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

	Function: miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios( ...	Module: exec	Source: TwoBodyJastrowRef.h:106-132 [...]	Coverage (incl. loops): 1.09% \| (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]; }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/optional: 433 - 952

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

433:       { return static_cast<const _Dp*>(this)->_M_payload._M_engaged; }

[...]

950: 	if (this->_M_is_engaged())

951: 	  return this->_M_get();

952: 	__throw_bad_optional_access();

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 106 - 132

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

106:   {

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

108:       ratios[k] = std::exp(Uat[VP.refPtcl] - computeU(VP.getRefPS(), VP.refPtcl, VP.getDistTableAB(myTableID).getDistRow(k).data()));

109:   }

[...]

126:     const int igt = P.GroupID[iat] * NumGroups;

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

128:     {

129:       const FuncType& f2(*F[igt + jg]);

130:       int iStart = P.first(jg);

131:       int iEnd   = P.last(jg);

132:       curUat += f2.evaluateV(iat, iStart, iEnd, dist, DistCompressed.data());

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 236 - 260

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

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); }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/refwrap.h: 338 - 338

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

338:       { return *_M_data; }

/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; }

0x430550 PUSH	%RBP

0x430551 MOV	%RSP,%RBP

0x430554 PUSH	%R15

0x430556 PUSH	%R14

0x430558 PUSH	%R13

0x43055a PUSH	%R12

0x43055c PUSH	%RBX

0x43055d SUB	$0x218,%RSP

0x430564 MOV	0x8(%RDX),%RAX

0x430568 MOV	%RDX,-0x40(%RBP)

0x43056c CMP	(%RDX),%RAX

0x43056f JE	430dda

0x430575 MOV	%RSI,%RCX

0x430578 MOV	%RDI,%R14

0x43057b XOR	%R15D,%R15D

0x43057e MOV	%RDI,-0x30(%RBP)

0x430582 MOV	%RSI,-0x38(%RBP)

0x430586 JMP	4305d2

0x430588 NOPL	(%RAX,%RAX,1)

(456) 0x430590 XORPD	%XMM6,%XMM6

(456) 0x430594 MOVSD	-0x48(%RBP),%XMM0

(456) 0x430599 SUBSD	%XMM6,%XMM0

(456) 0x43059d CALL	506a20 <exp>

(456) 0x4305a2 MOV	-0x40(%RBP),%RCX

(456) 0x4305a6 MOV	(%RCX),%RAX

(456) 0x4305a9 MOV	-0x50(%RBP),%R15

(456) 0x4305ad MOVSD	%XMM0,(%RAX,%R15,8)

(456) 0x4305b3 INC	%R15

(456) 0x4305b6 MOV	0x8(%RCX),%RCX

(456) 0x4305ba SUB	%RAX,%RCX

(456) 0x4305bd SAR	$0x3,%RCX

(456) 0x4305c1 CMP	%R15,%RCX

(456) 0x4305c4 MOV	-0x38(%RBP),%RCX

(456) 0x4305c8 MOV	-0x30(%RBP),%R14

(456) 0x4305cc JBE	430dda

(456) 0x4305d2 CMPB	$0,0x298(%RCX)

(456) 0x4305d9 JE	430dec

(456) 0x4305df MOVSXD	0x2a0(%RCX),%R12

(456) 0x4305e6 MOV	0xd8(%R14),%RAX

(456) 0x4305ed MOVSD	(%RAX,%R12,8),%XMM0

(456) 0x4305f3 MOVSD	%XMM0,-0x48(%RBP)

(456) 0x4305f8 MOV	0x290(%RCX),%RBX

(456) 0x4305ff MOV	0x248(%R14),%ESI

(456) 0x430606 MOV	%RCX,%RDI

(456) 0x430609 CALL	473f00 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

(456) 0x43060e MOV	0xa0(%R14),%RCX

(456) 0x430615 TEST	%RCX,%RCX

(456) 0x430618 MOV	%R15,-0x50(%RBP)

(456) 0x43061c JE	430590

(456) 0x430622 MOV	0x48(%RAX),%RAX

(456) 0x430626 LEA	(%R15,%R15,4),%RDX

(456) 0x43062a MOV	0x18(%RAX,%RDX,8),%RSI

(456) 0x43062f MOV	0x18(%RBX),%RAX

(456) 0x430633 MOV	(%RAX,%R12,4),%EAX

(456) 0x430637 IMUL	%ECX,%EAX

(456) 0x43063a MOV	0x1d0(%R14),%RDX

(456) 0x430641 MOV	0x200(%R14),%RDI

(456) 0x430648 MOV	%RDI,-0x80(%RBP)

