6 files changed, 173 insertions, 148 deletions
diff --git a/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll b/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll
index 6ef7219..9cf7aab 100644
--- a/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll
@@ -56,14 +56,9 @@ define void @PR90954(ptr %0, ptr %1, i32 %2) nounwind {
 ; CHECK-LABEL: PR90954:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    pushq %rbp
-; CHECK-NEXT:    movq %rsp, %rbp
-; CHECK-NEXT:    pushq %r15
 ; CHECK-NEXT:    pushq %r14
-; CHECK-NEXT:    pushq %r13
-; CHECK-NEXT:    pushq %r12
 ; CHECK-NEXT:    pushq %rbx
-; CHECK-NEXT:    andq $-1024, %rsp # imm = 0xFC00
-; CHECK-NEXT:    subq $5120, %rsp # imm = 0x1400
+; CHECK-NEXT:    subq $2912, %rsp # imm = 0xB60
 ; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
 ; CHECK-NEXT:    vmovups %zmm0, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movb $1, {{[0-9]+}}(%rsp)
@@ -79,29 +74,26 @@ define void @PR90954(ptr %0, ptr %1, i32 %2) nounwind {
 ; CHECK-NEXT:    movw $64, %cx
 ; CHECK-NEXT:    movw $16, %di
 ; CHECK-NEXT:    movb $1, %r8b
-; CHECK-NEXT:    movl $64, %r9d
-; CHECK-NEXT:    leaq {{[0-9]+}}(%rsp), %r10
-; CHECK-NEXT:    leaq {{[0-9]+}}(%rsp), %r11
-; CHECK-NEXT:    xorl %ebx, %ebx
-; CHECK-NEXT:    xorl %r14d, %r14d
+; CHECK-NEXT:    xorl %r9d, %r9d
+; CHECK-NEXT:    xorl %r10d, %r10d
 ; CHECK-NEXT:    jmp .LBB1_1
 ; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_5: # in Loop: Header=BB1_1 Depth=1
-; CHECK-NEXT:    incq %r14
-; CHECK-NEXT:    addl %edx, %ebx
+; CHECK-NEXT:    incq %r10
+; CHECK-NEXT:    addl %edx, %r9d
 ; CHECK-NEXT:  .LBB1_1: # =>This Loop Header: Depth=1
 ; CHECK-NEXT:    # Child Loop BB1_2 Depth 2
-; CHECK-NEXT:    movslq %ebx, %r15
-; CHECK-NEXT:    leaq (%rsi,%r15,4), %r15
-; CHECK-NEXT:    xorl %r12d, %r12d
-; CHECK-NEXT:    xorl %r13d, %r13d
+; CHECK-NEXT:    movslq %r9d, %r11
+; CHECK-NEXT:    leaq (%rsi,%r11,4), %r11
+; CHECK-NEXT:    xorl %ebx, %ebx
+; CHECK-NEXT:    xorl %r14d, %r14d
 ; CHECK-NEXT:    jmp .LBB1_2
 ; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_4: # in Loop: Header=BB1_2 Depth=2
-; CHECK-NEXT:    tilestored %tmm1, (%r15,%rax)
-; CHECK-NEXT:    incq %r13
-; CHECK-NEXT:    addq $64, %r15
-; CHECK-NEXT:    decq %r12
+; CHECK-NEXT:    tilestored %tmm1, (%r11,%rax)
+; CHECK-NEXT:    incq %r14
+; CHECK-NEXT:    addq $64, %r11
+; CHECK-NEXT:    decq %rbx
 ; CHECK-NEXT:    je .LBB1_5
 ; CHECK-NEXT:  .LBB1_2: # Parent Loop BB1_1 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -110,46 +102,12 @@ define void @PR90954(ptr %0, ptr %1, i32 %2) nounwind {
 ; CHECK-NEXT:    testb %r8b, %r8b
 ; CHECK-NEXT:    jne .LBB1_4
 ; CHECK-NEXT:  # %bb.3: # in Loop: Header=BB1_2 Depth=2
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    tileloadd (%r10,%r9), %tmm1
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    vmovaps %zmm0, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    tileloadd (%r11,%r9), %tmm2
