diff --git a/clang/include/clang/Basic/Builtins.def b/clang/include/clang/Basic/Builtins.def
--- a/clang/include/clang/Basic/Builtins.def
+++ b/clang/include/clang/Basic/Builtins.def
@@ -647,6 +647,9 @@
 BUILTIN(__builtin_elementwise_max, "v.", "nct")
 BUILTIN(__builtin_elementwise_min, "v.", "nct")
 BUILTIN(__builtin_elementwise_ceil, "v.", "nct")
+BUILTIN(__builtin_elementwise_floor, "v.", "nct")
+BUILTIN(__builtin_elementwise_roundeven, "v.", "nct")
+BUILTIN(__builtin_elementwise_trunc, "v.", "nct")
 BUILTIN(__builtin_reduce_max, "v.", "nct")
 BUILTIN(__builtin_reduce_min, "v.", "nct")
 BUILTIN(__builtin_reduce_xor, "v.", "nct")
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -3140,6 +3140,15 @@
   case Builtin::BI__builtin_elementwise_ceil:
     return RValue::get(
         emitUnaryBuiltin(*this, E, llvm::Intrinsic::ceil, "elt.ceil"));
+  case Builtin::BI__builtin_elementwise_floor:
+    return RValue::get(
+        emitUnaryBuiltin(*this, E, llvm::Intrinsic::floor, "elt.floor"));
+  case Builtin::BI__builtin_elementwise_roundeven:
+    return RValue::get(emitUnaryBuiltin(*this, E, llvm::Intrinsic::roundeven,
+                                        "elt.roundeven"));
+  case Builtin::BI__builtin_elementwise_trunc:
+    return RValue::get(
+        emitUnaryBuiltin(*this, E, llvm::Intrinsic::trunc, "elt.trunc"));
 
   case Builtin::BI__builtin_elementwise_max: {
     Value *Op0 = EmitScalarExpr(E->getArg(0));
diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
--- a/clang/lib/Sema/SemaChecking.cpp
+++ b/clang/lib/Sema/SemaChecking.cpp
@@ -2189,9 +2189,12 @@
     break;
   }
 
-  // __builtin_elementwise_ceil restricts the element type to floating point
+  // These builtins restrict the element type to floating point
   // types only.
-  case Builtin::BI__builtin_elementwise_ceil: {
+  case Builtin::BI__builtin_elementwise_ceil:
+  case Builtin::BI__builtin_elementwise_floor:
+  case Builtin::BI__builtin_elementwise_roundeven:
+  case Builtin::BI__builtin_elementwise_trunc: {
     if (PrepareBuiltinElementwiseMathOneArgCall(TheCall))
       return ExprError();
 
