OV - exec - Function miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector<double, std::allocator<double> >&, qmcplusplus::Vector<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, 3u> > >&, qmcplusplus::Vector<double, std::allocator<double> >&)

	Function: miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int ...	Module: exec	Source: einspline_spo_ref.hpp:203-230 [...]	Coverage: 0.22%

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h: 150 - 152

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

150:     return TinyVector<Type_t, 3>(lhs[0] * rhs[0] + lhs[1] * rhs[3] + lhs[2] * rhs[6],

151:                                  lhs[0] * rhs[1] + lhs[1] * rhs[4] + lhs[2] * rhs[7],

152:                                  lhs[0] * rhs[2] + lhs[1] * rhs[5] + lhs[2] * rhs[8]);

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h: 191 - 194

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

191:       if (-std::numeric_limits<T1>::epsilon() < val_dot[i] && val_dot[i] < 0)

192:         val_dot[i] = T1(0.0);

193:       else

194:         val_dot[i] -= std::floor(val_dot[i]);

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 183 - 183

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

183:     return (const_cast<T1&>(a) = b);

/usr/include/c++/11/bits/stl_algobase.h: 230 - 235

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

230:     min(const _Tp& __a, const _Tp& __b)

231:     {

232:       // concept requirements

233:       __glibcxx_function_requires(_LessThanComparableConcept<_Tp>)

234:       //return __b < __a ? __b : __a;

235:       if (__b < __a)

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp: 203 - 230

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

203:     ScopedTimer local_timer(timer);

204:

205:     auto u = Lattice.toUnit_floor(P.activeR(iat));

206:     for (int i = 0; i < nBlocks; ++i)

207:       MultiBsplineEvalRef::evaluate_vgh(einsplines[i], u[0], u[1], u[2], psi[i].data(), grad[i].data(), hess[i].data(),

208:                                         nSplinesPerBlock);

209:   }

210:

211:   inline void evaluate(const ParticleSet& P,

[...]

219:     for (int i = 0; i < nBlocks; ++i)

220:     {

221:       // in real simulation, phase needs to be applied. Here just fake computation

222:       const int first = i * nBlocks;

223:       for (int j = first; j < std::min((i + 1) * nSplinesPerBlock, OrbitalSetSize); j++)

224:       {

225:         psi_v[j]   = psi[i][j - first];

226:         dpsi_v[j]  = grad[i][j - first];

227:         d2psi_v[j] = hess[i].data(0)[j - first];

228:       }

229:     }

230:   }

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 146 - 146

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

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

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 229

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

223:     return X[i];

[...]

229:     return X[i];

/usr/include/c++/11/bits/stl_vector.h: 1046 - 1169

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

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

[...]

1169:       { return _M_data_ptr(this->_M_impl._M_start); }

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 203 - 241

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

203:   const Type_t operator[](size_t i) const { return Type_t(myData + i, nGhosts); }

[...]

237:   T* data() { return myData; }

238:   ///return the base

239:   const T* data() const { return myData; }

240:   ///return the pointer of the i-th components

241:   T* restrict data(size_t i) { return myData + i * nGhosts; }

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h: 242 - 249

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

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

[...]

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

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 217 - 217

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

217:   inline const PosType& activeR(int iat) const { return (activePtcl == iat) ? activePos : R[iat]; }

0x4447e0 STP	X29, X30, [SP, #864]!

0x4447e4 ADD	X29, SP, #0

0x4447e8 STP	X21, X22, [SP, #32]

0x4447ec ORR	X22, XZR, X0

0x4447f0 ORR	X21, XZR, X5

0x4447f4 LDR	X0, [X0, #840]

0x4447f8 STP	X19, X20, [SP, #16]

0x4447fc ORR	X20, XZR, X4

0x444800 STP	X23, X24, [SP, #48]

0x444804 ORR	W24, WZR, W2

0x444808 STP	X25, X26, [SP, #64]

0x44480c ORR	X25, XZR, X1

0x444810 STP	X27, X28, [SP, #80]

0x444814 STP	D8, D9, [SP, #96]

0x444818 STR	D10, [SP, #112]

0x44481c STP	X0, X3, [SP, #128]

0x444820 BL	479f20

0x444824 LDR	W0, [X25, #2436]

0x444828 ADD	X3, X25, #2440

0x44482c CMP	W24, W0

0x444830 B.EQ	444840

0x444834 LDR	X2, [X25, #1512]

