diff --git a/clang/include/clang/AST/Stmt.h b/clang/include/clang/AST/Stmt.h
--- a/clang/include/clang/AST/Stmt.h
+++ b/clang/include/clang/AST/Stmt.h
@@ -1458,6 +1458,15 @@
     return *getTrailingObjects<FPOptionsOverride>();
   }
 
+  /// Get FPOptions inside this statement. They may differ from outer options
+  /// due to pragmas.
+  /// \param CurFPOptions FPOptions outside this statement.
+  FPOptions getNewFPOptions(FPOptions CurFPOptions) const {
+    return hasStoredFPFeatures()
+               ? getStoredFPFeatures().applyOverrides(CurFPOptions)
+               : CurFPOptions;
+  }
+
   using body_iterator = Stmt **;
   using body_range = llvm::iterator_range<body_iterator>;
 
diff --git a/clang/lib/CodeGen/CGStmt.cpp b/clang/lib/CodeGen/CGStmt.cpp
--- a/clang/lib/CodeGen/CGStmt.cpp
+++ b/clang/lib/CodeGen/CGStmt.cpp
@@ -491,6 +491,8 @@
   assert((!GetLast || (GetLast && ExprResult)) &&
          "If GetLast is true then the CompoundStmt must have a StmtExprResult");
 
+  CGFPOptionsRAII SavedFPFeatues(*this, S.getNewFPOptions(CurFPFeatures));
+
   Address RetAlloca = Address::invalid();
 
   for (auto *CurStmt : S.body()) {
diff --git a/clang/lib/Sema/SemaTemplateInstantiateDecl.cpp b/clang/lib/Sema/SemaTemplateInstantiateDecl.cpp
--- a/clang/lib/Sema/SemaTemplateInstantiateDecl.cpp
+++ b/clang/lib/Sema/SemaTemplateInstantiateDecl.cpp
@@ -5051,6 +5051,9 @@
     // PushDeclContext because we don't have a scope.
     Sema::ContextRAII savedContext(*this, Function);
 
+    FPFeaturesStateRAII SavedFPFeatures(*this);
+    CurFPFeatures = FPOptions(getLangOpts());
+
     if (addInstantiatedParametersToScope(Function, PatternDecl, Scope,
                                          TemplateArgs))
       return;
diff --git a/clang/test/CodeGen/X86/avx512dq-builtins-constrained.c b/clang/test/CodeGen/X86/avx512dq-builtins-constrained.c
--- a/clang/test/CodeGen/X86/avx512dq-builtins-constrained.c
+++ b/clang/test/CodeGen/X86/avx512dq-builtins-constrained.c
@@ -4,7 +4,6 @@
 // RUN: %clang_cc1 -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +avx512dq -S -o - -Wall -Werror | FileCheck %s --check-prefix=CHECK-ASM --check-prefix=COMMON
 // RUN: %clang_cc1 -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +avx512dq -ffp-exception-behavior=maytrap -DSTRICT=1 -S -o - -Wall -Werror | FileCheck %s --check-prefix=CHECK-ASM --check-prefix=COMMON
 
-// FIXME: Every instance of "fpexcept.maytrap" is wrong.
 #ifdef STRICT
 // Test that the constrained intrinsics are picking up the exception
 // metadata from the AST instead of the global default from the command line.
