OV - exec - Function miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&)

	Function: miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios( ...	Module: exec	Source: OneBodyJastrowRef.h:133-155 [...]	Coverage (incl. loops): 0.02% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 313 - 316

--------------------------------------------------------------------------------

313:   inline int first(int igroup) const { return (*group_offsets_)[igroup]; }

314:

315:   ///return the last index of a group i

316:   inline int last(int igroup) const { return (*group_offsets_)[igroup + 1]; }

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 133 - 155

--------------------------------------------------------------------------------

133:   {

134:     for (int k = 0; k < ratios.size(); ++k)

135:       ratios[k] = std::exp(Vat[VP.refPtcl] - computeU(VP.getDistTableAB(myTableID).getDistRow(k).data()));

136:   }

137:

138:   inline valT computeU(const valT* dist)

139:   {

140:     valT curVat(0);

141:     if (NumGroups > 0)

142:     {

143:       for (int jg = 0; jg < NumGroups; ++jg)

144:       {

145:         if (F[jg] != nullptr)

146:           curVat += F[jg]->evaluateV(-1, Ions.first(jg), Ions.last(jg), dist, DistCompressed.data());

147:       }

148:     }

149:     else

150:     {

151:       for (int c = 0; c < Nions; ++c)

152:       {

153:         int gid = Ions.GroupID[c];

154:         if (F[gid] != nullptr)

155:           curVat += F[gid]->evaluate(dist[c]);

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 166 - 260

--------------------------------------------------------------------------------

166:     if (r >= cutoff_radius)

167:       return 0.0;

168:     r *= DeltaRInv;

169:     real_type ipart, t;

170:     t     = std::modf(r, &ipart);

171:     int i = (int)ipart;

172:     real_type tp[4];

173:     tp[0] = t * t * t;

[...]

179:       (SplineCoefs[i+0]*(A[ 0]*tp[0] + A[ 1]*tp[1] + A[ 2]*tp[2] + A[ 3]*tp[3])+

180:        SplineCoefs[i+1]*(A[ 4]*tp[0] + A[ 5]*tp[1] + A[ 6]*tp[2] + A[ 7]*tp[3])+

181:        SplineCoefs[i+2]*(A[ 8]*tp[0] + A[ 9]*tp[1] + A[10]*tp[2] + A[11]*tp[3])+

182:        SplineCoefs[i+3]*(A[12]*tp[0] + A[13]*tp[1] + A[14]*tp[2] + A[15]*tp[3]));

[...]

229:   const real_type* restrict distArray = _distArray + iStart;

[...]

236:   for (int jat = 0; jat < iLimit; jat++)

237:   {

238:     real_type r = distArray[jat];

239:     // pick the distances smaller than the cutoff and avoid the reference atom

240:     if (r < cutoff_radius && iStart + jat != iat)

241:       distArrayCompressed[iCount++] = distArray[jat];

242:   }

243:

244:   real_type d = 0.0;

245:   //#pragma omp simd reduction(+:d)

246:   for (int jat = 0; jat < iCount; jat++)

247:   {

248:     real_type r = distArrayCompressed[jat];

249:     r *= DeltaRInv;

250:     int i         = (int)r;

251:     real_type t   = r - real_type(i);

252:     real_type tp0 = t * t * t;

253:     real_type tp1 = t * t;

254:     real_type tp2 = t;

255:

256:     real_type d1 = SplineCoefs[i + 0] * (A[0] * tp0 + A[1] * tp1 + A[2] * tp2 + A[3]);

257:     real_type d2 = SplineCoefs[i + 1] * (A[4] * tp0 + A[5] * tp1 + A[6] * tp2 + A[7]);

258:     real_type d3 = SplineCoefs[i + 2] * (A[8] * tp0 + A[9] * tp1 + A[10] * tp2 + A[11]);

259:     real_type d4 = SplineCoefs[i + 3] * (A[12] * tp0 + A[13] * tp1 + A[14] * tp2 + A[15]);

260:     d += (d1 + d2 + d3 + d4);

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/shared_ptr_base.h: 1296 - 1296

--------------------------------------------------------------------------------

1296:       { return _M_ptr; }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 919 - 1169

--------------------------------------------------------------------------------

919:       { return size_type(this->_M_impl._M_finish - this->_M_impl._M_start); }

[...]

1046: 	return *(this->_M_impl._M_start + __n);

[...]

1064: 	return *(this->_M_impl._M_start + __n);

[...]

1169:       { return _M_data_ptr(this->_M_impl._M_start); }

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 249

--------------------------------------------------------------------------------

223:     return X[i];

[...]

229:     return X[i];

[...]

249:   inline const_pointer data() const { return X; }

0x42a9e0 PUSH	%RBP

0x42a9e1 MOV	%RSP,%RBP

0x42a9e4 PUSH	%R15

0x42a9e6 PUSH	%R14

0x42a9e8 PUSH	%R13

0x42a9ea PUSH	%R12

0x42a9ec PUSH	%RBX

0x42a9ed SUB	$0x208,%RSP

0x42a9f4 MOV	%RSI,-0x48(%RBP)

0x42a9f8 MOV	0x8(%RDX),%RAX

0x42a9fc MOV	%RDX,-0x50(%RBP)

0x42aa00 CMP	(%RDX),%RAX

0x42aa03 JE	42b397

0x42aa09 MOV	%RDI,%R14

0x42aa0c XOR	%R15D,%R15D

0x42aa0f MOV	%RDI,-0x40(%RBP)

0x42aa13 JMP	42aa5a

(376) 0x42aa15 XORPD	%XMM6,%XMM6

(376) 0x42aa19 NOPL	(%RAX)