0x444838 MOVZ	W1, #24

0x44483c SMADDL	X3, W24, W1, X2

0x444840 LDP	D6, D0, [X3]

0x444844 MOVI	D4, #0

0x444848 MOVZ	X4, #48304

0x44484c LDP	D2, D1, [X22, #232]

0x444850 FMOV	D3, X4

0x444854 LDP	D8, D17, [X22, #208]

0x444858 LDR	D5, [X3, #16]

0x44485c FMUL	D10, D0, D2

0x444860 LDP	D16, D7, [X22, #248]

0x444864 FMUL	D20, D0, D1

0x444868 LDR	D9, [X22, #264]

0x44486c LDR	D28, [X22, #224]

0x444870 FMADD	D18, D6, D8, D10

0x444874 FMADD	D22, D6, D17, D20

0x444878 FMUL	D23, D0, D16

0x44487c LDR	D29, [X22, #272]

0x444880 LDR	W5, [X22, #48]

0x444884 FMADD	D19, D5, D7, D18

0x444888 FMADD	D24, D5, D9, D22

0x44488c FRINTM	D21, D19

0x444890 FMADD	D30, D6, D28, D23

0x444894 FRINTM	D25, D24

0x444898 FMADD	D31, D5, D29, D30

0x44489c FRINTM	D6, D31

0x4448a0 FCMPE	D19, D4

0x4448a4 FSUB	D26, D19, S21

0x4448a8 FSUB	D27, D24, S25

0x4448ac FSUB	D0, D31, S6

0x4448b0 FCCMPE	D19, D3, #4, #4

0x4448b4 CSINC	W6, WZR, WZR, #13

0x4448b8 CMP	W6, #0

0x4448bc FCSEL	D10, D26, D4, #0

0x4448c0 FCMPE	D24, D4

0x4448c4 FCCMPE	D24, D3, #4, #4

0x4448c8 CSINC	W7, WZR, WZR, #13

0x4448cc CMP	W7, #0

0x4448d0 FCSEL	D9, D27, D4, #0

0x4448d4 FCMPE	D31, D4

0x4448d8 FCCMPE	D31, D3, #4, #4

0x4448dc CSINC	W8, WZR, WZR, #13

0x4448e0 CMP	W8, #0

0x4448e4 FCSEL	D8, D0, D4, #0

0x4448e8 CMP	W5, #0

0x4448ec B.LE	4449d8

0x4448f0 ADD	X19, X22, #816

0x4448f4 ADD	X28, X22, #768

0x4448f8 STP	X20, X21, [SP, #144]

0x4448fc MOVZ	X9, #0

0x444900 ADD	X23, X22, #744

0x444904 ORR	X21, XZR, X28

0x444908 MOVZ	X25, #0

0x44490c ORR	X28, XZR, X19

0x444910 MOVZ	X26, #0

0x444914 MOVZ	W24, #0

0x444918 ADD	X27, X22, #792

0x44491c ORR	X20, XZR, X23

0x444920 ORR	X19, XZR, X9

(815) 0x444924 LDR	X12, [X27]

(815) 0x444928 FMOV	D2, D8

(815) 0x44492c FMOV	D1, D9

(815) 0x444930 FMOV	D0, D10

(815) 0x444934 ADD	W24, W24, #1

(815) 0x444938 ADD	X23, X19, #8

(815) 0x44493c LDR	X14, [X28]

(815) 0x444940 LDR	X10, [X20]

(815) 0x444944 ADD	X13, X12, X25

(815) 0x444948 LDR	X11, [X21]

(815) 0x44494c ADD	X15, X14, X25

(815) 0x444950 LDRSW	X4, [X22, #64]

(815) 0x444954 LDR	X0, [X10, X19]

(815) 0x444958 LDR	X1, [X11, X26]

(815) 0x44495c LDR	X2, [X13, #24]

(815) 0x444960 LDR	X3, [X15, #24]

(815) 0x444964 BL	443dc0

(815) 0x444968 LDR	W1, [X22, #48]

(815) 0x44496c ADD	X18, X26, #24

(815) 0x444970 ADD	X0, X25, #40

(815) 0x444974 CMP	W24, W1

(815) 0x444978 B.GE	4449d4

(815) 0x44497c LDR	X3, [X28]

