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): 0.11% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/DistanceTable.h: 268 - 268

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

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

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 94

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

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

/home/eoseret/qaas_runs_GNR/173-773-5521/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; }

/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;

/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: 235 - 1115

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

235:       if (__b < __a)

[...]

924: 	*__first = __tmp;

[...]

1115:       if (__n <= 0)

/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_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 145 - 169

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

145:       X[i] = base[i * offset];

[...]

169:   inline Type_t& operator[](unsigned int i) { return X[i]; }

/home/eoseret/qaas_runs_GNR/173-773-5521/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];

392:       }

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

394:       {

395:         valT* restrict save_g   = dUat.data(idim);

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

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: }

/home/eoseret/qaas_runs_GNR/173-773-5521/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; }

/home/eoseret/qaas_runs_GNR/173-773-5521/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]; }

0x42b340 PUSH	%RBP

0x42b341 MOV	%RSP,%RBP

0x42b344 PUSH	%R15

0x42b346 PUSH	%R14

0x42b348 PUSH	%R13

0x42b34a PUSH	%R12

0x42b34c PUSH	%RBX

0x42b34d SUB	$0x98,%RSP

0x42b354 MOV	%RCX,-0xb0(%RBP)

0x42b35b MOV	%RDX,-0xa8(%RBP)

0x42b362 MOV	%RDI,%R12

0x42b365 TEST	%R8B,%R8B

0x42b368 MOV	%RDI,-0x60(%RBP)

0x42b36c JE	42bdc0

0x42b372 MOV	%RSI,%RBX

0x42b375 MOV	0x248(%R12),%ESI

0x42b37d MOV	%RBX,%RDI

0x42b380 CALL	479590 <_ZNK11qmcplusplus11ParticleSet14getDistTableAAEi>

0x42b385 MOV	0xa0(%R12),%R11

0x42b38d TEST	%R11,%R11

0x42b390 JE	42bdc0

0x42b396 MOV	%RAX,%R15

0x42b399 XOR	%ECX,%ECX

0x42b39b VMOVSD	0x10ce2b(%RIP),%XMM16

0x42b3a5 VMOVSD	0x10bcd1(%RIP),%XMM17

0x42b3af VBROADCASTSD	0x10bcc7(%RIP),%YMM18

0x42b3b9 MOV	%R11,-0x40(%RBP)

0x42b3bd MOV	%RBX,-0x70(%RBP)

0x42b3c1 MOV	%RAX,-0x90(%RBP)

0x42b3c8 JMP	42b41f

0x42b3ca NOPW	%CS:(%RAX,%RAX,1)

0x42b3d9 NOPW	%CS:(%RAX,%RAX,1)

0x42b3e8 NOPW	%CS:(%RAX,%RAX,1)

0x42b3f7 NOPW	(%RAX,%RAX,1)

(388) 0x42b400 MOV	-0x40(%RBP),%RAX

(388) 0x42b404 MOV	-0xb8(%RBP),%RCX

(388) 0x42b40b INC	%RCX

(388) 0x42b40e MOV	%RAX,-0x40(%RBP)

(388) 0x42b412 CMP	%RCX,%RAX

(388) 0x42b415 MOV	-0x70(%RBP),%RBX

(388) 0x42b419 JBE	42bdc0

(388) 0x42b41f MOV	0x268(%RBX),%RAX

(388) 0x42b426 MOV	0x18(%RAX),%RAX

(388) 0x42b42a MOVSXD	(%RAX,%RCX,4),%R10

(388) 0x42b42e MOV	%RCX,-0xb8(%RBP)

(388) 0x42b435 MOV	0x4(%RAX,%RCX,4),%EAX

(388) 0x42b439 MOV	%EAX,-0x74(%RBP)

(388) 0x42b43c CMP	%EAX,%R10D

(388) 0x42b43f JGE	42b400

(388) 0x42b441 MOV	0x140(%R12),%R9

(388) 0x42b449 MOV	0x158(%R12),%R13

(388) 0x42b451 MOV	0x170(%R12),%RBX

(388) 0x42b459 MOV	$0x1fffffffffffffff,%RAX

(388) 0x42b463 ADD	%R10,%RAX

(388) 0x42b466 MOV	%RAX,-0x98(%RBP)

(388) 0x42b46d MOVQ	$0,-0xa0(%RBP)

(388) 0x42b478 LEA	-0x1(%R10),%RAX

(388) 0x42b47c MOV	%RAX,-0xc0(%RBP)

(388) 0x42b483 JMP	42b4de

0x42b485 NOPW	%CS:(%RAX,%RAX,1)

0x42b494 NOPW	%CS:(%RAX,%RAX,1)

0x42b4a3 NOPW	%CS:(%RAX,%RAX,1)

0x42b4b2 NOPW	%CS:(%RAX,%RAX,1)

  (389) 0x42b4c0 INC	%R10

  (389) 0x42b4c3 INCQ	-0xa0(%RBP)

  (389) 0x42b4ca INCQ	-0x98(%RBP)

  (389) 0x42b4d1 MOV	%R11,%RAX

  (389) 0x42b4d4 CMP	%R10D,-0x74(%RBP)

  (389) 0x42b4d8 JE	42b404

  (389) 0x42b4de MOV	%RBX,-0x38(%RBP)

  (389) 0x42b4e2 MOV	0x48(%R15),%RAX

  (389) 0x42b4e6 LEA	(%R10,%R10,4),%RCX

  (389) 0x42b4ea MOV	%RCX,-0x68(%RBP)

  (389) 0x42b4ee MOV	0x18(%RAX,%RCX,8),%RDX

  (389) 0x42b4f3 TEST	%R10,%R10

  (389) 0x42b4f6 MOV	%R10,-0x58(%RBP)

  (389) 0x42b4fa MOV	%R9,-0x48(%RBP)

  (389) 0x42b4fe JLE	42b554

  (389) 0x42b500 MOV	%RDX,-0x50(%RBP)

  (389) 0x42b504 MOV	%R10D,%EDX

  (389) 0x42b507 SAL	$0x3,%RDX

  (389) 0x42b50b MOV	%R9,%RDI

  (389) 0x42b50e XOR	%ESI,%ESI

  (389) 0x42b510 MOV	%R12,%R14

  (389) 0x42b513 MOV	%R15,%R12

  (389) 0x42b516 MOV	%RDX,%R15

  (389) 0x42b519 MOV	%R11,%RBX

  (389) 0x42b51c VZEROUPPER

  (389) 0x42b51f CALL	534740 <__intel_avx_rep_memset>

  (389) 0x42b524 MOV	%R13,%RDI

  (389) 0x42b527 XOR	%ESI,%ESI

  (389) 0x42b529 MOV	%R15,%RDX

  (389) 0x42b52c CALL	534740 <__intel_avx_rep_memset>

  (389) 0x42b531 MOV	-0x38(%RBP),%RDI

  (389) 0x42b535 XOR	%ESI,%ESI

  (389) 0x42b537 MOV	%R15,%RDX

  (389) 0x42b53a MOV	%R12,%R15

  (389) 0x42b53d MOV	%R14,%R12

  (389) 0x42b540 CALL	534740 <__intel_avx_rep_memset>

  (389) 0x42b545 MOV	-0x50(%RBP),%RDX

  (389) 0x42b549 MOV	-0x48(%RBP),%R9

  (389) 0x42b54d MOV	-0x58(%RBP),%R10

  (389) 0x42b551 MOV	%RBX,%R11

  (389) 0x42b554 MOV	-0x40(%RBP),%RCX

  (389) 0x42b558 TEST	%RCX,%RCX

  (389) 0x42b55b JE	42b640

  (389) 0x42b561 MOV	-0x70(%RBP),%RAX

  (389) 0x42b565 MOV	0x18(%RAX),%RAX

  (389) 0x42b569 IMUL	(%RAX,%R10,4),%ECX

  (389) 0x42b56e MOVSXD	%ECX,%RAX

  (389) 0x42b571 SAL	$0x3,%RAX

  (389) 0x42b575 MOV	%RAX,-0x40(%RBP)

