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

	Function: miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int ...	Module: exec	Source: einspline_spo_ref.hpp:172-189 [...]	Coverage: 9.92%

/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]);

/usr/include/c++/11/bits/stl_algobase.h: 431 - 924

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

431: 	    __builtin_memmove(__result, __first, sizeof(_Tp) * _Num);

[...]

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

924: 	*__first = __tmp;

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp: 42 - 74

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

42:   x -= spline_m->x_grid.start;

43:   y -= spline_m->y_grid.start;

44:   z -= spline_m->z_grid.start;

45:   T tx, ty, tz;

46:   int ix, iy, iz;

47:   spline2::getSplineBound(x * spline_m->x_grid.delta_inv, tx, ix, spline_m->x_grid.num - 1);

48:   spline2::getSplineBound(y * spline_m->y_grid.delta_inv, ty, iy, spline_m->y_grid.num - 1);

49:   spline2::getSplineBound(z * spline_m->z_grid.delta_inv, tz, iz, spline_m->z_grid.num - 1);

[...]

57:   const intptr_t ys = spline_m->y_stride;

58:   const intptr_t zs = spline_m->z_stride;

59:

60:   constexpr int simdlen_ = QMC_SIMD_ALIGNMENT/sizeof(T);

61:   constexpr T zero(0);

62:

63:   std::fill(vals, vals + num_splines, zero);

64:

65:   for (size_t i = 0; i < 4; i++)

66:     for (size_t j = 0; j < 4; j++)

67:     {

68:       const T pre00           = a[i] * b[j];

69:       const T* restrict coefs = spline_m->coefs + (ix + i) * xs + (iy + j) * ys + iz * zs;

70: #pragma omp simd aligned(coefs: QMC_SIMD_ALIGNMENT) simdlen(simdlen_)

71:       for (size_t n = 0; n < num_splines; n++)

72:         vals[n] += pre00 *

73:             (c[0] * coefs[n] + c[1] * coefs[n + zs] + c[2] * coefs[n + 2 * zs] +

74:              c[3] * coefs[n + 3 * zs]);

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp: 172 - 189

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

172:     ScopedTimer local_timer(timer);

173:

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

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

176:       MultiBsplineEvalRef::evaluate_v(einsplines[i], u[0], u[1], u[2], psi[i].data(), nSplinesPerBlock);

177:   }

178:

179:   inline void evaluate(const ParticleSet& P, int iat, ValueVector_t& psi_v)

180:   {

181:     evaluate_v(P, iat);

182:

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

184:     {

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

186:       const int first = i * nBlocks;

187:       std::copy_n(psi[i].data(), std::min((i + 1) * nSplinesPerBlock, OrbitalSetSize) - first, psi_v.data() + first);

188:     }

189:   }

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

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

229:     return X[i];

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineData.hpp: 54 - 57

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

54:     a[0] = ((A00 * tx + A01) * tx + A02) * tx + A03;

55:     a[1] = ((A10 * tx + A11) * tx + A12) * tx + A13;

56:     a[2] = ((A20 * tx + A21) * tx + A22) * tx + A23;

57:     a[3] = ((A30 * tx + A31) * tx + A32) * tx + A33;

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

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

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

/usr/include/c++/11/bits/stl_algo.h: 751 - 751

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

751:       if (__n2 <= 0)

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp: 55 - 65

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

55:   if (x < 0)

[...]

62:     ind = static_cast<int>(x);

63:     dx = x - ind;

64:     // upper bound

65:     if (ind > nmax)

/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]; }

0x43e5c0 STP	X29, X30, [SP, #720]!