(815) 0x444980 FMOV	D2, D8

(815) 0x444984 FMOV	D1, D9

(815) 0x444988 FMOV	D0, D10

(815) 0x44498c ADD	W24, W24, #1

(815) 0x444990 ADD	X26, X26, #48

(815) 0x444994 LDR	X30, [X27]

(815) 0x444998 ADD	X25, X25, #80

(815) 0x44499c ADD	X19, X23, #8

(815) 0x4449a0 LDR	X16, [X20]

(815) 0x4449a4 ADD	X5, X3, X0

(815) 0x4449a8 LDR	X17, [X21]

(815) 0x4449ac ADD	X2, X30, X0

(815) 0x4449b0 LDRSW	X4, [X22, #64]

(815) 0x4449b4 LDR	X0, [X16, X23]

(815) 0x4449b8 LDR	X1, [X17, X18]

(815) 0x4449bc LDR	X2, [X2, #24]

(815) 0x4449c0 LDR	X3, [X5, #24]

(815) 0x4449c4 BL	443dc0

(815) 0x4449c8 LDR	W4, [X22, #48]

(815) 0x4449cc CMP	W24, W4

(815) 0x4449d0 B.LT	444924

0x4449d4 LDP	X20, X21, [SP, #144]

0x4449d8 LDR	X0, [SP, #128]

0x4449dc BL	47a180

0x4449e0 LDR	W27, [X22, #48]

0x4449e4 CMP	W27, #0

0x4449e8 B.LE	444bfc

0x4449ec LDR	W28, [X22, #64]

0x4449f0 MOVZ	W6, #24

0x4449f4 SBFM	X7, X27, #61, #31

0x4449f8 MOVZ	X24, #0

0x4449fc MOVZ	X23, #0

0x444a00 LDR	W15, [X22, #8]

0x444a04 SMADDL	X14, W27, W6, XZR

0x444a08 MOVZ	X18, #0

0x444a0c MOVZ	X30, #0

0x444a10 MOVZ	W17, #0

0x444a14 STR	X7, [SP, #128]

0x444a18 LDR	X26, [SP, #136]

0x444a1c ORR	W16, WZR, W28

(813) 0x444a20 CMP	W16, W15

(813) 0x444a24 CSEL	W8, W16, W15, #13

(813) 0x444a28 CMP	W17, W8

(813) 0x444a2c B.GE	444bd8

(813) 0x444a30 LDR	X13, [X22, #792]

(813) 0x444a34 SUB	W9, W8, W17

(813) 0x444a38 MOVZ	X0, #0

(813) 0x444a3c ANDS	X25, X9, #4160

(813) 0x444a40 SUB	W19, W9, #1

(813) 0x444a44 LDR	X10, [X26, #24]

(813) 0x444a48 LDR	X2, [X22, #816]

(813) 0x444a4c ADD	X1, X13, X23

(813) 0x444a50 LDRSW	X4, [X1, #8]

(813) 0x444a54 ADD	X7, X10, X30

(813) 0x444a58 LDR	X5, [X1, #24]

(813) 0x444a5c ADD	X3, X2, X23

(813) 0x444a60 LDR	X11, [X21, #24]

(813) 0x444a64 UBFM	X10, X4, #60, #59

(813) 0x444a68 LDR	X13, [X20, #24]

(813) 0x444a6c LDR	X12, [X22, #768]

(813) 0x444a70 ADD	X6, X11, X30

(813) 0x444a74 ADD	X11, X5, X10

(813) 0x444a78 LDR	X9, [X3, #24]

(813) 0x444a7c ADD	X1, X13, X24

(813) 0x444a80 LDR	X8, [X12, X18]

(813) 0x444a84 ADD	X12, X5, X4,LSL #3

(813) 0x444a88 B.EQ	444b28

(813) 0x444a8c CMP	X25, #1

(813) 0x444a90 B.EQ	444af4

(813) 0x444a94 CMP	X25, #2

(813) 0x444a98 B.EQ	444ac8

(813) 0x444a9c LDR	D4, [X8]

(813) 0x444aa0 MOVZ	X0, #1

(813) 0x444aa4 STR	D4, [X7]

(813) 0x444aa8 LDR	D3, [X5, X4,LSL #3]

(813) 0x444aac LDR	D5, [X5, X10]

(813) 0x444ab0 LDR	D17, [X5]