@@ -18,7 +17,7 @@
 __m512d test_mm512_cvtepi64_pd(__m512i __A) {
   // COMMON-LABEL: test_mm512_cvtepi64_pd
   // UNCONSTRAINED: sitofp <8 x i64> %{{.*}} to <8 x double>
-  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.sitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.sitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.strict")
   // CHECK-ASM: vcvtqq2pd
   return _mm512_cvtepi64_pd(__A);
 }
@@ -26,7 +25,7 @@
 __m512d test_mm512_mask_cvtepi64_pd(__m512d __W, __mmask8 __U, __m512i __A) {
   // COMMON-LABEL: test_mm512_mask_cvtepi64_pd
   // UNCONSTRAINED: sitofp <8 x i64> %{{.*}} to <8 x double>
-  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.sitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.sitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.strict")
   // COMMONIR: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}}
   // CHECK-ASM: vcvtqq2pd
   return _mm512_mask_cvtepi64_pd(__W, __U, __A);
@@ -35,7 +34,7 @@
 __m512d test_mm512_maskz_cvtepi64_pd(__mmask8 __U, __m512i __A) {
   // COMMON-LABEL: test_mm512_maskz_cvtepi64_pd
   // UNCONSTRAINED: sitofp <8 x i64> %{{.*}} to <8 x double>
-  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.sitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.sitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.strict")
   // COMMONIR: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}}
   // CHECK-ASM: vcvtqq2pd
   return _mm512_maskz_cvtepi64_pd(__U, __A);
@@ -148,7 +147,7 @@
 __m512d test_mm512_cvtepu64_pd(__m512i __A) {
   // COMMON-LABEL: test_mm512_cvtepu64_pd
   // UNCONSTRAINED: uitofp <8 x i64> %{{.*}} to <8 x double>
-  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.uitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.uitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.strict")
   // CHECK-ASM: vcvtuqq2pd
   return _mm512_cvtepu64_pd(__A);
 }
@@ -156,7 +155,7 @@
 __m512d test_mm512_mask_cvtepu64_pd(__m512d __W, __mmask8 __U, __m512i __A) {
   // COMMON-LABEL: test_mm512_mask_cvtepu64_pd
   // UNCONSTRAINED: uitofp <8 x i64> %{{.*}} to <8 x double>
-  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.uitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.uitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.strict")
   // COMMONIR: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}}
   // CHECK-ASM: vcvtuqq2pd
   return _mm512_mask_cvtepu64_pd(__W, __U, __A);
@@ -165,7 +164,7 @@
 __m512d test_mm512_maskz_cvtepu64_pd(__mmask8 __U, __m512i __A) {
   // COMMON-LABEL: test_mm512_maskz_cvtepu64_pd
   // UNCONSTRAINED: uitofp <8 x i64> %{{.*}} to <8 x double>
-  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.uitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+  // CONSTRAINED: call <8 x double> @llvm.experimental.constrained.uitofp.v8f64.v8i64(<8 x i64> %{{.*}}, metadata !"round.tonearest", metadata !"fpexcept.strict")
   // COMMONIR: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}}
   // CHECK-ASM: vcvtuqq2pd
   return _mm512_maskz_cvtepu64_pd(__U, __A);
diff --git a/clang/test/CodeGen/aarch64-v8.2a-neon-intrinsics-constrained.c b/clang/test/CodeGen/aarch64-v8.2a-neon-intrinsics-constrained.c
--- a/clang/test/CodeGen/aarch64-v8.2a-neon-intrinsics-constrained.c
+++ b/clang/test/CodeGen/aarch64-v8.2a-neon-intrinsics-constrained.c
@@ -23,7 +23,6 @@
 
 // Test that the constrained intrinsics are picking up the exception
 // metadata from the AST instead of the global default from the command line.
-// FIXME: All cases of "fpexcept.maytrap" in this test are wrong.
