Index: llvm/lib/Target/X86/X86InstrInfo.cpp
===================================================================
--- llvm/lib/Target/X86/X86InstrInfo.cpp
+++ llvm/lib/Target/X86/X86InstrInfo.cpp
@@ -3648,8 +3648,15 @@
 
 std::optional<DestSourcePair>
 X86InstrInfo::isCopyInstrImpl(const MachineInstr &MI) const {
-  if (MI.isMoveReg())
+  if (MI.isMoveReg()) {
+    // FIXME: Dirty hack for apparent invariant that doesn't hold when
+    // subreg_to_reg is coalesced with ordinary copies, such that the bits that
+    // were asserted as 0 are now undef.
+    if (MI.getOperand(0).isUndef() && MI.getOperand(0).getSubReg())
+      return std::nullopt;
+
     return DestSourcePair{MI.getOperand(0), MI.getOperand(1)};
+  }
   return std::nullopt;
 }
 
Index: llvm/test/CodeGen/X86/GlobalISel/add-ext.ll
===================================================================
--- llvm/test/CodeGen/X86/GlobalISel/add-ext.ll
+++ llvm/test/CodeGen/X86/GlobalISel/add-ext.ll
@@ -205,8 +205,8 @@
 ; CHECK-NEXT:    addq %rdi, %rcx
 ; CHECK-NEXT:    movl (%rcx), %ecx
 ; CHECK-NEXT:    addl (%rax), %ecx
-; CHECK-NEXT:    movl %esi, %esi
-; CHECK-NEXT:    imulq $4, %rsi, %rax
+; CHECK-NEXT:    movl %esi, %eax
+; CHECK-NEXT:    imulq $4, %rax, %rax
 ; CHECK-NEXT:    addq %rdi, %rax
 ; CHECK-NEXT:    movl %ecx, (%rax)
 ; CHECK-NEXT:    retq
Index: llvm/test/CodeGen/X86/coalescer-breaks-subreg-to-reg-liveness.ll
===================================================================
--- llvm/test/CodeGen/X86/coalescer-breaks-subreg-to-reg-liveness.ll
+++ llvm/test/CodeGen/X86/coalescer-breaks-subreg-to-reg-liveness.ll
@@ -37,12 +37,12 @@
 ; CHECK-NEXT:    movl %r8d, %r14d
 ; CHECK-NEXT:    movq %rcx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; CHECK-NEXT:    movq %rdx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
-; CHECK-NEXT:    movq %rsi, %r12
+; CHECK-NEXT:    movq %rsi, %r13
 ; CHECK-NEXT:    movq %rdi, %r15
 ; CHECK-NEXT:    incl %r14d
 ; CHECK-NEXT:    xorl %ebx, %ebx
-; CHECK-NEXT:    # implicit-def: $rax
-; CHECK-NEXT:    # kill: killed $rax
+; CHECK-NEXT:    # implicit-def: $r12
+; CHECK-NEXT:    movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; CHECK-NEXT:    jmp .LBB0_3
 ; CHECK-NEXT:    .p2align 4, 0x90
 ; CHECK-NEXT:  .LBB0_1: # %bb17
@@ -55,39 +55,42 @@
 ; CHECK-NEXT:    callq _Znwm@PLT
 ; CHECK-NEXT:    shlq $4, %r15
 ; CHECK-NEXT:    addq {{[-0-9]+}}(%r{{[sb]}}p), %r15 # 8-byte Folded Reload
-; CHECK-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload
-; CHECK-NEXT:    movq %rdx, %rcx
+; CHECK-NEXT:    movq %r12, %rcx
 ; CHECK-NEXT:    shrq $32, %rcx
 ; CHECK-NEXT:    movb %cl, 12(%rax)
-; CHECK-NEXT:    movl %edx, 8(%rax)
+; CHECK-NEXT:    movl %r12d, 8(%rax)
 ; CHECK-NEXT:    movq %r15, %rbx
 ; CHECK-NEXT:    movq %r13, %r15
+; CHECK-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %r13 # 8-byte Reload
 ; CHECK-NEXT:    decl %r14d
-; CHECK-NEXT:    je .LBB0_7
+; CHECK-NEXT:    je .LBB0_8
 ; CHECK-NEXT:  .LBB0_3: # %bb7
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    callq widget@PLT
-; CHECK-NEXT:    cmpb $-5, (%r12)
-; CHECK-NEXT:    jb .LBB0_5
-; CHECK-NEXT:  # %bb.4: # %bb12
+; CHECK-NEXT:    cmpb $-5, (%r13)
+; CHECK-NEXT:    jae .LBB0_5
+; CHECK-NEXT:  # %bb.4: # in Loop: Header=BB0_3 Depth=1
+; CHECK-NEXT:    movl %r12d, %r12d
+; CHECK-NEXT:    cmpq %r15, %rbx
+; CHECK-NEXT:    jbe .LBB0_1
+; CHECK-NEXT:    jmp .LBB0_7
+; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:  .LBB0_5: # %bb12
 ; CHECK-NEXT:    # in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    movq 0, %rax
 ; CHECK-NEXT:    movq 8, %rax
-; CHECK-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
-; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
-; CHECK-NEXT:  .LBB0_5: # %bb14
-; CHECK-NEXT:    # in Loop: Header=BB0_3 Depth=1
+; CHECK-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %r12 # 8-byte Reload
 ; CHECK-NEXT:    cmpq %r15, %rbx
 ; CHECK-NEXT:    jbe .LBB0_1
-; CHECK-NEXT:  # %bb.6: # in Loop: Header=BB0_3 Depth=1
+; CHECK-NEXT:  .LBB0_7: # in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    xorl %ebx, %ebx
 ; CHECK-NEXT:    decl %r14d
 ; CHECK-NEXT:    jne .LBB0_3
-; CHECK-NEXT:  .LBB0_7: # %bb21
+; CHECK-NEXT:  .LBB0_8: # %bb21
 ; CHECK-NEXT:    cmpb $0, 12(%rax)
-; CHECK-NEXT:    jne .LBB0_9
-; CHECK-NEXT:  # %bb.8: # %bb26
+; CHECK-NEXT:    jne .LBB0_10
+; CHECK-NEXT:  # %bb.9: # %bb26
 ; CHECK-NEXT:    addq $24, %rsp
 ; CHECK-NEXT:    popq %rbx
 ; CHECK-NEXT:    popq %r12
@@ -97,7 +100,7 @@
 ; CHECK-NEXT:    popq %rbp
 ; CHECK-NEXT:    .cfi_def_cfa %rsp, 8
 ; CHECK-NEXT:    retq
-; CHECK-NEXT:  .LBB0_9: # %bb25
+; CHECK-NEXT:  .LBB0_10: # %bb25
 ; CHECK-NEXT:    .cfi_def_cfa %rbp, 16
 ; CHECK-NEXT:    movq %r15, %rdi
 ; CHECK-NEXT:    callq pluto@PLT
Index: llvm/test/CodeGen/X86/dagcombine-cse.ll
===================================================================
--- llvm/test/CodeGen/X86/dagcombine-cse.ll
+++ llvm/test/CodeGen/X86/dagcombine-cse.ll
@@ -106,24 +106,24 @@
 ;
 ; X64-LABEL: square_high:
 ; X64:       ## %bb.0: ## %entry
-; X64-NEXT:    movl %esi, %esi
-; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    movl %esi, %ecx
+; X64-NEXT:    movq %rcx, %rax
 ; X64-NEXT:    mulq %rdi
-; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    movq %rdx, %rsi
 ; X64-NEXT:    movq %rax, %r8
 ; X64-NEXT:    movq %rdi, %rax
 ; X64-NEXT:    mulq %rdi
 ; X64-NEXT:    addq %r8, %rdx
-; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq %rsi, %rax
 ; X64-NEXT:    adcq $0, %rax
 ; X64-NEXT:    addq %rdx, %r8
-; X64-NEXT:    adcq %rcx, %rax
-; X64-NEXT:    imulq %rsi, %rsi
-; X64-NEXT:    addq %rax, %rsi
-; X64-NEXT:    shrdq $32, %rsi, %r8
-; X64-NEXT:    shrq $32, %rsi
+; X64-NEXT:    adcq %rsi, %rax
+; X64-NEXT:    imulq %rcx, %rcx
+; X64-NEXT:    addq %rax, %rcx
+; X64-NEXT:    shrdq $32, %rcx, %r8
+; X64-NEXT:    shrq $32, %rcx
 ; X64-NEXT:    movq %r8, %rax
-; X64-NEXT:    movq %rsi, %rdx
+; X64-NEXT:    movq %rcx, %rdx
 ; X64-NEXT:    retq
 entry:
   %conv = zext i96 %x to i192
Index: llvm/test/CodeGen/X86/fold-and-shift-x86_64.ll
===================================================================
--- llvm/test/CodeGen/X86/fold-and-shift-x86_64.ll
+++ llvm/test/CodeGen/X86/fold-and-shift-x86_64.ll
@@ -34,8 +34,8 @@
 define i8 @t3(ptr %X, i64 %i) {
 ; CHECK-LABEL: t3:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    movl %esi, %esi
-; CHECK-NEXT:    movzbl (%rdi,%rsi,4), %eax
+; CHECK-NEXT:    movl %esi, %eax
+; CHECK-NEXT:    movzbl (%rdi,%rax,4), %eax
 ; CHECK-NEXT:    retq
 