(456) 0x43064c MOVSXD	%EAX,%RDI

(456) 0x43064f DEC	%RCX

(456) 0x430652 MOV	0x268(%RBX),%RAX

(456) 0x430659 MOV	0x18(%RAX),%R8

(456) 0x43065d MOV	%RSI,-0x68(%RBP)

(456) 0x430661 LEA	0x38(%RSI),%RAX

(456) 0x430665 MOV	%RAX,-0x60(%RBP)

(456) 0x430669 MOV	%R12,-0x70(%RBP)

(456) 0x43066d NEG	%R12D

(456) 0x430670 MOV	%R12,-0x58(%RBP)

(456) 0x430674 XORPD	%XMM6,%XMM6

(456) 0x430678 XOR	%R11D,%R11D

(456) 0x43067b JMP	430694

0x43067d NOPL	(%RAX)

  (457) 0x430680 ADDSD	%XMM1,%XMM6

  (457) 0x430684 LEA	0x1(%R11),%RAX

  (457) 0x430688 CMP	%RCX,%R11

  (457) 0x43068b MOV	%RAX,%R11

  (457) 0x43068e JE	430594

  (457) 0x430694 MOVSXD	(%R8,%R11,4),%R9

  (457) 0x430698 MOV	0x4(%R8,%R11,4),%R10D

  (457) 0x43069d SUB	%R9D,%R10D

  (457) 0x4306a0 XORPD	%XMM1,%XMM1

  (457) 0x4306a4 TEST	%R10D,%R10D

  (457) 0x4306a7 JLE	430680

  (457) 0x4306a9 LEA	(%R11,%RDI,1),%RAX

  (457) 0x4306ad MOV	-0x80(%RBP),%RSI

  (457) 0x4306b1 MOV	(%RSI,%RAX,8),%R13

  (457) 0x4306b5 MOVSD	0x8(%R13),%XMM1

  (457) 0x4306bb MOV	%R10D,%EAX

  (457) 0x4306be XOR	%R14D,%R14D

  (457) 0x4306c1 CMP	$0x8,%R10D

  (457) 0x4306c5 JAE	430b90

  (457) 0x4306cb MOV	%EAX,%R10D

  (457) 0x4306ce AND	$-0x8,%R10D

  (457) 0x4306d2 CMP	%RAX,%R10

  (457) 0x4306d5 JAE	430720

  (457) 0x4306d7 MOV	-0x70(%RBP),%RBX

  (457) 0x4306db SUB	%R9D,%EBX

  (457) 0x4306de MOV	-0x68(%RBP),%RSI

  (457) 0x4306e2 LEA	(%RSI,%R9,8),%R9

  (457) 0x4306e6 JMP	4306f8

0x4306e8 NOPL	(%RAX,%RAX,1)

    (460) 0x4306f0 INC	%R10

    (460) 0x4306f3 CMP	%R10,%RAX

    (460) 0x4306f6 JE	430720

    (460) 0x4306f8 MOVSD	(%R9,%R10,8),%XMM0

    (460) 0x4306fe UCOMISD	%XMM0,%XMM1

    (460) 0x430702 JBE	4306f0

    (460) 0x430704 CMP	%R10D,%EBX

    (460) 0x430707 JE	4306f0

    (460) 0x430709 MOVSXD	%R14D,%R14

    (460) 0x43070c MOVSD	%XMM0,(%RDX,%R14,8)

    (460) 0x430712 INC	%R14D

    (460) 0x430715 JMP	4306f0

0x430717 NOPW	(%RAX,%RAX,1)

  (457) 0x430720 XORPD	%XMM1,%XMM1

  (457) 0x430724 TEST	%R14D,%R14D

  (457) 0x430727 JLE	430680

  (457) 0x43072d MOVSD	0x238(%R13),%XMM7

  (457) 0x430736 MOV	0x218(%R13),%R15

  (457) 0x43073d MOVSD	0x18(%R13),%XMM8

  (457) 0x430743 MOVSD	0x20(%R13),%XMM9

  (457) 0x430749 MOVSD	0x28(%R13),%XMM10

  (457) 0x43074f MOVSD	0x38(%R13),%XMM3

  (457) 0x430755 MOVSD	0x40(%R13),%XMM5

  (457) 0x43075b MOVSD	0x48(%R13),%XMM2

  (457) 0x430761 MOVSD	0x58(%R13),%XMM11

  (457) 0x430767 MOVSD	0x60(%R13),%XMM12

  (457) 0x43076d MOVSD	0x68(%R13),%XMM13

  (457) 0x430773 MOVSD	0x78(%R13),%XMM0

  (457) 0x430779 MOVSD	0x80(%R13),%XMM1

  (457) 0x430782 MOVAPS	%XMM1,-0x90(%RBP)

