OV - exec - Function miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, 3u> > >&, qmcplusplus::ParticleAttrib<double, std::allocator<double> >&, bool)

	Function: miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateGL(qmcp ...	Module: exec	Source: TwoBodyJastrowRef.h:268-432 [...]	Coverage (incl. loops): 0.05% \| (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/bits/stl_numeric.h: 140 - 141

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

140:       for (; __first != __last; ++__first)

141: 	__init = _GLIBCXX_MOVE_IF_20(__init) + *__first;

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 268 - 432

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

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

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

270:   {

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

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

273:     int iEnd   = std::min(jelmax, P.last(jg));

274:     f2.evaluateVGL(iat, iStart, iEnd, dist, u, du, d2u, DistCompressed.data(), DistIndice.data());

[...]

360:   const auto& d_table = P.getDistTableAA(myTableID);

361:   for (int ig = 0; ig < NumGroups; ++ig)

362:   {

363:     const int igt = ig * NumGroups;

364:     for (int iat = P.first(ig), last = P.last(ig); iat < last; ++iat)

365:     {

366:       computeU3(P, iat, d_table.getDistRow(iat).data(), cur_u.data(), cur_du.data(), cur_d2u.data(), true);

367:       Uat[iat] = std::accumulate(cur_u.begin(), cur_u.begin() + iat, valT());

[...]

375:       for (int jat = 0; jat < iat; ++jat)

376:         lap += d2u[jat] + lapfac * du[jat];

377:       for (int idim = 0; idim < OHMMS_DIM; ++idim)

378:       {

379:         const valT* restrict dX = displ.data(idim);

380:         valT s                  = valT();

381:         for (int jat = 0; jat < iat; ++jat)

382:           s += du[jat] * dX[jat];

383:         grad[idim] = s;

384:       }

385:       dUat(iat)  = grad;

386:       d2Uat[iat] = -lap;

387:       // add the contribution from the upper triangle

388:       for (int jat = 0; jat < iat; jat++)

389:       {

390:         Uat[jat] += u[jat];

391:         d2Uat[jat] -= d2u[jat] + lapfac * du[jat];

[...]

397:         for (int jat = 0; jat < iat; jat++)

398:           save_g[jat] -= du[jat] * dX[jat];

[...]

419: {

420:   if (fromscratch)

421:     recompute(P);

422:   LogValue = valT(0);

423:   for (int iat = 0; iat < N; ++iat)

424:   {

425:     LogValue += Uat[iat];

426:     G[iat] += dUat[iat];

427:     L[iat] += d2Uat[iat];

428:   }

429:

430:   constexpr valT mhalf(-0.5);

431:   LogValue = mhalf * LogValue;

432: }

/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: 1064 - 1169

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

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/stl_algobase.h: 924 - 1115

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

924: 	*__first = __tmp;

[...]

1115:       if (__n <= 0)

/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; }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h: 1028 - 1182

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

1028:       : _M_current(__i) { }

[...]

1182:     { return __lhs.base() != __rhs.base(); }

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/DistanceTable.h: 268 - 268

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

268:   const DistRow& getDistRow(int iel) const { return distances_[iel]; }

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 94

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

94:     (const_cast<T1&>(a) += b);

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 231 - 273

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

231:   inline const AoSElement_t operator[](size_t i) const { return AoSElement_t(myData + i, nGhosts); }

[...]

244:         *(_base + M * i) = rhs[i];

[...]

263:   inline Accessor operator()(size_t i) { return Accessor(myData + i, nGhosts); }

[...]

273:   inline const T* restrict data(size_t i) const { return myData + i * nGhosts; }

0x42faa0 PUSH	%RBP

0x42faa1 MOV	%RSP,%RBP

0x42faa4 PUSH	%R15

0x42faa6 PUSH	%R14

0x42faa8 PUSH	%R13

0x42faaa PUSH	%R12

0x42faac PUSH	%RBX

0x42faad SUB	$0x78,%RSP

0x42fab1 MOV	%RCX,-0x98(%RBP)

0x42fab8 MOV	%RDX,-0x90(%RBP)

0x42fabf MOV	%RSI,-0x60(%RBP)

0x42fac3 MOV	%RDI,%RBX

0x42fac6 TEST	%R8B,%R8B

0x42fac9 JE	430459

0x42facf MOV	0x248(%RBX),%ESI

0x42fad5 MOV	-0x60(%RBP),%RDI

0x42fad9 CALL	473ed0 <_ZNK11qmcplusplus11ParticleSet14getDistTableAAEi>

0x42fade MOV	%RAX,-0x88(%RBP)

0x42fae5 MOV	0xa0(%RBX),%R10

0x42faec TEST	%R10,%R10

0x42faef JE	430459

0x42faf5 XOR	%ECX,%ECX

0x42faf7 MOVSD	0xf9639(%RIP),%XMM6

0x42faff MOVAPD	0xfac39(%RIP),%XMM7

0x42fb07 MOV	%R10,%R12

0x42fb0a MOV	%RBX,-0x70(%RBP)

0x42fb0e JMP	42fb29

  (435) 0x42fb10 MOV	%R12,%RAX

  (435) 0x42fb13 MOV	-0xa0(%RBP),%RCX

  (435) 0x42fb1a INC	%RCX

  (435) 0x42fb1d MOV	%RAX,%R12

  (435) 0x42fb20 CMP	%RCX,%RAX

  (435) 0x42fb23 JBE	430459

  (435) 0x42fb29 MOV	-0x60(%RBP),%RAX

  (435) 0x42fb2d MOV	0x268(%RAX),%RAX

  (435) 0x42fb34 MOV	0x18(%RAX),%RAX

  (435) 0x42fb38 MOVSXD	(%RAX,%RCX,4),%RSI

  (435) 0x42fb3c MOV	0x4(%RAX,%RCX,4),%EAX

  (435) 0x42fb40 CMP	%EAX,%ESI

  (435) 0x42fb42 MOV	%RCX,-0xa0(%RBP)

  (435) 0x42fb49 JGE	42fb10

(436) 0x42fb4b MOV	%EAX,-0x7c(%RBP)

(436) 0x42fb4e MOV	0x140(%RBX),%R9

(436) 0x42fb55 MOV	0x158(%RBX),%R13

(436) 0x42fb5c MOV	0x170(%RBX),%RDI

(436) 0x42fb63 JMP	42fb7b

0x42fb65 NOPW	%CS:(%RAX,%RAX,1)

(436) 0x42fb70 INC	%RSI

(436) 0x42fb73 MOV	%R10,%RAX

(436) 0x42fb76 CMP	%ESI,-0x7c(%RBP)

(436) 0x42fb79 JE	42fb13

(436) 0x42fb7b MOV	%RDI,-0x38(%RBP)