 
 #if EXCEPT
 #pragma float_control(except, on)
@@ -33,7 +32,7 @@
 
 // COMMON-LABEL: test_vsqrt_f16
 // UNCONSTRAINED:  [[SQR:%.*]] = call <4 x half> @llvm.sqrt.v4f16(<4 x half> %a)
-// CONSTRAINED:    [[SQR:%.*]] = call <4 x half> @llvm.experimental.constrained.sqrt.v4f16(<4 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:    [[SQR:%.*]] = call <4 x half> @llvm.experimental.constrained.sqrt.v4f16(<4 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:      fsqrt v{{[0-9]+}}.4h, v{{[0-9]+}}.4h
 // COMMONIR:       ret <4 x half> [[SQR]]
 float16x4_t test_vsqrt_f16(float16x4_t a) {
@@ -42,7 +41,7 @@
 
 // COMMON-LABEL: test_vsqrtq_f16
 // UNCONSTRAINED:  [[SQR:%.*]] = call <8 x half> @llvm.sqrt.v8f16(<8 x half> %a)
-// CONSTRAINED:    [[SQR:%.*]] = call <8 x half> @llvm.experimental.constrained.sqrt.v8f16(<8 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:    [[SQR:%.*]] = call <8 x half> @llvm.experimental.constrained.sqrt.v8f16(<8 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:      fsqrt v{{[0-9]+}}.8h, v{{[0-9]+}}.8h
 // COMMONIR:       ret <8 x half> [[SQR]]
 float16x8_t test_vsqrtq_f16(float16x8_t a) {
@@ -51,7 +50,7 @@
 
 // COMMON-LABEL: test_vfma_f16
 // UNCONSTRAINED:  [[ADD:%.*]] = call <4 x half> @llvm.fma.v4f16(<4 x half> %b, <4 x half> %c, <4 x half> %a)
-// CONSTRAINED:    [[ADD:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> %b, <4 x half> %c, <4 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:    [[ADD:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> %b, <4 x half> %c, <4 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:      fmla v{{[0-9]+}}.4h, v{{[0-9]+}}.4h, v{{[0-9]+}}.4h
 // COMMONIR:       ret <4 x half> [[ADD]]
 float16x4_t test_vfma_f16(float16x4_t a, float16x4_t b, float16x4_t c) {
@@ -60,7 +59,7 @@
 
 // COMMON-LABEL: test_vfmaq_f16
 // UNCONSTRAINED:  [[ADD:%.*]] = call <8 x half> @llvm.fma.v8f16(<8 x half> %b, <8 x half> %c, <8 x half> %a)
-// CONSTRAINED:    [[ADD:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> %b, <8 x half> %c, <8 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:    [[ADD:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> %b, <8 x half> %c, <8 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:      fmla v{{[0-9]+}}.8h, v{{[0-9]+}}.8h, v{{[0-9]+}}.8h
 // COMMONIR:       ret <8 x half> [[ADD]]
 float16x8_t test_vfmaq_f16(float16x8_t a, float16x8_t b, float16x8_t c) {
@@ -70,7 +69,7 @@
 // COMMON-LABEL: test_vfms_f16
 // COMMONIR:       [[SUB:%.*]] = fneg <4 x half> %b
 // UNCONSTRAINED:  [[ADD:%.*]] = call <4 x half> @llvm.fma.v4f16(<4 x half> [[SUB]], <4 x half> %c, <4 x half> %a)
-// CONSTRAINED:    [[ADD:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[SUB]], <4 x half> %c, <4 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:    [[ADD:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[SUB]], <4 x half> %c, <4 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:      fmls v{{[0-9]+}}.4h, v{{[0-9]+}}.4h, v{{[0-9]+}}.4h
 // COMMONIR:       ret <4 x half> [[ADD]]
 float16x4_t test_vfms_f16(float16x4_t a, float16x4_t b, float16x4_t c) {
@@ -80,7 +79,7 @@
 // COMMON-LABEL: test_vfmsq_f16
 // COMMONIR:       [[SUB:%.*]] = fneg <8 x half> %b
 // UNCONSTRAINED:  [[ADD:%.*]] = call <8 x half> @llvm.fma.v8f16(<8 x half> [[SUB]], <8 x half> %c, <8 x half> %a)