(813) 0x444ab4 STR	D5, [X1, #16]

(813) 0x444ab8 STP	D17, D3, [X1]

(813) 0x444abc ADD	X1, X1, #24

(813) 0x444ac0 LDR	D2, [X9]

(813) 0x444ac4 STR	D2, [X6]

(813) 0x444ac8 LDR	D1, [X8, X0,LSL #3]

(813) 0x444acc STR	D1, [X7, X0,LSL #3]

(813) 0x444ad0 LDR	D16, [X5, X0,LSL #3]

(813) 0x444ad4 LDR	D7, [X12, X0,LSL #3]

(813) 0x444ad8 LDR	D18, [X11, X0,LSL #3]

(813) 0x444adc STP	D16, D7, [X1]

(813) 0x444ae0 ADD	X1, X1, #24

(813) 0x444ae4 STUR	D18, [X1, #504]

(813) 0x444ae8 LDR	D19, [X9, X0,LSL #3]

(813) 0x444aec STR	D19, [X6, X0,LSL #3]

(813) 0x444af0 ADD	X0, X0, #1

(813) 0x444af4 LDR	D20, [X8, X0,LSL #3]

(813) 0x444af8 CMP	X0, X19

(813) 0x444afc STR	D20, [X7, X0,LSL #3]

(813) 0x444b00 LDR	D21, [X5, X0,LSL #3]

(813) 0x444b04 LDR	D22, [X12, X0,LSL #3]

(813) 0x444b08 LDR	D23, [X11, X0,LSL #3]

(813) 0x444b0c STP	D21, D22, [X1]

(813) 0x444b10 ADD	X1, X1, #24

(813) 0x444b14 STUR	D23, [X1, #504]

(813) 0x444b18 LDR	D24, [X9, X0,LSL #3]

(813) 0x444b1c STR	D24, [X6, X0,LSL #3]

(813) 0x444b20 ADD	X0, X0, #1

(813) 0x444b24 B.EQ	444bd8

  (814) 0x444b28 LDR	D25, [X8, X0,LSL #3]

  (814) 0x444b2c ADD	X3, X0, #1

  (814) 0x444b30 ADD	X4, X0, #2

  (814) 0x444b34 ADD	X2, X0, #3

  (814) 0x444b38 ADD	X10, X1, #72

  (814) 0x444b3c STR	D25, [X7, X0,LSL #3]

  (814) 0x444b40 LDR	D26, [X5, X0,LSL #3]

  (814) 0x444b44 LDR	D27, [X12, X0,LSL #3]

  (814) 0x444b48 LDR	D10, [X11, X0,LSL #3]

  (814) 0x444b4c STP	D26, D27, [X1]

  (814) 0x444b50 STR	D10, [X1, #16]

  (814) 0x444b54 LDR	D9, [X9, X0,LSL #3]

  (814) 0x444b58 STR	D9, [X6, X0,LSL #3]

  (814) 0x444b5c ADD	X0, X0, #4

  (814) 0x444b60 LDR	D28, [X8, X3,LSL #3]

  (814) 0x444b64 STR	D28, [X7, X3,LSL #3]

  (814) 0x444b68 LDR	D29, [X5, X3,LSL #3]

  (814) 0x444b6c LDR	D30, [X12, X3,LSL #3]

  (814) 0x444b70 LDR	D31, [X11, X3,LSL #3]

  (814) 0x444b74 STP	D29, D30, [X1, #24]

  (814) 0x444b78 STR	D31, [X1, #40]

  (814) 0x444b7c LDR	D6, [X9, X3,LSL #3]

  (814) 0x444b80 STR	D6, [X6, X3,LSL #3]

  (814) 0x444b84 LDR	D0, [X8, X4,LSL #3]

  (814) 0x444b88 STR	D0, [X7, X4,LSL #3]

  (814) 0x444b8c LDR	D8, [X5, X4,LSL #3]

  (814) 0x444b90 LDR	D4, [X12, X4,LSL #3]

  (814) 0x444b94 LDR	D3, [X11, X4,LSL #3]

  (814) 0x444b98 STP	D8, D4, [X1, #48]

  (814) 0x444b9c ADD	X1, X1, #96

  (814) 0x444ba0 STUR	D3, [X1, #480]

  (814) 0x444ba4 LDR	D5, [X9, X4,LSL #3]