(436) 0x42fb7f MOV	-0x88(%RBP),%RAX

(436) 0x42fb86 MOV	0x48(%RAX),%RAX

(436) 0x42fb8a LEA	(%RSI,%RSI,4),%RCX

(436) 0x42fb8e MOV	%RCX,-0x48(%RBP)

(436) 0x42fb92 MOV	0x18(%RAX,%RCX,8),%R8

(436) 0x42fb97 TEST	%RSI,%RSI

(436) 0x42fb9a MOV	%RSI,-0x68(%RBP)

(436) 0x42fb9e MOV	%R9,-0x50(%RBP)

(436) 0x42fba2 JLE	42fc04

(436) 0x42fba4 MOV	%ESI,%EDX

(436) 0x42fba6 SAL	$0x3,%RDX

(436) 0x42fbaa MOV	%R9,%RDI

(436) 0x42fbad XOR	%ESI,%ESI

(436) 0x42fbaf MOV	%RBX,%R14

(436) 0x42fbb2 MOV	%R12,%RBX

(436) 0x42fbb5 MOV	%RDX,%R12

(436) 0x42fbb8 MOV	%R10,-0x40(%RBP)

(436) 0x42fbbc MOV	%R8,%R15

(436) 0x42fbbf CALL	519fe0 <_intel_fast_memset>

(436) 0x42fbc4 MOV	%R13,%RDI

(436) 0x42fbc7 XOR	%ESI,%ESI

(436) 0x42fbc9 MOV	%R12,%RDX

(436) 0x42fbcc CALL	519fe0 <_intel_fast_memset>

(436) 0x42fbd1 MOV	-0x38(%RBP),%RDI

(436) 0x42fbd5 XOR	%ESI,%ESI

(436) 0x42fbd7 MOV	%R12,%RDX

(436) 0x42fbda MOV	%RBX,%R12

(436) 0x42fbdd MOV	%R14,%RBX

(436) 0x42fbe0 CALL	519fe0 <_intel_fast_memset>

(436) 0x42fbe5 MOV	%R15,%R8

(436) 0x42fbe8 MOV	-0x50(%RBP),%R9

(436) 0x42fbec MOV	-0x40(%RBP),%R10

(436) 0x42fbf0 MOV	-0x68(%RBP),%RSI

(436) 0x42fbf4 MOVAPD	0xfab44(%RIP),%XMM7

(436) 0x42fbfc MOVSD	0xf9534(%RIP),%XMM6

(436) 0x42fc04 TEST	%R12,%R12

(436) 0x42fc07 JE	42fcd0

(436) 0x42fc0d MOV	-0x60(%RBP),%RAX

(436) 0x42fc11 MOV	0x18(%RAX),%RAX

(436) 0x42fc15 IMUL	(%RAX,%RSI,4),%R12D

(436) 0x42fc1a MOVSXD	%R12D,%RAX

(436) 0x42fc1d SAL	$0x3,%RAX

(436) 0x42fc21 MOV	%RAX,-0x40(%RBP)

(436) 0x42fc25 MOV	$0x1,%R12D

(436) 0x42fc2b MOV	%R13,%R15

(436) 0x42fc2e MOV	-0x38(%RBP),%R13

(436) 0x42fc32 NOPW	%CS:(%RAX,%RAX,1)

  (438) 0x42fc40 MOV	0x200(%RBX),%RAX

  (438) 0x42fc47 ADD	-0x40(%RBP),%RAX

  (438) 0x42fc4b MOV	-0x8(%RAX,%R12,8),%RDI

  (438) 0x42fc50 MOV	-0x60(%RBP),%RAX

  (438) 0x42fc54 MOV	0x268(%RAX),%RAX

  (438) 0x42fc5b MOV	0x18(%RAX),%RAX

  (438) 0x42fc5f MOV	-0x4(%RAX,%R12,4),%EDX

  (438) 0x42fc64 MOV	(%RAX,%R12,4),%ECX

  (438) 0x42fc68 CMP	%ESI,%ECX

  (438) 0x42fc6a CMOVGE	%ESI,%ECX

  (438) 0x42fc6d MOV	%R8,%R14

  (438) 0x42fc70 PUSHQ	0x1e8(%RBX)

  (438) 0x42fc76 PUSHQ	0x1d0(%RBX)

  (438) 0x42fc7c PUSH	%R13

  (438) 0x42fc7e PUSH	%R15

  (438) 0x42fc80 CALL	42c890 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi>

  (438) 0x42fc85 MOV	%R14,%R8

  (438) 0x42fc88 MOV	-0x50(%RBP),%R9

  (438) 0x42fc8c MOV	-0x68(%RBP),%RSI

  (438) 0x42fc90 ADD	$0x20,%RSP

  (438) 0x42fc94 MOV	%R12D,%EAX

  (438) 0x42fc97 MOV	0xa0(%RBX),%R10

  (438) 0x42fc9e INC	%R12

  (438) 0x42fca1 CMP	%RAX,%R10

  (438) 0x42fca4 JA	42fc40

(436) 0x42fca6 MOV	0x140(%RBX),%R9

(436) 0x42fcad MOV	%R10,%R12

(436) 0x42fcb0 MOVSD	0xf9480(%RIP),%XMM6

(436) 0x42fcb8 MOVAPD	0xfaa80(%RIP),%XMM7

(436) 0x42fcc0 JMP	42fcd3

0x42fcc2 NOPW	%CS:(%RAX,%RAX,1)

(436) 0x42fcd0 XOR	%R12D,%R12D

(436) 0x42fcd3 LEA	(,%RSI,8),%RAX

(436) 0x42fcdb XORPD	%XMM0,%XMM0

(436) 0x42fcdf XORPD	%XMM1,%XMM1

(436) 0x42fce3 TEST	%RAX,%RAX

(436) 0x42fce6 JE	42fd84

(436) 0x42fcec CMP	$0x8,%RSI

(436) 0x42fcf0 JB	42fd38

(436) 0x42fcf2 MOV	%RSI,%RAX

(436) 0x42fcf5 SHR	$0x3,%RAX

(436) 0x42fcf9 MOV	%R9,%RCX

(436) 0x42fcfc NOPL	(%RAX)

  (437) 0x42fd00 MOVUPD	(%RCX),%XMM2

  (437) 0x42fd04 MOVUPD	0x10(%RCX),%XMM3

  (437) 0x42fd09 MOVUPD	0x20(%RCX),%XMM4

  (437) 0x42fd0e ADDPD	%XMM2,%XMM4

  (437) 0x42fd12 MOVUPD	0x30(%RCX),%XMM2

  (437) 0x42fd17 ADDPD	%XMM3,%XMM2

  (437) 0x42fd1b ADDPD	%XMM4,%XMM2

  (437) 0x42fd1f MOVAPD	%XMM2,%XMM3

  (437) 0x42fd23 UNPCKHPD	%XMM2,%XMM3

  (437) 0x42fd27 ADDSD	%XMM2,%XMM3

  (437) 0x42fd2b ADDSD	%XMM3,%XMM1

  (437) 0x42fd2f ADD	$0x40,%RCX

  (437) 0x42fd33 DEC	%RAX

  (437) 0x42fd36 JNE	42fd00

(436) 0x42fd38 MOV	%ESI,%ECX

(436) 0x42fd3a AND	$0x7,%ECX

(436) 0x42fd3d DEC	%RCX

(436) 0x42fd40 CMP	$0x6,%RCX

(436) 0x42fd44 JA	42fd84

0x42fd46 MOV	%RSI,%RAX

0x42fd49 AND	$-0x8,%RAX

0x42fd4d JMP	0x52ac88(,%RCX,8)