  (389) 0x42b579 MOV	%R12,%RBX

  (389) 0x42b57c XOR	%R12D,%R12D

  (389) 0x42b57f MOV	%RDX,%R15

  (389) 0x42b582 MOV	%R13,%R14

  (389) 0x42b585 MOV	-0x38(%RBP),%R13

  (389) 0x42b589 NOPL	(%RAX)

    (404) 0x42b590 MOV	0x200(%RBX),%RAX

    (404) 0x42b597 ADD	-0x40(%RBP),%RAX

    (404) 0x42b59b MOV	(%RAX,%R12,8),%RDI

    (404) 0x42b59f MOV	-0x70(%RBP),%RAX

    (404) 0x42b5a3 MOV	0x268(%RAX),%RAX

    (404) 0x42b5aa MOV	0x18(%RAX),%RAX

    (404) 0x42b5ae MOV	(%RAX,%R12,4),%EDX

    (404) 0x42b5b2 MOVSXD	0x4(%RAX,%R12,4),%RAX

    (404) 0x42b5b7 INC	%R12

    (404) 0x42b5ba CMP	%RAX,%R10

    (404) 0x42b5bd MOV	%R10D,%ECX

    (404) 0x42b5c0 CMOVG	%EAX,%ECX

    (404) 0x42b5c3 MOV	%R10D,%ESI

    (404) 0x42b5c6 MOV	%R15,%R8

    (404) 0x42b5c9 PUSHQ	0x1e8(%RBX)

    (404) 0x42b5cf PUSHQ	0x1d0(%RBX)

    (404) 0x42b5d5 PUSH	%R13

    (404) 0x42b5d7 PUSH	%R14

    (404) 0x42b5d9 VZEROUPPER

    (404) 0x42b5dc CALL	427740 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi>

    (404) 0x42b5e1 MOV	-0x48(%RBP),%R9

    (404) 0x42b5e5 MOV	-0x58(%RBP),%R10

    (404) 0x42b5e9 ADD	$0x20,%RSP

    (404) 0x42b5ed MOV	0xa0(%RBX),%R11

    (404) 0x42b5f4 CMP	%R12,%R11

    (404) 0x42b5f7 JA	42b590

  (389) 0x42b5f9 MOV	0x140(%RBX),%R9

  (389) 0x42b600 MOV	%R11,-0x40(%RBP)

  (389) 0x42b604 MOV	%RBX,%R12

  (389) 0x42b607 MOV	-0x90(%RBP),%R15

  (389) 0x42b60e VMOVSD	0x10cbb8(%RIP),%XMM16

  (389) 0x42b618 VMOVSD	0x10ba5e(%RIP),%XMM17

  (389) 0x42b622 VBROADCASTSD	0x10ba54(%RIP),%YMM18

  (389) 0x42b62c JMP	42b648

0x42b62e NOPW	%CS:(%RAX,%RAX,1)

0x42b63d NOPL	(%RAX)

  (389) 0x42b640 MOVQ	$0,-0x40(%RBP)

  (389) 0x42b648 VXORPD	%XMM0,%XMM0,%XMM0

  (389) 0x42b64c VXORPD	%XMM1,%XMM1,%XMM1

  (389) 0x42b650 MOV	$0x1fffffffffffffff,%RAX

  (389) 0x42b65a TEST	%RAX,%R10

  (389) 0x42b65d JE	42b6de

  (389) 0x42b65f LEA	(%R10,%RAX,1),%RCX

  (389) 0x42b663 AND	%RAX,%RCX

  (389) 0x42b666 INC	%RCX

  (389) 0x42b669 MOV	%RCX,%RAX

  (389) 0x42b66c MOV	$0x3ffffffffffffffc,%RDX

  (389) 0x42b676 AND	%RDX,%RAX

  (389) 0x42b679 JE	42b6c0

  (389) 0x42b67b VXORPD	%XMM1,%XMM1,%XMM1

  (389) 0x42b67f XOR	%EDX,%EDX

  (389) 0x42b681 NOPW	%CS:(%RAX,%RAX,1)

    (403) 0x42b690 VADDPD	(%R9,%RDX,8),%YMM1,%YMM1

    (403) 0x42b696 ADD	$0x4,%RDX

    (403) 0x42b69a CMP	%RAX,%RDX

    (403) 0x42b69d JB	42b690

  (389) 0x42b69f VEXTRACTF128	$0x1,%YMM1,%XMM2

  (389) 0x42b6a5 VADDPD	%XMM2,%XMM1,%XMM1

  (389) 0x42b6a9 VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

  (389) 0x42b6ae VADDSD	%XMM2,%XMM1,%XMM1

  (389) 0x42b6b2 CMP	%RAX,%RCX

  (389) 0x42b6b5 JNE	42b6c2

  (389) 0x42b6b7 JMP	42b6de

0x42b6b9 NOPL	(%RAX)

  (389) 0x42b6c0 XOR	%EAX,%EAX

  (389) 0x42b6c2 MOV	$0x3d,%CL

  (389) 0x42b6c4 BZHI	%RCX,-0x98(%RBP),%RCX

  (389) 0x42b6cd INC	%RCX

    (402) 0x42b6d0 VADDSD	(%R9,%RAX,8),%XMM1,%XMM1

    (402) 0x42b6d6 INC	%RAX

    (402) 0x42b6d9 CMP	%RAX,%RCX

    (402) 0x42b6dc JNE	42b6d0

  (389) 0x42b6de MOV	0xd8(%R12),%RDX

  (389) 0x42b6e6 VMOVSD	%XMM1,(%RDX,%R10,8)

  (389) 0x42b6ec MOV	0x158(%R12),%R13

  (389) 0x42b6f4 MOV	0x170(%R12),%RBX

  (389) 0x42b6fc MOV	0x60(%R15),%RAX

  (389) 0x42b700 TEST	%R10,%R10

  (389) 0x42b703 JLE	42b7a5

  (389) 0x42b709 MOV	%R10,%RCX

  (389) 0x42b70c MOV	$0x7ffffffffffffffc,%RSI

  (389) 0x42b716 AND	%RSI,%RCX

  (389) 0x42b719 JE	42b780

  (389) 0x42b71b VXORPD	%XMM0,%XMM0,%XMM0

  (389) 0x42b71f XOR	%ESI,%ESI

  (389) 0x42b721 VBROADCASTSD	0x10caa6(%RIP),%YMM1

  (389) 0x42b72a NOPW	(%RAX,%RAX,1)

