diff --git a/llvm/lib/Target/X86/X86InstrAVX512.td b/llvm/lib/Target/X86/X86InstrAVX512.td
index d3adc06441f0..420a70ad5a21 100644
--- a/llvm/lib/Target/X86/X86InstrAVX512.td
+++ b/llvm/lib/Target/X86/X86InstrAVX512.td
@@ -6825,7 +6825,7 @@ let Constraints = "$src1 = $dst", hasSideEffects = 0 in {
     def rb    : AVX512FMA3S<opc, MRMSrcReg, (outs _.FRC:$dst),
                      (ins _.FRC:$src1, _.FRC:$src2, _.FRC:$src3, AVX512RC:$rc),
                      !strconcat(OpcodeStr,
-                              "\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
+                              "\t{$rc, $src3, $src2, $dst|$dst, $src2, $src3, $rc}"),
                      !if(MaskOnlyReg, [], [RHS_b])>, EVEX_B, EVEX_RC,
                      Sched<[SchedWriteFMA.Scl]>;
   }// isCodeGenOnly = 1
diff --git a/llvm/test/CodeGen/X86/avx512-fma-intrinsics.ll b/llvm/test/CodeGen/X86/avx512-fma-intrinsics.ll
index 99438064f85c..ff737b91264a 100644
--- a/llvm/test/CodeGen/X86/avx512-fma-intrinsics.ll
+++ b/llvm/test/CodeGen/X86/avx512-fma-intrinsics.ll
@@ -1154,14 +1154,14 @@ define <4 x float> @foo() {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    vmovss (%eax), %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xfa,0x10,0x00]
 ; X86-NEXT:    # xmm0 = mem[0],zero,zero,zero
-; X86-NEXT:    vfmsub213ss %xmm0, %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x38,0xab,0xc0]
+; X86-NEXT:    vfmsub213ss {rd-sae}, %xmm0, %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x38,0xab,0xc0]
 ; X86-NEXT:    retl # encoding: [0xc3]
 ;
 ; X64-LABEL: foo:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    vmovss (%rax), %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xfa,0x10,0x00]
 ; X64-NEXT:    # xmm0 = mem[0],zero,zero,zero
-; X64-NEXT:    vfmsub213ss %xmm0, %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x38,0xab,0xc0]
+; X64-NEXT:    vfmsub213ss {rd-sae}, %xmm0, %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x38,0xab,0xc0]
 ; X64-NEXT:    retq # encoding: [0xc3]
 entry:
   %0 = load <4 x float>, <4 x float>* undef, align 16
diff --git a/llvm/test/CodeGen/X86/avx512-intrinsics-fast-isel.ll b/llvm/test/CodeGen/X86/avx512-intrinsics-fast-isel.ll
index e222c0e1ae2c..80d54665cd93 100644
--- a/llvm/test/CodeGen/X86/avx512-intrinsics-fast-isel.ll
+++ b/llvm/test/CodeGen/X86/avx512-intrinsics-fast-isel.ll
@@ -5875,7 +5875,7 @@ define <2 x double> @test_mm_mask3_fmsub_round_sd(<2 x double> %__W, <2 x double
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movb {{[0-9]+}}(%esp), %al
 ; X86-NEXT:    vxorpd {{\.LCPI.*}}, %xmm2, %xmm3
-; X86-NEXT:    vfmadd213sd %xmm3, %xmm0, %xmm1
+; X86-NEXT:    vfmadd213sd {rn-sae}, %xmm3, %xmm0, %xmm1
 ; X86-NEXT:    kmovw %eax, %k1
 ; X86-NEXT:    vmovsd %xmm1, %xmm2, %xmm2 {%k1}
 ; X86-NEXT:    vmovapd %xmm2, %xmm0
@@ -5884,7 +5884,7 @@ define <2 x double> @test_mm_mask3_fmsub_round_sd(<2 x double> %__W, <2 x double
 ; X64-LABEL: test_mm_mask3_fmsub_round_sd:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    vxorpd {{.*}}(%rip), %xmm2, %xmm3
-; X64-NEXT:    vfmadd213sd %xmm3, %xmm0, %xmm1
+; X64-NEXT:    vfmadd213sd {rn-sae}, %xmm3, %xmm0, %xmm1
 ; X64-NEXT:    kmovw %edi, %k1
 ; X64-NEXT:    vmovsd %xmm1, %xmm2, %xmm2 {%k1}
 ; X64-NEXT:    vmovapd %xmm2, %xmm0