0x42fd54 ADDSD	0x30(%R9,%RAX,8),%XMM1

0x42fd5b ADDSD	0x28(%R9,%RAX,8),%XMM1

0x42fd62 ADDSD	0x20(%R9,%RAX,8),%XMM1

0x42fd69 ADDSD	0x18(%R9,%RAX,8),%XMM1

0x42fd70 ADDSD	0x10(%R9,%RAX,8),%XMM1

0x42fd77 ADDSD	0x8(%R9,%RAX,8),%XMM1

0x42fd7e ADDSD	(%R9,%RAX,8),%XMM1

(436) 0x42fd84 MOV	0xd8(%RBX),%RDX

(436) 0x42fd8b MOVSD	%XMM1,(%RDX,%RSI,8)

(436) 0x42fd90 MOV	0x158(%RBX),%R13

(436) 0x42fd97 MOV	0x170(%RBX),%RDI

(436) 0x42fd9e MOV	-0x88(%RBP),%RAX

(436) 0x42fda5 MOV	0x60(%RAX),%RAX

(436) 0x42fda9 TEST	%RSI,%RSI

(436) 0x42fdac JLE	42fe3c

(436) 0x42fdb2 MOV	%RSI,%RCX

(436) 0x42fdb5 AND	$-0x2,%RCX

(436) 0x42fdb9 JE	42fe10

(436) 0x42fdbb LEA	-0x1(%RCX),%R8

(436) 0x42fdbf XORPD	%XMM1,%XMM1

(436) 0x42fdc3 MOV	%RDI,%R11

(436) 0x42fdc6 XOR	%EDI,%EDI

(436) 0x42fdc8 NOPL	(%RAX,%RAX,1)

  (455) 0x42fdd0 MOVUPD	(%R13,%RDI,8),%XMM0

  (455) 0x42fdd7 ADDPD	%XMM0,%XMM0

  (455) 0x42fddb MOVUPD	(%R11,%RDI,8),%XMM2

  (455) 0x42fde1 ADDPD	%XMM2,%XMM1

  (455) 0x42fde5 ADDPD	%XMM0,%XMM1

  (455) 0x42fde9 ADD	$0x2,%RDI

  (455) 0x42fded CMP	%R8,%RDI

  (455) 0x42fdf0 JLE	42fdd0

(436) 0x42fdf2 MOVAPD	%XMM1,%XMM0

(436) 0x42fdf6 UNPCKHPD	%XMM1,%XMM0

(436) 0x42fdfa ADDSD	%XMM1,%XMM0

(436) 0x42fdfe CMP	%RCX,%RSI

(436) 0x42fe01 MOV	%R11,%RDI

(436) 0x42fe04 JNE	42fe20

(436) 0x42fe06 JMP	42fe3c

0x42fe08 NOPL	(%RAX,%RAX,1)

(436) 0x42fe10 XORPD	%XMM0,%XMM0

(436) 0x42fe14 XOR	%ECX,%ECX

(436) 0x42fe16 NOPW	%CS:(%RAX,%RAX,1)

  (454) 0x42fe20 MOVSD	(%R13,%RCX,8),%XMM1

  (454) 0x42fe27 ADDSD	(%RDI,%RCX,8),%XMM0

  (454) 0x42fe2c ADDSD	%XMM1,%XMM1

  (454) 0x42fe30 ADDSD	%XMM1,%XMM0

  (454) 0x42fe34 INC	%RCX

  (454) 0x42fe37 CMP	%RCX,%RSI

  (454) 0x42fe3a JNE	42fe20

(436) 0x42fe3c MOV	-0x48(%RBP),%RCX

(436) 0x42fe40 MOV	0x8(%RAX,%RCX,8),%R14

(436) 0x42fe45 MOV	0x18(%RAX,%RCX,8),%RAX

(436) 0x42fe4a XORPD	%XMM1,%XMM1

(436) 0x42fe4e XORPD	%XMM2,%XMM2

(436) 0x42fe52 TEST	%RSI,%RSI

(436) 0x42fe55 MOV	%RDI,-0x38(%RBP)

(436) 0x42fe59 JLE	42fed9

(436) 0x42fe5b MOV	%RSI,%R8

(436) 0x42fe5e AND	$-0x2,%R8

(436) 0x42fe62 JE	42feb0

(436) 0x42fe64 LEA	-0x1(%R8),%RCX

(436) 0x42fe68 XORPD	%XMM3,%XMM3

(436) 0x42fe6c XOR	%EDI,%EDI

(436) 0x42fe6e XCHG	%AX,%AX

  (453) 0x42fe70 MOVUPD	(%RAX,%RDI,8),%XMM2

  (453) 0x42fe75 MOVUPD	(%R13,%RDI,8),%XMM4

  (453) 0x42fe7c MULPD	%XMM2,%XMM4

  (453) 0x42fe80 ADDPD	%XMM4,%XMM3

  (453) 0x42fe84 ADD	$0x2,%RDI

  (453) 0x42fe88 CMP	%RCX,%RDI

  (453) 0x42fe8b JLE	42fe70

(436) 0x42fe8d MOVAPD	%XMM3,%XMM2

(436) 0x42fe91 UNPCKHPD	%XMM3,%XMM2

(436) 0x42fe95 ADDSD	%XMM3,%XMM2

(436) 0x42fe99 CMP	%R8,%RSI

(436) 0x42fe9c MOV	-0x38(%RBP),%RDI

(436) 0x42fea0 JNE	42fec0

(436) 0x42fea2 JMP	42fed9

0x42fea4 NOPW	%CS:(%RAX,%RAX,1)

(436) 0x42feb0 XOR	%R8D,%R8D

(436) 0x42feb3 NOPW	%CS:(%RAX,%RAX,1)