  (814) 0x444ba8 STR	D5, [X6, X4,LSL #3]

  (814) 0x444bac LDR	D17, [X8, X2,LSL #3]

  (814) 0x444bb0 STR	D17, [X7, X2,LSL #3]

  (814) 0x444bb4 LDR	D2, [X5, X2,LSL #3]

  (814) 0x444bb8 LDR	D1, [X12, X2,LSL #3]

  (814) 0x444bbc LDR	D16, [X11, X2,LSL #3]

  (814) 0x444bc0 STUR	D2, [X1, #488]

  (814) 0x444bc4 STP	D1, D16, [X10, #8]

  (814) 0x444bc8 LDR	D7, [X9, X2,LSL #3]

  (814) 0x444bcc STR	D7, [X6, X2,LSL #3]

  (814) 0x444bd0 CMP	X2, X19

  (814) 0x444bd4 B.NE	444b28

(813) 0x444bd8 LDR	X19, [SP, #128]

(813) 0x444bdc ADD	X18, X18, #24

(813) 0x444be0 ADD	W16, W16, W28

(813) 0x444be4 ADD	W17, W17, W27

(813) 0x444be8 ADD	X23, X23, #40

(813) 0x444bec ADD	X24, X24, X14

(813) 0x444bf0 ADD	X30, X30, X19

(813) 0x444bf4 CMP	X14, X18

(813) 0x444bf8 B.NE	444a20

0x444bfc LDP	X19, X20, [SP, #16]

0x444c00 LDP	X21, X22, [SP, #32]

0x444c04 LDP	X23, X24, [SP, #48]

0x444c08 LDP	X25, X26, [SP, #64]

0x444c0c LDP	X27, X28, [SP, #80]

0x444c10 LDP	D8, D9, [SP, #96]

0x444c14 LDR	D10, [SP, #112]

0x444c18 LDP	X29, X30, [SP], #160

0x444c1c RET

Coverage (%)	Name	Source Location	Module
►17.86+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:100	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:202	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►14.29+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:100	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:202	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►14.29+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:100	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:202	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►14.29+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:100	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:202	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►10.71+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:100	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:202	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►7.14+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:100	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:202	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►7.14+	miniqmcreference::DiracDetermi[...]	OhmmsVector.h:144	exec
○	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:238	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:177	exec
○	main._omp_fn.0	miniqmc.cpp:390	exec
○	GOMP_parallel		libomp.so
○	main	stl_vector.h:1043	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►7.14+	miniqmcreference::DiracDetermi[...]	OhmmsVector.h:144	exec
○	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:238	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:177	exec
○	main._omp_fn.0	miniqmc.cpp:390	exec
○	GOMP_parallel		libomp.so
○	main	stl_vector.h:1043	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►3.57+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:100	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:202	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►3.57+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:100	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:202	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec

Path /

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

Source file and lines	einspline_spo_ref.hpp:203-230
Module	exec

The function is defined in:

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h:150-152
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:191-194
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:183
/usr/include/c++/11/bits/stl_algobase.h:230-235
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp:203-211,219-230
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:146
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229
/usr/include/c++/11/bits/stl_vector.h:1046,1169
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:203,237-241
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:217

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 13.63 to 4.33 cycles (3.14x 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 25% of vector register length is used (average across all VPU instructions). By fully vectorizing your function, you can lower the cost of an iteration from 13.63 to 2.56 cycles (5.32x speedup).

Details

14% of VPU instructions are used in vector version (process two or more data elements in vector registers):

50% of VPU loads are used in vector version.
50% of VPU stores are used in vector version.
0% of VPU addition or subtraction instructions are used in vector version.
0% of VPU fused multiply-add instructions are used in vector version.
0% of VPU 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)

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 13.63 to 1.00 cycles (13.62x speedup).

FMA

Detected 6 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

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

The binary function is composed of 18 FP arithmetical operations:

9: addition or subtraction (6 inside FMA instructions)
9: multiply (6 inside FMA instructions)

The binary function is loading 284 bytes. The binary function is storing 160 bytes.

Arithmetic intensity

Arithmetic intensity is 0.04 FP operations per loaded or stored byte.