    (401) 0x42b730 VADDPD	(%RBX,%RSI,8),%YMM0,%YMM0

    (401) 0x42b735 VFMADD231PD	(%R13,%RSI,8),%YMM1,%YMM0

    (401) 0x42b73c ADD	$0x4,%RSI

    (401) 0x42b740 CMP	%RCX,%RSI

    (401) 0x42b743 JB	42b730

  (389) 0x42b745 VEXTRACTF128	$0x1,%YMM0,%XMM1

  (389) 0x42b74b VADDPD	%XMM1,%XMM0,%XMM0

  (389) 0x42b74f VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

  (389) 0x42b754 VADDSD	%XMM1,%XMM0,%XMM0

  (389) 0x42b758 JMP	42b7a0

0x42b75a NOPW	%CS:(%RAX,%RAX,1)

0x42b769 NOPW	%CS:(%RAX,%RAX,1)

0x42b778 NOPL	(%RAX,%RAX,1)

  (389) 0x42b780 VXORPD	%XMM0,%XMM0,%XMM0

  (389) 0x42b784 XOR	%ECX,%ECX

  (389) 0x42b786 NOPW	%CS:(%RAX,%RAX,1)

    (400) 0x42b790 VADDSD	(%RBX,%RCX,8),%XMM0,%XMM0

    (400) 0x42b795 VFMADD231SD	(%R13,%RCX,8),%XMM16,%XMM0

    (400) 0x42b79d INC	%RCX

    (400) 0x42b7a0 CMP	%RCX,%R10

    (400) 0x42b7a3 JNE	42b790

  (389) 0x42b7a5 MOV	-0x68(%RBP),%RCX

  (389) 0x42b7a9 MOV	0x8(%RAX,%RCX,8),%R14

  (389) 0x42b7ae MOV	0x18(%RAX,%RCX,8),%RAX

  (389) 0x42b7b3 VXORPD	%XMM2,%XMM2,%XMM2

  (389) 0x42b7b7 VXORPD	%XMM1,%XMM1,%XMM1

  (389) 0x42b7bb TEST	%R10,%R10

  (389) 0x42b7be JLE	42b864

  (389) 0x42b7c4 MOV	%R10,%RSI

  (389) 0x42b7c7 MOV	$0x7ffffffffffffffc,%RCX

  (389) 0x42b7d1 AND	%RCX,%RSI

  (389) 0x42b7d4 JE	42b840

  (389) 0x42b7d6 VXORPD	%XMM1,%XMM1,%XMM1

  (389) 0x42b7da XOR	%ECX,%ECX

  (389) 0x42b7dc NOPL	(%RAX)

    (399) 0x42b7e0 VMOVUPD	(%RAX,%RCX,8),%YMM3

    (399) 0x42b7e5 VFMADD231PD	(%R13,%RCX,8),%YMM3,%YMM1

    (399) 0x42b7ec ADD	$0x4,%RCX

    (399) 0x42b7f0 CMP	%RSI,%RCX

    (399) 0x42b7f3 JB	42b7e0

  (389) 0x42b7f5 VEXTRACTF128	$0x1,%YMM1,%XMM3

  (389) 0x42b7fb VADDPD	%XMM3,%XMM1,%XMM1

  (389) 0x42b7ff VSHUFPD	$0x1,%XMM1,%XMM1,%XMM3

  (389) 0x42b804 VADDSD	%XMM3,%XMM1,%XMM1

  (389) 0x42b808 JMP	42b85f

0x42b80a NOPW	%CS:(%RAX,%RAX,1)

0x42b819 NOPW	%CS:(%RAX,%RAX,1)

0x42b828 NOPW	%CS:(%RAX,%RAX,1)

0x42b837 NOPW	(%RAX,%RAX,1)

  (389) 0x42b840 XOR	%ESI,%ESI

  (389) 0x42b842 NOPW	%CS:(%RAX,%RAX,1)

    (398) 0x42b850 VMOVSD	(%RAX,%RSI,8),%XMM3

    (398) 0x42b855 VFMADD231SD	(%R13,%RSI,8),%XMM3,%XMM1

    (398) 0x42b85c INC	%RSI

    (398) 0x42b85f CMP	%RSI,%R10

    (398) 0x42b862 JNE	42b850

  (389) 0x42b864 TEST	%R10,%R10

  (389) 0x42b867 JLE	42b8e4

  (389) 0x42b869 MOV	%R10,%RSI

  (389) 0x42b86c MOV	$0x7ffffffffffffffc,%RCX

  (389) 0x42b876 AND	%RCX,%RSI

  (389) 0x42b879 JE	42b8c0

  (389) 0x42b87b LEA	(%RAX,%R14,8),%RCX

  (389) 0x42b87f VXORPD	%XMM2,%XMM2,%XMM2

  (389) 0x42b883 XOR	%EDI,%EDI

  (389) 0x42b885 NOPW	%CS:(%RAX,%RAX,1)

    (397) 0x42b890 VMOVUPD	(%RCX,%RDI,8),%YMM3

    (397) 0x42b895 VFMADD231PD	(%R13,%RDI,8),%YMM3,%YMM2

    (397) 0x42b89c ADD	$0x4,%RDI

    (397) 0x42b8a0 CMP	%RSI,%RDI

    (397) 0x42b8a3 JB	42b890

  (389) 0x42b8a5 VEXTRACTF128	$0x1,%YMM2,%XMM3

  (389) 0x42b8ab VADDPD	%XMM3,%XMM2,%XMM2

  (389) 0x42b8af VSHUFPD	$0x1,%XMM2,%XMM2,%XMM3

  (389) 0x42b8b4 VADDSD	%XMM3,%XMM2,%XMM2

  (389) 0x42b8b8 CMP	%RSI,%R10

  (389) 0x42b8bb JNE	42b8c6

  (389) 0x42b8bd JMP	42b8e4

0x42b8bf NOP

  (389) 0x42b8c0 VXORPD	%XMM2,%XMM2,%XMM2

  (389) 0x42b8c4 XOR	%ESI,%ESI

  (389) 0x42b8c6 LEA	(%RAX,%R14,8),%RCX

  (389) 0x42b8ca NOPW	(%RAX,%RAX,1)