  (457) 0x430789 MOVSD	0x88(%R13),%XMM1

  (457) 0x430792 MOVAPS	%XMM1,-0xa0(%RBP)

  (457) 0x430799 MOVQ	0x30(%R13),%XMM14

  (457) 0x43079f MOVQ	0x50(%R13),%XMM4

  (457) 0x4307a5 MOVSD	0x70(%R13),%XMM15

  (457) 0x4307ab MOV	%R14D,%R9D

  (457) 0x4307ae MOV	%R9,%R14

  (457) 0x4307b1 MOVSD	0x90(%R13),%XMM1

  (457) 0x4307ba MOV	$-0x2,%EAX

  (457) 0x4307bf AND	%RAX,%R14

  (457) 0x4307c2 MOVAPD	%XMM1,-0x190(%RBP)

  (457) 0x4307ca JE	430cd7

  (457) 0x4307d0 MOVSD	%XMM6,-0x78(%RBP)

  (457) 0x4307d5 MOVAPD	%XMM7,-0x180(%RBP)

  (457) 0x4307dd UNPCKLPD	%XMM7,%XMM7

  (457) 0x4307e1 MOVAPD	%XMM7,-0x240(%RBP)

  (457) 0x4307e9 MOVAPD	%XMM8,-0x170(%RBP)

  (457) 0x4307f2 UNPCKLPD	%XMM8,%XMM8

  (457) 0x4307f7 MOVAPD	%XMM8,-0x230(%RBP)

  (457) 0x430800 MOVAPD	%XMM9,-0x160(%RBP)

  (457) 0x430809 UNPCKLPD	%XMM9,%XMM9

  (457) 0x43080e MOVAPD	%XMM9,-0x220(%RBP)

  (457) 0x430817 MOVAPD	%XMM10,-0x150(%RBP)

  (457) 0x430820 UNPCKLPD	%XMM10,%XMM10

  (457) 0x430825 MOVAPD	%XMM10,-0x210(%RBP)

  (457) 0x43082e MOVDQA	%XMM14,-0x110(%RBP)

  (457) 0x430837 PUNPCKLQDQ	%XMM14,%XMM14

  (457) 0x43083c MOVDQA	%XMM14,-0x200(%RBP)

  (457) 0x430845 MOVAPD	%XMM0,%XMM10

  (457) 0x43084a MOVQ	%R15,%XMM0

  (457) 0x43084f PSHUFD	$0x44,%XMM0,%XMM0

  (457) 0x430854 MOVDQA	%XMM0,-0x1f0(%RBP)

  (457) 0x43085c MOVAPD	%XMM3,-0xe0(%RBP)

  (457) 0x430864 UNPCKLPD	%XMM3,%XMM3

  (457) 0x430868 MOVAPD	%XMM3,-0x1e0(%RBP)

  (457) 0x430870 MOVAPD	%XMM5,-0xc0(%RBP)

  (457) 0x430878 UNPCKLPD	%XMM5,%XMM5

  (457) 0x43087c MOVAPD	%XMM5,-0x1d0(%RBP)

  (457) 0x430884 MOVAPD	%XMM2,-0xf0(%RBP)

  (457) 0x43088c UNPCKLPD	%XMM2,%XMM2

  (457) 0x430890 MOVAPD	%XMM2,-0x1c0(%RBP)

  (457) 0x430898 MOVDQA	%XMM4,-0xd0(%RBP)

  (457) 0x4308a0 PUNPCKLQDQ	%XMM4,%XMM4

  (457) 0x4308a4 MOVDQA	%XMM4,-0x1b0(%RBP)

  (457) 0x4308ac MOVAPD	%XMM11,-0x140(%RBP)

  (457) 0x4308b5 UNPCKLPD	%XMM11,%XMM11

  (457) 0x4308ba MOVAPD	%XMM11,-0x1a0(%RBP)

  (457) 0x4308c3 MOVAPD	%XMM12,-0x130(%RBP)

  (457) 0x4308cc MOVAPD	%XMM12,%XMM6

  (457) 0x4308d1 UNPCKLPD	%XMM12,%XMM6

  (457) 0x4308d6 MOVAPD	%XMM13,-0x120(%RBP)