(376) 0x42aa20 MOVSD	-0x58(%RBP),%XMM0

(376) 0x42aa25 SUBSD	%XMM6,%XMM0

(376) 0x42aa29 CALL	506a20 <exp>

(376) 0x42aa2e MOV	-0x50(%RBP),%RCX

(376) 0x42aa32 MOV	(%RCX),%RAX

(376) 0x42aa35 MOV	-0x60(%RBP),%R15

(376) 0x42aa39 MOVSD	%XMM0,(%RAX,%R15,8)

(376) 0x42aa3f INC	%R15

(376) 0x42aa42 MOV	0x8(%RCX),%RCX

(376) 0x42aa46 SUB	%RAX,%RCX

(376) 0x42aa49 SAR	$0x3,%RCX

(376) 0x42aa4d CMP	%R15,%RCX

(376) 0x42aa50 MOV	-0x40(%RBP),%R14

(376) 0x42aa54 JBE	42b397

(376) 0x42aa5a MOV	-0x48(%RBP),%RDI

(376) 0x42aa5e MOVSXD	0x2a0(%RDI),%RAX

(376) 0x42aa65 MOV	0xf0(%R14),%RCX

(376) 0x42aa6c MOVSD	(%RCX,%RAX,8),%XMM0

(376) 0x42aa71 MOVSD	%XMM0,-0x58(%RBP)

(376) 0x42aa76 MOV	0xa8(%R14),%ESI

(376) 0x42aa7d CALL	473f00 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

(376) 0x42aa82 MOV	0x48(%RAX),%RAX

(376) 0x42aa86 LEA	(%R15,%R15,4),%RCX

(376) 0x42aa8a MOV	0x18(%RAX,%RCX,8),%RDI

(376) 0x42aa8f MOV	0x98(%R14),%EAX

(376) 0x42aa96 TEST	%EAX,%EAX

(376) 0x42aa98 MOV	%R15,-0x60(%RBP)

(376) 0x42aa9c JLE	42b220

(376) 0x42aaa2 MOV	0x1c8(%R14),%RCX

(376) 0x42aaa9 MOV	0xa0(%R14),%RDX

(376) 0x42aab0 MOV	0x148(%R14),%RSI

(376) 0x42aab7 DEC	%RAX

(376) 0x42aaba MOV	%RDI,-0x30(%RBP)

(376) 0x42aabe ADD	$0x38,%RDI

(376) 0x42aac2 MOV	%RDI,-0x68(%RBP)

(376) 0x42aac6 XORPD	%XMM6,%XMM6

(376) 0x42aaca XOR	%R8D,%R8D

(376) 0x42aacd JMP	42aae4

0x42aacf NOP

  (378) 0x42aad0 LEA	0x1(%R8),%RDI

  (378) 0x42aad4 ADDSD	%XMM2,%XMM6

  (378) 0x42aad8 CMP	%RAX,%R8

  (378) 0x42aadb MOV	%RDI,%R8

  (378) 0x42aade JE	42aa20

  (378) 0x42aae4 MOV	(%RCX,%R8,8),%R9

  (378) 0x42aae8 TEST	%R9,%R9

  (378) 0x42aaeb JE	42afe0

  (378) 0x42aaf1 MOV	0x268(%RDX),%RDI

  (378) 0x42aaf8 MOV	0x18(%RDI),%RDI

  (378) 0x42aafc MOVSXD	(%RDI,%R8,4),%R12

  (378) 0x42ab00 MOV	0x4(%RDI,%R8,4),%EDI

  (378) 0x42ab05 SUB	%R12D,%EDI

  (378) 0x42ab08 XORPD	%XMM2,%XMM2

  (378) 0x42ab0c TEST	%EDI,%EDI

  (378) 0x42ab0e JLE	42aad0

  (378) 0x42ab10 MOV	%R12D,%R10D

  (378) 0x42ab13 MOVSD	0x8(%R9),%XMM1

  (378) 0x42ab19 MOV	%EDI,%R15D

  (378) 0x42ab1c XOR	%R11D,%R11D

  (378) 0x42ab1f CMP	$0x8,%EDI

  (378) 0x42ab22 JAE	42aff5

  (378) 0x42ab28 MOV	%R15D,%EDI

  (378) 0x42ab2b AND	$-0x8,%EDI

  (378) 0x42ab2e CMP	%R15,%RDI

  (378) 0x42ab31 JAE	42ab80

  (378) 0x42ab33 MOVSXD	%R10D,%R10

  (378) 0x42ab36 NOT	%R12D

  (378) 0x42ab39 MOV	-0x30(%RBP),%RBX

  (378) 0x42ab3d LEA	(%RBX,%R10,8),%R10

  (378) 0x42ab41 JMP	42ab58

0x42ab43 NOPW	%CS:(%RAX,%RAX,1)

    (381) 0x42ab50 INC	%RDI

    (381) 0x42ab53 CMP	%RDI,%R15

    (381) 0x42ab56 JE	42ab80

    (381) 0x42ab58 MOVSD	(%R10,%RDI,8),%XMM0

    (381) 0x42ab5e UCOMISD	%XMM0,%XMM1

    (381) 0x42ab62 JBE	42ab50

    (381) 0x42ab64 CMP	%EDI,%R12D

    (381) 0x42ab67 JE	42ab50

    (381) 0x42ab69 MOVSXD	%R11D,%R11

    (381) 0x42ab6c MOVSD	%XMM0,(%RSI,%R11,8)

    (381) 0x42ab72 INC	%R11D

    (381) 0x42ab75 JMP	42ab50

0x42ab77 NOPW	(%RAX,%RAX,1)