+; CHECK-NEXT:    tilezero %tmm1
+; CHECK-NEXT:    tilezero %tmm2
 ; CHECK-NEXT:    tdpbf16ps %tmm2, %tmm1, %tmm0
-; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
-; CHECK-NEXT:    movabsq $64, %rax
-; CHECK-NEXT:    tilestored %tmm0, 3072(%rsp,%rax) # 1024-byte Folded Spill
-; CHECK-NEXT:    tileloadd 3072(%rsp,%rax), %tmm1 # 1024-byte Folded Reload
-; CHECK-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
+; CHECK-NEXT:    movabsq $64, %rbp
+; CHECK-NEXT:    tilestored %tmm0, 896(%rsp,%rbp) # 1024-byte Folded Spill
+; CHECK-NEXT:    tileloadd 896(%rsp,%rbp), %tmm1 # 1024-byte Folded Reload
 ; CHECK-NEXT:    jmp .LBB1_4
   %4 = shl i32 %2, 4
   %5 = icmp eq i64 0, 0
diff --git a/llvm/test/CodeGen/X86/fshl.ll b/llvm/test/CodeGen/X86/fshl.ll
index ec1b8a3..f998128 100644
--- a/llvm/test/CodeGen/X86/fshl.ll
+++ b/llvm/test/CodeGen/X86/fshl.ll
@@ -335,84 +335,83 @@ define i128 @var_shift_i128(i128 %x, i128 %y, i128 %z) nounwind {
 ; X86-SLOW-NEXT:    pushl %esi
 ; X86-SLOW-NEXT:    andl $-16, %esp
 ; X86-SLOW-NEXT:    subl $32, %esp
-; X86-SLOW-NEXT:    movl 24(%ebp), %esi
+; X86-SLOW-NEXT:    movl 24(%ebp), %edi
 ; X86-SLOW-NEXT:    movl 28(%ebp), %eax
 ; X86-SLOW-NEXT:    movl 48(%ebp), %edx
 ; X86-SLOW-NEXT:    movl 56(%ebp), %ecx
 ; X86-SLOW-NEXT:    testb $64, %cl
-; X86-SLOW-NEXT:    movl 52(%ebp), %edi
+; X86-SLOW-NEXT:    movl 52(%ebp), %ebx
 ; X86-SLOW-NEXT:    jne .LBB6_1
 ; X86-SLOW-NEXT:  # %bb.2:
 ; X86-SLOW-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X86-SLOW-NEXT:    movl %esi, %edx
-; X86-SLOW-NEXT:    movl 32(%ebp), %esi
-; X86-SLOW-NEXT:    movl %edi, %ecx
-; X86-SLOW-NEXT:    movl %eax, %edi
+; X86-SLOW-NEXT:    movl %edi, %edx
+; X86-SLOW-NEXT:    movl 32(%ebp), %edi
+; X86-SLOW-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-SLOW-NEXT:    movl %eax, %ebx
 ; X86-SLOW-NEXT:    movl 36(%ebp), %eax
 ; X86-SLOW-NEXT:    jmp .LBB6_3
 ; X86-SLOW-NEXT:  .LBB6_1:
 ; X86-SLOW-NEXT:    movl 40(%ebp), %ecx
 ; X86-SLOW-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X86-SLOW-NEXT:    movl 44(%ebp), %ecx
+; X86-SLOW-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X86-SLOW-NEXT:  .LBB6_3:
-; X86-SLOW-NEXT:    movl 56(%ebp), %ebx
-; X86-SLOW-NEXT:    testb $32, %bl
+; X86-SLOW-NEXT:    movl 56(%ebp), %ecx
+; X86-SLOW-NEXT:    testb $32, %cl
 ; X86-SLOW-NEXT:    jne .LBB6_4
 ; X86-SLOW-NEXT:  # %bb.5:
-; X86-SLOW-NEXT:    movl %ecx, %ebx
 ; X86-SLOW-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X86-SLOW-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-SLOW-NEXT:    movl %edx, %edi
+; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X86-SLOW-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X86-SLOW-NEXT:    jmp .LBB6_6
 ; X86-SLOW-NEXT:  .LBB6_4:
-; X86-SLOW-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X86-SLOW-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X86-SLOW-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X86-SLOW-NEXT:    movl %ecx, %edx
-; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-SLOW-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-SLOW-NEXT:    movl %edx, %ebx
+; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X86-SLOW-NEXT:  .LBB6_6:
-; X86-SLOW-NEXT:    movl %edx, %esi
+; X86-SLOW-NEXT:    movl %edi, %eax
+; X86-SLOW-NEXT:    shll %cl, %eax
+; X86-SLOW-NEXT:    shrl %esi
+; X86-SLOW-NEXT:    movl %ecx, %edx
+; X86-SLOW-NEXT:    notb %dl
+; X86-SLOW-NEXT:    movl %edx, %ecx
+; X86-SLOW-NEXT:    shrl %cl, %esi
+; X86-SLOW-NEXT:    orl %eax, %esi
+; X86-SLOW-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-SLOW-NEXT:    movl %ebx, %eax
 ; X86-SLOW-NEXT:    movl 56(%ebp), %ecx
-; X86-SLOW-NEXT:    shll %cl, %esi
-; X86-SLOW-NEXT:    movl %ebx, %edi
+; X86-SLOW-NEXT:    # kill: def $cl killed $cl killed $ecx
+; X86-SLOW-NEXT:    shll %cl, %eax
 ; X86-SLOW-NEXT:    shrl %edi
-; X86-SLOW-NEXT:    movl %ecx, %ebx
-; X86-SLOW-NEXT:    notb %bl
-; X86-SLOW-NEXT:    movl %ebx, %ecx
-; X86-SLOW-NEXT:    movb %bl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
+; X86-SLOW-NEXT:    movl %edx, %ecx
 ; X86-SLOW-NEXT:    shrl %cl, %edi
-; X86-SLOW-NEXT:    orl %esi, %edi
+; X86-SLOW-NEXT:    orl %eax, %edi
 ; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X86-SLOW-NEXT:    movl %esi, %eax
 ; X86-SLOW-NEXT:    movl 56(%ebp), %ecx
 ; X86-SLOW-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X86-SLOW-NEXT:    shll %cl, %eax
-; X86-SLOW-NEXT:    shrl %edx
-; X86-SLOW-NEXT:    movl %ebx, %ecx
-; X86-SLOW-NEXT:    shrl %cl, %edx
-; X86-SLOW-NEXT:    orl %eax, %edx
-; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X86-SLOW-NEXT:    movl %ebx, %eax
+; X86-SLOW-NEXT:    shrl %ebx
+; X86-SLOW-NEXT:    movl %edx, %ecx
+; X86-SLOW-NEXT:    shrl %cl, %ebx
+; X86-SLOW-NEXT:    orl %eax, %ebx
 ; X86-SLOW-NEXT:    movl 56(%ebp), %ecx
 ; X86-SLOW-NEXT:    # kill: def $cl killed $cl killed $ecx
+; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X86-SLOW-NEXT:    shll %cl, %eax
 ; X86-SLOW-NEXT:    shrl %esi
-; X86-SLOW-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
+; X86-SLOW-NEXT:    movl %edx, %ecx
 ; X86-SLOW-NEXT:    shrl %cl, %esi
 ; X86-SLOW-NEXT:    orl %eax, %esi
-; X86-SLOW-NEXT:    movl 56(%ebp), %ecx
-; X86-SLOW-NEXT:    # kill: def $cl killed $cl killed $ecx
-; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X86-SLOW-NEXT:    shll %cl, %eax
-; X86-SLOW-NEXT:    shrl %ebx
-; X86-SLOW-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X86-SLOW-NEXT:    shrl %cl, %ebx
-; X86-SLOW-NEXT:    orl %eax, %ebx
 ; X86-SLOW-NEXT:    movl 8(%ebp), %eax
-; X86-SLOW-NEXT:    movl %ebx, 12(%eax)
-; X86-SLOW-NEXT:    movl %esi, 8(%eax)
-; X86-SLOW-NEXT:    movl %edx, 4(%eax)
-; X86-SLOW-NEXT:    movl %edi, (%eax)
+; X86-SLOW-NEXT:    movl %esi, 12(%eax)
+; X86-SLOW-NEXT:    movl %ebx, 8(%eax)
+; X86-SLOW-NEXT:    movl %edi, 4(%eax)
+; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-SLOW-NEXT:    movl %ecx, (%eax)
 ; X86-SLOW-NEXT:    leal -12(%ebp), %esp
 ; X86-SLOW-NEXT:    popl %esi
 ; X86-SLOW-NEXT:    popl %edi
diff --git a/llvm/test/CodeGen/X86/fshr.ll b/llvm/test/CodeGen/X86/fshr.ll
index 544ab7f..c307833 100644
--- a/llvm/test/CodeGen/X86/fshr.ll
+++ b/llvm/test/CodeGen/X86/fshr.ll
@@ -322,79 +322,79 @@ define i128 @var_shift_i128(i128 %x, i128 %y, i128 %z) nounwind {
 ; X86-SLOW-NEXT:    subl $16, %esp
 ; X86-SLOW-NEXT:    movl 24(%ebp), %edx
 ; X86-SLOW-NEXT:    movl 28(%ebp), %esi
-; X86-SLOW-NEXT:    movl 48(%ebp), %ebx
+; X86-SLOW-NEXT:    movl 48(%ebp), %edi
 ; X86-SLOW-NEXT:    movl 56(%ebp), %eax
 ; X86-SLOW-NEXT:    testb $64, %al
-; X86-SLOW-NEXT:    movl 52(%ebp), %edi
+; X86-SLOW-NEXT:    movl 52(%ebp), %eax
 ; X86-SLOW-NEXT:    je .LBB6_1
 ; X86-SLOW-NEXT:  # %bb.2:
-; X86-SLOW-NEXT:    movl %ebx, (%esp) # 4-byte Spill
-; X86-SLOW-NEXT:    movl %edx, %ebx
+; X86-SLOW-NEXT:    movl %edi, (%esp) # 4-byte Spill
+; X86-SLOW-NEXT:    movl %edx, %edi
 ; X86-SLOW-NEXT:    movl 32(%ebp), %edx
-; X86-SLOW-NEXT:    movl %edi, %eax
-; X86-SLOW-NEXT:    movl %esi, %edi
+; X86-SLOW-NEXT:    movl %eax, %ecx
+; X86-SLOW-NEXT:    movl %esi, %eax
 ; X86-SLOW-NEXT:    movl 36(%ebp), %esi
 ; X86-SLOW-NEXT:    jmp .LBB6_3
 ; X86-SLOW-NEXT:  .LBB6_1:
-; X86-SLOW-NEXT:    movl 40(%ebp), %eax
-; X86-SLOW-NEXT:    movl %eax, (%esp) # 4-byte Spill
-; X86-SLOW-NEXT:    movl 44(%ebp), %eax
+; X86-SLOW-NEXT:    movl 40(%ebp), %ecx
+; X86-SLOW-NEXT:    movl %ecx, (%esp) # 4-byte Spill
+; X86-SLOW-NEXT:    movl 44(%ebp), %ecx
 ; X86-SLOW-NEXT:  .LBB6_3:
-; X86-SLOW-NEXT:    movl 56(%ebp), %ecx
-; X86-SLOW-NEXT:    testb $32, %cl
+; X86-SLOW-NEXT:    movl 56(%ebp), %ebx
+; X86-SLOW-NEXT:    testb $32, %bl
 ; X86-SLOW-NEXT:    je .LBB6_4
 ; X86-SLOW-NEXT:  # %bb.5:
-; X86-SLOW-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-SLOW-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X86-SLOW-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-SLOW-NEXT:    movl %ecx, %ebx
 ; X86-SLOW-NEXT:    jmp .LBB6_6
 ; X86-SLOW-NEXT:  .LBB6_4:
 ; X86-SLOW-NEXT:    movl %edx, %esi
+; X86-SLOW-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X86-SLOW-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X86-SLOW-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X86-SLOW-NEXT:    movl %eax, %ebx
-; X86-SLOW-NEXT:    movl (%esp), %eax # 4-byte Reload
+; X86-SLOW-NEXT:    movl %ecx, %edi
+; X86-SLOW-NEXT:    movl (%esp), %ebx # 4-byte Reload
 ; X86-SLOW-NEXT:  .LBB6_6:
-; X86-SLOW-NEXT:    shrl %cl, %eax
-; X86-SLOW-NEXT:    movl %eax, %edx
-; X86-SLOW-NEXT:    movl %ecx, %eax
-; X86-SLOW-NEXT:    notb %al
-; X86-SLOW-NEXT:    movl %ebx, %edi
-; X86-SLOW-NEXT:    addl %ebx, %ebx
-; X86-SLOW-NEXT:    movl %eax, %ecx
-; X86-SLOW-NEXT:    shll %cl, %ebx
-; X86-SLOW-NEXT:    orl %edx, %ebx
