test/Transforms/InstCombine/saturating-add-sub.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -instcombine -S | FileCheck %s

;
; Saturating addition.
;

declare i8 @llvm.uadd.sat.i8(i8, i8)
declare i8 @llvm.sadd.sat.i8(i8, i8)
declare <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8>, <2 x i8>)
declare <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8>, <2 x i8>)

; Constant uadd argument is canonicalized to the right.
define i8 @test_scalar_uadd_canonical(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_canonical(
; CHECK-NEXT:    [[X:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[A:%.*]], i8 10)
; CHECK-NEXT:    ret i8 [[X]]
;
  %x = call i8 @llvm.uadd.sat.i8(i8 10, i8 %a)
  ret i8 %x
}

define <2 x i8> @test_vector_uadd_canonical(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_uadd_canonical(
; CHECK-NEXT:    [[X:%.*]] = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 10, i8 20>)
; CHECK-NEXT:    ret <2 x i8> [[X]]
;
  %x = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> <i8 10, i8 20>, <2 x i8> %a)
  ret <2 x i8> %x
}

; Constant sadd argument is canonicalized to the right.
define i8 @test_scalar_sadd_canonical(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_canonical(
; CHECK-NEXT:    [[X:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A:%.*]], i8 -10)
; CHECK-NEXT:    ret i8 [[X]]
;
  %x = call i8 @llvm.sadd.sat.i8(i8 -10, i8 %a)
  ret i8 %x
}

define <2 x i8> @test_vector_sadd_canonical(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_sadd_canonical(
; CHECK-NEXT:    [[X:%.*]] = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 10, i8 -20>)
; CHECK-NEXT:    ret <2 x i8> [[X]]
;
  %x = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> <i8 10, i8 -20>, <2 x i8> %a)
  ret <2 x i8> %x
}

; Can combine uadds with constant operands.
define i8 @test_scalar_uadd_combine(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_combine(
; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[A:%.*]], i8 30)
; CHECK-NEXT:    ret i8 [[TMP1]]
;
  %x1 = call i8 @llvm.uadd.sat.i8(i8 %a, i8 10)
  %x2 = call i8 @llvm.uadd.sat.i8(i8 %x1, i8 20)
  ret i8 %x2
}

define <2 x i8> @test_vector_uadd_combine(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_uadd_combine(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 30, i8 30>)
; CHECK-NEXT:    ret <2 x i8> [[TMP1]]
;
  %x1 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 10, i8 10>)
  %x2 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %x1, <2 x i8> <i8 20, i8 20>)
  ret <2 x i8> %x2
}

; This could simplify, but currently doesn't.
define <2 x i8> @test_vector_uadd_combine_non_splat(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_uadd_combine_non_splat(
; CHECK-NEXT:    [[X1:%.*]] = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 10, i8 20>)
; CHECK-NEXT:    [[X2:%.*]] = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> [[X1]], <2 x i8> <i8 30, i8 40>)
; CHECK-NEXT:    ret <2 x i8> [[X2]]
;
  %x1 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 10, i8 20>)
  %x2 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %x1, <2 x i8> <i8 30, i8 40>)
  ret <2 x i8> %x2
}

; Can combine uadds even if they overflow.
define i8 @test_scalar_uadd_overflow(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_overflow(
; CHECK-NEXT:    ret i8 -1
;
  %y1 = call i8 @llvm.uadd.sat.i8(i8 %a, i8 100)
  %y2 = call i8 @llvm.uadd.sat.i8(i8 %y1, i8 200)
  ret i8 %y2
}

define <2 x i8> @test_vector_uadd_overflow(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_uadd_overflow(
; CHECK-NEXT:    ret <2 x i8> <i8 -1, i8 -1>
;
  %y1 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 100, i8 100>)
  %y2 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %y1, <2 x i8> <i8 200, i8 200>)
  ret <2 x i8> %y2
}

; Can combine sadds if sign matches.
define i8 @test_scalar_sadd_both_positive(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_both_positive(
; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A:%.*]], i8 30)
; CHECK-NEXT:    ret i8 [[TMP1]]
;
  %z1 = call i8 @llvm.sadd.sat.i8(i8 %a, i8 10)
  %z2 = call i8 @llvm.sadd.sat.i8(i8 %z1, i8 20)
  ret i8 %z2
}

define <2 x i8> @test_vector_sadd_both_positive(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_sadd_both_positive(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 30, i8 30>)
; CHECK-NEXT:    ret <2 x i8> [[TMP1]]
;
  %z1 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 10, i8 10>)
  %z2 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> %z1, <2 x i8> <i8 20, i8 20>)
  ret <2 x i8> %z2
}

define i8 @test_scalar_sadd_both_negative(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_both_negative(
; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A:%.*]], i8 -30)
; CHECK-NEXT:    ret i8 [[TMP1]]
;
  %u1 = call i8 @llvm.sadd.sat.i8(i8 %a, i8 -10)
  %u2 = call i8 @llvm.sadd.sat.i8(i8 %u1, i8 -20)
  ret i8 %u2
}

define <2 x i8> @test_vector_sadd_both_negative(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_sadd_both_negative(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 -30, i8 -30>)
; CHECK-NEXT:    ret <2 x i8> [[TMP1]]
;
  %u1 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 -10, i8 -10>)
  %u2 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> %u1, <2 x i8> <i8 -20, i8 -20>)
  ret <2 x i8> %u2
}

; Can't combine sadds if constants have different sign.
define i8 @test_scalar_sadd_different_sign(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_different_sign(
; CHECK-NEXT:    [[V1:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A:%.*]], i8 10)
; CHECK-NEXT:    [[V2:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[V1]], i8 -20)
; CHECK-NEXT:    ret i8 [[V2]]
;
  %v1 = call i8 @llvm.sadd.sat.i8(i8 %a, i8 10)
  %v2 = call i8 @llvm.sadd.sat.i8(i8 %v1, i8 -20)
  ret i8 %v2
}

; Can't combine sadds if they overflow.
define i8 @test_scalar_sadd_overflow(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_overflow(
; CHECK-NEXT:    [[W1:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A:%.*]], i8 100)
; CHECK-NEXT:    [[W2:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[W1]], i8 100)
; CHECK-NEXT:    ret i8 [[W2]]
;
  %w1 = call i8 @llvm.sadd.sat.i8(i8 %a, i8 100)
  %w2 = call i8 @llvm.sadd.sat.i8(i8 %w1, i8 100)
  ret i8 %w2
}

; neg uadd neg always overflows.
define i8 @test_scalar_uadd_neg_neg(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_neg_neg(
; CHECK-NEXT:    ret i8 -1
;
  %a_neg = or i8 %a, -128
  %r = call i8 @llvm.uadd.sat.i8(i8 %a_neg, i8 -10)
  ret i8 %r
}

define <2 x i8> @test_vector_uadd_neg_neg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_uadd_neg_neg(
; CHECK-NEXT:    ret <2 x i8> <i8 -1, i8 -1>
;
  %a_neg = or <2 x i8> %a, <i8 -128, i8 -128>
  %r = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a_neg, <2 x i8> <i8 -10, i8 -20>)
  ret <2 x i8> %r
}

; nneg uadd nneg never overflows.
define i8 @test_scalar_uadd_nneg_nneg(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_nneg_nneg(
; CHECK-NEXT:    [[A_NNEG:%.*]] = and i8 [[A:%.*]], 127
; CHECK-NEXT:    [[R:%.*]] = add nuw i8 [[A_NNEG]], 10
; CHECK-NEXT:    ret i8 [[R]]
;
  %a_nneg = and i8 %a, 127
  %r = call i8 @llvm.uadd.sat.i8(i8 %a_nneg, i8 10)
  ret i8 %r
}

define <2 x i8> @test_vector_uadd_nneg_nneg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_uadd_nneg_nneg(
; CHECK-NEXT:    [[A_NNEG:%.*]] = and <2 x i8> [[A:%.*]], <i8 127, i8 127>
; CHECK-NEXT:    [[R:%.*]] = add nuw <2 x i8> [[A_NNEG]], <i8 10, i8 20>
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %a_nneg = and <2 x i8> %a, <i8 127, i8 127>
  %r = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a_nneg, <2 x i8> <i8 10, i8 20>)
  ret <2 x i8> %r
}