  (378) 0x42ab80 TEST	%R11D,%R11D

  (378) 0x42ab83 JLE	42aad0

  (378) 0x42ab89 MOVSD	0x238(%R9),%XMM7

  (378) 0x42ab92 MOV	0x218(%R9),%R10

  (378) 0x42ab99 MOVSD	0x28(%R9),%XMM8

  (378) 0x42ab9f MOVSD	0x48(%R9),%XMM4

  (378) 0x42aba5 MOVSD	0x68(%R9),%XMM15

  (378) 0x42abab MOVSD	0x88(%R9),%XMM0

  (378) 0x42abb4 MOVAPS	%XMM0,-0x90(%RBP)

  (378) 0x42abbb MOVSD	0x18(%R9),%XMM9

  (378) 0x42abc1 MOVSD	0x20(%R9),%XMM10

  (378) 0x42abc7 MOVSD	0x30(%R9),%XMM11

  (378) 0x42abcd MOVSD	0x38(%R9),%XMM1

  (378) 0x42abd3 MOVSD	0x40(%R9),%XMM3

  (378) 0x42abd9 MOVSD	0x50(%R9),%XMM0

  (378) 0x42abdf MOVSD	0x58(%R9),%XMM12

  (378) 0x42abe5 MOVSD	0x60(%R9),%XMM13

  (378) 0x42abeb MOVQ	0x70(%R9),%XMM14

  (378) 0x42abf1 MOVSD	0x78(%R9),%XMM5

  (378) 0x42abf7 MOVSD	0x80(%R9),%XMM2

  (378) 0x42ac00 MOVAPS	%XMM2,-0x80(%RBP)

  (378) 0x42ac04 MOV	%R11D,%EBX

  (378) 0x42ac07 MOV	%RBX,%R11

  (378) 0x42ac0a MOVSD	0x90(%R9),%XMM2

  (378) 0x42ac13 MOV	$-0x2,%EDI

  (378) 0x42ac18 AND	%RDI,%R11

  (378) 0x42ac1b MOVAPD	%XMM2,-0x180(%RBP)

  (378) 0x42ac23 JE	42b125

  (378) 0x42ac29 MOVSD	%XMM6,-0x38(%RBP)

  (378) 0x42ac2e MOVAPD	%XMM7,-0x170(%RBP)

  (378) 0x42ac36 UNPCKLPD	%XMM7,%XMM7

  (378) 0x42ac3a MOVAPD	%XMM7,-0x230(%RBP)

  (378) 0x42ac42 MOVAPD	%XMM9,-0x140(%RBP)

  (378) 0x42ac4b UNPCKLPD	%XMM9,%XMM9

  (378) 0x42ac50 MOVAPD	%XMM9,-0x220(%RBP)

  (378) 0x42ac59 MOVAPD	%XMM10,-0x130(%RBP)

  (378) 0x42ac62 UNPCKLPD	%XMM10,%XMM10

  (378) 0x42ac67 MOVAPD	%XMM10,-0x210(%RBP)

  (378) 0x42ac70 MOVAPD	%XMM8,-0x160(%RBP)

  (378) 0x42ac79 UNPCKLPD	%XMM8,%XMM8

  (378) 0x42ac7e MOVAPD	%XMM8,-0x200(%RBP)

  (378) 0x42ac87 MOVAPD	%XMM11,-0x120(%RBP)

  (378) 0x42ac90 UNPCKLPD	%XMM11,%XMM11

  (378) 0x42ac95 MOVAPD	%XMM11,-0x1f0(%RBP)

  (378) 0x42ac9e MOVAPD	%XMM0,%XMM6

  (378) 0x42aca2 MOVQ	%R10,%XMM0

  (378) 0x42aca7 PSHUFD	$0x44,%XMM0,%XMM0

  (378) 0x42acac MOVDQA	%XMM0,-0x1e0(%RBP)

  (378) 0x42acb4 MOVAPD	%XMM1,-0xe0(%RBP)

  (378) 0x42acbc UNPCKLPD	%XMM1,%XMM1

  (378) 0x42acc0 MOVAPD	%XMM1,-0x1d0(%RBP)

  (378) 0x42acc8 MOVAPD	%XMM3,-0xd0(%RBP)

  (378) 0x42acd0 UNPCKLPD	%XMM3,%XMM3

  (378) 0x42acd4 MOVAPD	%XMM3,-0x1c0(%RBP)

  (378) 0x42acdc MOVAPD	%XMM4,-0xc0(%RBP)

  (378) 0x42ace4 UNPCKLPD	%XMM4,%XMM4

  (378) 0x42ace8 MOVAPD	%XMM4,-0x1b0(%RBP)

  (378) 0x42acf0 MOVAPD	%XMM6,-0xa0(%RBP)

  (378) 0x42acf8 UNPCKLPD	%XMM6,%XMM6

  (378) 0x42acfc MOVAPD	%XMM6,-0x1a0(%RBP)

  (378) 0x42ad04 MOVAPD	%XMM12,-0x110(%RBP)

  (378) 0x42ad0d UNPCKLPD	%XMM12,%XMM12

  (378) 0x42ad12 MOVAPD	%XMM12,-0x190(%RBP)

  (378) 0x42ad1b MOVAPD	%XMM13,-0x100(%RBP)

  (378) 0x42ad24 MOVAPD	%XMM13,%XMM8

  (378) 0x42ad29 UNPCKLPD	%XMM13,%XMM8

  (378) 0x42ad2e MOVAPD	%XMM15,-0x150(%RBP)

  (378) 0x42ad37 UNPCKLPD	%XMM15,%XMM15

  (378) 0x42ad3c MOVDQA	%XMM14,-0xf0(%RBP)

