[ScalarEvolutionExpander] Use IRBuilder::CreateBinOp in SCEVExpander::InsertBinop. #146443

topperc · 2025-07-01T00:50:54Z

Removes the shift pair from add1_3 in #146241.

I think there may be some regressions in here.

…:InsertBinop. Removes the shift pair from add1_3 in llvm#146241.

llvmbot · 2025-07-01T00:51:25Z

@llvm/pr-subscribers-backend-x86

@llvm/pr-subscribers-backend-aarch64

Author: Craig Topper (topperc)

Changes

Removes the shift pair from add1_3 in #146241.

I think there may be some regressions in here.

Patch is 24.13 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/146443.diff

12 Files Affected:

(modified) llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp (+8-8)
(modified) llvm/test/CodeGen/AArch64/sink-and-fold.ll (+4-6)
(modified) llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-dec-le-simple.ll (+16-14)
(modified) llvm/test/CodeGen/X86/break-false-dep.ll (+36-40)
(modified) llvm/test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll (+12-7)
(modified) llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll (+5-6)
(modified) llvm/test/Transforms/LoopStrengthReduce/X86/pr46943.ll (+3-6)
(modified) llvm/test/Transforms/LoopStrengthReduce/depth-limit-overrun.ll (+4-6)
(modified) llvm/test/Transforms/LoopStrengthReduce/lsr-rewrite-to-add-one.ll (+1-2)
(modified) llvm/test/Transforms/LoopStrengthReduce/wrong-hoisting-iv.ll (+3-9)
(modified) llvm/test/Transforms/LoopVectorize/if-conversion.ll (+1-1)
(modified) llvm/test/Transforms/LoopVectorize/version-stride-with-integer-casts.ll (+4-9)

diff --git a/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp b/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp
index 24fe08d6c3e4e..a8caa08d4fdb0 100644
--- a/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp
+++ b/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp
@@ -315,14 +315,14 @@ Value *SCEVExpander::InsertBinop(Instruction::BinaryOps Opcode,
   }
 
   // If we haven't found this binop, insert it.
-  // TODO: Use the Builder, which will make CreateBinOp below fold with
-  // InstSimplifyFolder.
-  Instruction *BO = Builder.Insert(BinaryOperator::Create(Opcode, LHS, RHS));
-  BO->setDebugLoc(Loc);
-  if (Flags & SCEV::FlagNUW)
-    BO->setHasNoUnsignedWrap();
-  if (Flags & SCEV::FlagNSW)
-    BO->setHasNoSignedWrap();
+  Value *BO = Builder.CreateBinOp(Opcode, LHS, RHS);
+  if (auto *BOI = dyn_cast<Instruction>(BO)) {
+    BOI->setDebugLoc(Loc);
+    if (Flags & SCEV::FlagNUW)
+      BOI->setHasNoUnsignedWrap();
+    if (Flags & SCEV::FlagNSW)
+      BOI->setHasNoSignedWrap();
+  }
 
   return BO;
 }
diff --git a/llvm/test/CodeGen/AArch64/sink-and-fold.ll b/llvm/test/CodeGen/AArch64/sink-and-fold.ll
index 163124c0d2757..43db4aa032d1a 100644
--- a/llvm/test/CodeGen/AArch64/sink-and-fold.ll
+++ b/llvm/test/CodeGen/AArch64/sink-and-fold.ll
@@ -151,7 +151,7 @@ define void @f4(ptr %a, i64 %n) nounwind "target-features"="+alu-lsl-fast" {
 ; CHECK-NEXT:  .LBB4_3: // %LI
 ; CHECK-NEXT:    // =>This Loop Header: Depth=1
 ; CHECK-NEXT:    // Child Loop BB4_6 Depth 2
-; CHECK-NEXT:    mov x8, xzr
+; CHECK-NEXT:    mov x21, xzr
 ; CHECK-NEXT:    add x23, x22, #1
 ; CHECK-NEXT:    b .LBB4_6
 ; CHECK-NEXT:  .LBB4_4: // %if.else
@@ -159,16 +159,14 @@ define void @f4(ptr %a, i64 %n) nounwind "target-features"="+alu-lsl-fast" {
 ; CHECK-NEXT:    ldr w0, [x20, x22, lsl #2]
 ; CHECK-NEXT:  .LBB4_5: // %LJ.latch
 ; CHECK-NEXT:    // in Loop: Header=BB4_6 Depth=2
-; CHECK-NEXT:    add x8, x21, #1
+; CHECK-NEXT:    cmp x21, x19
 ; CHECK-NEXT:    str w0, [x20, x21, lsl #2]
-; CHECK-NEXT:    sub x9, x8, #1
-; CHECK-NEXT:    cmp x9, x19
+; CHECK-NEXT:    add x21, x21, #1
 ; CHECK-NEXT:    b.ge .LBB4_2
 ; CHECK-NEXT:  .LBB4_6: // %LJ
 ; CHECK-NEXT:    // Parent Loop BB4_3 Depth=1
 ; CHECK-NEXT:    // => This Inner Loop Header: Depth=2
-; CHECK-NEXT:    mov x21, x8
-; CHECK-NEXT:    ldr w8, [x20, x8, lsl #2]
+; CHECK-NEXT:    ldr w8, [x20, x21, lsl #2]
 ; CHECK-NEXT:    tbz w8, #31, .LBB4_4
 ; CHECK-NEXT:  // %bb.7: // %if.then
 ; CHECK-NEXT:    // in Loop: Header=BB4_6 Depth=2
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-dec-le-simple.ll b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-dec-le-simple.ll
index 8e8934b6e9599..da72ddd81350d 100644
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-dec-le-simple.ll
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-dec-le-simple.ll
@@ -96,17 +96,18 @@ exit:
 define void @cbz_exit_minsize(ptr %in, ptr %res) #0 {
 ; CHECK-LABEL: cbz_exit_minsize:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    movs r2, #0
+; CHECK-NEXT:    push {r4, lr}
+; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:  .LBB3_1: @ %loop
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    ldr.w r3, [r0, r2, lsl #2]
-; CHECK-NEXT:    adds r2, #1
-; CHECK-NEXT:    cmp r3, #0
+; CHECK-NEXT:    ldr.w r4, [r0, r3, lsl #2]
+; CHECK-NEXT:    mov r2, r3
+; CHECK-NEXT:    adds r3, #1
+; CHECK-NEXT:    cmp r4, #0
 ; CHECK-NEXT:    bne .LBB3_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
-; CHECK-NEXT:    subs r0, r2, #1
-; CHECK-NEXT:    str r0, [r1]
-; CHECK-NEXT:    bx lr
+; CHECK-NEXT:    str r2, [r1]
+; CHECK-NEXT:    pop {r4, pc}
 entry:
   br label %loop
 
@@ -126,17 +127,18 @@ exit:
 define void @cbnz_exit_minsize(ptr %in, ptr %res) #0 {
 ; CHECK-LABEL: cbnz_exit_minsize:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    movs r2, #0
+; CHECK-NEXT:    push {r4, lr}
+; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:  .LBB4_1: @ %loop
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    ldr.w r3, [r0, r2, lsl #2]
-; CHECK-NEXT:    adds r2, #1
-; CHECK-NEXT:    cmp r3, #0
+; CHECK-NEXT:    ldr.w r4, [r0, r3, lsl #2]
+; CHECK-NEXT:    mov r2, r3
+; CHECK-NEXT:    adds r3, #1
+; CHECK-NEXT:    cmp r4, #0
 ; CHECK-NEXT:    beq .LBB4_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
-; CHECK-NEXT:    subs r0, r2, #1
-; CHECK-NEXT:    str r0, [r1]
-; CHECK-NEXT:    bx lr
+; CHECK-NEXT:    str r2, [r1]
+; CHECK-NEXT:    pop {r4, pc}
 entry:
   br label %loop
 
