Index: lib/Target/X86/X86ISelLowering.h
===================================================================
--- lib/Target/X86/X86ISelLowering.h
+++ lib/Target/X86/X86ISelLowering.h
@@ -249,7 +249,8 @@
       /// Note that these typically require refinement
       /// in order to obtain suitable precision.
       FRSQRT, FRCP,
-
+      FRSQRTS, FRCPS,
+	  
       // Thread Local Storage.
       TLSADDR,
 
Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -21782,7 +21782,9 @@
   case X86ISD::FMAXC:              return "X86ISD::FMAXC";
   case X86ISD::FMINC:              return "X86ISD::FMINC";
   case X86ISD::FRSQRT:             return "X86ISD::FRSQRT";
+  case X86ISD::FRSQRTS:             return "X86ISD::FRSQRTS";
   case X86ISD::FRCP:               return "X86ISD::FRCP";
+  case X86ISD::FRCPS:              return "X86ISD::FRCPS";
   case X86ISD::EXTRQI:             return "X86ISD::EXTRQI";
   case X86ISD::INSERTQI:           return "X86ISD::INSERTQI";
   case X86ISD::TLSADDR:            return "X86ISD::TLSADDR";
Index: lib/Target/X86/X86InstrFragmentsSIMD.td
===================================================================
--- lib/Target/X86/X86InstrFragmentsSIMD.td
+++ lib/Target/X86/X86InstrFragmentsSIMD.td
@@ -60,8 +60,8 @@
                         [SDNPCommutative, SDNPAssociative]>;
 def X86frsqrt  : SDNode<"X86ISD::FRSQRT",    SDTFPUnaryOp>;
 def X86frcp    : SDNode<"X86ISD::FRCP",      SDTFPUnaryOp>;
-def X86frsqrt14s: SDNode<"X86ISD::FRSQRT",  SDTFPBinOp>;
-def X86frcp14s : SDNode<"X86ISD::FRCP",    SDTFPBinOp>;
+def X86frsqrt14s: SDNode<"X86ISD::FRSQRTS",  SDTFPBinOp>;
+def X86frcp14s : SDNode<"X86ISD::FRCPS",    SDTFPBinOp>;
 def X86fhadd   : SDNode<"X86ISD::FHADD",     SDTFPBinOp>;
 def X86fhsub   : SDNode<"X86ISD::FHSUB",     SDTFPBinOp>;
 def X86hadd    : SDNode<"X86ISD::HADD",      SDTIntBinOp>;
Index: lib/Target/X86/X86IntrinsicsInfo.h
===================================================================
--- lib/Target/X86/X86IntrinsicsInfo.h
+++ lib/Target/X86/X86IntrinsicsInfo.h
@@ -2119,8 +2119,8 @@
   X86_INTRINSIC_DATA(avx512_rcp14_ps_128, INTR_TYPE_1OP_MASK, X86ISD::FRCP, 0),
   X86_INTRINSIC_DATA(avx512_rcp14_ps_256, INTR_TYPE_1OP_MASK, X86ISD::FRCP, 0),
   X86_INTRINSIC_DATA(avx512_rcp14_ps_512, INTR_TYPE_1OP_MASK, X86ISD::FRCP, 0),
-  X86_INTRINSIC_DATA(avx512_rcp14_sd, INTR_TYPE_SCALAR_MASK, X86ISD::FRCP, 0),
-  X86_INTRINSIC_DATA(avx512_rcp14_ss, INTR_TYPE_SCALAR_MASK, X86ISD::FRCP, 0),
+  X86_INTRINSIC_DATA(avx512_rcp14_sd, INTR_TYPE_SCALAR_MASK, X86ISD::FRCPS, 0),
+  X86_INTRINSIC_DATA(avx512_rcp14_ss, INTR_TYPE_SCALAR_MASK, X86ISD::FRCPS, 0),
   X86_INTRINSIC_DATA(avx512_rcp28_pd, INTR_TYPE_1OP_MASK_RM, X86ISD::RCP28, 0),
   X86_INTRINSIC_DATA(avx512_rcp28_ps, INTR_TYPE_1OP_MASK_RM, X86ISD::RCP28, 0),
   X86_INTRINSIC_DATA(avx512_rcp28_sd, INTR_TYPE_SCALAR_MASK_RM, X86ISD::RCP28, 0),
@@ -2131,8 +2131,8 @@
   X86_INTRINSIC_DATA(avx512_rsqrt14_ps_128, INTR_TYPE_1OP_MASK, X86ISD::FRSQRT, 0),
   X86_INTRINSIC_DATA(avx512_rsqrt14_ps_256, INTR_TYPE_1OP_MASK, X86ISD::FRSQRT, 0),
   X86_INTRINSIC_DATA(avx512_rsqrt14_ps_512, INTR_TYPE_1OP_MASK, X86ISD::FRSQRT, 0),
-  X86_INTRINSIC_DATA(avx512_rsqrt14_sd, INTR_TYPE_SCALAR_MASK, X86ISD::FRSQRT, 0),
-  X86_INTRINSIC_DATA(avx512_rsqrt14_ss, INTR_TYPE_SCALAR_MASK, X86ISD::FRSQRT, 0),
+  X86_INTRINSIC_DATA(avx512_rsqrt14_sd, INTR_TYPE_SCALAR_MASK, X86ISD::FRSQRTS, 0),
+  X86_INTRINSIC_DATA(avx512_rsqrt14_ss, INTR_TYPE_SCALAR_MASK, X86ISD::FRSQRTS, 0),
   X86_INTRINSIC_DATA(avx512_rsqrt28_pd, INTR_TYPE_1OP_MASK_RM,X86ISD::RSQRT28, 0),