0x43e5c4 ADD	X29, SP, #0

0x43e5c8 ADRP	X4,

0x43e5cc STP	X25, X26, [SP, #64]

0x43e5d0 ORR	X26, XZR, X0

0x43e5d4 LDR	X0, [X4, #4016]

0x43e5d8 STP	X19, X20, [SP, #16]

0x43e5dc ORR	X20, XZR, X1

0x43e5e0 ORR	W19, WZR, W2

0x43e5e4 LDR	X1, [X26, #840]

0x43e5e8 STP	D8, D9, [SP, #96]

0x43e5ec STP	D10, D11, [SP, #112]

0x43e5f0 STP	D12, D13, [SP, #128]

0x43e5f4 STP	X3, X1, [SP, #208]

0x43e5f8 LDR	X2, [X0]

0x43e5fc STR	X2, [SP, #296]

0x43e600 MOVZ	X2, #0

0x43e604 ORR	X0, XZR, X1

0x43e608 BL	479f20

0x43e60c LDR	W2, [X20, #2436]

0x43e610 CMP	W19, W2

0x43e614 B.EQ	43eb24

0x43e618 LDR	X5, [X20, #1512]

0x43e61c MOVZ	W3, #24

0x43e620 SMADDL	X6, W19, W3, X5

  (756) 0x43e624 LDP	D6, D0, [X6]

  (756) 0x43e628 MOVI	D4, #0

  (756) 0x43e62c MOVZ	X7, #48304

  (756) 0x43e630 LDP	D2, D1, [X26, #232]

  (756) 0x43e634 FMOV	D3, X7

  (756) 0x43e638 LDP	D8, D12, [X26, #208]

  (756) 0x43e63c LDR	D5, [X6, #16]

  (756) 0x43e640 FMUL	D9, D0, D2

  (756) 0x43e644 LDP	D11, D7, [X26, #248]

  (756) 0x43e648 FMUL	D17, D0, D1

  (756) 0x43e64c LDR	D10, [X26, #264]

  (756) 0x43e650 LDR	D27, [X26, #224]

  (756) 0x43e654 FMADD	D13, D6, D8, D9

  (756) 0x43e658 FMADD	D19, D6, D12, D17

  (756) 0x43e65c FMUL	D20, D0, D11

  (756) 0x43e660 LDR	D28, [X26, #272]

  (756) 0x43e664 LDR	W8, [X26, #48]

  (756) 0x43e668 FMADD	D16, D5, D7, D13

  (756) 0x43e66c FMADD	D21, D5, D10, D19

  (756) 0x43e670 FRINTM	D18, D16

  (756) 0x43e674 FMADD	D29, D6, D27, D20

  (756) 0x43e678 FRINTM	D22, D21

  (756) 0x43e67c FMADD	D30, D5, D28, D29

  (756) 0x43e680 FRINTM	D31, D30

  (756) 0x43e684 FCMPE	D16, D4

  (756) 0x43e688 FSUB	D23, D16, S18

  (756) 0x43e68c FSUB	D24, D21, S22

  (756) 0x43e690 FSUB	D6, D30, S31

  (756) 0x43e694 FCCMPE	D16, D3, #4, #4

  (756) 0x43e698 CSINC	W9, WZR, WZR, #13

  (756) 0x43e69c CMP	W9, #0

  (756) 0x43e6a0 FCSEL	D25, D23, D4, #0

  (756) 0x43e6a4 FCMPE	D21, D4

  (756) 0x43e6a8 FCCMPE	D21, D3, #4, #4

  (756) 0x43e6ac CSINC	W10, WZR, WZR, #13

  (756) 0x43e6b0 CMP	W10, #0

  (756) 0x43e6b4 FCSEL	D26, D24, D4, #0

  (756) 0x43e6b8 FCMPE	D30, D4

  (756) 0x43e6bc STR	D26, [SP, #192]

  (756) 0x43e6c0 FCCMPE	D30, D3, #4, #4

  (756) 0x43e6c4 CSINC	W11, WZR, WZR, #13

  (756) 0x43e6c8 CMP	W11, #0

  (756) 0x43e6cc FCSEL	D4, D6, D4, #0

  (756) 0x43e6d0 STP	D4, D25, [SP, #176]

  (756) 0x43e6d4 CMP	W8, #0

  (756) 0x43e6d8 B.LE	43ea7c

(757) 0x43e6dc ORR	X12, XZR, #3840

(757) 0x43e6e0 ORR	X13, XZR, #3840

(757) 0x43e6e4 LDR	X3, [X26, #768]