  (457) 0x4308df MOVAPD	%XMM13,%XMM7

  (457) 0x4308e4 UNPCKLPD	%XMM13,%XMM7

  (457) 0x4308e9 MOVAPD	%XMM15,-0x100(%RBP)

  (457) 0x4308f2 MOVAPD	%XMM15,%XMM9

  (457) 0x4308f7 UNPCKLPD	%XMM15,%XMM9

  (457) 0x4308fc MOVAPD	%XMM10,-0xb0(%RBP)

  (457) 0x430905 UNPCKLPD	%XMM10,%XMM10

  (457) 0x43090a MOVAPD	-0x90(%RBP),%XMM15

  (457) 0x430913 UNPCKLPD	%XMM15,%XMM15

  (457) 0x430918 MOVAPD	-0xa0(%RBP),%XMM11

  (457) 0x430921 UNPCKLPD	%XMM11,%XMM11

  (457) 0x430926 UNPCKLPD	%XMM1,%XMM1

  (457) 0x43092a XOR	%EAX,%EAX

  (457) 0x43092c PXOR	%XMM0,%XMM0

    (459) 0x430930 MOVAPD	(%RDX,%RAX,8),%XMM2

    (459) 0x430935 MULPD	-0x240(%RBP),%XMM2

    (459) 0x43093d CVTTPD2DQ	%XMM2,%XMM3

    (459) 0x430941 CVTDQ2PD	%XMM3,%XMM4

    (459) 0x430945 SUBPD	%XMM4,%XMM2

    (459) 0x430949 MOVAPD	%XMM2,%XMM8

    (459) 0x43094e MULPD	%XMM2,%XMM8

    (459) 0x430953 MOVAPD	%XMM8,%XMM4

    (459) 0x430958 MOVAPD	-0x220(%RBP),%XMM13

    (459) 0x430961 MULPD	%XMM8,%XMM13

    (459) 0x430966 MOVAPD	-0x210(%RBP),%XMM12

    (459) 0x43096f MULPD	%XMM2,%XMM12

    (459) 0x430974 PXOR	%XMM14,%XMM14

    (459) 0x430979 MULPD	%XMM2,%XMM4

    (459) 0x43097d PCMPGTD	%XMM3,%XMM14

    (459) 0x430982 PUNPCKLDQ	%XMM14,%XMM3

    (459) 0x430987 PSLLQ	$0x3,%XMM3

    (459) 0x43098c ADDPD	%XMM13,%XMM12

    (459) 0x430991 PADDQ	-0x1f0(%RBP),%XMM3

    (459) 0x430999 MOVQ	%XMM3,%RSI

    (459) 0x43099e PSHUFD	$-0x12,%XMM3,%XMM13

    (459) 0x4309a4 MOVAPD	%XMM4,%XMM14

    (459) 0x4309a9 MOVQ	%XMM13,%R10

    (459) 0x4309ae MOVAPD	-0x1d0(%RBP),%XMM13

    (459) 0x4309b7 MULPD	%XMM8,%XMM13

    (459) 0x4309bc MULPD	-0x230(%RBP),%XMM14

    (459) 0x4309c5 MOVAPD	-0x1c0(%RBP),%XMM5

    (459) 0x4309cd MULPD	%XMM2,%XMM5

    (459) 0x4309d1 ADDPD	%XMM13,%XMM5

    (459) 0x4309d6 ADDPD	-0x200(%RBP),%XMM12

    (459) 0x4309df MOVAPD	-0x1e0(%RBP),%XMM13

    (459) 0x4309e8 MULPD	%XMM4,%XMM13

    (459) 0x4309ed ADDPD	-0x1b0(%RBP),%XMM5

    (459) 0x4309f5 ADDPD	%XMM14,%XMM12

    (459) 0x4309fa ADDPD	%XMM13,%XMM5

    (459) 0x4309ff MOVDQA	%XMM3,%XMM14

    (459) 0x430a04 PADDQ	0xf9d03(%RIP),%XMM14

    (459) 0x430a0d MOVSD	(%RSI),%XMM13

    (459) 0x430a12 MOVQ	%XMM14,%RSI

    (459) 0x430a17 PSHUFD	$-0x12,%XMM14,%XMM14

    (459) 0x430a1d MOVHPD	(%R10),%XMM13

    (459) 0x430a22 MOVQ	%XMM14,%R10

    (459) 0x430a27 MOVSD	(%RSI),%XMM14

    (459) 0x430a2c MOVHPD	(%R10),%XMM14

