OV - exec - Function qmcplusplus::NonLocalPP<double>::evaluate(qmcplusplus::ParticleSet const&, qmcplusplus::WaveFunction&)

	Function: qmcplusplus::NonLocalPP<double>::evaluate(qmcplusplus::ParticleSet const&, qmcplusplus::Wa ...	Module: exec	Source: NonLocalPP.hpp:104-139 [...]	Coverage (incl. loops): 0.09% \| (excl. loops): 0.00%

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_construct.h: 119 - 119

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

119:       ::new((void*)__p) _Tp(std::forward<_Args>(__args)...);

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/StdRandom.h: 97 - 97

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

97:   inline result_type operator()() { return uniform(myRNG); }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h: 111 - 147

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

111: 	if (__builtin_expect(__n > this->_M_max_size(), false))

112: 	  {

113: 	    // _GLIBCXX_RESOLVE_LIB_DEFECTS

114: 	    // 3190. allocator::allocate sometimes returns too little storage

115: 	    if (__n > (std::size_t(-1) / sizeof(_Tp)))

116: 	      std::__throw_bad_array_new_length();

[...]

127: 	return static_cast<_Tp*>(::operator new(__n * sizeof(_Tp)));

[...]

145: 	::operator delete(__p

146: #if __cpp_sized_deallocation

147: 			  , __t * sizeof(_Tp)

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 43 - 63

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

43:     return (a + b);

[...]

63:     return (a * b);

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 231 - 231

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

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

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h: 77 - 79

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

77:     return TinyVector<Type_t, 3>(lhs[0] * rhs[0] + lhs[1] * rhs[1] + lhs[2] * rhs[2],

78:                                  lhs[3] * rhs[0] + lhs[4] * rhs[1] + lhs[5] * rhs[2],

79:                                  lhs[6] * rhs[0] + lhs[7] * rhs[1] + lhs[8] * rhs[2]);

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.h: 97 - 97

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

97:   int get_ei_TableID() const { return ei_TableID; }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 98 - 1770

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

98: 	: _M_start(), _M_finish(), _M_end_of_storage()

[...]

335: 	_M_deallocate(_M_impl._M_start,

336: 		      _M_impl._M_end_of_storage - _M_impl._M_start);

[...]

346: 	return __n != 0 ? _Tr::allocate(_M_impl, __n) : pointer();

[...]

353: 	if (__p)

[...]

361: 	this->_M_impl._M_start = this->_M_allocate(__n);

362: 	this->_M_impl._M_finish = this->_M_impl._M_start;

363: 	this->_M_impl._M_end_of_storage = this->_M_impl._M_start + __n;

[...]

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

[...]

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

[...]

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

[...]

1605: 	this->_M_impl._M_finish =

[...]

1769: 	if (__n > _S_max_size(_Tp_alloc_type(__a)))

1770: 	  __throw_length_error(

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h: 911 - 1115

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

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

912: 	*__first = __value;

[...]

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

924: 	*__first = __tmp;

[...]

1115:       if (__n <= 0)

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp: 104 - 139

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

104:     RealType phi(TWOPI * (myRNG())), psi(TWOPI * (myRNG())), cth((myRNG()) - 0.5);

105:     RealType sph(std::sin(phi)), cph(std::cos(phi)), sth(std::sqrt(1.0 - cth * cth)), sps(std::sin(psi)),

106:         cps(std::cos(psi));

107:     TensorType rmat(cph * cth * cps - sph * sps, sph * cth * cps + cph * sps, -sth * cps, -cph * cth * sps - sph * cps,

108:                     -sph * cth * sps + cph * cps, sth * sps, cph * sth, sph * sth, cth);

109:     const int n = sgridxyz_m.size();

110:     for (int i = 0; i < n; ++i)

111:       rrotsgrid[i] = dot(rmat, sgridxyz_m[i]);

112:   }

113:

114:   void evaluate(const ParticleSet& els, WaveFunction& wf)

115:   {

116:     ParticlePos rOnSphere(size());

117:     std::vector<QMCTraits::PosType> virtualPos(size());

118:     std::vector<QMCTraits::ValueType> ratios(size());

119:     randomize(rOnSphere); // pick random sphere

120:     const auto& d_ie = els.getDistTableAB(wf.get_ei_TableID());

121:

122:     for (int jel = 0; jel < els.getTotalNum(); ++jel)

123:     {

124:       const auto& dist  = d_ie.getDistRow(jel);

125:       const auto& displ = d_ie.getDisplRow(jel);

126:       for (int iat = 0; iat < ions_ref.getTotalNum(); ++iat)

127:       {

128:         //due to < Rmax condition, the actually iteration iat is [0,2] in a real simulation

129:         if (dist[iat] < Rmax)

130:         {

131:           for (int k = 0; k < size(); k++)

132:             virtualPos[k] = dist[iat] * rOnSphere[k] + displ[iat] + els.R[jel];

133:           auto& VP = *VPs[ions_ref.GroupID[iat]];

134:           VP.makeMoves(els, jel, virtualPos, true, iat);

135:           wf.evaluateRatios(VP, ratios);

136:         }

137:       }

138:     }

139:   }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_uninitialized.h: 578 - 602

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

578: 	      for (; __n > 0; --__n, (void) ++__cur)

[...]

602: 	      ++__first;

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 61 - 170

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

61:     for (size_t d = 0; d < D; ++d)

62:       X[d] = T(0);

[...]

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

[...]

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

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/unique_ptr.h: 173 - 173

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

173:       pointer    _M_ptr() const { return std::get<0>(_M_t); }

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 48 - 229

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

48:     if (n)

[...]

210:     if (nAllocated)

[...]

229:     return X[i];

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 277 - 277

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

277:   inline size_t getTotalNum() const { return TotalNum; }

0x40e430 PUSH	%RBP

0x40e431 MOV	%RSP,%RBP

0x40e434 PUSH	%R15

0x40e436 PUSH	%R14

0x40e438 PUSH	%R13

0x40e43a PUSH	%R12

0x40e43c PUSH	%RBX

0x40e43d SUB	$0x98,%RSP

0x40e444 MOV	%RDX,-0xa8(%RBP)

0x40e44b MOV	%RSI,-0xa0(%RBP)

0x40e452 MOV	%RDI,%R12

0x40e455 MOV	0x13f0(%RDI),%RAX

0x40e45c SUB	0x13e8(%RDI),%RAX

0x40e463 MOV	$0x555555555555555,%RBX

0x40e46d SAR	$0x3,%RAX

0x40e471 MOV	$-0x5555555555555555,%RCX

0x40e47b IMUL	%RCX,%RAX

0x40e47f MOVSXD	%EAX,%R15

0x40e482 SAL	$0x20,%RAX

0x40e486 MOV	%RAX,-0x98(%RBP)

0x40e48d MOV	%R15,-0x48(%RBP)

0x40e491 JE	40e587

0x40e497 CMP	%RBX,%R15

0x40e49a JA	40edaa

0x40e4a0 LEA	(,%R15,8),%RAX

0x40e4a8 LEA	(%RAX,%RAX,2),%R14

0x40e4ac MOV	%R14,%RDI

0x40e4af CALL	404450 <_Znwm@plt>

0x40e4b4 MOV	%RAX,-0x30(%RBP)

0x40e4b8 CMP	$0x8,%R15

0x40e4bc JB	40e50c

0x40e4be MOV	-0x48(%RBP),%RAX

0x40e4c2 SHR	$0x3,%RAX

0x40e4c6 MOV	-0x30(%RBP),%RCX

0x40e4ca ADD	$0xa0,%RCX

0x40e4d1 VXORPD	%XMM0,%XMM0,%XMM0

0x40e4d5 NOPW	%CS:(%RAX,%RAX,1)

(96) 0x40e4e0 VMOVUPD	%YMM0,-0xa0(%RCX)

(96) 0x40e4e8 VMOVUPD	%YMM0,-0x80(%RCX)

(96) 0x40e4ed VMOVUPD	%YMM0,-0x60(%RCX)

(96) 0x40e4f2 VMOVUPD	%YMM0,-0x40(%RCX)

(96) 0x40e4f7 VMOVUPD	%YMM0,-0x20(%RCX)

(96) 0x40e4fc VMOVUPD	%YMM0,(%RCX)

