are still two instances of
--passes=slp-vectorizer,instcombine left unchanged because it seems that
the tests are meant to run in conjunction with instcombine and removing
instcombine would invalidate their original objective:


[llvm/test/Transforms/SLPVectorizer/arith-div-undef.ll](https://github.com/llvm/llvm-project/blob/main/llvm/test/Transforms/SLPVectorizer/arith-div-undef.ll)

[llvm/test/Transforms/SLPVectorizer/slp-hr-with-reuse.ll](https://github.com/llvm/llvm-project/blob/main/llvm/test/Transforms/SLPVectorizer/slp-hr-with-reuse.ll)

Author: ericxu233

llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll

@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -S -passes=slp-vectorizer,instcombine -pass-remarks-output=%t | FileCheck %s
+; RUN: opt < %s -S -passes=slp-vectorizer -pass-remarks-output=%t | FileCheck %s
 ; RUN: cat %t | FileCheck -check-prefix=REMARK %s
-; RUN: opt < %s -S -aa-pipeline=basic-aa -passes='slp-vectorizer,instcombine' -pass-remarks-output=%t | FileCheck %s
+; RUN: opt < %s -S -aa-pipeline=basic-aa -passes='slp-vectorizer' -pass-remarks-output=%t | FileCheck %s
 ; RUN: cat %t | FileCheck -check-prefix=REMARK %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
@@ -16,10 +16,10 @@ target triple = "aarch64--linux-gnu"
 
 define internal i32 @gather_multiple_use(i32 %a, i32 %b, i32 %c, i32 %d) {
 ; CHECK-LABEL: @gather_multiple_use(
-; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x i32> poison, i32 [[C:%.*]], i64 0
-; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x i32> [[TMP1]], i32 [[A:%.*]], i64 1
-; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[B:%.*]], i64 2
-; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> [[TMP3]], i32 [[D:%.*]], i64 3
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x i32> poison, i32 [[C:%.*]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x i32> [[TMP1]], i32 [[A:%.*]], i32 1
+; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[B:%.*]], i32 2
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> [[TMP3]], i32 [[D:%.*]], i32 3
 ; CHECK-NEXT:    [[TMP5:%.*]] = lshr <4 x i32> [[TMP4]], splat (i32 15)
 ; CHECK-NEXT:    [[TMP6:%.*]] = and <4 x i32> [[TMP5]], splat (i32 65537)
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul nuw <4 x i32> [[TMP6]], splat (i32 65535)
@@ -57,22 +57,26 @@ define internal i32 @gather_multiple_use(i32 %a, i32 %b, i32 %c, i32 %d) {
 @data = global [6 x [258 x i8]] zeroinitializer, align 1
 define void @gather_load(ptr noalias %ptr) {
 ; CHECK-LABEL: @gather_load(
-; CHECK-NEXT:    [[ARRAYIDX182:%.*]] = getelementptr inbounds nuw i8, ptr [[PTR:%.*]], i64 2
-; CHECK-NEXT:    [[ARRAYIDX183:%.*]] = getelementptr inbounds nuw i8, ptr [[PTR]], i64 4
-; CHECK-NEXT:    [[ARRAYIDX184:%.*]] = getelementptr inbounds nuw i8, ptr [[PTR]], i64 6
-; CHECK-NEXT:    [[ARRAYIDX185:%.*]] = getelementptr inbounds nuw i8, ptr [[PTR]], i64 8
-; CHECK-NEXT:    [[L0:%.*]] = load i8, ptr getelementptr inbounds nuw (i8, ptr @data, i64 258), align 1
+; CHECK-NEXT:    [[ARRAYIDX182:%.*]] = getelementptr inbounds i16, ptr [[PTR:%.*]], i64 1
+; CHECK-NEXT:    [[ARRAYIDX183:%.*]] = getelementptr inbounds i16, ptr [[PTR]], i64 2
+; CHECK-NEXT:    [[ARRAYIDX184:%.*]] = getelementptr inbounds i16, ptr [[PTR]], i64 3
+; CHECK-NEXT:    [[ARRAYIDX185:%.*]] = getelementptr inbounds i16, ptr [[PTR]], i64 4
+; CHECK-NEXT:    [[ARRAYIDX149:%.*]] = getelementptr inbounds [6 x [258 x i8]], ptr @data, i64 0, i64 1, i64 0
+; CHECK-NEXT:    [[L0:%.*]] = load i8, ptr [[ARRAYIDX149]], align 1
 ; CHECK-NEXT:    [[CONV150:%.*]] = zext i8 [[L0]] to i16
-; CHECK-NEXT:    [[ADD152:%.*]] = add nuw nsw i16 [[CONV150]], 10
-; CHECK-NEXT:    [[L1:%.*]] = load i8, ptr getelementptr inbounds nuw (i8, ptr @data, i64 517), align 1
+; CHECK-NEXT:    [[ADD152:%.*]] = add i16 10, [[CONV150]]
+; CHECK-NEXT:    [[ARRAYIDX155:%.*]] = getelementptr inbounds [6 x [258 x i8]], ptr @data, i64 0, i64 2, i64 1
+; CHECK-NEXT:    [[L1:%.*]] = load i8, ptr [[ARRAYIDX155]], align 1
 ; CHECK-NEXT:    [[CONV156:%.*]] = zext i8 [[L1]] to i16
-; CHECK-NEXT:    [[ADD158:%.*]] = add nuw nsw i16 [[CONV156]], 20
-; CHECK-NEXT:    [[L2:%.*]] = load i8, ptr getelementptr inbounds nuw (i8, ptr @data, i64 776), align 1
+; CHECK-NEXT:    [[ADD158:%.*]] = add i16 20, [[CONV156]]
+; CHECK-NEXT:    [[ARRAYIDX161:%.*]] = getelementptr inbounds [6 x [258 x i8]], ptr @data, i64 0, i64 3, i64 2
+; CHECK-NEXT:    [[L2:%.*]] = load i8, ptr [[ARRAYIDX161]], align 1
 ; CHECK-NEXT:    [[CONV162:%.*]] = zext i8 [[L2]] to i16
-; CHECK-NEXT:    [[ADD164:%.*]] = add nuw nsw i16 [[CONV162]], 30
-; CHECK-NEXT:    [[L3:%.*]] = load i8, ptr getelementptr inbounds nuw (i8, ptr @data, i64 1035), align 1
+; CHECK-NEXT:    [[ADD164:%.*]] = add i16 30, [[CONV162]]
+; CHECK-NEXT:    [[ARRAYIDX167:%.*]] = getelementptr inbounds [6 x [258 x i8]], ptr @data, i64 0, i64 4, i64 3
+; CHECK-NEXT:    [[L3:%.*]] = load i8, ptr [[ARRAYIDX167]], align 1
 ; CHECK-NEXT:    [[CONV168:%.*]] = zext i8 [[L3]] to i16
-; CHECK-NEXT:    [[ADD170:%.*]] = add nuw nsw i16 [[CONV168]], 40
+; CHECK-NEXT:    [[ADD170:%.*]] = add i16 40, [[CONV168]]
 ; CHECK-NEXT:    store i16 [[ADD152]], ptr [[ARRAYIDX182]], align 2
 ; CHECK-NEXT:    store i16 [[ADD158]], ptr [[ARRAYIDX183]], align 2
 ; CHECK-NEXT:    store i16 [[ADD164]], ptr [[ARRAYIDX184]], align 2