    (459) 0x430a31 MULPD	%XMM5,%XMM14

    (459) 0x430a36 MOVAPD	%XMM6,%XMM5

    (459) 0x430a3a MULPD	%XMM8,%XMM5

    (459) 0x430a3f MULPD	%XMM12,%XMM13

    (459) 0x430a44 MOVAPD	%XMM7,%XMM12

    (459) 0x430a49 MULPD	%XMM2,%XMM12

    (459) 0x430a4e ADDPD	%XMM5,%XMM12

    (459) 0x430a53 MOVAPD	-0x1a0(%RBP),%XMM5

    (459) 0x430a5b MULPD	%XMM4,%XMM5

    (459) 0x430a5f ADDPD	%XMM9,%XMM12

    (459) 0x430a64 ADDPD	%XMM5,%XMM12

    (459) 0x430a69 ADDPD	%XMM0,%XMM13

    (459) 0x430a6e MOVDQA	%XMM3,%XMM0

    (459) 0x430a72 PADDQ	0xf9ca6(%RIP),%XMM0

    (459) 0x430a7a MOVQ	%XMM0,%RSI

    (459) 0x430a7f PSHUFD	$-0x12,%XMM0,%XMM0

    (459) 0x430a84 MOVQ	%XMM0,%R10

    (459) 0x430a89 MOVSD	(%RSI),%XMM5

    (459) 0x430a8d MOVHPD	(%R10),%XMM5

    (459) 0x430a92 MULPD	%XMM12,%XMM5

    (459) 0x430a97 ADDPD	%XMM14,%XMM5

    (459) 0x430a9c ADDPD	%XMM13,%XMM5

    (459) 0x430aa1 MULPD	%XMM15,%XMM8

    (459) 0x430aa6 MULPD	%XMM11,%XMM2

    (459) 0x430aab ADDPD	%XMM8,%XMM2

    (459) 0x430ab0 MULPD	%XMM10,%XMM4

    (459) 0x430ab5 ADDPD	%XMM1,%XMM2

    (459) 0x430ab9 ADDPD	%XMM4,%XMM2

    (459) 0x430abd PADDQ	0xf9c6b(%RIP),%XMM3

    (459) 0x430ac5 MOVQ	%XMM3,%RSI

    (459) 0x430aca PSHUFD	$-0x12,%XMM3,%XMM0

    (459) 0x430acf MOVQ	%XMM0,%R10

    (459) 0x430ad4 MOVSD	(%RSI),%XMM0

    (459) 0x430ad8 MOVHPD	(%R10),%XMM0

    (459) 0x430add MULPD	%XMM2,%XMM0

    (459) 0x430ae1 ADDPD	%XMM5,%XMM0

    (459) 0x430ae5 ADD	$0x2,%RAX

    (459) 0x430ae9 CMP	%R14,%RAX

    (459) 0x430aec JB	430930

  (457) 0x430af2 MOVAPD	%XMM0,%XMM1

  (457) 0x430af6 UNPCKHPD	%XMM0,%XMM1

  (457) 0x430afa ADDSD	%XMM0,%XMM1

  (457) 0x430afe CMP	%R9,%R14

  (457) 0x430b01 MOVSD	-0x78(%RBP),%XMM6

  (457) 0x430b06 MOVAPD	-0x180(%RBP),%XMM7

  (457) 0x430b0e MOVAPD	-0x170(%RBP),%XMM8

  (457) 0x430b17 MOVAPD	-0x160(%RBP),%XMM9

  (457) 0x430b20 MOVAPD	-0x150(%RBP),%XMM10

  (457) 0x430b29 MOVAPD	-0x140(%RBP),%XMM11

  (457) 0x430b32 MOVAPD	-0x130(%RBP),%XMM12

  (457) 0x430b3b MOVAPD	-0x120(%RBP),%XMM13

  (457) 0x430b44 MOVDQA	-0x110(%RBP),%XMM14

  (457) 0x430b4d MOVAPD	-0x100(%RBP),%XMM15

  (457) 0x430b56 MOVAPD	-0xf0(%RBP),%XMM2

  (457) 0x430b5e MOVAPD	-0xe0(%RBP),%XMM3

  (457) 0x430b66 MOVDQA	-0xd0(%RBP),%XMM4

  (457) 0x430b6e MOVAPD	-0xc0(%RBP),%XMM5

  (457) 0x430b76 MOVAPD	-0xb0(%RBP),%XMM0

  (457) 0x430b7e JE	430680

  (457) 0x430b84 JMP	430cde

0x430b89 NOPL	(%RAX)