  (452) 0x42fec0 MOVSD	(%RAX,%R8,8),%XMM3

  (452) 0x42fec6 MULSD	(%R13,%R8,8),%XMM3

  (452) 0x42fecd ADDSD	%XMM3,%XMM2

  (452) 0x42fed1 INC	%R8

  (452) 0x42fed4 CMP	%R8,%RSI

  (452) 0x42fed7 JNE	42fec0

(436) 0x42fed9 TEST	%RSI,%RSI

(436) 0x42fedc JLE	42ff69

(436) 0x42fee2 MOV	%RSI,%R11

(436) 0x42fee5 AND	$-0x2,%R11

(436) 0x42fee9 JE	42ff40

(436) 0x42feeb LEA	-0x1(%R11),%RCX

(436) 0x42feef LEA	(%RAX,%R14,8),%RDI

(436) 0x42fef3 XORPD	%XMM3,%XMM3

(436) 0x42fef7 XOR	%R8D,%R8D

(436) 0x42fefa NOPW	(%RAX,%RAX,1)

  (451) 0x42ff00 MOVUPD	(%RDI,%R8,8),%XMM1

  (451) 0x42ff06 MOVUPD	(%R13,%R8,8),%XMM4

  (451) 0x42ff0d MULPD	%XMM1,%XMM4

  (451) 0x42ff11 ADDPD	%XMM4,%XMM3

  (451) 0x42ff15 ADD	$0x2,%R8

  (451) 0x42ff19 CMP	%RCX,%R8

  (451) 0x42ff1c JLE	42ff00

(436) 0x42ff1e MOVAPD	%XMM3,%XMM1

(436) 0x42ff22 UNPCKHPD	%XMM3,%XMM1

(436) 0x42ff26 ADDSD	%XMM3,%XMM1

(436) 0x42ff2a CMP	%R11,%RSI

(436) 0x42ff2d MOV	-0x38(%RBP),%RDI

(436) 0x42ff31 JNE	42ff47

(436) 0x42ff33 JMP	42ff69

0x42ff35 NOPW	%CS:(%RAX,%RAX,1)

(436) 0x42ff40 XORPD	%XMM1,%XMM1

(436) 0x42ff44 XOR	%R11D,%R11D

(436) 0x42ff47 LEA	(%RAX,%R14,8),%RCX

(436) 0x42ff4b NOPL	(%RAX,%RAX,1)

  (450) 0x42ff50 MOVSD	(%RCX,%R11,8),%XMM3

  (450) 0x42ff56 MULSD	(%R13,%R11,8),%XMM3

  (450) 0x42ff5d ADDSD	%XMM3,%XMM1

  (450) 0x42ff61 INC	%R11

  (450) 0x42ff64 CMP	%R11,%RSI

  (450) 0x42ff67 JNE	42ff50

(436) 0x42ff69 TEST	%RSI,%RSI

(436) 0x42ff6c JLE	42ffd0

(436) 0x42ff6e MOV	%RSI,%R11

(436) 0x42ff71 AND	$-0x2,%R11

(436) 0x42ff75 JE	42ffe0

(436) 0x42ff77 LEA	-0x1(%R11),%RCX

(436) 0x42ff7b MOV	%R14,%RDI

(436) 0x42ff7e SAL	$0x4,%RDI

(436) 0x42ff82 ADD	%RAX,%RDI

(436) 0x42ff85 XORPD	%XMM4,%XMM4

(436) 0x42ff89 XOR	%R8D,%R8D

(436) 0x42ff8c NOPL	(%RAX)

  (449) 0x42ff90 MOVUPD	(%RDI,%R8,8),%XMM3

  (449) 0x42ff96 MOVUPD	(%R13,%R8,8),%XMM5

  (449) 0x42ff9d MULPD	%XMM3,%XMM5

  (449) 0x42ffa1 ADDPD	%XMM5,%XMM4

  (449) 0x42ffa5 ADD	$0x2,%R8

  (449) 0x42ffa9 CMP	%RCX,%R8

  (449) 0x42ffac JLE	42ff90

(436) 0x42ffae MOVAPD	%XMM4,%XMM3

(436) 0x42ffb2 UNPCKHPD	%XMM4,%XMM3

(436) 0x42ffb6 ADDSD	%XMM4,%XMM3

(436) 0x42ffba CMP	%R11,%RSI

(436) 0x42ffbd MOV	-0x38(%RBP),%RDI

(436) 0x42ffc1 JNE	42ffe7

(436) 0x42ffc3 JMP	430019

0x42ffc5 NOPW	%CS:(%RAX,%RAX,1)

(436) 0x42ffd0 XORPD	%XMM3,%XMM3

(436) 0x42ffd4 JMP	430019

0x42ffd6 NOPW	%CS:(%RAX,%RAX,1)

(436) 0x42ffe0 XORPD	%XMM3,%XMM3

(436) 0x42ffe4 XOR	%R11D,%R11D

(436) 0x42ffe7 MOV	%R14,%RCX

(436) 0x42ffea SAL	$0x4,%RCX

(436) 0x42ffee ADD	%RAX,%RCX

(436) 0x42fff1 NOPW	%CS:(%RAX,%RAX,1)

  (448) 0x430000 MOVSD	(%RCX,%R11,8),%XMM4

  (448) 0x430006 MULSD	(%R13,%R11,8),%XMM4

  (448) 0x43000d ADDSD	%XMM4,%XMM3

  (448) 0x430011 INC	%R11

  (448) 0x430014 CMP	%R11,%RSI

  (448) 0x430017 JNE	430000

(436) 0x430019 MOV	%R14,-0x48(%RBP)

(436) 0x43001d MOV	0xf0(%RBX),%R8

(436) 0x430024 MOV	0x100(%RBX),%R14

(436) 0x43002b LEA	(%RSI,%R8,1),%RCX

(436) 0x43002f MOVSD	%XMM2,(%R14,%RSI,8)

(436) 0x430035 MOVSD	%XMM1,(%R14,%RCX,8)

(436) 0x43003b MOV	%R8,-0x58(%RBP)

(436) 0x43003f LEA	(%RSI,%R8,2),%RCX

(436) 0x430043 MOVSD	%XMM3,(%R14,%RCX,8)

(436) 0x430049 XORPD	0xf8fef(%RIP),%XMM0

(436) 0x430051 MOV	0x128(%RBX),%R8

(436) 0x430058 MOVLPD	%XMM0,(%R8,%RSI,8)

(436) 0x43005e TEST	%RSI,%RSI

(436) 0x430061 JLE	42fb70

(436) 0x430067 MOV	%R12,-0x78(%RBP)

(436) 0x43006b MOV	%R10,-0x40(%RBP)

(436) 0x43006f LEA	(%RDX,%RSI,8),%R11

(436) 0x430073 ADD	$-0x8,%R11

(436) 0x430077 CMP	%R8,%R11

(436) 0x43007a SETAEB	-0x2e(%RBP)

(436) 0x43007e LEA	(%R8,%RSI,8),%RDI

(436) 0x430082 ADD	$-0x8,%RDI

(436) 0x430086 CMP	%RDX,%RDI

(436) 0x430089 SETAE	%CL

(436) 0x43008c CMP	%R9,%R11

(436) 0x43008f SETB	%R15B

(436) 0x430093 LEA	(%R9,%RSI,8),%R10

(436) 0x430097 ADD	$-0x8,%R10

(436) 0x43009b CMP	%RDX,%R10

(436) 0x43009e SETBB	-0x2d(%RBP)