(96) 0x40e500 ADD	$0xc0,%RCX

(96) 0x40e507 DEC	%RAX

(96) 0x40e50a JNE	40e4e0

0x40e50c MOV	$0x7fffffffffffff8,%RCX

0x40e516 MOV	-0x48(%RBP),%RSI

0x40e51a AND	%RSI,%RCX

0x40e51d CMP	%RSI,%RCX

0x40e520 JE	40e58f

0x40e522 ADD	$-0x18,%R14

0x40e526 MOV	%R14,%RDX

0x40e529 MOV	$-0x5555555555555555,%RAX

0x40e533 MULX	%RAX,%RAX,%RAX

0x40e538 SHR	$0x4,%RAX

0x40e53c SUB	%RCX,%RAX

0x40e53f INC	%RAX

0x40e542 MOV	$0x3b,%ECX

0x40e547 BZHI	%RCX,%RSI,%RCX

0x40e54c SHR	$0x3,%RCX

0x40e550 LEA	(%RCX,%RCX,2),%RCX

0x40e554 SAL	$0x6,%RCX

0x40e558 MOV	-0x30(%RBP),%RDX

0x40e55c LEA	0x10(%RCX,%RDX,1),%RCX

0x40e561 VXORPD	%XMM0,%XMM0,%XMM0

0x40e565 NOPW	%CS:(%RAX,%RAX,1)

(95) 0x40e570 VMOVUPD	%XMM0,-0x10(%RCX)

(95) 0x40e575 MOVQ	$0,(%RCX)

(95) 0x40e57c ADD	$0x18,%RCX

(95) 0x40e580 DEC	%RAX

(95) 0x40e583 JNE	40e570

0x40e585 JMP	40e58f

0x40e587 MOVQ	$0,-0x30(%RBP)

0x40e58f MOV	0x13f0(%R12),%R13

0x40e597 MOV	%R12,-0x40(%RBP)

0x40e59b SUB	0x13e8(%R12),%R13

0x40e5a3 SAR	$0x3,%R13

0x40e5a7 MOV	$-0x5555555555555555,%R12

0x40e5b1 IMUL	%R12,%R13

0x40e5b5 MOVSXD	%R13D,%R15

0x40e5b8 CMP	%RBX,%R15

0x40e5bb JA	40edaf

0x40e5c1 MOV	%R13,%RAX

0x40e5c4 SAL	$0x20,%RAX

0x40e5c8 VXORPD	%XMM0,%XMM0,%XMM0

0x40e5cc VMOVUPD	%XMM0,-0x60(%RBP)

0x40e5d1 MOVQ	$0,-0x50(%RBP)

0x40e5d9 JE	40e613

0x40e5db LEA	(,%R15,8),%RAX

0x40e5e3 LEA	(%RAX,%RAX,2),%R14

0x40e5e7 MOV	%R14,%RDI

0x40e5ea VZEROUPPER

0x40e5ed CALL	404450 <_Znwm@plt>

0x40e5f2 MOV	%RAX,-0x60(%RBP)

0x40e5f6 LEA	(%R15,%R15,2),%RCX

0x40e5fa LEA	(%RAX,%RCX,8),%RCX

0x40e5fe MOV	%RCX,-0x50(%RBP)

0x40e602 AND	$0x7,%R13D

0x40e606 CMP	$0x8,%R15

0x40e60a JAE	40e626

0x40e60c XOR	%ECX,%ECX

0x40e60e JMP	40e6ca

0x40e613 SAL	$0x3,%R15

0x40e617 LEA	(%R15,%R15,2),%RAX

0x40e61b MOV	%RAX,-0x50(%RBP)

0x40e61f XOR	%EAX,%EAX

0x40e621 JMP	40e724

0x40e626 SUB	%R13,%R15

0x40e629 LEA	0xb8(%RAX),%RDX

0x40e630 XOR	%ECX,%ECX

0x40e632 VXORPD	%XMM0,%XMM0,%XMM0

0x40e636 NOPW	%CS:(%RAX,%RAX,1)

(93) 0x40e640 VMOVUPD	%XMM0,-0xb8(%RDX)

(93) 0x40e648 MOVQ	$0,-0xa8(%RDX)

(93) 0x40e653 VMOVUPD	%XMM0,-0xa0(%RDX)

(93) 0x40e65b MOVQ	$0,-0x90(%RDX)

(93) 0x40e666 VMOVUPD	%XMM0,-0x88(%RDX)

(93) 0x40e66e MOVQ	$0,-0x78(%RDX)

(93) 0x40e676 VMOVUPD	%XMM0,-0x70(%RDX)

(93) 0x40e67b MOVQ	$0,-0x60(%RDX)

(93) 0x40e683 VMOVUPD	%XMM0,-0x58(%RDX)

(93) 0x40e688 MOVQ	$0,-0x48(%RDX)

(93) 0x40e690 VMOVUPD	%XMM0,-0x40(%RDX)

(93) 0x40e695 MOVQ	$0,-0x30(%RDX)

(93) 0x40e69d VMOVUPD	%XMM0,-0x28(%RDX)

(93) 0x40e6a2 MOVQ	$0,-0x18(%RDX)

(93) 0x40e6aa VMOVUPD	%XMM0,-0x10(%RDX)

(93) 0x40e6af MOVQ	$0,(%RDX)

(93) 0x40e6b6 ADD	$0x8,%RCX

(93) 0x40e6ba ADD	$0xc0,%RDX

(93) 0x40e6c1 CMP	%RCX,%R15

(93) 0x40e6c4 JNE	40e640

0x40e6ca TEST	%R13,%R13

0x40e6cd JE	40e707

0x40e6cf LEA	(%RCX,%RCX,2),%RCX

0x40e6d3 LEA	0x10(%RAX,%RCX,8),%RCX

0x40e6d8 SAL	$0x3,%R13D

0x40e6dc LEA	(%R13,%R13,2),%RDX

0x40e6e1 XOR	%ESI,%ESI

0x40e6e3 VXORPD	%XMM0,%XMM0,%XMM0

0x40e6e7 NOPW	(%RAX,%RAX,1)

(94) 0x40e6f0 VMOVUPD	%XMM0,-0x10(%RCX,%RSI,1)

(94) 0x40e6f6 MOVQ	$0,(%RCX,%RSI,1)

(94) 0x40e6fe ADD	$0x18,%RSI

(94) 0x40e702 CMP	%RSI,%RDX

(94) 0x40e705 JNE	40e6f0

0x40e707 ADD	%R14,%RAX

0x40e70a MOV	-0x40(%RBP),%RCX

0x40e70e MOV	0x13f0(%RCX),%R13

0x40e715 SUB	0x13e8(%RCX),%R13

0x40e71c SAR	$0x3,%R13

0x40e720 IMUL	%R12,%R13

0x40e724 MOV	%RAX,-0x58(%RBP)

0x40e728 MOVSXD	%R13D,%RBX

0x40e72b MOV	%RBX,%RAX

0x40e72e SHR	$0x3c,%RAX

0x40e732 JNE	40edbc

0x40e738 SAL	$0x20,%R13

0x40e73c VXORPD	%XMM0,%XMM0,%XMM0

0x40e740 VMOVUPD	%XMM0,-0x80(%RBP)

0x40e745 MOVQ	$0,-0x70(%RBP)

0x40e74d JE	40e78c

0x40e74f MOV	%R13,%R14

0x40e752 SAR	$0x1d,%R14

0x40e756 MOV	%R14,%RDI

0x40e759 VZEROUPPER

0x40e75c CALL	404450 <_Znwm@plt>

0x40e761 MOV	%RAX,-0x80(%RBP)

0x40e765 LEA	(%RAX,%RBX,8),%RBX

0x40e769 MOV	%RBX,-0x70(%RBP)

0x40e76d MOVQ	$0,(%RAX)

0x40e774 ADD	$0x8,%RAX

0x40e778 MOV	$0x100000000,%RCX

0x40e782 CMP	%RCX,%R13

0x40e785 JNE	40e798

0x40e787 MOV	%RAX,%RBX

0x40e78a JMP	40e7a9

0x40e78c SAL	$0x3,%RBX

0x40e790 MOV	%RBX,-0x70(%RBP)

0x40e794 XOR	%EBX,%EBX

0x40e796 JMP	40e7a9

0x40e798 ADD	$-0x8,%R14

0x40e79c MOV	%RAX,%RDI

0x40e79f XOR	%ESI,%ESI

0x40e7a1 MOV	%R14,%RDX

0x40e7a4 CALL	4efda0 <_intel_fast_memset>

0x40e7a9 MOV	-0x40(%RBP),%RAX

0x40e7ad MOV	%RBX,-0x78(%RBP)

0x40e7b1 LEA	0x13a0(%RAX),%R14

0x40e7b8 LEA	0x18(%RAX),%R13

0x40e7bc MOV	%R14,%RDI

0x40e7bf MOV	%R13,%RSI

0x40e7c2 VZEROUPPER

0x40e7c5 CALL	40f8d0 <_ZNSt25uniform_real_distributionIdEclISt23mersenne_twister_engineImLm32ELm624ELm397ELm31ELm2567483615ELm11ELm4294967295ELm7ELm2636928640ELm15ELm4022730752ELm18ELm1812433253EEEEdRT_>