-// CONSTRAINED:    [[ADD:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[SUB]], <8 x half> %c, <8 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:    [[ADD:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[SUB]], <8 x half> %c, <8 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:      fmls v{{[0-9]+}}.8h, v{{[0-9]+}}.8h, v{{[0-9]+}}.8h
 // COMMONIR:       ret <8 x half> [[ADD]]
 float16x8_t test_vfmsq_f16(float16x8_t a, float16x8_t b, float16x8_t c) {
@@ -96,7 +95,7 @@
 // COMMONIR:      [[TMP4:%.*]] = bitcast <8 x i8> [[TMP1]] to <4 x half>
 // COMMONIR:      [[TMP5:%.*]] = bitcast <8 x i8> [[TMP0]] to <4 x half>
 // UNCONSTRAINED: [[FMLA:%.*]] = call <4 x half> @llvm.fma.v4f16(<4 x half> [[TMP4]], <4 x half> [[LANE]], <4 x half> [[TMP5]])
-// CONSTRAINED:   [[FMLA:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[TMP4]], <4 x half> [[LANE]], <4 x half> [[TMP5]], metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMLA:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[TMP4]], <4 x half> [[LANE]], <4 x half> [[TMP5]], metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmla v{{[0-9]+}}.4h, v{{[0-9]+}}.4h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <4 x half> [[FMLA]]
 float16x4_t test_vfma_lane_f16(float16x4_t a, float16x4_t b, float16x4_t c) {
@@ -112,7 +111,7 @@
 // COMMONIR:      [[TMP4:%.*]] = bitcast <16 x i8> [[TMP1]] to <8 x half>
 // COMMONIR:      [[TMP5:%.*]] = bitcast <16 x i8> [[TMP0]] to <8 x half>
 // UNCONSTRAINED: [[FMLA:%.*]] = call <8 x half> @llvm.fma.v8f16(<8 x half> [[TMP4]], <8 x half> [[LANE]], <8 x half> [[TMP5]])
-// CONSTRAINED:   [[FMLA:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[TMP4]], <8 x half> [[LANE]], <8 x half> [[TMP5]], metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMLA:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[TMP4]], <8 x half> [[LANE]], <8 x half> [[TMP5]], metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmla v{{[0-9]+}}.8h, v{{[0-9]+}}.8h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <8 x half> [[FMLA]]
 float16x8_t test_vfmaq_lane_f16(float16x8_t a, float16x8_t b, float16x4_t c) {
@@ -128,7 +127,7 @@
 // COMMONIR:      [[TMP5:%.*]] = bitcast <16 x i8> [[TMP2]] to <8 x half>
 // COMMONIR:      [[LANE:%.*]] = shufflevector <8 x half> [[TMP5]], <8 x half> [[TMP5]], <4 x i32> <i32 7, i32 7, i32 7, i32 7>
 // UNCONSTRAINED: [[FMLA:%.*]] = call <4 x half> @llvm.fma.v4f16(<4 x half> [[LANE]], <4 x half> [[TMP4]], <4 x half> [[TMP3]])
-// CONSTRAINED:   [[FMLA:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[LANE]], <4 x half> [[TMP4]], <4 x half> [[TMP3]], metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMLA:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[LANE]], <4 x half> [[TMP4]], <4 x half> [[TMP3]], metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmla v{{[0-9]+}}.4h, v{{[0-9]+}}.4h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <4 x half> [[FMLA]]
 float16x4_t test_vfma_laneq_f16(float16x4_t a, float16x4_t b, float16x8_t c) {
@@ -144,7 +143,7 @@
 // COMMONIR:      [[TMP5:%.*]] = bitcast <16 x i8> [[TMP2]] to <8 x half>
 // COMMONIR:      [[LANE:%.*]] = shufflevector <8 x half> [[TMP5]], <8 x half> [[TMP5]], <8 x i32> <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
 // UNCONSTRAINED: [[FMLA:%.*]] = call <8 x half> @llvm.fma.v8f16(<8 x half> [[LANE]], <8 x half> [[TMP4]], <8 x half> [[TMP3]])
-// CONSTRAINED:   [[FMLA:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[LANE]], <8 x half> [[TMP4]], <8 x half> [[TMP3]], metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMLA:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[LANE]], <8 x half> [[TMP4]], <8 x half> [[TMP3]], metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmla v{{[0-9]+}}.8h, v{{[0-9]+}}.8h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <8 x half> [[FMLA]]
