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 (incl. loops): 22.00% \| (excl. loops): 0.02%

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp: 42 - 71

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

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 T zero(0);

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

62:

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

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

65:     {

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

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

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

69:         vals[n] += pre00 *

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

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

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h: 170 - 173

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

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

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

172:       else

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

/home/hbollore/qaas/qaas-runs/174-135-6342/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/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/Tensor.h: 213 - 213

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

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

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 1131 - 1263

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

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

[...]

1263:       { return _M_data_ptr(this->_M_impl._M_start); }

/home/hbollore/qaas/qaas-runs/174-135-6342/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/174-135-6342/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:   }

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_algo.h: 683 - 709

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

683:     { return std::copy(__first, __first + __n, __result); }

[...]

709:       if (__n2 <= 0)

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 229 - 229

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

229:     return X[i];

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp: 53 - 63

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

53:   if (x < 0)

[...]

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

61:     dx = x - ind;

62:     // upper bound

63:     if (ind > nmax)

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 143 - 143

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

143:     return (active_ptcl_ == iat) ? active_pos_ : R[iat];

/home/hbollore/qaas/qaas-runs/174-135-6342/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;

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_algobase.h: 238 - 952

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

238:       if (__b < __a)

[...]

413: 	{ *__to = *__from; }

[...]

451: 	  if (__builtin_expect(_Num > 1, true))

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

[...]

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

952: 	*__first = __tmp;

0x44e2a0 STP	X29, X30, [SP, #736]!

0x44e2a4 ADD	X29, SP, #0

0x44e2a8 STP	X19, X20, [SP, #16]

0x44e2ac ORR	W19, WZR, W2

0x44e2b0 STP	X21, X22, [SP, #32]

0x44e2b4 ORR	X22, XZR, X1

0x44e2b8 STP	X25, X26, [SP, #64]

0x44e2bc ORR	X25, XZR, X0

0x44e2c0 STP	D12, D13, [SP, #128]

0x44e2c4 STP	D14, D15, [SP, #144]

0x44e2c8 LDR	X0, [X0, #856]

0x44e2cc STP	X3, X0, [SP, #208]

0x44e2d0 BL	4be880

0x44e2d4 LDR	W0, [X22, #292]

0x44e2d8 ADD	X3, X22, #296

0x44e2dc CMP	W19, W0

0x44e2e0 B.EQ	44e2f0

0x44e2e4 LDR	X2, [X22, #64]

0x44e2e8 MOVZ	W1, #24

0x44e2ec SMADDL	X3, W19, W1, X2

0x44e2f0 ADD	X4, X25, #216

0x44e2f4 LDP	D25, D31, [X3]

0x44e2f8 MOVI	D27, #0

0x44e2fc MOVZ	X5, #48304

0x44e300 LDP	D29, D30, [X4, #24]

0x44e304 FMOV	D28, X5

0x44e308 LDR	D24, [X25, #216]

0x44e30c LDR	D26, [X3, #16]

0x44e310 FMUL	D0, D31, D29

0x44e314 LDP	D21, D4, [X4, #40]

0x44e318 FMUL	D1, D31, D30

0x44e31c LDP	D20, D23, [X4, #8]

0x44e320 LDP	D22, D6, [X4, #56]

0x44e324 FMADD	D3, D25, D24, D0

0x44e328 FMUL	D7, D31, D21

0x44e32c LDR	W6, [X25, #48]

0x44e330 FMADD	D2, D25, D20, D1

0x44e334 FMADD	D5, D26, D4, D3

0x44e338 FRINTM	D13, D5

0x44e33c FMADD	D15, D25, D23, D7

0x44e340 FMADD	D12, D26, D22, D2

0x44e344 FRINTM	D14, D12

0x44e348 FMADD	D17, D26, D6, D15

0x44e34c FRINTM	D18, D17

0x44e350 FCMPE	D5, D27

0x44e354 FSUB	D16, D5, S13

0x44e358 FSUB	D19, D12, S14

0x44e35c FSUB	D31, D17, S18

0x44e360 FCCMPE	D5, D28, #4, #4

0x44e364 CSINC	W7, WZR, WZR, #13

0x44e368 CMP	W7, #0

0x44e36c FCSEL	D25, D16, D27, #0

0x44e370 FCMPE	D12, D27

0x44e374 FCCMPE	D12, D28, #4, #4

0x44e378 CSINC	W8, WZR, WZR, #13

0x44e37c CMP	W8, #0

0x44e380 FCSEL	D29, D19, D27, #0

0x44e384 FCMPE	D17, D27

0x44e388 STP	D29, D25, [SP, #192]