0x40e7ca VMOVSD	%XMM0,-0x38(%RBP)

0x40e7cf MOV	%R14,%RDI

0x40e7d2 MOV	%R13,%RSI

0x40e7d5 CALL	40f8d0 <_ZNSt25uniform_real_distributionIdEclISt23mersenne_twister_engineImLm32ELm624ELm397ELm31ELm2567483615ELm11ELm4294967295ELm7ELm2636928640ELm15ELm4022730752ELm18ELm1812433253EEEEdRT_>

0x40e7da VMOVSD	%XMM0,-0x90(%RBP)

0x40e7e2 MOV	%R14,%RDI

0x40e7e5 MOV	%R13,%RSI

0x40e7e8 CALL	40f8d0 <_ZNSt25uniform_real_distributionIdEclISt23mersenne_twister_engineImLm32ELm624ELm397ELm31ELm2567483615ELm11ELm4294967295ELm7ELm2636928640ELm15ELm4022730752ELm18ELm1812433253EEEEdRT_>

0x40e7ed VMOVSD	%XMM0,-0xb0(%RBP)

0x40e7f5 VMOVSD	-0x38(%RBP),%XMM0

0x40e7fa VMULSD	0xee82e(%RIP),%XMM0,%XMM0

0x40e802 VMOVSD	-0x90(%RBP),%XMM1

0x40e80a VMULSD	0xee81e(%RIP),%XMM1,%XMM1

0x40e812 VMOVSD	%XMM1,-0x38(%RBP)

0x40e817 CALL	4df3e0 <__libm_sse2_sincos>

0x40e81c VMOVUPD	%XMM0,-0x90(%RBP)

0x40e824 VMOVUPD	%XMM1,-0xc0(%RBP)

0x40e82c VMOVSD	-0x38(%RBP),%XMM0

0x40e831 CALL	4df3e0 <__libm_sse2_sincos>

0x40e836 VMOVUPD	-0xc0(%RBP),%XMM29

0x40e83d VMOVUPD	-0x90(%RBP),%XMM28

0x40e844 MOV	-0x40(%RBP),%R13

0x40e848 MOV	0x13e8(%R13),%RAX

0x40e84f MOV	0x13f0(%R13),%RDX

0x40e856 SUB	%RAX,%RDX

0x40e859 SAR	$0x3,%RDX

0x40e85d IMUL	%R12,%RDX

0x40e861 TEST	%EDX,%EDX

0x40e863 MOV	-0x30(%RBP),%R8

0x40e867 MOV	-0xa0(%RBP),%RDI

0x40e86e JLE	40eb4c

0x40e874 VMOVSD	-0xb0(%RBP),%XMM2

0x40e87c VADDSD	0xee7b4(%RIP),%XMM2,%XMM2

0x40e884 VMOVSD	0xee7b4(%RIP),%XMM3

0x40e88c VFNMADD231SD	%XMM2,%XMM2,%XMM3

0x40e891 VSQRTSD	%XMM3,%XMM3,%XMM3

0x40e895 VMULSD	%XMM29,%XMM1,%XMM4

0x40e89b VMULSD	%XMM2,%XMM4,%XMM7

0x40e89f VMULSD	%XMM28,%XMM1,%XMM26

0x40e8a5 VMULSD	%XMM29,%XMM0,%XMM25

0x40e8ab VFMADD231SD	%XMM2,%XMM26,%XMM25

0x40e8b1 VMULSD	%XMM0,%XMM2,%XMM8

0x40e8b5 VFNMSUB231SD	%XMM29,%XMM8,%XMM26

0x40e8bb VPUNPCKLQDQ	%XMM8,%XMM0,%XMM8

0x40e8c0 VMOVDDUP	%XMM28,%XMM9

0x40e8c6 VPUNPCKLQDQ	%XMM4,%XMM7,%XMM4

0x40e8ca VFNMADD231PD	%XMM9,%XMM8,%XMM4

0x40e8cf VXORPD	0xee76f(%RIP){1to2},%XMM3,%XMM7

0x40e8d9 VMULSD	%XMM0,%XMM3,%XMM22

0x40e8df VMULSD	%XMM7,%XMM1,%XMM23

0x40e8e5 MOV	%EDX,%ECX

0x40e8e7 AND	$0x7fffffff,%ECX

0x40e8ed LEA	(%RCX,%RCX,2),%RSI

0x40e8f1 LEA	-0x8(%RAX,%RSI,8),%R9

0x40e8f6 CMP	%R8,%R9

0x40e8f9 JB	40e971

0x40e8fb LEA	-0x8(%R8,%RSI,8),%RSI

0x40e900 CMP	%RAX,%RSI

0x40e903 JB	40e971

0x40e905 VPUNPCKLQDQ	%XMM26,%XMM23,%XMM1

0x40e90b VPUNPCKLQDQ	%XMM22,%XMM25,%XMM0

0x40e911 SAL	$0x3,%RCX

0x40e915 LEA	(%RCX,%RCX,2),%RCX

0x40e919 XOR	%EDX,%EDX

0x40e91b NOPL	(%RAX,%RAX,1)

(92) 0x40e920 VMOVSD	0x10(%RAX,%RDX,1),%XMM5

(92) 0x40e926 VMULSD	%XMM2,%XMM5,%XMM6

(92) 0x40e92a VMOVUPD	(%RAX,%RDX,1),%XMM7

(92) 0x40e92f VPUNPCKLQDQ	%XMM7,%XMM5,%XMM5

(92) 0x40e933 VMULPD	%XMM5,%XMM1,%XMM5

(92) 0x40e937 VFMADD231PD	%XMM4,%XMM7,%XMM5

(92) 0x40e93c VFMADD231PD	0x8(%RAX,%RDX,1),%XMM0,%XMM5

(92) 0x40e943 VMULSD	%XMM29,%XMM7,%XMM7

(92) 0x40e949 VFMADD231SD	0x8(%RAX,%RDX,1),%XMM28,%XMM7

(92) 0x40e951 VFMADD213SD	%XMM6,%XMM3,%XMM7

(92) 0x40e956 VMOVUPD	%XMM5,(%R8,%RDX,1)

(92) 0x40e95c VMOVSD	%XMM7,0x10(%R8,%RDX,1)

(92) 0x40e963 ADD	$0x18,%RDX

(92) 0x40e967 CMP	%RDX,%RCX

(92) 0x40e96a JNE	40e920

0x40e96c JMP	40eb4c

0x40e971 AND	$0x7ffffffc,%RDX

0x40e978 JE	40ead1

0x40e97e VBROADCASTSD	%XMM4,%YMM27

0x40e984 VBROADCASTSD	%XMM25,%YMM8

0x40e98a VBROADCASTSD	%XMM23,%YMM9

0x40e990 VBROADCASTSD	%XMM26,%YMM10

0x40e996 VPERMPD	$0x55,%YMM4,%YMM11

0x40e99c VBROADCASTSD	%XMM22,%YMM12

0x40e9a2 VBROADCASTSD	%XMM29,%YMM13

0x40e9a8 VBROADCASTSD	%XMM28,%YMM14

0x40e9ae VBROADCASTSD	%XMM2,%YMM15

0x40e9b3 VBROADCASTSD	%XMM3,%YMM16

0x40e9b9 XOR	%ESI,%ESI

0x40e9bb VMOVUPD	0xeed7b(%RIP),%YMM17

0x40e9c5 VMOVUPD	0xeed91(%RIP),%YMM18

0x40e9cf VBROADCASTF32X4	0xeee27(%RIP),%YMM19

0x40e9d9 VMOVUPD	0xeedbd(%RIP),%YMM20

0x40e9e3 VMOVUPD	0xeedd3(%RIP),%YMM21

0x40e9ed XOR	%R9D,%R9D

0x40e9f0 MOV	-0x30(%RBP),%R8

0x40e9f4 NOPW	%CS:(%RAX,%RAX,1)