 float16x8_t test_vfmaq_laneq_f16(float16x8_t a, float16x8_t b, float16x8_t c) {
@@ -157,7 +156,7 @@
 // COMMONIR:      [[TMP2:%.*]] = insertelement <4 x half> [[TMP1]], half %c, i32 2
 // COMMONIR:      [[TMP3:%.*]] = insertelement <4 x half> [[TMP2]], half %c, i32 3
 // UNCONSTRAINED: [[FMA:%.*]]  = call <4 x half> @llvm.fma.v4f16(<4 x half> %b, <4 x half> [[TMP3]], <4 x half> %a)
-// CONSTRAINED:   [[FMA:%.*]]  = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> %b, <4 x half> [[TMP3]], <4 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMA:%.*]]  = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> %b, <4 x half> [[TMP3]], <4 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmla v{{[0-9]+}}.4h, v{{[0-9]+}}.4h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <4 x half> [[FMA]]
 float16x4_t test_vfma_n_f16(float16x4_t a, float16x4_t b, float16_t c) {
@@ -174,7 +173,7 @@
 // COMMONIR:      [[TMP6:%.*]] = insertelement <8 x half> [[TMP5]], half %c, i32 6
 // COMMONIR:      [[TMP7:%.*]] = insertelement <8 x half> [[TMP6]], half %c, i32 7
 // UNCONSTRAINED: [[FMA:%.*]]  = call <8 x half> @llvm.fma.v8f16(<8 x half> %b, <8 x half> [[TMP7]], <8 x half> %a)
-// CONSTRAINED:   [[FMA:%.*]]  = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> %b, <8 x half> [[TMP7]], <8 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMA:%.*]]  = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> %b, <8 x half> [[TMP7]], <8 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmla v{{[0-9]+}}.8h, v{{[0-9]+}}.8h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <8 x half> [[FMA]]
 float16x8_t test_vfmaq_n_f16(float16x8_t a, float16x8_t b, float16_t c) {
@@ -184,7 +183,7 @@
 // COMMON-LABEL: test_vfmah_lane_f16
 // COMMONIR:      [[EXTR:%.*]] = extractelement <4 x half> %c, i32 3
 // UNCONSTRAINED: [[FMA:%.*]]  = call half @llvm.fma.f16(half %b, half [[EXTR]], half %a)
-// CONSTRAINED:   [[FMA:%.*]]  = call half @llvm.experimental.constrained.fma.f16(half %b, half [[EXTR]], half %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMA:%.*]]  = call half @llvm.experimental.constrained.fma.f16(half %b, half [[EXTR]], half %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmla h{{[0-9]+}}, h{{[0-9]+}}, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret half [[FMA]]
 float16_t test_vfmah_lane_f16(float16_t a, float16_t b, float16x4_t c) {
@@ -194,7 +193,7 @@
 // COMMON-LABEL: test_vfmah_laneq_f16
 // COMMONIR:      [[EXTR:%.*]] = extractelement <8 x half> %c, i32 7
 // UNCONSTRAINED: [[FMA:%.*]]  = call half @llvm.fma.f16(half %b, half [[EXTR]], half %a)
-// CONSTRAINED:   [[FMA:%.*]]  = call half @llvm.experimental.constrained.fma.f16(half %b, half [[EXTR]], half %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMA:%.*]]  = call half @llvm.experimental.constrained.fma.f16(half %b, half [[EXTR]], half %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmla h{{[0-9]+}}, h{{[0-9]+}}, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret half [[FMA]]
 float16_t test_vfmah_laneq_f16(float16_t a, float16_t b, float16x8_t c) {
@@ -211,7 +210,7 @@
 // COMMONIR:      [[TMP4:%.*]] = bitcast <8 x i8> [[TMP1]] to <4 x half>
 // COMMONIR:      [[TMP5:%.*]] = bitcast <8 x i8> [[TMP0]] to <4 x half>
