diff --git a/lib/builtins/CMakeLists.txt b/lib/builtins/CMakeLists.txt
index 168f3e9..a58bd37 100644
--- a/lib/builtins/CMakeLists.txt
+++ b/lib/builtins/CMakeLists.txt
@@ -94,6 +94,7 @@
   floatunsisf.c
   floatuntidf.c
   floatuntisf.c
+  fp_mode.c
   int_util.c
   lshrdi3.c
   lshrti3.c
@@ -290,6 +291,7 @@
 set(i686_SOURCES ${i686_SOURCES} ${x86_ARCH_SOURCES})
 
 set(arm_SOURCES
+  arm/fp_mode.c
   arm/bswapdi2.S
   arm/bswapsi2.S
   arm/clzdi2.S
@@ -441,7 +443,8 @@
 
 set(aarch64_SOURCES
   ${GENERIC_TF_SOURCES}
-  ${GENERIC_SOURCES})
+  ${GENERIC_SOURCES}
+  aarch64/fp_mode.c)
 
 if (MINGW)
   set(aarch64_SOURCES
diff --git a/lib/builtins/aarch64/fp_mode.c b/lib/builtins/aarch64/fp_mode.c
new file mode 100644
index 0000000..aa81fbc
--- /dev/null
+++ b/lib/builtins/aarch64/fp_mode.c
@@ -0,0 +1,53 @@
+//===----- lib/aarch64/fp_mode.c - Floaing-point mode utilities ---*- C -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include <stdint.h>
+
+#include "../fp_mode.h"
+
+#define AARCH64_TONEAREST  0x0
+#define AARCH64_UPWARD     0x1
+#define AARCH64_DOWNWARD   0x2
+#define AARCH64_TOWARDZERO 0x3
+#define AARCH64_RMODE_MASK (AARCH64_TONEAREST | AARCH64_UPWARD | \
+                            AARCH64_DOWNWARD | AARCH64_TOWARDZERO)
+#define AARCH64_RMODE_SHIFT 22
+
+#define AARCH64_INEXACT     0x10
+
+FE_ROUND_MODE __fe_getround() {
+#ifdef __ARM_FP
+  uint64_t fpcr;
+  __asm__ __volatile__("mrs  %0, fpcr" : "=r" (fpcr));
+  fpcr = fpcr >> AARCH64_RMODE_SHIFT & AARCH64_RMODE_MASK;
+  switch (fpcr) {
+    case AARCH64_UPWARD:
+      return FE_UPWARD;
+    case AARCH64_DOWNWARD:
+      return FE_DOWNWARD;
+    case AARCH64_TOWARDZERO:
+      return FE_TOWARDZERO;
+    case AARCH64_TONEAREST:
+    default:
+      return FE_TONEAREST;
+  }
+#else
+  return FE_TONEAREST;
+#endif
+}
+
+int __fe_raise_inexact() {
+#ifdef __ARM_FP
+  uint64_t fpsr;
+  __asm__ __volatile__("mrs  %0, fpsr" : "=r" (fpsr));
+  __asm__ __volatile__("msr  fpsr, %0" : : "ri" (fpsr | AARCH64_INEXACT));
+  return 0;
+#else
+  return 0;
+#endif
+}
diff --git a/lib/builtins/adddf3.c b/lib/builtins/adddf3.c
index 9a39013..f616192 100644
--- a/lib/builtins/adddf3.c
+++ b/lib/builtins/adddf3.c
@@ -7,8 +7,7 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file implements double-precision soft-float addition with the IEEE-754
-// default rounding (to nearest, ties to even).
+// This file implements double-precision soft-float addition.
 //
 //===----------------------------------------------------------------------===//
 
diff --git a/lib/builtins/addsf3.c b/lib/builtins/addsf3.c
index c5c1a41..af92223 100644
--- a/lib/builtins/addsf3.c
+++ b/lib/builtins/addsf3.c
@@ -7,8 +7,7 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file implements single-precision soft-float addition with the IEEE-754
-// default rounding (to nearest, ties to even).
+// This file implements single-precision soft-float addition.
 //
 //===----------------------------------------------------------------------===//
 
diff --git a/lib/builtins/addtf3.c b/lib/builtins/addtf3.c
index e4bbe02..8e21da6 100644
--- a/lib/builtins/addtf3.c
+++ b/lib/builtins/addtf3.c
@@ -7,8 +7,7 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file implements quad-precision soft-float addition with the IEEE-754
-// default rounding (to nearest, ties to even).
+// This file implements quad-precision soft-float addition.
 //
 //===----------------------------------------------------------------------===//
 