; neg uadd nneg might overflow.
define i8 @test_scalar_uadd_neg_nneg(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_neg_nneg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or i8 [[A:%.*]], -128
; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[A_NEG]], i8 10)
; CHECK-NEXT:    ret i8 [[R]]
;
  %a_neg = or i8 %a, -128
  %r = call i8 @llvm.uadd.sat.i8(i8 %a_neg, i8 10)
  ret i8 %r
}

define <2 x i8> @test_vector_uadd_neg_nneg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_uadd_neg_nneg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or <2 x i8> [[A:%.*]], <i8 -128, i8 -128>
; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> [[A_NEG]], <2 x i8> <i8 10, i8 20>)
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %a_neg = or <2 x i8> %a, <i8 -128, i8 -128>
  %r = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a_neg, <2 x i8> <i8 10, i8 20>)
  ret <2 x i8> %r
}

define i8 @test_scalar_uadd_never_overflows(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_never_overflows(
; CHECK-NEXT:    [[A_MASKED:%.*]] = and i8 [[A:%.*]], -127
; CHECK-NEXT:    [[R:%.*]] = add nuw nsw i8 [[A_MASKED]], 1
; CHECK-NEXT:    ret i8 [[R]]
;
  %a_masked = and i8 %a, 129
  %r = call i8 @llvm.uadd.sat.i8(i8 %a_masked, i8 1)
  ret i8 %r
}

define <2 x i8> @test_vector_uadd_never_overflows(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_uadd_never_overflows(
; CHECK-NEXT:    [[A_MASKED:%.*]] = and <2 x i8> [[A:%.*]], <i8 -127, i8 -127>
; CHECK-NEXT:    [[R:%.*]] = add nuw nsw <2 x i8> [[A_MASKED]], <i8 1, i8 1>
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %a_masked = and <2 x i8> %a, <i8 129, i8 129>
  %r = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a_masked, <2 x i8> <i8 1, i8 1>)
  ret <2 x i8> %r
}

define i8 @test_scalar_uadd_always_overflows(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_always_overflows(
; CHECK-NEXT:    ret i8 -1
;
  %a_masked = or i8 %a, 192
  %r = call i8 @llvm.uadd.sat.i8(i8 %a_masked, i8 64)
  ret i8 %r
}

define <2 x i8> @test_vector_uadd_always_overflows(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_uadd_always_overflows(
; CHECK-NEXT:    ret <2 x i8> <i8 -1, i8 -1>
;
  %a_masked = or <2 x i8> %a, <i8 192, i8 192>
  %r = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a_masked, <2 x i8> <i8 64, i8 64>)
  ret <2 x i8> %r
}

; neg sadd nneg never overflows.
define i8 @test_scalar_sadd_neg_nneg(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_neg_nneg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or i8 [[A:%.*]], -128
; CHECK-NEXT:    [[R:%.*]] = add nsw i8 [[A_NEG]], 10
; CHECK-NEXT:    ret i8 [[R]]
;
  %a_neg = or i8 %a, -128
  %r = call i8 @llvm.sadd.sat.i8(i8 %a_neg, i8 10)
  ret i8 %r
}

define <2 x i8> @test_vector_sadd_neg_nneg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_sadd_neg_nneg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or <2 x i8> [[A:%.*]], <i8 -128, i8 -128>
; CHECK-NEXT:    [[R:%.*]] = add nsw <2 x i8> [[A_NEG]], <i8 10, i8 20>
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %a_neg = or <2 x i8> %a, <i8 -128, i8 -128>
  %r = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> %a_neg, <2 x i8> <i8 10, i8 20>)
  ret <2 x i8> %r
}

; nneg sadd neg never overflows.
define i8 @test_scalar_sadd_nneg_neg(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_nneg_neg(
; CHECK-NEXT:    [[A_NNEG:%.*]] = and i8 [[A:%.*]], 127
; CHECK-NEXT:    [[R:%.*]] = add nsw i8 [[A_NNEG]], -10
; CHECK-NEXT:    ret i8 [[R]]
;
  %a_nneg = and i8 %a, 127
  %r = call i8 @llvm.sadd.sat.i8(i8 %a_nneg, i8 -10)
  ret i8 %r
}

define <2 x i8> @test_vector_sadd_nneg_neg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_sadd_nneg_neg(
; CHECK-NEXT:    [[A_NNEG:%.*]] = and <2 x i8> [[A:%.*]], <i8 127, i8 127>
; CHECK-NEXT:    [[R:%.*]] = add nsw <2 x i8> [[A_NNEG]], <i8 -10, i8 -20>
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %a_nneg = and <2 x i8> %a, <i8 127, i8 127>
  %r = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> %a_nneg, <2 x i8> <i8 -10, i8 -20>)
  ret <2 x i8> %r
}

; neg sadd neg might overflow.
define i8 @test_scalar_sadd_neg_neg(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_neg_neg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or i8 [[A:%.*]], -128
; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A_NEG]], i8 -10)
; CHECK-NEXT:    ret i8 [[R]]
;
  %a_neg = or i8 %a, -128
  %r = call i8 @llvm.sadd.sat.i8(i8 %a_neg, i8 -10)
  ret i8 %r
}

define <2 x i8> @test_vector_sadd_neg_neg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_sadd_neg_neg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or <2 x i8> [[A:%.*]], <i8 -128, i8 -128>
; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> [[A_NEG]], <2 x i8> <i8 -10, i8 -20>)
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %a_neg = or <2 x i8> %a, <i8 -128, i8 -128>
  %r = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> %a_neg, <2 x i8> <i8 -10, i8 -20>)
  ret <2 x i8> %r
}

define i8 @test_scalar_sadd_always_overflows_low(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_always_overflows_low(
; CHECK-NEXT:    ret i8 -128
;
  %cmp = icmp slt i8 %a, -120
  %min = select i1 %cmp, i8 %a, i8 -120
  %r = call i8 @llvm.sadd.sat.i8(i8 %min, i8 -10)
  ret i8 %r
}

define i8 @test_scalar_sadd_always_overflows_high(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_always_overflows_high(
; CHECK-NEXT:    ret i8 127
;
  %cmp = icmp sgt i8 %a, 120
  %max = select i1 %cmp, i8 %a, i8 120
  %r = call i8 @llvm.sadd.sat.i8(i8 %max, i8 10)
  ret i8 %r
}

; While this is a no-overflow condition, the nuw flag gets lost due to
; canonicalization and we can no longer determine this
define i8 @test_scalar_uadd_sub_nuw_lost_no_ov(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_sub_nuw_lost_no_ov(
; CHECK-NEXT:    [[B:%.*]] = add i8 [[A:%.*]], -10
; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[B]], i8 9)
; CHECK-NEXT:    ret i8 [[R]]
;
  %b = sub nuw i8 %a, 10
  %r = call i8 @llvm.uadd.sat.i8(i8 %b, i8 9)
  ret i8 %r
}

define i8 @test_scalar_uadd_urem_no_ov(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_urem_no_ov(
; CHECK-NEXT:    [[B:%.*]] = urem i8 [[A:%.*]], 100
; CHECK-NEXT:    [[R:%.*]] = add nuw nsw i8 [[B]], -100
; CHECK-NEXT:    ret i8 [[R]]
;
  %b = urem i8 %a, 100
  %r = call i8 @llvm.uadd.sat.i8(i8 %b, i8 156)
  ret i8 %r
}

define i8 @test_scalar_uadd_urem_may_ov(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_urem_may_ov(
; CHECK-NEXT:    [[B:%.*]] = urem i8 [[A:%.*]], 100
; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[B]], i8 -99)
; CHECK-NEXT:    ret i8 [[R]]
;
  %b = urem i8 %a, 100
  %r = call i8 @llvm.uadd.sat.i8(i8 %b, i8 157)
  ret i8 %r
}

; We have a constant range for the LHS, but only known bits for the RHS
define i8 @test_scalar_uadd_udiv_known_bits(i8 %a, i8 %b) {
; CHECK-LABEL: @test_scalar_uadd_udiv_known_bits(
; CHECK-NEXT:    [[AA:%.*]] = udiv i8 -66, [[A:%.*]]
; CHECK-NEXT:    [[BB:%.*]] = and i8 [[B:%.*]], 63
; CHECK-NEXT:    [[R:%.*]] = add nuw i8 [[AA]], [[BB]]
; CHECK-NEXT:    ret i8 [[R]]
;
  %aa = udiv i8 190, %a
  %bb = and i8 %b, 63
  %r = call i8 @llvm.uadd.sat.i8(i8 %aa, i8 %bb)
  ret i8 %r
}

define i8 @test_scalar_sadd_srem_no_ov(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_srem_no_ov(
; CHECK-NEXT:    [[B:%.*]] = srem i8 [[A:%.*]], 100
; CHECK-NEXT:    [[R:%.*]] = add nsw i8 [[B]], 28
; CHECK-NEXT:    ret i8 [[R]]
;
  %b = srem i8 %a, 100
  %r = call i8 @llvm.sadd.sat.i8(i8 %b, i8 28)
  ret i8 %r
}

define i8 @test_scalar_sadd_srem_may_ov(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_srem_may_ov(
; CHECK-NEXT:    [[B:%.*]] = srem i8 [[A:%.*]], 100
; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[B]], i8 29)
; CHECK-NEXT:    ret i8 [[R]]
;
  %b = srem i8 %a, 100
  %r = call i8 @llvm.sadd.sat.i8(i8 %b, i8 29)
  ret i8 %r
}

define i8 @test_scalar_sadd_srem_and_no_ov(i8 %a, i8 %b) {
; CHECK-LABEL: @test_scalar_sadd_srem_and_no_ov(
; CHECK-NEXT:    [[AA:%.*]] = srem i8 [[A:%.*]], 100
; CHECK-NEXT:    [[BB:%.*]] = and i8 [[B:%.*]], 15
; CHECK-NEXT:    [[R:%.*]] = add nsw i8 [[AA]], [[BB]]
; CHECK-NEXT:    ret i8 [[R]]
;
  %aa = srem i8 %a, 100
  %bb = and i8 %b, 15
  %r = call i8 @llvm.sadd.sat.i8(i8 %aa, i8 %bb)
  ret i8 %r
}

;
; Saturating subtraction.
;

declare i8 @llvm.usub.sat.i8(i8, i8)
declare i8 @llvm.ssub.sat.i8(i8, i8)
declare <2 x i8> @llvm.usub.sat.v2i8(<2 x i8>, <2 x i8>)
declare <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8>, <2 x i8>)

; Cannot canonicalize usub to uadd.
define i8 @test_scalar_usub_canonical(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_canonical(
; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.usub.sat.i8(i8 [[A:%.*]], i8 10)
; CHECK-NEXT:    ret i8 [[R]]
;
  %r = call i8 @llvm.usub.sat.i8(i8 %a, i8 10)
  ret i8 %r
}