    (396) 0x42b8d0 VMOVSD	(%RCX,%RSI,8),%XMM3

    (396) 0x42b8d5 VFMADD231SD	(%R13,%RSI,8),%XMM3,%XMM2

    (396) 0x42b8dc INC	%RSI

    (396) 0x42b8df CMP	%RSI,%R10

    (396) 0x42b8e2 JNE	42b8d0

  (389) 0x42b8e4 TEST	%R10,%R10

  (389) 0x42b8e7 JLE	42b940

  (389) 0x42b8e9 MOV	%R10,%RSI

  (389) 0x42b8ec MOV	$0x7ffffffffffffffc,%RCX

  (389) 0x42b8f6 AND	%RCX,%RSI

  (389) 0x42b8f9 JE	42b980

  (389) 0x42b8ff MOV	%R14,%RCX

  (389) 0x42b902 SAL	$0x4,%RCX

  (389) 0x42b906 ADD	%RAX,%RCX

  (389) 0x42b909 VXORPD	%XMM3,%XMM3,%XMM3

  (389) 0x42b90d XOR	%EDI,%EDI

  (389) 0x42b90f NOP

    (395) 0x42b910 VMOVUPD	(%RCX,%RDI,8),%YMM4

    (395) 0x42b915 VFMADD231PD	(%R13,%RDI,8),%YMM4,%YMM3

    (395) 0x42b91c ADD	$0x4,%RDI

    (395) 0x42b920 CMP	%RSI,%RDI

    (395) 0x42b923 JB	42b910

  (389) 0x42b925 VEXTRACTF128	$0x1,%YMM3,%XMM4

  (389) 0x42b92b VADDPD	%XMM4,%XMM3,%XMM3

  (389) 0x42b92f VSHUFPD	$0x1,%XMM3,%XMM3,%XMM4

  (389) 0x42b934 VADDSD	%XMM4,%XMM3,%XMM3

  (389) 0x42b938 CMP	%RSI,%R10

  (389) 0x42b93b JNE	42b986

  (389) 0x42b93d JMP	42b9a4

0x42b93f NOP

  (389) 0x42b940 VXORPD	%XMM3,%XMM3,%XMM3

  (389) 0x42b944 JMP	42b9a4

0x42b946 NOPW	%CS:(%RAX,%RAX,1)

0x42b955 NOPW	%CS:(%RAX,%RAX,1)

0x42b964 NOPW	%CS:(%RAX,%RAX,1)

0x42b973 NOPW	%CS:(%RAX,%RAX,1)

  (389) 0x42b980 VXORPD	%XMM3,%XMM3,%XMM3

  (389) 0x42b984 XOR	%ESI,%ESI

  (389) 0x42b986 MOV	%R14,%RCX

  (389) 0x42b989 SAL	$0x4,%RCX

  (389) 0x42b98d ADD	%RAX,%RCX

    (394) 0x42b990 VMOVSD	(%RCX,%RSI,8),%XMM4

    (394) 0x42b995 VFMADD231SD	(%R13,%RSI,8),%XMM4,%XMM3

    (394) 0x42b99c INC	%RSI

    (394) 0x42b99f CMP	%RSI,%R10

    (394) 0x42b9a2 JNE	42b990

  (389) 0x42b9a4 VPUNPCKLQDQ	%XMM2,%XMM1,%XMM1

  (389) 0x42b9a8 MOV	0xf0(%R12),%RDI

  (389) 0x42b9b0 MOV	0x100(%R12),%RSI

  (389) 0x42b9b8 VMOVLPD	%XMM1,(%RSI,%R10,8)

  (389) 0x42b9be LEA	(%R10,%RDI,1),%RCX

  (389) 0x42b9c2 VMOVHPD	%XMM1,(%RSI,%RCX,8)

  (389) 0x42b9c7 LEA	(%R10,%RDI,2),%RCX

  (389) 0x42b9cb VMOVSD	%XMM3,(%RSI,%RCX,8)

  (389) 0x42b9d0 VXORPD	0x10b66e(%RIP){1to2},%XMM0,%XMM0

  (389) 0x42b9da MOV	0x128(%R12),%R8

  (389) 0x42b9e2 VMOVLPD	%XMM0,(%R8,%R10,8)

  (389) 0x42b9e8 TEST	%R10,%R10

  (389) 0x42b9eb JLE	42b4c0

  (389) 0x42b9f1 MOV	%RDI,-0x80(%RBP)

  (389) 0x42b9f5 MOV	%R14,-0x88(%RBP)

  (389) 0x42b9fc MOV	%R11,-0x68(%RBP)

  (389) 0x42ba00 LEA	-0x1(%R10),%RCX

  (389) 0x42ba04 LEA	(%RDX,%RCX,8),%R10

  (389) 0x42ba08 CMP	%R8,%R10

  (389) 0x42ba0b SETAEB	-0x2d(%RBP)

  (389) 0x42ba0f LEA	(%R8,%RCX,8),%RDI

  (389) 0x42ba13 CMP	%RDX,%RDI

  (389) 0x42ba16 SETAE	%R12B

  (389) 0x42ba1a CMP	%R9,%R10

  (389) 0x42ba1d MOV	%R13,%R14

  (389) 0x42ba20 MOV	%RBX,%R13

  (389) 0x42ba23 SETB	%BL

  (389) 0x42ba26 LEA	(%R9,%RCX,8),%R11

  (389) 0x42ba2a CMP	%RDX,%R11

  (389) 0x42ba2d SETBB	-0x2c(%RBP)

  (389) 0x42ba31 CMP	%R8,%R11

  (389) 0x42ba34 SETB	%R15B

  (389) 0x42ba38 MOV	%R9,-0x48(%RBP)

  (389) 0x42ba3c CMP	%R9,%RDI

  (389) 0x42ba3f SETBB	-0x2b(%RBP)

  (389) 0x42ba43 CMP	%R14,%R10

  (389) 0x42ba46 SETB	%R9B

  (389) 0x42ba4a LEA	(%R14,%RCX,8),%R11

  (389) 0x42ba4e CMP	%RDX,%R11

  (389) 0x42ba51 SETBB	-0x2a(%RBP)

  (389) 0x42ba55 CMP	%R13,%R10

  (389) 0x42ba58 SETB	%R10B

  (389) 0x42ba5c LEA	(%R13,%RCX,8),%RCX

  (389) 0x42ba61 CMP	%RDX,%RCX

  (389) 0x42ba64 SETBB	-0x29(%RBP)

  (389) 0x42ba68 CMP	%R8,%R11

  (389) 0x42ba6b SETB	%R11B

  (389) 0x42ba6f MOV	%R14,-0x50(%RBP)

  (389) 0x42ba73 CMP	%R14,%RDI

  (389) 0x42ba76 SETB	%R14B

  (389) 0x42ba7a CMP	%R8,%RCX

  (389) 0x42ba7d SETB	%CL

  (389) 0x42ba80 MOV	%R13,-0x38(%RBP)

  (389) 0x42ba84 CMP	%R13,%RDI

  (389) 0x42ba87 SETB	%DIL

  (389) 0x42ba8b TEST	%R12B,-0x2d(%RBP)

  (389) 0x42ba8f JNE	42bb80

  (389) 0x42ba95 OR	-0x2c(%RBP),%BL

  (389) 0x42ba98 JE	42bb80

  (389) 0x42ba9e OR	-0x2b(%RBP),%R15B

  (389) 0x42baa2 JE	42bb80

  (389) 0x42baa8 OR	-0x2a(%RBP),%R9B

  (389) 0x42baac JE	42bb80

  (389) 0x42bab2 OR	-0x29(%RBP),%R10B

  (389) 0x42bab6 JE	42bb80

  (389) 0x42babc OR	%R14B,%R11B

  (389) 0x42babf JE	42bb80

  (389) 0x42bac5 OR	%DIL,%CL

  (389) 0x42bac8 JE	42bb80

  (389) 0x42bace MOV	-0x58(%RBP),%RDI

  (389) 0x42bad2 MOV	%RDI,%R9

  (389) 0x42bad5 MOV	$0x7ffffffffffffffc,%RCX

  (389) 0x42badf AND	%RCX,%R9

  (389) 0x42bae2 MOV	-0x60(%RBP),%R12

  (389) 0x42bae6 MOV	-0x88(%RBP),%R14

  (389) 0x42baed JE	42bc00

  (389) 0x42baf3 XOR	%ECX,%ECX

  (389) 0x42baf5 MOV	-0x48(%RBP),%R10

  (389) 0x42baf9 MOV	-0x38(%RBP),%R11

  (389) 0x42bafd MOV	-0x50(%RBP),%R13

  (389) 0x42bb01 NOPW	%CS:(%RAX,%RAX,1)