diff --git a/lib/builtins/arm/fp_mode.c b/lib/builtins/arm/fp_mode.c
new file mode 100644
index 0000000..8fecee8
--- /dev/null
+++ b/lib/builtins/arm/fp_mode.c
@@ -0,0 +1,53 @@
+//===----- lib/arm/fp_mode.c - Floaing-point mode utilities -------*- C -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include <stdint.h>
+
+#include "../fp_mode.h"
+
+#define ARM_TONEAREST  0x0
+#define ARM_UPWARD     0x1
+#define ARM_DOWNWARD   0x2
+#define ARM_TOWARDZERO 0x3
+#define ARM_RMODE_MASK (ARM_TONEAREST | ARM_UPWARD | \
+                        ARM_DOWNWARD | ARM_TOWARDZERO)
+#define ARM_RMODE_SHIFT 22
+
+#define ARM_INEXACT     0x1000
+
+FE_ROUND_MODE __fe_getround() {
+#ifdef __ARM_FP
+  uint32_t fpscr;
+  __asm__ __volatile__("vmrs  %0, fpscr" : "=r" (fpscr));
+  fpscr = fpscr >> ARM_RMODE_SHIFT & ARM_RMODE_MASK;
+  switch (fpscr) {
+    case ARM_UPWARD:
+      return FE_UPWARD;
+    case ARM_DOWNWARD:
+      return FE_DOWNWARD;
+    case ARM_TOWARDZERO:
+      return FE_TOWARDZERO;
+    case ARM_TONEAREST:
+    default:
+      return FE_TONEAREST;
+  }
+#else
+  return FE_TONEAREST;
+#endif
+}
+
+int __fe_raise_inexact() {
+#ifdef __ARM_FP
+  uint32_t fpscr;
+  __asm__ __volatile__("vmrs  %0, fpscr" : "=r" (fpscr));
+  __asm__ __volatile__("vmsr  fpscr, %0" : : "ri" (fpscr | ARM_INEXACT));
+  return 0;
+#else
+  return 0;
+#endif
+}
diff --git a/lib/builtins/fp_add_impl.inc b/lib/builtins/fp_add_impl.inc
index b47be1b..5d006dc 100644
--- a/lib/builtins/fp_add_impl.inc
+++ b/lib/builtins/fp_add_impl.inc
@@ -13,6 +13,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "fp_lib.h"
+#include "fp_mode.h"
 
 static __inline fp_t __addXf3__(fp_t a, fp_t b) {
     rep_t aRep = toRep(a);
@@ -138,7 +139,21 @@
 
     // Final rounding.  The result may overflow to infinity, but that is the
     // correct result in that case.
-    if (roundGuardSticky > 0x4) result++;
-    if (roundGuardSticky == 0x4) result += result & 1;
+    switch (__fe_getround()){
+    case FE_TONEAREST:
+      if (roundGuardSticky > 0x4) result++;
+      if (roundGuardSticky == 0x4) result += result & 1;
+      break;
+    case FE_DOWNWARD:
+      if (resultSign && roundGuardSticky) result++;
+      break;
+    case FE_UPWARD:
+      if (!resultSign && roundGuardSticky) result++;
+      break;
+    case FE_TOWARDZERO:
+      break;
+    }
+    if (roundGuardSticky)
+      __fe_raise_inexact();
     return fromRep(result);
 }
diff --git a/lib/builtins/fp_mode.c b/lib/builtins/fp_mode.c
new file mode 100644
index 0000000..9b82830
--- /dev/null
+++ b/lib/builtins/fp_mode.c
@@ -0,0 +1,24 @@
+//===----- lib/fp_mode.c - Floaing-point environment mode utilities --C -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file provides a default implementaion of fp_mode.h for architectures
+// that does not support or does not have an implementation of floating point
+// environment mode.
+//
+//===----------------------------------------------------------------------===//
+
+#include "fp_mode.h"
+
+// IEEE-754 default rounding (to nearest, ties to even).
+FE_ROUND_MODE __fe_getround() {
+  return FE_TONEAREST;
+}
+
+int __fe_raise_inexact() {
+  return 0;
+}
diff --git a/lib/builtins/fp_mode.h b/lib/builtins/fp_mode.h
new file mode 100644
index 0000000..51bec04
--- /dev/null
+++ b/lib/builtins/fp_mode.h
@@ -0,0 +1,29 @@
+//===----- lib/fp_mode.h - Floaing-point environment mode utilities --C -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file is not part of the interface of this library.
+//
+// This file defines an interface for accessing hardware floating point
+// environment mode.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef FP_MODE
+#define FP_MODE
+
+typedef enum {
+  FE_TONEAREST,
+  FE_DOWNWARD,
+  FE_UPWARD,
+  FE_TOWARDZERO
+} FE_ROUND_MODE;
+
+FE_ROUND_MODE __fe_getround();
+int __fe_raise_inexact();
+
+#endif // FP_MODE_H
diff --git a/lib/builtins/subdf3.c b/lib/builtins/subdf3.c
index a892fa6..72b3b1a 100644
--- a/lib/builtins/subdf3.c
+++ b/lib/builtins/subdf3.c
@@ -7,8 +7,7 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file implements double-precision soft-float subtraction with the
-// IEEE-754 default rounding (to nearest, ties to even).
+// This file implements double-precision soft-float subtraction.
 //
 //===----------------------------------------------------------------------===//
 