 // UNCONSTRAINED: [[FMA:%.*]] = call <4 x half> @llvm.fma.v4f16(<4 x half> [[TMP4]], <4 x half> [[LANE]], <4 x half> [[TMP5]])
-// CONSTRAINED:   [[FMA:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[TMP4]], <4 x half> [[LANE]], <4 x half> [[TMP5]], metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMA:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[TMP4]], <4 x half> [[LANE]], <4 x half> [[TMP5]], metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmls v{{[0-9]+}}.4h, v{{[0-9]+}}.4h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <4 x half> [[FMA]]
 float16x4_t test_vfms_lane_f16(float16x4_t a, float16x4_t b, float16x4_t c) {
@@ -228,7 +227,7 @@
 // COMMONIR:      [[TMP4:%.*]] = bitcast <16 x i8> [[TMP1]] to <8 x half>
 // COMMONIR:      [[TMP5:%.*]] = bitcast <16 x i8> [[TMP0]] to <8 x half>
 // UNCONSTRAINED: [[FMLA:%.*]] = call <8 x half> @llvm.fma.v8f16(<8 x half> [[TMP4]], <8 x half> [[LANE]], <8 x half> [[TMP5]])
-// CONSTRAINED:   [[FMLA:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[TMP4]], <8 x half> [[LANE]], <8 x half> [[TMP5]], metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMLA:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[TMP4]], <8 x half> [[LANE]], <8 x half> [[TMP5]], metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmls v{{[0-9]+}}.8h, v{{[0-9]+}}.8h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <8 x half> [[FMLA]]
 float16x8_t test_vfmsq_lane_f16(float16x8_t a, float16x8_t b, float16x4_t c) {
@@ -246,7 +245,7 @@
 // COMMONIR:      [[TMP5:%.*]] = bitcast <16 x i8> [[TMP2]] to <8 x half>
 // COMMONIR:      [[LANE:%.*]] = shufflevector <8 x half> [[TMP5]], <8 x half> [[TMP5]], <4 x i32> <i32 7, i32 7, i32 7, i32 7>
 // UNCONSTRAINED: [[FMLA:%.*]] = call <4 x half> @llvm.fma.v4f16(<4 x half> [[LANE]], <4 x half> [[TMP4]], <4 x half> [[TMP3]])
-// CONSTRAINED:   [[FMLA:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[LANE]], <4 x half> [[TMP4]], <4 x half> [[TMP3]], metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMLA:%.*]] = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[LANE]], <4 x half> [[TMP4]], <4 x half> [[TMP3]], metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmls v{{[0-9]+}}.4h, v{{[0-9]+}}.4h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <4 x half> [[FMLA]]
 float16x4_t test_vfms_laneq_f16(float16x4_t a, float16x4_t b, float16x8_t c) {
@@ -264,7 +263,7 @@
 // COMMONIR:      [[TMP5:%.*]] = bitcast <16 x i8> [[TMP2]] to <8 x half>
 // COMMONIR:      [[LANE:%.*]] = shufflevector <8 x half> [[TMP5]], <8 x half> [[TMP5]], <8 x i32> <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
 // UNCONSTRAINED: [[FMLA:%.*]] = call <8 x half> @llvm.fma.v8f16(<8 x half> [[LANE]], <8 x half> [[TMP4]], <8 x half> [[TMP3]])
-// CONSTRAINED:   [[FMLA:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[LANE]], <8 x half> [[TMP4]], <8 x half> [[TMP3]], metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMLA:%.*]] = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[LANE]], <8 x half> [[TMP4]], <8 x half> [[TMP3]], metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmls v{{[0-9]+}}.8h, v{{[0-9]+}}.8h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <8 x half> [[FMLA]]
 float16x8_t test_vfmsq_laneq_f16(float16x8_t a, float16x8_t b, float16x8_t c) {
@@ -278,7 +277,7 @@
 // COMMONIR:      [[TMP2:%.*]] = insertelement <4 x half> [[TMP1]], half %c, i32 2
 // COMMONIR:      [[TMP3:%.*]] = insertelement <4 x half> [[TMP2]], half %c, i32 3
