Index: lib/Analysis/InstructionSimplify.cpp
===================================================================
--- lib/Analysis/InstructionSimplify.cpp
+++ lib/Analysis/InstructionSimplify.cpp
@@ -4890,6 +4890,35 @@
     if (match(Op0, m_Undef()) || match(Op1, m_Undef()))
       return Constant::getNullValue(ReturnType);
     break;
+  case Intrinsic::uadd_sat:
+    // sat(X + MAX) -> MAX
+    if (match(Op1, m_AllOnes()))
+      return Constant::getAllOnesValue(ReturnType);
+    // sat(MAX + X) -> MAX
+    if (match(Op0, m_AllOnes()))
+      return Constant::getAllOnesValue(ReturnType);
+    LLVM_FALLTHROUGH;
+  case Intrinsic::sadd_sat:
+    // X + 0 -> X, X + undef -> X
+    if (match(Op1, m_Zero()) || match(Op1, m_Undef()))
+      return Op0;
+    // 0 + X -> X, undef + X -> X
+    if (match(Op0, m_Zero()) || match(Op0, m_Undef()))
+      return Op1;
+    break;
+  case Intrinsic::usub_sat:
+    // sat(0 - X) -> 0, sat(X - MAX) -> 0
+    if (match(Op0, m_Zero()) || match(Op1, m_AllOnes()))
+      return Constant::getNullValue(ReturnType);
+    LLVM_FALLTHROUGH;
+  case Intrinsic::ssub_sat:
+    // X - X -> 0, X - undef -> 0, undef - X -> 0
+    if (Op0 == Op1 || match(Op0, m_Undef()) || match(Op1, m_Undef()))
+      return Constant::getNullValue(ReturnType);
+    // X - 0 -> X
+    if (match(Op1, m_Zero()))
+      return Op0;
+    break;
   case Intrinsic::load_relative:
     if (auto *C0 = dyn_cast<Constant>(Op0))
       if (auto *C1 = dyn_cast<Constant>(Op1))
Index: test/Transforms/InstSimplify/saturating-add-sub.ll
===================================================================
--- /dev/null
+++ test/Transforms/InstSimplify/saturating-add-sub.ll
@@ -0,0 +1,182 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -instsimplify -S | FileCheck %s
+
+declare void @dummy(i8)
+declare void @dummy_vec(<2 x i8>)
+
+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>)
+
+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>)
+
+define void @test_add_scalar(i8 %a) {
+; CHECK-LABEL: @test_add_scalar(
+; CHECK-NEXT:    call void @dummy(i8 [[A:%.*]])
+; CHECK-NEXT:    call void @dummy(i8 [[A]])
+; CHECK-NEXT:    call void @dummy(i8 -1)
+; CHECK-NEXT:    call void @dummy(i8 [[A]])
+; CHECK-NEXT:    call void @dummy(i8 [[A]])
+; CHECK-NEXT:    call void @dummy(i8 [[A]])
+; CHECK-NEXT:    call void @dummy(i8 [[A]])
+; CHECK-NEXT:    [[Y3:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[A]], i8 127)
+; CHECK-NEXT:    call void @dummy(i8 [[Y3]])
+; CHECK-NEXT:    call void @dummy(i8 [[A]])
+; CHECK-NEXT:    call void @dummy(i8 [[A]])
+; CHECK-NEXT:    ret void
+;
+  %x1 = call i8 @llvm.uadd.sat.i8(i8 %a, i8 0)
+  call void @dummy(i8 %x1)
+  %x2 = call i8 @llvm.uadd.sat.i8(i8 0, i8 %a)
+  call void @dummy(i8 %x2)
+  %x3 = call i8 @llvm.uadd.sat.i8(i8 %a, i8 255)
+  call void @dummy(i8 %x3)
+  %x4 = call i8 @llvm.uadd.sat.i8(i8 %a, i8 undef)
+  call void @dummy(i8 %x4)
+  %x5 = call i8 @llvm.uadd.sat.i8(i8 undef, i8 %a)
+  call void @dummy(i8 %x5)
+
+  %y1 = call i8 @llvm.sadd.sat.i8(i8 %a, i8 0)
+  call void @dummy(i8 %y1)
+  %y2 = call i8 @llvm.sadd.sat.i8(i8 0, i8 %a)
+  call void @dummy(i8 %y2)
+  %y3 = call i8 @llvm.sadd.sat.i8(i8 %a, i8 127)
+  call void @dummy(i8 %y3)
+  %y4 = call i8 @llvm.sadd.sat.i8(i8 %a, i8 undef)
+  call void @dummy(i8 %y4)
+  %y5 = call i8 @llvm.sadd.sat.i8(i8 undef, i8 %a)
+  call void @dummy(i8 %y5)
+
+  ret void
+}
+
+define void @test_add_vector(<2 x i8> %a) {
+; CHECK-LABEL: @test_add_vector(
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> [[A:%.*]])
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> <i8 -1, i8 -1>)
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> [[A]])
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> <i8 -1, i8 -1>)
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> [[A]])
+; CHECK-NEXT:    [[Y2:%.*]] = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> [[A]], <2 x i8> <i8 127, i8 127>)
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> [[Y2]])
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> [[A]])
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> [[A]])
+; CHECK-NEXT:    ret void
+;
+  %x1 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 0, i8 0>)
+  call void @dummy_vec(<2 x i8> %x1)
+  %x2 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 255, i8 255>)
+  call void @dummy_vec(<2 x i8> %x2)
+  %x3 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 0, i8 undef>)
+  call void @dummy_vec(<2 x i8> %x3)
+  %x4 = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 undef, i8 undef>)
+  call void @dummy_vec(<2 x i8> %x4)
+
