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): 0.09% \| (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: 924 - 1115

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

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];

[...]

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]; }

0x422e60 PUSH	%RBP

0x422e61 MOV	%RSP,%RBP

0x422e64 PUSH	%R15

0x422e66 PUSH	%R14

0x422e68 PUSH	%R13

0x422e6a PUSH	%R12

0x422e6c PUSH	%RBX

0x422e6d SUB	$0x88,%RSP

0x422e74 MOV	%RCX,-0xa8(%RBP)

0x422e7b MOV	%RDX,-0xa0(%RBP)

0x422e82 MOV	%RDI,%R12

0x422e85 TEST	%R8B,%R8B

0x422e88 MOV	%RDI,-0x40(%RBP)

0x422e8c JE	4237f4

0x422e92 MOV	%RSI,%R13

0x422e95 MOV	0x248(%R12),%ESI

0x422e9d MOV	%R13,%RDI

0x422ea0 CALL	460b50 <_ZNK11qmcplusplus11ParticleSet14getDistTableAAEi>

0x422ea5 MOV	%RAX,-0x98(%RBP)

0x422eac MOV	0xa0(%R12),%R10

0x422eb4 TEST	%R10,%R10

0x422eb7 JE	4237f4

0x422ebd MOV	$0x7ffffffffffffffc,%R15

0x422ec7 XOR	%ECX,%ECX

0x422ec9 VMOVSD	0xdb3e7(%RIP),%XMM5

0x422ed1 MOV	%R10,-0x38(%RBP)

0x422ed5 MOV	%R13,-0x68(%RBP)

0x422ed9 JMP	422efb

0x422edb NOPL	(%RAX,%RAX,1)

(383) 0x422ee0 MOV	-0x38(%RBP),%RAX

(383) 0x422ee4 MOV	-0xb0(%RBP),%RCX

(383) 0x422eeb INC	%RCX

(383) 0x422eee MOV	%RAX,-0x38(%RBP)

(383) 0x422ef2 CMP	%RCX,%RAX

(383) 0x422ef5 JBE	4237f4

(383) 0x422efb MOV	0x268(%R13),%RAX

(383) 0x422f02 MOV	0x18(%RAX),%RAX

(383) 0x422f06 MOVSXD	(%RAX,%RCX,4),%RSI

(383) 0x422f0a MOV	%RCX,-0xb0(%RBP)

(383) 0x422f11 MOV	0x4(%RAX,%RCX,4),%EAX

(383) 0x422f15 MOV	%EAX,-0x84(%RBP)

(383) 0x422f1b CMP	%EAX,%ESI

(383) 0x422f1d JGE	422ee0

(383) 0x422f1f MOV	0x140(%R12),%R9

(383) 0x422f27 MOV	0x158(%R12),%R11

(383) 0x422f2f MOV	0x170(%R12),%RBX

(383) 0x422f37 MOV	$0x1fffffffffffffff,%RAX

(383) 0x422f41 ADD	%RSI,%RAX

(383) 0x422f44 MOV	%RAX,-0x90(%RBP)

(383) 0x422f4b JMP	422f69

0x422f4d NOPL	(%RAX)

  (384) 0x422f50 INC	%RSI

  (384) 0x422f53 INCQ	-0x90(%RBP)

  (384) 0x422f5a MOV	%R10,%RAX

  (384) 0x422f5d CMP	%ESI,-0x84(%RBP)

  (384) 0x422f63 JE	422ee4

  (384) 0x422f69 MOV	%RBX,-0x58(%RBP)

  (384) 0x422f6d MOV	%R11,-0x50(%RBP)

  (384) 0x422f71 MOV	-0x98(%RBP),%RAX

  (384) 0x422f78 MOV	0x48(%RAX),%RAX

  (384) 0x422f7c LEA	(%RSI,%RSI,4),%RCX

  (384) 0x422f80 MOV	%RCX,-0x48(%RBP)

  (384) 0x422f84 MOV	0x18(%RAX,%RCX,8),%R8

  (384) 0x422f89 TEST	%RSI,%RSI

  (384) 0x422f8c MOV	%RSI,-0x78(%RBP)

  (384) 0x422f90 MOV	%R9,-0x60(%RBP)

  (384) 0x422f94 JLE	422ff4

  (384) 0x422f96 MOV	%ESI,%EBX

  (384) 0x422f98 SAL	$0x3,%RBX

  (384) 0x422f9c MOV	%R9,%RDI

  (384) 0x422f9f XOR	%ESI,%ESI

  (384) 0x422fa1 MOV	%RBX,%RDX

  (384) 0x422fa4 MOV	%R10,%R14

  (384) 0x422fa7 MOV	%R15,%R12

  (384) 0x422faa MOV	%R13,%R15

  (384) 0x422fad MOV	%R8,%R13

  (384) 0x422fb0 VZEROUPPER

  (384) 0x422fb3 CALL	4efda0 <_intel_fast_memset>

  (384) 0x422fb8 MOV	-0x50(%RBP),%RDI

  (384) 0x422fbc XOR	%ESI,%ESI

  (384) 0x422fbe MOV	%RBX,%RDX

  (384) 0x422fc1 CALL	4efda0 <_intel_fast_memset>

  (384) 0x422fc6 MOV	-0x58(%RBP),%RDI

  (384) 0x422fca XOR	%ESI,%ESI

  (384) 0x422fcc MOV	%RBX,%RDX

  (384) 0x422fcf CALL	4efda0 <_intel_fast_memset>

  (384) 0x422fd4 MOV	%R13,%R8

  (384) 0x422fd7 MOV	%R15,%R13

  (384) 0x422fda MOV	%R12,%R15

  (384) 0x422fdd MOV	-0x40(%RBP),%R12

  (384) 0x422fe1 MOV	-0x60(%RBP),%R9

  (384) 0x422fe5 MOV	-0x78(%RBP),%RSI

  (384) 0x422fe9 MOV	%R14,%R10

  (384) 0x422fec VMOVSD	0xdb2c4(%RIP),%XMM5

  (384) 0x422ff4 MOV	-0x38(%RBP),%RCX

  (384) 0x422ff8 TEST	%RCX,%RCX

  (384) 0x422ffb JE	4230c0

  (384) 0x423001 MOV	0x18(%R13),%RAX

  (384) 0x423005 IMUL	(%RAX,%RSI,4),%ECX

  (384) 0x423009 MOV	%R12,%R14

  (384) 0x42300c MOVSXD	%ECX,%RAX

  (384) 0x42300f SAL	$0x3,%RAX

  (384) 0x423013 MOV	%RAX,-0x38(%RBP)