0x44e38c FCCMPE	D17, D28, #4, #4

0x44e390 CSINC	W9, WZR, WZR, #13

0x44e394 CMP	W9, #0

0x44e398 FCSEL	D27, D31, D27, #0

0x44e39c STR	D27, [SP, #176]

0x44e3a0 CMP	W6, #0

0x44e3a4 B.LE	44e7b8

0x44e3a8 ORR	X10, XZR, #3840

0x44e3ac ORR	X11, XZR, #3840

0x44e3b0 STP	D10, D11, [SP, #112]

0x44e3b4 MOVK	X10, #16325

0x44e3b8 MOVK	X11, #16357

0x44e3bc STP	X23, X24, [SP, #48]

0x44e3c0 FMOV	D11, X10

0x44e3c4 FMOV	D12, X11

0x44e3c8 STP	X27, X28, [SP, #80]

0x44e3cc STP	D8, D9, [SP, #96]

0x44e3d0 LDRSW	X23, [X25, #64]

0x44e3d4 LDR	X27, [X25, #784]

0x44e3d8 LDR	X26, [X25, #760]

0x44e3dc ADD	X12, X26, W6,UXTW #3

0x44e3e0 UBFM	X28, X23, #61, #60

0x44e3e4 STR	X12, [SP, #184]

    (958) 0x44e3e8 LDR	X21, [X26]

    (958) 0x44e3ec LDR	D30, [SP, #200]

    (958) 0x44e3f0 LDR	D20, [SP, #176]

    (958) 0x44e3f4 LDR	D28, [X21, #40]

    (958) 0x44e3f8 LDP	D8, D9, [X21, #72]

    (958) 0x44e3fc LDR	D10, [X21, #120]

    (958) 0x44e400 FSUB	D0, D30, S28

    (958) 0x44e404 LDR	D23, [SP, #192]

    (958) 0x44e408 LDR	X5, [X27]

    (958) 0x44e40c FSUB	D3, D20, S10

    (958) 0x44e410 FMUL	D1, D0, D8

    (958) 0x44e414 FSUB	D2, D23, S9

    (958) 0x44e418 FCMPE	D1, #0

    (958) 0x44e41c B.MI	44e88c

    (958) 0x44e420 LDR	W14, [X21, #56]

    (958) 0x44e424 FCVTZS	W13, D1

    (958) 0x44e428 SUB	W15, W14, #1

    (958) 0x44e42c CMP	W15, W13

    (958) 0x44e430 B.LT	44e8a4

    (958) 0x44e434 ORR	X16, XZR, #3840

    (958) 0x44e438 FRINTZ	D26, D1

    (958) 0x44e43c FSUB	D24, D1, S26

    (958) 0x44e440 FMOV	D21, #0.5000000

    (958) 0x44e444 SBFM	X19, X13, #0, #31

    (958) 0x44e448 MOVK	X16, #49093

    (958) 0x44e44c FMOV	D4, #-0.5000000

    (958) 0x44e450 FMOV	D5, #-1.0000000

    (958) 0x44e454 FMOV	D13, X16

    (958) 0x44e458 FMSUB	D22, D24, D21, D21

    (958) 0x44e45c FMUL	D6, D24, D24

    (958) 0x44e460 FMADD	D7, D24, D21, D5

    (958) 0x44e464 FMADD	D16, D24, D22, D21

    (958) 0x44e468 FMUL	D14, D24, D13

    (958) 0x44e46c FMADD	D28, D7, D6, D12

    (958) 0x44e470 FMADD	D29, D24, D16, D11

    (958) 0x44e474 FADD	D15, D14, D21

    (958) 0x44e478 FNMUL	D0, D14, D6

    (958) 0x44e47c FMADD	D17, D24, D15, D4

    (958) 0x44e480 FMADD	D13, D24, D17, D11

    (958) 0x44e484 LDR	D18, [X21, #112]

    (958) 0x44e488 FMUL	D19, D2, D18

    (958) 0x44e48c FCMPE	D19, #0

    (958) 0x44e490 B.MI	44e850

    (958) 0x44e494 LDR	W24, [X21, #96]