(757) 0x43e6e8 MOVK	X12, #16325

(757) 0x43e6ec MOVK	X13, #16357

(757) 0x43e6f0 STP	X27, X28, [SP, #80]

(757) 0x43e6f4 SUB	W14, W8, #1

(757) 0x43e6f8 MOVZ	W15, #24

(757) 0x43e6fc FMOV	D12, X12

(757) 0x43e700 FMOV	D11, X13

(757) 0x43e704 ADD	X27, X3, #24

(757) 0x43e708 LDRSW	X19, [X26, #64]

(757) 0x43e70c UMADDL	X16, W14, W15, X27

(757) 0x43e710 STP	X21, X22, [SP, #32]

(757) 0x43e714 LDR	X28, [X26, #744]

(757) 0x43e718 UBFM	X22, X19, #61, #60

(757) 0x43e71c STP	X23, X24, [SP, #48]

(757) 0x43e720 STP	D14, D15, [SP, #144]

(757) 0x43e724 STR	X16, [SP, #200]

(757) 0x43e728 LDR	X20, [X28]

(757) 0x43e72c LDP	D0, D5, [SP, #184]

(757) 0x43e730 LDR	D1, [SP, #176]

(757) 0x43e734 LDR	D15, [X20, #40]

(757) 0x43e738 LDP	D14, D3, [X20, #72]

(757) 0x43e73c LDR	D2, [X20, #120]

(757) 0x43e740 FSUB	D8, D0, S15

(757) 0x43e744 LDR	W17, [X20, #56]

(757) 0x43e748 FSUB	D7, D5, S3

(757) 0x43e74c LDR	X3, [X3]

(757) 0x43e750 FSUB	D9, D1, S2

(757) 0x43e754 FMUL	D10, D8, D14

(757) 0x43e758 FCMPE	D10, #0

(757) 0x43e75c B.MI	43e970

(757) 0x43e760 FCVTZS	W18, D10

(757) 0x43e764 SUB	W21, W17, #1

(757) 0x43e768 CMP	W21, W18

(757) 0x43e76c B.GE	43ea24

(757) 0x43e770 ADRP	X23,

(757) 0x43e774 ADRP	X24,

(757) 0x43e778 MOVI	D15, #0

(757) 0x43e77c FMOV	D27, D11

(757) 0x43e780 SBFM	X21, X21, #0, #31

(757) 0x43e784 LDR	D28, [X23, #1704]

(757) 0x43e788 LDR	D29, [X24, #1712]

(757) 0x43e78c LDR	D30, [X20, #112]

(757) 0x43e790 LDR	W25, [X20, #96]

(757) 0x43e794 FMUL	D31, D7, D30

(757) 0x43e798 FCMPE	D31, #0

(757) 0x43e79c B.MI	43e958

(757) 0x43e7a0 FCVTZS	W30, D31

(757) 0x43e7a4 SUB	W4, W25, #1

(757) 0x43e7a8 CMP	W4, W30

(757) 0x43e7ac B.GE	43e988

(757) 0x43e7b0 ADRP	X0,

(757) 0x43e7b4 ADRP	X1,

(757) 0x43e7b8 MOVI	D8, #0

(757) 0x43e7bc FMOV	D16, D11

(757) 0x43e7c0 SBFM	X6, X4, #0, #31

(757) 0x43e7c4 LDR	D17, [X0, #1704]

(757) 0x43e7c8 LDR	D19, [X1, #1712]

(757) 0x43e7cc LDR	D18, [X20, #152]

(757) 0x43e7d0 LDR	W2, [X20, #136]

(757) 0x43e7d4 FMUL	D9, D9, D18

(757) 0x43e7d8 FCMPE	D9, #0

(757) 0x43e7dc B.MI	43e940

(757) 0x43e7e0 FCVTZS	W5, D9

(757) 0x43e7e4 SUB	W7, W2, #1

(757) 0x43e7e8 CMP	W7, W5

(757) 0x43e7ec B.GE	43e9d0

(757) 0x43e7f0 ADRP	X9,

(757) 0x43e7f4 ADRP	X10,

(757) 0x43e7f8 MOVI	D13, #0

(757) 0x43e7fc FMOV	D10, D11

(757) 0x43e800 SBFM	X11, X7, #0, #31

(757) 0x43e804 LDR	D14, [X9, #1704]