  (384) 0x423017 XOR	%EAX,%EAX

  (384) 0x423019 MOV	-0x58(%RBP),%R13

  (384) 0x42301d MOV	-0x50(%RBP),%R15

  (384) 0x423021 NOPW	%CS:(%RAX,%RAX,1)

    (403) 0x423030 MOV	0x200(%R14),%RCX

    (403) 0x423037 ADD	-0x38(%RBP),%RCX

    (403) 0x42303b MOV	(%RCX,%RAX,8),%RDI

    (403) 0x42303f MOV	-0x68(%RBP),%RCX

    (403) 0x423043 MOV	0x268(%RCX),%RCX

    (403) 0x42304a MOV	0x18(%RCX),%RCX

    (403) 0x42304e LEA	0x1(%RAX),%RBX

    (403) 0x423052 MOV	(%RCX,%RAX,4),%EDX

    (403) 0x423055 MOV	0x4(%RCX,%RAX,4),%ECX

    (403) 0x423059 CMP	%ESI,%ECX

    (403) 0x42305b CMOVGE	%ESI,%ECX

    (403) 0x42305e MOV	%R8,%R12

    (403) 0x423061 PUSHQ	0x1e8(%R14)

    (403) 0x423068 PUSHQ	0x1d0(%R14)

    (403) 0x42306f PUSH	%R13

    (403) 0x423071 PUSH	%R15

    (403) 0x423073 VZEROUPPER

    (403) 0x423076 CALL	41fba0 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi>

    (403) 0x42307b MOV	%R12,%R8

    (403) 0x42307e MOV	-0x60(%RBP),%R9

    (403) 0x423082 MOV	-0x78(%RBP),%RSI

    (403) 0x423086 ADD	$0x20,%RSP

    (403) 0x42308a MOV	0xa0(%R14),%R10

    (403) 0x423091 MOV	%RBX,%RAX

    (403) 0x423094 CMP	%RBX,%R10

    (403) 0x423097 JA	423030

  (384) 0x423099 MOV	0x140(%R14),%R9

  (384) 0x4230a0 MOV	%R10,-0x38(%RBP)

  (384) 0x4230a4 MOV	%R14,%R12

  (384) 0x4230a7 MOV	-0x68(%RBP),%R13

  (384) 0x4230ab MOV	$0x7ffffffffffffffc,%R15

  (384) 0x4230b5 VMOVSD	0xdb1fb(%RIP),%XMM5

  (384) 0x4230bd JMP	4230c8

0x4230bf NOP

  (384) 0x4230c0 MOVQ	$0,-0x38(%RBP)

  (384) 0x4230c8 VXORPD	%XMM0,%XMM0,%XMM0

  (384) 0x4230cc VXORPD	%XMM1,%XMM1,%XMM1

  (384) 0x4230d0 MOV	$0x1fffffffffffffff,%RAX

  (384) 0x4230da TEST	%RAX,%RSI

  (384) 0x4230dd JE	42315e

  (384) 0x4230df LEA	(%RSI,%RAX,1),%RCX

  (384) 0x4230e3 AND	%RAX,%RCX

  (384) 0x4230e6 INC	%RCX

  (384) 0x4230e9 MOV	%RCX,%RAX

  (384) 0x4230ec MOV	$0x3ffffffffffffffc,%RDX

  (384) 0x4230f6 AND	%RDX,%RAX

  (384) 0x4230f9 JE	423140

  (384) 0x4230fb VXORPD	%XMM1,%XMM1,%XMM1

  (384) 0x4230ff XOR	%EDX,%EDX

  (384) 0x423101 NOPW	%CS:(%RAX,%RAX,1)

    (402) 0x423110 VADDPD	(%R9,%RDX,8),%YMM1,%YMM1

    (402) 0x423116 ADD	$0x4,%RDX

    (402) 0x42311a CMP	%RAX,%RDX

    (402) 0x42311d JB	423110

  (384) 0x42311f VEXTRACTF128	$0x1,%YMM1,%XMM2

  (384) 0x423125 VADDPD	%XMM2,%XMM1,%XMM1

  (384) 0x423129 VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

  (384) 0x42312e VADDSD	%XMM2,%XMM1,%XMM1

  (384) 0x423132 CMP	%RAX,%RCX

  (384) 0x423135 JNE	423142

  (384) 0x423137 JMP	42315e

0x423139 NOPL	(%RAX)

  (384) 0x423140 XOR	%EAX,%EAX

  (384) 0x423142 MOV	$0x3d,%CL

  (384) 0x423144 BZHI	%RCX,-0x90(%RBP),%RCX

  (384) 0x42314d INC	%RCX

    (401) 0x423150 VADDSD	(%R9,%RAX,8),%XMM1,%XMM1

    (401) 0x423156 INC	%RAX

    (401) 0x423159 CMP	%RAX,%RCX

    (401) 0x42315c JNE	423150

  (384) 0x42315e MOV	0xd8(%R12),%RDX

  (384) 0x423166 VMOVSD	%XMM1,(%RDX,%RSI,8)

  (384) 0x42316b MOV	0x158(%R12),%R11

  (384) 0x423173 MOV	0x170(%R12),%RBX

  (384) 0x42317b MOV	-0x98(%RBP),%RAX

  (384) 0x423182 MOV	0x60(%RAX),%RAX

  (384) 0x423186 TEST	%RSI,%RSI

  (384) 0x423189 JLE	423203

  (384) 0x42318b MOV	%RSI,%RCX

  (384) 0x42318e AND	%R15,%RCX

  (384) 0x423191 JE	4231e0

  (384) 0x423193 VXORPD	%XMM0,%XMM0,%XMM0

  (384) 0x423197 XOR	%EDI,%EDI

  (384) 0x423199 VBROADCASTSD	0xdb116(%RIP),%YMM1

  (384) 0x4231a2 NOPW	%CS:(%RAX,%RAX,1)

