diff --git a/clang/lib/CodeGen/CGExprScalar.cpp b/clang/lib/CodeGen/CGExprScalar.cpp
--- a/clang/lib/CodeGen/CGExprScalar.cpp
+++ b/clang/lib/CodeGen/CGExprScalar.cpp
@@ -732,6 +732,7 @@
           BO->getLHS()->getType().getCanonicalType());
       auto *RHSMatTy = dyn_cast<ConstantMatrixType>(
           BO->getRHS()->getType().getCanonicalType());
+      CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, Ops.FPFeatures);
       if (LHSMatTy && RHSMatTy)
         return MB.CreateMatrixMultiply(Ops.LHS, Ops.RHS, LHSMatTy->getNumRows(),
                                        LHSMatTy->getNumColumns(),
@@ -3206,6 +3207,7 @@
         "first operand must be a matrix");
     assert(BO->getRHS()->getType().getCanonicalType()->isArithmeticType() &&
            "second operand must be an arithmetic type");
+    CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, Ops.FPFeatures);
     return MB.CreateScalarDiv(Ops.LHS, Ops.RHS,
                               Ops.Ty->hasUnsignedIntegerRepresentation());
   }
@@ -3585,6 +3587,7 @@
 
   if (op.Ty->isConstantMatrixType()) {
     llvm::MatrixBuilder<CGBuilderTy> MB(Builder);
+    CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, op.FPFeatures);
     return MB.CreateAdd(op.LHS, op.RHS);
   }
 
@@ -3734,6 +3737,7 @@
 
     if (op.Ty->isConstantMatrixType()) {
       llvm::MatrixBuilder<CGBuilderTy> MB(Builder);
+      CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, op.FPFeatures);
       return MB.CreateSub(op.LHS, op.RHS);
     }
 
diff --git a/clang/test/CodeGen/fp-matrix-pragma.c b/clang/test/CodeGen/fp-matrix-pragma.c
new file mode 100644
--- /dev/null
+++ b/clang/test/CodeGen/fp-matrix-pragma.c
@@ -0,0 +1,26 @@
+// RUN: %clang_cc1 -emit-llvm -S -fenable-matrix --target=arm64-unknown-iphoneos -g0 -mllvm -disable-llvm-optzns -o - | FileCheck %s
+
+typedef float fx2x2_t __attribute__((matrix_type(2, 2)));
+typedef int ix2x2_t __attribute__((matrix_type(2, 2)));
+
+fx2x2_t fp_matrix_contract(fx2x2_t a, fx2x2_t b, float c, float d) {
+// CHECK: call contract <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32
+// CHECK: fdiv contract <4 x float>
+// CHECK: fmul contract <4 x float>
+#pragma clang fp contract(fast)
+  return (a * b / c) * d;
+}
+
+fx2x2_t fp_matrix_reassoc(fx2x2_t a, fx2x2_t b, fx2x2_t c) {
+// CHECK: fadd reassoc <4 x float>
+// CHECK: fsub reassoc <4 x float>
+#pragma clang fp reassociate(on)
+  return a + b - c;
+}
+
+ix2x2_t int_matrix_ops(ix2x2_t a, ix2x2_t b, ix2x2_t c) {
+// CHECK: call <4 x i32> @llvm.matrix.multiply.v4i32.v4i32.v4i32
+// CHECK: add <4 x i32>
+#pragma clang fp contract(fast) reassociate(on)
+  return a * b + c;
+}