    (393) 0x42bb10 VMOVUPD	(%RDX,%RCX,8),%YMM0

    (393) 0x42bb15 VADDPD	(%R10,%RCX,8),%YMM0,%YMM0

    (393) 0x42bb1b VMOVUPD	%YMM0,(%RDX,%RCX,8)

    (393) 0x42bb20 VMOVUPD	(%R13,%RCX,8),%YMM0

    (393) 0x42bb27 VFMSUB213PD	(%R11,%RCX,8),%YMM18,%YMM0

    (393) 0x42bb2e VADDPD	(%R8,%RCX,8),%YMM0,%YMM0

    (393) 0x42bb34 VMOVUPD	%YMM0,(%R8,%RCX,8)

    (393) 0x42bb3a ADD	$0x4,%RCX

    (393) 0x42bb3e CMP	%R9,%RCX

    (393) 0x42bb41 JB	42bb10

  (389) 0x42bb43 JMP	42bc3f

0x42bb48 NOPW	%CS:(%RAX,%RAX,1)

0x42bb57 NOPW	%CS:(%RAX,%RAX,1)

0x42bb66 NOPW	%CS:(%RAX,%RAX,1)

0x42bb75 NOPW	%CS:(%RAX,%RAX,1)

  (389) 0x42bb80 XOR	%ECX,%ECX

  (389) 0x42bb82 MOV	-0x60(%RBP),%R12

  (389) 0x42bb86 MOV	-0x58(%RBP),%RDI

  (389) 0x42bb8a MOV	-0x48(%RBP),%R9

  (389) 0x42bb8e MOV	-0x38(%RBP),%R10

  (389) 0x42bb92 MOV	-0x50(%RBP),%R13

  (389) 0x42bb96 MOV	-0x88(%RBP),%R14

  (389) 0x42bb9d NOPL	(%RAX)

    (390) 0x42bba0 VMOVSD	(%RDX,%RCX,8),%XMM0

    (390) 0x42bba5 VADDSD	(%R9,%RCX,8),%XMM0,%XMM0

    (390) 0x42bbab VMOVSD	%XMM0,(%RDX,%RCX,8)

    (390) 0x42bbb0 VMOVSD	(%R13,%RCX,8),%XMM0

    (390) 0x42bbb7 VFMSUB213SD	(%R10,%RCX,8),%XMM17,%XMM0

    (390) 0x42bbbe VADDSD	(%R8,%RCX,8),%XMM0,%XMM0

    (390) 0x42bbc4 VMOVSD	%XMM0,(%R8,%RCX,8)

    (390) 0x42bbca INC	%RCX

    (390) 0x42bbcd CMP	%RCX,%RDI

    (390) 0x42bbd0 JNE	42bba0

  (389) 0x42bbd2 JMP	42bc44

0x42bbd4 NOPW	%CS:(%RAX,%RAX,1)

0x42bbe3 NOPW	%CS:(%RAX,%RAX,1)

0x42bbf2 NOPW	%CS:(%RAX,%RAX,1)

  (389) 0x42bc00 XOR	%R9D,%R9D

  (389) 0x42bc03 MOV	-0x48(%RBP),%R10

  (389) 0x42bc07 MOV	-0x38(%RBP),%R11

  (389) 0x42bc0b MOV	-0x50(%RBP),%R13

  (389) 0x42bc0f NOP

    (392) 0x42bc10 VMOVSD	(%RDX,%R9,8),%XMM0

    (392) 0x42bc16 VADDSD	(%R10,%R9,8),%XMM0,%XMM0

    (392) 0x42bc1c VMOVSD	%XMM0,(%RDX,%R9,8)

    (392) 0x42bc22 VMOVSD	(%R13,%R9,8),%XMM0

    (392) 0x42bc29 VFMSUB213SD	(%R11,%R9,8),%XMM17,%XMM0

    (392) 0x42bc30 VADDSD	(%R8,%R9,8),%XMM0,%XMM0

    (392) 0x42bc36 VMOVSD	%XMM0,(%R8,%R9,8)

    (392) 0x42bc3c INC	%R9

    (392) 0x42bc3f CMP	%R9,%RDI

    (392) 0x42bc42 JNE	42bc10

  (389) 0x42bc44 MOV	-0xc0(%RBP),%RCX

  (389) 0x42bc4b ADD	-0xa0(%RBP),%RCX

  (389) 0x42bc52 JNE	42bc80

  (389) 0x42bc54 XOR	%EDX,%EDX

  (389) 0x42bc56 MOV	-0x80(%RBP),%RDI

  (389) 0x42bc5a JMP	42bd4c

0x42bc5f NOPW	%CS:(%RAX,%RAX,1)

0x42bc6e NOPW	%CS:(%RAX,%RAX,1)

0x42bc7d NOPL	(%RAX)

  (389) 0x42bc80 MOV	%RDI,%R8

  (389) 0x42bc83 MOV	$0x7ffffffffffffffe,%RCX

  (389) 0x42bc8d AND	%RCX,%R8

  (389) 0x42bc90 LEA	0x8(%RAX),%R9

  (389) 0x42bc94 LEA	0x8(%RSI),%R10

  (389) 0x42bc98 LEA	0x8(%RAX,%R14,8),%R11

  (389) 0x42bc9d MOV	-0x80(%RBP),%RDI

  (389) 0x42bca1 LEA	0x8(%RSI,%RDI,8),%RBX

  (389) 0x42bca6 MOV	%R14,%RCX

  (389) 0x42bca9 SAL	$0x4,%RCX

  (389) 0x42bcad LEA	0x8(%RAX,%RCX,1),%RCX

  (389) 0x42bcb2 MOV	%RDI,%RDX

  (389) 0x42bcb5 SAL	$0x4,%RDX

  (389) 0x42bcb9 LEA	0x8(%RSI,%RDX,1),%R15

  (389) 0x42bcbe XOR	%EDX,%EDX

    (391) 0x42bcc0 VMOVSD	(%R13,%RDX,8),%XMM0

    (391) 0x42bcc7 VMOVSD	-0x8(%R9,%RDX,8),%XMM1

    (391) 0x42bcce VFNMADD213SD	-0x8(%R10,%RDX,8),%XMM0,%XMM1

    (391) 0x42bcd5 VMOVSD	%XMM1,-0x8(%R10,%RDX,8)

    (391) 0x42bcdc VMOVSD	-0x8(%R11,%RDX,8),%XMM1

    (391) 0x42bce3 VFNMADD213SD	-0x8(%RBX,%RDX,8),%XMM0,%XMM1

    (391) 0x42bcea VMOVSD	%XMM1,-0x8(%RBX,%RDX,8)