    (400) 0x4231b0 VADDPD	(%RBX,%RDI,8),%YMM0,%YMM0

    (400) 0x4231b5 VFMADD231PD	(%R11,%RDI,8),%YMM1,%YMM0

    (400) 0x4231bb ADD	$0x4,%RDI

    (400) 0x4231bf CMP	%RCX,%RDI

    (400) 0x4231c2 JB	4231b0

  (384) 0x4231c4 VEXTRACTF128	$0x1,%YMM0,%XMM1

  (384) 0x4231ca VADDPD	%XMM1,%XMM0,%XMM0

  (384) 0x4231ce VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

  (384) 0x4231d3 VADDSD	%XMM1,%XMM0,%XMM0

  (384) 0x4231d7 JMP	4231fe

0x4231d9 NOPL	(%RAX)

  (384) 0x4231e0 VXORPD	%XMM0,%XMM0,%XMM0

  (384) 0x4231e4 XOR	%ECX,%ECX

  (384) 0x4231e6 NOPW	%CS:(%RAX,%RAX,1)

    (399) 0x4231f0 VADDSD	(%RBX,%RCX,8),%XMM0,%XMM0

    (399) 0x4231f5 VFMADD231SD	(%R11,%RCX,8),%XMM5,%XMM0

    (399) 0x4231fb INC	%RCX

    (399) 0x4231fe CMP	%RCX,%RSI

    (399) 0x423201 JNE	4231f0

  (384) 0x423203 MOV	-0x48(%RBP),%RCX

  (384) 0x423207 MOV	0x8(%RAX,%RCX,8),%R14

  (384) 0x42320c MOV	0x18(%RAX,%RCX,8),%RAX

  (384) 0x423211 VXORPD	%XMM2,%XMM2,%XMM2

  (384) 0x423215 VXORPD	%XMM1,%XMM1,%XMM1

  (384) 0x423219 TEST	%RSI,%RSI

  (384) 0x42321c JLE	423283

  (384) 0x42321e MOV	%RSI,%RDI

  (384) 0x423221 AND	%R15,%RDI

  (384) 0x423224 JE	423260

  (384) 0x423226 VXORPD	%XMM1,%XMM1,%XMM1

  (384) 0x42322a XOR	%ECX,%ECX

  (384) 0x42322c NOPL	(%RAX)

    (398) 0x423230 VMOVUPD	(%RAX,%RCX,8),%YMM3

    (398) 0x423235 VFMADD231PD	(%R11,%RCX,8),%YMM3,%YMM1

    (398) 0x42323b ADD	$0x4,%RCX

    (398) 0x42323f CMP	%RDI,%RCX

    (398) 0x423242 JB	423230

  (384) 0x423244 VEXTRACTF128	$0x1,%YMM1,%XMM3

  (384) 0x42324a VADDPD	%XMM3,%XMM1,%XMM1

  (384) 0x42324e VSHUFPD	$0x1,%XMM1,%XMM1,%XMM3

  (384) 0x423253 VADDSD	%XMM3,%XMM1,%XMM1

  (384) 0x423257 JMP	42327e

0x423259 NOPL	(%RAX)

  (384) 0x423260 XOR	%EDI,%EDI

  (384) 0x423262 NOPW	%CS:(%RAX,%RAX,1)

    (397) 0x423270 VMOVSD	(%RAX,%RDI,8),%XMM3

    (397) 0x423275 VFMADD231SD	(%R11,%RDI,8),%XMM3,%XMM1

    (397) 0x42327b INC	%RDI

    (397) 0x42327e CMP	%RDI,%RSI

    (397) 0x423281 JNE	423270

  (384) 0x423283 TEST	%RSI,%RSI

  (384) 0x423286 JLE	4232f4

  (384) 0x423288 MOV	%RSI,%R8

  (384) 0x42328b AND	%R15,%R8

  (384) 0x42328e JE	4232d0

  (384) 0x423290 LEA	(%RAX,%R14,8),%RCX

  (384) 0x423294 VXORPD	%XMM2,%XMM2,%XMM2

  (384) 0x423298 XOR	%EDI,%EDI

  (384) 0x42329a NOPW	(%RAX,%RAX,1)

    (396) 0x4232a0 VMOVUPD	(%RCX,%RDI,8),%YMM3

    (396) 0x4232a5 VFMADD231PD	(%R11,%RDI,8),%YMM3,%YMM2

    (396) 0x4232ab ADD	$0x4,%RDI

    (396) 0x4232af CMP	%R8,%RDI

    (396) 0x4232b2 JB	4232a0

  (384) 0x4232b4 VEXTRACTF128	$0x1,%YMM2,%XMM3

  (384) 0x4232ba VADDPD	%XMM3,%XMM2,%XMM2

  (384) 0x4232be VSHUFPD	$0x1,%XMM2,%XMM2,%XMM3

  (384) 0x4232c3 VADDSD	%XMM3,%XMM2,%XMM2

  (384) 0x4232c7 CMP	%R8,%RSI

  (384) 0x4232ca JNE	4232d7

  (384) 0x4232cc JMP	4232f4

0x4232ce XCHG	%AX,%AX

  (384) 0x4232d0 VXORPD	%XMM2,%XMM2,%XMM2

  (384) 0x4232d4 XOR	%R8D,%R8D

  (384) 0x4232d7 LEA	(%RAX,%R14,8),%RCX

  (384) 0x4232db NOPL	(%RAX,%RAX,1)

    (395) 0x4232e0 VMOVSD	(%RCX,%R8,8),%XMM3

    (395) 0x4232e6 VFMADD231SD	(%R11,%R8,8),%XMM3,%XMM2

    (395) 0x4232ec INC	%R8

    (395) 0x4232ef CMP	%R8,%RSI

    (395) 0x4232f2 JNE	4232e0

  (384) 0x4232f4 TEST	%RSI,%RSI

  (384) 0x4232f7 JLE	423350

  (384) 0x4232f9 MOV	%RSI,%R8

  (384) 0x4232fc AND	%R15,%R8

  (384) 0x4232ff JE	423360

  (384) 0x423301 MOV	%R14,%RCX

  (384) 0x423304 SAL	$0x4,%RCX

  (384) 0x423308 ADD	%RAX,%RCX

  (384) 0x42330b VXORPD	%XMM3,%XMM3,%XMM3

  (384) 0x42330f XOR	%EDI,%EDI

  (384) 0x423311 NOPW	%CS:(%RAX,%RAX,1)