+  %y1 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 0, i8 0>)
+  call void @dummy_vec(<2 x i8> %y1)
+  %y2 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 127, i8 127>)
+  call void @dummy_vec(<2 x i8> %y2)
+  %y3 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 0, i8 undef>)
+  call void @dummy_vec(<2 x i8> %y3)
+  %y4 = call <2 x i8> @llvm.sadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 undef, i8 undef>)
+  call void @dummy_vec(<2 x i8> %y4)
+
+  ret void
+}
+
+define void @test_sub_scalar(i8 %a) {
+; CHECK-LABEL: @test_sub_scalar(
+; CHECK-NEXT:    call void @dummy(i8 [[A:%.*]])
+; CHECK-NEXT:    call void @dummy(i8 0)
+; CHECK-NEXT:    call void @dummy(i8 0)
+; CHECK-NEXT:    call void @dummy(i8 0)
+; CHECK-NEXT:    call void @dummy(i8 0)
+; CHECK-NEXT:    call void @dummy(i8 0)
+; CHECK-NEXT:    call void @dummy(i8 [[A]])
+; CHECK-NEXT:    [[Y2:%.*]] = call i8 @llvm.ssub.sat.i8(i8 0, i8 [[A]])
+; CHECK-NEXT:    call void @dummy(i8 [[Y2]])
+; CHECK-NEXT:    [[Y3:%.*]] = call i8 @llvm.ssub.sat.i8(i8 [[A]], i8 127)
+; CHECK-NEXT:    call void @dummy(i8 [[Y3]])
+; CHECK-NEXT:    call void @dummy(i8 0)
+; CHECK-NEXT:    call void @dummy(i8 0)
+; CHECK-NEXT:    call void @dummy(i8 0)
+; CHECK-NEXT:    ret void
+;
+  %x1 = call i8 @llvm.usub.sat.i8(i8 %a, i8 0)
+  call void @dummy(i8 %x1)
+  %x2 = call i8 @llvm.usub.sat.i8(i8 0, i8 %a)
+  call void @dummy(i8 %x2)
+  %x3 = call i8 @llvm.usub.sat.i8(i8 %a, i8 255)
+  call void @dummy(i8 %x3)
+  %x4 = call i8 @llvm.usub.sat.i8(i8 %a, i8 undef)
+  call void @dummy(i8 %x4)
+  %x5 = call i8 @llvm.usub.sat.i8(i8 undef, i8 %a)
+  call void @dummy(i8 %x5)
+  %x6 = call i8 @llvm.usub.sat.i8(i8 %a, i8 %a)
+  call void @dummy(i8 %x6)
+
+  %y1 = call i8 @llvm.ssub.sat.i8(i8 %a, i8 0)
+  call void @dummy(i8 %y1)
+  %y2 = call i8 @llvm.ssub.sat.i8(i8 0, i8 %a)
+  call void @dummy(i8 %y2)
+  %y3 = call i8 @llvm.ssub.sat.i8(i8 %a, i8 127)
+  call void @dummy(i8 %y3)
+  %y4 = call i8 @llvm.ssub.sat.i8(i8 %a, i8 undef)
+  call void @dummy(i8 %y4)
+  %y5 = call i8 @llvm.ssub.sat.i8(i8 undef, i8 %a)
+  call void @dummy(i8 %y5)
+  %y6 = call i8 @llvm.ssub.sat.i8(i8 %a, i8 %a)
+  call void @dummy(i8 %y6)
+
+  ret void
+}
+
+define void @test_sub_vector(<2 x i8> %a) {
+; CHECK-LABEL: @test_sub_vector(
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> [[A:%.*]])
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> zeroinitializer)
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> zeroinitializer)
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> [[A]])
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> zeroinitializer)
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> zeroinitializer)
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> [[A]])
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> zeroinitializer)
+; CHECK-NEXT:    [[Y3:%.*]] = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> [[A]], <2 x i8> <i8 127, i8 127>)
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> [[Y3]])
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> [[A]])
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> zeroinitializer)
+; CHECK-NEXT:    call void @dummy_vec(<2 x i8> zeroinitializer)
+; CHECK-NEXT:    ret void
+;
+  %x1 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 0, i8 0>)
+  call void @dummy_vec(<2 x i8> %x1)
+  %x2 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> <i8 0, i8 0>, <2 x i8> %a)
+  call void @dummy_vec(<2 x i8> %x2)
+  %x3 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 255, i8 255>)
+  call void @dummy_vec(<2 x i8> %x3)
+  %x4 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 0, i8 undef>)
+  call void @dummy_vec(<2 x i8> %x4)
+  %x5 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 undef, i8 undef>)
+  call void @dummy_vec(<2 x i8> %x5)
+  %x6 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> %a, <2 x i8> %a)
+  call void @dummy_vec(<2 x i8> %x6)
+
+  %y1 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 0, i8 0>)
+  call void @dummy_vec(<2 x i8> %y1)
+  %y2 = call <2 x i8> @llvm.usub.sat.v2i8(<2 x i8> <i8 0, i8 0>, <2 x i8> %a)
+  call void @dummy_vec(<2 x i8> %y2)
+  %y3 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 127, i8 127>)
+  call void @dummy_vec(<2 x i8> %y3)
+  %y4 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 0, i8 undef>)
+  call void @dummy_vec(<2 x i8> %y4)
+  %y5 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 undef, i8 undef>)
+  call void @dummy_vec(<2 x i8> %y5)
+  %y6 = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %a, <2 x i8> %a)
+  call void @dummy_vec(<2 x i8> %y6)
+
+  ret void
+}