 entry:
Index: llvm/test/CodeGen/X86/unfold-masked-merge-scalar-constmask-lowhigh.ll
===================================================================
--- llvm/test/CodeGen/X86/unfold-masked-merge-scalar-constmask-lowhigh.ll
+++ llvm/test/CodeGen/X86/unfold-masked-merge-scalar-constmask-lowhigh.ll
@@ -78,18 +78,18 @@
 define i64 @out64_constmask(i64 %x, i64 %y) {
 ; CHECK-NOBMI-LABEL: out64_constmask:
 ; CHECK-NOBMI:       # %bb.0:
-; CHECK-NOBMI-NEXT:    movl %edi, %edi
+; CHECK-NOBMI-NEXT:    movl %edi, %ecx
 ; CHECK-NOBMI-NEXT:    movabsq $-4294967296, %rax # imm = 0xFFFFFFFF00000000
 ; CHECK-NOBMI-NEXT:    andq %rsi, %rax
-; CHECK-NOBMI-NEXT:    orq %rdi, %rax
+; CHECK-NOBMI-NEXT:    orq %rcx, %rax
 ; CHECK-NOBMI-NEXT:    retq
 ;
 ; CHECK-BMI-LABEL: out64_constmask:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    movl %edi, %edi
+; CHECK-BMI-NEXT:    movl %edi, %ecx
 ; CHECK-BMI-NEXT:    movabsq $-4294967296, %rax # imm = 0xFFFFFFFF00000000
 ; CHECK-BMI-NEXT:    andq %rsi, %rax
-; CHECK-BMI-NEXT:    orq %rdi, %rax
+; CHECK-BMI-NEXT:    orq %rcx, %rax
 ; CHECK-BMI-NEXT:    retq
   %mx = and i64 %x, 4294967295
   %my = and i64 %y, -4294967296