(436) 0x4300a2 CMP	%R8,%R10

(436) 0x4300a5 SETB	%R12B

(436) 0x4300a9 MOV	%R9,-0x50(%RBP)

(436) 0x4300ad CMP	%R9,%RDI

(436) 0x4300b0 SETBB	-0x2c(%RBP)

(436) 0x4300b4 CMP	%R13,%R11

(436) 0x4300b7 SETB	%R10B

(436) 0x4300bb LEA	-0x8(,%RSI,8),%RBX

(436) 0x4300c3 ADD	%R13,%RBX

(436) 0x4300c6 CMP	%RDX,%RBX

(436) 0x4300c9 SETBB	-0x2b(%RBP)

(436) 0x4300cd CMP	-0x38(%RBP),%R11

(436) 0x4300d1 SETB	%R11B

(436) 0x4300d5 MOV	-0x38(%RBP),%R9

(436) 0x4300d9 LEA	(%R9,%RSI,8),%R9

(436) 0x4300dd ADD	$-0x8,%R9

(436) 0x4300e1 CMP	%RDX,%R9

(436) 0x4300e4 SETBB	-0x2a(%RBP)

(436) 0x4300e8 CMP	%R8,%RBX

(436) 0x4300eb SETB	%BL

(436) 0x4300ee CMP	%R13,%RDI

(436) 0x4300f1 SETBB	-0x29(%RBP)

(436) 0x4300f5 CMP	%R8,%R9

(436) 0x4300f8 SETB	%R9B

(436) 0x4300fc CMP	-0x38(%RBP),%RDI

(436) 0x430100 MOV	-0x38(%RBP),%RDI

(436) 0x430104 SETB	%SIL

(436) 0x430108 TEST	%CL,-0x2e(%RBP)

(436) 0x43010b JNE	4301d0

(436) 0x430111 OR	-0x2d(%RBP),%R15B

(436) 0x430115 JE	4301d0

(436) 0x43011b OR	-0x2c(%RBP),%R12B

(436) 0x43011f JE	4301d0

(436) 0x430125 OR	-0x2b(%RBP),%R10B

(436) 0x430129 JE	4301d0

(436) 0x43012f OR	-0x2a(%RBP),%R11B

(436) 0x430133 JE	4301d0

(436) 0x430139 OR	-0x29(%RBP),%BL

(436) 0x43013c JE	4301d0

(436) 0x430142 OR	%SIL,%R9B

(436) 0x430145 JE	4301d0

(436) 0x43014b MOV	-0x68(%RBP),%RSI

(436) 0x43014f MOV	%RSI,%R11

(436) 0x430152 AND	$-0x2,%R11

(436) 0x430156 JE	430226

(436) 0x43015c LEA	-0x1(%R11),%RCX

(436) 0x430160 MOV	%R13,%R15

(436) 0x430163 MOV	%RDI,%R13

(436) 0x430166 XOR	%EDI,%EDI

(436) 0x430168 MOV	-0x50(%RBP),%R9

(436) 0x43016c NOPL	(%RAX)

  (447) 0x430170 MOVUPD	(%RDX,%RDI,8),%XMM0

  (447) 0x430175 MOVUPD	(%R9,%RDI,8),%XMM1

  (447) 0x43017b ADDPD	%XMM0,%XMM1

  (447) 0x43017f MOVUPD	%XMM1,(%RDX,%RDI,8)

  (447) 0x430184 MOVUPD	(%R15,%RDI,8),%XMM0

  (447) 0x43018a MULPD	%XMM7,%XMM0

  (447) 0x43018e MOVUPD	(%R13,%RDI,8),%XMM1

  (447) 0x430195 SUBPD	%XMM1,%XMM0

  (447) 0x430199 MOVUPD	(%R8,%RDI,8),%XMM1

  (447) 0x43019f ADDPD	%XMM0,%XMM1

  (447) 0x4301a3 MOVUPD	%XMM1,(%R8,%RDI,8)

  (447) 0x4301a9 ADD	$0x2,%RDI

  (447) 0x4301ad CMP	%RCX,%RDI

  (447) 0x4301b0 JLE	430170

(436) 0x4301b2 CMP	%R11,%RSI

(436) 0x4301b5 MOV	-0x70(%RBP),%RBX

(436) 0x4301b9 MOV	-0x40(%RBP),%R10

(436) 0x4301bd MOV	-0x78(%RBP),%R12

(436) 0x4301c1 MOV	%R13,%RDI

(436) 0x4301c4 MOV	%R15,%R13

(436) 0x4301c7 JNE	430240

(436) 0x4301c9 JMP	430277

0x4301ce XCHG	%AX,%AX

(436) 0x4301d0 XOR	%ECX,%ECX

(436) 0x4301d2 MOV	-0x70(%RBP),%RBX

(436) 0x4301d6 MOV	-0x68(%RBP),%RSI

(436) 0x4301da MOV	-0x40(%RBP),%R10

(436) 0x4301de MOV	-0x50(%RBP),%R9

(436) 0x4301e2 MOV	-0x78(%RBP),%R12

(436) 0x4301e6 NOPW	%CS:(%RAX,%RAX,1)

  (439) 0x4301f0 MOVSD	(%RDX,%RCX,8),%XMM0

  (439) 0x4301f5 ADDSD	(%R9,%RCX,8),%XMM0

  (439) 0x4301fb MOVSD	%XMM0,(%RDX,%RCX,8)

  (439) 0x430200 MOVSD	(%R13,%RCX,8),%XMM0

  (439) 0x430207 MULSD	%XMM6,%XMM0

  (439) 0x43020b SUBSD	(%RDI,%RCX,8),%XMM0

  (439) 0x430210 ADDSD	(%R8,%RCX,8),%XMM0

  (439) 0x430216 MOVSD	%XMM0,(%R8,%RCX,8)

  (439) 0x43021c INC	%RCX

  (439) 0x43021f CMP	%RCX,%RSI

  (439) 0x430222 JNE	4301f0

(436) 0x430224 JMP	430277

(436) 0x430226 XOR	%R11D,%R11D

(436) 0x430229 MOV	-0x70(%RBP),%RBX

(436) 0x43022d MOV	-0x40(%RBP),%R10

(436) 0x430231 MOV	-0x50(%RBP),%R9

(436) 0x430235 MOV	-0x78(%RBP),%R12

(436) 0x430239 NOPL	(%RAX)

  (446) 0x430240 MOVSD	(%RDX,%R11,8),%XMM0

  (446) 0x430246 ADDSD	(%R9,%R11,8),%XMM0

  (446) 0x43024c MOVSD	%XMM0,(%RDX,%R11,8)