(91) 0x40ea00 VMOVUPD	0x20(%RAX,%RSI,1),%YMM0

(91) 0x40ea06 VBLENDPD	$0x3,(%RAX,%RSI,1),%YMM0,%YMM1

(91) 0x40ea0d VMOVUPD	0x10(%RAX,%RSI,1),%XMM24

(91) 0x40ea15 VMOVUPD	0x20(%RAX,%RSI,1),%XMM5

(91) 0x40ea1b VINSERTF32X4	$0x1,0x40(%RAX,%RSI,1),%YMM24,%YMM6

(91) 0x40ea24 VBLENDPD	$0xa,%YMM6,%YMM1,%YMM7

(91) 0x40ea2a VSHUFPD	$0x5,%YMM0,%YMM1,%YMM0

(91) 0x40ea2f VBROADCASTSD	0x50(%RAX,%RSI,1),%YMM1

(91) 0x40ea36 VBLENDPD	$0x8,%YMM1,%YMM0,%YMM0

(91) 0x40ea3c VBLENDPD	$0xc,0x40(%RAX,%RSI,1),%YMM5,%YMM1

(91) 0x40ea44 VBLENDPD	$0xa,%YMM1,%YMM6,%YMM1

(91) 0x40ea4a VMULPD	%YMM1,%YMM9,%YMM5

(91) 0x40ea4e VFMADD231PD	%YMM27,%YMM7,%YMM5

(91) 0x40ea54 VFMADD231PD	%YMM8,%YMM0,%YMM5

(91) 0x40ea59 VMULPD	%YMM7,%YMM10,%YMM6

(91) 0x40ea5d VFMADD231PD	%YMM11,%YMM0,%YMM6

(91) 0x40ea62 VFMADD231PD	%YMM1,%YMM12,%YMM6

(91) 0x40ea67 VMULPD	%YMM7,%YMM13,%YMM7

(91) 0x40ea6b VMULPD	%YMM1,%YMM15,%YMM1

(91) 0x40ea6f VFMADD231PD	%YMM0,%YMM14,%YMM7

(91) 0x40ea74 VFMADD213PD	%YMM1,%YMM16,%YMM7

(91) 0x40ea7a VMOVAPD	%YMM6,%YMM0

(91) 0x40ea7e VPERMT2PD	%YMM5,%YMM17,%YMM0

(91) 0x40ea84 VMOVAPD	%YMM5,%YMM1

(91) 0x40ea88 VPERMT2PD	%YMM6,%YMM18,%YMM1

(91) 0x40ea8e VPERMT2PD	%YMM5,%YMM19,%YMM6

(91) 0x40ea94 VPERMT2PD	%YMM7,%YMM21,%YMM1

(91) 0x40ea9a VBLENDPD	$0x2,%YMM7,%YMM0,%YMM0

(91) 0x40eaa0 VMOVUPD	%YMM0,0x20(%R8,%RSI,1)

(91) 0x40eaa7 VMOVUPD	%YMM1,(%R8,%RSI,1)

(91) 0x40eaad VPERMT2PD	%YMM6,%YMM20,%YMM7

(91) 0x40eab3 VMOVUPD	%YMM7,0x40(%R8,%RSI,1)

(91) 0x40eaba ADD	$0x4,%R9

(91) 0x40eabe ADD	$0x60,%RSI

(91) 0x40eac2 CMP	%RDX,%R9

(91) 0x40eac5 JB	40ea00

0x40eacb CMP	%EDX,%ECX

0x40eacd JNE	40ead7

0x40eacf JMP	40eb4c

0x40ead1 XOR	%EDX,%EDX

0x40ead3 MOV	-0x30(%RBP),%R8

0x40ead7 VPUNPCKLQDQ	%XMM26,%XMM23,%XMM1

0x40eadd VPUNPCKLQDQ	%XMM22,%XMM25,%XMM0

0x40eae3 SUB	%RDX,%RCX

0x40eae6 LEA	(%RDX,%RDX,2),%RDX

0x40eaea LEA	0x10(,%RDX,8),%RDX

0x40eaf2 NOPW	%CS:(%RAX,%RAX,1)

(90) 0x40eb00 VMOVSD	(%RAX,%RDX,1),%XMM5

(90) 0x40eb05 VMULSD	%XMM2,%XMM5,%XMM6

(90) 0x40eb09 VMOVUPD	-0x10(%RAX,%RDX,1),%XMM7

(90) 0x40eb0f VPUNPCKLQDQ	%XMM7,%XMM5,%XMM5

(90) 0x40eb13 VMULPD	%XMM5,%XMM1,%XMM5

(90) 0x40eb17 VFMADD231PD	%XMM4,%XMM7,%XMM5

(90) 0x40eb1c VFMADD231PD	-0x8(%RAX,%RDX,1),%XMM0,%XMM5

(90) 0x40eb23 VMULSD	%XMM29,%XMM7,%XMM7

(90) 0x40eb29 VFMADD231SD	-0x8(%RAX,%RDX,1),%XMM28,%XMM7

(90) 0x40eb31 VFMADD213SD	%XMM6,%XMM3,%XMM7

(90) 0x40eb36 VMOVUPD	%XMM5,-0x10(%R8,%RDX,1)

(90) 0x40eb3d VMOVSD	%XMM7,(%R8,%RDX,1)

(90) 0x40eb43 ADD	$0x18,%RDX

(90) 0x40eb47 DEC	%RCX

(90) 0x40eb4a JNE	40eb00

0x40eb4c MOV	-0xa8(%RBP),%RAX

0x40eb53 MOV	0x38(%RAX),%ESI

0x40eb56 MOV	%RDI,%RBX

0x40eb59 VZEROUPPER

0x40eb5c CALL	460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x40eb61 MOV	%RAX,-0x90(%RBP)

0x40eb68 MOV	0x260(%RBX),%RCX

0x40eb6f TEST	%RCX,%RCX

0x40eb72 JE	40ed4f

0x40eb78 MOV	0x1418(%R13),%RAX

0x40eb7f CMPQ	$0,0x260(%RAX)

0x40eb87 JE	40ed4f

0x40eb8d MOV	%RBX,%RSI

0x40eb90 MOVQ	$0,-0x38(%RBP)

0x40eb98 JMP	40ebbb

0x40eb9a NOPW	(%RAX,%RAX,1)

(87) 0x40eba0 MOV	0x260(%RSI),%RCX

(87) 0x40eba7 MOV	-0x38(%RBP),%RDI

(87) 0x40ebab INC	%RDI

(87) 0x40ebae MOV	%RDI,-0x38(%RBP)

(87) 0x40ebb2 CMP	%RDI,%RCX

(87) 0x40ebb5 JBE	40ed4f

(87) 0x40ebbb CMPQ	$0,0x260(%RAX)

(87) 0x40ebc3 JE	40eba7

(87) 0x40ebc5 MOV	-0x90(%RBP),%RDX

(87) 0x40ebcc MOV	0x48(%RDX),%RCX

(87) 0x40ebd0 MOV	0x60(%RDX),%RDX

(87) 0x40ebd4 MOV	-0x38(%RBP),%R8

(87) 0x40ebd8 LEA	(,%R8,8),%RDI

(87) 0x40ebe0 LEA	(%RDI,%RDI,4),%RDI

(87) 0x40ebe4 LEA	0x18(%RCX,%RDI,1),%R15

(87) 0x40ebe9 LEA	0x18(%RDX,%RDI,1),%RBX

(87) 0x40ebee LEA	(%R8,%R8,2),%R12

(87) 0x40ebf2 XOR	%R14D,%R14D

(87) 0x40ebf5 JMP	40ec0c

0x40ebf7 NOPW	(%RAX,%RAX,1)

  (88) 0x40ec00 INC	%R14

  (88) 0x40ec03 CMP	%R14,0x260(%RAX)