    (391) 0x42bcf0 VMOVSD	-0x8(%RCX,%RDX,8),%XMM1

    (391) 0x42bcf6 VFNMADD213SD	-0x8(%R15,%RDX,8),%XMM0,%XMM1

    (391) 0x42bcfd VMOVSD	%XMM1,-0x8(%R15,%RDX,8)

    (391) 0x42bd04 VMOVSD	0x8(%R13,%RDX,8),%XMM0

    (391) 0x42bd0b VMOVSD	(%R9,%RDX,8),%XMM1

    (391) 0x42bd11 VFNMADD213SD	(%R10,%RDX,8),%XMM0,%XMM1

    (391) 0x42bd17 VMOVSD	%XMM1,(%R10,%RDX,8)

    (391) 0x42bd1d VMOVSD	(%R11,%RDX,8),%XMM1

    (391) 0x42bd23 VFNMADD213SD	(%RBX,%RDX,8),%XMM0,%XMM1

    (391) 0x42bd29 VMOVSD	%XMM1,(%RBX,%RDX,8)

    (391) 0x42bd2e VMOVSD	(%RCX,%RDX,8),%XMM1

    (391) 0x42bd33 VFNMADD213SD	(%R15,%RDX,8),%XMM0,%XMM1

    (391) 0x42bd39 VMOVSD	%XMM1,(%R15,%RDX,8)

    (391) 0x42bd3f ADD	$0x2,%RDX

    (391) 0x42bd43 CMP	%RDX,%R8

    (391) 0x42bd46 JNE	42bcc0

  (389) 0x42bd4c MOV	-0x58(%RBP),%R10

  (389) 0x42bd50 TEST	$0x1,%R10B

  (389) 0x42bd54 MOV	-0x68(%RBP),%R11

  (389) 0x42bd58 MOV	-0x90(%RBP),%R15

  (389) 0x42bd5f MOV	-0x48(%RBP),%R9

  (389) 0x42bd63 MOV	-0x38(%RBP),%RBX

  (389) 0x42bd67 JE	42b4c0

  (389) 0x42bd6d VMOVSD	(%R13,%RDX,8),%XMM0

  (389) 0x42bd74 VMOVSD	(%RAX,%RDX,8),%XMM1

  (389) 0x42bd79 VFNMADD213SD	(%RSI,%RDX,8),%XMM0,%XMM1

  (389) 0x42bd7f VMOVSD	%XMM1,(%RSI,%RDX,8)

  (389) 0x42bd84 LEA	(%RDX,%R14,1),%RCX

  (389) 0x42bd88 VMOVSD	(%RAX,%RCX,8),%XMM1

  (389) 0x42bd8d LEA	(%RDX,%RDI,1),%RCX

  (389) 0x42bd91 VFNMADD213SD	(%RSI,%RCX,8),%XMM0,%XMM1

  (389) 0x42bd97 VMOVSD	%XMM1,(%RSI,%RCX,8)

  (389) 0x42bd9c LEA	(%RDX,%R14,2),%RCX

  (389) 0x42bda0 VMOVSD	(%RAX,%RCX,8),%XMM1

  (389) 0x42bda5 LEA	(%RDX,%RDI,2),%RAX

  (389) 0x42bda9 VFNMADD213SD	(%RSI,%RAX,8),%XMM0,%XMM1

  (389) 0x42bdaf VMOVSD	%XMM1,(%RSI,%RAX,8)

  (389) 0x42bdb4 JMP	42b4c0

0x42bdb9 NOPL	(%RAX)

0x42bdc0 MOVQ	$0,0x10(%R12)

0x42bdc9 MOV	0x90(%R12),%R10

0x42bdd1 TEST	%R10,%R10

0x42bdd4 JE	42be40

0x42bdd6 MOV	0xd8(%R12),%R9

0x42bdde MOV	0x100(%R12),%RDX

0x42bde6 MOVSXD	0xf0(%R12),%RDI

0x42bdee MOV	-0xa8(%RBP),%RAX

0x42bdf5 MOV	0x18(%RAX),%RSI

0x42bdf9 MOV	0x128(%R12),%RAX

0x42be01 MOV	-0xb0(%RBP),%RCX

0x42be08 MOV	0x18(%RCX),%RCX

0x42be0c LEA	(%RDI,%RDI,1),%R8

0x42be10 CMP	$0x1,%R10

0x42be14 JNE	42be80

0x42be16 VXORPD	%XMM0,%XMM0,%XMM0

0x42be1a XOR	%R11D,%R11D

0x42be1d MOV	-0x60(%RBP),%R13

0x42be21 JMP	42bf5a

0x42be26 NOPW	%CS:(%RAX,%RAX,1)

0x42be35 NOPW	%CS:(%RAX,%RAX,1)

0x42be40 VMOVSD	0x10b200(%RIP),%XMM0

0x42be48 JMP	42bfc6

0x42be4d NOPW	%CS:(%RAX,%RAX,1)

0x42be5c NOPW	%CS:(%RAX,%RAX,1)

0x42be6b NOPW	%CS:(%RAX,%RAX,1)

0x42be7a NOPW	(%RAX,%RAX,1)

0x42be80 MOV	%R10,%RBX

0x42be83 AND	$-0x2,%RBX

0x42be87 LEA	0x8(%RDX,%RDI,8),%R14

0x42be8c LEA	0x8(%RDX,%R8,8),%R15

0x42be91 LEA	0x28(%RSI),%R12

0x42be95 VXORPD	%XMM0,%XMM0,%XMM0

0x42be99 XOR	%R11D,%R11D

0x42be9c MOV	-0x60(%RBP),%R13

(387) 0x42bea0 VADDSD	(%R9,%R11,8),%XMM0,%XMM0

(387) 0x42bea6 VMOVSD	%XMM0,0x10(%R13)

(387) 0x42beac VMOVSD	(%RDX,%R11,8),%XMM0

(387) 0x42beb2 VMOVHPD	-0x8(%R14,%R11,8),%XMM0,%XMM0

(387) 0x42beb9 VADDPD	-0x28(%R12),%XMM0,%XMM0

(387) 0x42bec0 VMOVSD	-0x18(%R12),%XMM1

(387) 0x42bec7 VADDSD	-0x8(%R15,%R11,8),%XMM1,%XMM1

(387) 0x42bece VMOVUPD	%XMM0,-0x28(%R12)

(387) 0x42bed5 VMOVSD	%XMM1,-0x18(%R12)

(387) 0x42bedc VMOVSD	(%RCX,%R11,8),%XMM0

(387) 0x42bee2 VADDSD	(%RAX,%R11,8),%XMM0,%XMM0

(387) 0x42bee8 VMOVSD	%XMM0,(%RCX,%R11,8)

(387) 0x42beee VMOVSD	0x8(%R9,%R11,8),%XMM0

(387) 0x42bef5 VADDSD	0x10(%R13),%XMM0,%XMM0

(387) 0x42befb VMOVSD	%XMM0,0x10(%R13)