; Canonicalize ssub to sadd.
define i8 @test_scalar_ssub_canonical(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_canonical(
; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A:%.*]], i8 -10)
; CHECK-NEXT:    ret i8 [[TMP1]]
;
  %r = call i8 @llvm.ssub.sat.i8(i8 %a, i8 10)
  ret i8 %r
}

define <2 x i8> @test_vector_ssub_canonical(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_ssub_canonical(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 -10, i8 -10>)
; CHECK-NEXT:    ret <2 x i8> [[TMP1]]
;
  %r = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 10, i8 10>)
  ret <2 x i8> %r
}

define <2 x i8> @test_vector_ssub_canonical_min_non_splat(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_ssub_canonical_min_non_splat(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 -10, i8 10>)
; CHECK-NEXT:    ret <2 x i8> [[TMP1]]
;
  %r = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 10, i8 -10>)
  ret <2 x i8> %r
}

; Cannot canonicalize signed min.
define i8 @test_scalar_ssub_canonical_min(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_canonical_min(
; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.ssub.sat.i8(i8 [[A:%.*]], i8 -128)
; CHECK-NEXT:    ret i8 [[R]]
;
  %r = call i8 @llvm.ssub.sat.i8(i8 %a, i8 -128)
  ret i8 %r
}

define <2 x i8> @test_vector_ssub_canonical_min(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_ssub_canonical_min(
; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 -128, i8 -10>)
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %r = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 -128, i8 -10>)
  ret <2 x i8> %r
}

; Can combine usubs with constant operands.
define i8 @test_scalar_usub_combine(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_combine(
; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.usub.sat.i8(i8 [[A:%.*]], i8 30)
; CHECK-NEXT:    ret i8 [[TMP1]]
;
  %x1 = call i8 @llvm.usub.sat.i8(i8 %a, i8 10)
  %x2 = call i8 @llvm.usub.sat.i8(i8 %x1, i8 20)
  ret i8 %x2
}

define <2 x i8> @test_vector_usub_combine(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_combine(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 30, i8 30>)
; CHECK-NEXT:    ret <2 x i8> [[TMP1]]
;
  %x1 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 10, i8 10>)
  %x2 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %x1, <2 x i8> <i8 20, i8 20>)
  ret <2 x i8> %x2
}

; This could simplify, but currently doesn't.
define <2 x i8> @test_vector_usub_combine_non_splat(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_combine_non_splat(
; CHECK-NEXT:    [[X1:%.*]] = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 10, i8 20>)
; CHECK-NEXT:    [[X2:%.*]] = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> [[X1]], <2 x i8> <i8 30, i8 40>)
; CHECK-NEXT:    ret <2 x i8> [[X2]]
;
  %x1 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 10, i8 20>)
  %x2 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %x1, <2 x i8> <i8 30, i8 40>)
  ret <2 x i8> %x2
}

; Can combine usubs even if they overflow.
define i8 @test_scalar_usub_overflow(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_overflow(
; CHECK-NEXT:    ret i8 0
;
  %y1 = call i8 @llvm.usub.sat.i8(i8 %a, i8 100)
  %y2 = call i8 @llvm.usub.sat.i8(i8 %y1, i8 200)
  ret i8 %y2
}

define <2 x i8> @test_vector_usub_overflow(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_overflow(
; CHECK-NEXT:    ret <2 x i8> zeroinitializer
;
  %y1 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 100, i8 100>)
  %y2 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %y1, <2 x i8> <i8 200, i8 200>)
  ret <2 x i8> %y2
}

; Can combine ssubs if sign matches.
define i8 @test_scalar_ssub_both_positive(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_both_positive(
; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A:%.*]], i8 -30)
; CHECK-NEXT:    ret i8 [[TMP1]]
;
  %z1 = call i8 @llvm.ssub.sat.i8(i8 %a, i8 10)
  %z2 = call i8 @llvm.ssub.sat.i8(i8 %z1, i8 20)
  ret i8 %z2
}

define <2 x i8> @test_vector_ssub_both_positive(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_ssub_both_positive(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 -30, i8 -30>)
; CHECK-NEXT:    ret <2 x i8> [[TMP1]]
;
  %z1 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 10, i8 10>)
  %z2 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %z1, <2 x i8> <i8 20, i8 20>)
  ret <2 x i8> %z2
}

define i8 @test_scalar_ssub_both_negative(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_both_negative(
; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A:%.*]], i8 30)
; CHECK-NEXT:    ret i8 [[TMP1]]
;
  %u1 = call i8 @llvm.ssub.sat.i8(i8 %a, i8 -10)
  %u2 = call i8 @llvm.ssub.sat.i8(i8 %u1, i8 -20)
  ret i8 %u2
}

define <2 x i8> @test_vector_ssub_both_negative(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_ssub_both_negative(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 30, i8 30>)
; CHECK-NEXT:    ret <2 x i8> [[TMP1]]
;
  %u1 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 -10, i8 -10>)
  %u2 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %u1, <2 x i8> <i8 -20, i8 -20>)
  ret <2 x i8> %u2
}

; Can't combine ssubs if constants have different sign.
define i8 @test_scalar_ssub_different_sign(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_different_sign(
; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A:%.*]], i8 -10)
; CHECK-NEXT:    [[TMP2:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[TMP1]], i8 20)
; CHECK-NEXT:    ret i8 [[TMP2]]
;
  %v1 = call i8 @llvm.ssub.sat.i8(i8 %a, i8 10)
  %v2 = call i8 @llvm.ssub.sat.i8(i8 %v1, i8 -20)
  ret i8 %v2
}

; Can combine sadd and ssub with appropriate signs.
define i8 @test_scalar_sadd_ssub(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_ssub(
; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A:%.*]], i8 30)
; CHECK-NEXT:    ret i8 [[TMP1]]
;
  %v1 = call i8 @llvm.sadd.sat.i8(i8 10, i8 %a)
  %v2 = call i8 @llvm.ssub.sat.i8(i8 %v1, i8 -20)
  ret i8 %v2
}

define <2 x i8> @test_vector_sadd_ssub(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_sadd_ssub(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 -30, i8 -30>)
; CHECK-NEXT:    ret <2 x i8> [[TMP1]]
;
  %v1 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> <i8 -10, i8 -10>, <2 x i8> %a)
  %v2 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %v1, <2 x i8> <i8 20, i8 20>)
  ret <2 x i8> %v2
}

; Can't combine ssubs if they overflow.
define i8 @test_scalar_ssub_overflow(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_overflow(
; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A:%.*]], i8 -100)
; CHECK-NEXT:    [[TMP2:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[TMP1]], i8 -100)
; CHECK-NEXT:    ret i8 [[TMP2]]
;
  %w1 = call i8 @llvm.ssub.sat.i8(i8 %a, i8 100)
  %w2 = call i8 @llvm.ssub.sat.i8(i8 %w1, i8 100)
  ret i8 %w2
}

; nneg usub neg always overflows.
define i8 @test_scalar_usub_nneg_neg(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_nneg_neg(
; CHECK-NEXT:    ret i8 0
;
  %a_nneg = and i8 %a, 127
  %r = call i8 @llvm.usub.sat.i8(i8 %a_nneg, i8 -10)
  ret i8 %r
}

define <2 x i8> @test_vector_usub_nneg_neg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_nneg_neg(
; CHECK-NEXT:    ret <2 x i8> zeroinitializer
;
  %a_nneg = and <2 x i8> %a, <i8 127, i8 127>
  %r = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a_nneg, <2 x i8> <i8 -10, i8 -20>)
  ret <2 x i8> %r
}

; neg usub nneg never overflows.
define i8 @test_scalar_usub_neg_nneg(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_neg_nneg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or i8 [[A:%.*]], -128
; CHECK-NEXT:    [[R:%.*]] = add i8 [[A_NEG]], -10
; CHECK-NEXT:    ret i8 [[R]]
;
  %a_neg = or i8 %a, -128
  %r = call i8 @llvm.usub.sat.i8(i8 %a_neg, i8 10)
  ret i8 %r
}

define <2 x i8> @test_vector_usub_neg_nneg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_neg_nneg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or <2 x i8> [[A:%.*]], <i8 -128, i8 -128>
; CHECK-NEXT:    [[R:%.*]] = add <2 x i8> [[A_NEG]], <i8 -10, i8 -20>
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %a_neg = or <2 x i8> %a, <i8 -128, i8 -128>
  %r = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a_neg, <2 x i8> <i8 10, i8 20>)
  ret <2 x i8> %r
}