(757) 0x43e808 LDR	D9, [X10, #1712]

(757) 0x43e80c STP	D29, D27, [SP, #240]

(757) 0x43e810 STR	D28, [SP, #256]

(757) 0x43e814 STP	D19, D16, [SP, #272]

(757) 0x43e818 STR	D17, [SP, #288]

(757) 0x43e81c LDP	X25, X23, [X20, #16]

(757) 0x43e820 LDR	X24, [X20, #32]

(757) 0x43e824 CBZ	X22, 43e844

0x43e828 ORR	X0, XZR, X3

0x43e82c ORR	X2, XZR, X22

0x43e830 STP	X6, X11, [SP, #160]

0x43e834 MOVZ	W1, #0

0x43e838 BL	403890

0x43e83c LDP	X6, X11, [SP, #160]

0x43e840 ORR	X3, XZR, X0

(757) 0x43e844 MADD	X13, X21, X25, XZR

(757) 0x43e848 UBFM	X2, X23, #61, #60

(757) 0x43e84c UBFM	X1, X24, #61, #60

(757) 0x43e850 MOVZ	X12, #0

(757) 0x43e854 ADD	X15, SP, #232

(757) 0x43e858 DUP	Z5.D, Z13.D[0]

(757) 0x43e85c DUP	Z23.D, Z9.D[0]

(757) 0x43e860 DUP	Z18.D, Z10.D[0]

(757) 0x43e864 DUP	Z21.D, Z14.D[0]

(757) 0x43e868 LDR	X14, [X20, #8]

(757) 0x43e86c MADD	X4, X24, X11, X13

(757) 0x43e870 CNTD	X24, ALL

(757) 0x43e874 ADD	X11, SP, #264

(757) 0x43e878 WHILELO	P2.D, XZR, X19

(757) 0x43e87c PTRUE	P1.B, ALL

(757) 0x43e880 MADD	X13, X2, X6, X14

(757) 0x43e884 FMOV	D27, D8

(757) 0x43e888 ADD	X16, X13, X4,LSL #3

(757) 0x43e88c MOVZ	X20, #0

(757) 0x43e890 FMUL	D28, D15, D27

(757) 0x43e894 CBZ	X19, 43e8ec

0x43e898 ADD	X17, X16, X1

0x43e89c MOVZ	X30, #0

0x43e8a0 DUP	Z29.D, Z28.D[0]

0x43e8a4 ADD	X18, X17, X1

0x43e8a8 ORR	P0.B, P2/Z, P2.B, P2.B

0x43e8ac ADD	X21, X18, X1

(755) 0x43e8b0 LD1D	{Z7.D}, P0/Z, [X17, X30,LSL #3]

(755) 0x43e8b4 LD1D	{Z16.D}, P0/Z, [X16, X30,LSL #3]

(755) 0x43e8b8 LD1D	{Z2.D}, P0/Z, [X21, X30,LSL #3]

(755) 0x43e8bc LD1D	{Z19.D}, P0/Z, [X18, X30,LSL #3]

(755) 0x43e8c0 LD1D	{Z20.D}, P0/Z, [X3, X30,LSL #3]

(755) 0x43e8c4 FMUL	Z1.D, Z23.D, Z7.D

(755) 0x43e8c8 FMUL	Z17.D, Z21.D, Z2.D

(755) 0x43e8cc FMAD	Z16.D, P1/M, Z5.D, Z1.D

(755) 0x43e8d0 FMAD	Z19.D, P1/M, Z18.D, Z17.D

(755) 0x43e8d4 FADD	Z22.D, Z16.D, Z19.D

(755) 0x43e8d8 FMAD	Z22.D, P1/M, Z29.D, Z20.D

(755) 0x43e8dc ST1D	{Z22.D}, P0, [X3, X30,LSL #3]