diff --git a/llvm/test/CodeGen/X86/break-false-dep.ll b/llvm/test/CodeGen/X86/break-false-dep.ll
index 6943622fac7f2..6df19767b2bb4 100644
--- a/llvm/test/CodeGen/X86/break-false-dep.ll
+++ b/llvm/test/CodeGen/X86/break-false-dep.ll
@@ -1308,28 +1308,27 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; SSE-LINUX-NEXT:  .LBB13_1: # %inner_loop
 ; SSE-LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-LINUX-NEXT:    movq %rcx, %r8
-; SSE-LINUX-NEXT:    shrq $6, %r8
-; SSE-LINUX-NEXT:    movq (%rsi,%r8,8), %r8
-; SSE-LINUX-NEXT:    btq %rcx, %r8
-; SSE-LINUX-NEXT:    leaq 1(%rcx), %rcx
+; SSE-LINUX-NEXT:    shrq $6, %rcx
+; SSE-LINUX-NEXT:    movq (%rsi,%rcx,8), %r9
+; SSE-LINUX-NEXT:    leaq 1(%r8), %rcx
+; SSE-LINUX-NEXT:    btq %r8, %r9
 ; SSE-LINUX-NEXT:    jae .LBB13_1
 ; SSE-LINUX-NEXT:  # %bb.2: # %loop_end
 ; SSE-LINUX-NEXT:    # in Loop: Header=BB13_1 Depth=1
-; SSE-LINUX-NEXT:    leaq 1(%rax), %r8
+; SSE-LINUX-NEXT:    leaq 1(%rax), %r9
 ; SSE-LINUX-NEXT:    xorps %xmm4, %xmm4
-; SSE-LINUX-NEXT:    cvtsi2sd %r8, %xmm4
+; SSE-LINUX-NEXT:    cvtsi2sd %r9, %xmm4
 ; SSE-LINUX-NEXT:    movapd %xmm0, %xmm5
 ; SSE-LINUX-NEXT:    subsd %xmm4, %xmm5
 ; SSE-LINUX-NEXT:    mulsd %xmm1, %xmm5
-; SSE-LINUX-NEXT:    leaq -1(%rcx), %r9
 ; SSE-LINUX-NEXT:    xorps %xmm4, %xmm4
-; SSE-LINUX-NEXT:    cvtsi2sd %r9, %xmm4
+; SSE-LINUX-NEXT:    cvtsi2sd %r8, %xmm4
 ; SSE-LINUX-NEXT:    mulsd %xmm2, %xmm4
 ; SSE-LINUX-NEXT:    addsd %xmm5, %xmm4
 ; SSE-LINUX-NEXT:    divsd %xmm3, %xmm4
 ; SSE-LINUX-NEXT:    movsd %xmm4, -8(%rdi,%rax,8)
-; SSE-LINUX-NEXT:    movq %r8, %rax
-; SSE-LINUX-NEXT:    cmpq %r8, %rdx
+; SSE-LINUX-NEXT:    movq %r9, %rax
+; SSE-LINUX-NEXT:    cmpq %r9, %rdx
 ; SSE-LINUX-NEXT:    jge .LBB13_1
 ; SSE-LINUX-NEXT:  # %bb.3: # %loopdone
 ; SSE-LINUX-NEXT:    retq
@@ -1380,28 +1379,27 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; SSE-WIN-NEXT:  .LBB13_1: # %inner_loop
 ; SSE-WIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-WIN-NEXT:    movq %r9, %r10
-; SSE-WIN-NEXT:    shrq $6, %r10
-; SSE-WIN-NEXT:    movq (%rdx,%r10,8), %r10
-; SSE-WIN-NEXT:    btq %r9, %r10
-; SSE-WIN-NEXT:    leaq 1(%r9), %r9
+; SSE-WIN-NEXT:    shrq $6, %r9
+; SSE-WIN-NEXT:    movq (%rdx,%r9,8), %r11
+; SSE-WIN-NEXT:    leaq 1(%r10), %r9
+; SSE-WIN-NEXT:    btq %r10, %r11
 ; SSE-WIN-NEXT:    jae .LBB13_1
 ; SSE-WIN-NEXT:  # %bb.2: # %loop_end
 ; SSE-WIN-NEXT:    # in Loop: Header=BB13_1 Depth=1
-; SSE-WIN-NEXT:    leaq 1(%r8), %r10
+; SSE-WIN-NEXT:    leaq 1(%r8), %r11
 ; SSE-WIN-NEXT:    xorps %xmm4, %xmm4
-; SSE-WIN-NEXT:    cvtsi2sd %r10, %xmm4
+; SSE-WIN-NEXT:    cvtsi2sd %r11, %xmm4
 ; SSE-WIN-NEXT:    movapd %xmm2, %xmm5
 ; SSE-WIN-NEXT:    subsd %xmm4, %xmm5
 ; SSE-WIN-NEXT:    mulsd %xmm3, %xmm5
-; SSE-WIN-NEXT:    leaq -1(%r9), %r11
 ; SSE-WIN-NEXT:    xorps %xmm4, %xmm4
-; SSE-WIN-NEXT:    cvtsi2sd %r11, %xmm4
+; SSE-WIN-NEXT:    cvtsi2sd %r10, %xmm4
 ; SSE-WIN-NEXT:    mulsd %xmm1, %xmm4
 ; SSE-WIN-NEXT:    addsd %xmm5, %xmm4
 ; SSE-WIN-NEXT:    divsd %xmm0, %xmm4
 ; SSE-WIN-NEXT:    movsd %xmm4, -8(%rcx,%r8,8)
-; SSE-WIN-NEXT:    movq %r10, %r8
-; SSE-WIN-NEXT:    cmpq %r10, %rax
+; SSE-WIN-NEXT:    movq %r11, %r8
+; SSE-WIN-NEXT:    cmpq %r11, %rax
 ; SSE-WIN-NEXT:    jge .LBB13_1
 ; SSE-WIN-NEXT:  # %bb.3: # %loopdone
 ; SSE-WIN-NEXT:    movaps (%rsp), %xmm7 # 16-byte Reload
@@ -1465,25 +1463,24 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; AVX1-NEXT:  .LBB13_1: # %inner_loop
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    movq %r9, %r10
-; AVX1-NEXT:    shrq $6, %r10
-; AVX1-NEXT:    movq (%rdx,%r10,8), %r10
-; AVX1-NEXT:    btq %r9, %r10
-; AVX1-NEXT:    leaq 1(%r9), %r9
+; AVX1-NEXT:    shrq $6, %r9
+; AVX1-NEXT:    movq (%rdx,%r9,8), %r11
+; AVX1-NEXT:    leaq 1(%r10), %r9
+; AVX1-NEXT:    btq %r10, %r11
 ; AVX1-NEXT:    jae .LBB13_1
 ; AVX1-NEXT:  # %bb.2: # %loop_end
 ; AVX1-NEXT:    # in Loop: Header=BB13_1 Depth=1
-; AVX1-NEXT:    leaq 1(%r8), %r10
-; AVX1-NEXT:    vcvtsi2sd %r10, %xmm6, %xmm4
+; AVX1-NEXT:    leaq 1(%r8), %r11
+; AVX1-NEXT:    vcvtsi2sd %r11, %xmm6, %xmm4
 ; AVX1-NEXT:    vsubsd %xmm4, %xmm2, %xmm4
 ; AVX1-NEXT:    vmulsd %xmm3, %xmm4, %xmm4
-; AVX1-NEXT:    leaq -1(%r9), %r11
-; AVX1-NEXT:    vcvtsi2sd %r11, %xmm6, %xmm5
+; AVX1-NEXT:    vcvtsi2sd %r10, %xmm6, %xmm5
 ; AVX1-NEXT:    vmulsd %xmm1, %xmm5, %xmm5
 ; AVX1-NEXT:    vaddsd %xmm5, %xmm4, %xmm4
 ; AVX1-NEXT:    vdivsd %xmm0, %xmm4, %xmm4
 ; AVX1-NEXT:    vmovsd %xmm4, -8(%rcx,%r8,8)
-; AVX1-NEXT:    movq %r10, %r8
-; AVX1-NEXT:    cmpq %r10, %rax
+; AVX1-NEXT:    movq %r11, %r8
+; AVX1-NEXT:    cmpq %r11, %rax
 ; AVX1-NEXT:    jge .LBB13_1
 ; AVX1-NEXT:  # %bb.3: # %loopdone
 ; AVX1-NEXT:    vmovaps (%rsp), %xmm7 # 16-byte Reload
@@ -1547,25 +1544,24 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; AVX512VL-NEXT:  .LBB13_1: # %inner_loop
 ; AVX512VL-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VL-NEXT:    movq %r9, %r10
-; AVX512VL-NEXT:    shrq $6, %r10
-; AVX512VL-NEXT:    movq (%rdx,%r10,8), %r10
-; AVX512VL-NEXT:    btq %r9, %r10
-; AVX512VL-NEXT:    leaq 1(%r9), %r9
+; AVX512VL-NEXT:    shrq $6, %r9
+; AVX512VL-NEXT:    movq (%rdx,%r9,8), %r11
+; AVX512VL-NEXT:    leaq 1(%r10), %r9
+; AVX512VL-NEXT:    btq %r10, %r11
 ; AVX512VL-NEXT:    jae .LBB13_1
 ; AVX512VL-NEXT:  # %bb.2: # %loop_end
 ; AVX512VL-NEXT:    # in Loop: Header=BB13_1 Depth=1
-; AVX512VL-NEXT:    leaq 1(%r8), %r10
-; AVX512VL-NEXT:    vcvtsi2sd %r10, %xmm6, %xmm4
+; AVX512VL-NEXT:    leaq 1(%r8), %r11
+; AVX512VL-NEXT:    vcvtsi2sd %r11, %xmm6, %xmm4
 ; AVX512VL-NEXT:    vsubsd %xmm4, %xmm2, %xmm4
 ; AVX512VL-NEXT:    vmulsd %xmm3, %xmm4, %xmm4
-; AVX512VL-NEXT:    leaq -1(%r9), %r11
-; AVX512VL-NEXT:    vcvtsi2sd %r11, %xmm6, %xmm5
+; AVX512VL-NEXT:    vcvtsi2sd %r10, %xmm6, %xmm5
 ; AVX512VL-NEXT:    vmulsd %xmm1, %xmm5, %xmm5
 ; AVX512VL-NEXT:    vaddsd %xmm5, %xmm4, %xmm4
 ; AVX512VL-NEXT:    vdivsd %xmm0, %xmm4, %xmm4
 ; AVX512VL-NEXT:    vmovsd %xmm4, -8(%rcx,%r8,8)
-; AVX512VL-NEXT:    movq %r10, %r8
-; AVX512VL-NEXT:    cmpq %r10, %rax
+; AVX512VL-NEXT:    movq %r11, %r8
+; AVX512VL-NEXT:    cmpq %r11, %rax
 ; AVX512VL-NEXT:    jge .LBB13_1
 ; AVX512VL-NEXT:  # %bb.3: # %loopdone
 ; AVX512VL-NEXT:    vmovaps (%rsp), %xmm7 # 16-byte Reload
diff --git a/llvm/test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll b/llvm/test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll
index 097575ca86bcc..94d6b180c061a 100644
--- a/llvm/test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll
+++ b/llvm/test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll
@@ -13,9 +13,10 @@ define void @test1(ptr %s, i32 %n) {
 ; CHECK-NEXT:    b.ge .LBB0_2
 ; CHECK-NEXT:  .LBB0_1: // %while_body
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    str w9, [x8, #3140]
+; CHECK-NEXT:    mov w10, w9
 ; CHECK-NEXT:    add w9, w9, #1
 ; CHECK-NEXT:    str w9, [x8, #3136]
+; CHECK-NEXT:    str w10, [x8, #3140]
 ; CHECK-NEXT:    cmp w9, w1
 ; CHECK-NEXT:    b.lt .LBB0_1
 ; CHECK-NEXT:  .LBB0_2: // %while_end
@@ -52,9 +53,10 @@ define void @test2(ptr %struct, i32 %n) {
 ; CHECK-NEXT:    b.ge .LBB1_3
 ; CHECK-NEXT:  .LBB1_2: // %while_body
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    str w9, [x8, #3140]
+; CHECK-NEXT:    mov w10, w9
 ; CHECK-NEXT:    add w9, w9, #1
 ; CHECK-NEXT:    str w9, [x8, #3136]
+; CHECK-NEXT:    str w10, [x8, #3140]
 ; CHECK-NEXT:    cmp w9, w1
 ; CHECK-NEXT:    b.lt .LBB1_2
 ; CHECK-NEXT:  .LBB1_3: // %while_end
@@ -93,9 +95,10 @@ define void @test3(ptr %s1, ptr %s2, i1 %cond, i32 %n) {
 ; CHECK-NEXT:    b.ge .LBB2_3
 ; CHECK-NEXT:  .LBB2_2: // %while_body
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    str w9, [x8, #3140]
+; CHECK-NEXT:    mov w10, w9
 ; CHECK-NEXT:    add w9, w9, #1
 ; CHECK-NEXT:    str w9, [x8, #3136]
+; CHECK-NEXT:    str w10, [x8, #3140]