  (378) 0x42ad45 MOVDQA	%XMM14,%XMM9

  (378) 0x42ad4a PUNPCKLQDQ	%XMM14,%XMM9

  (378) 0x42ad4f MOVAPD	%XMM5,-0xb0(%RBP)

  (378) 0x42ad57 MOVAPD	%XMM5,%XMM13

  (378) 0x42ad5c UNPCKLPD	%XMM5,%XMM13

  (378) 0x42ad61 MOVAPD	-0x80(%RBP),%XMM12

  (378) 0x42ad67 UNPCKLPD	%XMM12,%XMM12

  (378) 0x42ad6c MOVAPD	-0x90(%RBP),%XMM10

  (378) 0x42ad75 UNPCKLPD	%XMM10,%XMM10

  (378) 0x42ad7a MOVAPD	%XMM2,%XMM5

  (378) 0x42ad7e UNPCKLPD	%XMM2,%XMM5

  (378) 0x42ad82 XOR	%EDI,%EDI

  (378) 0x42ad84 PXOR	%XMM0,%XMM0

  (378) 0x42ad88 NOPL	(%RAX,%RAX,1)

    (380) 0x42ad90 MOVAPD	(%RSI,%RDI,8),%XMM4

    (380) 0x42ad95 MULPD	-0x230(%RBP),%XMM4

    (380) 0x42ad9d CVTTPD2DQ	%XMM4,%XMM2

    (380) 0x42ada1 CVTDQ2PD	%XMM2,%XMM1

    (380) 0x42ada5 SUBPD	%XMM1,%XMM4

    (380) 0x42ada9 MOVAPD	%XMM4,%XMM6

    (380) 0x42adad MULPD	%XMM4,%XMM6

    (380) 0x42adb1 MOVAPD	%XMM6,%XMM11

    (380) 0x42adb6 MOVAPD	%XMM6,%XMM3

    (380) 0x42adba MULPD	%XMM4,%XMM11

    (380) 0x42adbf MOVAPD	%XMM4,%XMM1

    (380) 0x42adc3 MULPD	-0x200(%RBP),%XMM1

    (380) 0x42adcb PXOR	%XMM14,%XMM14

    (380) 0x42add0 MULPD	-0x210(%RBP),%XMM3

    (380) 0x42add8 PCMPGTD	%XMM2,%XMM14

    (380) 0x42addd PUNPCKLDQ	%XMM14,%XMM2

    (380) 0x42ade2 PSLLQ	$0x3,%XMM2

    (380) 0x42ade7 ADDPD	-0x1f0(%RBP),%XMM1

    (380) 0x42adef PADDQ	-0x1e0(%RBP),%XMM2

    (380) 0x42adf7 MOVQ	%XMM2,%R9

    (380) 0x42adfc PSHUFD	$-0x12,%XMM2,%XMM7

    (380) 0x42ae01 MOVAPD	%XMM11,%XMM14

    (380) 0x42ae06 MOVQ	%XMM7,%R14

    (380) 0x42ae0b MOVAPD	%XMM6,%XMM7

    (380) 0x42ae0f MULPD	-0x1c0(%RBP),%XMM7

    (380) 0x42ae17 ADDPD	%XMM3,%XMM1

    (380) 0x42ae1b MOVAPD	%XMM4,%XMM3

    (380) 0x42ae1f MULPD	-0x1b0(%RBP),%XMM3

    (380) 0x42ae27 ADDPD	-0x1a0(%RBP),%XMM3

    (380) 0x42ae2f ADDPD	%XMM7,%XMM3

    (380) 0x42ae33 MOVDQA	%XMM2,%XMM7

    (380) 0x42ae37 PADDQ	0xff8d1(%RIP),%XMM7

    (380) 0x42ae3f MOVQ	%XMM7,%R15

    (380) 0x42ae44 MULPD	-0x220(%RBP),%XMM14

    (380) 0x42ae4d PSHUFD	$-0x12,%XMM7,%XMM7

    (380) 0x42ae52 MOVQ	%XMM7,%R12

    (380) 0x42ae57 MOVAPD	%XMM6,%XMM7

    (380) 0x42ae5b ADDPD	%XMM14,%XMM1

    (380) 0x42ae60 MOVAPD	%XMM4,%XMM14

    (380) 0x42ae65 MULPD	%XMM15,%XMM14

    (380) 0x42ae6a ADDPD	%XMM9,%XMM14

    (380) 0x42ae6f MULPD	%XMM8,%XMM7

    (380) 0x42ae74 ADDPD	%XMM7,%XMM14

    (380) 0x42ae79 MOVAPD	%XMM11,%XMM7

    (380) 0x42ae7e MULPD	-0x1d0(%RBP),%XMM7

    (380) 0x42ae86 ADDPD	%XMM7,%XMM3

    (380) 0x42ae8a MOVSD	(%R9),%XMM7

    (380) 0x42ae8f MOVHPD	(%R14),%XMM7

    (380) 0x42ae94 MULPD	%XMM1,%XMM7

    (380) 0x42ae98 MOVSD	(%R15),%XMM1

    (380) 0x42ae9d MOVHPD	(%R12),%XMM1

    (380) 0x42aea3 MULPD	%XMM3,%XMM1

    (380) 0x42aea7 MOVAPD	%XMM11,%XMM3

    (380) 0x42aeac MULPD	-0x190(%RBP),%XMM3

    (380) 0x42aeb4 ADDPD	%XMM3,%XMM14

    (380) 0x42aeb9 ADDPD	%XMM0,%XMM7

    (380) 0x42aebd MOVDQA	%XMM2,%XMM0

    (380) 0x42aec1 PADDQ	0xff857(%RIP),%XMM0

    (380) 0x42aec9 MOVQ	%XMM0,%R9