  (457) 0x430b90 MOV	%EAX,%R15D

  (457) 0x430b93 AND	$-0x8,%R15D

  (457) 0x430b97 MOV	-0x60(%RBP),%RSI

  (457) 0x430b9b LEA	(%RSI,%R9,8),%R12

  (457) 0x430b9f MOV	-0x58(%RBP),%RSI

  (457) 0x430ba3 LEA	(%RSI,%R9,1),%R10D

  (457) 0x430ba7 XOR	%EBX,%EBX

  (457) 0x430ba9 XOR	%R14D,%R14D

  (457) 0x430bac JMP	430bbd

0x430bae XCHG	%AX,%AX

    (461) 0x430bb0 ADD	$0x8,%RBX

    (461) 0x430bb4 CMP	%RBX,%R15

    (461) 0x430bb7 JE	4306cb

    (461) 0x430bbd MOVSD	-0x38(%R12,%RBX,8),%XMM0

    (461) 0x430bc4 UCOMISD	%XMM0,%XMM1

    (461) 0x430bc8 JBE	430bdd

    (461) 0x430bca MOV	%R10D,%ESI

    (461) 0x430bcd ADD	%EBX,%ESI

    (461) 0x430bcf JE	430bdd

    (461) 0x430bd1 MOVSXD	%R14D,%R14

    (461) 0x430bd4 MOVSD	%XMM0,(%RDX,%R14,8)

    (461) 0x430bda INC	%R14D

    (461) 0x430bdd MOVSD	-0x30(%R12,%RBX,8),%XMM0

    (461) 0x430be4 UCOMISD	%XMM0,%XMM1

    (461) 0x430be8 JBE	430bff

    (461) 0x430bea LEA	(%R10,%RBX,1),%ESI

    (461) 0x430bee CMP	$-0x1,%ESI

    (461) 0x430bf1 JE	430bff

    (461) 0x430bf3 MOVSXD	%R14D,%R14

    (461) 0x430bf6 MOVSD	%XMM0,(%RDX,%R14,8)

    (461) 0x430bfc INC	%R14D

    (461) 0x430bff MOVSD	-0x28(%R12,%RBX,8),%XMM0

    (461) 0x430c06 UCOMISD	%XMM0,%XMM1

    (461) 0x430c0a JBE	430c21

    (461) 0x430c0c LEA	(%R10,%RBX,1),%ESI

    (461) 0x430c10 CMP	$-0x2,%ESI

    (461) 0x430c13 JE	430c21

    (461) 0x430c15 MOVSXD	%R14D,%R14

    (461) 0x430c18 MOVSD	%XMM0,(%RDX,%R14,8)

    (461) 0x430c1e INC	%R14D

    (461) 0x430c21 MOVSD	-0x20(%R12,%RBX,8),%XMM0

    (461) 0x430c28 UCOMISD	%XMM0,%XMM1

    (461) 0x430c2c JBE	430c43

    (461) 0x430c2e LEA	(%R10,%RBX,1),%ESI

    (461) 0x430c32 CMP	$-0x3,%ESI

    (461) 0x430c35 JE	430c43

    (461) 0x430c37 MOVSXD	%R14D,%R14

    (461) 0x430c3a MOVSD	%XMM0,(%RDX,%R14,8)

    (461) 0x430c40 INC	%R14D

    (461) 0x430c43 MOVSD	-0x18(%R12,%RBX,8),%XMM0

    (461) 0x430c4a UCOMISD	%XMM0,%XMM1

    (461) 0x430c4e JBE	430c65

    (461) 0x430c50 LEA	(%R10,%RBX,1),%ESI

    (461) 0x430c54 CMP	$-0x4,%ESI

    (461) 0x430c57 JE	430c65

    (461) 0x430c59 MOVSXD	%R14D,%R14

    (461) 0x430c5c MOVSD	%XMM0,(%RDX,%R14,8)

    (461) 0x430c62 INC	%R14D

    (461) 0x430c65 MOVSD	-0x10(%R12,%RBX,8),%XMM0

    (461) 0x430c6c UCOMISD	%XMM0,%XMM1

    (461) 0x430c70 JBE	430c87

    (461) 0x430c72 LEA	(%R10,%RBX,1),%ESI

    (461) 0x430c76 CMP	$-0x5,%ESI

    (461) 0x430c79 JE	430c87

    (461) 0x430c7b MOVSXD	%R14D,%R14

    (461) 0x430c7e MOVSD	%XMM0,(%RDX,%R14,8)