 ; CHECK-NEXT:    cmp w9, w3
 ; CHECK-NEXT:    b.lt .LBB2_2
 ; CHECK-NEXT:  .LBB2_3: // %while_end
@@ -146,10 +149,11 @@ define void @test4(i32 %n) uwtable personality ptr @__FrameHandler {
 ; CHECK-NEXT:    .cfi_offset w30, -32
 ; CHECK-NEXT:    .cfi_remember_state
 ; CHECK-NEXT:    mov w19, w0
-; CHECK-NEXT:    mov w20, wzr
+; CHECK-NEXT:    mov w9, wzr
 ; CHECK-NEXT:  .LBB3_1: // %while_cond
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:  .Ltmp0:
+; CHECK-NEXT:    mov w20, w9
 ; CHECK-NEXT:    bl foo
 ; CHECK-NEXT:  .Ltmp1:
 ; CHECK-NEXT:  // %bb.2: // %while_cond_x.split
@@ -160,9 +164,9 @@ define void @test4(i32 %n) uwtable personality ptr @__FrameHandler {
 ; CHECK-NEXT:    b.ge .LBB3_4
 ; CHECK-NEXT:  // %bb.3: // %while_body
 ; CHECK-NEXT:    // in Loop: Header=BB3_1 Depth=1
+; CHECK-NEXT:    add w9, w20, #1
 ; CHECK-NEXT:    str w20, [x8, #3140]
-; CHECK-NEXT:    add w20, w20, #1
-; CHECK-NEXT:    str w20, [x8, #3136]
+; CHECK-NEXT:    str w9, [x8, #3136]
 ; CHECK-NEXT:    b .LBB3_1
 ; CHECK-NEXT:  .LBB3_4: // %while_end
 ; CHECK-NEXT:    ldp x20, x19, [sp, #16] // 16-byte Folded Reload
@@ -221,9 +225,10 @@ define void @test5(ptr %s, i32 %n) {
 ; CHECK-NEXT:    b.ge .LBB4_2
 ; CHECK-NEXT:  .LBB4_1: // %while_body
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    str w9, [x8, #2180]
+; CHECK-NEXT:    mov w10, w9
 ; CHECK-NEXT:    add w9, w9, #1
 ; CHECK-NEXT:    str w9, [x8, #2176]
+; CHECK-NEXT:    str w10, [x8, #2180]
 ; CHECK-NEXT:    cmp w9, w1
 ; CHECK-NEXT:    b.lt .LBB4_1
 ; CHECK-NEXT:  .LBB4_2: // %while_end
diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll
index 7ae78ae6a1fd4..6a70fe48de7e2 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll
@@ -20,17 +20,16 @@ define i64 @sqlite3DropTriggerPtr() nounwind {
 ; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    movq %rbx, %rcx
 ; CHECK-NEXT:    testb %al, %al
-; CHECK-NEXT:    je .LBB0_4
+; CHECK-NEXT:    je .LBB0_3
 ; CHECK-NEXT:  # %bb.2: # %bb4
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
-; CHECK-NEXT:    incq %rbx
+; CHECK-NEXT:    leaq 1(%rcx), %rbx
 ; CHECK-NEXT:    testb %al, %al
 ; CHECK-NEXT:    jne .LBB0_1
-; CHECK-NEXT:  # %bb.3: # %bb8split
-; CHECK-NEXT:    decq %rbx
-; CHECK-NEXT:  .LBB0_4: # %bb8
-; CHECK-NEXT:    movq %rbx, %rax
+; CHECK-NEXT:  .LBB0_3: # %bb8
+; CHECK-NEXT:    movq %rcx, %rax
 ; CHECK-NEXT:    popq %rbx
 ; CHECK-NEXT:    retq
 bb:
diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/pr46943.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/pr46943.ll
index 89523b4487d49..b59ca63abfa41 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/X86/pr46943.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/X86/pr46943.ll
@@ -19,8 +19,7 @@ define i8 @drop_nuw() {
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8 [[IV_NEXT]], 0
 ; CHECK-NEXT:    br i1 [[CMP]], label [[EXIT:%.*]], label [[LOOP]]
 ; CHECK:       exit:
-; CHECK-NEXT:    [[TMP0:%.*]] = add i8 [[IV_NEXT]], -1
-; CHECK-NEXT:    ret i8 [[TMP0]]
+; CHECK-NEXT:    ret i8 [[IV]]
 ;
 entry:
   br label %loop
@@ -49,8 +48,7 @@ define i8 @drop_nsw() {
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8 [[IV_NEXT]], 127
 ; CHECK-NEXT:    br i1 [[CMP]], label [[EXIT:%.*]], label [[LOOP]]
 ; CHECK:       exit:
-; CHECK-NEXT:    [[TMP0:%.*]] = add i8 [[IV_NEXT]], 1
-; CHECK-NEXT:    ret i8 [[TMP0]]
+; CHECK-NEXT:    ret i8 [[IV]]
 ;
 entry:
   br label %loop
@@ -79,8 +77,7 @@ define i8 @already_postinc() {
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8 [[IV_NEXT]], -1
 ; CHECK-NEXT:    br i1 [[CMP]], label [[EXIT:%.*]], label [[LOOP]]
 ; CHECK:       exit:
-; CHECK-NEXT:    [[TMP0:%.*]] = add i8 [[IV_NEXT]], -1
-; CHECK-NEXT:    ret i8 [[TMP0]]
+; CHECK-NEXT:    ret i8 [[IV]]
 ;
 entry:
   br label %loop
diff --git a/llvm/test/Transforms/LoopStrengthReduce/depth-limit-overrun.ll b/llvm/test/Transforms/LoopStrengthReduce/depth-limit-overrun.ll
index 9c3698a740992..a46d75ae537ab 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/depth-limit-overrun.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/depth-limit-overrun.ll
@@ -22,10 +22,9 @@ define void @test(i32 %A, i32 %B, i32 %C) {
 ; DEFAULT:       preheader:
 ; DEFAULT-NEXT:    [[I15:%.*]] = shl i32 [[B]], 1
 ; DEFAULT-NEXT:    [[TMP1:%.*]] = mul i32 [[PHI2]], -1
-; DEFAULT-NEXT:    [[TMP2:%.*]] = mul i32 [[TMP1]], -1
-; DEFAULT-NEXT:    [[TMP3:%.*]] = sub i32 [[PHI4]], [[TMP2]]
+; DEFAULT-NEXT:    [[TMP3:%.*]] = sub i32 [[PHI4]], [[PHI2]]
 ; DEFAULT-NEXT:    [[TMP4:%.*]] = add i32 [[B]], [[PHI4]]
-; DEFAULT-NEXT:    [[TMP5:%.*]] = sub i32 [[TMP4]], [[TMP2]]
+; DEFAULT-NEXT:    [[TMP5:%.*]] = sub i32 [[TMP4]], [[PHI2]]
 ; DEFAULT-NEXT:    [[TMP6:%.*]] = sub i32 14, [[TMP5]]
 ; DEFAULT-NEXT:    [[TMP7:%.*]] = add i32 [[TMP0]], [[PHI2]]
 ; DEFAULT-NEXT:    br label [[INNER_LOOP:%.*]]
@@ -87,10 +86,9 @@ define void @test(i32 %A, i32 %B, i32 %C) {
 ; LIMIT:       preheader:
 ; LIMIT-NEXT:    [[I15:%.*]] = shl i32 [[B]], 1
 ; LIMIT-NEXT:    [[TMP1:%.*]] = mul i32 [[PHI2]], -1
-; LIMIT-NEXT:    [[TMP2:%.*]] = mul i32 [[TMP1]], -1
-; LIMIT-NEXT:    [[TMP3:%.*]] = sub i32 [[PHI4]], [[TMP2]]
+; LIMIT-NEXT:    [[TMP3:%.*]] = sub i32 [[PHI4]], [[PHI2]]
 ; LIMIT-NEXT:    [[TMP4:%.*]] = add i32 [[B]], [[PHI4]]
-; LIMIT-NEXT:    [[TMP5:%.*]] = sub i32 [[TMP4]], [[TMP2]]
+; LIMIT-NEXT:    [[TMP5:%.*]] = sub i32 [[TMP4]], [[PHI2]]
 ; LIMIT-NEXT:    [[TMP6:%.*]] = sub i32 14, [[TMP5]]
 ; LIMIT-NEXT:    [[TMP7:%.*]] = add i32 [[TMP0]], [[PHI2]]
 ; LIMIT-NEXT:    br label [[INNER_LOOP:%.*]]
diff --git a/llvm/test/Transforms/LoopStrengthReduce/lsr-rewrite-to-add-one.ll b/llvm/test/Transforms/LoopStrengthReduce/lsr-rewrite-to-add-one.ll
index 74d861cf5168c..d66905ae26f14 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/lsr-rewrite-to-add-one.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/lsr-rewrite-to-add-one.ll
@@ -20,8 +20,7 @@ define i32 @test(i1 %c.1, ptr %src) {
 ; CHECK-NEXT:    [[OR:%.*]] = or i1 [[P]], [[T]]
 ; CHECK-NEXT:    [[ZEXT_OR:%.*]] = zext i1 [[OR]] to i32
 ; CHECK-NEXT:    [[LSR_IV_NEXT]] = add nuw i32 [[LSR_IV]], 1
-; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[LSR_IV_NEXT]], -1
-; CHECK-NEXT:    [[LOOP_HEADER_TERMCOND:%.*]] = icmp sgt i32 [[TMP0]], -1050
+; CHECK-NEXT:    [[LOOP_HEADER_TERMCOND:%.*]] = icmp sgt i32 [[LSR_IV]], -1050
 ; CHECK-NEXT:    br i1 [[LOOP_HEADER_TERMCOND]], label [[LOOP_HEADER]], label [[EXIT:%.*]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    [[ZEXT_OR_LCSSA:%.*]] = phi i32 [ [[ZEXT_OR]], [[LOOP_LATCH]] ]
diff --git a/llvm/test/Transforms/LoopStrengthReduce/wrong-hoisting-iv.ll b/llvm/test/Transforms/LoopStrengthReduce/wrong-hoisting-iv.ll
index 502042eaf9b9c..007d84f9120e3 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/wrong-hoisting-iv.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/wrong-hoisting-iv.ll
@@ -16,9 +16,7 @@ define void @test1() {
 ; CHECK-NEXT:    [[VAL4:%.*]] = sub i32 [[VAL]], [[VAL3]]
 ; CHECK-NEXT:    [[VAL5:%.*]] = ashr i32 undef, undef
 ; CHECK-NEXT:    [[VAL6:%.*]] = sub i32 [[VAL4]], [[VAL5]]
-; CHECK-NEXT:    [[TMP0:%.*]] = mul i32 [[VAL]], 7
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i32 [[VAL3]], 7
-; CHECK-NEXT:    [[TMP2:%.*]] = sub i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP2:%.*]] = mul i32 [[VAL]], 7
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i32 [[VAL5]], 7
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i32 [[TMP2]], [[TMP3]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = shl i32 [[VAL6]], 3
@@ -58,10 +56,8 @@ define void @test1() {
 ; CHECK:       bb20.bb15splitsplitsplit_crit_edge:
 ; CHECK-NEXT:    [[TMP14:%.*]] = mul i32 [[VAL]], 3
 ; CHECK-NEXT:    [[TMP15:%.*]] = mul i32 [[VAL1]], [[VAL2]]
-; CHECK-NEXT:    [[TMP16:%.*]] = mul i32 [[TMP15]], 3
-; CHECK-NEXT:    [[TMP17:%.*]] = sub i32 [[TMP14]...
[truncated]

