diff --git a/lib/CodeGen/CGBuiltin.cpp b/lib/CodeGen/CGBuiltin.cpp
index 48ed65e3c7a3213167fa64385deeac9a675d3869..6678ebe71cf2d4cf5cf6911f4d0ecd5254abd283 100644
--- a/lib/CodeGen/CGBuiltin.cpp
+++ b/lib/CodeGen/CGBuiltin.cpp
@@ -2132,7 +2132,9 @@ Value *CodeGenFunction::EmitARMBuiltinExpr(unsigned BuiltinID,
     Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
     Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
     Ops[2] = Builder.CreateBitCast(Ops[2], Ty);
-    return Builder.CreateCall3(F, Ops[0], Ops[1], Ops[2]);
+
+    // NEON intrinsic puts accumulator first, unlike the LLVM fma.
+    return Builder.CreateCall3(F, Ops[1], Ops[2], Ops[0]);
   }
   case ARM::BI__builtin_neon_vpadal_v:
   case ARM::BI__builtin_neon_vpadalq_v: {
diff --git a/test/CodeGen/arm-neon-fma.c b/test/CodeGen/arm-neon-fma.c
new file mode 100644
index 0000000000000000000000000000000000000000..7511fe16c6bdb5ccd2e11bf1021f74ff91948118
--- /dev/null
+++ b/test/CodeGen/arm-neon-fma.c
@@ -0,0 +1,16 @@
+// REQUIRES: arm-registered-target
+// RUN: %clang -target thumbv7-none-linux-gnueabihf \
+// RUN:   -mcpu=cortex-a8 -mfloat-abi=hard \
+// RUN:   -O3 -S -emit-llvm -o - %s | FileCheck %s
+
+#include <arm_neon.h>
+
+float32x2_t test_fma_order(float32x2_t accum, float32x2_t lhs, float32x2_t rhs) {
+  return vfma_f32(accum, lhs, rhs);
+// CHECK: call <2 x float> @llvm.fma.v2f32(<2 x float> %lhs, <2 x float> %rhs, <2 x float> %accum)
+}
+
+float32x4_t test_fmaq_order(float32x4_t accum, float32x4_t lhs, float32x4_t rhs) {
+  return vfmaq_f32(accum, lhs, rhs);
+// CHECK: call <4 x float> @llvm.fma.v4f32(<4 x float> %lhs, <4 x float> %rhs, <4 x float> %accum)
+}