    (380) 0x42aece PSHUFD	$-0x12,%XMM0,%XMM0

    (380) 0x42aed3 MOVQ	%XMM0,%R14

    (380) 0x42aed8 MOVSD	(%R9),%XMM3

    (380) 0x42aedd MOVHPD	(%R14),%XMM3

    (380) 0x42aee2 MULPD	%XMM14,%XMM3

    (380) 0x42aee7 ADDPD	%XMM1,%XMM3

    (380) 0x42aeeb ADDPD	%XMM7,%XMM3

    (380) 0x42aeef MULPD	%XMM12,%XMM6

    (380) 0x42aef4 MULPD	%XMM10,%XMM4

    (380) 0x42aef9 ADDPD	%XMM5,%XMM4

    (380) 0x42aefd ADDPD	%XMM6,%XMM4

    (380) 0x42af01 MULPD	%XMM13,%XMM11

    (380) 0x42af06 ADDPD	%XMM11,%XMM4

    (380) 0x42af0b PADDQ	0xff81d(%RIP),%XMM2

    (380) 0x42af13 MOVQ	%XMM2,%R9

    (380) 0x42af18 PSHUFD	$-0x12,%XMM2,%XMM0

    (380) 0x42af1d MOVQ	%XMM0,%R14

    (380) 0x42af22 MOVSD	(%R9),%XMM0

    (380) 0x42af27 MOVHPD	(%R14),%XMM0

    (380) 0x42af2c MULPD	%XMM4,%XMM0

    (380) 0x42af30 ADDPD	%XMM3,%XMM0

    (380) 0x42af34 ADD	$0x2,%RDI

    (380) 0x42af38 CMP	%R11,%RDI

    (380) 0x42af3b JB	42ad90

  (378) 0x42af41 MOVAPD	%XMM0,%XMM2

  (378) 0x42af45 UNPCKHPD	%XMM0,%XMM2

  (378) 0x42af49 ADDSD	%XMM0,%XMM2

  (378) 0x42af4d CMP	%RBX,%R11

  (378) 0x42af50 MOVSD	-0x38(%RBP),%XMM6

  (378) 0x42af55 MOVAPD	-0x170(%RBP),%XMM7

  (378) 0x42af5d MOVAPD	-0x160(%RBP),%XMM8

  (378) 0x42af66 MOVAPD	-0x150(%RBP),%XMM15

  (378) 0x42af6f MOVAPD	-0x140(%RBP),%XMM9

  (378) 0x42af78 MOVAPD	-0x130(%RBP),%XMM10

  (378) 0x42af81 MOVAPD	-0x120(%RBP),%XMM11

  (378) 0x42af8a MOVAPD	-0x110(%RBP),%XMM12

  (378) 0x42af93 MOVAPD	-0x100(%RBP),%XMM13

  (378) 0x42af9c MOVDQA	-0xf0(%RBP),%XMM14

  (378) 0x42afa5 MOVAPD	-0xe0(%RBP),%XMM1

  (378) 0x42afad MOVAPD	-0xd0(%RBP),%XMM3

  (378) 0x42afb5 MOVAPD	-0xc0(%RBP),%XMM4

  (378) 0x42afbd MOVAPD	-0xb0(%RBP),%XMM5

  (378) 0x42afc5 MOVAPD	-0xa0(%RBP),%XMM0

  (378) 0x42afcd JE	42aad0

  (378) 0x42afd3 JMP	42b12c

0x42afd8 NOPL	(%RAX,%RAX,1)

  (378) 0x42afe0 LEA	0x1(%R8),%RDI

  (378) 0x42afe4 CMP	%RAX,%R8

  (378) 0x42afe7 MOV	%RDI,%R8

  (378) 0x42afea JNE	42aae4

(376) 0x42aff0 JMP	42aa20

  (378) 0x42aff5 MOV	%R15D,%EBX

  (378) 0x42aff8 AND	$-0x8,%EBX

  (378) 0x42affb MOV	-0x68(%RBP),%RDI

  (378) 0x42afff LEA	(%RDI,%R12,8),%RDI

  (378) 0x42b003 XOR	%R13D,%R13D

  (378) 0x42b006 XOR	%R11D,%R11D

  (378) 0x42b009 JMP	42b01d

0x42b00b NOPL	(%RAX,%RAX,1)

    (382) 0x42b010 ADD	$0x8,%R13

    (382) 0x42b014 CMP	%R13,%RBX

    (382) 0x42b017 JE	42ab28

    (382) 0x42b01d MOVSD	-0x38(%RDI,%R13,8),%XMM0

    (382) 0x42b024 LEA	(%R10,%R13,1),%R14

    (382) 0x42b028 UCOMISD	%XMM0,%XMM1

    (382) 0x42b02c JBE	42b040

    (382) 0x42b02e CMP	$-0x1,%R14D

    (382) 0x42b032 JE	42b040

    (382) 0x42b034 MOVSXD	%R11D,%R11

    (382) 0x42b037 MOVSD	%XMM0,(%RSI,%R11,8)

    (382) 0x42b03d INC	%R11D

    (382) 0x42b040 MOVSD	-0x30(%RDI,%R13,8),%XMM0

    (382) 0x42b047 UCOMISD	%XMM0,%XMM1

    (382) 0x42b04b JBE	42b05f

    (382) 0x42b04d CMP	$-0x2,%R14D

    (382) 0x42b051 JE	42b05f

    (382) 0x42b053 MOVSXD	%R11D,%R11

    (382) 0x42b056 MOVSD	%XMM0,(%RSI,%R11,8)