llvmbot · 2025-07-01T00:51:25Z

@llvm/pr-subscribers-llvm-transforms

Author: Craig Topper (topperc)

Changes

Removes the shift pair from add1_3 in #146241.

I think there may be some regressions in here.

Patch is 24.13 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/146443.diff

12 Files Affected:

(modified) llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp (+8-8)
(modified) llvm/test/CodeGen/AArch64/sink-and-fold.ll (+4-6)
(modified) llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-dec-le-simple.ll (+16-14)
(modified) llvm/test/CodeGen/X86/break-false-dep.ll (+36-40)
(modified) llvm/test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll (+12-7)
(modified) llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll (+5-6)
(modified) llvm/test/Transforms/LoopStrengthReduce/X86/pr46943.ll (+3-6)
(modified) llvm/test/Transforms/LoopStrengthReduce/depth-limit-overrun.ll (+4-6)
(modified) llvm/test/Transforms/LoopStrengthReduce/lsr-rewrite-to-add-one.ll (+1-2)
(modified) llvm/test/Transforms/LoopStrengthReduce/wrong-hoisting-iv.ll (+3-9)
(modified) llvm/test/Transforms/LoopVectorize/if-conversion.ll (+1-1)
(modified) llvm/test/Transforms/LoopVectorize/version-stride-with-integer-casts.ll (+4-9)

diff --git a/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp b/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp
index 24fe08d6c3e4e..a8caa08d4fdb0 100644
--- a/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp
+++ b/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp
@@ -315,14 +315,14 @@ Value *SCEVExpander::InsertBinop(Instruction::BinaryOps Opcode,
   }
 
   // If we haven't found this binop, insert it.
-  // TODO: Use the Builder, which will make CreateBinOp below fold with
-  // InstSimplifyFolder.
-  Instruction *BO = Builder.Insert(BinaryOperator::Create(Opcode, LHS, RHS));
-  BO->setDebugLoc(Loc);
-  if (Flags & SCEV::FlagNUW)
-    BO->setHasNoUnsignedWrap();
-  if (Flags & SCEV::FlagNSW)
-    BO->setHasNoSignedWrap();
+  Value *BO = Builder.CreateBinOp(Opcode, LHS, RHS);
+  if (auto *BOI = dyn_cast<Instruction>(BO)) {
+    BOI->setDebugLoc(Loc);
+    if (Flags & SCEV::FlagNUW)
+      BOI->setHasNoUnsignedWrap();
+    if (Flags & SCEV::FlagNSW)
+      BOI->setHasNoSignedWrap();
+  }
 
   return BO;
 }
diff --git a/llvm/test/CodeGen/AArch64/sink-and-fold.ll b/llvm/test/CodeGen/AArch64/sink-and-fold.ll
index 163124c0d2757..43db4aa032d1a 100644
--- a/llvm/test/CodeGen/AArch64/sink-and-fold.ll
+++ b/llvm/test/CodeGen/AArch64/sink-and-fold.ll
@@ -151,7 +151,7 @@ define void @f4(ptr %a, i64 %n) nounwind "target-features"="+alu-lsl-fast" {
 ; CHECK-NEXT:  .LBB4_3: // %LI
 ; CHECK-NEXT:    // =>This Loop Header: Depth=1
 ; CHECK-NEXT:    // Child Loop BB4_6 Depth 2
-; CHECK-NEXT:    mov x8, xzr
+; CHECK-NEXT:    mov x21, xzr
 ; CHECK-NEXT:    add x23, x22, #1
 ; CHECK-NEXT:    b .LBB4_6
 ; CHECK-NEXT:  .LBB4_4: // %if.else
@@ -159,16 +159,14 @@ define void @f4(ptr %a, i64 %n) nounwind "target-features"="+alu-lsl-fast" {
 ; CHECK-NEXT:    ldr w0, [x20, x22, lsl #2]
 ; CHECK-NEXT:  .LBB4_5: // %LJ.latch
 ; CHECK-NEXT:    // in Loop: Header=BB4_6 Depth=2
-; CHECK-NEXT:    add x8, x21, #1
+; CHECK-NEXT:    cmp x21, x19
 ; CHECK-NEXT:    str w0, [x20, x21, lsl #2]
-; CHECK-NEXT:    sub x9, x8, #1
-; CHECK-NEXT:    cmp x9, x19
+; CHECK-NEXT:    add x21, x21, #1
 ; CHECK-NEXT:    b.ge .LBB4_2
 ; CHECK-NEXT:  .LBB4_6: // %LJ
 ; CHECK-NEXT:    // Parent Loop BB4_3 Depth=1
 ; CHECK-NEXT:    // => This Inner Loop Header: Depth=2
-; CHECK-NEXT:    mov x21, x8
-; CHECK-NEXT:    ldr w8, [x20, x8, lsl #2]
+; CHECK-NEXT:    ldr w8, [x20, x21, lsl #2]
 ; CHECK-NEXT:    tbz w8, #31, .LBB4_4
 ; CHECK-NEXT:  // %bb.7: // %if.then
 ; CHECK-NEXT:    // in Loop: Header=BB4_6 Depth=2
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-dec-le-simple.ll b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-dec-le-simple.ll
index 8e8934b6e9599..da72ddd81350d 100644
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-dec-le-simple.ll
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/no-dec-le-simple.ll
@@ -96,17 +96,18 @@ exit:
 define void @cbz_exit_minsize(ptr %in, ptr %res) #0 {
 ; CHECK-LABEL: cbz_exit_minsize:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    movs r2, #0
+; CHECK-NEXT:    push {r4, lr}
+; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:  .LBB3_1: @ %loop
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    ldr.w r3, [r0, r2, lsl #2]
-; CHECK-NEXT:    adds r2, #1
-; CHECK-NEXT:    cmp r3, #0
+; CHECK-NEXT:    ldr.w r4, [r0, r3, lsl #2]
+; CHECK-NEXT:    mov r2, r3
+; CHECK-NEXT:    adds r3, #1
+; CHECK-NEXT:    cmp r4, #0
 ; CHECK-NEXT:    bne .LBB3_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
-; CHECK-NEXT:    subs r0, r2, #1
-; CHECK-NEXT:    str r0, [r1]
-; CHECK-NEXT:    bx lr
+; CHECK-NEXT:    str r2, [r1]
+; CHECK-NEXT:    pop {r4, pc}
 entry:
   br label %loop
 
@@ -126,17 +127,18 @@ exit:
 define void @cbnz_exit_minsize(ptr %in, ptr %res) #0 {
 ; CHECK-LABEL: cbnz_exit_minsize:
 ; CHECK:       @ %bb.0: @ %entry
-; CHECK-NEXT:    movs r2, #0
+; CHECK-NEXT:    push {r4, lr}
+; CHECK-NEXT:    movs r3, #0
 ; CHECK-NEXT:  .LBB4_1: @ %loop
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    ldr.w r3, [r0, r2, lsl #2]
-; CHECK-NEXT:    adds r2, #1
-; CHECK-NEXT:    cmp r3, #0
+; CHECK-NEXT:    ldr.w r4, [r0, r3, lsl #2]
+; CHECK-NEXT:    mov r2, r3
+; CHECK-NEXT:    adds r3, #1
+; CHECK-NEXT:    cmp r4, #0
 ; CHECK-NEXT:    beq .LBB4_1
 ; CHECK-NEXT:  @ %bb.2: @ %exit
-; CHECK-NEXT:    subs r0, r2, #1
-; CHECK-NEXT:    str r0, [r1]
-; CHECK-NEXT:    bx lr
+; CHECK-NEXT:    str r2, [r1]
+; CHECK-NEXT:    pop {r4, pc}
 entry:
   br label %loop
 