(755) 0x43e8e0 ADD	X30, X30, X24

(755) 0x43e8e4 WHILELO	P0.D, X30, X19

(755) 0x43e8e8 B.NE	43e8b0

(757) 0x43e8ec ADD	X16, X16, X2

(757) 0x43e8f0 CMP	X20, #24

(757) 0x43e8f4 B.EQ	43e908

(757) 0x43e8f8 ADD	X14, X20, X11

(757) 0x43e8fc ADD	X20, X20, #8

(757) 0x43e900 LDR	D27, [X14, #8]

(757) 0x43e904 B	43e890

(757) 0x43e908 ADD	X4, X4, X25

(757) 0x43e90c CMP	X12, #24

(757) 0x43e910 B.EQ	43e924

(757) 0x43e914 ADD	X23, X12, X15

(757) 0x43e918 ADD	X12, X12, #8

(757) 0x43e91c LDR	D15, [X23, #8]

(757) 0x43e920 B	43e884

(757) 0x43e924 LDR	X12, [SP, #200]

(757) 0x43e928 ADD	X28, X28, #8

(757) 0x43e92c ORR	X3, XZR, X27

(757) 0x43e930 CMP	X12, X27

(757) 0x43e934 B.EQ	43ea6c

(757) 0x43e938 ADD	X27, X27, #24

(757) 0x43e93c B	43e728

(757) 0x43e940 FMOV	D10, D12

(757) 0x43e944 MOVI	D14, #0

(757) 0x43e948 MOVZ	X11, #0

(757) 0x43e94c FMOV	D9, D11

(757) 0x43e950 FMOV	D13, D12

(757) 0x43e954 B	43e80c

(757) 0x43e958 FMOV	D16, D12

(757) 0x43e95c MOVI	D17, #0

(757) 0x43e960 MOVZ	X6, #0

(757) 0x43e964 FMOV	D19, D11

(757) 0x43e968 FMOV	D8, D12

(757) 0x43e96c B	43e7cc

(757) 0x43e970 FMOV	D27, D12

(757) 0x43e974 MOVI	D28, #0

(757) 0x43e978 MOVZ	X21, #0

(757) 0x43e97c FMOV	D29, D11

(757) 0x43e980 FMOV	D15, D12

(757) 0x43e984 B	43e78c

(757) 0x43e988 SCVTF	D4, W30

(757) 0x43e98c FMOV	D14, #0.5000000

(757) 0x43e990 SBFM	X6, X30, #0, #31

(757) 0x43e994 FMOV	D6, #-0.5000000

(757) 0x43e998 FMOV	D3, #-1.0000000

(757) 0x43e99c FSUB	D0, D31, S4

(757) 0x43e9a0 FMUL	D5, D0, D12

(757) 0x43e9a4 FMSUB	D8, D0, D14, D14

(757) 0x43e9a8 FMUL	D7, D0, D0

(757) 0x43e9ac FMADD	D10, D0, D14, D3

(757) 0x43e9b0 FMADD	D2, D0, D8, D14

(757) 0x43e9b4 FSUB	D1, D14, S5

(757) 0x43e9b8 FMADD	D19, D7, D10, D11

(757) 0x43e9bc FMUL	D17, D5, D7

(757) 0x43e9c0 FMADD	D16, D0, D2, D12

(757) 0x43e9c4 FMADD	D13, D0, D1, D6

(757) 0x43e9c8 FMADD	D8, D0, D13, D12

(757) 0x43e9cc B	43e7cc

(757) 0x43e9d0 SCVTF	D20, W5

(757) 0x43e9d4 ORR	X8, XZR, #3840

(757) 0x43e9d8 FMOV	D22, #0.5000000

(757) 0x43e9dc MOVK	X8, #49093

(757) 0x43e9e0 FMOV	D21, #-0.5000000

(757) 0x43e9e4 FMOV	D23, #-1.0000000

(757) 0x43e9e8 SBFM	X11, X5, #0, #31

(757) 0x43e9ec FMOV	D24, X8

(757) 0x43e9f0 FSUB	D25, D9, S20

(757) 0x43e9f4 FMUL	D26, D25, D24

(757) 0x43e9f8 FMSUB	D30, D25, D22, D22