  (446) 0x430252 MOVSD	(%R13,%R11,8),%XMM0

  (446) 0x430259 MULSD	%XMM6,%XMM0

  (446) 0x43025d SUBSD	(%RDI,%R11,8),%XMM0

  (446) 0x430263 ADDSD	(%R8,%R11,8),%XMM0

  (446) 0x430269 MOVSD	%XMM0,(%R8,%R11,8)

  (446) 0x43026f INC	%R11

  (446) 0x430272 CMP	%R11,%RSI

  (446) 0x430275 JNE	430240

(436) 0x430277 TEST	%RSI,%RSI

(436) 0x43027a JLE	42fb70

(436) 0x430280 MOV	%RSI,%RDX

(436) 0x430283 AND	$-0x2,%RDX

(436) 0x430287 JE	4302c4

(436) 0x430289 LEA	-0x1(%RDX),%RCX

(436) 0x43028d XOR	%EDI,%EDI

(436) 0x43028f NOP

  (445) 0x430290 MOVUPD	(%RAX,%RDI,8),%XMM0

  (445) 0x430295 MOVUPD	(%R13,%RDI,8),%XMM1

  (445) 0x43029c MULPD	%XMM0,%XMM1

  (445) 0x4302a0 MOVUPD	(%R14,%RDI,8),%XMM0

  (445) 0x4302a6 SUBPD	%XMM1,%XMM0

  (445) 0x4302aa MOVUPD	%XMM0,(%R14,%RDI,8)

  (445) 0x4302b0 ADD	$0x2,%RDI

  (445) 0x4302b4 CMP	%RCX,%RDI

  (445) 0x4302b7 JLE	430290

(436) 0x4302b9 CMP	%RDX,%RSI

(436) 0x4302bc MOV	-0x38(%RBP),%RDI

(436) 0x4302c0 JNE	4302d0

(436) 0x4302c2 JMP	4302f4

(436) 0x4302c4 XOR	%EDX,%EDX

(436) 0x4302c6 NOPW	%CS:(%RAX,%RAX,1)

  (440) 0x4302d0 MOVSD	(%RAX,%RDX,8),%XMM0

  (440) 0x4302d5 MULSD	(%R13,%RDX,8),%XMM0

  (440) 0x4302dc MOVSD	(%R14,%RDX,8),%XMM1

  (440) 0x4302e2 SUBSD	%XMM0,%XMM1

  (440) 0x4302e6 MOVSD	%XMM1,(%R14,%RDX,8)

  (440) 0x4302ec INC	%RDX

  (440) 0x4302ef CMP	%RDX,%RSI

  (440) 0x4302f2 JNE	4302d0

(436) 0x4302f4 TEST	%RSI,%RSI

(436) 0x4302f7 JLE	42fb70

(436) 0x4302fd MOV	%RSI,%RDX

(436) 0x430300 AND	$-0x2,%RDX

(436) 0x430304 JE	430351

(436) 0x430306 LEA	-0x1(%RDX),%RCX

(436) 0x43030a MOV	-0x58(%RBP),%RDI

(436) 0x43030e LEA	(%R14,%RDI,8),%RDI

(436) 0x430312 MOV	-0x48(%RBP),%R8

(436) 0x430316 LEA	(%RAX,%R8,8),%R8

(436) 0x43031a XOR	%R11D,%R11D

(436) 0x43031d NOPL	(%RAX)

  (444) 0x430320 MOVUPD	(%R8,%R11,8),%XMM0

  (444) 0x430326 MOVUPD	(%R13,%R11,8),%XMM1

  (444) 0x43032d MULPD	%XMM0,%XMM1

  (444) 0x430331 MOVUPD	(%RDI,%R11,8),%XMM0

  (444) 0x430337 SUBPD	%XMM1,%XMM0

  (444) 0x43033b MOVUPD	%XMM0,(%RDI,%R11,8)

  (444) 0x430341 ADD	$0x2,%R11

  (444) 0x430345 CMP	%RCX,%R11

  (444) 0x430348 JLE	430320

(436) 0x43034a CMP	%RDX,%RSI

(436) 0x43034d JNE	430353

(436) 0x43034f JMP	430392

(436) 0x430351 XOR	%EDX,%EDX

(436) 0x430353 MOV	-0x58(%RBP),%RCX

(436) 0x430357 LEA	(%R14,%RCX,8),%RCX

(436) 0x43035b MOV	-0x48(%RBP),%RDI

(436) 0x43035f LEA	(%RAX,%RDI,8),%RDI

(436) 0x430363 NOPW	%CS:(%RAX,%RAX,1)

  (441) 0x430370 MOVSD	(%RDI,%RDX,8),%XMM0

  (441) 0x430375 MULSD	(%R13,%RDX,8),%XMM0

  (441) 0x43037c MOVSD	(%RCX,%RDX,8),%XMM1

  (441) 0x430381 SUBSD	%XMM0,%XMM1

  (441) 0x430385 MOVSD	%XMM1,(%RCX,%RDX,8)

  (441) 0x43038a INC	%RDX

  (441) 0x43038d CMP	%RDX,%RSI

  (441) 0x430390 JNE	430370

(436) 0x430392 TEST	%RSI,%RSI

(436) 0x430395 MOV	-0x38(%RBP),%RDI

(436) 0x430399 JLE	42fb70

(436) 0x43039f MOV	%RSI,%RDX

(436) 0x4303a2 AND	$-0x2,%RDX

(436) 0x4303a6 JE	430409

(436) 0x4303a8 LEA	-0x1(%RDX),%RCX

(436) 0x4303ac MOV	-0x58(%RBP),%RDI

(436) 0x4303b0 SAL	$0x4,%RDI

(436) 0x4303b4 ADD	%R14,%RDI

(436) 0x4303b7 MOV	-0x48(%RBP),%R8

(436) 0x4303bb SAL	$0x4,%R8

(436) 0x4303bf ADD	%RAX,%R8

(436) 0x4303c2 XOR	%R11D,%R11D

(436) 0x4303c5 NOPW	%CS:(%RAX,%RAX,1)

  (443) 0x4303d0 MOVUPD	(%R8,%R11,8),%XMM0

  (443) 0x4303d6 MOVUPD	(%R13,%R11,8),%XMM1

  (443) 0x4303dd MULPD	%XMM0,%XMM1

  (443) 0x4303e1 MOVUPD	(%RDI,%R11,8),%XMM0

  (443) 0x4303e7 SUBPD	%XMM1,%XMM0

  (443) 0x4303eb MOVUPD	%XMM0,(%RDI,%R11,8)