diff --git a/llvm/test/CodeGen/X86/break-false-dep.ll b/llvm/test/CodeGen/X86/break-false-dep.ll
index 6943622fac7f2..6df19767b2bb4 100644
--- a/llvm/test/CodeGen/X86/break-false-dep.ll
+++ b/llvm/test/CodeGen/X86/break-false-dep.ll
@@ -1308,28 +1308,27 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; SSE-LINUX-NEXT:  .LBB13_1: # %inner_loop
 ; SSE-LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-LINUX-NEXT:    movq %rcx, %r8
-; SSE-LINUX-NEXT:    shrq $6, %r8
-; SSE-LINUX-NEXT:    movq (%rsi,%r8,8), %r8
-; SSE-LINUX-NEXT:    btq %rcx, %r8
-; SSE-LINUX-NEXT:    leaq 1(%rcx), %rcx
+; SSE-LINUX-NEXT:    shrq $6, %rcx
+; SSE-LINUX-NEXT:    movq (%rsi,%rcx,8), %r9
+; SSE-LINUX-NEXT:    leaq 1(%r8), %rcx
+; SSE-LINUX-NEXT:    btq %r8, %r9
 ; SSE-LINUX-NEXT:    jae .LBB13_1
 ; SSE-LINUX-NEXT:  # %bb.2: # %loop_end
 ; SSE-LINUX-NEXT:    # in Loop: Header=BB13_1 Depth=1
-; SSE-LINUX-NEXT:    leaq 1(%rax), %r8
+; SSE-LINUX-NEXT:    leaq 1(%rax), %r9
 ; SSE-LINUX-NEXT:    xorps %xmm4, %xmm4
-; SSE-LINUX-NEXT:    cvtsi2sd %r8, %xmm4
+; SSE-LINUX-NEXT:    cvtsi2sd %r9, %xmm4
 ; SSE-LINUX-NEXT:    movapd %xmm0, %xmm5
 ; SSE-LINUX-NEXT:    subsd %xmm4, %xmm5
 ; SSE-LINUX-NEXT:    mulsd %xmm1, %xmm5
-; SSE-LINUX-NEXT:    leaq -1(%rcx), %r9
 ; SSE-LINUX-NEXT:    xorps %xmm4, %xmm4
-; SSE-LINUX-NEXT:    cvtsi2sd %r9, %xmm4
+; SSE-LINUX-NEXT:    cvtsi2sd %r8, %xmm4
 ; SSE-LINUX-NEXT:    mulsd %xmm2, %xmm4
 ; SSE-LINUX-NEXT:    addsd %xmm5, %xmm4
 ; SSE-LINUX-NEXT:    divsd %xmm3, %xmm4
 ; SSE-LINUX-NEXT:    movsd %xmm4, -8(%rdi,%rax,8)
-; SSE-LINUX-NEXT:    movq %r8, %rax
-; SSE-LINUX-NEXT:    cmpq %r8, %rdx
+; SSE-LINUX-NEXT:    movq %r9, %rax
+; SSE-LINUX-NEXT:    cmpq %r9, %rdx
 ; SSE-LINUX-NEXT:    jge .LBB13_1
 ; SSE-LINUX-NEXT:  # %bb.3: # %loopdone
 ; SSE-LINUX-NEXT:    retq
@@ -1380,28 +1379,27 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; SSE-WIN-NEXT:  .LBB13_1: # %inner_loop
 ; SSE-WIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-WIN-NEXT:    movq %r9, %r10
-; SSE-WIN-NEXT:    shrq $6, %r10
-; SSE-WIN-NEXT:    movq (%rdx,%r10,8), %r10
-; SSE-WIN-NEXT:    btq %r9, %r10
-; SSE-WIN-NEXT:    leaq 1(%r9), %r9
+; SSE-WIN-NEXT:    shrq $6, %r9
+; SSE-WIN-NEXT:    movq (%rdx,%r9,8), %r11
+; SSE-WIN-NEXT:    leaq 1(%r10), %r9
+; SSE-WIN-NEXT:    btq %r10, %r11
 ; SSE-WIN-NEXT:    jae .LBB13_1
 ; SSE-WIN-NEXT:  # %bb.2: # %loop_end
 ; SSE-WIN-NEXT:    # in Loop: Header=BB13_1 Depth=1
-; SSE-WIN-NEXT:    leaq 1(%r8), %r10
+; SSE-WIN-NEXT:    leaq 1(%r8), %r11
 ; SSE-WIN-NEXT:    xorps %xmm4, %xmm4
-; SSE-WIN-NEXT:    cvtsi2sd %r10, %xmm4
+; SSE-WIN-NEXT:    cvtsi2sd %r11, %xmm4
 ; SSE-WIN-NEXT:    movapd %xmm2, %xmm5
 ; SSE-WIN-NEXT:    subsd %xmm4, %xmm5
 ; SSE-WIN-NEXT:    mulsd %xmm3, %xmm5
-; SSE-WIN-NEXT:    leaq -1(%r9), %r11
 ; SSE-WIN-NEXT:    xorps %xmm4, %xmm4
-; SSE-WIN-NEXT:    cvtsi2sd %r11, %xmm4
+; SSE-WIN-NEXT:    cvtsi2sd %r10, %xmm4
 ; SSE-WIN-NEXT:    mulsd %xmm1, %xmm4
 ; SSE-WIN-NEXT:    addsd %xmm5, %xmm4
 ; SSE-WIN-NEXT:    divsd %xmm0, %xmm4
 ; SSE-WIN-NEXT:    movsd %xmm4, -8(%rcx,%r8,8)
-; SSE-WIN-NEXT:    movq %r10, %r8
-; SSE-WIN-NEXT:    cmpq %r10, %rax
+; SSE-WIN-NEXT:    movq %r11, %r8
+; SSE-WIN-NEXT:    cmpq %r11, %rax
 ; SSE-WIN-NEXT:    jge .LBB13_1
 ; SSE-WIN-NEXT:  # %bb.3: # %loopdone
 ; SSE-WIN-NEXT:    movaps (%rsp), %xmm7 # 16-byte Reload
@@ -1465,25 +1463,24 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; AVX1-NEXT:  .LBB13_1: # %inner_loop
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    movq %r9, %r10
-; AVX1-NEXT:    shrq $6, %r10
-; AVX1-NEXT:    movq (%rdx,%r10,8), %r10
-; AVX1-NEXT:    btq %r9, %r10
-; AVX1-NEXT:    leaq 1(%r9), %r9
+; AVX1-NEXT:    shrq $6, %r9
+; AVX1-NEXT:    movq (%rdx,%r9,8), %r11
+; AVX1-NEXT:    leaq 1(%r10), %r9
+; AVX1-NEXT:    btq %r10, %r11
 ; AVX1-NEXT:    jae .LBB13_1
 ; AVX1-NEXT:  # %bb.2: # %loop_end
 ; AVX1-NEXT:    # in Loop: Header=BB13_1 Depth=1
-; AVX1-NEXT:    leaq 1(%r8), %r10
-; AVX1-NEXT:    vcvtsi2sd %r10, %xmm6, %xmm4
+; AVX1-NEXT:    leaq 1(%r8), %r11
+; AVX1-NEXT:    vcvtsi2sd %r11, %xmm6, %xmm4
 ; AVX1-NEXT:    vsubsd %xmm4, %xmm2, %xmm4
 ; AVX1-NEXT:    vmulsd %xmm3, %xmm4, %xmm4
-; AVX1-NEXT:    leaq -1(%r9), %r11
-; AVX1-NEXT:    vcvtsi2sd %r11, %xmm6, %xmm5
+; AVX1-NEXT:    vcvtsi2sd %r10, %xmm6, %xmm5
 ; AVX1-NEXT:    vmulsd %xmm1, %xmm5, %xmm5
 ; AVX1-NEXT:    vaddsd %xmm5, %xmm4, %xmm4
 ; AVX1-NEXT:    vdivsd %xmm0, %xmm4, %xmm4
 ; AVX1-NEXT:    vmovsd %xmm4, -8(%rcx,%r8,8)
-; AVX1-NEXT:    movq %r10, %r8
-; AVX1-NEXT:    cmpq %r10, %rax
+; AVX1-NEXT:    movq %r11, %r8
+; AVX1-NEXT:    cmpq %r11, %rax
 ; AVX1-NEXT:    jge .LBB13_1
 ; AVX1-NEXT:  # %bb.3: # %loopdone
 ; AVX1-NEXT:    vmovaps (%rsp), %xmm7 # 16-byte Reload
@@ -1547,25 +1544,24 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; AVX512VL-NEXT:  .LBB13_1: # %inner_loop
 ; AVX512VL-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VL-NEXT:    movq %r9, %r10
-; AVX512VL-NEXT:    shrq $6, %r10
-; AVX512VL-NEXT:    movq (%rdx,%r10,8), %r10
-; AVX512VL-NEXT:    btq %r9, %r10
-; AVX512VL-NEXT:    leaq 1(%r9), %r9
+; AVX512VL-NEXT:    shrq $6, %r9
+; AVX512VL-NEXT:    movq (%rdx,%r9,8), %r11
+; AVX512VL-NEXT:    leaq 1(%r10), %r9
+; AVX512VL-NEXT:    btq %r10, %r11