 // UNCONSTRAINED: [[FMA:%.*]]  = call <4 x half> @llvm.fma.v4f16(<4 x half> [[SUB]], <4 x half> [[TMP3]], <4 x half> %a)
-// CONSTRAINED:   [[FMA:%.*]]  = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[SUB]], <4 x half> [[TMP3]], <4 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMA:%.*]]  = call <4 x half> @llvm.experimental.constrained.fma.v4f16(<4 x half> [[SUB]], <4 x half> [[TMP3]], <4 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmls v{{[0-9]+}}.4h, v{{[0-9]+}}.4h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <4 x half> [[FMA]]
 float16x4_t test_vfms_n_f16(float16x4_t a, float16x4_t b, float16_t c) {
@@ -296,7 +295,7 @@
 // COMMONIR:      [[TMP6:%.*]] = insertelement <8 x half> [[TMP5]], half %c, i32 6
 // COMMONIR:      [[TMP7:%.*]] = insertelement <8 x half> [[TMP6]], half %c, i32 7
 // UNCONSTRAINED: [[FMA:%.*]]  = call <8 x half> @llvm.fma.v8f16(<8 x half> [[SUB]], <8 x half> [[TMP7]], <8 x half> %a)
-// CONSTRAINED:   [[FMA:%.*]]  = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[SUB]], <8 x half> [[TMP7]], <8 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMA:%.*]]  = call <8 x half> @llvm.experimental.constrained.fma.v8f16(<8 x half> [[SUB]], <8 x half> [[TMP7]], <8 x half> %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmls v{{[0-9]+}}.8h, v{{[0-9]+}}.8h, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret <8 x half> [[FMA]]
 float16x8_t test_vfmsq_n_f16(float16x8_t a, float16x8_t b, float16_t c) {
@@ -314,7 +313,7 @@
 // CHECK-ASM:     fcvt h{{[0-9]+}}, s{{[0-9]+}}
 // COMMONIR:      [[EXTR:%.*]] = extractelement <4 x half> %c, i32 3
 // UNCONSTRAINED: [[FMA:%.*]]  = call half @llvm.fma.f16(half [[SUB]], half [[EXTR]], half %a)
-// CONSTRAINED:   [[FMA:%.*]]  = call half @llvm.experimental.constrained.fma.f16(half [[SUB]], half [[EXTR]], half %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMA:%.*]]  = call half @llvm.experimental.constrained.fma.f16(half [[SUB]], half [[EXTR]], half %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmla h{{[0-9]+}}, h{{[0-9]+}}, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret half [[FMA]]
 float16_t test_vfmsh_lane_f16(float16_t a, float16_t b, float16x4_t c) {
@@ -332,7 +331,7 @@
 // CHECK-ASM:     fcvt h{{[0-9]+}}, s{{[0-9]+}}
 // COMMONIR:      [[EXTR:%.*]] = extractelement <8 x half> %c, i32 7
 // UNCONSTRAINED: [[FMA:%.*]]  = call half @llvm.fma.f16(half [[SUB]], half [[EXTR]], half %a)
-// CONSTRAINED:   [[FMA:%.*]]  = call half @llvm.experimental.constrained.fma.f16(half [[SUB]], half [[EXTR]], half %a, metadata !"round.tonearest", metadata !"fpexcept.maytrap")
+// CONSTRAINED:   [[FMA:%.*]]  = call half @llvm.experimental.constrained.fma.f16(half [[SUB]], half [[EXTR]], half %a, metadata !"round.tonearest", metadata !"fpexcept.strict")
 // CHECK-ASM:     fmla h{{[0-9]+}}, h{{[0-9]+}}, v{{[0-9]+}}.h[{{[0-9]+}}]
 // COMMONIR:      ret half [[FMA]]
 float16_t test_vfmsh_laneq_f16(float16_t a, float16_t b, float16x8_t c) {
diff --git a/clang/test/CodeGen/complex-strictfp.c b/clang/test/CodeGen/complex-strictfp.c
--- a/clang/test/CodeGen/complex-strictfp.c
+++ b/clang/test/CodeGen/complex-strictfp.c
@@ -5,8 +5,6 @@
 // Test that the constrained intrinsics are picking up the exception
 // metadata from the AST instead of the global default from the command line.
 // Include rounding metadata in the testing.
-// FIXME: All cases of "fpexcept.maytrap" in this test are wrong.
-// FIXME: All cases of "round.tonearest" in this test are wrong.