diff --git a/lib/builtins/subsf3.c b/lib/builtins/subsf3.c
index 4b27861..9974f21 100644
--- a/lib/builtins/subsf3.c
+++ b/lib/builtins/subsf3.c
@@ -7,8 +7,7 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file implements single-precision soft-float subtraction with the
-// IEEE-754 default rounding (to nearest, ties to even).
+// This file implements single-precision soft-float subtraction.
 //
 //===----------------------------------------------------------------------===//
 
diff --git a/lib/builtins/subtf3.c b/lib/builtins/subtf3.c
index 609b816..22871cb 100644
--- a/lib/builtins/subtf3.c
+++ b/lib/builtins/subtf3.c
@@ -7,8 +7,7 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// This file implements quad-precision soft-float subtraction with the
-// IEEE-754 default rounding (to nearest, ties to even).
+// This file implements quad-precision soft-float subtraction.
 //
 //===----------------------------------------------------------------------===//
 
diff --git a/test/builtins/Unit/addtf3_test.c b/test/builtins/Unit/addtf3_test.c
index 57a4729..afbca12 100644
--- a/test/builtins/Unit/addtf3_test.c
+++ b/test/builtins/Unit/addtf3_test.c
@@ -12,11 +12,12 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "int_lib.h"
+#include <fenv.h>
 #include <stdio.h>
 
 #if __LDBL_MANT_DIG__ == 113
 
+#include "int_lib.h"
 #include "fp_test.h"
 
 // Returns: a + b
@@ -75,6 +76,26 @@
                      UINT64_C(0x61e58dd6c51eb77c)))
         return 1;
 
+#if (defined(__arm__) || defined(__aarch64__)) && defined(__ARM_FP)
+    // Rounding mode tests on supported architectures
+    long double m = 1234.0L, n = 0.01L;
+    fesetround(FE_UPWARD);
+    if (__addtf3(m, n) != 1235.0L)
+        return 1;
+
+    fesetround(FE_DOWNWARD);
+    if (__addtf3(m, n) != 1234.0L)
+        return 1;
+
+    fesetround(FE_TOWARDZERO);
+    if (__addtf3(m, n) != 1234.0L)
+        return 1;
+
+    fesetround(FE_TONEAREST);
+    if (__addtf3(m, n) != 1234.0L)
+        return 1;
+#endif
+
 #else
     printf("skipped\n");
 
diff --git a/test/builtins/Unit/subtf3_test.c b/test/builtins/Unit/subtf3_test.c
index 771242b..96afd57 100644
--- a/test/builtins/Unit/subtf3_test.c
+++ b/test/builtins/Unit/subtf3_test.c
@@ -12,6 +12,7 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include <fenv.h>
 #include <stdio.h>
 
 #if __LDBL_MANT_DIG__ == 113
@@ -68,6 +69,26 @@
                      UINT64_C(0xa44a7bca780a166c)))
         return 1;
 
+#if (defined(__arm__) || defined(__aarch64__)) && defined(__ARM_FP)
+    // Rounding mode tests on supported architectures
+    long double m = 1234.0L, n = 0.01L;
+    fesetround(FE_UPWARD);
+    if (__subtf3(m, n) != 1234.0L)
+        return 1;
+
+    fesetround(FE_DOWNWARD);
+    if (__subtf3(m, n) != 1233.0L)
+        return 1;
+
+    fesetround(FE_TOWARDZERO);
+    if (__subtf3(m, n) != 1233.0L)
+        return 1;
+
+    fesetround(FE_TONEAREST);
+    if (__subtf3(m, n) != 1234.0L)
+        return 1;
+#endif
+
 #else
     printf("skipped\n");