 ; AVX512VL-NEXT:    jae .LBB13_1
 ; AVX512VL-NEXT:  # %bb.2: # %loop_end
 ; AVX512VL-NEXT:    # in Loop: Header=BB13_1 Depth=1
-; AVX512VL-NEXT:    leaq 1(%r8), %r10
-; AVX512VL-NEXT:    vcvtsi2sd %r10, %xmm6, %xmm4
+; AVX512VL-NEXT:    leaq 1(%r8), %r11
+; AVX512VL-NEXT:    vcvtsi2sd %r11, %xmm6, %xmm4
 ; AVX512VL-NEXT:    vsubsd %xmm4, %xmm2, %xmm4
 ; AVX512VL-NEXT:    vmulsd %xmm3, %xmm4, %xmm4
-; AVX512VL-NEXT:    leaq -1(%r9), %r11
-; AVX512VL-NEXT:    vcvtsi2sd %r11, %xmm6, %xmm5
+; AVX512VL-NEXT:    vcvtsi2sd %r10, %xmm6, %xmm5
 ; AVX512VL-NEXT:    vmulsd %xmm1, %xmm5, %xmm5
 ; AVX512VL-NEXT:    vaddsd %xmm5, %xmm4, %xmm4
 ; AVX512VL-NEXT:    vdivsd %xmm0, %xmm4, %xmm4
 ; AVX512VL-NEXT:    vmovsd %xmm4, -8(%rcx,%r8,8)
-; AVX512VL-NEXT:    movq %r10, %r8
-; AVX512VL-NEXT:    cmpq %r10, %rax
+; AVX512VL-NEXT:    movq %r11, %r8
+; AVX512VL-NEXT:    cmpq %r11, %rax
 ; AVX512VL-NEXT:    jge .LBB13_1
 ; AVX512VL-NEXT:  # %bb.3: # %loopdone
 ; AVX512VL-NEXT:    vmovaps (%rsp), %xmm7 # 16-byte Reload
diff --git a/llvm/test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll b/llvm/test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll
index 097575ca86bcc..94d6b180c061a 100644
--- a/llvm/test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll
+++ b/llvm/test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll
@@ -13,9 +13,10 @@ define void @test1(ptr %s, i32 %n) {
 ; CHECK-NEXT:    b.ge .LBB0_2
 ; CHECK-NEXT:  .LBB0_1: // %while_body
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    str w9, [x8, #3140]
+; CHECK-NEXT:    mov w10, w9
 ; CHECK-NEXT:    add w9, w9, #1
 ; CHECK-NEXT:    str w9, [x8, #3136]
+; CHECK-NEXT:    str w10, [x8, #3140]
 ; CHECK-NEXT:    cmp w9, w1
 ; CHECK-NEXT:    b.lt .LBB0_1
 ; CHECK-NEXT:  .LBB0_2: // %while_end
@@ -52,9 +53,10 @@ define void @test2(ptr %struct, i32 %n) {
 ; CHECK-NEXT:    b.ge .LBB1_3
 ; CHECK-NEXT:  .LBB1_2: // %while_body
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    str w9, [x8, #3140]
+; CHECK-NEXT:    mov w10, w9
 ; CHECK-NEXT:    add w9, w9, #1
 ; CHECK-NEXT:    str w9, [x8, #3136]
+; CHECK-NEXT:    str w10, [x8, #3140]
 ; CHECK-NEXT:    cmp w9, w1
 ; CHECK-NEXT:    b.lt .LBB1_2
 ; CHECK-NEXT:  .LBB1_3: // %while_end
@@ -93,9 +95,10 @@ define void @test3(ptr %s1, ptr %s2, i1 %cond, i32 %n) {
 ; CHECK-NEXT:    b.ge .LBB2_3
 ; CHECK-NEXT:  .LBB2_2: // %while_body
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    str w9, [x8, #3140]
+; CHECK-NEXT:    mov w10, w9
 ; CHECK-NEXT:    add w9, w9, #1
 ; CHECK-NEXT:    str w9, [x8, #3136]
+; CHECK-NEXT:    str w10, [x8, #3140]
 ; CHECK-NEXT:    cmp w9, w3
 ; CHECK-NEXT:    b.lt .LBB2_2
 ; CHECK-NEXT:  .LBB2_3: // %while_end
@@ -146,10 +149,11 @@ define void @test4(i32 %n) uwtable personality ptr @__FrameHandler {
 ; CHECK-NEXT:    .cfi_offset w30, -32
 ; CHECK-NEXT:    .cfi_remember_state
 ; CHECK-NEXT:    mov w19, w0
-; CHECK-NEXT:    mov w20, wzr
+; CHECK-NEXT:    mov w9, wzr
 ; CHECK-NEXT:  .LBB3_1: // %while_cond
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:  .Ltmp0:
+; CHECK-NEXT:    mov w20, w9
 ; CHECK-NEXT:    bl foo
 ; CHECK-NEXT:  .Ltmp1:
 ; CHECK-NEXT:  // %bb.2: // %while_cond_x.split
@@ -160,9 +164,9 @@ define void @test4(i32 %n) uwtable personality ptr @__FrameHandler {
 ; CHECK-NEXT:    b.ge .LBB3_4
 ; CHECK-NEXT:  // %bb.3: // %while_body
 ; CHECK-NEXT:    // in Loop: Header=BB3_1 Depth=1
+; CHECK-NEXT:    add w9, w20, #1
 ; CHECK-NEXT:    str w20, [x8, #3140]
-; CHECK-NEXT:    add w20, w20, #1
-; CHECK-NEXT:    str w20, [x8, #3136]
+; CHECK-NEXT:    str w9, [x8, #3136]
 ; CHECK-NEXT:    b .LBB3_1
 ; CHECK-NEXT:  .LBB3_4: // %while_end
 ; CHECK-NEXT:    ldp x20, x19, [sp, #16] // 16-byte Folded Reload
@@ -221,9 +225,10 @@ define void @test5(ptr %s, i32 %n) {
 ; CHECK-NEXT:    b.ge .LBB4_2
 ; CHECK-NEXT:  .LBB4_1: // %while_body
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    str w9, [x8, #2180]
+; CHECK-NEXT:    mov w10, w9
 ; CHECK-NEXT:    add w9, w9, #1
 ; CHECK-NEXT:    str w9, [x8, #2176]
+; CHECK-NEXT:    str w10, [x8, #2180]
 ; CHECK-NEXT:    cmp w9, w1
 ; CHECK-NEXT:    b.lt .LBB4_1
 ; CHECK-NEXT:  .LBB4_2: // %while_end
diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll
index 7ae78ae6a1fd4..6a70fe48de7e2 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll
@@ -20,17 +20,16 @@ define i64 @sqlite3DropTriggerPtr() nounwind {
 ; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    movq %rbx, %rcx
 ; CHECK-NEXT:    testb %al, %al
-; CHECK-NEXT:    je .LBB0_4
+; CHECK-NEXT:    je .LBB0_3
 ; CHECK-NEXT:  # %bb.2: # %bb4
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
-; CHECK-NEXT:    incq %rbx
+; CHECK-NEXT:    leaq 1(%rcx), %rbx
 ; CHECK-NEXT:    testb %al, %al
 ; CHECK-NEXT:    jne .LBB0_1
-; CHECK-NEXT:  # %bb.3: # %bb8split
-; CHECK-NEXT:    decq %rbx
-; CHECK-NEXT:  .LBB0_4: # %bb8
-; CHECK-NEXT:    movq %rbx, %rax
+; CHECK-NEXT:  .LBB0_3: # %bb8
+; CHECK-NEXT:    movq %rcx, %rax
 ; CHECK-NEXT:    popq %rbx
 ; CHECK-NEXT:    retq
 bb:
diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/pr46943.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/pr46943.ll