 
 #pragma float_control(except, on)
 #pragma STDC FENV_ROUND FE_UPWARD
@@ -74,7 +72,7 @@
 // CHECK-NEXT:    [[G1_REAL:%.*]] = load double, double* getelementptr inbounds ({ double, double }, { double, double }* @g1, i32 0, i32 0), align 8
 // CHECK-NEXT:    [[G1_IMAG:%.*]] = load double, double* getelementptr inbounds ({ double, double }, { double, double }* @g1, i32 0, i32 1), align 8
 // CHECK-NEXT:    [[TMP0:%.*]] = load double, double* @D, align 8
-// CHECK-NEXT:    [[ADD_R:%.*]] = call double @llvm.experimental.constrained.fadd.f64(double [[G1_REAL]], double [[TMP0]], metadata !"round.tonearest", metadata !"fpexcept.maytrap") #[[ATTR2]]
+// CHECK-NEXT:    [[ADD_R:%.*]] = call double @llvm.experimental.constrained.fadd.f64(double [[G1_REAL]], double [[TMP0]], metadata !"round.upward", metadata !"fpexcept.strict") #[[ATTR2]]
 // CHECK-NEXT:    store double [[ADD_R]], double* getelementptr inbounds ({ double, double }, { double, double }* @g1, i32 0, i32 0), align 8
 // CHECK-NEXT:    store double [[G1_IMAG]], double* getelementptr inbounds ({ double, double }, { double, double }* @g1, i32 0, i32 1), align 8
 // CHECK-NEXT:    ret void
@@ -88,7 +86,7 @@
 // CHECK-NEXT:    [[TMP0:%.*]] = load double, double* @D, align 8
 // CHECK-NEXT:    [[G1_REAL:%.*]] = load double, double* getelementptr inbounds ({ double, double }, { double, double }* @g1, i32 0, i32 0), align 8
 // CHECK-NEXT:    [[G1_IMAG:%.*]] = load double, double* getelementptr inbounds ({ double, double }, { double, double }* @g1, i32 0, i32 1), align 8
-// CHECK-NEXT:    [[ADD_R:%.*]] = call double @llvm.experimental.constrained.fadd.f64(double [[TMP0]], double [[G1_REAL]], metadata !"round.tonearest", metadata !"fpexcept.maytrap") #[[ATTR2]]
+// CHECK-NEXT:    [[ADD_R:%.*]] = call double @llvm.experimental.constrained.fadd.f64(double [[TMP0]], double [[G1_REAL]], metadata !"round.upward", metadata !"fpexcept.strict") #[[ATTR2]]
 // CHECK-NEXT:    store double [[ADD_R]], double* getelementptr inbounds ({ double, double }, { double, double }* @g1, i32 0, i32 0), align 8
 // CHECK-NEXT:    store double [[G1_IMAG]], double* getelementptr inbounds ({ double, double }, { double, double }* @g1, i32 0, i32 1), align 8
 // CHECK-NEXT:    ret void
diff --git a/clang/test/CodeGen/pragma-fenv_access.cpp b/clang/test/CodeGen/pragma-fenv_access.cpp
new file mode 100644
--- /dev/null
+++ b/clang/test/CodeGen/pragma-fenv_access.cpp
@@ -0,0 +1,42 @@
+// RUN: %clang_cc1 -S -triple x86_64-linux-gnu -emit-llvm %s -o - | FileCheck %s
+
+template <typename T>
+T templ_01(T a, T b) {
+  return a * b;
+}
+
+#pragma STDC FENV_ACCESS ON
+
+float func_02(float a, float b) {
+  return 1.0f + templ_01<float>(a, b);
+}
+
+// CHECK-LABEL: define {{.*}} @_Z7func_02ff
+// CHECK: call noundef float @_Z8templ_01IfET_S0_S0_
+// CHECK: call float @llvm.experimental.constrained.fadd.f32({{.*}}, metadata !"round.dynamic", metadata !"fpexcept.strict")
+
+// CHECK-LABEL: define {{.*}} @_Z8templ_01IfET_S0_S0_
+// CHECK: fmul float
+
+
+#pragma STDC FENV_ACCESS OFF
+#pragma STDC FENV_ROUND FE_UPWARD
+
+template <typename T>
+T templ_03(T a, T b) {
+  return a * b;
+}
+
+#pragma STDC FENV_ACCESS ON
+
+float func_04(float a, float b) {
+  return 1.0f + templ_03<float>(a, b);
+}
+
+
+// CHECK-LABEL: define {{.*}} @_Z7func_04ff
+// CHECK: call noundef float @_Z8templ_03IfET_S0_S0_
+// CHECK: call float @llvm.experimental.constrained.fadd.f32({{.*}}, metadata !"round.upward", metadata !"fpexcept.strict")
+
+// CHECK-LABEL: define {{.*}} @_Z8templ_03IfET_S0_S0_
+// CHECK: call float @llvm.experimental.constrained.fmul.f32({{.*}}, metadata !"round.upward", metadata !"fpexcept.ignore")