    (382) 0x42b05c INC	%R11D

    (382) 0x42b05f MOVSD	-0x28(%RDI,%R13,8),%XMM0

    (382) 0x42b066 UCOMISD	%XMM0,%XMM1

    (382) 0x42b06a JBE	42b07e

    (382) 0x42b06c CMP	$-0x3,%R14D

    (382) 0x42b070 JE	42b07e

    (382) 0x42b072 MOVSXD	%R11D,%R11

    (382) 0x42b075 MOVSD	%XMM0,(%RSI,%R11,8)

    (382) 0x42b07b INC	%R11D

    (382) 0x42b07e MOVSD	-0x20(%RDI,%R13,8),%XMM0

    (382) 0x42b085 UCOMISD	%XMM0,%XMM1

    (382) 0x42b089 JBE	42b09d

    (382) 0x42b08b CMP	$-0x4,%R14D

    (382) 0x42b08f JE	42b09d

    (382) 0x42b091 MOVSXD	%R11D,%R11

    (382) 0x42b094 MOVSD	%XMM0,(%RSI,%R11,8)

    (382) 0x42b09a INC	%R11D

    (382) 0x42b09d MOVSD	-0x18(%RDI,%R13,8),%XMM0

    (382) 0x42b0a4 UCOMISD	%XMM0,%XMM1

    (382) 0x42b0a8 JBE	42b0bc

    (382) 0x42b0aa CMP	$-0x5,%R14D

    (382) 0x42b0ae JE	42b0bc

    (382) 0x42b0b0 MOVSXD	%R11D,%R11

    (382) 0x42b0b3 MOVSD	%XMM0,(%RSI,%R11,8)

    (382) 0x42b0b9 INC	%R11D

    (382) 0x42b0bc MOVSD	-0x10(%RDI,%R13,8),%XMM0

    (382) 0x42b0c3 UCOMISD	%XMM0,%XMM1

    (382) 0x42b0c7 JBE	42b0db

    (382) 0x42b0c9 CMP	$-0x6,%R14D

    (382) 0x42b0cd JE	42b0db

    (382) 0x42b0cf MOVSXD	%R11D,%R11

    (382) 0x42b0d2 MOVSD	%XMM0,(%RSI,%R11,8)

    (382) 0x42b0d8 INC	%R11D

    (382) 0x42b0db MOVSD	-0x8(%RDI,%R13,8),%XMM0

    (382) 0x42b0e2 UCOMISD	%XMM0,%XMM1

    (382) 0x42b0e6 JBE	42b0fa

    (382) 0x42b0e8 CMP	$-0x7,%R14D

    (382) 0x42b0ec JE	42b0fa

    (382) 0x42b0ee MOVSXD	%R11D,%R11

    (382) 0x42b0f1 MOVSD	%XMM0,(%RSI,%R11,8)

    (382) 0x42b0f7 INC	%R11D

    (382) 0x42b0fa MOVSD	(%RDI,%R13,8),%XMM0

    (382) 0x42b100 UCOMISD	%XMM0,%XMM1

    (382) 0x42b104 JBE	42b010

    (382) 0x42b10a CMP	$-0x8,%R14D

    (382) 0x42b10e JE	42b010

    (382) 0x42b114 MOVSXD	%R11D,%R11

    (382) 0x42b117 MOVSD	%XMM0,(%RSI,%R11,8)

    (382) 0x42b11d INC	%R11D

    (382) 0x42b120 JMP	42b010

  (378) 0x42b125 XORPD	%XMM2,%XMM2

  (378) 0x42b129 XOR	%R11D,%R11D

  (378) 0x42b12c UNPCKLPD	-0x90(%RBP),%XMM15

  (378) 0x42b135 UNPCKLPD	%XMM4,%XMM8

  (378) 0x42b13a PUNPCKLQDQ	-0x180(%RBP),%XMM14

  (378) 0x42b143 UNPCKLPD	%XMM0,%XMM11

  (378) 0x42b148 UNPCKLPD	-0x80(%RBP),%XMM13

  (378) 0x42b14e UNPCKLPD	%XMM3,%XMM10

  (378) 0x42b153 UNPCKLPD	%XMM5,%XMM12

  (378) 0x42b158 UNPCKLPD	%XMM1,%XMM9

  (378) 0x42b15d NOPL	(%RAX)