(387) 0x42bf01 VMOVSD	0x8(%RDX,%R11,8),%XMM0

(387) 0x42bf08 VMOVHPD	(%R14,%R11,8),%XMM0,%XMM0

(387) 0x42bf0e VADDPD	-0x10(%R12),%XMM0,%XMM0

(387) 0x42bf15 VMOVSD	(%R12),%XMM1

(387) 0x42bf1b VADDSD	(%R15,%R11,8),%XMM1,%XMM1

(387) 0x42bf21 VMOVUPD	%XMM0,-0x10(%R12)

(387) 0x42bf28 VMOVSD	%XMM1,(%R12)

(387) 0x42bf2e VMOVSD	0x8(%RCX,%R11,8),%XMM0

(387) 0x42bf35 VADDSD	0x8(%RAX,%R11,8),%XMM0,%XMM0

(387) 0x42bf3c VMOVSD	%XMM0,0x8(%RCX,%R11,8)

(387) 0x42bf43 VMOVSD	0x10(%R13),%XMM0

(387) 0x42bf49 ADD	$0x2,%R11

(387) 0x42bf4d ADD	$0x30,%R12

(387) 0x42bf51 CMP	%R11,%RBX

(387) 0x42bf54 JNE	42bea0

0x42bf5a TEST	$0x1,%R10B

0x42bf5e MOV	%R13,%R12

0x42bf61 JE	42bfbe

0x42bf63 VADDSD	(%R9,%R11,8),%XMM0,%XMM0

0x42bf69 VMOVSD	%XMM0,0x10(%R12)

0x42bf70 ADD	%R11,%RDI

0x42bf73 ADD	%R11,%R8

0x42bf76 LEA	(%R11,%R11,2),%R9

0x42bf7a VMOVSD	(%RDX,%R11,8),%XMM0

0x42bf80 VMOVHPD	(%RDX,%RDI,8),%XMM0,%XMM0

0x42bf85 VADDPD	(%RSI,%R9,8),%XMM0,%XMM0

0x42bf8b VMOVSD	0x10(%RSI,%R9,8),%XMM1

0x42bf92 VADDSD	(%RDX,%R8,8),%XMM1,%XMM1

0x42bf98 VMOVUPD	%XMM0,(%RSI,%R9,8)

0x42bf9e VMOVSD	%XMM1,0x10(%RSI,%R9,8)

0x42bfa5 VMOVSD	(%RCX,%R11,8),%XMM0

0x42bfab VADDSD	(%RAX,%R11,8),%XMM0,%XMM0

0x42bfb1 VMOVSD	%XMM0,(%RCX,%R11,8)

0x42bfb7 VMOVSD	0x10(%R12),%XMM0

0x42bfbe VMULSD	0x10b072(%RIP),%XMM0,%XMM0

0x42bfc6 VMOVSD	%XMM0,0x10(%R12)

0x42bfcd ADD	$0x98,%RSP

0x42bfd4 POP	%RBX

0x42bfd5 POP	%R12

0x42bfd7 POP	%R13

0x42bfd9 POP	%R14

0x42bfdb POP	%R15

0x42bfdd POP	%RBP

0x42bfde VZEROUPPER

0x42bfe1 RET

0x42bfe2 NOPW	%CS:(%RAX,%RAX,1)

0x42bfec NOPW	%CS:(%RAX,%RAX,1)

0x42bff6 NOPW	%CS:(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
►99.84+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:411	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.extracted.112	miniqmc.cpp:397	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so

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_4

Source file and lines	TwoBodyJastrowRef.h:268-432
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/DistanceTable.h:268
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:231,244,263,273
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:140-141
/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:235,924,1115
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h:1028,1182
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:145,169
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:268-274,360-367,375-398,419-432
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229,249
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316

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 23.33 to 6.00 cycles (3.89x speedup).

Workaround

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

Vectorization

Your function is not vectorized. Only 13% of vector register length is used (average across all SSE/AVX instructions).

Details

12% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

5% of SSE/AVX loads are used in vector version.
8% of SSE/AVX stores are used in vector version.
25% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX multiply instructions are used in vector version.
27% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Workaround

Read the "512-bits vectorization" report at "Potential" confidence level.

Execution units bottlenecks

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

512-bits vectorization

On some x86 processors supporting 512-bits vectorization, compilers are often too conservative and limit vectorization to 256 bits. Performance can then be improved by enforcing 512-bits vectorization, especially with many vectorized and high trip count loops. 512-bits vectorization performance overhead (compared to 256-bits) is generally lower on newer processors.

Workaround

Recompile with -mprefer-vector-width=512

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_GNR/173-773-5521/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.

VZEROUPPER: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:432

Type of elements and instruction set

4 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 1 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (two at a time).

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

The binary function is composed of 6 FP arithmetical operations:

5: addition or subtraction
1: multiply

The binary function is loading 216 bytes (27 double precision FP elements). The binary function is storing 104 bytes (13 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.02 FP operations per loaded or stored byte.

General properties

nb instructions	133
nb uops	135
loop length	958
used x86 registers	16
used mmx registers	0
used xmm registers	4
used ymm registers	1
used zmm registers	0
nb stack references	6
ADD-SUB / MUL ratio	4.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	23.33 cycles
front end	23.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	4.90	4.90	11.33	11.33	9.50	4.70	4.70	9.50	9.50	9.50	4.80	11.33
cycles	4.90	4.90	11.33	11.33	9.50	4.70	4.70	9.50	9.50	9.50	4.80	11.33

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	23.33
Dispatch	11.33
Overall L1	23.33

Vectorization ratios

INT

all	5%
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)
other	12%

all	19%
load	7%
store	20%
mul	0%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	66%

INT+FP

all	12%
load	5%
store	8%
mul	0%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	27%

Vector efficiency ratios

INT

all	12%
load	12%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	14%

all	14%
load	13%
store	15%
mul	12%
add-sub	15%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	20%

INT+FP

all	13%
load	13%
store	13%
mul	12%
add-sub	15%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 23.33 cycles. At this rate:

4% of peak load performance is reached (9.26 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.46 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 23.33 to 11.33 cycles (2.06x speedup).

ASM code

In the binary file, the address of the function is: 42b340

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
SUB $0x98,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RCX,-0xb0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDX,-0xa8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
TEST %R8B,%R8B	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
MOV %RDI,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JE 42bdc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa80>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x248(%R12),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 479590 <_ZNK11qmcplusplus11ParticleSet14getDistTableAAEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0xa0(%R12),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %R11,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 42bdc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa80>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD 0x10ce2b(%RIP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x10bcd1(%RIP),%XMM17	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VBROADCASTSD 0x10bcc7(%RIP),%YMM18	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	0.33	scal (12.5%)
MOV %R11,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RBX,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JMP 42b41f <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xdf>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVQ $0,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x90(%R12),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
TEST %R10,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 42be40 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xb00>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0xd8(%R12),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x100(%R12),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0xf0(%R12),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RAX),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x128(%R12),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xb0(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RCX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RDI,%RDI,1),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x1,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 42be80 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xb40>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	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	0.17	N/A
MOV -0x60(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
JMP 42bf5a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xc1a>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD 0x10b200(%RIP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
JMP 42bfc6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xc86>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R10,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
AND $-0x2,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (12.5%)
LEA 0x8(%RDX,%RDI,8),%R14	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA 0x8(%RDX,%R8,8),%R15	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA 0x28(%RSI),%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	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	0.17	N/A
MOV -0x60(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
TEST $0x1,%R10B	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
MOV %R13,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JE 42bfbe <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xc7e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VADDSD (%R9,%R11,8),%XMM0,%XMM0	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM0,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R11,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %R11,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%R11,%R11,2),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RDX,%R11,8),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVHPD (%RDX,%RDI,8),%XMM0,%XMM0	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VADDPD (%RSI,%R9,8),%XMM0,%XMM0	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (25.0%)
VMOVSD 0x10(%RSI,%R9,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDSD (%RDX,%R8,8),%XMM1,%XMM1	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVUPD %XMM0,(%RSI,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
VMOVSD %XMM1,0x10(%RSI,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD (%RCX,%R11,8),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDSD (%RAX,%R11,8),%XMM0,%XMM0	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM0,(%RCX,%R11,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD 0x10(%R12),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMULSD 0x10b072(%RIP),%XMM0,%XMM0	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM0,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x98,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run icx_4