    (461) 0x430c84 INC	%R14D

    (461) 0x430c87 MOVSD	-0x8(%R12,%RBX,8),%XMM0

    (461) 0x430c8e UCOMISD	%XMM0,%XMM1

    (461) 0x430c92 JBE	430ca9

    (461) 0x430c94 LEA	(%R10,%RBX,1),%ESI

    (461) 0x430c98 CMP	$-0x6,%ESI

    (461) 0x430c9b JE	430ca9

    (461) 0x430c9d MOVSXD	%R14D,%R14

    (461) 0x430ca0 MOVSD	%XMM0,(%RDX,%R14,8)

    (461) 0x430ca6 INC	%R14D

    (461) 0x430ca9 MOVSD	(%R12,%RBX,8),%XMM0

    (461) 0x430caf UCOMISD	%XMM0,%XMM1

    (461) 0x430cb3 JBE	430bb0

    (461) 0x430cb9 LEA	(%R10,%RBX,1),%ESI

    (461) 0x430cbd CMP	$-0x7,%ESI

    (461) 0x430cc0 JE	430bb0

    (461) 0x430cc6 MOVSXD	%R14D,%R14

    (461) 0x430cc9 MOVSD	%XMM0,(%RDX,%R14,8)

    (461) 0x430ccf INC	%R14D

    (461) 0x430cd2 JMP	430bb0

  (457) 0x430cd7 XORPD	%XMM1,%XMM1

  (457) 0x430cdb XOR	%R14D,%R14D

  (457) 0x430cde UNPCKLPD	-0x90(%RBP),%XMM11

  (457) 0x430ce7 UNPCKLPD	%XMM5,%XMM8

  (457) 0x430cec UNPCKLPD	%XMM0,%XMM12

  (457) 0x430cf1 UNPCKLPD	%XMM3,%XMM9

  (457) 0x430cf6 UNPCKLPD	-0xa0(%RBP),%XMM13

  (457) 0x430cff UNPCKLPD	%XMM2,%XMM10

  (457) 0x430d04 UNPCKLPD	-0x190(%RBP),%XMM15

  (457) 0x430d0d PUNPCKLQDQ	%XMM4,%XMM14

  (457) 0x430d12 NOPW	%CS:(%RAX,%RAX,1)