  (88) 0x40ec0a JBE	40eba0

  (88) 0x40ec0c MOV	(%R15),%RCX

  (88) 0x40ec0f VMOVSD	(%R13),%XMM0

  (88) 0x40ec15 VUCOMISD	(%RCX,%R14,8),%XMM0

  (88) 0x40ec1b JBE	40ec00

  (88) 0x40ec1d MOV	0x13f0(%R13),%RCX

  (88) 0x40ec24 SUB	0x13e8(%R13),%RCX

  (88) 0x40ec2b SHR	$0x3,%RCX

  (88) 0x40ec2f IMUL	$-0x55555555,%ECX,%ECX

  (88) 0x40ec35 TEST	%ECX,%ECX

  (88) 0x40ec37 JLE	40ecf9

  (88) 0x40ec3d VPBROADCASTQ	%R14,%XMM0

  (88) 0x40ec43 MOV	$0x10,%EAX

  (88) 0x40ec48 XOR	%ECX,%ECX

  (88) 0x40ec4a MOV	-0x30(%RBP),%R8

  (88) 0x40ec4e XCHG	%AX,%AX

    (89) 0x40ec50 MOV	(%R15),%RDX

    (89) 0x40ec53 VMOVDDUP	(%RDX,%R14,8),%XMM1

    (89) 0x40ec59 MOV	(%RBX),%RDX

    (89) 0x40ec5c MOVSXD	-0x10(%RBX),%R9

    (89) 0x40ec60 VMOVSD	(%R8,%RAX,1),%XMM2

    (89) 0x40ec66 LEA	(%R14,%R9,2),%RDI

    (89) 0x40ec6a VFMADD213SD	(%RDX,%RDI,8),%XMM1,%XMM2

    (89) 0x40ec70 VMOVQ	%R9,%XMM3

    (89) 0x40ec75 VPSLLDQ	$0x8,%XMM3,%XMM3

    (89) 0x40ec7a VPADDQ	%XMM3,%XMM0,%XMM3

    (89) 0x40ec7e VPSLLQ	$0x3,%XMM3,%XMM3

    (89) 0x40ec83 VPBROADCASTQ	%RDX,%XMM4

    (89) 0x40ec89 VPADDQ	%XMM3,%XMM4,%XMM3

    (89) 0x40ec8d VMOVQ	%XMM3,%RDX

    (89) 0x40ec92 VMOVSD	(%RDX),%XMM4

    (89) 0x40ec96 VPEXTRQ	$0x1,%XMM3,%RDX

    (89) 0x40ec9c VMOVHPD	(%RDX),%XMM4,%XMM3

    (89) 0x40eca0 MOV	0x40(%RSI),%RDX

    (89) 0x40eca4 VADDSD	0x10(%RDX,%R12,8),%XMM2,%XMM2

    (89) 0x40ecab VFMADD231PD	-0x10(%R8,%RAX,1),%XMM1,%XMM3

    (89) 0x40ecb2 VADDPD	(%RDX,%R12,8),%XMM3,%XMM1

    (89) 0x40ecb8 MOV	-0x60(%RBP),%RDX

    (89) 0x40ecbc VMOVUPD	%XMM1,-0x10(%RDX,%RAX,1)

    (89) 0x40ecc2 VMOVSD	%XMM2,(%RDX,%RAX,1)

    (89) 0x40ecc7 MOV	0x13f0(%R13),%RDX

    (89) 0x40ecce SUB	0x13e8(%R13),%RDX

    (89) 0x40ecd5 INC	%RCX

    (89) 0x40ecd8 SHR	$0x3,%RDX

    (89) 0x40ecdc IMUL	$-0x55555555,%EDX,%EDX

    (89) 0x40ece2 MOVSXD	%EDX,%RDX

    (89) 0x40ece5 ADD	$0x18,%RAX

    (89) 0x40ece9 CMP	%RDX,%RCX

    (89) 0x40ecec JL	40ec50

  (88) 0x40ecf2 MOV	0x1418(%R13),%RAX

  (88) 0x40ecf9 MOV	0x18(%RAX),%RAX

  (88) 0x40ecfd MOVSXD	(%RAX,%R14,4),%RAX

  (88) 0x40ed01 MOV	0x1400(%R13),%RCX

  (88) 0x40ed08 MOV	(%RCX,%RAX,8),%R13

  (88) 0x40ed0c MOV	%R13,%RDI

  (88) 0x40ed0f MOV	-0x38(%RBP),%RDX

  (88) 0x40ed13 LEA	-0x60(%RBP),%RCX

  (88) 0x40ed17 MOV	$0x1,%R8D

  (88) 0x40ed1d MOV	%R14D,%R9D

  (88) 0x40ed20 CALL	464e40 <_ZN11qmcplusplus18VirtualParticleSet9makeMovesERKNS_11ParticleSetEiRKSt6vectorINS_10TinyVectorIdLj3EEESaIS6_EEbi>

  (88) 0x40ed25 MOV	-0xa8(%RBP),%RDI

  (88) 0x40ed2c MOV	%R13,%RSI

  (88) 0x40ed2f LEA	-0x80(%RBP),%RDX

  (88) 0x40ed33 CALL	412f30 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE>

  (88) 0x40ed38 MOV	-0x40(%RBP),%R13

  (88) 0x40ed3c MOV	0x1418(%R13),%RAX

  (88) 0x40ed43 MOV	-0xa0(%RBP),%RSI

  (88) 0x40ed4a JMP	40ec00

0x40ed4f MOV	-0x80(%RBP),%RDI

0x40ed53 TEST	%RDI,%RDI

0x40ed56 JE	40ed64

0x40ed58 MOV	-0x70(%RBP),%RSI

0x40ed5c SUB	%RDI,%RSI

0x40ed5f CALL	404070 <_ZdlPvm@plt>

0x40ed64 MOV	-0x60(%RBP),%RDI

0x40ed68 TEST	%RDI,%RDI

0x40ed6b JE	40ed79

0x40ed6d MOV	-0x50(%RBP),%RSI

0x40ed71 SUB	%RDI,%RSI

0x40ed74 CALL	404070 <_ZdlPvm@plt>

0x40ed79 CMPQ	$0,-0x98(%RBP)

0x40ed81 JE	40ed98

0x40ed83 MOV	-0x48(%RBP),%RAX

0x40ed87 SAL	$0x3,%RAX

0x40ed8b LEA	(%RAX,%RAX,2),%RSI

0x40ed8f MOV	-0x30(%RBP),%RDI

0x40ed93 CALL	404070 <_ZdlPvm@plt>

0x40ed98 ADD	$0x98,%RSP

0x40ed9f POP	%RBX

0x40eda0 POP	%R12

0x40eda2 POP	%R13

0x40eda4 POP	%R14

0x40eda6 POP	%R15

0x40eda8 POP	%RBP

0x40eda9 RET

0x40edaa CALL	404530 <_ZSt28__throw_bad_array_new_lengthv@plt>

0x40edaf MOV	$0x4fd934,%EDI

0x40edb4 VZEROUPPER

0x40edb7 CALL	404260 <_ZSt20__throw_length_errorPKc@plt>

0x40edbc MOV	$0x4fd934,%EDI

0x40edc1 VZEROUPPER

0x40edc4 CALL	404260 <_ZSt20__throw_length_errorPKc@plt>

0x40edc9 JMP	40edea

0x40edcb MOV	%RAX,%R14

0x40edce MOV	-0x60(%RBP),%RDI

0x40edd2 TEST	%RDI,%RDI

0x40edd5 JE	40edff

0x40edd7 JMP	40ee26

0x40edd9 MOV	%RAX,%R14

0x40eddc CMPQ	$0,-0x98(%RBP)

0x40ede4 JE	40ee09

0x40ede6 JMP	40ee3c

0x40ede8 JMP	40edea

0x40edea MOV	%RAX,%R14

0x40eded MOV	-0x80(%RBP),%RDI

0x40edf1 TEST	%RDI,%RDI

0x40edf4 JNE	40ee11

0x40edf6 MOV	-0x60(%RBP),%RDI

0x40edfa TEST	%RDI,%RDI

0x40edfd JNE	40ee26

(86) 0x40edff CMPQ	$0,-0x98(%RBP)

(86) 0x40ee07 JNE	40ee3c

(86) 0x40ee09 MOV	%R14,%RDI

(86) 0x40ee0c CALL	404270 <_Unwind_Resume@plt>

(86) 0x40ee11 MOV	-0x70(%RBP),%RSI

(86) 0x40ee15 SUB	%RDI,%RSI

(86) 0x40ee18 CALL	404070 <_ZdlPvm@plt>

(86) 0x40ee1d MOV	-0x60(%RBP),%RDI

(86) 0x40ee21 TEST	%RDI,%RDI

(86) 0x40ee24 JE	40edff

(86) 0x40ee26 MOV	-0x50(%RBP),%RSI

(86) 0x40ee2a SUB	%RDI,%RSI

(86) 0x40ee2d CALL	404070 <_ZdlPvm@plt>

(86) 0x40ee32 CMPQ	$0,-0x98(%RBP)

(86) 0x40ee3a JE	40ee09

0x40ee3c MOV	-0x48(%RBP),%RAX

0x40ee40 SAL	$0x3,%RAX

0x40ee44 LEA	(%RAX,%RAX,2),%RSI

0x40ee48 MOV	-0x30(%RBP),%RDI

0x40ee4c CALL	404070 <_ZdlPvm@plt>

0x40ee51 MOV	%R14,%RDI

0x40ee54 CALL	404270 <_Unwind_Resume@plt>

0x40ee59 NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►100.00+	main.extracted.107	NewTimer.h:249	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	NonLocalPP.hpp:104-139
Module	exec

The function is defined in:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_construct.h:119
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/StdRandom.h:97
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:111-116,127,145-147
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:43,63
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:231
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h:77-79
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.h:97
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:98,335-336,346,353,361-363,919,1046,1064,1605,1769-1770
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:911-912,923-924,1115
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:104-139
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_uninitialized.h:578,602
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:61-62,145,170
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/unique_ptr.h:173
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:48,210,229
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:277

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 59.33 to 19.33 cycles (3.07x speedup).

