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:115-139 [...]	Coverage (incl. loops): 0.05% \| (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)...);

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h: 111 - 145

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

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleAttrib.h: 34 - 34

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

34:   explicit inline ParticleAttrib(size_t n = 0) : __my_base(n), InUnit(0) {}

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 277 - 277

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

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.h: 97 - 97

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

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 62 - 145

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

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

[...]

144:     for (int i = 0; i < D; ++i)

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

/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,

[...]

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_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 46 - 302

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

46:   explicit inline Vector(size_t n = 0, Type_t val = Type_t()) : nLocal(n)

47:   {

48:     if (n)

[...]

144:   virtual ~Vector() { free(); }

[...]

210:     if (nAllocated)

211:     {

212:       mAllocator.deallocate(X, nAllocated);

[...]

223:     return X[i];

[...]

229:     return X[i];

[...]

289:   T* X = nullptr;

[...]

300:     X          = mAllocator.allocate(n);

301:     nLocal     = n;

302:     nAllocated = n;

/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_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp: 115 - 139

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

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/unique_ptr.h: 173 - 173

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

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 43 - 63

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

43:     return (a + b);

[...]

63:     return (a * b);

/home/eoseret/qaas_runs_ZEN5/173-938-0042/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); }

0x22ca00 PUSH	%RBP

0x22ca01 MOV	%RSP,%RBP

0x22ca04 PUSH	%R15

0x22ca06 PUSH	%R14

0x22ca08 PUSH	%R13

0x22ca0a PUSH	%R12

0x22ca0c PUSH	%RBX

0x22ca0d SUB	$0x88,%RSP

0x22ca14 MOV	0x13f0(%RDI),%RAX

0x22ca1b MOV	$-0x5555555555555555,%RBX

0x22ca25 VXORPD	%XMM0,%XMM0,%XMM0

0x22ca29 MOV	%RDX,-0x70(%RBP)

0x22ca2d MOV	%RSI,-0x68(%RBP)

0x22ca31 MOV	%RDI,%R15

0x22ca34 SUB	0x13e8(%RDI),%RAX

0x22ca3b SAR	$0x3,%RAX

0x22ca3f IMUL	%RBX,%RAX

0x22ca43 MOV	%RAX,%RCX

0x22ca46 MOVSXD	%EAX,%R14

0x22ca49 SAL	$0x20,%RCX

0x22ca4d MOV	%R14,-0x90(%RBP)

0x22ca54 VMOVUPD	%XMM0,-0x88(%RBP)

0x22ca5c TEST	%RCX,%RCX

0x22ca5f JE	22cacd

0x22ca61 JS	22ce25

0x22ca67 LEA	(,%R14,8),%RAX

0x22ca6f LEA	(%RAX,%RAX,2),%R12

0x22ca73 MOV	%R12,%RDI

0x22ca76 CALL	2f6c50 <@plt_start@+0x10>

0x22ca7b VXORPD	%XMM0,%XMM0,%XMM0

0x22ca7f MOV	%RAX,-0x80(%RBP)

0x22ca83 MOV	%R14,-0x90(%RBP)

0x22ca8a XOR	%ECX,%ECX

0x22ca8c MOV	%R14,-0x88(%RBP)

0x22ca93 NOPW	%CS:(%RAX,%RAX,1)

(56) 0x22caa0 VMOVUPD	%XMM0,(%RAX,%RCX,1)

(56) 0x22caa5 MOVQ	$0,0x10(%RAX,%RCX,1)

(56) 0x22caae ADD	$0x18,%RCX

(56) 0x22cab2 CMP	%RCX,%R12

(56) 0x22cab5 JNE	22caa0

0x22cab7 MOV	0x13f0(%R15),%RAX

0x22cabe SUB	0x13e8(%R15),%RAX

0x22cac5 SAR	$0x3,%RAX

0x22cac9 IMUL	%RBX,%RAX

0x22cacd MOV	%RAX,%RDX

0x22cad0 LEA	0xcbb59(%RIP),%RCX

0x22cad7 SAL	$0x20,%RDX

0x22cadb MOV	%RCX,-0x98(%RBP)

0x22cae2 MOVL	$0,-0x74(%RBP)

0x22cae9 TEST	%RDX,%RDX

0x22caec JS	22ce2a

0x22caf2 MOVSXD	%EAX,%R14

0x22caf5 VXORPD	%XMM0,%XMM0,%XMM0

0x22caf9 MOVQ	$0,-0x30(%RBP)

0x22cb01 VMOVAPD	%XMM0,-0x40(%RBP)

0x22cb06 JE	22cb57

0x22cb08 LEA	(,%R14,8),%RAX

0x22cb10 LEA	(%RAX,%RAX,2),%R13

0x22cb14 MOV	%R13,%RDI

0x22cb17 CALL	2f6c50 <@plt_start@+0x10>

0x22cb1c MOV	%RAX,%R12

0x22cb1f MOV	%RAX,-0x40(%RBP)

0x22cb23 LEA	(%R14,%R14,2),%RAX

0x22cb27 MOV	%R12,%RDI

0x22cb2a XOR	%ESI,%ESI

0x22cb2c MOV	%R13,%RDX

0x22cb2f LEA	(%R12,%RAX,8),%RAX

0x22cb33 MOV	%RAX,-0x30(%RBP)

0x22cb37 CALL	2f6df0 <@plt_start@+0x1b0>

0x22cb3c MOV	0x13f0(%R15),%RAX

0x22cb43 ADD	%R13,%R12

0x22cb46 SUB	0x13e8(%R15),%RAX

0x22cb4d SAR	$0x3,%RAX

0x22cb51 IMUL	%RBX,%RAX

0x22cb55 JMP	22cb6e

0x22cb57 SAL	$0x3,%R14

0x22cb5b MOVQ	$0,-0x40(%RBP)

0x22cb63 XOR	%R12D,%R12D

0x22cb66 LEA	(%R14,%R14,2),%RCX

0x22cb6a MOV	%RCX,-0x30(%RBP)

0x22cb6e MOV	%RAX,%RBX

0x22cb71 SAL	$0x20,%RBX

0x22cb75 MOV	%R12,-0x38(%RBP)

0x22cb79 TEST	%RBX,%RBX

0x22cb7c JS	22ce36

0x22cb82 MOVSXD	%EAX,%R14

0x22cb85 VXORPD	%XMM0,%XMM0,%XMM0

0x22cb89 MOVQ	$0,-0x50(%RBP)

0x22cb91 VMOVAPD	%XMM0,-0x60(%RBP)

0x22cb96 JE	22cbd8

0x22cb98 MOV	%RBX,%R13

0x22cb9b SHR	$0x1d,%R13

0x22cb9f MOV	%R13,%RDI

0x22cba2 CALL	2f6c50 <@plt_start@+0x10>

0x22cba7 LEA	(%RAX,%R14,8),%R14

0x22cbab MOV	%RAX,%RDI

0x22cbae MOV	%RAX,-0x60(%RBP)

0x22cbb2 MOV	%RAX,%R12

0x22cbb5 MOVQ	$0,(%RAX)

0x22cbbc ADD	$0x8,%RDI

0x22cbc0 MOV	$0x100000000,%RAX

0x22cbca MOV	%R14,-0x50(%RBP)

0x22cbce CMP	%RAX,%RBX

0x22cbd1 JNE	22cbf0

0x22cbd3 MOV	%RDI,%R14

0x22cbd6 JMP	22cbfe

0x22cbd8 SAL	$0x3,%R14

0x22cbdc MOVQ	$0,-0x60(%RBP)

0x22cbe4 XOR	%R12D,%R12D

0x22cbe7 MOV	%R14,-0x50(%RBP)

0x22cbeb XOR	%R14D,%R14D

0x22cbee JMP	22cbfe

0x22cbf0 ADD	$-0x8,%R13

0x22cbf4 XOR	%ESI,%ESI

0x22cbf6 MOV	%R13,%RDX

0x22cbf9 CALL	2f6df0 <@plt_start@+0x1b0>

0x22cbfe MOV	%R14,-0x58(%RBP)

0x22cc02 LEA	-0x98(%RBP),%RSI

0x22cc09 MOV	%R15,%RDI

0x22cc0c CALL	22c5b0 <_ZN11qmcplusplus10NonLocalPPIdE9randomizeINS_14ParticleAttribINS_10TinyVectorIdLj3EEESaIS5_EEEEEvRT_>

0x22cc11 MOV	-0x70(%RBP),%RAX

0x22cc15 MOV	0x38(%RAX),%ESI

0x22cc18 MOV	-0x68(%RBP),%RBX

0x22cc1c MOV	%RBX,%RDI

0x22cc1f CALL	27d7e0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x22cc24 MOV	%RAX,-0xa0(%RBP)

0x22cc2b MOV	0x260(%RBX),%RCX

0x22cc32 TEST	%RCX,%RCX

0x22cc35 JE	22cdd7

0x22cc3b MOV	0x1418(%R15),%RAX

0x22cc42 MOV	%RBX,%RSI

0x22cc45 XOR	%R13D,%R13D

0x22cc48 JMP	22cc63

0x22cc4a NOPW	(%RAX,%RAX,1)

(53) 0x22cc50 MOV	0x260(%RSI),%RCX

(53) 0x22cc57 INC	%R13

(53) 0x22cc5a CMP	%R13,%RCX

(53) 0x22cc5d JBE	22cdd3

(53) 0x22cc63 CMPQ	$0,0x260(%RAX)

(53) 0x22cc6b JE	22cc57

(53) 0x22cc6d MOV	-0xa0(%RBP),%RDI

(53) 0x22cc74 LEA	(,%R13,8),%RDX

(53) 0x22cc7c XOR	%R12D,%R12D

(53) 0x22cc7f LEA	(%RDX,%RDX,4),%RDX

(53) 0x22cc83 MOV	0x48(%RDI),%RCX

(53) 0x22cc87 MOV	0x60(%RDI),%RDI

(53) 0x22cc8b LEA	0x18(%RCX,%RDX,1),%R14

(53) 0x22cc90 LEA	0x18(%RDI,%RDX,1),%RBX

(53) 0x22cc95 JMP	22ccb7

0x22cc97 NOPW	(%RAX,%RAX,1)

  (54) 0x22cca0 MOV	0x1418(%R15),%RAX

  (54) 0x22cca7 MOV	-0x68(%RBP),%RSI

  (54) 0x22ccab INC	%R12

  (54) 0x22ccae CMP	%R12,0x260(%RAX)

  (54) 0x22ccb5 JBE	22cc50

  (54) 0x22ccb7 MOV	(%R14),%RCX

  (54) 0x22ccba VMOVSD	(%RCX,%R12,8),%XMM0

  (54) 0x22ccc0 VUCOMISD	(%R15),%XMM0

  (54) 0x22ccc5 JAE	22ccab

  (54) 0x22ccc7 MOV	0x13f0(%R15),%RCX

  (54) 0x22ccce SUB	0x13e8(%R15),%RCX

  (54) 0x22ccd5 SHR	$0x3,%RCX

  (54) 0x22ccd9 IMUL	$-0x55555555,%ECX,%ECX

  (54) 0x22ccdf TEST	%ECX,%ECX

  (54) 0x22cce1 JLE	22cd8b

  (54) 0x22cce7 MOV	$0x10,%EAX

  (54) 0x22ccec XOR	%ECX,%ECX

  (54) 0x22ccee XCHG	%AX,%AX

    (55) 0x22ccf0 MOV	(%RBX),%RDI

    (55) 0x22ccf3 MOV	-0x10(%RBX),%R9

    (55) 0x22ccf7 MOV	(%R14),%RDX

    (55) 0x22ccfa MOV	-0x80(%RBP),%R10

    (55) 0x22ccfe INC	%RCX

    (55) 0x22cd01 LEA	(%RDI,%R12,8),%R8

    (55) 0x22cd05 SAL	$0x20,%R9

    (55) 0x22cd09 VMOVDDUP	(%RDX,%R12,8),%XMM1

    (55) 0x22cd0f VMOVSD	(%RDI,%R12,8),%XMM2

    (55) 0x22cd15 VMOVSD	(%R10,%RAX,1),%XMM0

    (55) 0x22cd1b LEA	(%R13,%R13,2),%RDI

    (55) 0x22cd20 MOV	%R9,%RDX

    (55) 0x22cd23 SAR	$0x1d,%RDX

    (55) 0x22cd27 SAR	$0x1c,%R9

    (55) 0x22cd2b VMOVHPD	(%RDX,%R8,1),%XMM2,%XMM2

    (55) 0x22cd31 MOV	0x40(%RSI),%RDX

    (55) 0x22cd35 VFMADD213SD	(%R9,%R8,1),%XMM1,%XMM0

    (55) 0x22cd3b VFMADD231PD	-0x10(%R10,%RAX,1),%XMM1,%XMM2

    (55) 0x22cd42 VADDSD	0x10(%RDX,%RDI,8),%XMM0,%XMM0

    (55) 0x22cd48 VADDPD	(%RDX,%RDI,8),%XMM2,%XMM1

    (55) 0x22cd4d MOV	-0x40(%RBP),%RDX

    (55) 0x22cd51 VMOVUPD	%XMM1,-0x10(%RDX,%RAX,1)

    (55) 0x22cd57 VMOVSD	%XMM0,(%RDX,%RAX,1)

    (55) 0x22cd5c ADD	$0x18,%RAX

    (55) 0x22cd60 MOV	0x13f0(%R15),%RDX

    (55) 0x22cd67 SUB	0x13e8(%R15),%RDX

    (55) 0x22cd6e SHR	$0x3,%RDX

    (55) 0x22cd72 IMUL	$-0x55555555,%EDX,%EDX

    (55) 0x22cd78 MOVSXD	%EDX,%RDX

    (55) 0x22cd7b CMP	%RDX,%RCX

    (55) 0x22cd7e JL	22ccf0

  (54) 0x22cd84 MOV	0x1418(%R15),%RAX

  (54) 0x22cd8b MOV	0x18(%RAX),%RAX

  (54) 0x22cd8f MOV	0x1400(%R15),%RCX

  (54) 0x22cd96 MOVSXD	(%RAX,%R12,4),%RAX

  (54) 0x22cd9a MOV	(%RCX,%RAX,8),%RDI

  (54) 0x22cd9e LEA	-0x40(%RBP),%RCX

  (54) 0x22cda2 MOV	$0x1,%R8D

  (54) 0x22cda8 MOV	%RDI,-0xa8(%RBP)

  (54) 0x22cdaf MOV	%R13D,%EDX

  (54) 0x22cdb2 MOV	%R12D,%R9D

  (54) 0x22cdb5 CALL	2a1090 <_ZN11qmcplusplus18VirtualParticleSet9makeMovesERKNS_11ParticleSetEiRKSt6vectorINS_10TinyVectorIdLj3EEESaIS6_EEbi>

  (54) 0x22cdba MOV	-0x70(%RBP),%RDI

  (54) 0x22cdbe MOV	-0xa8(%RBP),%RSI

  (54) 0x22cdc5 LEA	-0x60(%RBP),%RDX

  (54) 0x22cdc9 CALL	230720 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE>

  (54) 0x22cdce JMP	22cca0

0x22cdd3 MOV	-0x60(%RBP),%R12

0x22cdd7 TEST	%R12,%R12

0x22cdda JE	22cde4

0x22cddc MOV	%R12,%RDI

0x22cddf CALL	2f6c70 <@plt_start@+0x30>

0x22cde4 MOV	-0x40(%RBP),%RDI

0x22cde8 TEST	%RDI,%RDI

0x22cdeb JE	22cdf2

0x22cded CALL	2f6c70 <@plt_start@+0x30>

0x22cdf2 LEA	0xcb87f(%RIP),%RAX

0x22cdf9 MOV	%RAX,-0x98(%RBP)

0x22ce00 CMPQ	$0,-0x88(%RBP)

0x22ce08 JE	22ce13

0x22ce0a MOV	-0x80(%RBP),%RDI

0x22ce0e CALL	2f6c70 <@plt_start@+0x30>

0x22ce13 ADD	$0x88,%RSP

0x22ce1a POP	%RBX

0x22ce1b POP	%R12

0x22ce1d POP	%R13

0x22ce1f POP	%R14

0x22ce21 POP	%R15

0x22ce23 POP	%RBP

0x22ce24 RET

0x22ce25 CALL	2f6e40 <@plt_start@+0x200>

0x22ce2a LEA	-0x24ce0(%RIP),%RDI

0x22ce31 CALL	2f6c80 <@plt_start@+0x40>

0x22ce36 LEA	-0x24cec(%RIP),%RDI

0x22ce3d CALL	2f6c80 <@plt_start@+0x40>

0x22ce42 JMP	22ce75

0x22ce44 JMP	22ce75

0x22ce46 MOV	%RAX,%RBX

0x22ce49 MOV	-0x40(%RBP),%RDI

0x22ce4d TEST	%RDI,%RDI

0x22ce50 JE	22ce86

0x22ce52 JMP	22ceb7

0x22ce54 MOV	%RAX,%RBX

0x22ce57 LEA	0xcb81a(%RIP),%RAX

0x22ce5e MOV	%RAX,-0x98(%RBP)

0x22ce65 CMPQ	$0,-0x88(%RBP)

0x22ce6d JE	22ce9e

0x22ce6f JMP	22ced4

0x22ce71 MOV	-0x60(%RBP),%R12

0x22ce75 MOV	%RAX,%RBX

0x22ce78 TEST	%R12,%R12

0x22ce7b JNE	22cea6

0x22ce7d MOV	-0x40(%RBP),%RDI

0x22ce81 TEST	%RDI,%RDI

0x22ce84 JNE	22ceb7

(52) 0x22ce86 LEA	0xcb7eb(%RIP),%RAX

(52) 0x22ce8d MOV	%RAX,-0x98(%RBP)

(52) 0x22ce94 CMPQ	$0,-0x88(%RBP)

(52) 0x22ce9c JNE	22ced4

(52) 0x22ce9e MOV	%RBX,%RDI

(52) 0x22cea1 CALL	2f6c90 <@plt_start@+0x50>

(52) 0x22cea6 MOV	%R12,%RDI

(52) 0x22cea9 CALL	2f6c70 <@plt_start@+0x30>

(52) 0x22ceae MOV	-0x40(%RBP),%RDI

(52) 0x22ceb2 TEST	%RDI,%RDI

(52) 0x22ceb5 JE	22ce86

(52) 0x22ceb7 CALL	2f6c70 <@plt_start@+0x30>

(52) 0x22cebc LEA	0xcb7b5(%RIP),%RAX

(52) 0x22cec3 MOV	%RAX,-0x98(%RBP)

(52) 0x22ceca CMPQ	$0,-0x88(%RBP)

(52) 0x22ced2 JE	22ce9e

0x22ced4 MOV	-0x80(%RBP),%RDI

0x22ced8 CALL	2f6c70 <@plt_start@+0x30>

0x22cedd MOV	%RBX,%RDI

0x22cee0 CALL	2f6c90 <@plt_start@+0x50>

0x22cee5 INT	$0x3

0x22cee6 INT	$0x3

0x22cee7 INT	$0x3

0x22cee8 INT	$0x3

0x22cee9 INT	$0x3

0x22ceea INT	$0x3

0x22ceeb INT	$0x3

0x22ceec INT	$0x3

0x22ceed INT	$0x3

0x22ceee INT	$0x3

0x22ceef INT	$0x3

Coverage (%)	Name	Source Location	Module
►96.44+	main.omp_outlined.64	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►2.89+	main.omp_outlined.64	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_fork_call		libomp.so
○	__kmpc_fork_call		libomp.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		libc.so.6

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

Path /

Average path: Display a virtual path defined by average values of all real paths

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run orig_0

Source file and lines	NonLocalPP.hpp:115-139
Module	exec

The function is defined in:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_construct.h:119
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:111-116,127,145
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleAttrib.h:34
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:277
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.h:97
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:62,144-145
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:98,335,346,353,361-363,919,1046,1064,1605,1769-1770
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:911-912,923-924,1115
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:46-48,144,210-212,223,229,289,300-302
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_uninitialized.h:578,602
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:115-139
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/unique_ptr.h:173
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:43,63
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:231

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 24.25 to 5.38 cycles (4.51x speedup).

Workaround

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

Vectorization

Your function is not vectorized. Only 12% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your function, you can lower the cost of an iteration from 24.25 to 1.87 cycles (12.97x speedup).

Details

11% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

0% of SSE/AVX loads are used in vector version.
11% of SSE/AVX stores are used in vector version.
0% of SSE/AVX addition or subtraction instructions are used in vector version.
14% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

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

No data for this section

CALL instructions

Detected function call instructions.

Details

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

@plt_start@: 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_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:120
unknown: 10 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:62
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:924
- /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:116
- /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
- /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
void qmcplusplus::NonLocalPP
::randomize
, std::allocator
> > >(qmcplusplus::ParticleAttrib
, std::allocator > >&): 1 occurrences►
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:119

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 156 bytes. The binary function is storing 236 bytes.

General properties

nb instructions	193
nb uops	194
loop length	785
used x86 registers	12
used mmx registers	0
used xmm registers	1
used ymm registers	0
used zmm registers	0
nb stack references	14

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	24.25 cycles
front end	24.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	14.00	14.00	14.00	16.00	16.00	16.00	15.50	15.50	15.50	15.50	0.00	0.00	0.00	0.00	1.50	1.50
cycles	14.00	14.00	14.00	16.00	16.00	16.00	15.50	15.50	15.50	15.50	0.00	0.00	0.00	0.00	1.50	1.50

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	24.25
Dispatch	16.00
Overall L1	24.25

Vectorization ratios

INT

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

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

INT+FP

all	11%
load	0%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	14%

Vector efficiency ratios

INT

all	11%
load	10%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

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

INT+FP

all	12%
load	10%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 24.25 cycles. At this rate:

2% of peak load performance is reached (6.43 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
7% of peak store performance is reached (9.73 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 24.25 to 16.00 cycles (1.52x speedup).

ASM code

In the binary file, the address of the function is: 22ca00

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x88,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x13f0(%RDI),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV $-0x5555555555555555,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOV %RDX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RSI,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RDI,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB 0x13e8(%RDI),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
SAR $0x3,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
IMUL %RBX,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOVSXD %EAX,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAL $0x20,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %R14,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMOVUPD %XMM0,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
TEST %RCX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 22cacd <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0xcd>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JS 22ce25 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x425>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
LEA (,%R14,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%RAX,2),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f6c50 <@plt_start@+0x10>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R14,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOV %R14,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV 0x13f0(%R15),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
SUB 0x13e8(%R15),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
SAR $0x3,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
IMUL %RBX,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RAX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
LEA 0xcbb59(%RIP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x20,%RDX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %RCX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOVL $0,-0x74(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
TEST %RDX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JS 22ce2a <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x42a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVSXD %EAX,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVQ $0,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
VMOVAPD %XMM0,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
JE 22cb57 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x157>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
LEA (,%R14,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%RAX,2),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f6c50 <@plt_start@+0x10>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%R14,%R14,2),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R12,%RDI	1	0	0	0	0	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	0	0	0	0.25	scal (6.3%)
MOV %R13,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
LEA (%R12,%RAX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CALL 2f6df0 <@plt_start@+0x1b0>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV 0x13f0(%R15),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %R13,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB 0x13e8(%R15),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
SAR $0x3,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
IMUL %RBX,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
JMP 22cb6e <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x16e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
SAL $0x3,%R14	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOVQ $0,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
LEA (%R14,%R14,2),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RCX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x20,%RBX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV %R12,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
TEST %RBX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JS 22ce36 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x436>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVSXD %EAX,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVQ $0,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
VMOVAPD %XMM0,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
JE 22cbd8 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1d8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RBX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SHR $0x1d,%R13	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f6c50 <@plt_start@+0x10>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
LEA (%RAX,%R14,8),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RAX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVQ $0,(%RAX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
ADD $0x8,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x100000000,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMP %RAX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JNE 22cbf0 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1f0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 22cbfe <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
SAL $0x3,%R14	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOVQ $0,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV %R14,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 22cbfe <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
ADD $-0x8,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOV %R13,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CALL 2f6df0 <@plt_start@+0x1b0>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV %R14,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA -0x98(%RBP),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R15,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 22c5b0 <_ZN11qmcplusplus10NonLocalPPIdE9randomizeINS_14ParticleAttribINS_10TinyVectorIdLj3EEESaIS5_EEEEEvRT_>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x38(%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOV -0x68(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 27d7e0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV %RAX,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x260(%RBX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
TEST %RCX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 22cdd7 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x3d7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0x1418(%R15),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RBX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 22cc63 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x263>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x60(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %R12,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 22cde4 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x3e4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f6c70 <@plt_start@+0x30>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV -0x40(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 22cdf2 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x3f2>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CALL 2f6c70 <@plt_start@+0x30>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
LEA 0xcb87f(%RIP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMPQ $0,-0x88(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 22ce13 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x413>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x80(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CALL 2f6c70 <@plt_start@+0x30>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
ADD $0x88,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 2f6e40 <@plt_start@+0x200>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
LEA -0x24ce0(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CALL 2f6c80 <@plt_start@+0x40>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
LEA -0x24cec(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CALL 2f6c80 <@plt_start@+0x40>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
JMP 22ce75 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x475>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
JMP 22ce75 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x475>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x40(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 22ce86 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x486>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 22ceb7 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x4b7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0xcb81a(%RIP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMPQ $0,-0x88(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 22ce9e <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x49e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 22ced4 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x4d4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0x60(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R12,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JNE 22cea6 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x4a6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x40(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 22ceb7 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x4b7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x80(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CALL 2f6c70 <@plt_start@+0x30>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f6c90 <@plt_start@+0x50>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				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:115-139
Module	exec

The function is defined in:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_construct.h:119
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/ext/new_allocator.h:111-116,127,145
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleAttrib.h:34
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:277
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.h:97
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:62,144-145
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:98,335,346,353,361-363,919,1046,1064,1605,1769-1770
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:911-912,923-924,1115
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:46-48,144,210-212,223,229,289,300-302
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_uninitialized.h:578,602
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:115-139
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/unique_ptr.h:173
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:43,63
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:231

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 24.25 to 5.38 cycles (4.51x speedup).

Workaround

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

Vectorization

Details

11% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

0% of SSE/AVX loads are used in vector version.
11% of SSE/AVX stores are used in vector version.
0% of SSE/AVX addition or subtraction instructions are used in vector version.
14% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

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

No data for this section

CALL instructions

Detected function call instructions.

Details

@plt_start@: 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_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:120
unknown: 10 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:62
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:924
- /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:116
- /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
- /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
void qmcplusplus::NonLocalPP
::randomize
, std::allocator
> > >(qmcplusplus::ParticleAttrib
, std::allocator > >&): 1 occurrences►
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp:119

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 156 bytes. The binary function is storing 236 bytes.

General properties

nb instructions	193
nb uops	194
loop length	785
used x86 registers	12
used mmx registers	0
used xmm registers	1
used ymm registers	0
used zmm registers	0
nb stack references	14

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	24.25 cycles
front end	24.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	14.00	14.00	14.00	16.00	16.00	16.00	15.50	15.50	15.50	15.50	0.00	0.00	0.00	0.00	1.50	1.50
cycles	14.00	14.00	14.00	16.00	16.00	16.00	15.50	15.50	15.50	15.50	0.00	0.00	0.00	0.00	1.50	1.50

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	24.25
Dispatch	16.00
Overall L1	24.25

Vectorization ratios

INT

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

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

INT+FP

all	11%
load	0%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	14%

Vector efficiency ratios

INT

all	11%
load	10%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

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

INT+FP

all	12%
load	10%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 24.25 cycles. At this rate:

2% of peak load performance is reached (6.43 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
7% of peak store performance is reached (9.73 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: 22ca00

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x88,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x13f0(%RDI),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV $-0x5555555555555555,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOV %RDX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RSI,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RDI,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB 0x13e8(%RDI),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
SAR $0x3,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
IMUL %RBX,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOVSXD %EAX,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAL $0x20,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %R14,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMOVUPD %XMM0,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
TEST %RCX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 22cacd <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0xcd>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JS 22ce25 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x425>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
LEA (,%R14,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%RAX,2),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f6c50 <@plt_start@+0x10>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R14,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOV %R14,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV 0x13f0(%R15),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
SUB 0x13e8(%R15),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
SAR $0x3,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
IMUL %RBX,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RAX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
LEA 0xcbb59(%RIP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x20,%RDX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %RCX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOVL $0,-0x74(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
TEST %RDX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JS 22ce2a <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x42a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVSXD %EAX,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVQ $0,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
VMOVAPD %XMM0,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
JE 22cb57 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x157>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
LEA (,%R14,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%RAX,2),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f6c50 <@plt_start@+0x10>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%R14,%R14,2),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R12,%RDI	1	0	0	0	0	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	0	0	0	0.25	scal (6.3%)
MOV %R13,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
LEA (%R12,%RAX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CALL 2f6df0 <@plt_start@+0x1b0>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV 0x13f0(%R15),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %R13,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB 0x13e8(%R15),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
SAR $0x3,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
IMUL %RBX,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
JMP 22cb6e <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x16e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
SAL $0x3,%R14	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOVQ $0,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
LEA (%R14,%R14,2),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RCX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x20,%RBX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV %R12,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
TEST %RBX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JS 22ce36 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x436>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVSXD %EAX,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVQ $0,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
VMOVAPD %XMM0,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
JE 22cbd8 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1d8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RBX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SHR $0x1d,%R13	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f6c50 <@plt_start@+0x10>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
LEA (%RAX,%R14,8),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RAX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVQ $0,(%RAX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
ADD $0x8,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x100000000,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMP %RAX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JNE 22cbf0 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1f0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 22cbfe <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
SAL $0x3,%R14	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOVQ $0,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV %R14,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 22cbfe <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x1fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
ADD $-0x8,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOV %R13,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CALL 2f6df0 <@plt_start@+0x1b0>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV %R14,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA -0x98(%RBP),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R15,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 22c5b0 <_ZN11qmcplusplus10NonLocalPPIdE9randomizeINS_14ParticleAttribINS_10TinyVectorIdLj3EEESaIS5_EEEEEvRT_>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x38(%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOV -0x68(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 27d7e0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV %RAX,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x260(%RBX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
TEST %RCX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 22cdd7 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x3d7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0x1418(%R15),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RBX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 22cc63 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x263>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x60(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %R12,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 22cde4 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x3e4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f6c70 <@plt_start@+0x30>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV -0x40(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 22cdf2 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x3f2>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CALL 2f6c70 <@plt_start@+0x30>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
LEA 0xcb87f(%RIP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMPQ $0,-0x88(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 22ce13 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x413>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x80(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CALL 2f6c70 <@plt_start@+0x30>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
ADD $0x88,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 2f6e40 <@plt_start@+0x200>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
LEA -0x24ce0(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CALL 2f6c80 <@plt_start@+0x40>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
LEA -0x24cec(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CALL 2f6c80 <@plt_start@+0x40>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
JMP 22ce75 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x475>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
JMP 22ce75 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x475>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x40(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 22ce86 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x486>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 22ceb7 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x4b7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0xcb81a(%RIP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMPQ $0,-0x88(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 22ce9e <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x49e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 22ced4 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x4d4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0x60(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R12,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JNE 22cea6 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x4a6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x40(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 22ceb7 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x4b7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x80(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CALL 2f6c70 <@plt_start@+0x30>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f6c90 <@plt_start@+0x50>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A

Name	Coverage (%)	Time (s)
▼qmcplusplus::NonLocalPP::evaluate(qmcplusplus::ParticleSet const&, qmcplusplus::WaveFunction&)–	0.05	0.08
▼Loop 53 - NonLocalPP.hpp:122-135 - exec–	0.00	0.01
▼Loop 54 - NonLocalPP.hpp:126-135 - exec–	0.04	0.07
○Loop 55 - NonLocalPP.hpp:131-132 - exec	0.00	0.01
○Loop 52 - OhmmsVector.h:144-210 - exec	0.00	0.00
○Loop 56 - stl_algobase.h:911-912 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code