Index: clang/lib/CodeGen/CGExprScalar.cpp
===================================================================
--- clang/lib/CodeGen/CGExprScalar.cpp
+++ clang/lib/CodeGen/CGExprScalar.cpp
@@ -3782,7 +3782,8 @@
          "Only fadd/fsub can be the root of an fmuladd.");
 
   // Check whether this op is marked as fusable.
-  if (!op.FPFeatures.allowFPContractWithinStatement())
+  if (!op.FPFeatures.allowFPContractWithinStatement() &&
+      !op.FPFeatures.allowFPContractAcrossStatement())
     return nullptr;
 
   Value *LHS = op.LHS;
Index: clang/test/CodeGen/ffp-contract-fast-option.cpp
===================================================================
--- clang/test/CodeGen/ffp-contract-fast-option.cpp
+++ clang/test/CodeGen/ffp-contract-fast-option.cpp
@@ -1,29 +1,44 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
 // RUN: %clang_cc1 -O3 -ffp-contract=fast -triple %itanium_abi_triple -emit-llvm -o - %s | FileCheck %s
 
+// CHECK-LABEL: @_Z13fp_contract_1fff(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call contract float @llvm.fmuladd.f32(float [[A:%.*]], float [[B:%.*]], float [[C:%.*]])
+// CHECK-NEXT:    ret float [[TMP0]]
+//
 float fp_contract_1(float a, float b, float c) {
-  // CHECK-LABEL: fp_contract_1fff(
-  // CHECK: fmul contract float
-  // CHECK: fadd contract float
   return a * b + c;
 }
 
+// CHECK-LABEL: @_Z13fp_contract_2fff(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[NEG:%.*]] = fneg contract float [[C:%.*]]
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call contract float @llvm.fmuladd.f32(float [[A:%.*]], float [[B:%.*]], float [[NEG]])
+// CHECK-NEXT:    ret float [[TMP0]]
+//
 float fp_contract_2(float a, float b, float c) {
-  // CHECK-LABEL: fp_contract_2fff(
-  // CHECK: fmul contract float
-  // CHECK: fsub contract float
   return a * b - c;
 }
 
+// CHECK-LABEL: @_Z13fp_contract_3Pfff(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = load float, ptr [[A:%.*]], align 4, !tbaa [[TBAA2:![0-9]+]]
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call contract float @llvm.fmuladd.f32(float [[B:%.*]], float [[C:%.*]], float [[TMP0]])
+// CHECK-NEXT:    store float [[TMP1]], ptr [[A]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    ret void
+//
 void fp_contract_3(float *a, float b, float c) {
-  // CHECK-LABEL: fp_contract_3Pfff(
-  // CHECK: fmul contract float
-  // CHECK: fadd contract float
   a[0] += b * c;
 }
 
+// CHECK-LABEL: @_Z13fp_contract_4Pfff(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = load float, ptr [[A:%.*]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[NEG:%.*]] = fneg contract float [[B:%.*]]
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call contract float @llvm.fmuladd.f32(float [[NEG]], float [[C:%.*]], float [[TMP0]])
+// CHECK-NEXT:    store float [[TMP1]], ptr [[A]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    ret void
+//
 void fp_contract_4(float *a, float b, float c) {
-  // CHECK-LABEL: fp_contract_4Pfff(
-  // CHECK: fmul contract float
-  // CHECK: fsub contract float
   a[0] -= b * c;
 }
Index: clang/test/CodeGen/ffp-contract-option.c
===================================================================
--- clang/test/CodeGen/ffp-contract-option.c
+++ clang/test/CodeGen/ffp-contract-option.c
@@ -73,9 +73,8 @@
 
   // CHECK-CONTRACTFAST: load float, ptr
   // CHECK-CONTRACTFAST: load float, ptr
-  // CHECK-CONTRACTFAST: fmul contract float
   // CHECK-CONTRACTFAST: load float, ptr
-  // CHECK-CONTRACTFAST: fadd contract float
+  // CHECK-CONTRACTFAST: call contract float @llvm.fmuladd.f32
 
   // CHECK-CONTRACTOFF: load float, ptr
   // CHECK-CONTRACTOFF: load float, ptr
@@ -90,9 +89,8 @@
 
   // CHECK-FASTFAST: load float, ptr
   // CHECK-FASTFAST: load float, ptr
-  // CHECK-FASTFAST: fmul fast float
   // CHECK-FASTFAST: load float, ptr
-  // CHECK-FASTFAST: fadd fast float {{.*}}, {{.*}}
+  // CHECK-FASTFAST: call fast float @llvm.fmuladd.f32
 
   // CHECK-NOFAST: load float, ptr
   // CHECK-NOFAST: load float, ptr
Index: clang/test/CodeGen/ffp-model.c
===================================================================
--- clang/test/CodeGen/ffp-model.c
+++ clang/test/CodeGen/ffp-model.c
@@ -19,9 +19,8 @@
   // CHECK: define{{.*}} float @mymuladd
   return x * y + z;
 