    (394) 0x423320 VMOVUPD	(%RCX,%RDI,8),%YMM4

    (394) 0x423325 VFMADD231PD	(%R11,%RDI,8),%YMM4,%YMM3

    (394) 0x42332b ADD	$0x4,%RDI

    (394) 0x42332f CMP	%R8,%RDI

    (394) 0x423332 JB	423320

  (384) 0x423334 VEXTRACTF128	$0x1,%YMM3,%XMM4

  (384) 0x42333a VADDPD	%XMM4,%XMM3,%XMM3

  (384) 0x42333e VSHUFPD	$0x1,%XMM3,%XMM3,%XMM4

  (384) 0x423343 VADDSD	%XMM4,%XMM3,%XMM3

  (384) 0x423347 CMP	%R8,%RSI

  (384) 0x42334a JNE	423367

  (384) 0x42334c JMP	423394

0x42334e XCHG	%AX,%AX

  (384) 0x423350 VXORPD	%XMM3,%XMM3,%XMM3

  (384) 0x423354 JMP	423394

0x423356 NOPW	%CS:(%RAX,%RAX,1)

  (384) 0x423360 VXORPD	%XMM3,%XMM3,%XMM3

  (384) 0x423364 XOR	%R8D,%R8D

  (384) 0x423367 MOV	%R14,%RCX

  (384) 0x42336a SAL	$0x4,%RCX

  (384) 0x42336e ADD	%RAX,%RCX

  (384) 0x423371 NOPW	%CS:(%RAX,%RAX,1)

    (393) 0x423380 VMOVSD	(%RCX,%R8,8),%XMM4

    (393) 0x423386 VFMADD231SD	(%R11,%R8,8),%XMM4,%XMM3

    (393) 0x42338c INC	%R8

    (393) 0x42338f CMP	%R8,%RSI

    (393) 0x423392 JNE	423380

  (384) 0x423394 MOV	%R14,-0x48(%RBP)

  (384) 0x423398 VPUNPCKLQDQ	%XMM2,%XMM1,%XMM1

  (384) 0x42339c MOV	0xf0(%R12),%RDI

  (384) 0x4233a4 MOV	0x100(%R12),%R14

  (384) 0x4233ac VMOVQ	%RDI,%XMM2

  (384) 0x4233b1 VPSLLDQ	$0x8,%XMM2,%XMM2

  (384) 0x4233b6 VPBROADCASTQ	%RSI,%XMM4

  (384) 0x4233bc VPADDQ	%XMM2,%XMM4,%XMM2

  (384) 0x4233c0 VPSLLQ	$0x3,%XMM2,%XMM2

  (384) 0x4233c5 VPBROADCASTQ	%R14,%XMM4

  (384) 0x4233cb VPADDQ	%XMM2,%XMM4,%XMM2

  (384) 0x4233cf VMOVQ	%XMM2,%RCX

  (384) 0x4233d4 VMOVLPD	%XMM1,(%RCX)

  (384) 0x4233d8 VPEXTRQ	$0x1,%XMM2,%RCX

  (384) 0x4233de VMOVHPD	%XMM1,(%RCX)

  (384) 0x4233e2 MOV	%RDI,-0x70(%RBP)

  (384) 0x4233e6 LEA	(%RSI,%RDI,2),%RCX

  (384) 0x4233ea VMOVSD	%XMM3,(%R14,%RCX,8)

  (384) 0x4233f0 VXORPD	0xd9c4e(%RIP){1to2},%XMM0,%XMM0

  (384) 0x4233fa MOV	0x128(%R12),%R8

  (384) 0x423402 VMOVLPD	%XMM0,(%R8,%RSI,8)

  (384) 0x423408 TEST	%RSI,%RSI

  (384) 0x42340b JLE	422f50

  (384) 0x423411 MOV	%R10,-0x80(%RBP)

  (384) 0x423415 DEC	%RSI

  (384) 0x423418 MOV	%RBX,%R13

  (384) 0x42341b MOV	%R11,%RDI

  (384) 0x42341e LEA	(%RDX,%RSI,8),%R11

  (384) 0x423422 CMP	%R8,%R11

  (384) 0x423425 SETAEB	-0x2e(%RBP)

  (384) 0x423429 LEA	(%R8,%RSI,8),%RBX

  (384) 0x42342d CMP	%RDX,%RBX

  (384) 0x423430 SETAEB	-0x2d(%RBP)

  (384) 0x423434 CMP	%R9,%R11

  (384) 0x423437 SETB	%R12B

  (384) 0x42343b LEA	(%R9,%RSI,8),%RCX

  (384) 0x42343f CMP	%RDX,%RCX

  (384) 0x423442 SETBB	-0x2c(%RBP)

  (384) 0x423446 CMP	%R8,%RCX

  (384) 0x423449 SETB	%CL

  (384) 0x42344c MOV	%R9,-0x60(%RBP)

  (384) 0x423450 CMP	%R9,%RBX

  (384) 0x423453 SETBB	-0x2b(%RBP)

  (384) 0x423457 CMP	%RDI,%R11

  (384) 0x42345a SETB	%R10B

  (384) 0x42345e LEA	(%RDI,%RSI,8),%R15

  (384) 0x423462 CMP	%RDX,%R15

  (384) 0x423465 SETBB	-0x2a(%RBP)

  (384) 0x423469 CMP	%R13,%R11

  (384) 0x42346c SETB	%R11B

  (384) 0x423470 LEA	(%R13,%RSI,8),%R9

  (384) 0x423475 CMP	%RDX,%R9

  (384) 0x423478 SETBB	-0x29(%RBP)

  (384) 0x42347c CMP	%R8,%R15

  (384) 0x42347f SETB	%R15B

  (384) 0x423483 MOV	%RDI,-0x50(%RBP)

  (384) 0x423487 CMP	%RDI,%RBX

  (384) 0x42348a SETB	%DIL

  (384) 0x42348e CMP	%R8,%R9

  (384) 0x423491 SETB	%R9B

  (384) 0x423495 MOV	%R13,-0x58(%RBP)

  (384) 0x423499 CMP	%R13,%RBX

  (384) 0x42349c SETB	%SIL

  (384) 0x4234a0 MOVZX	-0x2d(%RBP),%EBX

  (384) 0x4234a4 TEST	%BL,-0x2e(%RBP)