    (458) 0x430d20 MOVSD	(%RDX,%R14,8),%XMM0

    (458) 0x430d26 MULSD	%XMM7,%XMM0

    (458) 0x430d2a CVTTPD2DQ	%XMM0,%XMM2

    (458) 0x430d2e CVTDQ2PD	%XMM2,%XMM2

    (458) 0x430d32 CVTTSD2SI	%XMM0,%EAX

    (458) 0x430d36 SUBSD	%XMM2,%XMM0

    (458) 0x430d3a MOVAPD	%XMM0,%XMM2

    (458) 0x430d3e MULSD	%XMM0,%XMM2

    (458) 0x430d42 MOVAPD	%XMM2,%XMM3

    (458) 0x430d46 MULSD	%XMM0,%XMM3

    (458) 0x430d4a MOVAPD	%XMM2,%XMM4

    (458) 0x430d4e UNPCKLPD	%XMM3,%XMM4

    (458) 0x430d52 MOVAPD	%XMM12,%XMM5

    (458) 0x430d57 MULPD	%XMM4,%XMM5

    (458) 0x430d5b UNPCKLPD	%XMM2,%XMM3

    (458) 0x430d5f MOVAPD	%XMM3,%XMM2

    (458) 0x430d63 MULPD	%XMM9,%XMM4

    (458) 0x430d68 MULPD	%XMM8,%XMM3

    (458) 0x430d6d ADDPD	%XMM4,%XMM3

    (458) 0x430d71 MULPD	%XMM11,%XMM2

    (458) 0x430d76 ADDPD	%XMM5,%XMM2

    (458) 0x430d7a UNPCKLPD	%XMM0,%XMM0

    (458) 0x430d7e MOVAPD	%XMM10,%XMM4

    (458) 0x430d83 MULPD	%XMM0,%XMM4

    (458) 0x430d87 ADDPD	%XMM14,%XMM4

    (458) 0x430d8c ADDPD	%XMM3,%XMM4

    (458) 0x430d90 CLTQ

    (458) 0x430d92 MULPD	%XMM13,%XMM0

    (458) 0x430d97 ADDPD	%XMM15,%XMM0

    (458) 0x430d9c ADDPD	%XMM2,%XMM0

    (458) 0x430da0 MOVUPD	(%R15,%RAX,8),%XMM2

    (458) 0x430da6 MULPD	%XMM4,%XMM2

    (458) 0x430daa MOVUPD	0x10(%R15,%RAX,8),%XMM3

    (458) 0x430db1 MULPD	%XMM0,%XMM3

    (458) 0x430db5 ADDPD	%XMM2,%XMM3

    (458) 0x430db9 MOVAPD	%XMM3,%XMM0

    (458) 0x430dbd UNPCKHPD	%XMM3,%XMM0

    (458) 0x430dc1 ADDSD	%XMM3,%XMM0

    (458) 0x430dc5 ADDSD	%XMM0,%XMM1

    (458) 0x430dc9 INC	%R14

    (458) 0x430dcc CMP	%R14,%R9

    (458) 0x430dcf JNE	430d20

  (457) 0x430dd5 JMP	430680

0x430dda ADD	$0x218,%RSP

0x430de1 POP	%RBX

0x430de2 POP	%R12

0x430de4 POP	%R13

0x430de6 POP	%R14

0x430de8 POP	%R15

0x430dea POP	%RBP

0x430deb RET

0x430dec CALL	430f00 <_ZSt27__throw_bad_optional_accessv>

0x430df1 NOPW	%CS:(%RAX,%RAX,1)

0x430dfb NOPL	(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
►95.19+	_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
►2.67+	_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	TwoBodyJastrowRef.h:106-132
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
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/optional:433,950-952
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:106-109,126-132
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: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
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/refwrap.h:338
/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 3.50 to 0.24 cycles (14.36x 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

CALL instructions

Detected function call instructions.

Details

Calling (and then returning from) a function prevents many compiler optimizations (like vectorization), breaks control flow (which reduces pipeline performance) and executes extra instructions to save/restore the registers used inside it, which is very expensive (dozens of cycles). Consider to inline small functions.

std::__throw_bad_optional_access(): 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/optional:952

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	35
nb uops	28
loop length	131
used x86 registers	12
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	3.50 cycles
front end	3.50 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	1.33	1.33	1.33	1.50	1.50	1.50	1.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	1.00	1.00	1.00	1.33	1.33	1.33	1.50	1.50	1.50	1.50	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	3.50
Dispatch	1.50
Overall L1	3.50

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 3.50 cycles. At this rate:

1% of peak load performance is reached (4.57 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (6.86 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 3.50 to 1.50 cycles (2.33x speedup).

ASM code

In the binary file, the address of the function is: 430550

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 $0x218,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
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,-0x40(%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 430dda <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x88a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
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,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RSI,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 4305d2 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x82>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	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
NOPL (%RAX)	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 $0x218,%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
CALL 430f00 <_ZSt27__throw_bad_optional_accessv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
NOPW %CS:(%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

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	TwoBodyJastrowRef.h:106-132
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
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/optional:433,950-952
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:106-109,126-132
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: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
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/refwrap.h:338
/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

CALL instructions

Detected function call instructions.

Details

std::__throw_bad_optional_access(): 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/optional:952

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	35
nb uops	28
loop length	131
used x86 registers	12
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	3.50 cycles
front end	3.50 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	1.33	1.33	1.33	1.50	1.50	1.50	1.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	1.00	1.00	1.00	1.33	1.33	1.33	1.50	1.50	1.50	1.50	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	3.50
Dispatch	1.50
Overall L1	3.50

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 3.50 cycles. At this rate:

1% of peak load performance is reached (4.57 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (6.86 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: 430550

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 $0x218,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
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,-0x40(%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 430dda <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x88a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
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,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RSI,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 4305d2 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x82>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	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
NOPL (%RAX)	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 $0x218,%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
CALL 430f00 <_ZSt27__throw_bad_optional_accessv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
NOPW %CS:(%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

Name	Coverage (%)	Time (s)
▼miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)–	1.09	1.82
▼Loop 456 - TwoBodyJastrowRef.h:107-132 - exec–	0.00	0.01
▼Loop 457 - BsplineFunctor.h:236-260 - exec–	0.01	0.02
○Loop 461 - BsplineFunctor.h:236-241 - exec	1.02	1.69
○Loop 459 - BsplineFunctor.h:246-260 - exec	0.06	0.10
○Loop 458 - BsplineFunctor.h:246-260 - exec	0.00	0.01
○Loop 460 - BsplineFunctor.h:236-241 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

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

CALL instructions

Details

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