(757) 0x43e9fc FMUL	D31, D25, D25

(757) 0x43ea00 FMADD	D4, D25, D22, D23

(757) 0x43ea04 FMADD	D6, D25, D30, D22

(757) 0x43ea08 FADD	D3, D26, D22

(757) 0x43ea0c FMADD	D9, D4, D31, D11

(757) 0x43ea10 FNMUL	D14, D26, D31

(757) 0x43ea14 FMADD	D10, D25, D6, D12

(757) 0x43ea18 FMADD	D0, D25, D3, D21

(757) 0x43ea1c FMADD	D13, D25, D0, D12

(757) 0x43ea20 B	43e80c

(757) 0x43ea24 SCVTF	D13, W18

(757) 0x43ea28 FMOV	D16, #0.5000000

(757) 0x43ea2c SBFM	X21, X18, #0, #31

(757) 0x43ea30 FMOV	D17, #-0.5000000

(757) 0x43ea34 FMOV	D18, #-1.0000000

(757) 0x43ea38 FSUB	D19, D10, S13

(757) 0x43ea3c FMUL	D20, D19, D12

(757) 0x43ea40 FMSUB	D21, D19, D16, D16

(757) 0x43ea44 FMUL	D22, D19, D19

(757) 0x43ea48 FMADD	D23, D19, D16, D18

(757) 0x43ea4c FMADD	D24, D19, D21, D16

(757) 0x43ea50 FSUB	D25, D16, S20

(757) 0x43ea54 FMADD	D29, D22, D23, D11

(757) 0x43ea58 FMUL	D28, D20, D22

(757) 0x43ea5c FMADD	D27, D19, D24, D12

(757) 0x43ea60 FMADD	D26, D19, D25, D17

(757) 0x43ea64 FMADD	D15, D19, D26, D12

(757) 0x43ea68 B	43e78c

(757) 0x43ea6c LDP	D14, D15, [SP, #144]

(757) 0x43ea70 LDP	X21, X22, [SP, #32]

(757) 0x43ea74 LDP	X23, X24, [SP, #48]

(757) 0x43ea78 LDP	X27, X28, [SP, #80]

  (756) 0x43ea7c MOVZ	X20, #0

  (756) 0x43ea80 MOVZ	W19, #0

  (756) 0x43ea84 LDR	X0, [SP, #216]

  (756) 0x43ea88 BL	47a180

  (756) 0x43ea8c LDR	W10, [X26, #48]

  (756) 0x43ea90 CMP	W10, #0

  (756) 0x43ea94 B.LE	43eaec

    (758) 0x43ea98 LDR	W0, [X26, #64]

    (758) 0x43ea9c MADD	W15, W10, W19, WZR

    (758) 0x43eaa0 ADD	W19, W19, #1

    (758) 0x43eaa4 LDR	W25, [X26, #8]

    (758) 0x43eaa8 MADD	W1, W19, W0, WZR

    (758) 0x43eaac CMP	W1, W25

    (758) 0x43eab0 CSEL	W2, W1, W25, #13

    (758) 0x43eab4 SUB	W5, W2, W15

    (758) 0x43eab8 CMP	W5, #0

    (758) 0x43eabc B.LE	43eae0

    (758) 0x43eac0 LDR	X8, [SP, #208]

    (758) 0x43eac4 SBFM	X2, X5, #61, #31

    (758) 0x43eac8 LDR	X7, [X26, #768]

    (758) 0x43eacc LDR	X9, [X8, #24]

    (758) 0x43ead0 ADD	X0, X9, W15,SXTW #3

    (758) 0x43ead4 LDR	X1, [X7, X20]

    (758) 0x43ead8 BL	4036e0

    (758) 0x43eadc LDR	W10, [X26, #48]

    (758) 0x43eae0 ADD	X20, X20, #24

    (758) 0x43eae4 CMP	W19, W10

    (758) 0x43eae8 B.LT	43ea98

  (756) 0x43eaec ADRP	X26,

  (756) 0x43eaf0 LDR	X6, [X26, #4016]