    (379) 0x42b160 MOVSD	(%RSI,%R11,8),%XMM0

    (379) 0x42b166 MULSD	%XMM7,%XMM0

    (379) 0x42b16a CVTTPD2DQ	%XMM0,%XMM1

    (379) 0x42b16e CVTDQ2PD	%XMM1,%XMM1

    (379) 0x42b172 CVTTSD2SI	%XMM0,%EDI

    (379) 0x42b176 SUBSD	%XMM1,%XMM0

    (379) 0x42b17a MOVAPD	%XMM0,%XMM1

    (379) 0x42b17e MULSD	%XMM0,%XMM1

    (379) 0x42b182 MOVAPD	%XMM1,%XMM3

    (379) 0x42b186 MULSD	%XMM0,%XMM3

    (379) 0x42b18a UNPCKLPD	%XMM1,%XMM1

    (379) 0x42b18e MOVAPD	%XMM1,%XMM4

    (379) 0x42b192 MULPD	%XMM13,%XMM1

    (379) 0x42b197 UNPCKLPD	%XMM0,%XMM0

    (379) 0x42b19b MOVAPD	%XMM0,%XMM5

    (379) 0x42b19f UNPCKLPD	%XMM3,%XMM3

    (379) 0x42b1a3 MULPD	%XMM15,%XMM5

    (379) 0x42b1a8 ADDPD	%XMM14,%XMM5

    (379) 0x42b1ad ADDPD	%XMM1,%XMM5

    (379) 0x42b1b1 MOVAPD	%XMM3,%XMM1

    (379) 0x42b1b5 MULPD	%XMM12,%XMM1

    (379) 0x42b1ba ADDPD	%XMM1,%XMM5

    (379) 0x42b1be MULPD	%XMM8,%XMM0

    (379) 0x42b1c3 MULPD	%XMM10,%XMM4

    (379) 0x42b1c8 ADDPD	%XMM11,%XMM0

    (379) 0x42b1cd ADDPD	%XMM4,%XMM0

    (379) 0x42b1d1 MULPD	%XMM9,%XMM3

    (379) 0x42b1d6 MOVSXD	%EDI,%RDI

    (379) 0x42b1d9 ADDPD	%XMM3,%XMM0

    (379) 0x42b1dd MOVUPD	(%R10,%RDI,8),%XMM1

    (379) 0x42b1e3 MULPD	%XMM0,%XMM1

    (379) 0x42b1e7 MOVUPD	0x10(%R10,%RDI,8),%XMM0

    (379) 0x42b1ee MULPD	%XMM5,%XMM0

    (379) 0x42b1f2 ADDPD	%XMM1,%XMM0

    (379) 0x42b1f6 MOVAPD	%XMM0,%XMM1

    (379) 0x42b1fa UNPCKHPD	%XMM0,%XMM1

    (379) 0x42b1fe ADDSD	%XMM0,%XMM1

    (379) 0x42b202 ADDSD	%XMM1,%XMM2

    (379) 0x42b206 INC	%R11

    (379) 0x42b209 CMP	%R11,%RBX

    (379) 0x42b20c JNE	42b160

  (378) 0x42b212 JMP	42aad0

0x42b217 NOPW	(%RAX,%RAX,1)

(376) 0x42b220 MOV	0x90(%R14),%EBX

(376) 0x42b227 TEST	%EBX,%EBX

(376) 0x42b229 JLE	42aa15

(376) 0x42b22f MOV	%RDI,-0x30(%RBP)

(376) 0x42b233 MOV	0xa0(%R14),%RAX

(376) 0x42b23a MOV	0x1c8(%R14),%R14

(376) 0x42b241 MOV	0x18(%RAX),%R15

(376) 0x42b245 XORPD	%XMM6,%XMM6

(376) 0x42b249 XOR	%R12D,%R12D

(376) 0x42b24c JMP	42b260

0x42b24e XCHG	%AX,%AX

  (377) 0x42b250 ADDSD	%XMM1,%XMM6

  (377) 0x42b254 INC	%R12

  (377) 0x42b257 CMP	%R12,%RBX

  (377) 0x42b25a JE	42aa20

  (377) 0x42b260 MOVSXD	(%R15,%R12,4),%RAX

  (377) 0x42b264 MOV	(%R14,%RAX,8),%R13

  (377) 0x42b268 TEST	%R13,%R13

  (377) 0x42b26b JE	42b254

  (377) 0x42b26d MOV	-0x30(%RBP),%RAX

  (377) 0x42b271 MOVSD	(%RAX,%R12,8),%XMM0

  (377) 0x42b277 MOVSD	0x8(%R13),%XMM2

  (377) 0x42b27d XORPD	%XMM1,%XMM1

  (377) 0x42b281 UCOMISD	%XMM0,%XMM2

  (377) 0x42b285 JBE	42b250

  (377) 0x42b287 MULSD	0x238(%R13),%XMM0

  (377) 0x42b290 LEA	-0x70(%RBP),%RDI

  (377) 0x42b294 MOVSD	%XMM6,-0x38(%RBP)