; nneg usub nneg never may overflow.
define i8 @test_scalar_usub_nneg_nneg(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_nneg_nneg(
; CHECK-NEXT:    [[A_NNEG:%.*]] = and i8 [[A:%.*]], 127
; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.usub.sat.i8(i8 [[A_NNEG]], i8 10)
; CHECK-NEXT:    ret i8 [[R]]
;
  %a_nneg = and i8 %a, 127
  %r = call i8 @llvm.usub.sat.i8(i8 %a_nneg, i8 10)
  ret i8 %r
}

define <2 x i8> @test_vector_usub_nneg_nneg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_nneg_nneg(
; CHECK-NEXT:    [[A_NNEG:%.*]] = and <2 x i8> [[A:%.*]], <i8 127, i8 127>
; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> [[A_NNEG]], <2 x i8> <i8 10, i8 20>)
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %a_nneg = and <2 x i8> %a, <i8 127, i8 127>
  %r = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a_nneg, <2 x i8> <i8 10, i8 20>)
  ret <2 x i8> %r
}

define i8 @test_scalar_usub_never_overflows(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_never_overflows(
; CHECK-NEXT:    [[A_MASKED:%.*]] = or i8 [[A:%.*]], 64
; CHECK-NEXT:    [[R:%.*]] = add nsw i8 [[A_MASKED]], -10
; CHECK-NEXT:    ret i8 [[R]]
;
  %a_masked = or i8 %a, 64
  %r = call i8 @llvm.usub.sat.i8(i8 %a_masked, i8 10)
  ret i8 %r
}

define <2 x i8> @test_vector_usub_never_overflows(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_never_overflows(
; CHECK-NEXT:    [[A_MASKED:%.*]] = or <2 x i8> [[A:%.*]], <i8 64, i8 64>
; CHECK-NEXT:    [[R:%.*]] = add nsw <2 x i8> [[A_MASKED]], <i8 -10, i8 -10>
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %a_masked = or <2 x i8> %a, <i8 64, i8 64>
  %r = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a_masked, <2 x i8> <i8 10, i8 10>)
  ret <2 x i8> %r
}

define i8 @test_scalar_usub_always_overflows(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_always_overflows(
; CHECK-NEXT:    ret i8 0
;
  %a_masked = and i8 %a, 64
  %r = call i8 @llvm.usub.sat.i8(i8 %a_masked, i8 100)
  ret i8 %r
}

define <2 x i8> @test_vector_usub_always_overflows(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_always_overflows(
; CHECK-NEXT:    ret <2 x i8> zeroinitializer
;
  %a_masked = and <2 x i8> %a, <i8 64, i8 64>
  %r = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a_masked, <2 x i8> <i8 100, i8 100>)
  ret <2 x i8> %r
}

; neg ssub neg never overflows.
define i8 @test_scalar_ssub_neg_neg(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_neg_neg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or i8 [[A:%.*]], -128
; CHECK-NEXT:    [[R:%.*]] = add nsw i8 [[A_NEG]], 10
; CHECK-NEXT:    ret i8 [[R]]
;
  %a_neg = or i8 %a, -128
  %r = call i8 @llvm.ssub.sat.i8(i8 %a_neg, i8 -10)
  ret i8 %r
}

define <2 x i8> @test_vector_ssub_neg_neg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_ssub_neg_neg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or <2 x i8> [[A:%.*]], <i8 -128, i8 -128>
; CHECK-NEXT:    [[R:%.*]] = add nsw <2 x i8> [[A_NEG]], <i8 10, i8 20>
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %a_neg = or <2 x i8> %a, <i8 -128, i8 -128>
  %r = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a_neg, <2 x i8> <i8 -10, i8 -20>)
  ret <2 x i8> %r
}

; nneg ssub nneg never overflows.
define i8 @test_scalar_ssub_nneg_nneg(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_nneg_nneg(
; CHECK-NEXT:    [[A_NNEG:%.*]] = and i8 [[A:%.*]], 127
; CHECK-NEXT:    [[R:%.*]] = add nsw i8 [[A_NNEG]], -10
; CHECK-NEXT:    ret i8 [[R]]
;
  %a_nneg = and i8 %a, 127
  %r = call i8 @llvm.ssub.sat.i8(i8 %a_nneg, i8 10)
  ret i8 %r
}

define <2 x i8> @test_vector_ssub_nneg_nneg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_ssub_nneg_nneg(
; CHECK-NEXT:    [[A_NNEG:%.*]] = and <2 x i8> [[A:%.*]], <i8 127, i8 127>
; CHECK-NEXT:    [[R:%.*]] = add nsw <2 x i8> [[A_NNEG]], <i8 -10, i8 -20>
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %a_nneg = and <2 x i8> %a, <i8 127, i8 127>
  %r = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a_nneg, <2 x i8> <i8 10, i8 20>)
  ret <2 x i8> %r
}

; neg ssub nneg may overflow.
define i8 @test_scalar_ssub_neg_nneg(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_neg_nneg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or i8 [[A:%.*]], -128
; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A_NEG]], i8 -10)
; CHECK-NEXT:    ret i8 [[TMP1]]
;
  %a_neg = or i8 %a, -128
  %r = call i8 @llvm.ssub.sat.i8(i8 %a_neg, i8 10)
  ret i8 %r
}

define <2 x i8> @test_vector_ssub_neg_nneg(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_ssub_neg_nneg(
; CHECK-NEXT:    [[A_NEG:%.*]] = or <2 x i8> [[A:%.*]], <i8 -128, i8 -128>
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> [[A_NEG]], <2 x i8> <i8 -10, i8 -20>)
; CHECK-NEXT:    ret <2 x i8> [[TMP1]]
;
  %a_neg = or <2 x i8> %a, <i8 -128, i8 -128>
  %r = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a_neg, <2 x i8> <i8 10, i8 20>)
  ret <2 x i8> %r
}

define i8 @test_scalar_ssub_always_overflows_low(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_always_overflows_low(
; CHECK-NEXT:    ret i8 -128
;
  %cmp = icmp sgt i8 %a, 120
  %max = select i1 %cmp, i8 %a, i8 120
  %r = call i8 @llvm.ssub.sat.i8(i8 -10, i8 %max)
  ret i8 %r
}

define i8 @test_scalar_ssub_always_overflows_high(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_always_overflows_high(
; CHECK-NEXT:    ret i8 127
;
  %cmp = icmp slt i8 %a, -120
  %min = select i1 %cmp, i8 %a, i8 -120
  %r = call i8 @llvm.ssub.sat.i8(i8 10, i8 %min)
  ret i8 %r
}

define i8 @test_scalar_usub_add_nuw_no_ov(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_add_nuw_no_ov(
; CHECK-NEXT:    [[R:%.*]] = add i8 [[A:%.*]], 1
; CHECK-NEXT:    ret i8 [[R]]
;
  %b = add nuw i8 %a, 10
  %r = call i8 @llvm.usub.sat.i8(i8 %b, i8 9)
  ret i8 %r
}

define i8 @test_scalar_usub_add_nuw_eq(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_add_nuw_eq(
; CHECK-NEXT:    ret i8 [[A:%.*]]
;
  %b = add nuw i8 %a, 10
  %r = call i8 @llvm.usub.sat.i8(i8 %b, i8 10)
  ret i8 %r
}

define i8 @test_scalar_usub_add_nuw_may_ov(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_add_nuw_may_ov(
; CHECK-NEXT:    [[B:%.*]] = add nuw i8 [[A:%.*]], 10
; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.usub.sat.i8(i8 [[B]], i8 11)
; CHECK-NEXT:    ret i8 [[R]]
;
  %b = add nuw i8 %a, 10
  %r = call i8 @llvm.usub.sat.i8(i8 %b, i8 11)
  ret i8 %r
}

define i8 @test_scalar_usub_urem_must_ov(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_urem_must_ov(
; CHECK-NEXT:    ret i8 0
;
  %b = urem i8 %a, 10
  %r = call i8 @llvm.usub.sat.i8(i8 %b, i8 10)
  ret i8 %r
}

; Like the previous case, the result is always zero here. However, as there's
; no actual overflow, we won't know about it.
define i8 @test_scalar_usub_urem_must_zero(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_urem_must_zero(
; CHECK-NEXT:    [[B:%.*]] = urem i8 [[A:%.*]], 10
; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.usub.sat.i8(i8 [[B]], i8 9)
; CHECK-NEXT:    ret i8 [[R]]
;
  %b = urem i8 %a, 10
  %r = call i8 @llvm.usub.sat.i8(i8 %b, i8 9)
  ret i8 %r
}

; We have a constant range for the LHS, but only known bits for the RHS
define i8 @test_scalar_usub_add_nuw_known_bits(i8 %a, i8 %b) {
; CHECK-LABEL: @test_scalar_usub_add_nuw_known_bits(
; CHECK-NEXT:    [[AA:%.*]] = add nuw i8 [[A:%.*]], 10
; CHECK-NEXT:    [[BB:%.*]] = and i8 [[B:%.*]], 7
; CHECK-NEXT:    [[R:%.*]] = sub nuw i8 [[AA]], [[BB]]
; CHECK-NEXT:    ret i8 [[R]]
;
  %aa = add nuw i8 %a, 10
  %bb = and i8 %b, 7
  %r = call i8 @llvm.usub.sat.i8(i8 %aa, i8 %bb)
  ret i8 %r
}

define i8 @test_scalar_usub_add_nuw_inferred(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_add_nuw_inferred(
; CHECK-NEXT:    [[B:%.*]] = call i8 @llvm.usub.sat.i8(i8 [[A:%.*]], i8 10)
; CHECK-NEXT:    [[R:%.*]] = add nuw i8 [[B]], 9
; CHECK-NEXT:    ret i8 [[R]]
;
  %b = call i8 @llvm.usub.sat.i8(i8 %a, i8 10)
  %r = add i8 %b, 9
  ret i8 %r
}

define <2 x i8> @test_vector_usub_add_nuw_no_ov(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_add_nuw_no_ov(
; CHECK-NEXT:    [[R:%.*]] = add <2 x i8> [[A:%.*]], <i8 1, i8 1>
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %b = add nuw <2 x i8> %a, <i8 10, i8 10>
  %r = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %b, <2 x i8> <i8 9, i8 9>)
  ret <2 x i8> %r
}