    (958) 0x44e498 FCVTZS	W20, D19

    (958) 0x44e49c SUB	W30, W24, #1

    (958) 0x44e4a0 CMP	W30, W20

    (958) 0x44e4a4 B.LT	44e8c4

    (958) 0x44e4a8 ORR	X22, XZR, #3840

    (958) 0x44e4ac FRINTZ	D25, D19

    (958) 0x44e4b0 FSUB	D8, D19, S25

    (958) 0x44e4b4 FMOV	D31, #0.5000000

    (958) 0x44e4b8 SBFM	X7, X20, #0, #31

    (958) 0x44e4bc MOVK	X22, #49093

    (958) 0x44e4c0 FMOV	D27, #-0.5000000

    (958) 0x44e4c4 FMOV	D9, #-1.0000000

    (958) 0x44e4c8 FMOV	D10, X22

    (958) 0x44e4cc FMSUB	D1, D8, D31, D31

    (958) 0x44e4d0 FMUL	D23, D8, D8

    (958) 0x44e4d4 FMADD	D20, D8, D31, D9

    (958) 0x44e4d8 FMADD	D2, D8, D1, D31

    (958) 0x44e4dc FMUL	D30, D8, D10

    (958) 0x44e4e0 FMADD	D5, D20, D23, D12

    (958) 0x44e4e4 FMADD	D21, D8, D2, D11

    (958) 0x44e4e8 FADD	D26, D30, D31

    (958) 0x44e4ec FNMUL	D4, D30, D23

    (958) 0x44e4f0 FMADD	D24, D8, D26, D27

    (958) 0x44e4f4 FMADD	D15, D8, D24, D11

    (958) 0x44e4f8 LDR	D22, [X21, #152]

    (958) 0x44e4fc FMUL	D3, D3, D22

    (958) 0x44e500 FCMPE	D3, #0

    (958) 0x44e504 B.MI	44e874

    (959) 0x44e508 LDR	W3, [X21, #136]

    (959) 0x44e50c FCVTZS	W2, D3

    (959) 0x44e510 SUB	W4, W3, #1

    (959) 0x44e514 CMP	W4, W2

    (959) 0x44e518 B.LT	44e8e4

  (957) 0x44e51c ORR	X8, XZR, #3840

  (957) 0x44e520 FRINTZ	D6, D3

  (957) 0x44e524 FSUB	D7, D3, S6

  (957) 0x44e528 FMOV	D16, #0.5000000

  (957) 0x44e52c SBFM	X6, X2, #0, #31

  (957) 0x44e530 MOVK	X8, #49093

  (957) 0x44e534 FMOV	D14, #-1.0000000

  (957) 0x44e538 FMOV	D17, #-0.5000000

  (957) 0x44e53c FMOV	D19, X8

  (957) 0x44e540 FMSUB	D25, D7, D16, D16

  (957) 0x44e544 FMADD	D8, D7, D16, D14

  (957) 0x44e548 FMUL	D18, D7, D7

  (957) 0x44e54c FMADD	D31, D7, D25, D16

  (957) 0x44e550 FMUL	D9, D7, D19

  (957) 0x44e554 FMADD	D8, D8, D18, D12

  (957) 0x44e558 FMADD	D14, D7, D31, D11

  (957) 0x44e55c FADD	D27, D9, D16

  (957) 0x44e560 FNMUL	D9, D9, D18

  (957) 0x44e564 FMADD	D10, D7, D27, D17

  (957) 0x44e568 FMADD	D10, D7, D10, D11

    (958) 0x44e56c LDR	X22, [X21, #32]

    (958) 0x44e570 STP	D28, D29, [SP, #232]

    (958) 0x44e574 STR	D0, [SP, #248]

    (958) 0x44e578 STP	D5, D21, [SP, #264]

    (958) 0x44e57c STR	D4, [SP, #280]

    (958) 0x44e580 LDP	X20, X24, [X21, #16]

    (958) 0x44e584 CBZ	X28, 44e5a4

    (958) 0x44e588 ORR	X0, XZR, X5

    (958) 0x44e58c ORR	X2, XZR, X28

    (958) 0x44e590 MOVZ	W1, #0

    (958) 0x44e594 STP	X7, X6, [SP, #160]

    (958) 0x44e598 BL	403e90

    (958) 0x44e59c LDP	X7, X6, [SP, #160]

    (958) 0x44e5a0 ORR	X5, XZR, X0

    (958) 0x44e5a4 MADD	X12, X22, X6, XZR

    (958) 0x44e5a8 LDR	X21, [X21, #8]