-; X86-SLOW-NEXT:    movl %ebx, (%esp) # 4-byte Spill
 ; X86-SLOW-NEXT:    movl 56(%ebp), %ecx
-; X86-SLOW-NEXT:    # kill: def $cl killed $cl killed $ecx
-; X86-SLOW-NEXT:    shrl %cl, %edi
-; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X86-SLOW-NEXT:    leal (%ebx,%ebx), %edx
-; X86-SLOW-NEXT:    movl %eax, %ecx
-; X86-SLOW-NEXT:    shll %cl, %edx
-; X86-SLOW-NEXT:    orl %edi, %edx
+; X86-SLOW-NEXT:    shrl %cl, %ebx
+; X86-SLOW-NEXT:    movl %ecx, %edx
+; X86-SLOW-NEXT:    notb %dl
+; X86-SLOW-NEXT:    movl %edi, %eax
+; X86-SLOW-NEXT:    addl %edi, %edi
+; X86-SLOW-NEXT:    movl %edx, %ecx
+; X86-SLOW-NEXT:    shll %cl, %edi
+; X86-SLOW-NEXT:    orl %ebx, %edi
+; X86-SLOW-NEXT:    movl %edi, (%esp) # 4-byte Spill
 ; X86-SLOW-NEXT:    movl 56(%ebp), %ecx
 ; X86-SLOW-NEXT:    # kill: def $cl killed $cl killed $ecx
-; X86-SLOW-NEXT:    shrl %cl, %ebx
-; X86-SLOW-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-SLOW-NEXT:    shrl %cl, %eax
 ; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X86-SLOW-NEXT:    leal (%edi,%edi), %ebx
-; X86-SLOW-NEXT:    movl %eax, %ecx
+; X86-SLOW-NEXT:    movl %edx, %ecx
 ; X86-SLOW-NEXT:    shll %cl, %ebx
-; X86-SLOW-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X86-SLOW-NEXT:    orl %eax, %ebx
 ; X86-SLOW-NEXT:    movl 56(%ebp), %ecx
 ; X86-SLOW-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X86-SLOW-NEXT:    shrl %cl, %edi
+; X86-SLOW-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-SLOW-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-SLOW-NEXT:    leal (%eax,%eax), %edi
+; X86-SLOW-NEXT:    movl %edx, %ecx
+; X86-SLOW-NEXT:    shll %cl, %edi
+; X86-SLOW-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X86-SLOW-NEXT:    movl 56(%ebp), %ecx
+; X86-SLOW-NEXT:    # kill: def $cl killed $cl killed $ecx
+; X86-SLOW-NEXT:    shrl %cl, %eax
 ; X86-SLOW-NEXT:    addl %esi, %esi
-; X86-SLOW-NEXT:    movl %eax, %ecx
+; X86-SLOW-NEXT:    movl %edx, %ecx
 ; X86-SLOW-NEXT:    shll %cl, %esi
-; X86-SLOW-NEXT:    orl %edi, %esi
-; X86-SLOW-NEXT:    movl 8(%ebp), %ecx
-; X86-SLOW-NEXT:    movl %esi, 12(%ecx)
-; X86-SLOW-NEXT:    movl %ebx, 8(%ecx)
-; X86-SLOW-NEXT:    movl %edx, 4(%ecx)
-; X86-SLOW-NEXT:    movl (%esp), %eax # 4-byte Reload
-; X86-SLOW-NEXT:    movl %eax, (%ecx)
-; X86-SLOW-NEXT:    movl %ecx, %eax
+; X86-SLOW-NEXT:    orl %eax, %esi
+; X86-SLOW-NEXT:    movl 8(%ebp), %eax
+; X86-SLOW-NEXT:    movl %esi, 12(%eax)
+; X86-SLOW-NEXT:    movl %edi, 8(%eax)
+; X86-SLOW-NEXT:    movl %ebx, 4(%eax)
+; X86-SLOW-NEXT:    movl (%esp), %ecx # 4-byte Reload
+; X86-SLOW-NEXT:    movl %ecx, (%eax)
 ; X86-SLOW-NEXT:    leal -12(%ebp), %esp
 ; X86-SLOW-NEXT:    popl %esi
 ; X86-SLOW-NEXT:    popl %edi
diff --git a/llvm/test/CodeGen/X86/pr161693.ll b/llvm/test/CodeGen/X86/pr161693.ll
new file mode 100644
index 0000000..de8188f
--- /dev/null
+++ b/llvm/test/CodeGen/X86/pr161693.ll
@@ -0,0 +1,40 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc < %s -mtriple=x86_64-- | FileCheck %s