Workaround

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

Vectorization

Your function is poorly vectorized. Only 16% of vector register length is used (average across all SSE/AVX instructions).

Details

22% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

42% of SSE/AVX loads are used in vector version.
14% of SSE/AVX stores are used in vector version.
0% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX multiply instructions are used in vector version.
25% of SSE/AVX fused multiply-add instructions are used in vector version.
0% of SSE/AVX divide and square root instructions are used in vector version.
26% 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

Detected 5 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

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.

_Unwind_Resume@plt: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:145
__libm_sse2_sincos: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:105
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:105
_intel_fast_memset: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:924
double std::uniform_real_distribution
::operator()
>(std::mersenne_twister_engine
&): 3 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/StdRandom.h:97
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/StdRandom.h:97
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/StdRandom.h:97
operator delete(void*, unsigned long): 4 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:145
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:145
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:145
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:145
operator new(unsigned long): 3 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:127
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:127
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:127
qmcplusplus::ParticleSet::getDistTableAB(int) const: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:120
std::__throw_bad_array_new_length(): 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:116
std::__throw_length_error(char const*): 2 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1770
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1770

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.

MULX: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:911
VZEROUPPER: 6 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:127
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:127
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/StdRandom.h:97
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:120
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1770
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1770

Vector unaligned load/store instructions

Detected 4 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:111
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:111
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:111
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:111

Workaround

Use vector aligned instructions:

align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Type of elements and instruction set

14 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 21 FP arithmetical operations:

6: addition or subtraction (5 inside FMA instructions)
14: multiply (5 inside FMA instructions)
1: square root

The binary function is loading 540 bytes (67 double precision FP elements). The binary function is storing 256 bytes (32 double precision FP elements).

Arithmetic intensity

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

General properties

nb instructions	331
nb uops	356
loop length	1544
used x86 registers	14
used mmx registers	0
used xmm registers	14
used ymm registers	16
used zmm registers	0
nb stack references	16
ADD-SUB / MUL ratio	0.11

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	59.33 cycles
front end	59.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	27.70	27.53	20.00	20.00	26.00	27.57	27.60	26.00	26.00	26.00	27.60	20.00
cycles	27.70	27.53	20.00	20.00	26.00	27.57	27.60	26.00	26.00	26.00	27.60	20.00

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

4.50

Cycles summary

Front-end	59.33
Dispatch	27.70
DIV/SQRT	4.50
Overall L1	59.33

Vectorization ratios

INT

all	9%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	16%

all	37%
load	50%
store	50%
mul	0%
add-sub	0%
fma	25%
div/sqrt	0%
other	47%

INT+FP

all	22%
load	42%
store	14%
mul	0%
add-sub	0%
fma	25%
div/sqrt	0%
other	26%

Vector efficiency ratios

INT

all	12%
load	12%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	14%

all	19%
load	25%
store	18%
mul	12%
add-sub	12%
fma	15%
div/sqrt	12%
other	19%

INT+FP

all	16%
load	23%
store	13%
mul	12%
add-sub	12%
fma	15%
div/sqrt	12%
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 59.33 cycles. At this rate:

4% of peak load performance is reached (9.10 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.31 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 59.33 to 27.70 cycles (2.14x speedup).

ASM code

In the binary file, the address of the function is: 40e430

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	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 %RSI,-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
MOV 0x13f0(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB 0x13e8(%RDI),%RAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV $0x555555555555555,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
SAR $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV $-0x5555555555555555,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
IMUL %RCX,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD %EAX,%R15	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
SAL $0x20,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	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 %R15,-0x48(%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 40e587 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x157>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP %RBX,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JA 40edaa <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x97a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%R15,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RAX,%RAX,2),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 404450 <_Znwm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP $0x8,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 40e50c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0xdc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SHR $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x30(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0xa0,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	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%)
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x7fffffffffffff8,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV -0x48(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
AND %RSI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %RSI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 40e58f <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x15f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD $-0x18,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $-0x5555555555555555,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MULX %RAX,%RAX,%RAX	2	0	1	0	0	0	1	0	0	0	0	0	0	3-4	1	N/A
SHR $0x4,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SUB %RCX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
INC %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x3b,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
BZHI %RCX,%RSI,%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
SHR $0x3,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RCX,%RCX,2),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x6,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x30(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RCX,%RDX,1),%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	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%)
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 40e58f <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x15f>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOVQ $0,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x13f0(%R12),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12,-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%)
SUB 0x13e8(%R12),%R13	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
SAR $0x3,%R13	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV $-0x5555555555555555,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
IMUL %R12,%R13	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD %R13D,%R15	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
CMP %RBX,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JA 40edaf <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x97f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R13,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAL $0x20,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	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%)
VMOVUPD %XMM0,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ $0,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
JE 40e613 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1e3>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%R15,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RAX,%RAX,2),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404450 <_Znwm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,-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%)
LEA (%R15,%R15,2),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RAX,%RCX,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
AND $0x7,%R13D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP $0x8,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JAE 40e626 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1f6>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 40e6ca <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x29a>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
SAL $0x3,%R15	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%R15,%R15,2),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 40e724 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x2f4>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
SUB %R13,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0xb8(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %ECX,%ECX	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%)
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R13,%R13	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 40e707 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x2d7>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RCX,%RCX,2),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x10(%RAX,%RCX,8),%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
SAL $0x3,%R13D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%R13,%R13,2),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %ESI,%ESI	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%)
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R14,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x40(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x13f0(%RCX),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB 0x13e8(%RCX),%R13	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
SAR $0x3,%R13	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL %R12,%R13	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVSXD %R13D,%RBX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %RBX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x3c,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
JNE 40edbc <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x98c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SAL $0x20,%R13	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	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%)
VMOVUPD %XMM0,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ $0,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
JE 40e78c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x35c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R13,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SAR $0x1d,%R14	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (12.5%)
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404450 <_Znwm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (%RAX,%RBX,8),%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
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%)
MOVQ $0,(%RAX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x100000000,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
CMP %RCX,%R13	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 40e798 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x368>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 40e7a9 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x379>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
SAL $0x3,%RBX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
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%)
XOR %EBX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 40e7a9 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x379>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
ADD $-0x8,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 4efda0 <_intel_fast_memset>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x40(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RBX,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA 0x13a0(%RAX),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x18(%RAX),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 40f8d0 <_ZNSt25uniform_real_distributionIdEclISt23mersenne_twister_engineImLm32ELm624ELm397ELm31ELm2567483615ELm11ELm4294967295ELm7ELm2636928640ELm15ELm4022730752ELm18ELm1812433253EEEEdRT_>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVSD %XMM0,-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 %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 40f8d0 <_ZNSt25uniform_real_distributionIdEclISt23mersenne_twister_engineImLm32ELm624ELm397ELm31ELm2567483615ELm11ELm4294967295ELm7ELm2636928640ELm15ELm4022730752ELm18ELm1812433253EEEEdRT_>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVSD %XMM0,-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%)
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 40f8d0 <_ZNSt25uniform_real_distributionIdEclISt23mersenne_twister_engineImLm32ELm624ELm397ELm31ELm2567483615ELm11ELm4294967295ELm7ELm2636928640ELm15ELm4022730752ELm18ELm1812433253EEEEdRT_>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVSD %XMM0,-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%)
VMOVSD -0x38(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMULSD 0xee82e(%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 -0x90(%RBP),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMULSD 0xee81e(%RIP),%XMM1,%XMM1	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 %XMM1,-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%)
CALL 4df3e0 <__libm_sse2_sincos>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVUPD %XMM0,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
VMOVUPD %XMM1,-0xc0(%RBP)	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 -0x38(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CALL 4df3e0 <__libm_sse2_sincos>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVUPD -0xc0(%RBP),%XMM29	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
VMOVUPD -0x90(%RBP),%XMM28	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOV -0x40(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x13e8(%R13),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x13f0(%R13),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %RAX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAR $0x3,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL %R12,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
TEST %EDX,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
MOV -0x30(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xa0(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JLE 40eb4c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x71c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVSD -0xb0(%RBP),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDSD 0xee7b4(%RIP),%XMM2,%XMM2	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 0xee7b4(%RIP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD231SD %XMM2,%XMM2,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VSQRTSD %XMM3,%XMM3,%XMM3	1	1	0	0	0	0	0	0	0	0	0	0	0	13-19	4.50	scal (12.5%)
VMULSD %XMM29,%XMM1,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM2,%XMM4,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM28,%XMM1,%XMM26	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM29,%XMM0,%XMM25	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VFMADD231SD %XMM2,%XMM26,%XMM25	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM0,%XMM2,%XMM8	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VFNMSUB231SD %XMM29,%XMM8,%XMM26	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VPUNPCKLQDQ %XMM8,%XMM0,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVDDUP %XMM28,%XMM9	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VPUNPCKLQDQ %XMM4,%XMM7,%XMM4	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFNMADD231PD %XMM9,%XMM8,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
VXORPD 0xee76f(%RIP){1to2},%XMM3,%XMM7	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
VMULSD %XMM0,%XMM3,%XMM22	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM7,%XMM1,%XMM23	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %EDX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x7fffffff,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
LEA (%RCX,%RCX,2),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x8(%RAX,%RSI,8),%R9	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %R8,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 40e971 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x541>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x8(%R8,%RSI,8),%RSI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %RAX,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 40e971 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x541>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VPUNPCKLQDQ %XMM26,%XMM23,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
VPUNPCKLQDQ %XMM22,%XMM25,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
SAL $0x3,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RCX,%RCX,2),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EDX,%EDX	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
JMP 40eb4c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x71c>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
AND $0x7ffffffc,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 40ead1 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x6a1>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VBROADCASTSD %XMM4,%YMM27	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM25,%YMM8	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM23,%YMM9	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM26,%YMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VPERMPD $0x55,%YMM4,%YMM11	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VBROADCASTSD %XMM22,%YMM12	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM29,%YMM13	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM28,%YMM14	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM2,%YMM15	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM3,%YMM16	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVUPD 0xeed7b(%RIP),%YMM17	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0xeed91(%RIP),%YMM18	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VBROADCASTF32X4 0xeee27(%RIP),%YMM19	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	5-8	0.33	vect (25.0%)
VMOVUPD 0xeedbd(%RIP),%YMM20	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0xeedd3(%RIP),%YMM21	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
MOV -0x30(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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
CMP %EDX,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 40ead7 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x6a7>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 40eb4c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x71c>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x30(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VPUNPCKLQDQ %XMM26,%XMM23,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
VPUNPCKLQDQ %XMM22,%XMM25,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
SUB %RDX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%RDX,%RDX,2),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x10(,%RDX,8),%RDX	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
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 0x38(%RAX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
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%)
MOV 0x260(%RBX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RCX,%RCX	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 40ed4f <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x91f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x1418(%R13),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMPQ $0,0x260(%RAX)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 40ed4f <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x91f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RBX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVQ $0,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
JMP 40ebbb <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x78b>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	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 (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x80(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RDI,%RDI	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 40ed64 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x934>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %RDI,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CALL 404070 <_ZdlPvm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x60(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RDI,%RDI	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 40ed79 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x949>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x50(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %RDI,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CALL 404070 <_ZdlPvm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
CMPQ $0,-0x98(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 40ed98 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x968>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SAL $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RAX,%RAX,2),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x30(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 404070 <_ZdlPvm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x98,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
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
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
CALL 404530 <_ZSt28__throw_bad_array_new_lengthv@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV $0x4fd934,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404260 <_ZSt20__throw_length_errorPKc@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV $0x4fd934,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404260 <_ZSt20__throw_length_errorPKc@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
JMP 40edea <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9ba>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x60(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RDI,%RDI	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 40edff <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9cf>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 40ee26 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9f6>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMPQ $0,-0x98(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 40ee09 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9d9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 40ee3c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0xa0c>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
JMP 40edea <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9ba>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x80(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RDI,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JNE 40ee11 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9e1>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x60(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RDI,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JNE 40ee26 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9f6>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SAL $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RAX,%RAX,2),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x30(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 404070 <_ZdlPvm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 404270 <_Unwind_Resume@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	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	NonLocalPP.hpp:104-139
Module	exec