  (756) 0x43eaf4 LDR	X2, [SP, #296]

  (756) 0x43eaf8 LDR	X1, [X6]

  (756) 0x43eafc SUBS	X2, X2, X1

  (756) 0x43eb00 MOVZ	X1, #0

  (756) 0x43eb04 B.NE	43eb2c

  (756) 0x43eb08 LDP	X19, X20, [SP, #16]

  (756) 0x43eb0c LDP	X25, X26, [SP, #64]

  (756) 0x43eb10 LDP	D8, D9, [SP, #96]

  (756) 0x43eb14 LDP	D10, D11, [SP, #112]

  (756) 0x43eb18 LDP	D12, D13, [SP, #128]

  (756) 0x43eb1c LDP	X29, X30, [SP], #304

  (756) 0x43eb20 RET

  (756) 0x43eb24 ADD	X6, X20, #2440

  (756) 0x43eb28 B	43e624

0x43eb2c STP	X21, X22, [SP, #32]

0x43eb30 STP	X23, X24, [SP, #48]

0x43eb34 STP	X27, X28, [SP, #80]

0x43eb38 STP	D14, D15, [SP, #144]

0x43eb3c BL	403d80

Coverage (%)	Name	Source Location	Module
►20.10+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:194	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:214	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►19.38+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:194	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:214	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►10.41+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:194	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:214	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►10.41+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:194	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:214	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►10.33+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:194	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:214	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►10.17+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:194	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:214	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►9.69+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:194	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:214	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►9.53+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:194	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:214	exec
○	main._omp_fn.1	refwrap.h:337	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:172-189
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
/usr/include/c++/11/bits/stl_algobase.h:431,923-924
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp:42-49,57-74
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp:172-189
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:229
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineData.hpp:54-57
/usr/include/c++/11/bits/stl_vector.h:1169
/usr/include/c++/11/bits/stl_algo.h:751
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:55,62-65
/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 6.50 to 2.50 cycles (2.60x speedup).

Workaround

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

Vectorization

Your function is poorly vectorized. Only 32% 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 6.50 to 5.83 cycles (1.11x speedup).

Details

37% of VPU instructions are used in vector version (process two or more data elements in vector registers):

0% of VPU addition or subtraction instructions are used in vector version.
0% of VPU fused multiply-add instructions are used in vector version.
22% 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 6.50 to 1.50 cycles (4.33x 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 52 bytes. The binary function is storing 200 bytes.

General properties

nb instructions	43
loop length	172
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

5.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	2.00	2.00	5.75	5.75	5.75	5.75	2.50	2.50	0.00	0.00	6.50	6.50	6.00	4.50	4.50
cycles	2.00	2.00	5.75	5.75	5.75	5.75	2.50	2.50	0.00	0.00	6.50	6.50	6.00	4.50	4.50

Cycles executing div or sqrt instructions

Cycles summary

Front-end	5.38
Overall L1	6.50

Vectorization ratios

all	37%
load	NA (no load vectorizable/vectorized instructions)
store	100%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	22%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 6.50 cycles. At this rate:

8% of peak load performance is reached (8.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
64% of peak store performance is reached (30.77 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 43e5c0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
STP X29, X30, [SP, #720]!	1	0	0	0.25	0.25	0.25	0.25	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	1	0.25
ADRP X4, <4c15c8>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X26, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR X0, [X4, #4016]	1	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	0.50	0.50	0	0.50	0.50	1	0.50
ORR X20, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ORR W19, WZR, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR X1, [X26, #840]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
STP D10, D11, [SP, #112]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
STP D12, D13, [SP, #128]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
STP X3, X1, [SP, #208]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
LDR X2, [X0]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STR X2, [SP, #296]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
MOVZ X2, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ORR X0, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
BL 479f20 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDR W2, [X20, #2436]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP W19, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43eb24 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x564>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR X5, [X20, #1512]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
MOVZ W3, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
SMADDL X6, W19, W3, X5	1	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
ORR X0, XZR, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ORR X2, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STP X6, X11, [SP, #160]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
MOVZ W1, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
BL 403890 <@plt_start@+0x210>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDP X6, X11, [SP, #160]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
ORR X3, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X17, X16, X1	1	0	0	0.25	0.25	0.25	0.25	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	1	0.25
DUP Z29.D, Z28.D[0]	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	2	0.50
ADD X18, X17, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ORR P0.B, P2/Z, P2.B, P2.B	1	0	0	0	0	1	0	0	0	0	0	0	0	0	1	1
ADD X21, X18, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X27, X28, [SP, #80]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP D14, D15, [SP, #144]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
BL 403d80 <@plt_start@+0x700>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50