-  // CHECK-FAST: fmul fast float
   // CHECK-FAST: load float, ptr
-  // CHECK-FAST: fadd fast float
+  // CHECK-FAST: call fast float @llvm.fmuladd.f32
 
   // CHECK-PRECISE: load float, ptr
   // CHECK-PRECISE: load float, ptr
@@ -36,13 +35,11 @@
 
   // CHECK-STRICT-FAST: load float, ptr
   // CHECK-STRICT-FAST: load float, ptr
-  // CHECK-STRICT-FAST: fmul fast float {{.*}}, {{.*}}
   // CHECK-STRICT-FAST: load float, ptr
-  // CHECK-STRICT-FAST: fadd fast float {{.*}}, {{.*}}
+  // CHECK-STRICT-FAST: call fast float @llvm.fmuladd.f32
 
   // CHECK-FAST1: load float, ptr
   // CHECK-FAST1: load float, ptr
-  // CHECK-FAST1: fmul fast float {{.*}}, {{.*}}
   // CHECK-FAST1: load float, ptr {{.*}}
-  // CHECK-FAST1: fadd fast float {{.*}}, {{.*}}
+  // CHECK-FAST1: call fast float @llvm.fmuladd.f32
 }
Index: clang/test/CodeGen/fp-contract-fast-pragma.cpp
===================================================================
--- clang/test/CodeGen/fp-contract-fast-pragma.cpp
+++ clang/test/CodeGen/fp-contract-fast-pragma.cpp
@@ -1,19 +1,25 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
 // RUN: %clang_cc1 -O3 -triple %itanium_abi_triple -emit-llvm -o - %s | FileCheck %s
 
 // Is FP_CONTRACT honored in a simple case?
+// CHECK-LABEL: @_Z13fp_contract_1fff(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call contract float @llvm.fmuladd.f32(float [[A:%.*]], float [[B:%.*]], float [[C:%.*]])
+// CHECK-NEXT:    ret float [[TMP0]]
+//
 float fp_contract_1(float a, float b, float c) {
-// CHECK: _Z13fp_contract_1fff
-// CHECK: %[[M:.+]] = fmul contract float %a, %b
-// CHECK-NEXT: fadd contract float %[[M]], %c
 #pragma clang fp contract(fast)
   return a * b + c;
 }
 
 // Is FP_CONTRACT state cleared on exiting compound statements?
+// CHECK-LABEL: @_Z13fp_contract_2fff(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[MUL:%.*]] = fmul float [[A:%.*]], [[B:%.*]]
+// CHECK-NEXT:    [[ADD:%.*]] = fadd float [[MUL]], [[C:%.*]]
+// CHECK-NEXT:    ret float [[ADD]]
+//
 float fp_contract_2(float a, float b, float c) {
-  // CHECK: _Z13fp_contract_2fff
-  // CHECK: %[[M:.+]] = fmul float %a, %b
-  // CHECK-NEXT: fadd float %[[M]], %c
   {
 #pragma clang fp contract(fast)
   }
@@ -30,10 +36,12 @@
   return a * b + c;
 }
 
+// CHECK-LABEL: @_Z13fp_contract_3fff(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call contract float @llvm.fmuladd.f32(float [[A:%.*]], float [[B:%.*]], float [[C:%.*]])
+// CHECK-NEXT:    ret float [[TMP0]]
+//
 float fp_contract_3(float a, float b, float c) {
-  // CHECK: _Z13fp_contract_3fff
-  // CHECK: %[[M:.+]] = fmul contract float %a, %b
-  // CHECK-NEXT: fadd contract float %[[M]], %c
   return template_muladd<float>(a, b, c);
 }
 
@@ -45,25 +53,32 @@
   }
 };
 
+// CHECK-LABEL: @_ZN13fp_contract_4IiE6methodEfff(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call contract float @llvm.fmuladd.f32(float [[A:%.*]], float [[B:%.*]], float [[C:%.*]])
+// CHECK-NEXT:    ret float [[TMP0]]
+//
 template class fp_contract_4<int>;
-// CHECK: _ZN13fp_contract_4IiE6methodEfff
-// CHECK: %[[M:.+]] = fmul contract float %a, %b
-// CHECK-NEXT: fadd contract float %[[M]], %c
 
 // Check file-scoped FP_CONTRACT
 #pragma clang fp contract(fast)
+// CHECK-LABEL: @_Z13fp_contract_5fff(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call contract float @llvm.fmuladd.f32(float [[A:%.*]], float [[B:%.*]], float [[C:%.*]])
+// CHECK-NEXT:    ret float [[TMP0]]
+//
 float fp_contract_5(float a, float b, float c) {
-  // CHECK: _Z13fp_contract_5fff
-  // CHECK: %[[M:.+]] = fmul contract float %a, %b
-  // CHECK-NEXT: fadd contract float %[[M]], %c
   return a * b + c;
 }
 