    (958) 0x44e5ac CBZ	X23, 44e794

    (958) 0x44e5b0 MADD	X13, X19, X20, XZR

    (958) 0x44e5b4 UBFM	X2, X24, #60, #59

    (958) 0x44e5b8 UBFM	X16, X20, #61, #60

    (958) 0x44e5bc MADD	X19, X7, X24, X24

    (958) 0x44e5c0 ADD	X15, SP, #224

    (958) 0x44e5c4 ADD	X17, SP, #256

    (958) 0x44e5c8 MADD	X14, X7, X24, X12

    (958) 0x44e5cc UBFM	X18, X22, #61, #60

    (958) 0x44e5d0 UBFM	X11, X22, #60, #59

    (958) 0x44e5d4 ADD	X30, X22, X13

    (958) 0x44e5d8 ADD	X0, X22, X22,LSL #1

    (958) 0x44e5dc ADD	X1, X19, X13

    (958) 0x44e5e0 ADD	X3, X1, X12

    (958) 0x44e5e4 ADD	X4, X14, X30

    (958) 0x44e5e8 ADD	X24, X21, X3,LSL #3

    (958) 0x44e5ec UBFM	X10, X0, #61, #60

    (958) 0x44e5f0 ADD	X14, X21, X4,LSL #3

      (962) 0x44e5f4 FMOV	D29, D15

      (962) 0x44e5f8 ADD	X7, X14, X18,LSL #1

      (962) 0x44e5fc ORR	X20, XZR, X17

      (962) 0x44e600 ADD	X8, X18, X14

      (962) 0x44e604 ORR	X6, XZR, X14

      (962) 0x44e608 ORR	X12, XZR, X24

        (963) 0x44e60c LDR	D28, [X20, #8]

        (963) 0x44e610 FMUL	D0, D13, D29

        (963) 0x44e614 SUB	X9, X6, X18

        (963) 0x44e618 ORR	X13, XZR, X12

        (963) 0x44e61c MOVZ	X21, #0

        (963) 0x44e620 FMUL	D1, D13, D28

        (963) 0x44e624 TBZ	W23, #0, 44e690

        (963) 0x44e628 LDR	D30, [X6]

        (963) 0x44e62c MOVZ	X21, #1

        (963) 0x44e630 ADD	X13, X12, #8

        (963) 0x44e634 LDR	D21, [X7]

        (963) 0x44e638 LDR	D23, [X12, X22,LSL #3]

        (963) 0x44e63c LDR	D20, [X12, X10]

        (963) 0x44e640 FMUL	D24, D8, D30

        (963) 0x44e644 LDR	D5, [X8]

        (963) 0x44e648 FMUL	D4, D9, D21

        (963) 0x44e64c LDR	D6, [X9]

        (963) 0x44e650 FMUL	D2, D8, D23

        (963) 0x44e654 LDR	D16, [X12, X11]

        (963) 0x44e658 FMUL	D26, D9, D20

        (963) 0x44e65c LDR	D18, [X12]

        (963) 0x44e660 FMADD	D22, D5, D14, D4

        (963) 0x44e664 FMADD	D7, D6, D10, D24

        (963) 0x44e668 LDR	D3, [X5]

        (963) 0x44e66c FMADD	D17, D14, D16, D26

        (963) 0x44e670 FMADD	D31, D10, D18, D2

        (963) 0x44e674 FADD	D19, D7, D22

        (963) 0x44e678 FADD	D27, D31, D17

        (963) 0x44e67c FMADD	D25, D0, D19, D3

        (963) 0x44e680 FMADD	D29, D1, D27, D25

        (963) 0x44e684 STR	D29, [X5]

        (963) 0x44e688 CMP	X23, X21

        (963) 0x44e68c B.EQ	44e750

          (961) 0x44e690 LDR	D28, [X6, X21,LSL #3]

          (961) 0x44e694 ADD	X30, X13, #8

          (961) 0x44e698 ADD	X19, X21, #1

          (961) 0x44e69c LDR	D23, [X7, X21,LSL #3]

          (961) 0x44e6a0 LDR	D20, [X9, X21,LSL #3]

          (961) 0x44e6a4 LDR	D2, [X8, X21,LSL #3]

          (961) 0x44e6a8 FMUL	D26, D8, D28

          (961) 0x44e6ac LDR	D30, [X13, X22,LSL #3]

          (961) 0x44e6b0 FMUL	D24, D9, D23

          (961) 0x44e6b4 LDR	D21, [X13, X10]