Source file and lines	TwoBodyJastrowRef.h:268-432
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/DistanceTable.h:268
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:231,244,263,273
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:140-141
/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:235,924,1115
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h:1028,1182
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:145,169
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:268-274,360-367,375-398,419-432
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229,249
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316

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 23.33 to 6.00 cycles (3.89x speedup).

Workaround

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

Vectorization

Your function is not vectorized. Only 13% of vector register length is used (average across all SSE/AVX instructions).

Details

12% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

5% of SSE/AVX loads are used in vector version.
8% of SSE/AVX stores are used in vector version.
25% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX multiply instructions are used in vector version.
27% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Workaround

Read the "512-bits vectorization" report at "Potential" confidence level.

Execution units bottlenecks

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

512-bits vectorization

Workaround

Recompile with -mprefer-vector-width=512

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_GNR/173-773-5521/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.

VZEROUPPER: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:432

Type of elements and instruction set

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

The binary function is composed of 6 FP arithmetical operations:

5: addition or subtraction
1: multiply

The binary function is loading 216 bytes (27 double precision FP elements). The binary function is storing 104 bytes (13 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.02 FP operations per loaded or stored byte.

General properties

nb instructions	133
nb uops	135
loop length	958
used x86 registers	16
used mmx registers	0
used xmm registers	4
used ymm registers	1
used zmm registers	0
nb stack references	6
ADD-SUB / MUL ratio	4.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	23.33 cycles
front end	23.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	4.90	4.90	11.33	11.33	9.50	4.70	4.70	9.50	9.50	9.50	4.80	11.33
cycles	4.90	4.90	11.33	11.33	9.50	4.70	4.70	9.50	9.50	9.50	4.80	11.33

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	23.33
Dispatch	11.33
Overall L1	23.33

Vectorization ratios

INT

all	5%
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)
other	12%

all	19%
load	7%
store	20%
mul	0%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	66%

INT+FP

all	12%
load	5%
store	8%
mul	0%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	27%

Vector efficiency ratios

INT

all	12%
load	12%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	14%

all	14%
load	13%
store	15%
mul	12%
add-sub	15%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	20%

INT+FP

all	13%
load	13%
store	13%
mul	12%
add-sub	15%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 23.33 cycles. At this rate:

4% of peak load performance is reached (9.26 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.46 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: 42b340

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
SUB $0x98,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RCX,-0xb0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDX,-0xa8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
TEST %R8B,%R8B	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
MOV %RDI,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JE 42bdc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa80>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x248(%R12),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 479590 <_ZNK11qmcplusplus11ParticleSet14getDistTableAAEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0xa0(%R12),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %R11,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 42bdc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa80>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD 0x10ce2b(%RIP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x10bcd1(%RIP),%XMM17	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VBROADCASTSD 0x10bcc7(%RIP),%YMM18	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	0.33	scal (12.5%)
MOV %R11,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RBX,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JMP 42b41f <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xdf>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVQ $0,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x90(%R12),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
TEST %R10,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 42be40 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xb00>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0xd8(%R12),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x100(%R12),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0xf0(%R12),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RAX),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x128(%R12),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xb0(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RCX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RDI,%RDI,1),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x1,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 42be80 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xb40>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	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	0.17	N/A
MOV -0x60(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
JMP 42bf5a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xc1a>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD 0x10b200(%RIP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
JMP 42bfc6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xc86>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R10,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
AND $-0x2,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (12.5%)
LEA 0x8(%RDX,%RDI,8),%R14	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA 0x8(%RDX,%R8,8),%R15	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA 0x28(%RSI),%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	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	0.17	N/A
MOV -0x60(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
TEST $0x1,%R10B	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
MOV %R13,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JE 42bfbe <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xc7e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VADDSD (%R9,%R11,8),%XMM0,%XMM0	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM0,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R11,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %R11,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%R11,%R11,2),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RDX,%R11,8),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVHPD (%RDX,%RDI,8),%XMM0,%XMM0	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VADDPD (%RSI,%R9,8),%XMM0,%XMM0	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (25.0%)
VMOVSD 0x10(%RSI,%R9,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDSD (%RDX,%R8,8),%XMM1,%XMM1	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVUPD %XMM0,(%RSI,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
VMOVSD %XMM1,0x10(%RSI,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD (%RCX,%R11,8),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDSD (%RAX,%R11,8),%XMM0,%XMM0	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM0,(%RCX,%R11,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD 0x10(%R12),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMULSD 0x10b072(%RIP),%XMM0,%XMM0	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM0,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x98,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::TwoBodyJastrowRef >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib, std::allocator > >&, qmcplusplus::Particle...–	0.11	0.09
○Loop 387 - TwoBodyJastrowRef.h:423-427 - exec	0.00	0.00
▼Loop 388 - TwoBodyJastrowRef.h:268-420 - exec–	0.00	0.00
▼Loop 389 - TwoBodyJastrowRef.h:268-420 - exec–	0.00	0.01
○Loop 391 - TwoBodyJastrowRef.h:393-398 - exec	0.03	0.02
○Loop 397 - TwoBodyJastrowRef.h:381-382 - exec	0.02	0.02
○Loop 395 - TwoBodyJastrowRef.h:381-382 - exec	0.02	0.02
○Loop 399 - TwoBodyJastrowRef.h:381-382 - exec	0.02	0.02
○Loop 401 - TwoBodyJastrowRef.h:375-376 - exec	0.01	0.01
○Loop 393 - TwoBodyJastrowRef.h:388-391 - exec	0.01	0.01
○Loop 403 - stl_numeric.h:140-141 - exec	0.00	0.01
○Loop 394 - TwoBodyJastrowRef.h:381-382 - exec	0.00	0.00
○Loop 392 - TwoBodyJastrowRef.h:388-391 - exec	0.00	0.00
○Loop 396 - TwoBodyJastrowRef.h:381-382 - exec	0.00	0.00
○Loop 398 - TwoBodyJastrowRef.h:381-382 - exec	0.00	0.00
○Loop 404 - TwoBodyJastrowRef.h:269-274 - exec	0.00	0.00
○Loop 402 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 390 - TwoBodyJastrowRef.h:388-391 - exec	0.00	0.00
○Loop 400 - TwoBodyJastrowRef.h:375-376 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

512-bits vectorization

Workaround

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

512-bits vectorization

Workaround

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