  (384) 0x4234a7 JNE	423570

  (384) 0x4234ad OR	-0x2c(%RBP),%R12B

  (384) 0x4234b1 JE	423570

  (384) 0x4234b7 OR	-0x2b(%RBP),%CL

  (384) 0x4234ba JE	423570

  (384) 0x4234c0 OR	-0x2a(%RBP),%R10B

  (384) 0x4234c4 JE	423570

  (384) 0x4234ca OR	-0x29(%RBP),%R11B

  (384) 0x4234ce JE	423570

  (384) 0x4234d4 OR	%DIL,%R15B

  (384) 0x4234d7 JE	423570

  (384) 0x4234dd OR	%SIL,%R9B

  (384) 0x4234e0 JE	423570

  (384) 0x4234e6 MOV	-0x78(%RBP),%RSI

  (384) 0x4234ea MOV	%RSI,%RDI

  (384) 0x4234ed MOV	$0x7ffffffffffffffc,%R15

  (384) 0x4234f7 AND	%R15,%RDI

  (384) 0x4234fa JE	4235de

  (384) 0x423500 XOR	%ECX,%ECX

  (384) 0x423502 MOV	-0x40(%RBP),%R12

  (384) 0x423506 VBROADCASTSD	0xd9b81(%RIP),%YMM1

  (384) 0x42350f MOV	-0x80(%RBP),%R10

  (384) 0x423513 MOV	-0x68(%RBP),%R13

  (384) 0x423517 MOV	-0x60(%RBP),%R9

  (384) 0x42351b MOV	-0x58(%RBP),%RBX

  (384) 0x42351f MOV	-0x50(%RBP),%R11

  (384) 0x423523 NOPW	%CS:(%RAX,%RAX,1)

    (392) 0x423530 VMOVUPD	(%RDX,%RCX,8),%YMM0

    (392) 0x423535 VADDPD	(%R9,%RCX,8),%YMM0,%YMM0

    (392) 0x42353b VMOVUPD	%YMM0,(%RDX,%RCX,8)

    (392) 0x423540 VMOVUPD	(%R11,%RCX,8),%YMM0

    (392) 0x423546 VFMSUB213PD	(%RBX,%RCX,8),%YMM1,%YMM0

    (392) 0x42354c VADDPD	(%R8,%RCX,8),%YMM0,%YMM0

    (392) 0x423552 VMOVUPD	%YMM0,(%R8,%RCX,8)

    (392) 0x423558 ADD	$0x4,%RCX

    (392) 0x42355c CMP	%RDI,%RCX

    (392) 0x42355f JB	423530

  (384) 0x423561 CMP	%RDI,%RSI

  (384) 0x423564 JE	4235d0

  (384) 0x423566 JMP	4235f8

0x42356b NOPL	(%RAX,%RAX,1)

  (384) 0x423570 XOR	%ECX,%ECX

  (384) 0x423572 MOV	-0x40(%RBP),%R12

  (384) 0x423576 MOV	$0x7ffffffffffffffc,%R15

  (384) 0x423580 VMOVSD	0xd9b08(%RIP),%XMM1

  (384) 0x423588 MOV	-0x80(%RBP),%R10

  (384) 0x42358c MOV	-0x68(%RBP),%R13

  (384) 0x423590 MOV	-0x78(%RBP),%RSI

  (384) 0x423594 MOV	-0x60(%RBP),%R9

  (384) 0x423598 MOV	-0x58(%RBP),%RBX

  (384) 0x42359c MOV	-0x50(%RBP),%R11

    (385) 0x4235a0 VMOVSD	(%RDX,%RCX,8),%XMM0

    (385) 0x4235a5 VADDSD	(%R9,%RCX,8),%XMM0,%XMM0

    (385) 0x4235ab VMOVSD	%XMM0,(%RDX,%RCX,8)

    (385) 0x4235b0 VMOVSD	(%R11,%RCX,8),%XMM0

    (385) 0x4235b6 VFMSUB213SD	(%RBX,%RCX,8),%XMM1,%XMM0

    (385) 0x4235bc VADDSD	(%R8,%RCX,8),%XMM0,%XMM0

    (385) 0x4235c2 VMOVSD	%XMM0,(%R8,%RCX,8)

    (385) 0x4235c8 INC	%RCX

    (385) 0x4235cb CMP	%RCX,%RSI

    (385) 0x4235ce JNE	4235a0

  (384) 0x4235d0 TEST	%RSI,%RSI

  (384) 0x4235d3 JG	42365b

  (384) 0x4235d9 JMP	422f50

  (384) 0x4235de XOR	%EDI,%EDI

  (384) 0x4235e0 MOV	-0x40(%RBP),%R12

  (384) 0x4235e4 MOV	-0x80(%RBP),%R10

  (384) 0x4235e8 MOV	-0x68(%RBP),%R13

  (384) 0x4235ec MOV	-0x60(%RBP),%R9

  (384) 0x4235f0 MOV	-0x58(%RBP),%RBX

  (384) 0x4235f4 MOV	-0x50(%RBP),%R11

  (384) 0x4235f8 MOV	%RSI,%RCX

  (384) 0x4235fb SUB	%RDI,%RCX

  (384) 0x4235fe VPBROADCASTQ	%RCX,%YMM0

  (384) 0x423604 VPCMPNLEUQ	0xdadd1(%RIP),%YMM0,%K1

  (384) 0x42360f VMOVUPD	(%RDX,%RDI,8),%YMM0{%K1}{z}

  (384) 0x423616 VMOVUPD	(%R9,%RDI,8),%YMM1{%K1}{z}

  (384) 0x42361d VADDPD	%YMM1,%YMM0,%YMM0

  (384) 0x423621 VMOVUPD	%YMM0,(%RDX,%RDI,8){%K1}

  (384) 0x423628 VMOVUPD	(%R11,%RDI,8),%YMM0{%K1}{z}

  (384) 0x42362f VMOVUPD	(%RBX,%RDI,8),%YMM1{%K1}{z}

  (384) 0x423636 VFMSUB231PD	0xd9a50(%RIP){1to4},%YMM0,%YMM1

  (384) 0x423640 VMOVUPD	(%R8,%RDI,8),%YMM0{%K1}{z}

  (384) 0x423647 VADDPD	%YMM1,%YMM0,%YMM0

  (384) 0x42364b VMOVUPD	%YMM0,(%R8,%RDI,8){%K1}

  (384) 0x423652 TEST	%RSI,%RSI

  (384) 0x423655 JLE	422f50

  (384) 0x42365b MOV	%RSI,%RDX

  (384) 0x42365e AND	%R15,%RDX

  (384) 0x423661 JE	423692

  (384) 0x423663 XOR	%ECX,%ECX

  (384) 0x423665 NOPW	%CS:(%RAX,%RAX,1)