index 89523b4487d49..b59ca63abfa41 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/X86/pr46943.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/X86/pr46943.ll
@@ -19,8 +19,7 @@ define i8 @drop_nuw() {
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8 [[IV_NEXT]], 0
 ; CHECK-NEXT:    br i1 [[CMP]], label [[EXIT:%.*]], label [[LOOP]]
 ; CHECK:       exit:
-; CHECK-NEXT:    [[TMP0:%.*]] = add i8 [[IV_NEXT]], -1
-; CHECK-NEXT:    ret i8 [[TMP0]]
+; CHECK-NEXT:    ret i8 [[IV]]
 ;
 entry:
   br label %loop
@@ -49,8 +48,7 @@ define i8 @drop_nsw() {
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8 [[IV_NEXT]], 127
 ; CHECK-NEXT:    br i1 [[CMP]], label [[EXIT:%.*]], label [[LOOP]]
 ; CHECK:       exit:
-; CHECK-NEXT:    [[TMP0:%.*]] = add i8 [[IV_NEXT]], 1
-; CHECK-NEXT:    ret i8 [[TMP0]]
+; CHECK-NEXT:    ret i8 [[IV]]
 ;
 entry:
   br label %loop
@@ -79,8 +77,7 @@ define i8 @already_postinc() {
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8 [[IV_NEXT]], -1
 ; CHECK-NEXT:    br i1 [[CMP]], label [[EXIT:%.*]], label [[LOOP]]
 ; CHECK:       exit:
-; CHECK-NEXT:    [[TMP0:%.*]] = add i8 [[IV_NEXT]], -1
-; CHECK-NEXT:    ret i8 [[TMP0]]
+; CHECK-NEXT:    ret i8 [[IV]]
 ;
 entry:
   br label %loop
diff --git a/llvm/test/Transforms/LoopStrengthReduce/depth-limit-overrun.ll b/llvm/test/Transforms/LoopStrengthReduce/depth-limit-overrun.ll
index 9c3698a740992..a46d75ae537ab 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/depth-limit-overrun.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/depth-limit-overrun.ll
@@ -22,10 +22,9 @@ define void @test(i32 %A, i32 %B, i32 %C) {
 ; DEFAULT:       preheader:
 ; DEFAULT-NEXT:    [[I15:%.*]] = shl i32 [[B]], 1
 ; DEFAULT-NEXT:    [[TMP1:%.*]] = mul i32 [[PHI2]], -1
-; DEFAULT-NEXT:    [[TMP2:%.*]] = mul i32 [[TMP1]], -1
-; DEFAULT-NEXT:    [[TMP3:%.*]] = sub i32 [[PHI4]], [[TMP2]]
+; DEFAULT-NEXT:    [[TMP3:%.*]] = sub i32 [[PHI4]], [[PHI2]]
 ; DEFAULT-NEXT:    [[TMP4:%.*]] = add i32 [[B]], [[PHI4]]
-; DEFAULT-NEXT:    [[TMP5:%.*]] = sub i32 [[TMP4]], [[TMP2]]
+; DEFAULT-NEXT:    [[TMP5:%.*]] = sub i32 [[TMP4]], [[PHI2]]
 ; DEFAULT-NEXT:    [[TMP6:%.*]] = sub i32 14, [[TMP5]]
 ; DEFAULT-NEXT:    [[TMP7:%.*]] = add i32 [[TMP0]], [[PHI2]]
 ; DEFAULT-NEXT:    br label [[INNER_LOOP:%.*]]
@@ -87,10 +86,9 @@ define void @test(i32 %A, i32 %B, i32 %C) {
 ; LIMIT:       preheader:
 ; LIMIT-NEXT:    [[I15:%.*]] = shl i32 [[B]], 1
 ; LIMIT-NEXT:    [[TMP1:%.*]] = mul i32 [[PHI2]], -1
-; LIMIT-NEXT:    [[TMP2:%.*]] = mul i32 [[TMP1]], -1
-; LIMIT-NEXT:    [[TMP3:%.*]] = sub i32 [[PHI4]], [[TMP2]]
+; LIMIT-NEXT:    [[TMP3:%.*]] = sub i32 [[PHI4]], [[PHI2]]
 ; LIMIT-NEXT:    [[TMP4:%.*]] = add i32 [[B]], [[PHI4]]
-; LIMIT-NEXT:    [[TMP5:%.*]] = sub i32 [[TMP4]], [[TMP2]]
+; LIMIT-NEXT:    [[TMP5:%.*]] = sub i32 [[TMP4]], [[PHI2]]
 ; LIMIT-NEXT:    [[TMP6:%.*]] = sub i32 14, [[TMP5]]
 ; LIMIT-NEXT:    [[TMP7:%.*]] = add i32 [[TMP0]], [[PHI2]]
 ; LIMIT-NEXT:    br label [[INNER_LOOP:%.*]]
diff --git a/llvm/test/Transforms/LoopStrengthReduce/lsr-rewrite-to-add-one.ll b/llvm/test/Transforms/LoopStrengthReduce/lsr-rewrite-to-add-one.ll
index 74d861cf5168c..d66905ae26f14 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/lsr-rewrite-to-add-one.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/lsr-rewrite-to-add-one.ll
@@ -20,8 +20,7 @@ define i32 @test(i1 %c.1, ptr %src) {
 ; CHECK-NEXT:    [[OR:%.*]] = or i1 [[P]], [[T]]
 ; CHECK-NEXT:    [[ZEXT_OR:%.*]] = zext i1 [[OR]] to i32
 ; CHECK-NEXT:    [[LSR_IV_NEXT]] = add nuw i32 [[LSR_IV]], 1
-; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[LSR_IV_NEXT]], -1
-; CHECK-NEXT:    [[LOOP_HEADER_TERMCOND:%.*]] = icmp sgt i32 [[TMP0]], -1050
+; CHECK-NEXT:    [[LOOP_HEADER_TERMCOND:%.*]] = icmp sgt i32 [[LSR_IV]], -1050
 ; CHECK-NEXT:    br i1 [[LOOP_HEADER_TERMCOND]], label [[LOOP_HEADER]], label [[EXIT:%.*]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    [[ZEXT_OR_LCSSA:%.*]] = phi i32 [ [[ZEXT_OR]], [[LOOP_LATCH]] ]
diff --git a/llvm/test/Transforms/LoopStrengthReduce/wrong-hoisting-iv.ll b/llvm/test/Transforms/LoopStrengthReduce/wrong-hoisting-iv.ll
index 502042eaf9b9c..007d84f9120e3 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/wrong-hoisting-iv.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/wrong-hoisting-iv.ll
@@ -16,9 +16,7 @@ define void @test1() {
 ; CHECK-NEXT:    [[VAL4:%.*]] = sub i32 [[VAL]], [[VAL3]]
 ; CHECK-NEXT:    [[VAL5:%.*]] = ashr i32 undef, undef
 ; CHECK-NEXT:    [[VAL6:%.*]] = sub i32 [[VAL4]], [[VAL5]]
-; CHECK-NEXT:    [[TMP0:%.*]] = mul i32 [[VAL]], 7
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i32 [[VAL3]], 7
-; CHECK-NEXT:    [[TMP2:%.*]] = sub i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP2:%.*]] = mul i32 [[VAL]], 7
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i32 [[VAL5]], 7
 ; CHECK-NEXT:    [[TMP4:%.*]] = sub i32 [[TMP2]], [[TMP3]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = shl i32 [[VAL6]], 3
@@ -58,10 +56,8 @@ define void @test1() {
 ; CHECK:       bb20.bb15splitsplitsplit_crit_edge:
 ; CHECK-NEXT:    [[TMP14:%.*]] = mul i32 [[VAL]], 3
 ; CHECK-NEXT:    [[TMP15:%.*]] = mul i32 [[VAL1]], [[VAL2]]
-; CHECK-NEXT:    [[TMP16:%.*]] = mul i32 [[TMP15]], 3
-; CHECK-NEXT:    [[TMP17:%.*]] = sub i32 [[TMP14]...
[truncated]