The function is defined in:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_construct.h:119
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/StdRandom.h:97
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:111-116,127,145-147
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:43,63
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:231
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h:77-79
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.h:97
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:98,335-336,346,353,361-363,919,1046,1064,1605,1769-1770
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:911-912,923-924,1115
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:104-139
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_uninitialized.h:578,602
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:61-62,145,170
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/unique_ptr.h:173
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:48,210,229
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:277

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Workaround

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

Vectorization

Your function is poorly vectorized. Only 16% of vector register length is used (average across all SSE/AVX instructions).

Details

22% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

42% of SSE/AVX loads are used in vector version.
14% of SSE/AVX stores are used in vector version.
0% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX multiply instructions are used in vector version.
25% of SSE/AVX fused multiply-add instructions are used in vector version.
0% of SSE/AVX divide and square root instructions are used in vector version.
26% 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

Detected 5 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

CALL instructions

Detected function call instructions.

Details

_Unwind_Resume@plt: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:145
__libm_sse2_sincos: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:105
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:105
_intel_fast_memset: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:924
double std::uniform_real_distribution
::operator()
>(std::mersenne_twister_engine
&): 3 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/StdRandom.h:97
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/StdRandom.h:97
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/StdRandom.h:97
operator delete(void*, unsigned long): 4 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:145
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:145
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:145
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:145
operator new(unsigned long): 3 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:127
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:127
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:127
qmcplusplus::ParticleSet::getDistTableAB(int) const: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:120
std::__throw_bad_array_new_length(): 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:116
std::__throw_length_error(char const*): 2 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1770
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1770

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.

MULX: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:911
VZEROUPPER: 6 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:127
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:127
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/StdRandom.h:97
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:120
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1770
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1770

Vector unaligned load/store instructions

Detected 4 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:111
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:111
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:111
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:111

Workaround

Use vector aligned instructions:

align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Type of elements and instruction set

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

The binary function is composed of 21 FP arithmetical operations:

6: addition or subtraction (5 inside FMA instructions)
14: multiply (5 inside FMA instructions)
1: square root

The binary function is loading 540 bytes (67 double precision FP elements). The binary function is storing 256 bytes (32 double precision FP elements).

Arithmetic intensity

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

General properties

nb instructions	331
nb uops	356
loop length	1544
used x86 registers	14
used mmx registers	0
used xmm registers	14
used ymm registers	16
used zmm registers	0
nb stack references	16
ADD-SUB / MUL ratio	0.11

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	59.33 cycles
front end	59.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	27.70	27.53	20.00	20.00	26.00	27.57	27.60	26.00	26.00	26.00	27.60	20.00
cycles	27.70	27.53	20.00	20.00	26.00	27.57	27.60	26.00	26.00	26.00	27.60	20.00

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

4.50

Cycles summary

Front-end	59.33
Dispatch	27.70
DIV/SQRT	4.50
Overall L1	59.33

Vectorization ratios

INT

all	9%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	16%

all	37%
load	50%
store	50%
mul	0%
add-sub	0%
fma	25%
div/sqrt	0%
other	47%

INT+FP

all	22%
load	42%
store	14%
mul	0%
add-sub	0%
fma	25%
div/sqrt	0%
other	26%

Vector efficiency ratios

INT

all	12%
load	12%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	14%

all	19%
load	25%
store	18%
mul	12%
add-sub	12%
fma	15%
div/sqrt	12%
other	19%

INT+FP

all	16%
load	23%
store	13%
mul	12%
add-sub	12%
fma	15%
div/sqrt	12%
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 59.33 cycles. At this rate:

4% of peak load performance is reached (9.10 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.31 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: 40e430