    (391) 0x423670 VMOVUPD	(%RAX,%RCX,8),%YMM0

    (391) 0x423675 VMOVUPD	(%R11,%RCX,8),%YMM1

    (391) 0x42367b VFNMADD213PD	(%R14,%RCX,8),%YMM0,%YMM1

    (391) 0x423681 VMOVUPD	%YMM1,(%R14,%RCX,8)

    (391) 0x423687 ADD	$0x4,%RCX

    (391) 0x42368b CMP	%RDX,%RCX

    (391) 0x42368e JB	423670

  (384) 0x423690 JMP	4236ba

  (384) 0x423692 XOR	%EDX,%EDX

  (384) 0x423694 NOPW	%CS:(%RAX,%RAX,1)

    (386) 0x4236a0 VMOVSD	(%RAX,%RDX,8),%XMM0

    (386) 0x4236a5 VMOVSD	(%R11,%RDX,8),%XMM1

    (386) 0x4236ab VFNMADD213SD	(%R14,%RDX,8),%XMM0,%XMM1

    (386) 0x4236b1 VMOVSD	%XMM1,(%R14,%RDX,8)

    (386) 0x4236b7 INC	%RDX

    (386) 0x4236ba CMP	%RDX,%RSI

    (386) 0x4236bd JNE	4236a0

  (384) 0x4236bf TEST	%RSI,%RSI

  (384) 0x4236c2 JLE	422f50

  (384) 0x4236c8 MOV	%RSI,%RDX

  (384) 0x4236cb AND	%R15,%RDX

  (384) 0x4236ce JE	423718

  (384) 0x4236d0 MOV	-0x70(%RBP),%RCX

  (384) 0x4236d4 LEA	(%R14,%RCX,8),%RCX

  (384) 0x4236d8 MOV	-0x48(%RBP),%RDI

  (384) 0x4236dc LEA	(%RAX,%RDI,8),%RDI

  (384) 0x4236e0 XOR	%R8D,%R8D

  (384) 0x4236e3 NOPW	%CS:(%RAX,%RAX,1)

    (390) 0x4236f0 VMOVUPD	(%RDI,%R8,8),%YMM0

    (390) 0x4236f6 VMOVUPD	(%R11,%R8,8),%YMM1

    (390) 0x4236fc VFNMADD213PD	(%RCX,%R8,8),%YMM0,%YMM1

    (390) 0x423702 VMOVUPD	%YMM1,(%RCX,%R8,8)

    (390) 0x423708 ADD	$0x4,%R8

    (390) 0x42370c CMP	%RDX,%R8

    (390) 0x42370f JB	4236f0

  (384) 0x423711 CMP	%RDX,%RSI

  (384) 0x423714 JNE	42371a

  (384) 0x423716 JMP	42374e

  (384) 0x423718 XOR	%EDX,%EDX

  (384) 0x42371a MOV	-0x70(%RBP),%RCX

  (384) 0x42371e LEA	(%R14,%RCX,8),%RCX

  (384) 0x423722 MOV	-0x48(%RBP),%RDI

  (384) 0x423726 LEA	(%RAX,%RDI,8),%RDI

  (384) 0x42372a NOPW	(%RAX,%RAX,1)

    (387) 0x423730 VMOVSD	(%RDI,%RDX,8),%XMM0

    (387) 0x423735 VMOVSD	(%R11,%RDX,8),%XMM1

    (387) 0x42373b VFNMADD213SD	(%RCX,%RDX,8),%XMM0,%XMM1

    (387) 0x423741 VMOVSD	%XMM1,(%RCX,%RDX,8)

    (387) 0x423746 INC	%RDX

    (387) 0x423749 CMP	%RDX,%RSI

    (387) 0x42374c JNE	423730

  (384) 0x42374e TEST	%RSI,%RSI

  (384) 0x423751 JLE	422f50

  (384) 0x423757 MOV	%RSI,%RDX

  (384) 0x42375a AND	%R15,%RDX

  (384) 0x42375d JE	4237ac

  (384) 0x42375f MOV	-0x70(%RBP),%RCX

  (384) 0x423763 SAL	$0x4,%RCX

  (384) 0x423767 ADD	%R14,%RCX

  (384) 0x42376a MOV	-0x48(%RBP),%RDI

  (384) 0x42376e SAL	$0x4,%RDI

  (384) 0x423772 ADD	%RAX,%RDI

  (384) 0x423775 XOR	%R8D,%R8D

  (384) 0x423778 NOPL	(%RAX,%RAX,1)

    (389) 0x423780 VMOVUPD	(%RDI,%R8,8),%YMM0

    (389) 0x423786 VMOVUPD	(%R11,%R8,8),%YMM1

    (389) 0x42378c VFNMADD213PD	(%RCX,%R8,8),%YMM0,%YMM1

    (389) 0x423792 VMOVUPD	%YMM1,(%RCX,%R8,8)

    (389) 0x423798 ADD	$0x4,%R8

    (389) 0x42379c CMP	%RDX,%R8

    (389) 0x42379f JB	423780

  (384) 0x4237a1 CMP	%RDX,%RSI

  (384) 0x4237a4 JE	422f50

  (384) 0x4237aa JMP	4237ae

  (384) 0x4237ac XOR	%EDX,%EDX

  (384) 0x4237ae MOV	-0x70(%RBP),%RCX

  (384) 0x4237b2 SAL	$0x4,%RCX

  (384) 0x4237b6 ADD	%RCX,%R14

  (384) 0x4237b9 MOV	-0x48(%RBP),%RCX

  (384) 0x4237bd SAL	$0x4,%RCX

  (384) 0x4237c1 ADD	%RCX,%RAX

  (384) 0x4237c4 NOPW	%CS:(%RAX,%RAX,1)