  (443) 0x4303f1 ADD	$0x2,%R11

  (443) 0x4303f5 CMP	%RCX,%R11

  (443) 0x4303f8 JLE	4303d0

(436) 0x4303fa CMP	%RDX,%RSI

(436) 0x4303fd MOV	-0x38(%RBP),%RDI

(436) 0x430401 JE	42fb70

(436) 0x430407 JMP	43040b

(436) 0x430409 XOR	%EDX,%EDX

(436) 0x43040b MOV	-0x58(%RBP),%RCX

(436) 0x43040f SAL	$0x4,%RCX

(436) 0x430413 ADD	%RCX,%R14

(436) 0x430416 MOV	-0x48(%RBP),%RCX

(436) 0x43041a SAL	$0x4,%RCX

(436) 0x43041e ADD	%RCX,%RAX

(436) 0x430421 NOPW	%CS:(%RAX,%RAX,1)

  (442) 0x430430 MOVSD	(%RAX,%RDX,8),%XMM0

  (442) 0x430435 MULSD	(%R13,%RDX,8),%XMM0

  (442) 0x43043c MOVSD	(%R14,%RDX,8),%XMM1

  (442) 0x430442 SUBSD	%XMM0,%XMM1

  (442) 0x430446 MOVSD	%XMM1,(%R14,%RDX,8)

  (442) 0x43044c INC	%RDX

  (442) 0x43044f CMP	%RDX,%RSI

  (442) 0x430452 JNE	430430

(436) 0x430454 JMP	42fb70

0x430459 MOVQ	$0,0x10(%RBX)

0x430461 MOV	0x90(%RBX),%RAX

0x430468 TEST	%RAX,%RAX

0x43046b JE	430530

0x430471 MOV	0xd8(%RBX),%RCX

0x430478 MOV	0xf0(%RBX),%RDX

0x43047f MOV	0x100(%RBX),%RSI

0x430486 MOV	-0x90(%RBP),%RDI

0x43048d MOV	0x18(%RDI),%RDI

0x430491 MOV	0x128(%RBX),%R8

0x430498 MOV	-0x98(%RBP),%R9

0x43049f MOV	0x18(%R9),%R9

0x4304a3 SAL	$0x20,%RDX

0x4304a7 ADD	$0x10,%RDI

0x4304ab MOV	%RDX,%R10

0x4304ae SAR	$0x1c,%R10

0x4304b2 ADD	%RSI,%R10

0x4304b5 SAR	$0x1d,%RDX

0x4304b9 ADD	%RSI,%RDX

0x4304bc XORPD	%XMM0,%XMM0

0x4304c0 XOR	%R11D,%R11D

0x4304c3 NOPW	%CS:(%RAX,%RAX,1)

(434) 0x4304d0 ADDSD	(%RCX,%R11,8),%XMM0

(434) 0x4304d6 MOVSD	%XMM0,0x10(%RBX)

(434) 0x4304db MOVUPD	-0x10(%RDI),%XMM0

(434) 0x4304e0 MOVSD	(%RSI,%R11,8),%XMM1

(434) 0x4304e6 MOVHPD	(%RDX,%R11,8),%XMM1

(434) 0x4304ec ADDPD	%XMM0,%XMM1

(434) 0x4304f0 MOVSD	(%RDI),%XMM0

(434) 0x4304f4 ADDSD	(%R10,%R11,8),%XMM0

(434) 0x4304fa MOVUPD	%XMM1,-0x10(%RDI)

(434) 0x4304ff MOVSD	%XMM0,(%RDI)

(434) 0x430503 MOVSD	(%R9,%R11,8),%XMM0

(434) 0x430509 ADDSD	(%R8,%R11,8),%XMM0

(434) 0x43050f MOVSD	%XMM0,(%R9,%R11,8)

(434) 0x430515 MOVSD	0x10(%RBX),%XMM0

(434) 0x43051a INC	%R11

(434) 0x43051d ADD	$0x18,%RDI

(434) 0x430521 CMP	%R11,%RAX

(434) 0x430524 JNE	4304d0

0x430526 MULSD	0xf8bf2(%RIP),%XMM0

0x43052e JMP	430538

0x430530 MOVSD	0xfa0f8(%RIP),%XMM0

0x430538 MOVSD	%XMM0,0x10(%RBX)

0x43053d ADD	$0x78,%RSP

0x430541 POP	%RBX

0x430542 POP	%R12

0x430544 POP	%R13

0x430546 POP	%R14

0x430548 POP	%R15

0x43054a POP	%RBP

0x43054b RET

0x43054c NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►95.22+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:411	exec
○	_ZN11qmcplusplus12WaveFunction[...]	WaveFunction.cpp:175	exec
○	main.extracted.112	miniqmc.cpp:397	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
►3.08+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:411	exec
○	_ZN11qmcplusplus12WaveFunction[...]	WaveFunction.cpp:175	exec
○	main.extracted.112	miniqmc.cpp:397	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:378	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	stl_uninitialized.h:99	exec
►1.24+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:411	exec
○	_ZN11qmcplusplus12WaveFunction[...]	WaveFunction.cpp:175	exec
○	main.extracted.112	miniqmc.cpp:397	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so

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:268-432
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/bits/stl_numeric.h:140-141
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:268-274,360-367,375-391,397-398,419-432
/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:1064,1169
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:924,1115
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229,249
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h:1028,1182
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/DistanceTable.h:268
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:231,244,263,273

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 9.00 to 3.50 cycles (2.57x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your function is probably not vectorized. Only 12% 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 9.00 to 0.86 cycles (10.47x speedup).

Details

Store and arithmetical 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.

FMA

Presence of both ADD/SUB and MUL operations.

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

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.

qmcplusplus::ParticleSet::getDistTableAA(int) const: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:360

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

JMP: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:140

Type of elements and instruction set

8 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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

The binary function is composed of 8 FP arithmetical operations:

7: addition or subtraction
1: multiply

The binary function is loading 196 bytes (24 double precision FP elements). The binary function is storing 56 bytes (7 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.03 FP operations per loaded or stored byte.

General properties

nb instructions	80
nb uops	72
loop length	414
used x86 registers	16
used mmx registers	0
used xmm registers	4
used ymm registers	0
used zmm registers	0
nb stack references	5
ADD-SUB / MUL ratio	7.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	9.00 cycles
front end	9.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	3.00	3.00	3.00	3.67	3.67	3.67	8.00	8.00	8.00	8.00	0.50	0.50	3.50	3.50	0.50	0.50
cycles	3.00	3.00	3.00	3.67	3.67	3.67	8.00	8.00	8.00	8.00	0.50	0.50	3.50	3.50	0.50	0.50

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	9.00
Dispatch	8.00
Overall L1	9.00

Vectorization ratios

INT

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

all	15%
load	9%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	5%
load	6%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Vector efficiency ratios

INT

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

all	14%
load	13%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	12%
load	12%
store	11%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 9.00 cycles. At this rate:

8% of peak load performance is reached (21.78 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (6.22 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 9.00 to 8.00 cycles (1.13x speedup).