  (377) 0x42b299 CALL	506aa0 <modf>

  (377) 0x42b29e CVTTSD2SI	-0x70(%RBP),%EAX

  (377) 0x42b2a3 CLTQ

  (377) 0x42b2a5 MOV	0x218(%R13),%RCX

  (377) 0x42b2ac MOVAPD	%XMM0,%XMM4

  (377) 0x42b2b0 MULSD	%XMM0,%XMM4

  (377) 0x42b2b4 MOVAPD	%XMM4,%XMM1

  (377) 0x42b2b8 MULSD	%XMM0,%XMM1

  (377) 0x42b2bc MOVSD	0x18(%R13),%XMM5

  (377) 0x42b2c2 MOVSD	0x20(%R13),%XMM6

  (377) 0x42b2c8 MOVHPD	0x38(%R13),%XMM6

  (377) 0x42b2ce MOVSD	0x28(%R13),%XMM3

  (377) 0x42b2d4 MOVSD	0x60(%R13),%XMM7

  (377) 0x42b2da MOVHPD	0x78(%R13),%XMM7

  (377) 0x42b2e0 MOVSD	0x30(%R13),%XMM2

  (377) 0x42b2e6 MOVAPD	%XMM4,%XMM8

  (377) 0x42b2eb UNPCKLPD	%XMM1,%XMM8

  (377) 0x42b2f0 MULPD	%XMM8,%XMM7

  (377) 0x42b2f5 MULPD	%XMM6,%XMM8

  (377) 0x42b2fa MOVHPD	0x40(%R13),%XMM5

  (377) 0x42b300 MOVSD	0x58(%R13),%XMM6

  (377) 0x42b306 MOVHPD	0x80(%R13),%XMM6

  (377) 0x42b30f UNPCKLPD	%XMM4,%XMM1

  (377) 0x42b313 MULPD	%XMM1,%XMM6

  (377) 0x42b317 ADDPD	%XMM7,%XMM6

  (377) 0x42b31b MULPD	%XMM5,%XMM1

  (377) 0x42b31f ADDPD	%XMM8,%XMM1

  (377) 0x42b324 MOVSD	0x68(%R13),%XMM4

  (377) 0x42b32a MOVHPD	0x88(%R13),%XMM4

  (377) 0x42b333 MOVHPD	0x48(%R13),%XMM3

  (377) 0x42b339 UNPCKLPD	%XMM0,%XMM0

  (377) 0x42b33d MULPD	%XMM0,%XMM3

  (377) 0x42b341 MULPD	%XMM4,%XMM0

  (377) 0x42b345 MOVSD	0x70(%R13),%XMM4

  (377) 0x42b34b MOVHPD	0x90(%R13),%XMM4

  (377) 0x42b354 ADDPD	%XMM0,%XMM4

  (377) 0x42b358 ADDPD	%XMM6,%XMM4

  (377) 0x42b35c MOVSD	-0x38(%RBP),%XMM6

  (377) 0x42b361 MOVHPD	0x50(%R13),%XMM2

  (377) 0x42b367 ADDPD	%XMM3,%XMM2

  (377) 0x42b36b ADDPD	%XMM1,%XMM2

  (377) 0x42b36f MOVUPD	(%RCX,%RAX,8),%XMM0

  (377) 0x42b374 MULPD	%XMM2,%XMM0

  (377) 0x42b378 MOVUPD	0x10(%RCX,%RAX,8),%XMM2

  (377) 0x42b37e MULPD	%XMM4,%XMM2

  (377) 0x42b382 ADDPD	%XMM0,%XMM2

  (377) 0x42b386 MOVAPD	%XMM2,%XMM1

  (377) 0x42b38a UNPCKHPD	%XMM2,%XMM1

  (377) 0x42b38e ADDSD	%XMM2,%XMM1

  (377) 0x42b392 JMP	42b250

0x42b397 ADD	$0x208,%RSP

0x42b39e POP	%RBX

0x42b39f POP	%R12

0x42b3a1 POP	%R13

0x42b3a3 POP	%R14

0x42b3a5 POP	%R15

0x42b3a7 POP	%RBP

0x42b3a8 RET

0x42b3a9 NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►94.97+	_ZN11qmcplusplus12WaveFunction[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:126	exec
○	main.extracted.107	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►2.49+	_ZN11qmcplusplus12WaveFunction[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:126	exec
○	main.extracted.107	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	stl_uninitialized.h:99	exec

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

Path /

Average path: Display a virtual path defined by average values of all real paths

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run icx_3

Source file and lines	OneBodyJastrowRef.h:133-155
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:133-155
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:166-173,179-182,229,236-260
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/shared_ptr_base.h:1296
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:919,1046,1064,1169
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229,249

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 11% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 3.13 to 0.22 cycles (14.27x speedup).

Details

All SSE/AVX instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

Matching between your function (in the source code) and the binary function

The binary function does not contain any FP arithmetical operations. The binary function is loading 16 bytes. The binary function is storing 24 bytes.

General properties

nb instructions	33
nb uops	25
loop length	125
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	3.13 cycles
front end	3.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	1.00	1.00	1.00	1.00	1.00	1.00	1.25	1.25	1.25	1.25	0.00	0.00	0.00	0.00	0.00	0.00
cycles	1.00	1.00	1.00	1.00	1.00	1.00	1.25	1.25	1.25	1.25	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	3.13
Dispatch	1.25
Overall L1	3.13

Vectorization ratios

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

all	11%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	10%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 3.13 cycles. At this rate:

2% of peak load performance is reached (5.12 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (7.68 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 3.13 to 1.25 cycles (2.50x speedup).

ASM code

In the binary file, the address of the function is: 42a9e0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x208,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RSI,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x8(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP (%RDX),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 42b397 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x9b7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOV %RDI,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 42aa5a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x7a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x208,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run icx_3

Source file and lines	OneBodyJastrowRef.h:133-155
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:133-155
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:166-173,179-182,229,236-260
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/shared_ptr_base.h:1296
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:919,1046,1064,1169
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229,249

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Details

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

Matching between your function (in the source code) and the binary function

The binary function does not contain any FP arithmetical operations. The binary function is loading 16 bytes. The binary function is storing 24 bytes.

General properties

nb instructions	33
nb uops	25
loop length	125
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	3.13 cycles
front end	3.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	1.00	1.00	1.00	1.00	1.00	1.00	1.25	1.25	1.25	1.25	0.00	0.00	0.00	0.00	0.00	0.00
cycles	1.00	1.00	1.00	1.00	1.00	1.00	1.25	1.25	1.25	1.25	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	3.13
Dispatch	1.25
Overall L1	3.13

Vectorization ratios

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

all	11%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	10%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 3.13 cycles. At this rate:

2% of peak load performance is reached (5.12 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (7.68 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 42a9e0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x208,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RSI,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x8(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP (%RDX),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 42b397 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x9b7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOV %RDI,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 42aa5a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x7a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x208,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::OneBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)–	0.02	0.04
▼Loop 376 - OneBodyJastrowRef.h:134-155 - exec–	0.01	0.01
▼Loop 378 - OneBodyJastrowRef.h:134-146 - exec–	0.00	0.01
○Loop 382 - BsplineFunctor.h:236-241 - exec	0.01	0.02
○Loop 379 - BsplineFunctor.h:246-260 - exec	0.00	0.01
○Loop 380 - BsplineFunctor.h:246-260 - exec	0.00	0.00
○Loop 381 - BsplineFunctor.h:236-241 - exec	0.00	0.00
○Loop 377 - BsplineFunctor.h:166-182 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

Type of elements and instruction set

Matching between your function (in the source code) and the binary function

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Vectorization

Details

Workaround

Execution units bottlenecks

Type of elements and instruction set

Matching between your function (in the source code) and the binary function

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code