; Can be optimized if the usub.sat RHS constant range handles non-splat vectors.
define <2 x i8> @test_vector_usub_add_nuw_no_ov_nonsplat1(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_add_nuw_no_ov_nonsplat1(
; CHECK-NEXT:    [[B:%.*]] = add nuw <2 x i8> [[A:%.*]], <i8 10, i8 10>
; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> [[B]], <2 x i8> <i8 10, i8 9>)
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %b = add nuw <2 x i8> %a, <i8 10, i8 10>
  %r = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %b, <2 x i8> <i8 10, i8 9>)
  ret <2 x i8> %r
}

; Can be optimized if the add nuw RHS constant range handles non-splat vectors.
define <2 x i8> @test_vector_usub_add_nuw_no_ov_nonsplat2(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_add_nuw_no_ov_nonsplat2(
; CHECK-NEXT:    [[B:%.*]] = add nuw <2 x i8> [[A:%.*]], <i8 10, i8 9>
; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> [[B]], <2 x i8> <i8 9, i8 9>)
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %b = add nuw <2 x i8> %a, <i8 10, i8 9>
  %r = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %b, <2 x i8> <i8 9, i8 9>)
  ret <2 x i8> %r
}

; Can be optimized if constant range is tracked per-element.
define <2 x i8> @test_vector_usub_add_nuw_no_ov_nonsplat3(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_usub_add_nuw_no_ov_nonsplat3(
; CHECK-NEXT:    [[B:%.*]] = add nuw <2 x i8> [[A:%.*]], <i8 10, i8 9>
; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> [[B]], <2 x i8> <i8 10, i8 9>)
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %b = add nuw <2 x i8> %a, <i8 10, i8 9>
  %r = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %b, <2 x i8> <i8 10, i8 9>)
  ret <2 x i8> %r
}

define i8 @test_scalar_ssub_add_nsw_no_ov(i8 %a, i8 %b) {
; CHECK-LABEL: @test_scalar_ssub_add_nsw_no_ov(
; CHECK-NEXT:    [[AA:%.*]] = add nsw i8 [[A:%.*]], 7
; CHECK-NEXT:    [[BB:%.*]] = and i8 [[B:%.*]], 7
; CHECK-NEXT:    [[R:%.*]] = sub nsw i8 [[AA]], [[BB]]
; CHECK-NEXT:    ret i8 [[R]]
;
  %aa = add nsw i8 %a, 7
  %bb = and i8 %b, 7
  %r = call i8 @llvm.ssub.sat.i8(i8 %aa, i8 %bb)
  ret i8 %r
}

define i8 @test_scalar_ssub_add_nsw_may_ov(i8 %a, i8 %b) {
; CHECK-LABEL: @test_scalar_ssub_add_nsw_may_ov(
; CHECK-NEXT:    [[AA:%.*]] = add nsw i8 [[A:%.*]], 6
; CHECK-NEXT:    [[BB:%.*]] = and i8 [[B:%.*]], 7
; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.ssub.sat.i8(i8 [[AA]], i8 [[BB]])
; CHECK-NEXT:    ret i8 [[R]]
;
  %aa = add nsw i8 %a, 6
  %bb = and i8 %b, 7
  %r = call i8 @llvm.ssub.sat.i8(i8 %aa, i8 %bb)
  ret i8 %r
}

define <2 x i8> @test_vector_ssub_add_nsw_no_ov_splat(<2 x i8> %a, <2 x i8> %b) {
; CHECK-LABEL: @test_vector_ssub_add_nsw_no_ov_splat(
; CHECK-NEXT:    [[AA:%.*]] = add nsw <2 x i8> [[A:%.*]], <i8 7, i8 7>
; CHECK-NEXT:    [[BB:%.*]] = and <2 x i8> [[B:%.*]], <i8 7, i8 7>
; CHECK-NEXT:    [[R:%.*]] = sub nsw <2 x i8> [[AA]], [[BB]]
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %aa = add nsw <2 x i8> %a, <i8 7, i8 7>
  %bb = and <2 x i8> %b, <i8 7, i8 7>
  %r = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %aa, <2 x i8> %bb)
  ret <2 x i8> %r
}

define <2 x i8> @test_vector_ssub_add_nsw_no_ov_nonsplat1(<2 x i8> %a, <2 x i8> %b) {
; CHECK-LABEL: @test_vector_ssub_add_nsw_no_ov_nonsplat1(
; CHECK-NEXT:    [[AA:%.*]] = add nsw <2 x i8> [[A:%.*]], <i8 7, i8 7>
; CHECK-NEXT:    [[BB:%.*]] = and <2 x i8> [[B:%.*]], <i8 7, i8 6>
; CHECK-NEXT:    [[R:%.*]] = sub nsw <2 x i8> [[AA]], [[BB]]
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %aa = add nsw <2 x i8> %a, <i8 7, i8 7>
  %bb = and <2 x i8> %b, <i8 7, i8 6>
  %r = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %aa, <2 x i8> %bb)
  ret <2 x i8> %r
}

define <2 x i8> @test_vector_ssub_add_nsw_no_ov_nonsplat2(<2 x i8> %a, <2 x i8> %b) {
; CHECK-LABEL: @test_vector_ssub_add_nsw_no_ov_nonsplat2(
; CHECK-NEXT:    [[AA:%.*]] = add nsw <2 x i8> [[A:%.*]], <i8 7, i8 8>
; CHECK-NEXT:    [[BB:%.*]] = and <2 x i8> [[B:%.*]], <i8 7, i8 7>
; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> [[AA]], <2 x i8> [[BB]])
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %aa = add nsw <2 x i8> %a, <i8 7, i8 8>
  %bb = and <2 x i8> %b, <i8 7, i8 7>
  %r = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %aa, <2 x i8> %bb)
  ret <2 x i8> %r
}

define <2 x i8> @test_vector_ssub_add_nsw_no_ov_nonsplat3(<2 x i8> %a, <2 x i8> %b) {
; CHECK-LABEL: @test_vector_ssub_add_nsw_no_ov_nonsplat3(
; CHECK-NEXT:    [[AA:%.*]] = add nsw <2 x i8> [[A:%.*]], <i8 7, i8 6>
; CHECK-NEXT:    [[BB:%.*]] = and <2 x i8> [[B:%.*]], <i8 7, i8 6>
; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> [[AA]], <2 x i8> [[BB]])
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %aa = add nsw <2 x i8> %a, <i8 7, i8 6>
  %bb = and <2 x i8> %b, <i8 7, i8 6>
  %r = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %aa, <2 x i8> %bb)
  ret <2 x i8> %r
}

define i8 @test_scalar_usub_add(i8 %a, i8 %b) {
; CHECK-LABEL: @test_scalar_usub_add(
; CHECK-NEXT:    [[SAT:%.*]] = call i8 @llvm.usub.sat.i8(i8 [[A:%.*]], i8 [[B:%.*]])
; CHECK-NEXT:    [[RES:%.*]] = add i8 [[SAT]], [[B]]
; CHECK-NEXT:    ret i8 [[RES]]
;
  %sat = call i8 @llvm.usub.sat.i8(i8 %a, i8 %b)
  %res = add i8 %sat, %b
  ret i8 %res
}

define i8 @test_scalar_usub_add_extra_use(i8 %a, i8 %b, i8* %p) {
; CHECK-LABEL: @test_scalar_usub_add_extra_use(
; CHECK-NEXT:    [[SAT:%.*]] = call i8 @llvm.usub.sat.i8(i8 [[A:%.*]], i8 [[B:%.*]])
; CHECK-NEXT:    store i8 [[SAT]], i8* [[P:%.*]], align 1
; CHECK-NEXT:    [[RES:%.*]] = add i8 [[SAT]], [[B]]
; CHECK-NEXT:    ret i8 [[RES]]
;
  %sat = call i8 @llvm.usub.sat.i8(i8 %a, i8 %b)
  store i8 %sat, i8* %p
  %res = add i8 %sat, %b
  ret i8 %res
}

define i8 @test_scalar_usub_add_commuted(i8 %a, i8 %b) {
; CHECK-LABEL: @test_scalar_usub_add_commuted(
; CHECK-NEXT:    [[SAT:%.*]] = call i8 @llvm.usub.sat.i8(i8 [[A:%.*]], i8 [[B:%.*]])
; CHECK-NEXT:    [[RES:%.*]] = add i8 [[SAT]], [[B]]
; CHECK-NEXT:    ret i8 [[RES]]
;
  %sat = call i8 @llvm.usub.sat.i8(i8 %a, i8 %b)
  %res = add i8 %b, %sat
  ret i8 %res
}

define i8 @test_scalar_usub_add_commuted_wrong(i8 %a, i8 %b) {
; CHECK-LABEL: @test_scalar_usub_add_commuted_wrong(
; CHECK-NEXT:    [[SAT:%.*]] = call i8 @llvm.usub.sat.i8(i8 [[B:%.*]], i8 [[A:%.*]])
; CHECK-NEXT:    [[RES:%.*]] = add i8 [[SAT]], [[B]]
; CHECK-NEXT:    ret i8 [[RES]]
;
  %sat = call i8 @llvm.usub.sat.i8(i8 %b, i8 %a)
  %res = add i8 %sat, %b
  ret i8 %res
}

