; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
; RUN: llc < %s -mtriple=x86_64 | FileCheck %s

; GitHub issue #161036

; Positive test : umin(sub(a,b),a) with scalar types should be folded
define i64 @underflow_compare_fold_i64(i64 %a, i64 %b) {
; CHECK-LABEL: underflow_compare_fold_i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movq %rdi, %rax
; CHECK-NEXT:    subq %rsi, %rax
; CHECK-NEXT:    cmpq %rdi, %rax
; CHECK-NEXT:    cmovaeq %rdi, %rax
; CHECK-NEXT:    retq
  %sub = sub i64 %a, %b
  %cond = tail call i64 @llvm.umin.i64(i64 %sub, i64 %a)
  ret i64 %cond
}

; Positive test : umin(a,sub(a,b)) with scalar types should be folded
define i64 @underflow_compare_fold_i64_commute(i64 %a, i64 %b) {
; CHECK-LABEL: underflow_compare_fold_i64_commute:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movq %rdi, %rax
; CHECK-NEXT:    subq %rsi, %rax
; CHECK-NEXT:    cmpq %rax, %rdi
; CHECK-NEXT:    cmovbq %rdi, %rax
; CHECK-NEXT:    retq
  %sub = sub i64 %a, %b
  %cond = tail call i64 @llvm.umin.i64(i64 %a, i64 %sub)
  ret i64 %cond
}

; Positive test : multi-use is OK since the sub instruction still runs once
define i64 @underflow_compare_fold_i64_multi_use(i64 %a, i64 %b, ptr addrspace(1) %ptr) {
; CHECK-LABEL: underflow_compare_fold_i64_multi_use:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movq %rdi, %rax
; CHECK-NEXT:    subq %rsi, %rax
; CHECK-NEXT:    movq %rax, (%rdx)
; CHECK-NEXT:    cmpq %rdi, %rax
; CHECK-NEXT:    cmovaeq %rdi, %rax
; CHECK-NEXT:    retq
  %sub = sub i64 %a, %b
  store i64 %sub, ptr addrspace(1) %ptr
  %cond = call i64 @llvm.umin.i64(i64 %sub, i64 %a)
  ret i64 %cond
}

; Positive test : i32
define i32 @underflow_compare_fold_i32(i32 %a, i32 %b) {
; CHECK-LABEL: underflow_compare_fold_i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movl %edi, %eax
; CHECK-NEXT:    subl %esi, %eax
; CHECK-NEXT:    cmpl %edi, %eax
; CHECK-NEXT:    cmovael %edi, %eax
; CHECK-NEXT:    retq
  %sub = sub i32 %a, %b
  %cond = tail call i32 @llvm.umin.i32(i32 %sub, i32 %a)
  ret i32 %cond
}

; Positive test : i32
define i32 @underflow_compare_fold_i32_commute(i32 %a, i32 %b) {
; CHECK-LABEL: underflow_compare_fold_i32_commute:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movl %edi, %eax
; CHECK-NEXT:    subl %esi, %eax
; CHECK-NEXT:    cmpl %eax, %edi
; CHECK-NEXT:    cmovbl %edi, %eax
; CHECK-NEXT:    retq
  %sub = sub i32 %a, %b
  %cond = tail call i32 @llvm.umin.i32(i32 %a, i32 %sub)
  ret i32 %cond
}

; Positive test : i32
define i32 @underflow_compare_fold_i32_multi_use(i32 %a, i32 %b, ptr addrspace(1) %ptr) {
; CHECK-LABEL: underflow_compare_fold_i32_multi_use:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movl %edi, %eax
; CHECK-NEXT:    subl %esi, %eax
; CHECK-NEXT:    movl %eax, (%rdx)
; CHECK-NEXT:    cmpl %edi, %eax
; CHECK-NEXT:    cmovael %edi, %eax
; CHECK-NEXT:    retq
  %sub = sub i32 %a, %b
  store i32 %sub, ptr addrspace(1) %ptr
  %cond = call i32 @llvm.umin.i32(i32 %sub, i32 %a)
  ret i32 %cond
}

; Positive test : i16
define i16 @underflow_compare_fold_i16(i16 %a, i16 %b) {
; CHECK-LABEL: underflow_compare_fold_i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movl %edi, %eax
; CHECK-NEXT:    subl %esi, %eax
; CHECK-NEXT:    cmpw %di, %ax
; CHECK-NEXT:    cmovael %edi, %eax
; CHECK-NEXT:    # kill: def $ax killed $ax killed $eax
; CHECK-NEXT:    retq
  %sub = sub i16 %a, %b
  %cond = tail call i16 @llvm.umin.i16(i16 %sub, i16 %a)
  ret i16 %cond
}

; Positive test : i16
define i16 @underflow_compare_fold_i16_commute(i16 %a, i16 %b) {
; CHECK-LABEL: underflow_compare_fold_i16_commute:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movl %edi, %eax
; CHECK-NEXT:    subl %esi, %eax
; CHECK-NEXT:    cmpw %ax, %di
; CHECK-NEXT:    cmovbl %edi, %eax
; CHECK-NEXT:    # kill: def $ax killed $ax killed $eax
; CHECK-NEXT:    retq
  %sub = sub i16 %a, %b
  %cond = tail call i16 @llvm.umin.i16(i16 %a, i16 %sub)
  ret i16 %cond
}

; Positive test : i16
define i16 @underflow_compare_fold_i16_multi_use(i16 %a, i16 %b, ptr addrspace(1) %ptr) {
; CHECK-LABEL: underflow_compare_fold_i16_multi_use:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movl %edi, %eax
; CHECK-NEXT:    subl %esi, %eax
; CHECK-NEXT:    movw %ax, (%rdx)
; CHECK-NEXT:    cmpw %di, %ax
; CHECK-NEXT:    cmovael %edi, %eax
; CHECK-NEXT:    # kill: def $ax killed $ax killed $eax
; CHECK-NEXT:    retq
  %sub = sub i16 %a, %b
  store i16 %sub, ptr addrspace(1) %ptr
  %cond = call i16 @llvm.umin.i16(i16 %sub, i16 %a)
  ret i16 %cond
}


; Negative test, vector types : umin(sub(a,b),a) but with vectors
define <16 x i8> @underflow_compare_dontfold_vectors(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: underflow_compare_dontfold_vectors:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movdqa %xmm0, %xmm2
; CHECK-NEXT:    psubb %xmm1, %xmm2
; CHECK-NEXT:    pminub %xmm2, %xmm0
; CHECK-NEXT:    retq
  %sub = sub <16 x i8> %a, %b
  %cond = tail call <16 x i8> @llvm.umin.v16i8(<16 x i8> %sub, <16 x i8> %a)
  ret <16 x i8> %cond
}

; Negative test, pattern mismatch : umin(add(a,b),a)
define i64 @umin_add(i64 %a, i64 %b) {
; CHECK-LABEL: umin_add:
; CHECK:       # %bb.0:
; CHECK-NEXT:    leaq (%rsi,%rdi), %rax
; CHECK-NEXT:    cmpq %rdi, %rax
; CHECK-NEXT:    cmovaeq %rdi, %rax
; CHECK-NEXT:    retq
  %add = add i64 %a, %b
  %cond = tail call i64 @llvm.umin.i64(i64 %add, i64 %a)
  ret i64 %cond
}