General properties

nb instructions	109
loop length	436
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

13.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	3.00	3.00	10.75	10.75	10.75	10.75	7.00	7.00	7.00	7.00	12.50	12.17	12.33	4.50	4.50
cycles	3.00	3.00	10.75	10.75	10.75	10.75	7.00	7.00	7.00	7.00	12.50	12.17	12.33	4.50	4.50

Cycles executing div or sqrt instructions

Cycles summary

Front-end	13.63
Overall L1	13.63

Vectorization ratios

all	14%
load	50%
store	50%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	0%
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 13.63 cycles. At this rate:

21% of peak load performance is reached (20.84 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
24% of peak store performance is reached (11.74 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 4447e0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
STP X29, X30, [SP, #864]!	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	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	0	0	0	0	1	0.25
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X22, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X21, XZR, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X0, [X0, #840]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X20, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR W24, WZR, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X25, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X27, X28, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
STR D10, [SP, #112]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
STP X0, X3, [SP, #128]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
BL 479f20 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W0, [X25, #2436]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X3, X25, #2440	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP W24, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.EQ 444840 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x60>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR X2, [X25, #1512]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
MOVZ W1, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SMADDL X3, W24, W1, X2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
LDP D6, D0, [X3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
MOVI D4, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
MOVZ X4, #48304	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDP D2, D1, [X22, #232]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FMOV D3, X4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
LDP D8, D17, [X22, #208]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDR D5, [X3, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FMUL D10, D0, D2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25
LDP D16, D7, [X22, #248]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FMUL D20, D0, D1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25
LDR D9, [X22, #264]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDR D28, [X22, #224]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FMADD D18, D6, D8, D10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FMADD D22, D6, D17, D20	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FMUL D23, D0, D16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25
LDR D29, [X22, #272]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDR W5, [X22, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
FMADD D19, D5, D7, D18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FMADD D24, D5, D9, D22	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FRINTM D21, D19	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50
FMADD D30, D6, D28, D23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FRINTM D25, D24	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50
FMADD D31, D5, D29, D30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FRINTM D6, D31	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50
FCMPE D19, D4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
FSUB D26, D19, S21	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
FSUB D27, D24, S25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
FSUB D0, D31, S6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
FCCMPE D19, D3, #4, #4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
CSINC W6, WZR, WZR, #13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP W6, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
FCSEL D10, D26, D4, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FCMPE D24, D4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
FCCMPE D24, D3, #4, #4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
CSINC W7, WZR, WZR, #13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP W7, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
FCSEL D9, D27, D4, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FCMPE D31, D4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
FCCMPE D31, D3, #4, #4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
CSINC W8, WZR, WZR, #13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP W8, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
FCSEL D8, D0, D4, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
CMP W5, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LE 4449d8 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x1f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X19, X22, #816	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X28, X22, #768	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X20, X21, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
MOVZ X9, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X23, X22, #744	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X21, XZR, X28	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X25, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X28, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X26, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ W24, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X27, X22, #792	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X20, XZR, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X19, XZR, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDP X20, X21, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDR X0, [SP, #128]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
BL 47a180 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W27, [X22, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP W27, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LE 444bfc <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x41c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W28, [X22, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
MOVZ W6, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SBFM X7, X27, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X24, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X23, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR W15, [X22, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
SMADDL X14, W27, W6, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
MOVZ X18, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X30, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ W17, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STR X7, [SP, #128]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
LDR X26, [SP, #136]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ORR W16, WZR, W28	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X27, X28, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDR D10, [SP, #112]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDP X29, X30, [SP], #160	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Source file and lines	einspline_spo_ref.hpp:203-230
Module	exec

The function is defined in:

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h:150-152
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:191-194
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:183
/usr/include/c++/11/bits/stl_algobase.h:230-235
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp:203-211,219-230
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:146
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229
/usr/include/c++/11/bits/stl_vector.h:1046,1169
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:203,237-241
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:217

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 13.63 to 4.33 cycles (3.14x speedup).

Workaround

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

Vectorization

Details

14% of VPU instructions are used in vector version (process two or more data elements in vector registers):

50% of VPU loads are used in vector version.
50% of VPU stores are used in vector version.
0% of VPU addition or subtraction instructions are used in vector version.
0% of VPU fused multiply-add instructions are used in vector version.
0% of VPU 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)

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 13.63 to 1.00 cycles (13.62x speedup).

FMA

Detected 6 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

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

The binary function is composed of 18 FP arithmetical operations:

9: addition or subtraction (6 inside FMA instructions)
9: multiply (6 inside FMA instructions)

The binary function is loading 284 bytes. The binary function is storing 160 bytes.