   X86_INTRINSIC_DATA(avx512_rsqrt28_ps, INTR_TYPE_1OP_MASK_RM,X86ISD::RSQRT28, 0),
   X86_INTRINSIC_DATA(avx512_rsqrt28_sd, INTR_TYPE_SCALAR_MASK_RM,X86ISD::RSQRT28, 0),
Index: test/CodeGen/X86/avx512-intrinsics.ll
===================================================================
--- test/CodeGen/X86/avx512-intrinsics.ll
+++ test/CodeGen/X86/avx512-intrinsics.ll
@@ -126,26 +126,6 @@
 }
 declare <16 x float> @llvm.x86.avx512.rsqrt14.ps.512(<16 x float>, <16 x float>, i16) nounwind readnone
 
-define <4 x float> @test_rsqrt14_ss(<4 x float> %a0) {
-; CHECK-LABEL: test_rsqrt14_ss:
-; CHECK:       ## BB#0:
-; CHECK-NEXT:    vrsqrt14ss %xmm0, %xmm0, %xmm0
-; CHECK-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.avx512.rsqrt14.ss(<4 x float> %a0, <4 x float> %a0, <4 x float> zeroinitializer, i8 -1) ; <<4 x float>> [#uses=1]
-  ret <4 x float> %res
-}
-declare <4 x float> @llvm.x86.avx512.rsqrt14.ss(<4 x float>, <4 x float>, <4 x float>, i8) nounwind readnone
-
-define <4 x float> @test_rcp14_ss(<4 x float> %a0) {
-; CHECK-LABEL: test_rcp14_ss:
-; CHECK:       ## BB#0:
-; CHECK-NEXT:    vrcp14ss %xmm0, %xmm0, %xmm0
-; CHECK-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.avx512.rcp14.ss(<4 x float> %a0, <4 x float> %a0, <4 x float> zeroinitializer, i8 -1) ; <<4 x float>> [#uses=1]
-  ret <4 x float> %res
-}
-declare <4 x float> @llvm.x86.avx512.rcp14.ss(<4 x float>, <4 x float>, <4 x float>, i8) nounwind readnone
-
 define <8 x double> @test_sqrt_pd_512(<8 x double> %a0) {
 ; CHECK-LABEL: test_sqrt_pd_512:
 ; CHECK:       ## BB#0:
Index: test/CodeGen/X86/avx512-scalarIntrinsics.ll
===================================================================
--- test/CodeGen/X86/avx512-scalarIntrinsics.ll
+++ test/CodeGen/X86/avx512-scalarIntrinsics.ll
@@ -0,0 +1,43 @@
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=skx | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s
+
+
+define <4 x float> @test_rsqrt14_ss(<4 x float> %a0) {
+  ; CHECK-LABEL: test_rsqrt14_ss:
+  ; CHECK:       ## BB#0:
+  ; CHECK-NEXT:    vrsqrt14ss %xmm0, %xmm0, %xmm0
+  ; CHECK-NEXT:    retq
+    %res = call <4 x float> @llvm.x86.avx512.rsqrt14.ss(<4 x float> %a0, <4 x float> %a0, <4 x float> zeroinitializer, i8 -1) ; <<4 x float>> [#uses=1]
+    ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.avx512.rsqrt14.ss(<4 x float>, <4 x float>, <4 x float>, i8) nounwind readnone
+
+define <4 x float> @test_rcp14_ss(<4 x float> %a0) {
+  ; CHECK-LABEL: test_rcp14_ss:
+  ; CHECK:       ## BB#0:
+  ; CHECK-NEXT:    vrcp14ss %xmm0, %xmm0, %xmm0
+  ; CHECK-NEXT:    retq
+    %res = call <4 x float> @llvm.x86.avx512.rcp14.ss(<4 x float> %a0, <4 x float> %a0, <4 x float> zeroinitializer, i8 -1) ; <<4 x float>> [#uses=1]
+    ret <4 x float> %res
+}
+
+define <4 x float> @test_rsqrt14_sd(<4 x float> %a0) {
+  ; CHECK-LABEL: test_rsqrt14_sd:
+  ; CHECK:       ## BB#0:
+  ; CHECK-NEXT:    vrsqrt14sd %xmm0, %xmm0, %xmm0
+  ; CHECK-NEXT:    retq
+    %res = call <4 x float> @llvm.x86.avx512.rsqrt14.sd(<4 x float> %a0, <4 x float> %a0, <4 x float> zeroinitializer, i8 -1) ; <<4 x float>> [#uses=1]
+    ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.avx512.rsqrt14.sd(<4 x float>, <4 x float>, <4 x float>, i8) nounwind readnone
+
+define <4 x float> @test_rcp14_sd(<4 x float> %a0) {
+  ; CHECK-LABEL: test_rcp14_sd:
+  ; CHECK:       ## BB#0:
+  ; CHECK-NEXT:    vrcp14sd %xmm0, %xmm0, %xmm0
+  ; CHECK-NEXT:    retq
+    %res = call <4 x float> @llvm.x86.avx512.rcp14.sd(<4 x float> %a0, <4 x float> %a0, <4 x float> zeroinitializer, i8 -1) ; <<4 x float>> [#uses=1]
+    ret <4 x float> %res
+}
+
+