    (388) 0x4237d0 VMOVSD	(%RAX,%RDX,8),%XMM0

    (388) 0x4237d5 VMOVSD	(%R11,%RDX,8),%XMM1

    (388) 0x4237db VFNMADD213SD	(%R14,%RDX,8),%XMM0,%XMM1

    (388) 0x4237e1 VMOVSD	%XMM1,(%R14,%RDX,8)

    (388) 0x4237e7 INC	%RDX

    (388) 0x4237ea CMP	%RDX,%RSI

    (388) 0x4237ed JNE	4237d0

  (384) 0x4237ef JMP	422f50

0x4237f4 MOVQ	$0,0x10(%R12)

0x4237fd MOV	0x90(%R12),%R10

0x423805 TEST	%R10,%R10

0x423808 JE	42385a

0x42380a MOV	0xd8(%R12),%R9

0x423812 MOV	0x100(%R12),%RDX

0x42381a MOVSXD	0xf0(%R12),%RDI

0x423822 MOV	-0xa0(%RBP),%RAX

0x423829 MOV	0x18(%RAX),%RSI

0x42382d MOV	0x128(%R12),%RAX

0x423835 MOV	-0xa8(%RBP),%RCX

0x42383c MOV	0x18(%RCX),%RCX

0x423840 LEA	(%RDI,%RDI,1),%R8

0x423844 CMP	$0x1,%R10

0x423848 JNE	423867

0x42384a VXORPD	%XMM0,%XMM0,%XMM0

0x42384e XOR	%R11D,%R11D

0x423851 MOV	-0x40(%RBP),%R13

0x423855 JMP	42394a

0x42385a VMOVSD	0xd97e6(%RIP),%XMM0

0x423862 JMP	4239b6

0x423867 MOV	%R10,%RBX

0x42386a AND	$-0x2,%RBX

0x42386e LEA	0x8(%RDX,%RDI,8),%R14

0x423873 LEA	0x8(%RDX,%R8,8),%R15

0x423878 LEA	0x28(%RSI),%R12

0x42387c VXORPD	%XMM0,%XMM0,%XMM0

0x423880 XOR	%R11D,%R11D

0x423883 MOV	-0x40(%RBP),%R13

0x423887 NOPW	(%RAX,%RAX,1)

(382) 0x423890 VADDSD	(%R9,%R11,8),%XMM0,%XMM0

(382) 0x423896 VMOVSD	%XMM0,0x10(%R13)

(382) 0x42389c VMOVSD	(%RDX,%R11,8),%XMM0

(382) 0x4238a2 VMOVHPD	-0x8(%R14,%R11,8),%XMM0,%XMM0

(382) 0x4238a9 VADDPD	-0x28(%R12),%XMM0,%XMM0

(382) 0x4238b0 VMOVSD	-0x18(%R12),%XMM1

(382) 0x4238b7 VADDSD	-0x8(%R15,%R11,8),%XMM1,%XMM1

(382) 0x4238be VMOVUPD	%XMM0,-0x28(%R12)

(382) 0x4238c5 VMOVSD	%XMM1,-0x18(%R12)

(382) 0x4238cc VMOVSD	(%RCX,%R11,8),%XMM0

(382) 0x4238d2 VADDSD	(%RAX,%R11,8),%XMM0,%XMM0

(382) 0x4238d8 VMOVSD	%XMM0,(%RCX,%R11,8)

(382) 0x4238de VMOVSD	0x8(%R9,%R11,8),%XMM0

(382) 0x4238e5 VADDSD	0x10(%R13),%XMM0,%XMM0

(382) 0x4238eb VMOVSD	%XMM0,0x10(%R13)

(382) 0x4238f1 VMOVSD	0x8(%RDX,%R11,8),%XMM0

(382) 0x4238f8 VMOVHPD	(%R14,%R11,8),%XMM0,%XMM0

(382) 0x4238fe VADDPD	-0x10(%R12),%XMM0,%XMM0

(382) 0x423905 VMOVSD	(%R12),%XMM1

(382) 0x42390b VADDSD	(%R15,%R11,8),%XMM1,%XMM1

(382) 0x423911 VMOVUPD	%XMM0,-0x10(%R12)

(382) 0x423918 VMOVSD	%XMM1,(%R12)

(382) 0x42391e VMOVSD	0x8(%RCX,%R11,8),%XMM0

(382) 0x423925 VADDSD	0x8(%RAX,%R11,8),%XMM0,%XMM0

(382) 0x42392c VMOVSD	%XMM0,0x8(%RCX,%R11,8)

(382) 0x423933 VMOVSD	0x10(%R13),%XMM0

(382) 0x423939 ADD	$0x2,%R11

(382) 0x42393d ADD	$0x30,%R12

(382) 0x423941 CMP	%R11,%RBX

(382) 0x423944 JNE	423890

0x42394a TEST	$0x1,%R10B

0x42394e MOV	%R13,%R12

0x423951 JE	4239ae

0x423953 VADDSD	(%R9,%R11,8),%XMM0,%XMM0

0x423959 VMOVSD	%XMM0,0x10(%R12)

0x423960 ADD	%R11,%RDI

0x423963 ADD	%R11,%R8

0x423966 LEA	(%R11,%R11,2),%R9

0x42396a VMOVSD	(%RDX,%R11,8),%XMM0

0x423970 VMOVHPD	(%RDX,%RDI,8),%XMM0,%XMM0

0x423975 VADDPD	(%RSI,%R9,8),%XMM0,%XMM0

0x42397b VMOVSD	0x10(%RSI,%R9,8),%XMM1

0x423982 VADDSD	(%RDX,%R8,8),%XMM1,%XMM1

0x423988 VMOVUPD	%XMM0,(%RSI,%R9,8)

0x42398e VMOVSD	%XMM1,0x10(%RSI,%R9,8)

0x423995 VMOVSD	(%RCX,%R11,8),%XMM0

0x42399b VADDSD	(%RAX,%R11,8),%XMM0,%XMM0

0x4239a1 VMOVSD	%XMM0,(%RCX,%R11,8)

0x4239a7 VMOVSD	0x10(%R12),%XMM0

0x4239ae VMULSD	0xd9682(%RIP),%XMM0,%XMM0

0x4239b6 VMOVSD	%XMM0,0x10(%R12)

0x4239bd ADD	$0x88,%RSP

0x4239c4 POP	%RBX

0x4239c5 POP	%R12

0x4239c7 POP	%R13

0x4239c9 POP	%R14

0x4239cb POP	%R15

0x4239cd POP	%RBP

0x4239ce VZEROUPPER

0x4239d1 RET

0x4239d2 NOPW	%CS:(%RAX,%RAX,1)

0x4239dc NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►99.72+	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 orig_0

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: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:268-274,360-367,375-391,397-398,419-432
/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 17.83 to 5.67 cycles (3.15x 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). By fully vectorizing your function, you can lower the cost of an iteration from 17.83 to 1.54 cycles (11.59x speedup).