 // Verify that we can handle multiple flags on the same pragma
 #pragma clang fp contract(fast) contract(off)
+// CHECK-LABEL: @_Z13fp_contract_6fff(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[MUL:%.*]] = fmul float [[A:%.*]], [[B:%.*]]
+// CHECK-NEXT:    [[ADD:%.*]] = fadd float [[MUL]], [[C:%.*]]
+// CHECK-NEXT:    ret float [[ADD]]
+//
 float fp_contract_6(float a, float b, float c) {
-  // CHECK: _Z13fp_contract_6fff
-  // CHECK: %[[M:.+]] = fmul float %a, %b
-  // CHECK-NEXT: fadd float %[[M]], %c
   return a * b + c;
 }
Index: clang/test/CodeGen/fp-floatcontrol-stack.cpp
===================================================================
--- clang/test/CodeGen/fp-floatcontrol-stack.cpp
+++ clang/test/CodeGen/fp-floatcontrol-stack.cpp
@@ -23,8 +23,7 @@
 //CHECK-DEBSTRICT: llvm.experimental.constrained.fmul{{.*}}tonearest{{.*}}strict
 #endif
 #if FAST
-//CHECK-FAST: fmul fast float
-//CHECK-FAST: fadd fast float
+//CHECK-FAST: call fast float @llvm.fmuladd.f32
 #endif
 
 #pragma float_control(push)
@@ -49,8 +48,7 @@
 #endif
 #if FAST
 //Not possible to enable float_control(except) in FAST mode.
-//CHECK-FAST: fmul fast float
-//CHECK-FAST: fadd fast float
+//CHECK-FAST: call fast float @llvm.fmuladd.f32
 #endif
 
 #pragma float_control(pop)
@@ -70,8 +68,7 @@
 //CHECK-NOHONOR: call nnan ninf float @llvm.fmuladd{{.*}}
 #endif
 #if FAST
-//CHECK-FAST: fmul fast float
-//CHECK-FAST: fadd fast float
+//CHECK-FAST: call fast float @llvm.fmuladd.f32
 #endif
 
 #pragma float_control(except, off)
@@ -87,8 +84,7 @@
 //CHECK-NOHONOR: call nnan ninf float @llvm.fmuladd{{.*}}
 #endif
 #if FAST
-//CHECK-FAST: fmul fast float
-//CHECK-FAST: fadd fast float
+//CHECK-FAST: call fast float @llvm.fmuladd.f32
 #endif
 
 #pragma float_control(precise, on, push)
@@ -121,8 +117,7 @@
 //CHECK-NOHONOR: call nnan ninf float @llvm.fmuladd{{.*}}
 #endif
 #if FAST
-//CHECK-FAST: fmul fast float
-//CHECK-FAST: fadd fast float
+//CHECK-FAST: call fast float @llvm.fmuladd.f32
 #endif
 #pragma float_control(precise, off)
                     float precise_off FUN(4)
@@ -131,21 +126,17 @@
 // Note: precise_off enables fp_contract=fast and the instructions
 // generated do not include the contract flag, although it was enabled
 // in IRBuilder.
-//CHECK-DDEFAULT: fmul fast float
-//CHECK-DDEFAULT: fadd fast float
+//CHECK-DDEFAULT: call fast float @llvm.fmuladd.f32
 #endif
 #if EBSTRICT
-//CHECK-DEBSTRICT: fmul fast float
-//CHECK-DEBSTRICT: fadd fast float
+//CHECK-DEBSTRICT: call fast float @llvm.fmuladd.f32
 #endif
 #if NOHONOR
 // fast math should be enabled, and contract should be fast
-//CHECK-NOHONOR: fmul fast float
-//CHECK-NOHONOR: fadd fast float
+//CHECK-NOHONOR: call fast float @llvm.fmuladd.f32
 #endif
 #if FAST
-//CHECK-FAST: fmul fast float
-//CHECK-FAST: fadd fast float
+//CHECK-FAST: call fast float @llvm.fmuladd.f32
 #endif
 
 #pragma float_control(precise, on)
@@ -185,21 +176,17 @@
                                 float precise_off2 FUN(4)
 //CHECK-LABEL: define {{.*}} @_Z12precise_off2f{{.*}}
 #if DEFAULT
-//CHECK-DDEFAULT: fmul fast float
-//CHECK-DDEFAULT: fadd fast float
+//CHECK-DDEFAULT: call fast float @llvm.fmuladd.f32
 #endif
 #if EBSTRICT
-//CHECK-DEBSTRICT: fmul fast float
-//CHECK-DEBSTRICT: fadd fast float
+//CHECK-DEBSTRICT: call fast float @llvm.fmuladd.f32
 #endif
 #if NOHONOR
 // fast math settings since precise is off
-//CHECK-NOHONOR: fmul fast float
-//CHECK-NOHONOR: fadd fast float
+//CHECK-NOHONOR: call fast float @llvm.fmuladd.f32
 #endif
 #if FAST
-//CHECK-FAST: fmul fast float
-//CHECK-FAST: fadd fast float
+//CHECK-FAST: call fast float @llvm.fmuladd.f32
 #endif
 
 #pragma float_control(pop)