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	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 %RSI,-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
MOV 0x13f0(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB 0x13e8(%RDI),%RAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV $0x555555555555555,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
SAR $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV $-0x5555555555555555,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
IMUL %RCX,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD %EAX,%R15	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
SAL $0x20,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	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 %R15,-0x48(%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 40e587 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x157>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP %RBX,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JA 40edaa <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x97a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%R15,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RAX,%RAX,2),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 404450 <_Znwm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP $0x8,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 40e50c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0xdc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SHR $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x30(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0xa0,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	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%)
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x7fffffffffffff8,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV -0x48(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
AND %RSI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %RSI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 40e58f <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x15f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD $-0x18,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $-0x5555555555555555,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MULX %RAX,%RAX,%RAX	2	0	1	0	0	0	1	0	0	0	0	0	0	3-4	1	N/A
SHR $0x4,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SUB %RCX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
INC %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x3b,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
BZHI %RCX,%RSI,%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
SHR $0x3,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RCX,%RCX,2),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x6,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x30(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RCX,%RDX,1),%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	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%)
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 40e58f <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x15f>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOVQ $0,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x13f0(%R12),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12,-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%)
SUB 0x13e8(%R12),%R13	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
SAR $0x3,%R13	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV $-0x5555555555555555,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
IMUL %R12,%R13	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD %R13D,%R15	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
CMP %RBX,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JA 40edaf <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x97f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R13,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAL $0x20,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	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%)
VMOVUPD %XMM0,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ $0,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
JE 40e613 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1e3>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%R15,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RAX,%RAX,2),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404450 <_Znwm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,-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%)
LEA (%R15,%R15,2),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RAX,%RCX,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
AND $0x7,%R13D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP $0x8,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JAE 40e626 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1f6>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 40e6ca <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x29a>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
SAL $0x3,%R15	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%R15,%R15,2),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 40e724 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x2f4>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
SUB %R13,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0xb8(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %ECX,%ECX	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%)
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R13,%R13	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 40e707 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x2d7>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RCX,%RCX,2),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x10(%RAX,%RCX,8),%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
SAL $0x3,%R13D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%R13,%R13,2),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %ESI,%ESI	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%)
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R14,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x40(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x13f0(%RCX),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB 0x13e8(%RCX),%R13	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
SAR $0x3,%R13	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL %R12,%R13	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVSXD %R13D,%RBX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %RBX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x3c,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
JNE 40edbc <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x98c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SAL $0x20,%R13	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	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%)
VMOVUPD %XMM0,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ $0,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
JE 40e78c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x35c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R13,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SAR $0x1d,%R14	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (12.5%)
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404450 <_Znwm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (%RAX,%RBX,8),%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
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%)
MOVQ $0,(%RAX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
ADD $0x8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x100000000,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
CMP %RCX,%R13	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 40e798 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x368>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 40e7a9 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x379>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
SAL $0x3,%RBX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
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%)
XOR %EBX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 40e7a9 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x379>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
ADD $-0x8,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 4efda0 <_intel_fast_memset>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x40(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RBX,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA 0x13a0(%RAX),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x18(%RAX),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 40f8d0 <_ZNSt25uniform_real_distributionIdEclISt23mersenne_twister_engineImLm32ELm624ELm397ELm31ELm2567483615ELm11ELm4294967295ELm7ELm2636928640ELm15ELm4022730752ELm18ELm1812433253EEEEdRT_>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVSD %XMM0,-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 %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 40f8d0 <_ZNSt25uniform_real_distributionIdEclISt23mersenne_twister_engineImLm32ELm624ELm397ELm31ELm2567483615ELm11ELm4294967295ELm7ELm2636928640ELm15ELm4022730752ELm18ELm1812433253EEEEdRT_>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVSD %XMM0,-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%)
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 40f8d0 <_ZNSt25uniform_real_distributionIdEclISt23mersenne_twister_engineImLm32ELm624ELm397ELm31ELm2567483615ELm11ELm4294967295ELm7ELm2636928640ELm15ELm4022730752ELm18ELm1812433253EEEEdRT_>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVSD %XMM0,-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%)
VMOVSD -0x38(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMULSD 0xee82e(%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 -0x90(%RBP),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMULSD 0xee81e(%RIP),%XMM1,%XMM1	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 %XMM1,-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%)
CALL 4df3e0 <__libm_sse2_sincos>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVUPD %XMM0,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
VMOVUPD %XMM1,-0xc0(%RBP)	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 -0x38(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CALL 4df3e0 <__libm_sse2_sincos>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVUPD -0xc0(%RBP),%XMM29	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
VMOVUPD -0x90(%RBP),%XMM28	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOV -0x40(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x13e8(%R13),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x13f0(%R13),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %RAX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAR $0x3,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL %R12,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
TEST %EDX,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
MOV -0x30(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xa0(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JLE 40eb4c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x71c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVSD -0xb0(%RBP),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDSD 0xee7b4(%RIP),%XMM2,%XMM2	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 0xee7b4(%RIP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD231SD %XMM2,%XMM2,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VSQRTSD %XMM3,%XMM3,%XMM3	1	1	0	0	0	0	0	0	0	0	0	0	0	13-19	4.50	scal (12.5%)
VMULSD %XMM29,%XMM1,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM2,%XMM4,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM28,%XMM1,%XMM26	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM29,%XMM0,%XMM25	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VFMADD231SD %XMM2,%XMM26,%XMM25	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM0,%XMM2,%XMM8	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VFNMSUB231SD %XMM29,%XMM8,%XMM26	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VPUNPCKLQDQ %XMM8,%XMM0,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVDDUP %XMM28,%XMM9	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VPUNPCKLQDQ %XMM4,%XMM7,%XMM4	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFNMADD231PD %XMM9,%XMM8,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
VXORPD 0xee76f(%RIP){1to2},%XMM3,%XMM7	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
VMULSD %XMM0,%XMM3,%XMM22	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM7,%XMM1,%XMM23	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %EDX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x7fffffff,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
LEA (%RCX,%RCX,2),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x8(%RAX,%RSI,8),%R9	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %R8,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 40e971 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x541>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x8(%R8,%RSI,8),%RSI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %RAX,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 40e971 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x541>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VPUNPCKLQDQ %XMM26,%XMM23,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
VPUNPCKLQDQ %XMM22,%XMM25,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
SAL $0x3,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RCX,%RCX,2),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EDX,%EDX	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
JMP 40eb4c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x71c>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
AND $0x7ffffffc,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 40ead1 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x6a1>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VBROADCASTSD %XMM4,%YMM27	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM25,%YMM8	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM23,%YMM9	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM26,%YMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VPERMPD $0x55,%YMM4,%YMM11	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VBROADCASTSD %XMM22,%YMM12	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM29,%YMM13	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM28,%YMM14	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM2,%YMM15	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM3,%YMM16	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVUPD 0xeed7b(%RIP),%YMM17	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0xeed91(%RIP),%YMM18	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VBROADCASTF32X4 0xeee27(%RIP),%YMM19	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	5-8	0.33	vect (25.0%)
VMOVUPD 0xeedbd(%RIP),%YMM20	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0xeedd3(%RIP),%YMM21	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
MOV -0x30(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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
CMP %EDX,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 40ead7 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x6a7>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 40eb4c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x71c>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x30(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VPUNPCKLQDQ %XMM26,%XMM23,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
VPUNPCKLQDQ %XMM22,%XMM25,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
SUB %RDX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%RDX,%RDX,2),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x10(,%RDX,8),%RDX	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
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 0x38(%RAX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
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%)
MOV 0x260(%RBX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RCX,%RCX	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 40ed4f <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x91f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x1418(%R13),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMPQ $0,0x260(%RAX)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 40ed4f <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x91f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RBX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVQ $0,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
JMP 40ebbb <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x78b>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	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 (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x80(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RDI,%RDI	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 40ed64 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x934>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %RDI,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CALL 404070 <_ZdlPvm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x60(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RDI,%RDI	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 40ed79 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x949>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x50(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %RDI,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CALL 404070 <_ZdlPvm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
CMPQ $0,-0x98(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 40ed98 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x968>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SAL $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RAX,%RAX,2),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x30(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 404070 <_ZdlPvm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x98,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
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
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
CALL 404530 <_ZSt28__throw_bad_array_new_lengthv@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV $0x4fd934,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404260 <_ZSt20__throw_length_errorPKc@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV $0x4fd934,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404260 <_ZSt20__throw_length_errorPKc@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
JMP 40edea <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9ba>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x60(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RDI,%RDI	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 40edff <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9cf>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 40ee26 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9f6>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMPQ $0,-0x98(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 40ee09 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9d9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 40ee3c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0xa0c>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
JMP 40edea <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9ba>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x80(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RDI,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JNE 40ee11 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9e1>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x60(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RDI,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JNE 40ee26 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x9f6>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SAL $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RAX,%RAX,2),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x30(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 404070 <_ZdlPvm@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 404270 <_Unwind_Resume@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	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)
▼qmcplusplus::NonLocalPP::evaluate(qmcplusplus::ParticleSet const&, qmcplusplus::WaveFunction&)–	0.09	0.08
▼Loop 87 - NonLocalPP.hpp:122-135 - exec–	0.00	0.01
▼Loop 88 - NonLocalPP.hpp:126-135 - exec–	0.09	0.07
○Loop 89 - NonLocalPP.hpp:131-132 - exec	0.01	0.01
○Loop 92 - NonLocalPP.hpp:110-111 - exec	0.00	0.00
○Loop 91 - NonLocalPP.hpp:110-111 - exec	0.00	0.00
○Loop 93 - stl_uninitialized.h:578-578 - exec	0.00	0.00
○Loop 94 - stl_uninitialized.h:578-578 - exec	0.00	0.00
○Loop 90 - NonLocalPP.hpp:110-111 - exec	0.00	0.00
○Loop 95 - stl_algobase.h:911-912 - exec	0.00	0.00
○Loop 86 - OhmmsVector.h:48-210 - exec	0.00	0.00
○Loop 96 - stl_algobase.h:911-912 - 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

Vector unaligned load/store instructions

Details

Workaround

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

Vector unaligned load/store instructions

Details

Workaround

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