[X86] Insert FMUL for estimated non reciprocal SQRT when `RefinementSteps` = 0

[spatel]

LGTM

llvm/lib/Target/X86/X86ISelLowering.cpp

if ((VT == MVT::f32 && Subtarget.hasSSE1()) ||
       (VT == MVT::v8f32 && Subtarget.hasAVX()) ||
       (VT == MVT::v16f32 && Subtarget.useAVX512Regs())) {
     if (RefinementSteps == ReciprocalEstimate::Unspecified)
       RefinementSteps = 1;
 
     UseOneConstNR = false;
     // There is no FSQRT for 512-bits, but there is RSQRT14.
     unsigned Opcode = VT == MVT::v16f32 ? X86ISD::RSQRT14 : X86ISD::FRSQRT;
-    return DAG.getNode(Opcode, DL, VT, Op);
+    SDValue Estimate = DAG.getNode(Opcode, DL, VT, Op);
+    if (RefinementSteps == 0 && !Reciprocal)
+      Estimate = DAG.getNode(ISD::FMUL, DL, VT, Op, Estimate);
+    return Estimate;
   }
 
   if (VT.getScalarType() == MVT::f16 && isTypeLegal(VT) &&
       Subtarget.hasFP16()) {
     if (RefinementSteps == ReciprocalEstimate::Unspecified)
       RefinementSteps = 0;
 
     if (VT == MVT::f16) {

llvm/test/CodeGen/X86/sqrt-fastmath.ll

; AVX512-NEXT:    retq
   %div = fdiv fast float 1.0, %sqrt
   ret float %div
 }
 
 define float @f32_estimate2(float %x) #5 {
 ; SSE-LABEL: f32_estimate2:
 ; SSE:       # %bb.0:
 ; SSE-NEXT:    rsqrtss %xmm0, %xmm1
+; SSE-NEXT:    mulss %xmm0, %xmm1
 ; SSE-NEXT:    andps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
 ; SSE-NEXT:    cmpltss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
 ; SSE-NEXT:    andnps %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: f32_estimate2:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    vandps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
-; AVX1-NEXT:    vrsqrtss %xmm0, %xmm0, %xmm0
-; AVX1-NEXT:    vcmpltss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm1
+; AVX1-NEXT:    vrsqrtss %xmm0, %xmm0, %xmm1
+; AVX1-NEXT:    vandps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm2
+; AVX1-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vcmpltss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2, %xmm1
 ; AVX1-NEXT:    vandnps %xmm0, %xmm1, %xmm0
 ; AVX1-NEXT:    retq
 ;
 ; AVX512-LABEL: f32_estimate2:
 ; AVX512:       # %bb.0:
 ; AVX512-NEXT:    vrsqrtss %xmm0, %xmm0, %xmm1
+; AVX512-NEXT:    vmulss %xmm1, %xmm0, %xmm1
 ; AVX512-NEXT:    vbroadcastss {{.*#+}} xmm2 = [NaN,NaN,NaN,NaN]
 ; AVX512-NEXT:    vandps %xmm2, %xmm0, %xmm0
 ; AVX512-NEXT:    vcmpltss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %k1
 ; AVX512-NEXT:    vxorps %xmm0, %xmm0, %xmm0
 ; AVX512-NEXT:    vmovss %xmm0, %xmm1, %xmm1 {%k1}
 ; AVX512-NEXT:    vmovaps %xmm1, %xmm0
 ; AVX512-NEXT:    retq
   %sqrt = tail call fast float @llvm.sqrt.f32(float %x)
; AVX512-NEXT:    retq
   %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt
   ret <4 x float> %div
 }
 
 define <4 x float> @v4f32_estimate2(<4 x float> %x) #5 {
 ; SSE-LABEL: v4f32_estimate2:
 ; SSE:       # %bb.0:
 ; SSE-NEXT:    rsqrtps %xmm0, %xmm2
+; SSE-NEXT:    mulps %xmm0, %xmm2
 ; SSE-NEXT:    andps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
 ; SSE-NEXT:    movaps {{.*#+}} xmm1 = [1.17549435E-38,1.17549435E-38,1.17549435E-38,1.17549435E-38]
 ; SSE-NEXT:    cmpleps %xmm0, %xmm1
 ; SSE-NEXT:    andps %xmm2, %xmm1
 ; SSE-NEXT:    movaps %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: v4f32_estimate2:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    vandps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
-; AVX1-NEXT:    vmovaps {{.*#+}} xmm2 = [1.17549435E-38,1.17549435E-38,1.17549435E-38,1.17549435E-38]
-; AVX1-NEXT:    vcmpleps %xmm1, %xmm2, %xmm1
-; AVX1-NEXT:    vrsqrtps %xmm0, %xmm0
+; AVX1-NEXT:    vrsqrtps %xmm0, %xmm1
+; AVX1-NEXT:    vandps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm2
+; AVX1-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovaps {{.*#+}} xmm1 = [1.17549435E-38,1.17549435E-38,1.17549435E-38,1.17549435E-38]
+; AVX1-NEXT:    vcmpleps %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vandps %xmm0, %xmm1, %xmm0
 ; AVX1-NEXT:    retq
 ;
 ; AVX512-LABEL: v4f32_estimate2:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    vbroadcastss {{.*#+}} xmm1 = [NaN,NaN,NaN,NaN]
-; AVX512-NEXT:    vandps %xmm1, %xmm0, %xmm1
+; AVX512-NEXT:    vrsqrtps %xmm0, %xmm1
+; AVX512-NEXT:    vmulps %xmm1, %xmm0, %xmm1
+; AVX512-NEXT:    vbroadcastss {{.*#+}} xmm2 = [NaN,NaN,NaN,NaN]
+; AVX512-NEXT:    vandps %xmm2, %xmm0, %xmm0
 ; AVX512-NEXT:    vbroadcastss {{.*#+}} xmm2 = [1.17549435E-38,1.17549435E-38,1.17549435E-38,1.17549435E-38]
-; AVX512-NEXT:    vcmpleps %xmm1, %xmm2, %xmm1
-; AVX512-NEXT:    vrsqrtps %xmm0, %xmm0
-; AVX512-NEXT:    vandps %xmm0, %xmm1, %xmm0
+; AVX512-NEXT:    vcmpleps %xmm0, %xmm2, %xmm0
+; AVX512-NEXT:    vandps %xmm1, %xmm0, %xmm0
 ; AVX512-NEXT:    retq
   %sqrt = tail call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> %x)
   ret <4 x float> %sqrt
 }
 
 define <8 x float> @v8f32_no_estimate(<8 x float> %x) #0 {
 ; SSE-LABEL: v8f32_no_estimate:
 ; SSE:       # %bb.0: