OV - exec - Function qmcplusplus::WaveFunction::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&)

	Function: qmcplusplus::WaveFunction::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<do ...	Module: exec	Source: WaveFunction.cpp:261-276 [...]	Coverage: 0.01%

/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h: 242 - 249

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

242:   ScopeGuard(TIMER& t) : timer(t) { timer.start(); }

[...]

249:   ~ScopeGuard() { timer.stop(); }

/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_construct.h: 119 - 119

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

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

/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/refwrap.h: 347 - 347

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

347:       { return *_M_data; }

/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.cpp: 261 - 276

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

261: {

262:   assert(VP.getTotalNum() == ratios.size());

263:   if (VP.refPtcl < nelup)

264:     Det_up->evaluateRatios(VP, ratios);

265:   else

266:     Det_dn->evaluateRatios(VP, ratios);

267:

268:   std::vector<valT> t(ratios.size());

269:   for (size_t i = 0; i < Jastrows.size(); i++)

270:   {

271:     ScopedTimer local_timer(jastrow_timers[i]);

272:     Jastrows[i]->evaluateRatios(VP, t);

273:     for (int j = 0; j < ratios.size(); ++j)

274:       ratios[j] *= t[j];

275:   }

276: }

/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_algobase.h: 952 - 1146

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

952: 	*__first = __tmp;

[...]

1146:       if (__n <= 0)

/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/new_allocator.h: 104 - 172

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

104:       ~__new_allocator() _GLIBCXX_USE_NOEXCEPT { }

[...]

151: 	return static_cast<_Tp*>(_GLIBCXX_OPERATOR_NEW(__n * sizeof(_Tp)));

[...]

172: 	_GLIBCXX_OPERATOR_DELETE(_GLIBCXX_SIZED_DEALLOC(__p, __n));

/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_vector.h: 99 - 1920

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

99: 	: _M_start(), _M_finish(), _M_end_of_storage()

[...]

368: 	_M_deallocate(_M_impl._M_start,

369: 		      _M_impl._M_end_of_storage - _M_impl._M_start);

[...]

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

[...]

388: 	if (__p)

[...]

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

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

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

[...]

992:       size() const _GLIBCXX_NOEXCEPT

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

[...]

1128:       operator[](size_type __n) _GLIBCXX_NOEXCEPT

1129:       {

1130: 	__glibcxx_requires_subscript(__n);

1131: 	return *(this->_M_impl._M_start + __n);

[...]

1719: 	this->_M_impl._M_finish =

[...]

1919: 	if (__n > _S_max_size(_Tp_alloc_type(__a)))

1920: 	  __throw_length_error(

0x40fd30 STP	X29, X30, [SP, #912]!

0x40fd34 ADD	X29, SP, #0

0x40fd38 STP	X19, X20, [SP, #16]

0x40fd3c STP	X21, X22, [SP, #32]

0x40fd40 ORR	X22, XZR, X2

0x40fd44 STP	X23, X24, [SP, #48]

0x40fd48 ORR	X23, XZR, X0

0x40fd4c ORR	X24, XZR, X1

0x40fd50 LDR	W0, [X0, #52]

0x40fd54 LDR	W3, [X1, #672]

0x40fd58 STR	X25, [SP, #64]

0x40fd5c CMP	W3, W0

0x40fd60 B.GE	4101e0

0x40fd64 LDR	X0, [X23]

0x40fd68 LDR	X6, [X0]

0x40fd6c LDR	X7, [X6, #72]

0x40fd70 BLR	X7

0x40fd74 LDP	X1, X19, [X22]

0x40fd78 ORR	X2, XZR, #7933

0x40fd7c SUB	X19, X19, X1

0x40fd80 SBFM	X20, X19, #3, #63

0x40fd84 CMP	X19, X2

0x40fd88 B.HI	41024c

0x40fd8c STP	XZR, XZR, [SP, #80]

0x40fd90 STR	XZR, [SP, #96]

0x40fd94 CBZ	X20, 4101f4

0x40fd98 ORR	X0, XZR, X19

0x40fd9c BL	403e80

0x40fda0 ADD	X25, X0, X19

0x40fda4 ORR	X10, XZR, X0

0x40fda8 STR	X0, [SP, #80]

0x40fdac ORR	X21, XZR, X0

0x40fdb0 STR	XZR, [X10], #8

0x40fdb4 STR	X25, [SP, #96]

0x40fdb8 CMP	X20, #1

0x40fdbc B.EQ	410214

0x40fdc0 SUB	X2, X19, #8

0x40fdc4 MOVZ	W1, #0

0x40fdc8 ORR	X0, XZR, X10

0x40fdcc ADD	X20, X23, #16

0x40fdd0 BL	403bd0

0x40fdd4 LDR	X18, [X20, #8]

0x40fdd8 ADD	X13, X25, X0

0x40fddc MOVN	X12, #7

0x40fde0 SUB	X14, X12, X21

0x40fde4 LDR	X0, [X23, #16]

0x40fde8 ADD	X15, X14, X13

0x40fdec STR	X15, [SP, #88]

0x40fdf0 CMP	X0, X18

0x40fdf4 B.EQ	410038

0x40fdf8 MOVZ	X19, #0

0x40fdfc ADD	X23, X23, #88

(197) 0x40fe00 LDR	X21, [X23]

(197) 0x40fe04 UBFM	X25, X19, #61, #60

(197) 0x40fe08 LDR	X21, [X21, X25]

(197) 0x40fe0c ORR	X0, XZR, X21

(197) 0x40fe10 BL	4c43c0

(197) 0x40fe14 LDR	X30, [X20]

(197) 0x40fe18 ADD	X2, SP, #80

(197) 0x40fe1c ORR	X1, XZR, X24

(197) 0x40fe20 LDR	X0, [X30, X25]

(197) 0x40fe24 LDR	X3, [X0]

(197) 0x40fe28 LDR	X4, [X3, #72]

(197) 0x40fe2c BLR	X4

(197) 0x40fe30 LDP	X12, X5, [X22]

(197) 0x40fe34 SUB	X6, X5, X12

(197) 0x40fe38 SBFM	X11, X6, #3, #63

(197) 0x40fe3c CMP	X12, X5

(197) 0x40fe40 B.EQ	41000c

(197) 0x40fe44 LDR	X13, [SP, #80]

(197) 0x40fe48 CMP	X6, #8

(197) 0x40fe4c B.LS	41005c

(197) 0x40fe50 ADD	X7, X13, #8

(197) 0x40fe54 CMP	X12, X7

(197) 0x40fe58 B.EQ	41005c

(197) 0x40fe5c CMP	X6, #0

(197) 0x40fe60 CSINC	X14, X11, XZR, #1

(197) 0x40fe64 UBFM	X2, X14, #1, #63

(197) 0x40fe68 UBFM	X1, X2, #60, #59

(197) 0x40fe6c MOVZ	X18, #0

(197) 0x40fe70 SUB	X8, X1, #16

(197) 0x40fe74 UBFM	X9, X8, #4, #63

(197) 0x40fe78 ADD	X10, X9, #1

(197) 0x40fe7c ANDS	X15, X10, #4224

(197) 0x40fe80 B.EQ	40ff48

(197) 0x40fe84 CMP	X15, #1

(197) 0x40fe88 B.EQ	40ff2c

(197) 0x40fe8c CMP	X15, #2

(197) 0x40fe90 B.EQ	40ff18

(197) 0x40fe94 CMP	X15, #3

(197) 0x40fe98 B.EQ	40ff04

(197) 0x40fe9c CMP	X15, #4

(197) 0x40fea0 B.EQ	40fef0

(197) 0x40fea4 CMP	X15, #5

(197) 0x40fea8 B.EQ	40fedc

(197) 0x40feac CMP	X15, #6

(197) 0x40feb0 B.EQ	40fec8

(197) 0x40feb4 LDR	Q30, [X12]

(197) 0x40feb8 MOVZ	X18, #16

(197) 0x40febc LDR	Q31, [X13]

(197) 0x40fec0 FMUL	V0.2D, V31.2D, V30.2D

(197) 0x40fec4 STR	Q0, [X12]

(197) 0x40fec8 LDR	Q29, [X13, X18]

(197) 0x40fecc LDR	Q28, [X12, X18]

(197) 0x40fed0 FMUL	V1.2D, V29.2D, V28.2D

(197) 0x40fed4 STR	Q1, [X12, X18]

(197) 0x40fed8 ADD	X18, X18, #16

(197) 0x40fedc LDR	Q27, [X13, X18]

(197) 0x40fee0 LDR	Q26, [X12, X18]

(197) 0x40fee4 FMUL	V2.2D, V27.2D, V26.2D

(197) 0x40fee8 STR	Q2, [X12, X18]

(197) 0x40feec ADD	X18, X18, #16

(197) 0x40fef0 LDR	Q25, [X13, X18]

(197) 0x40fef4 LDR	Q24, [X12, X18]

(197) 0x40fef8 FMUL	V3.2D, V25.2D, V24.2D

(197) 0x40fefc STR	Q3, [X12, X18]

(197) 0x40ff00 ADD	X18, X18, #16

(197) 0x40ff04 LDR	Q23, [X13, X18]

(197) 0x40ff08 LDR	Q22, [X12, X18]

(197) 0x40ff0c FMUL	V4.2D, V23.2D, V22.2D

(197) 0x40ff10 STR	Q4, [X12, X18]

(197) 0x40ff14 ADD	X18, X18, #16

(197) 0x40ff18 LDR	Q21, [X13, X18]

(197) 0x40ff1c LDR	Q20, [X12, X18]

(197) 0x40ff20 FMUL	V5.2D, V21.2D, V20.2D

(197) 0x40ff24 STR	Q5, [X12, X18]

(197) 0x40ff28 ADD	X18, X18, #16

(197) 0x40ff2c LDR	Q19, [X13, X18]

(197) 0x40ff30 LDR	Q18, [X12, X18]

(197) 0x40ff34 FMUL	V6.2D, V19.2D, V18.2D

(197) 0x40ff38 STR	Q6, [X12, X18]

(197) 0x40ff3c ADD	X18, X18, #16

(197) 0x40ff40 CMP	X1, X18

(197) 0x40ff44 B.EQ	40fff0

  (200) 0x40ff48 LDR	Q7, [X13, X18]

  (200) 0x40ff4c ADD	X0, X18, #16

  (200) 0x40ff50 ADD	X17, X18, #32

  (200) 0x40ff54 ADD	X16, X18, #48

  (200) 0x40ff58 ADD	X25, X18, #64

  (200) 0x40ff5c LDR	Q16, [X12, X18]

  (200) 0x40ff60 ADD	X30, X18, #80

  (200) 0x40ff64 ADD	X3, X18, #96

  (200) 0x40ff68 ADD	X4, X18, #112

  (200) 0x40ff6c FMUL	V17.2D, V7.2D, V16.2D

  (200) 0x40ff70 STR	Q17, [X12, X18]

  (200) 0x40ff74 ADD	X18, X18, #128

  (200) 0x40ff78 LDR	Q30, [X13, X0]

  (200) 0x40ff7c LDR	Q31, [X12, X0]

  (200) 0x40ff80 FMUL	V0.2D, V30.2D, V31.2D

  (200) 0x40ff84 STR	Q0, [X12, X0]

  (200) 0x40ff88 LDR	Q29, [X13, X17]

  (200) 0x40ff8c LDR	Q28, [X12, X17]

  (200) 0x40ff90 FMUL	V1.2D, V29.2D, V28.2D

  (200) 0x40ff94 STR	Q1, [X12, X17]

  (200) 0x40ff98 LDR	Q27, [X13, X16]

  (200) 0x40ff9c LDR	Q26, [X12, X16]

  (200) 0x40ffa0 FMUL	V2.2D, V27.2D, V26.2D

  (200) 0x40ffa4 STR	Q2, [X12, X16]

  (200) 0x40ffa8 LDR	Q25, [X13, X25]

  (200) 0x40ffac LDR	Q24, [X12, X25]

  (200) 0x40ffb0 FMUL	V3.2D, V25.2D, V24.2D

  (200) 0x40ffb4 STR	Q3, [X12, X25]

  (200) 0x40ffb8 LDR	Q23, [X13, X30]

  (200) 0x40ffbc LDR	Q22, [X12, X30]

  (200) 0x40ffc0 FMUL	V4.2D, V23.2D, V22.2D

  (200) 0x40ffc4 STR	Q4, [X12, X30]

  (200) 0x40ffc8 LDR	Q21, [X13, X3]

  (200) 0x40ffcc LDR	Q20, [X12, X3]

  (200) 0x40ffd0 FMUL	V5.2D, V21.2D, V20.2D

  (200) 0x40ffd4 STR	Q5, [X12, X3]

  (200) 0x40ffd8 LDR	Q19, [X13, X4]

  (200) 0x40ffdc LDR	Q18, [X12, X4]

  (200) 0x40ffe0 FMUL	V6.2D, V19.2D, V18.2D

  (200) 0x40ffe4 STR	Q6, [X12, X4]

  (200) 0x40ffe8 CMP	X1, X18

  (200) 0x40ffec B.NE	40ff48

(197) 0x40fff0 TBZ	W14, #0, 41000c

(197) 0x40fff4 AND	X5, X14, #8127

(197) 0x40fff8 UBFM	X6, X5, #61, #60

(197) 0x40fffc LDR	D7, [X12, X6]

(197) 0x410000 LDR	D16, [X13, X6]

(197) 0x410004 FMUL	D17, D7, D16

(197) 0x410008 STR	D17, [X12, X6]

  (198) 0x41000c ORR	X0, XZR, X21

  (198) 0x410010 ADD	X19, X19, #1

  (198) 0x410014 BL	4c4660

  (198) 0x410018 LDP	X21, X12, [X20]

  (198) 0x41001c SUB	X11, X12, X21

  (198) 0x410020 CMP	X19, X11,ASR #3

  (198) 0x410024 B.CC	40fe00

  (198) 0x410028 LDR	X21, [SP, #80]

  (198) 0x41002c CBZ	X21, 410044

  (198) 0x410030 LDR	X13, [SP, #96]

  (198) 0x410034 SUB	X19, X13, X21

  (198) 0x410038 ORR	X1, XZR, X19

  (198) 0x41003c ORR	X0, XZR, X21

  (198) 0x410040 BL	403d70

  (198) 0x410044 LDR	X25, [SP, #64]

  (198) 0x410048 LDP	X19, X20, [SP, #16]

  (198) 0x41004c LDP	X21, X22, [SP, #32]

  (198) 0x410050 LDP	X23, X24, [SP, #48]

  (198) 0x410054 LDP	X29, X30, [SP], #112

  (198) 0x410058 RET

  (198) 0x41005c LDR	D30, [X12]

  (198) 0x410060 SUB	X7, X11, #1

  (198) 0x410064 MOVZ	X1, #1

  (198) 0x410068 AND	X14, X7, #4224

  (198) 0x41006c LDR	D31, [X13]

  (198) 0x410070 FMUL	D0, D30, D31

  (198) 0x410074 STR	D0, [X12]

  (198) 0x410078 CMP	X11, X1

  (198) 0x41007c B.LS	41000c

  (198) 0x410080 CBZ	X14, 410134

  (198) 0x410084 CMP	X14, #1

  (198) 0x410088 B.EQ	410118

  (198) 0x41008c CMP	X14, #2

  (198) 0x410090 B.EQ	410104

  (198) 0x410094 CMP	X14, #3

  (198) 0x410098 B.EQ	4100f0

  (198) 0x41009c CMP	X14, #4

  (198) 0x4100a0 B.EQ	4100dc

  (198) 0x4100a4 CMP	X14, #5

  (198) 0x4100a8 B.EQ	4100c8

  (198) 0x4100ac CMP	X14, #6

  (198) 0x4100b0 B.NE	410234

  (198) 0x4100b4 LDR	D27, [X12, X1,LSL #3]

  (198) 0x4100b8 LDR	D26, [X13, X1,LSL #3]

  (198) 0x4100bc FMUL	D2, D27, D26

  (198) 0x4100c0 STR	D2, [X12, X1,LSL #3]

  (198) 0x4100c4 ADD	X1, X1, #1

  (198) 0x4100c8 LDR	D25, [X12, X1,LSL #3]

  (198) 0x4100cc LDR	D24, [X13, X1,LSL #3]

  (198) 0x4100d0 FMUL	D3, D25, D24

  (198) 0x4100d4 STR	D3, [X12, X1,LSL #3]

  (198) 0x4100d8 ADD	X1, X1, #1

  (198) 0x4100dc LDR	D23, [X12, X1,LSL #3]

  (198) 0x4100e0 LDR	D22, [X13, X1,LSL #3]

  (198) 0x4100e4 FMUL	D4, D23, D22

  (198) 0x4100e8 STR	D4, [X12, X1,LSL #3]

  (198) 0x4100ec ADD	X1, X1, #1

  (198) 0x4100f0 LDR	D21, [X12, X1,LSL #3]

  (198) 0x4100f4 LDR	D20, [X13, X1,LSL #3]

  (198) 0x4100f8 FMUL	D5, D21, D20

  (198) 0x4100fc STR	D5, [X12, X1,LSL #3]

  (198) 0x410100 ADD	X1, X1, #1

  (198) 0x410104 LDR	D19, [X12, X1,LSL #3]

  (198) 0x410108 LDR	D18, [X13, X1,LSL #3]

  (198) 0x41010c FMUL	D6, D19, D18

  (198) 0x410110 STR	D6, [X12, X1,LSL #3]

  (198) 0x410114 ADD	X1, X1, #1

  (198) 0x410118 LDR	D7, [X12, X1,LSL #3]

  (198) 0x41011c LDR	D16, [X13, X1,LSL #3]

  (198) 0x410120 FMUL	D17, D7, D16

  (198) 0x410124 STR	D17, [X12, X1,LSL #3]

  (198) 0x410128 ADD	X1, X1, #1

  (198) 0x41012c CMP	X11, X1

  (198) 0x410130 B.LS	41000c

    (199) 0x410134 LDR	D30, [X12, X1,LSL #3]

    (199) 0x410138 ADD	X2, X1, #1

    (199) 0x41013c ADD	X10, X1, #2

    (199) 0x410140 ADD	X9, X1, #3

    (199) 0x410144 ADD	X8, X1, #4

    (199) 0x410148 LDR	D31, [X13, X1,LSL #3]

    (199) 0x41014c ADD	X15, X1, #5

    (199) 0x410150 ADD	X18, X1, #6

    (199) 0x410154 ADD	X0, X1, #7

    (199) 0x410158 FMUL	D0, D30, D31

    (199) 0x41015c STR	D0, [X12, X1,LSL #3]

    (199) 0x410160 ADD	X1, X1, #8

    (199) 0x410164 LDR	D29, [X12, X2,LSL #3]

    (199) 0x410168 LDR	D28, [X13, X2,LSL #3]

    (199) 0x41016c FMUL	D1, D29, D28

    (199) 0x410170 STR	D1, [X12, X2,LSL #3]

    (199) 0x410174 LDR	D27, [X12, X10,LSL #3]

    (199) 0x410178 LDR	D26, [X13, X10,LSL #3]

    (199) 0x41017c FMUL	D2, D27, D26

    (199) 0x410180 STR	D2, [X12, X10,LSL #3]

    (199) 0x410184 LDR	D25, [X12, X9,LSL #3]

    (199) 0x410188 LDR	D24, [X13, X9,LSL #3]

    (199) 0x41018c FMUL	D3, D25, D24

    (199) 0x410190 STR	D3, [X12, X9,LSL #3]

    (199) 0x410194 LDR	D23, [X12, X8,LSL #3]

    (199) 0x410198 LDR	D22, [X13, X8,LSL #3]

    (199) 0x41019c FMUL	D4, D23, D22

    (199) 0x4101a0 STR	D4, [X12, X8,LSL #3]

    (199) 0x4101a4 LDR	D21, [X12, X15,LSL #3]

    (199) 0x4101a8 LDR	D20, [X13, X15,LSL #3]

    (199) 0x4101ac FMUL	D5, D21, D20

    (199) 0x4101b0 STR	D5, [X12, X15,LSL #3]

    (199) 0x4101b4 LDR	D19, [X12, X18,LSL #3]

    (199) 0x4101b8 LDR	D18, [X13, X18,LSL #3]

    (199) 0x4101bc FMUL	D6, D19, D18

    (199) 0x4101c0 STR	D6, [X12, X18,LSL #3]

    (199) 0x4101c4 LDR	D7, [X12, X0,LSL #3]

    (199) 0x4101c8 LDR	D16, [X13, X0,LSL #3]

    (199) 0x4101cc FMUL	D17, D7, D16

    (199) 0x4101d0 STR	D17, [X12, X0,LSL #3]

    (199) 0x4101d4 CMP	X11, X1

    (199) 0x4101d8 B.HI	410134

  (198) 0x4101dc B	41000c

0x4101e0 LDR	X0, [X23, #8]

0x4101e4 LDR	X4, [X0]

0x4101e8 LDR	X5, [X4, #72]

0x4101ec BLR	X5

0x4101f0 B	40fd74

0x4101f4 LDR	X9, [X23, #16]

0x4101f8 ADD	X20, X23, #16

0x4101fc STR	XZR, [SP, #96]

0x410200 LDR	X8, [X20, #8]

0x410204 STP	XZR, XZR, [SP, #80]

0x410208 CMP	X9, X8

0x41020c B.NE	40fdf8

0x410210 B	410044

0x410214 LDR	X17, [X23, #16]

0x410218 ADD	X20, X23, #16

0x41021c MOVZ	X19, #8

0x410220 STR	X10, [SP, #88]

0x410224 LDR	X16, [X20, #8]

0x410228 CMP	X16, X17

0x41022c B.NE	40fdf8

0x410230 B	410038

  (198) 0x410234 LDR	D29, [X12, X1,LSL #3]

  (198) 0x410238 LDR	D28, [X13, X1,LSL #3]

  (198) 0x41023c FMUL	D1, D29, D28

  (198) 0x410240 STR	D1, [X12, X1,LSL #3]

  (198) 0x410244 MOVZ	X1, #2

  (198) 0x410248 B	4100b4

0x41024c ADRP	X17,

0x410250 ADD	X0, X17, #136

0x410254 BL	403ec0

0x410258 ORR	X22, XZR, X0

0x41025c B	41026c

0x410260 ORR	X22, XZR, X0

0x410264 ORR	X0, XZR, X21

0x410268 BL	4c4660

0x41026c LDR	X0, [SP, #80]

0x410270 LDR	X16, [SP, #96]

0x410274 SUB	X1, X16, X0

0x410278 CBZ	X0, 410280

0x41027c BL	403d70

0x410280 ORR	X0, XZR, X22

0x410284 BL	403e10

Coverage (%)	Name	Source Location	Module

Path /

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

Source file and lines	WaveFunction.cpp:261-276
Module	exec

The function is defined in:

/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_construct.h:119
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/refwrap.h:347
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.cpp:261-276
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_algobase.h:952,1146
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/new_allocator.h:104,151,172
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_vector.h:99,368-369,380,388,398-400,992-993,1128-1131,1719,1919-1920

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 24% of vector register length is used (average across all VPU instructions). By vectorizing your function, you can lower the cost of an iteration from 11.50 to 1.94 cycles (5.94x speedup).

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized function can use their full power.

Workaround

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

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 11.50 to 4.00 cycles (2.87x speedup).

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 136 bytes. The binary function is storing 160 bytes.

General properties

nb instructions	88
loop length	352
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

11.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	10.00	10.00	11.50	11.50	11.50	11.50	0.00	0.00	0.00	0.00	10.33	10.33	10.33	7.00	7.00
cycles	10.00	10.00	11.50	11.50	11.50	11.50	0.00	0.00	0.00	0.00	10.33	10.33	10.33	7.00	7.00

Execution ports to units layout:

P0:
P1:
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P7 (128 bits): VPU, ALU, FP store data
P8 (128 bits): VPU, ALU, DIV/SQRT
P9 (128 bits): ALU, VPU
P10 (256 bits): store address, load
P11 (256 bits): store address, load
P12 (256 bits): load
P13 (64 bits): store data
P14 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.00
Overall L1	11.50

Vectorization ratios

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
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	0%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 11.50 cycles. At this rate:

12% of peak load performance is reached (11.83 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
28% of peak store performance is reached (13.91 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 40fd30

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P10	P11	P12	P13	P14	Latency	Recip. throughput
STP X29, X30, [SP, #912]!	1	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0.50	0.50	1	0.50
ADD X29, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X22, XZR, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X23, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ORR X24, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR W0, [X0, #52]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR W3, [X1, #672]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STR X25, [SP, #64]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
CMP W3, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.GE 4101e0 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x4b0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDR X0, [X23]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X6, [X0]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X7, [X6, #72]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
BLR X7	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
LDP X1, X19, [X22]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
ORR X2, XZR, #7933	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
SUB X19, X19, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
SBFM X20, X19, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
CMP X19, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.HI 41024c <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x51c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STP XZR, XZR, [SP, #80]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR XZR, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
CBZ X20, 4101f4 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x4c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
BL 403e80 <@plt_start@+0x490>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
ADD X25, X0, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ORR X10, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR X0, [SP, #80]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X21, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR XZR, [X10], #8	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR X25, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
CMP X20, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 410214 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x4e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
SUB X2, X19, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
MOVZ W1, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ORR X0, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X20, X23, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
BL 403bd0 <@plt_start@+0x1e0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
LDR X18, [X20, #8]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X13, X25, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
MOVN X12, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
SUB X14, X12, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR X0, [X23, #16]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X15, X14, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR X15, [SP, #88]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
CMP X0, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 410038 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
MOVZ X19, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X23, X23, #88	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR X0, [X23, #8]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X4, [X0]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X5, [X4, #72]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
BLR X5	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
B 40fd74 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x44>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDR X9, [X23, #16]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X20, X23, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR XZR, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
LDR X8, [X20, #8]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STP XZR, XZR, [SP, #80]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
CMP X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.NE 40fdf8 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0xc8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
B 410044 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x314>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDR X17, [X23, #16]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X20, X23, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
MOVZ X19, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR X10, [SP, #88]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
LDR X16, [X20, #8]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X16, X17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.NE 40fdf8 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0xc8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
B 410038 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ADRP X17, <52c24c>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X0, X17, #136	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
BL 403ec0 <@plt_start@+0x4d0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
ORR X22, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
B 41026c <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x53c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ORR X22, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ORR X0, XZR, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
BL 4c4660 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
LDR X0, [SP, #80]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X16, [SP, #96]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
SUB X1, X16, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
CBZ X0, 410280 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x550>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
BL 403d70 <@plt_start@+0x380>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
BL 403e10 <@plt_start@+0x420>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50

Source file and lines	WaveFunction.cpp:261-276
Module	exec

The function is defined in:

/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_construct.h:119
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/refwrap.h:347
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.cpp:261-276
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_algobase.h:952,1146
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/new_allocator.h:104,151,172
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_vector.h:99,368-369,380,388,398-400,992-993,1128-1131,1719,1919-1920

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized function can use their full power.

Workaround

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

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 11.50 to 4.00 cycles (2.87x speedup).

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 136 bytes. The binary function is storing 160 bytes.

General properties

nb instructions	88
loop length	352
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

11.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	10.00	10.00	11.50	11.50	11.50	11.50	0.00	0.00	0.00	0.00	10.33	10.33	10.33	7.00	7.00
cycles	10.00	10.00	11.50	11.50	11.50	11.50	0.00	0.00	0.00	0.00	10.33	10.33	10.33	7.00	7.00

Execution ports to units layout:

P0:
P1:
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P7 (128 bits): VPU, ALU, FP store data
P8 (128 bits): VPU, ALU, DIV/SQRT
P9 (128 bits): ALU, VPU
P10 (256 bits): store address, load
P11 (256 bits): store address, load
P12 (256 bits): load
P13 (64 bits): store data
P14 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.00
Overall L1	11.50

Vectorization ratios

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
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	0%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 11.50 cycles. At this rate:

12% of peak load performance is reached (11.83 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
28% of peak store performance is reached (13.91 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 40fd30

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P10	P11	P12	P13	P14	Latency	Recip. throughput
STP X29, X30, [SP, #912]!	1	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0.50	0.50	1	0.50
ADD X29, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X22, XZR, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X23, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ORR X24, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR W0, [X0, #52]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR W3, [X1, #672]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STR X25, [SP, #64]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
CMP W3, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.GE 4101e0 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x4b0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDR X0, [X23]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X6, [X0]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X7, [X6, #72]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
BLR X7	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
LDP X1, X19, [X22]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
ORR X2, XZR, #7933	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
SUB X19, X19, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
SBFM X20, X19, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
CMP X19, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.HI 41024c <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x51c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STP XZR, XZR, [SP, #80]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR XZR, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
CBZ X20, 4101f4 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x4c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
BL 403e80 <@plt_start@+0x490>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
ADD X25, X0, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ORR X10, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR X0, [SP, #80]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X21, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR XZR, [X10], #8	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR X25, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
CMP X20, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 410214 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x4e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
SUB X2, X19, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
MOVZ W1, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ORR X0, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X20, X23, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
BL 403bd0 <@plt_start@+0x1e0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
LDR X18, [X20, #8]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X13, X25, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
MOVN X12, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
SUB X14, X12, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR X0, [X23, #16]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X15, X14, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR X15, [SP, #88]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
CMP X0, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 410038 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
MOVZ X19, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X23, X23, #88	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR X0, [X23, #8]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X4, [X0]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X5, [X4, #72]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
BLR X5	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
B 40fd74 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x44>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDR X9, [X23, #16]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X20, X23, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR XZR, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
LDR X8, [X20, #8]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STP XZR, XZR, [SP, #80]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
CMP X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.NE 40fdf8 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0xc8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
B 410044 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x314>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDR X17, [X23, #16]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X20, X23, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
MOVZ X19, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR X10, [SP, #88]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
LDR X16, [X20, #8]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X16, X17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.NE 40fdf8 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0xc8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
B 410038 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ADRP X17, <52c24c>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X0, X17, #136	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
BL 403ec0 <@plt_start@+0x4d0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
ORR X22, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
B 41026c <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x53c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ORR X22, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ORR X0, XZR, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
BL 4c4660 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
LDR X0, [SP, #80]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X16, [SP, #96]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
SUB X1, X16, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
CBZ X0, 410280 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE+0x550>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
BL 403d70 <@plt_start@+0x380>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
BL 403e10 <@plt_start@+0x420>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50

Name	Coverage (%)	Time (s)
▼qmcplusplus::WaveFunction::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)–	0.01	0.01
▼Loop 197 - WaveFunction.cpp:269-276 - exec–	0.01	0.01
○Loop 200 - stl_vector.h:992-1128 - exec	0	0
▼Loop 198 - WaveFunction.cpp:269-276 - exec–	0	0
○Loop 199 - WaveFunction.cpp:273-274 - exec	0	0

Report Configuration

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code