ASM code

In the binary file, the address of the function is: 42faa0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	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	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	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	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	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	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x78,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RDX,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RSI,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R8B,%R8B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JE 430459 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x9b9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0x248(%RBX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOV -0x60(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CALL 473ed0 <_ZNK11qmcplusplus11ParticleSet14getDistTableAAEi>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0xa0(%RBX),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
TEST %R10,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 430459 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x9b9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOVSD 0xf9639(%RIP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD 0xfac39(%RIP),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %R10,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RBX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
JMP 42fb29 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x89>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	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	0	0	0	0	0	0.09	N/A
MOV %RSI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 0x52ac88(,%RCX,8)	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	N/A
ADDSD 0x30(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD 0x28(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD 0x20(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD 0x18(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD 0x10(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD 0x8(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD (%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	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	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	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	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	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	0	0	0	0	0	0.09	N/A
MOVQ $0,0x10(%RBX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
MOV 0x90(%RBX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 430530 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa90>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0xd8(%RBX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0xf0(%RBX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV 0x100(%RBX),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV -0x90(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x128(%RBX),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV -0x98(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%R9),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
SAL $0x20,%RDX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD $0x10,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDX,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SAR $0x1c,%R10	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD %RSI,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SAR $0x1d,%RDX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD %RSI,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MULSD 0xf8bf2(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
JMP 430538 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa98>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOVSD 0xfa0f8(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD %XMM0,0x10(%RBX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
ADD $0x78,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	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	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	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	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	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	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	0	0	0	0	0	0	1	0.50	N/A
NOPL (%RAX)	0	0	0	0	0	0	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:268-432
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/bits/stl_numeric.h:140-141
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:268-274,360-367,375-391,397-398,419-432
/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:1064,1169
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:924,1115
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229,249
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h:1028,1182
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/DistanceTable.h:268
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:231,244,263,273

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 9.00 to 3.50 cycles (2.57x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

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.

FMA

Presence of both ADD/SUB and MUL operations.

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

CALL instructions

Detected function call instructions.

Details

qmcplusplus::ParticleSet::getDistTableAA(int) const: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:360

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

JMP: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:140

Type of elements and instruction set

8 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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

The binary function is composed of 8 FP arithmetical operations:

7: addition or subtraction
1: multiply

The binary function is loading 196 bytes (24 double precision FP elements). The binary function is storing 56 bytes (7 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.03 FP operations per loaded or stored byte.

General properties

nb instructions	80
nb uops	72
loop length	414
used x86 registers	16
used mmx registers	0
used xmm registers	4
used ymm registers	0
used zmm registers	0
nb stack references	5
ADD-SUB / MUL ratio	7.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	9.00 cycles
front end	9.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	3.00	3.00	3.00	3.67	3.67	3.67	8.00	8.00	8.00	8.00	0.50	0.50	3.50	3.50	0.50	0.50
cycles	3.00	3.00	3.00	3.67	3.67	3.67	8.00	8.00	8.00	8.00	0.50	0.50	3.50	3.50	0.50	0.50

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	9.00
Dispatch	8.00
Overall L1	9.00

Vectorization ratios

INT

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

all	15%
load	9%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	5%
load	6%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Vector efficiency ratios

INT

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

all	14%
load	13%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	12%
load	12%
store	11%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 9.00 cycles. At this rate:

8% of peak load performance is reached (21.78 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (6.22 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: 42faa0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	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	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	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	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	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	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x78,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RDX,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RSI,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R8B,%R8B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JE 430459 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x9b9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0x248(%RBX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOV -0x60(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CALL 473ed0 <_ZNK11qmcplusplus11ParticleSet14getDistTableAAEi>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0xa0(%RBX),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
TEST %R10,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 430459 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x9b9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOVSD 0xf9639(%RIP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD 0xfac39(%RIP),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %R10,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RBX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
JMP 42fb29 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x89>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	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	0	0	0	0	0	0.09	N/A
MOV %RSI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 0x52ac88(,%RCX,8)	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	N/A
ADDSD 0x30(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD 0x28(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD 0x20(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD 0x18(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD 0x10(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD 0x8(%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADDSD (%R9,%RAX,8),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	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	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	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	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	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	0	0	0	0	0	0.09	N/A
MOVQ $0,0x10(%RBX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
MOV 0x90(%RBX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 430530 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa90>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0xd8(%RBX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0xf0(%RBX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV 0x100(%RBX),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV -0x90(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x128(%RBX),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV -0x98(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%R9),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
SAL $0x20,%RDX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD $0x10,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDX,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SAR $0x1c,%R10	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD %RSI,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SAR $0x1d,%RDX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD %RSI,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MULSD 0xf8bf2(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
JMP 430538 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa98>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOVSD 0xfa0f8(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD %XMM0,0x10(%RBX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
ADD $0x78,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	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	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	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	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	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	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	0	0	0	0	0	0	1	0.50	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::TwoBodyJastrowRef >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib, std::allocator > >&, qmcplusplus::Particle...–	0.05	0.09
○Loop 434 - TwoBodyJastrowRef.h:422-427 - exec	0.00	0.00
▼Loop 436 - TwoBodyJastrowRef.h:268-420 - exec–	0.00	0.00
○Loop 449 - TwoBodyJastrowRef.h:381-382 - exec	0.01	0.02
○Loop 451 - TwoBodyJastrowRef.h:381-382 - exec	0.01	0.02
○Loop 453 - TwoBodyJastrowRef.h:381-382 - exec	0.01	0.02
○Loop 455 - TwoBodyJastrowRef.h:375-376 - exec	0.01	0.01
○Loop 447 - TwoBodyJastrowRef.h:388-420 - exec	0.01	0.01
○Loop 443 - TwoBodyJastrowRef.h:397-398 - exec	0.00	0.01
○Loop 444 - TwoBodyJastrowRef.h:397-398 - exec	0.00	0.01
○Loop 445 - TwoBodyJastrowRef.h:397-398 - exec	0.00	0.01
○Loop 437 - stl_numeric.h:140-141 - exec	0.00	0.01
○Loop 438 - TwoBodyJastrowRef.h:269-274 - exec	0.00	0.00
○Loop 450 - TwoBodyJastrowRef.h:381-382 - exec	0.00	0.00
○Loop 442 - TwoBodyJastrowRef.h:397-398 - exec	0.00	0.00
○Loop 446 - TwoBodyJastrowRef.h:388-391 - exec	0.00	0.00
○Loop 440 - TwoBodyJastrowRef.h:397-398 - exec	0.00	0.00
○Loop 441 - TwoBodyJastrowRef.h:397-398 - exec	0.00	0.00
○Loop 448 - TwoBodyJastrowRef.h:381-382 - exec	0.00	0.00
○Loop 435 - TwoBodyJastrowRef.h:361-364 - exec	0.00	0.00
○Loop 439 - TwoBodyJastrowRef.h:388-391 - exec	0.00	0.00
○Loop 454 - TwoBodyJastrowRef.h:375-376 - exec	0.00	0.00
○Loop 452 - TwoBodyJastrowRef.h:381-382 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

FMA

Workaround

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

FMA

Workaround

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code