nikic · 2025-07-01T10:24:33Z

llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp

+    if (Flags & SCEV::FlagNUW)
+      BOI->setHasNoUnsignedWrap();
+    if (Flags & SCEV::FlagNSW)
+      BOI->setHasNoSignedWrap();


You can't set flags after the fact with InstSimplifyFolder. You need to add a new IRBuilder method like CreateNoWrapBinOp that accepts the flags as arguments.

nikic · 2025-07-01T10:28:23Z

llvm/test/Transforms/LoopStrengthReduce/X86/pr46943.ll

@@ -19,8 +19,7 @@ define i8 @drop_nuw() {
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8 [[IV_NEXT]], 0
 ; CHECK-NEXT:    br i1 [[CMP]], label [[EXIT:%.*]], label [[LOOP]]
 ; CHECK:       exit:
-; CHECK-NEXT:    [[TMP0:%.*]] = add i8 [[IV_NEXT]], -1
-; CHECK-NEXT:    ret i8 [[TMP0]]
+; CHECK-NEXT:    ret i8 [[IV]]


Without looking into it too deeply, changes like this might be problematic for LSR? Now the live-out is going to be the pre-inc IV rather than the post-inc one. (LSR should probably be wrapping things into Unknown in cases where it cares.)

[ScalarEvolutionExpander] Use IRBuilder::CreateBinOp in SCEVExpander:…

a17d514

…:InsertBinop. Removes the shift pair from add1_3 in llvm#146241.

topperc requested review from nikic, fhahn and preames July 1, 2025 00:50

llvmbot added backend:AArch64 backend:X86 llvm:transforms labels Jul 1, 2025

nikic reviewed Jul 1, 2025

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[ScalarEvolutionExpander] Use IRBuilder::CreateBinOp in SCEVExpander::InsertBinop. #146443

[ScalarEvolutionExpander] Use IRBuilder::CreateBinOp in SCEVExpander::InsertBinop. #146443

topperc commented Jul 1, 2025

Uh oh!

llvmbot commented Jul 1, 2025 •

edited

Loading

Uh oh!

llvmbot commented Jul 1, 2025

Uh oh!

nikic Jul 1, 2025

Uh oh!

nikic Jul 1, 2025

Uh oh!

Uh oh!

[ScalarEvolutionExpander] Use IRBuilder::CreateBinOp in SCEVExpander::InsertBinop. #146443

Are you sure you want to change the base?

[ScalarEvolutionExpander] Use IRBuilder::CreateBinOp in SCEVExpander::InsertBinop. #146443

Conversation

topperc commented Jul 1, 2025

Uh oh!

llvmbot commented Jul 1, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

llvmbot commented Jul 1, 2025

Uh oh!

nikic Jul 1, 2025

Choose a reason for hiding this comment

Uh oh!

nikic Jul 1, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

llvmbot commented Jul 1, 2025 •

edited

Loading