define i8 @test_scalar_usub_add_const(i8 %a) {
; CHECK-LABEL: @test_scalar_usub_add_const(
; CHECK-NEXT:    [[SAT:%.*]] = call i8 @llvm.usub.sat.i8(i8 [[A:%.*]], i8 42)
; CHECK-NEXT:    [[RES:%.*]] = add nuw i8 [[SAT]], 42
; CHECK-NEXT:    ret i8 [[RES]]
;
  %sat = call i8 @llvm.usub.sat.i8(i8 %a, i8 42)
  %res = add i8 %sat, 42
  ret i8 %res
}

define i8 @test_scalar_uadd_sub(i8 %a, i8 %b) {
; CHECK-LABEL: @test_scalar_uadd_sub(
; CHECK-NEXT:    [[SAT:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[A:%.*]], i8 [[B:%.*]])
; CHECK-NEXT:    [[RES:%.*]] = sub i8 [[SAT]], [[B]]
; CHECK-NEXT:    ret i8 [[RES]]
;
  %sat = call i8 @llvm.uadd.sat.i8(i8 %a, i8 %b)
  %res = sub i8 %sat, %b
  ret i8 %res
}

define i8 @test_scalar_uadd_sub_extra_use(i8 %a, i8 %b, i8* %p) {
; CHECK-LABEL: @test_scalar_uadd_sub_extra_use(
; CHECK-NEXT:    [[SAT:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[A:%.*]], i8 [[B:%.*]])
; CHECK-NEXT:    store i8 [[SAT]], i8* [[P:%.*]], align 1
; CHECK-NEXT:    [[RES:%.*]] = sub i8 [[SAT]], [[B]]
; CHECK-NEXT:    ret i8 [[RES]]
;
  %sat = call i8 @llvm.uadd.sat.i8(i8 %a, i8 %b)
  store i8 %sat, i8* %p
  %res = sub i8 %sat, %b
  ret i8 %res
}

define i8 @test_scalar_uadd_sub_commuted(i8 %a, i8 %b) {
; CHECK-LABEL: @test_scalar_uadd_sub_commuted(
; CHECK-NEXT:    [[SAT:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[B:%.*]], i8 [[A:%.*]])
; CHECK-NEXT:    [[RES:%.*]] = sub i8 [[SAT]], [[B]]
; CHECK-NEXT:    ret i8 [[RES]]
;
  %sat = call i8 @llvm.uadd.sat.i8(i8 %b, i8 %a)
  %res = sub i8 %sat, %b
  ret i8 %res
}

define i8 @test_scalar_uadd_sub_commuted_wrong(i8 %a, i8 %b) {
; CHECK-LABEL: @test_scalar_uadd_sub_commuted_wrong(
; CHECK-NEXT:    [[SAT:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[A:%.*]], i8 [[B:%.*]])
; CHECK-NEXT:    [[RES:%.*]] = sub i8 [[B]], [[SAT]]
; CHECK-NEXT:    ret i8 [[RES]]
;
  %sat = call i8 @llvm.uadd.sat.i8(i8 %a, i8 %b)
  %res = sub i8 %b, %sat
  ret i8 %res
}

define i8 @test_scalar_uadd_sub_const(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_sub_const(
; CHECK-NEXT:    [[SAT:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[A:%.*]], i8 42)
; CHECK-NEXT:    [[RES:%.*]] = add i8 [[SAT]], -42
; CHECK-NEXT:    ret i8 [[RES]]
;
  %sat = call i8 @llvm.uadd.sat.i8(i8 %a, i8 42)
  %res = sub i8 %sat, 42
  ret i8 %res
}

define i1 @scalar_uadd_eq_zero(i8 %a, i8 %b) {
; CHECK-LABEL: @scalar_uadd_eq_zero(
; CHECK-NEXT:    [[TMP1:%.*]] = or i8 [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i8 [[TMP1]], 0
; CHECK-NEXT:    ret i1 [[TMP2]]
;
  %sat = call i8 @llvm.uadd.sat.i8(i8 %a, i8 %b)
  %cmp = icmp eq i8 %sat, 0
  ret i1 %cmp
}

define i1 @scalar_uadd_ne_zero(i8 %a, i8 %b) {
; CHECK-LABEL: @scalar_uadd_ne_zero(
; CHECK-NEXT:    [[TMP1:%.*]] = or i8 [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = icmp ne i8 [[TMP1]], 0
; CHECK-NEXT:    ret i1 [[TMP2]]
;
  %sat = call i8 @llvm.uadd.sat.i8(i8 %a, i8 %b)
  %cmp = icmp ne i8 %sat, 0
  ret i1 %cmp
}

define i1 @scalar_usub_eq_zero(i8 %a, i8 %b) {
; CHECK-LABEL: @scalar_usub_eq_zero(
; CHECK-NEXT:    [[CMP:%.*]] = icmp ule i8 [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    ret i1 [[CMP]]
;
  %sat = call i8 @llvm.usub.sat.i8(i8 %a, i8 %b)
  %cmp = icmp eq i8 %sat, 0
  ret i1 %cmp
}

define i1 @scalar_usub_ne_zero(i8 %a, i8 %b) {
; CHECK-LABEL: @scalar_usub_ne_zero(
; CHECK-NEXT:    [[CMP:%.*]] = icmp ugt i8 [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    ret i1 [[CMP]]
;
  %sat = call i8 @llvm.usub.sat.i8(i8 %a, i8 %b)
  %cmp = icmp ne i8 %sat, 0
  ret i1 %cmp
}

; Raw IR tests

define i32 @uadd_sat(i32 %x, i32 %y) {
; CHECK-LABEL: @uadd_sat(
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[X:%.*]], i32 [[Y:%.*]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %notx = xor i32 %x, -1
  %a = add i32 %y, %x
  %c = icmp ult i32 %notx, %y
  %r = select i1 %c, i32 -1, i32 %a
  ret i32 %r
}

define i32 @uadd_sat_commute_add(i32 %xp, i32 %y) {
; CHECK-LABEL: @uadd_sat_commute_add(
; CHECK-NEXT:    [[X:%.*]] = urem i32 42, [[XP:%.*]]
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[X]], i32 [[Y:%.*]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %x = urem i32 42, %xp ; thwart complexity-based-canonicalization
  %notx = xor i32 %x, -1
  %a = add i32 %x, %y
  %c = icmp ult i32 %notx, %y
  %r = select i1 %c, i32 -1, i32 %a
  ret i32 %r
}

define i32 @uadd_sat_ugt(i32 %x, i32 %yp) {
; CHECK-LABEL: @uadd_sat_ugt(
; CHECK-NEXT:    [[Y:%.*]] = sdiv i32 [[YP:%.*]], 2442
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[X:%.*]], i32 [[Y]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %y = sdiv i32 %yp, 2442 ; thwart complexity-based-canonicalization
  %notx = xor i32 %x, -1
  %a = add i32 %y, %x
  %c = icmp ugt i32 %y, %notx
  %r = select i1 %c, i32 -1, i32 %a
  ret i32 %r
}

define <2 x i32> @uadd_sat_ugt_commute_add(<2 x i32> %xp, <2 x i32> %yp) {
; CHECK-LABEL: @uadd_sat_ugt_commute_add(
; CHECK-NEXT:    [[Y:%.*]] = sdiv <2 x i32> [[YP:%.*]], <i32 2442, i32 4242>
; CHECK-NEXT:    [[X:%.*]] = srem <2 x i32> <i32 42, i32 43>, [[XP:%.*]]
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> [[X]], <2 x i32> [[Y]])
; CHECK-NEXT:    ret <2 x i32> [[TMP1]]
;
  %y = sdiv <2 x i32> %yp, <i32 2442, i32 4242> ; thwart complexity-based-canonicalization
  %x = srem <2 x i32> <i32 42, i32 43>, %xp     ; thwart complexity-based-canonicalization
  %notx = xor <2 x i32> %x, <i32 -1, i32 -1>
  %a = add <2 x i32> %x, %y
  %c = icmp ugt <2 x i32> %y, %notx
  %r = select <2 x i1> %c, <2 x i32> <i32 -1, i32 -1>, <2 x i32> %a
  ret <2 x i32> %r
}

define i32 @uadd_sat_commute_select(i32 %x, i32 %yp) {
; CHECK-LABEL: @uadd_sat_commute_select(
; CHECK-NEXT:    [[Y:%.*]] = sdiv i32 [[YP:%.*]], 2442
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[X:%.*]], i32 [[Y]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %y = sdiv i32 %yp, 2442 ; thwart complexity-based-canonicalization
  %notx = xor i32 %x, -1
  %a = add i32 %y, %x
  %c = icmp ult i32 %y, %notx
  %r = select i1 %c, i32 %a, i32 -1
  ret i32 %r
}

define i32 @uadd_sat_commute_select_commute_add(i32 %xp, i32 %yp) {
; CHECK-LABEL: @uadd_sat_commute_select_commute_add(
; CHECK-NEXT:    [[X:%.*]] = urem i32 42, [[XP:%.*]]
; CHECK-NEXT:    [[Y:%.*]] = sdiv i32 [[YP:%.*]], 2442
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[X]], i32 [[Y]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %x = urem i32 42, %xp ; thwart complexity-based-canonicalization
  %y = sdiv i32 %yp, 2442 ; thwart complexity-based-canonicalization
  %notx = xor i32 %x, -1
  %a = add i32 %x, %y
  %c = icmp ult i32 %y, %notx
  %r = select i1 %c, i32 %a, i32 -1
  ret i32 %r
}

define <2 x i32> @uadd_sat_commute_select_ugt(<2 x i32> %x, <2 x i32> %y) {
; CHECK-LABEL: @uadd_sat_commute_select_ugt(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> [[X:%.*]], <2 x i32> [[Y:%.*]])
; CHECK-NEXT:    ret <2 x i32> [[TMP1]]
;
  %notx = xor <2 x i32> %x, <i32 -1, i32 -1>
  %a = add <2 x i32> %y, %x
  %c = icmp ugt <2 x i32> %notx, %y
  %r = select <2 x i1> %c, <2 x i32> %a, <2 x i32> <i32 -1, i32 -1>
  ret <2 x i32> %r
}

define i32 @uadd_sat_commute_select_ugt_commute_add(i32 %xp, i32 %y) {
; CHECK-LABEL: @uadd_sat_commute_select_ugt_commute_add(
; CHECK-NEXT:    [[X:%.*]] = srem i32 42, [[XP:%.*]]
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[X]], i32 [[Y:%.*]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %x = srem i32 42, %xp   ; thwart complexity-based-canonicalization
  %notx = xor i32 %x, -1
  %a = add i32 %x, %y
  %c = icmp ugt i32 %notx, %y
  %r = select i1 %c, i32 %a, i32 -1
  ret i32 %r
}

; Negative test - make sure we have a -1 in the select.

define i32 @not_uadd_sat(i32 %x, i32 %y) {
; CHECK-LABEL: @not_uadd_sat(
; CHECK-NEXT:    [[A:%.*]] = add i32 [[X:%.*]], -2
; CHECK-NEXT:    [[C:%.*]] = icmp ugt i32 [[X]], 1
; CHECK-NEXT:    [[R:%.*]] = select i1 [[C]], i32 [[A]], i32 [[Y:%.*]]
; CHECK-NEXT:    ret i32 [[R]]
;
  %a = add i32 %x, -2
  %c = icmp ugt i32 %x, 1
  %r = select i1 %c, i32 %a, i32 %y
  ret i32 %r
}

; Negative test - make sure the predicate is 'ult'.

define i32 @not_uadd_sat2(i32 %x, i32 %y) {
; CHECK-LABEL: @not_uadd_sat2(
; CHECK-NEXT:    [[A:%.*]] = add i32 [[X:%.*]], -2
; CHECK-NEXT:    [[C:%.*]] = icmp ugt i32 [[X]], 1
; CHECK-NEXT:    [[R:%.*]] = select i1 [[C]], i32 [[A]], i32 -1
; CHECK-NEXT:    ret i32 [[R]]
;
  %a = add i32 %x, -2
  %c = icmp ugt i32 %x, 1
  %r = select i1 %c, i32 %a, i32 -1
  ret i32 %r
}

; The add may include a 'not' op rather than the cmp.

define i32 @uadd_sat_not(i32 %x, i32 %y) {
; CHECK-LABEL: @uadd_sat_not(
; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X:%.*]], -1
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[NOTX]], i32 [[Y:%.*]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %notx = xor i32 %x, -1
  %a = add i32 %notx, %y
  %c = icmp ult i32 %x, %y
  %r = select i1 %c, i32 -1, i32 %a
  ret i32 %r
}

define i32 @uadd_sat_not_commute_add(i32 %xp, i32 %yp) {
; CHECK-LABEL: @uadd_sat_not_commute_add(
; CHECK-NEXT:    [[X:%.*]] = srem i32 42, [[XP:%.*]]
; CHECK-NEXT:    [[Y:%.*]] = urem i32 42, [[YP:%.*]]
; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X]], -1
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[Y]], i32 [[NOTX]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %x = srem i32 42, %xp ; thwart complexity-based-canonicalization
  %y = urem i32 42, %yp ; thwart complexity-based-canonicalization
  %notx = xor i32 %x, -1
  %a = add i32 %y, %notx
  %c = icmp ult i32 %x, %y
  %r = select i1 %c, i32 -1, i32 %a
  ret i32 %r
}

define i32 @uadd_sat_not_ugt(i32 %x, i32 %y) {
; CHECK-LABEL: @uadd_sat_not_ugt(
; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X:%.*]], -1
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[NOTX]], i32 [[Y:%.*]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %notx = xor i32 %x, -1
  %a = add i32 %notx, %y
  %c = icmp ugt i32 %y, %x
  %r = select i1 %c, i32 -1, i32 %a
  ret i32 %r
}

define <2 x i32> @uadd_sat_not_ugt_commute_add(<2 x i32> %x, <2 x i32> %yp) {
; CHECK-LABEL: @uadd_sat_not_ugt_commute_add(
; CHECK-NEXT:    [[Y:%.*]] = sdiv <2 x i32> [[YP:%.*]], <i32 2442, i32 4242>
; CHECK-NEXT:    [[NOTX:%.*]] = xor <2 x i32> [[X:%.*]], <i32 -1, i32 -1>
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> [[Y]], <2 x i32> [[NOTX]])
; CHECK-NEXT:    ret <2 x i32> [[TMP1]]
;
  %y = sdiv <2 x i32> %yp, <i32 2442, i32 4242> ; thwart complexity-based-canonicalization
  %notx = xor <2 x i32> %x, <i32 -1, i32 -1>
  %a = add <2 x i32> %y, %notx
  %c = icmp ugt <2 x i32> %y, %x
  %r = select <2 x i1> %c, <2 x i32> <i32 -1, i32 -1>, <2 x i32> %a
  ret <2 x i32> %r
}

define i32 @uadd_sat_not_commute_select(i32 %x, i32 %y) {
; CHECK-LABEL: @uadd_sat_not_commute_select(
; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X:%.*]], -1
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[NOTX]], i32 [[Y:%.*]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %notx = xor i32 %x, -1
  %a = add i32 %notx, %y
  %c = icmp ult i32 %y, %x
  %r = select i1 %c, i32 %a, i32 -1
  ret i32 %r
}

define i32 @uadd_sat_not_commute_select_commute_add(i32 %x, i32 %yp) {
; CHECK-LABEL: @uadd_sat_not_commute_select_commute_add(
; CHECK-NEXT:    [[Y:%.*]] = sdiv i32 42, [[YP:%.*]]
; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X:%.*]], -1
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[Y]], i32 [[NOTX]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %y = sdiv i32 42, %yp ; thwart complexity-based-canonicalization
  %notx = xor i32 %x, -1
  %a = add i32 %y, %notx
  %c = icmp ult i32 %y, %x
  %r = select i1 %c, i32 %a, i32 -1
  ret i32 %r
}

define <2 x i32> @uadd_sat_not_commute_select_ugt(<2 x i32> %xp, <2 x i32> %yp) {
; CHECK-LABEL: @uadd_sat_not_commute_select_ugt(
; CHECK-NEXT:    [[X:%.*]] = urem <2 x i32> <i32 42, i32 -42>, [[XP:%.*]]
; CHECK-NEXT:    [[Y:%.*]] = srem <2 x i32> <i32 12, i32 412>, [[YP:%.*]]
; CHECK-NEXT:    [[NOTX:%.*]] = xor <2 x i32> [[X]], <i32 -1, i32 -1>
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> [[Y]], <2 x i32> [[NOTX]])
; CHECK-NEXT:    ret <2 x i32> [[TMP1]]
;
  %x = urem <2 x i32> <i32 42, i32 -42>, %xp ; thwart complexity-based-canonicalization
  %y = srem <2 x i32> <i32 12, i32 412>, %yp ; thwart complexity-based-canonicalization
  %notx = xor <2 x i32> %x, <i32 -1, i32 -1>
  %a = add <2 x i32> %y, %notx
  %c = icmp ugt <2 x i32> %x, %y
  %r = select <2 x i1> %c, <2 x i32> %a, <2 x i32> <i32 -1, i32 -1>
  ret <2 x i32> %r
}

define i32 @uadd_sat_not_commute_select_ugt_commute_add(i32 %x, i32 %y) {
; CHECK-LABEL: @uadd_sat_not_commute_select_ugt_commute_add(
; CHECK-NEXT:    [[NOTX:%.*]] = xor i32 [[X:%.*]], -1
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[NOTX]], i32 [[Y:%.*]])
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %notx = xor i32 %x, -1
  %a = add i32 %notx, %y
  %c = icmp ugt i32 %x, %y
  %r = select i1 %c, i32 %a, i32 -1
  ret i32 %r
}

define i32 @uadd_sat_constant(i32 %x) {
; CHECK-LABEL: @uadd_sat_constant(
; CHECK-NEXT:    [[A:%.*]] = add i32 [[X:%.*]], 42
; CHECK-NEXT:    [[C:%.*]] = icmp ugt i32 [[X]], -43
; CHECK-NEXT:    [[R:%.*]] = select i1 [[C]], i32 -1, i32 [[A]]
; CHECK-NEXT:    ret i32 [[R]]
;
  %a = add i32 %x, 42
  %c = icmp ugt i32 %x, -43
  %r = select i1 %c, i32 -1, i32 %a
  ret i32 %r
}

define i32 @uadd_sat_constant_commute(i32 %x) {
; CHECK-LABEL: @uadd_sat_constant_commute(
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[X:%.*]], i32 42)
; CHECK-NEXT:    ret i32 [[TMP1]]
;
  %a = add i32 %x, 42
  %c = icmp ult i32 %x, -43
  %r = select i1 %c, i32 %a, i32 -1
  ret i32 %r
}