Details

13% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

6% 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.
30% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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_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 200 bytes (25 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	100
nb uops	102
loop length	478
used x86 registers	16
used mmx registers	0
used xmm registers	3
used ymm registers	0
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	17.83 cycles
front end	17.83 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	5.10	5.10	10.67	10.67	9.50	4.90	4.90	9.50	9.50	9.50	5.00	10.67
cycles	5.10	5.10	10.67	10.67	9.50	4.90	4.90	9.50	9.50	9.50	5.00	10.67

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	17.83
Dispatch	10.67
Overall L1	17.83

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	21%
load	8%
store	20%
mul	0%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	13%
load	6%
store	8%
mul	0%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	30%

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	15%
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	25%

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	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 17.83 cycles. At this rate:

5% of peak load performance is reached (11.21 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (5.83 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 17.83 to 10.67 cycles (1.67x speedup).

ASM code

In the binary file, the address of the function is: 422e60

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 $0x88,%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,-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 %RDX,-0xa0(%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,-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%)
JE 4237f4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x994>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%R13	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 %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 460b50 <_ZNK11qmcplusplus11ParticleSet14getDistTableAAEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,-0x98(%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 0xa0(%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 4237f4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x994>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x7ffffffffffffffc,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	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 0xdb3e7(%RIP),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R10,-0x38(%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 %R13,-0x68(%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 422efb <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x9b>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPL (%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
NOP	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
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XCHG %AX,%AX	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
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 42385a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x9fa>	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 -0xa0(%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 -0xa8(%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 423867 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa07>	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 -0x40(%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 42394a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xaea>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VMOVSD 0xd97e6(%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 4239b6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xb56>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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 -0x40(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
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 4239ae <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xb4e>	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 0xd9682(%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 $0x88,%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
NOPL (%RAX)	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 orig_0

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: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:268-274,360-367,375-391,397-398,419-432
/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 17.83 to 5.67 cycles (3.15x speedup).

Workaround

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

Vectorization

Details

13% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

6% 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.
30% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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

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 200 bytes (25 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	100
nb uops	102
loop length	478
used x86 registers	16
used mmx registers	0
used xmm registers	3
used ymm registers	0
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	17.83 cycles
front end	17.83 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	5.10	5.10	10.67	10.67	9.50	4.90	4.90	9.50	9.50	9.50	5.00	10.67
cycles	5.10	5.10	10.67	10.67	9.50	4.90	4.90	9.50	9.50	9.50	5.00	10.67

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	17.83
Dispatch	10.67
Overall L1	17.83

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	21%
load	8%
store	20%
mul	0%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	13%
load	6%
store	8%
mul	0%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	30%

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	15%
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	25%

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	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 17.83 cycles. At this rate:

5% of peak load performance is reached (11.21 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (5.83 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: 422e60

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 $0x88,%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,-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 %RDX,-0xa0(%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,-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%)
JE 4237f4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x994>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%R13	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 %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 460b50 <_ZNK11qmcplusplus11ParticleSet14getDistTableAAEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,-0x98(%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 0xa0(%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 4237f4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x994>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x7ffffffffffffffc,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	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 0xdb3e7(%RIP),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R10,-0x38(%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 %R13,-0x68(%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 422efb <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x9b>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPL (%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
NOP	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
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XCHG %AX,%AX	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
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 42385a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x9fa>	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 -0xa0(%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 -0xa8(%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 423867 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa07>	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 -0x40(%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 42394a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xaea>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VMOVSD 0xd97e6(%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 4239b6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xb56>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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 -0x40(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
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 4239ae <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xb4e>	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 0xd9682(%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 $0x88,%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
NOPL (%RAX)	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...–	0.09	0.08
○Loop 382 - TwoBodyJastrowRef.h:423-427 - exec	0.00	0.00
▼Loop 383 - TwoBodyJastrowRef.h:268-420 - exec–	0.00	0.00
▼Loop 384 - TwoBodyJastrowRef.h:268-420 - exec–	0.00	0.01
○Loop 398 - TwoBodyJastrowRef.h:381-382 - exec	0.02	0.02
○Loop 396 - TwoBodyJastrowRef.h:381-382 - exec	0.02	0.02
○Loop 394 - TwoBodyJastrowRef.h:381-382 - exec	0.02	0.01
○Loop 400 - TwoBodyJastrowRef.h:375-376 - exec	0.01	0.01
○Loop 392 - TwoBodyJastrowRef.h:388-391 - exec	0.01	0.01
○Loop 389 - TwoBodyJastrowRef.h:397-398 - exec	0.01	0.01
○Loop 391 - TwoBodyJastrowRef.h:397-398 - exec	0.01	0.01
○Loop 390 - TwoBodyJastrowRef.h:397-398 - exec	0.00	0.01
○Loop 402 - stl_numeric.h:140-141 - exec	0.00	0.01
○Loop 403 - TwoBodyJastrowRef.h:269-274 - exec	0.00	0.00
○Loop 397 - TwoBodyJastrowRef.h:381-382 - exec	0.00	0.00
○Loop 395 - TwoBodyJastrowRef.h:381-382 - exec	0.00	0.00
○Loop 393 - TwoBodyJastrowRef.h:381-382 - exec	0.00	0.00
○Loop 387 - TwoBodyJastrowRef.h:397-398 - exec	0.00	0.00
○Loop 401 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 386 - TwoBodyJastrowRef.h:397-398 - exec	0.00	0.01
○Loop 388 - TwoBodyJastrowRef.h:397-398 - exec	0.00	0.00
○Loop 385 - TwoBodyJastrowRef.h:388-391 - exec	0.00	0.00
○Loop 399 - TwoBodyJastrowRef.h:375-376 - 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