diff --git a/clang/test/CodeGen/builtins-elementwise-math.c b/clang/test/CodeGen/builtins-elementwise-math.c
--- a/clang/test/CodeGen/builtins-elementwise-math.c
+++ b/clang/test/CodeGen/builtins-elementwise-math.c
@@ -205,3 +205,51 @@
   // CHECK-NEXT: call <4 x float> @llvm.ceil.v4f32(<4 x float> [[VF1]])
   vf2 = __builtin_elementwise_ceil(vf1);
 }
+
+void test_builtin_elementwise_floor(float f1, float f2, double d1, double d2,
+                                    float4 vf1, float4 vf2) {
+  // CHECK-LABEL: define void @test_builtin_elementwise_floor(
+  // CHECK:      [[F1:%.+]] = load float, float* %f1.addr, align 4
+  // CHECK-NEXT:  call float @llvm.floor.f32(float [[F1]])
+  f2 = __builtin_elementwise_floor(f1);
+
+  // CHECK:      [[D1:%.+]] = load double, double* %d1.addr, align 8
+  // CHECK-NEXT: call double @llvm.floor.f64(double [[D1]])
+  d2 = __builtin_elementwise_floor(d1);
+
+  // CHECK:      [[VF1:%.+]] = load <4 x float>, <4 x float>* %vf1.addr, align 16
+  // CHECK-NEXT: call <4 x float> @llvm.floor.v4f32(<4 x float> [[VF1]])
+  vf2 = __builtin_elementwise_floor(vf1);
+}
+
+void test_builtin_elementwise_roundeven(float f1, float f2, double d1, double d2,
+                                        float4 vf1, float4 vf2) {
+  // CHECK-LABEL: define void @test_builtin_elementwise_roundeven(
+  // CHECK:      [[F1:%.+]] = load float, float* %f1.addr, align 4
+  // CHECK-NEXT:  call float @llvm.roundeven.f32(float [[F1]])
+  f2 = __builtin_elementwise_roundeven(f1);
+
+  // CHECK:      [[D1:%.+]] = load double, double* %d1.addr, align 8
+  // CHECK-NEXT: call double @llvm.roundeven.f64(double [[D1]])
+  d2 = __builtin_elementwise_roundeven(d1);
+
+  // CHECK:      [[VF1:%.+]] = load <4 x float>, <4 x float>* %vf1.addr, align 16
+  // CHECK-NEXT: call <4 x float> @llvm.roundeven.v4f32(<4 x float> [[VF1]])
+  vf2 = __builtin_elementwise_roundeven(vf1);
+}
+
+void test_builtin_elementwise_trunc(float f1, float f2, double d1, double d2,
+                                    float4 vf1, float4 vf2) {
+  // CHECK-LABEL: define void @test_builtin_elementwise_trunc(
+  // CHECK:      [[F1:%.+]] = load float, float* %f1.addr, align 4
+  // CHECK-NEXT:  call float @llvm.trunc.f32(float [[F1]])
+  f2 = __builtin_elementwise_trunc(f1);
+
+  // CHECK:      [[D1:%.+]] = load double, double* %d1.addr, align 8
+  // CHECK-NEXT: call double @llvm.trunc.f64(double [[D1]])
+  d2 = __builtin_elementwise_trunc(d1);
+
+  // CHECK:      [[VF1:%.+]] = load <4 x float>, <4 x float>* %vf1.addr, align 16
+  // CHECK-NEXT: call <4 x float> @llvm.trunc.v4f32(<4 x float> [[VF1]])
+  vf2 = __builtin_elementwise_trunc(vf1);
+}
diff --git a/clang/test/Sema/builtins-elementwise-math.c b/clang/test/Sema/builtins-elementwise-math.c
--- a/clang/test/Sema/builtins-elementwise-math.c
+++ b/clang/test/Sema/builtins-elementwise-math.c
@@ -156,3 +156,66 @@
   uv = __builtin_elementwise_ceil(uv);
   // expected-error@-1 {{1st argument must be a floating point type (was 'unsigned4' (vector of 4 'unsigned int' values))}}
 }
+
+void test_builtin_elementwise_floor(int i, float f, double d, float4 v, int3 iv, unsigned u, unsigned4 uv) {
+
+  struct Foo s = __builtin_elementwise_floor(f);
+  // expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'float'}}
+
+  i = __builtin_elementwise_floor();
+  // expected-error@-1 {{too few arguments to function call, expected 1, have 0}}
+
+  i = __builtin_elementwise_floor(i);
+  // expected-error@-1 {{1st argument must be a floating point type (was 'int')}}
+
+  i = __builtin_elementwise_floor(f, f);
+  // expected-error@-1 {{too many arguments to function call, expected 1, have 2}}
+
+  u = __builtin_elementwise_floor(u);
+  // expected-error@-1 {{1st argument must be a floating point type (was 'unsigned int')}}
+
+  uv = __builtin_elementwise_floor(uv);
+  // expected-error@-1 {{1st argument must be a floating point type (was 'unsigned4' (vector of 4 'unsigned int' values))}}
+}
+
+void test_builtin_elementwise_roundeven(int i, float f, double d, float4 v, int3 iv, unsigned u, unsigned4 uv) {
+
+  struct Foo s = __builtin_elementwise_roundeven(f);
+  // expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'float'}}
+
+  i = __builtin_elementwise_roundeven();
+  // expected-error@-1 {{too few arguments to function call, expected 1, have 0}}
+
+  i = __builtin_elementwise_roundeven(i);
+  // expected-error@-1 {{1st argument must be a floating point type (was 'int')}}
+
+  i = __builtin_elementwise_roundeven(f, f);
+  // expected-error@-1 {{too many arguments to function call, expected 1, have 2}}
+
+  u = __builtin_elementwise_roundeven(u);
+  // expected-error@-1 {{1st argument must be a floating point type (was 'unsigned int')}}
+
+  uv = __builtin_elementwise_roundeven(uv);
+  // expected-error@-1 {{1st argument must be a floating point type (was 'unsigned4' (vector of 4 'unsigned int' values))}}
+}
+
+void test_builtin_elementwise_trunc(int i, float f, double d, float4 v, int3 iv, unsigned u, unsigned4 uv) {
+
+  struct Foo s = __builtin_elementwise_trunc(f);
+  // expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'float'}}
+
+  i = __builtin_elementwise_trunc();
+  // expected-error@-1 {{too few arguments to function call, expected 1, have 0}}
+
+  i = __builtin_elementwise_trunc(i);
+  // expected-error@-1 {{1st argument must be a floating point type (was 'int')}}
+
+  i = __builtin_elementwise_trunc(f, f);
+  // expected-error@-1 {{too many arguments to function call, expected 1, have 2}}
+
+  u = __builtin_elementwise_trunc(u);
+  // expected-error@-1 {{1st argument must be a floating point type (was 'unsigned int')}}
+
+  uv = __builtin_elementwise_trunc(uv);
+  // expected-error@-1 {{1st argument must be a floating point type (was 'unsigned4' (vector of 4 'unsigned int' values))}}
+}