define <4 x i32> @uadd_sat_constant_vec(<4 x i32> %x) {
; CHECK-LABEL: @uadd_sat_constant_vec(
; CHECK-NEXT:    [[A:%.*]] = add <4 x i32> [[X:%.*]], <i32 42, i32 42, i32 42, i32 42>
; CHECK-NEXT:    [[C:%.*]] = icmp ugt <4 x i32> [[X]], <i32 -43, i32 -43, i32 -43, i32 -43>
; CHECK-NEXT:    [[R:%.*]] = select <4 x i1> [[C]], <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, <4 x i32> [[A]]
; CHECK-NEXT:    ret <4 x i32> [[R]]
;
  %a = add <4 x i32> %x, <i32 42, i32 42, i32 42, i32 42>
  %c = icmp ugt <4 x i32> %x, <i32 -43, i32 -43, i32 -43, i32 -43>
  %r = select <4 x i1> %c, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, <4 x i32> %a
  ret <4 x i32> %r
}

define <4 x i32> @uadd_sat_constant_vec_commute(<4 x i32> %x) {
; CHECK-LABEL: @uadd_sat_constant_vec_commute(
; CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> [[X:%.*]], <4 x i32> <i32 42, i32 42, i32 42, i32 42>)
; CHECK-NEXT:    ret <4 x i32> [[TMP1]]
;
  %a = add <4 x i32> %x, <i32 42, i32 42, i32 42, i32 42>
  %c = icmp ult <4 x i32> %x, <i32 -43, i32 -43, i32 -43, i32 -43>
  %r = select <4 x i1> %c, <4 x i32> %a, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
  ret <4 x i32> %r
}

define <4 x i32> @uadd_sat_constant_vec_commute_undefs(<4 x i32> %x) {
; CHECK-LABEL: @uadd_sat_constant_vec_commute_undefs(
; CHECK-NEXT:    [[A:%.*]] = add <4 x i32> [[X:%.*]], <i32 42, i32 42, i32 42, i32 undef>
; CHECK-NEXT:    [[C:%.*]] = icmp ult <4 x i32> [[X]], <i32 -43, i32 -43, i32 undef, i32 -43>
; CHECK-NEXT:    [[R:%.*]] = select <4 x i1> [[C]], <4 x i32> [[A]], <4 x i32> <i32 -1, i32 undef, i32 -1, i32 -1>
; CHECK-NEXT:    ret <4 x i32> [[R]]
;
  %a = add <4 x i32> %x, <i32 42, i32 42, i32 42, i32 undef>
  %c = icmp ult <4 x i32> %x, <i32 -43, i32 -43, i32 undef, i32 -43>
  %r = select <4 x i1> %c, <4 x i32> %a, <4 x i32> <i32 -1, i32 undef, i32 -1, i32 -1>
  ret <4 x i32> %r
}

declare i32 @get_i32()
declare <2 x i8> @get_v2i8()

define i32 @unsigned_sat_variable_using_min_add(i32 %x) {
; CHECK-LABEL: @unsigned_sat_variable_using_min_add(
; CHECK-NEXT:    [[Y:%.*]] = call i32 @get_i32()
; CHECK-NEXT:    [[R:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[X:%.*]], i32 [[Y]])
; CHECK-NEXT:    ret i32 [[R]]
;
  %y = call i32 @get_i32() ; thwart complexity-based canonicalization
  %noty = xor i32 %y, -1
  %c = icmp ult i32 %x, %noty
  %s = select i1 %c, i32 %x, i32 %noty
  %r = add i32 %s, %y
  ret i32 %r
}

define i32 @unsigned_sat_variable_using_min_commute_add(i32 %x) {
; CHECK-LABEL: @unsigned_sat_variable_using_min_commute_add(
; CHECK-NEXT:    [[Y:%.*]] = call i32 @get_i32()
; CHECK-NEXT:    [[R:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[X:%.*]], i32 [[Y]])
; CHECK-NEXT:    ret i32 [[R]]
;
  %y = call i32 @get_i32() ; thwart complexity-based canonicalization
  %noty = xor i32 %y, -1
  %c = icmp ult i32 %x, %noty
  %s = select i1 %c, i32 %x, i32 %noty
  %r = add i32 %y, %s
  ret i32 %r
}

define <2 x i8> @unsigned_sat_variable_using_min_commute_select(<2 x i8> %x) {
; CHECK-LABEL: @unsigned_sat_variable_using_min_commute_select(
; CHECK-NEXT:    [[Y:%.*]] = call <2 x i8> @get_v2i8()
; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> [[X:%.*]], <2 x i8> [[Y]])
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %y = call <2 x i8> @get_v2i8() ; thwart complexity-based canonicalization
  %noty = xor <2 x i8> %y, <i8 -1, i8 -1>
  %c = icmp ult <2 x i8> %noty, %x
  %s = select <2 x i1> %c, <2 x i8> %noty, <2 x i8> %x
  %r = add <2 x i8> %s, %y
  ret <2 x i8> %r
}

define <2 x i8> @unsigned_sat_variable_using_min_commute_add_select(<2 x i8> %x) {
; CHECK-LABEL: @unsigned_sat_variable_using_min_commute_add_select(
; CHECK-NEXT:    [[Y:%.*]] = call <2 x i8> @get_v2i8()
; CHECK-NEXT:    [[R:%.*]] = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> [[X:%.*]], <2 x i8> [[Y]])
; CHECK-NEXT:    ret <2 x i8> [[R]]
;
  %y = call <2 x i8> @get_v2i8() ; thwart complexity-based canonicalization
  %noty = xor <2 x i8> %y, <i8 -1, i8 -1>
  %c = icmp ult <2 x i8> %noty, %x
  %s = select <2 x i1> %c, <2 x i8> %noty, <2 x i8> %x
  %r = add <2 x i8> %y, %s
  ret <2 x i8> %r
}

; Negative test

define i32 @unsigned_sat_variable_using_wrong_min(i32 %x) {
; CHECK-LABEL: @unsigned_sat_variable_using_wrong_min(
; CHECK-NEXT:    [[Y:%.*]] = call i32 @get_i32()
; CHECK-NEXT:    [[NOTY:%.*]] = xor i32 [[Y]], -1
; CHECK-NEXT:    [[C:%.*]] = icmp sgt i32 [[NOTY]], [[X:%.*]]
; CHECK-NEXT:    [[S:%.*]] = select i1 [[C]], i32 [[X]], i32 [[NOTY]]
; CHECK-NEXT:    [[R:%.*]] = add i32 [[Y]], [[S]]
; CHECK-NEXT:    ret i32 [[R]]
;
  %y = call i32 @get_i32() ; thwart complexity-based canonicalization
  %noty = xor i32 %y, -1
  %c = icmp slt i32 %x, %noty
  %s = select i1 %c, i32 %x, i32 %noty
  %r = add i32 %y, %s
  ret i32 %r
}

; Negative test

define i32 @unsigned_sat_variable_using_wrong_value(i32 %x, i32 %z) {
; CHECK-LABEL: @unsigned_sat_variable_using_wrong_value(
; CHECK-NEXT:    [[Y:%.*]] = call i32 @get_i32()
; CHECK-NEXT:    [[NOTY:%.*]] = xor i32 [[Y]], -1
; CHECK-NEXT:    [[C:%.*]] = icmp ugt i32 [[NOTY]], [[X:%.*]]
; CHECK-NEXT:    [[S:%.*]] = select i1 [[C]], i32 [[X]], i32 [[NOTY]]
; CHECK-NEXT:    [[R:%.*]] = add i32 [[S]], [[Z:%.*]]
; CHECK-NEXT:    ret i32 [[R]]
;
  %y = call i32 @get_i32() ; thwart complexity-based canonicalization
  %noty = xor i32 %y, -1
  %c = icmp ult i32 %x, %noty
  %s = select i1 %c, i32 %x, i32 %noty
  %r = add i32 %z, %s
  ret i32 %r
}

; If we have a constant operand, there's no commutativity variation.

define i32 @unsigned_sat_constant_using_min(i32 %x) {
; CHECK-LABEL: @unsigned_sat_constant_using_min(
; CHECK-NEXT:    [[R:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[X:%.*]], i32 -43)
; CHECK-NEXT:    ret i32 [[R]]
;
  %c = icmp ult i32 %x, 42
  %s = select i1 %c, i32 %x, i32 42
  %r = add i32 %s, -43
  ret i32 %r
}

define <2 x i32> @unsigned_sat_constant_using_min_splat(<2 x i32> %x) {
; CHECK-LABEL: @unsigned_sat_constant_using_min_splat(
; CHECK-NEXT:    [[R:%.*]] = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> [[X:%.*]], <2 x i32> <i32 -15, i32 -15>)
; CHECK-NEXT:    ret <2 x i32> [[R]]
;
  %c = icmp ult <2 x i32> %x, <i32 14, i32 14>
  %s = select <2 x i1> %c, <2 x i32> %x, <2 x i32> <i32 14, i32 14>
  %r = add <2 x i32> %s, <i32 -15, i32 -15>
  ret <2 x i32> %r
}

; Negative test

define i32 @unsigned_sat_constant_using_min_wrong_constant(i32 %x) {
; CHECK-LABEL: @unsigned_sat_constant_using_min_wrong_constant(
; CHECK-NEXT:    [[C:%.*]] = icmp ult i32 [[X:%.*]], 42
; CHECK-NEXT:    [[S:%.*]] = select i1 [[C]], i32 [[X]], i32 42
; CHECK-NEXT:    [[R:%.*]] = add nsw i32 [[S]], -42
; CHECK-NEXT:    ret i32 [[R]]
;
  %c = icmp ult i32 %x, 42
  %s = select i1 %c, i32 %x, i32 42
  %r = add i32 %s, -42
  ret i32 %r
}