Arithmetic intensity

Arithmetic intensity is 0.04 FP operations per loaded or stored byte.

General properties

nb instructions	109
loop length	436
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

13.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	3.00	3.00	10.75	10.75	10.75	10.75	7.00	7.00	7.00	7.00	12.50	12.17	12.33	4.50	4.50
cycles	3.00	3.00	10.75	10.75	10.75	10.75	7.00	7.00	7.00	7.00	12.50	12.17	12.33	4.50	4.50

Cycles executing div or sqrt instructions

Cycles summary

Front-end	13.63
Overall L1	13.63

Vectorization ratios

all	14%
load	50%
store	50%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	0%
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 13.63 cycles. At this rate:

21% of peak load performance is reached (20.84 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
24% of peak store performance is reached (11.74 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 4447e0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
STP X29, X30, [SP, #864]!	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	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	0	0	0	0	1	0.25
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X22, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X21, XZR, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X0, [X0, #840]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X20, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR W24, WZR, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X25, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X27, X28, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
STR D10, [SP, #112]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
STP X0, X3, [SP, #128]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
BL 479f20 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W0, [X25, #2436]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X3, X25, #2440	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP W24, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.EQ 444840 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x60>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR X2, [X25, #1512]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
MOVZ W1, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SMADDL X3, W24, W1, X2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
LDP D6, D0, [X3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
MOVI D4, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
MOVZ X4, #48304	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDP D2, D1, [X22, #232]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FMOV D3, X4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
LDP D8, D17, [X22, #208]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDR D5, [X3, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FMUL D10, D0, D2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25
LDP D16, D7, [X22, #248]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FMUL D20, D0, D1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25
LDR D9, [X22, #264]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDR D28, [X22, #224]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FMADD D18, D6, D8, D10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FMADD D22, D6, D17, D20	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FMUL D23, D0, D16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25
LDR D29, [X22, #272]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDR W5, [X22, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
FMADD D19, D5, D7, D18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FMADD D24, D5, D9, D22	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FRINTM D21, D19	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50
FMADD D30, D6, D28, D23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FRINTM D25, D24	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50
FMADD D31, D5, D29, D30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25
FRINTM D6, D31	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50
FCMPE D19, D4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
FSUB D26, D19, S21	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
FSUB D27, D24, S25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
FSUB D0, D31, S6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
FCCMPE D19, D3, #4, #4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
CSINC W6, WZR, WZR, #13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP W6, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
FCSEL D10, D26, D4, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FCMPE D24, D4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
FCCMPE D24, D3, #4, #4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
CSINC W7, WZR, WZR, #13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP W7, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
FCSEL D9, D27, D4, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FCMPE D31, D4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
FCCMPE D31, D3, #4, #4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
CSINC W8, WZR, WZR, #13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP W8, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
FCSEL D8, D0, D4, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
CMP W5, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LE 4449d8 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x1f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X19, X22, #816	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X28, X22, #768	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X20, X21, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
MOVZ X9, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X23, X22, #744	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X21, XZR, X28	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X25, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X28, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X26, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ W24, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X27, X22, #792	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X20, XZR, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X19, XZR, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDP X20, X21, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDR X0, [SP, #128]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
BL 47a180 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W27, [X22, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP W27, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LE 444bfc <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x41c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W28, [X22, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
MOVZ W6, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SBFM X7, X27, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X24, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X23, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR W15, [X22, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
SMADDL X14, W27, W6, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
MOVZ X18, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X30, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ W17, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STR X7, [SP, #128]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
LDR X26, [SP, #136]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ORR W16, WZR, W28	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X27, X28, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDR D10, [SP, #112]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDP X29, X30, [SP], #160	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Name	Coverage (%)	Time (s)
▼miniqmcreference::einspline_spo_ref::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector >&, qmcplusplus::Vector, std::allocator >...–	0.22	0.14
○Loop 815 - einspline_spo_ref.hpp:206-207 - exec	0	0
▼Loop 813 - einspline_spo_ref.hpp:219-227 - exec–	0	0
○Loop 814 - einspline_spo_ref.hpp:223-227 - exec	0.22	0.14

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Expensive FP math instructions/calls

FMA

Workaround

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Expensive FP math instructions/calls

FMA

Workaround

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code