Source file and lines	einspline_spo_ref.hpp:172-189
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
/usr/include/c++/11/bits/stl_algobase.h:431,923-924
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp:42-49,57-74
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp:172-189
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:229
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineData.hpp:54-57
/usr/include/c++/11/bits/stl_vector.h:1169
/usr/include/c++/11/bits/stl_algo.h:751
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:55,62-65
/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 6.50 to 2.50 cycles (2.60x speedup).

Workaround

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

Vectorization

Details

37% of VPU instructions are used in vector version (process two or more data elements in vector registers):

0% of VPU addition or subtraction instructions are used in vector version.
0% of VPU fused multiply-add instructions are used in vector version.
22% 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 6.50 to 1.50 cycles (4.33x 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 52 bytes. The binary function is storing 200 bytes.

General properties

nb instructions	43
loop length	172
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

5.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	2.00	2.00	5.75	5.75	5.75	5.75	2.50	2.50	0.00	0.00	6.50	6.50	6.00	4.50	4.50
cycles	2.00	2.00	5.75	5.75	5.75	5.75	2.50	2.50	0.00	0.00	6.50	6.50	6.00	4.50	4.50

Cycles executing div or sqrt instructions

Cycles summary

Front-end	5.38
Overall L1	6.50

Vectorization ratios

all	37%
load	NA (no load vectorizable/vectorized instructions)
store	100%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	22%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 6.50 cycles. At this rate:

8% of peak load performance is reached (8.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
64% of peak store performance is reached (30.77 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 43e5c0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
STP X29, X30, [SP, #720]!	1	0	0	0.25	0.25	0.25	0.25	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	1	0.25
ADRP X4, <4c15c8>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X26, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR X0, [X4, #4016]	1	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	0.50	0.50	0	0.50	0.50	1	0.50
ORR X20, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ORR W19, WZR, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR X1, [X26, #840]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
STP D10, D11, [SP, #112]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
STP D12, D13, [SP, #128]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
STP X3, X1, [SP, #208]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
LDR X2, [X0]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STR X2, [SP, #296]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
MOVZ X2, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ORR X0, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
BL 479f20 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDR W2, [X20, #2436]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP W19, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43eb24 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x564>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR X5, [X20, #1512]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
MOVZ W3, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
SMADDL X6, W19, W3, X5	1	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1
ORR X0, XZR, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ORR X2, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STP X6, X11, [SP, #160]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
MOVZ W1, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
BL 403890 <@plt_start@+0x210>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDP X6, X11, [SP, #160]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
ORR X3, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X17, X16, X1	1	0	0	0.25	0.25	0.25	0.25	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	1	0.25
DUP Z29.D, Z28.D[0]	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	2	0.50
ADD X18, X17, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ORR P0.B, P2/Z, P2.B, P2.B	1	0	0	0	0	1	0	0	0	0	0	0	0	0	1	1
ADD X21, X18, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X27, X28, [SP, #80]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP D14, D15, [SP, #144]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
BL 403d80 <@plt_start@+0x700>	1	0.50	0.50	0.50	0.50	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 >&)–	9.92	6.24
○Loop 755 - MultiBsplineRef.hpp:72-74 - exec	9.85	6.2
▼Loop 757 - MultiBsplineRef.hpp:42-73 - exec–	0.06	0.04
▼Loop 756 - ParticleSet.h:217-217 - exec–	0	0
○Loop 758 - einspline_spo_ref.hpp:183-187 - exec	0	0

Report Configuration

Code clean check

Workaround

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

Code clean check

Workaround

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