+
+define void @PR161693() #0 {
+; CHECK-LABEL: PR161693:
+; CHECK:       # %bb.0: # %start
+; CHECK-NEXT:    movzbl (%rax), %eax
+; CHECK-NEXT:    andb $-33, %al
+; CHECK-NEXT:    addb $-71, %al
+; CHECK-NEXT:    .p2align 4
+; CHECK-NEXT:  .LBB0_1: # %loop
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    cmpb $-6, %al
+; CHECK-NEXT:    setb %cl
+; CHECK-NEXT:    leal (%rcx,%rcx), %edx
+; CHECK-NEXT:    orb %cl, %dl
+; CHECK-NEXT:    leal (,%rdx,4), %ecx
+; CHECK-NEXT:    orb %dl, %cl
+; CHECK-NEXT:    je .LBB0_1
+; CHECK-NEXT:  # %bb.2: # %exit
+; CHECK-NEXT:    retq
+start:
+  br label %loop
+
+loop:
+  %.val.i.i89 = load <16 x i8>, ptr poison, align 1
+  %.not49.i = icmp ult <16 x i8> zeroinitializer, splat (i8 -10)
+  %i = and <16 x i8> %.val.i.i89, splat (i8 -33)
+  %i1 = add <16 x i8> %i, splat (i8 -71)
+  %.not51.i = icmp ult <16 x i8> %i1, splat (i8 -6)
+  %.not46.i = and <16 x i1> %.not49.i, %.not51.i
+  %i2 = bitcast <16 x i1> %.not46.i to i16
+  %_0.i = icmp eq i16 %i2, 0
+  br i1 %_0.i, label %loop, label %exit
+
+exit:
+  ret void
+}
+
+attributes #0 = { "target-features"="+soft-float" }
diff --git a/llvm/test/CodeGen/X86/sbb.ll b/llvm/test/CodeGen/X86/sbb.ll
index 78d609d..f5a3468 100644
--- a/llvm/test/CodeGen/X86/sbb.ll
+++ b/llvm/test/CodeGen/X86/sbb.ll
@@ -365,3 +365,32 @@ define i32 @uge_sext_add(i32 %0, i32 %1, i32 %2) {
   %6 = add nsw i32 %5, %0
   ret i32 %6
 }
+
+define i32 @sub_sub_ugt(i32 %a, i32 %b) {
+; CHECK-LABEL: sub_sub_ugt:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    movl %edi, %eax
+; CHECK-NEXT:    cmpl %edi, %esi
+; CHECK-NEXT:    sbbl %esi, %eax
+; CHECK-NEXT:    retq
+  %cmp = icmp ugt i32 %a, %b
+  %conv = zext i1 %cmp to i32
+  %sub = sub i32 %a, %b
+  %res = sub i32 %sub, %conv
+  ret i32 %res
+}
+
+define i32 @sub_sub_ult(i32 %a, i32 %b) {
+; CHECK-LABEL: sub_sub_ult:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    movl %edi, %eax
+; CHECK-NEXT:    cmpl %edi, %esi
+; CHECK-NEXT:    sbbl %esi, %eax
+; CHECK-NEXT:    retq
+  %cmp = icmp ult i32 %b, %a
+  %conv = zext i1 %cmp to i32
+  %sub = sub i32 %a, %b
+  %res = sub i32 %sub, %conv
+  ret i32 %res
+}
+
diff --git a/llvm/test/CodeGen/X86/shift-i128.ll b/llvm/test/CodeGen/X86/shift-i128.ll
index 7462c77..049ee47 100644
--- a/llvm/test/CodeGen/X86/shift-i128.ll
+++ b/llvm/test/CodeGen/X86/shift-i128.ll
@@ -613,8 +613,7 @@ define void @test_shl_v2i128(<2 x i128> %x, <2 x i128> %a, ptr nocapture %r) nou
 ; i686-NEXT:    shldl %cl, %esi, %ebx
 ; i686-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; i686-NEXT:    movl %edi, %esi
-; i686-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; i686-NEXT:    movl %eax, %ecx
+; i686-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; i686-NEXT:    shll %cl, %esi
 ; i686-NEXT:    shldl %cl, %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; i686-NEXT:    negl %edx