          (961) 0x44e6b8 FMADD	D4, D20, D10, D26

          (961) 0x44e6bc LDR	D22, [X13, X11]

          (961) 0x44e6c0 FMADD	D5, D2, D14, D24

          (961) 0x44e6c4 LDP	D7, D17, [X13], #16

          (961) 0x44e6c8 FMUL	D3, D8, D30

          (961) 0x44e6cc FMUL	D6, D9, D21

          (961) 0x44e6d0 LDR	D25, [X5, X21,LSL #3]

          (961) 0x44e6d4 LDR	D31, [X6, X19,LSL #3]

          (961) 0x44e6d8 FMADD	D16, D10, D7, D3

          (961) 0x44e6dc LDR	D19, [X7, X19,LSL #3]

          (961) 0x44e6e0 FMADD	D18, D14, D22, D6

          (961) 0x44e6e4 LDR	D27, [X9, X19,LSL #3]

          (961) 0x44e6e8 FADD	D29, D4, D5

          (961) 0x44e6ec LDR	D23, [X8, X19,LSL #3]

          (961) 0x44e6f0 FMUL	D20, D8, D31

          (961) 0x44e6f4 LDR	D2, [X30, X22,LSL #3]

          (961) 0x44e6f8 FMUL	D26, D9, D19

          (961) 0x44e6fc LDR	D28, [X30, X10]

          (961) 0x44e700 FMADD	D24, D0, D29, D25

          (961) 0x44e704 FMADD	D30, D27, D10, D20

          (961) 0x44e708 LDR	D21, [X30, X11]

          (961) 0x44e70c FADD	D4, D16, D18

          (961) 0x44e710 FMADD	D5, D23, D14, D26

          (961) 0x44e714 FMUL	D22, D8, D2

          (961) 0x44e718 FMUL	D3, D9, D28

          (961) 0x44e71c FMADD	D6, D1, D4, D24

          (961) 0x44e720 FMADD	D25, D10, D17, D22

          (961) 0x44e724 FMADD	D31, D14, D21, D3

          (961) 0x44e728 FADD	D7, D30, D5

          (961) 0x44e72c STR	D6, [X5, X21,LSL #3]

          (961) 0x44e730 ADD	X21, X21, #2

          (961) 0x44e734 LDR	D17, [X5, X19,LSL #3]

          (961) 0x44e738 FADD	D16, D25, D31

          (961) 0x44e73c FMADD	D19, D0, D7, D17

          (961) 0x44e740 FMADD	D18, D1, D16, D19

          (961) 0x44e744 STR	D18, [X5, X19,LSL #3]

          (961) 0x44e748 CMP	X23, X21

          (961) 0x44e74c B.NE	44e690

        (963) 0x44e750 ADD	X20, X20, #16

        (963) 0x44e754 ADD	X0, SP, #288

        (963) 0x44e758 CMP	X0, X20

        (963) 0x44e75c B.EQ	44e778

        (963) 0x44e760 LDR	D29, [X20]

        (963) 0x44e764 ADD	X12, X12, X2

        (963) 0x44e768 ADD	X6, X6, X2

        (963) 0x44e76c ADD	X8, X8, X2

        (963) 0x44e770 ADD	X7, X7, X2

        (963) 0x44e774 B	44e60c

      (962) 0x44e778 ADD	X15, X15, #8

      (962) 0x44e77c CMP	X17, X15

      (962) 0x44e780 B.EQ	44e794

      (962) 0x44e784 LDR	D13, [X15]

      (962) 0x44e788 ADD	X24, X24, X16

      (962) 0x44e78c ADD	X14, X14, X16

      (962) 0x44e790 B	44e5f4

    (958) 0x44e794 LDR	X24, [SP, #184]

    (958) 0x44e798 ADD	X26, X26, #8

    (958) 0x44e79c ADD	X27, X27, #24

    (958) 0x44e7a0 CMP	X24, X26

    (958) 0x44e7a4 B.NE	44e3e8

(960) 0x44e7a8 LDP	D8, D9, [SP, #96]

(960) 0x44e7ac LDP	X23, X24, [SP, #48]

(960) 0x44e7b0 LDP	X27, X28, [SP, #80]

(960) 0x44e7b4 LDP	D10, D11, [SP, #112]

(960) 0x44e7b8 MOVZ	X19, #0

(960) 0x44e7bc MOVZ	W20, #24

(960) 0x44e7c0 LDR	X0, [SP, #216]

(960) 0x44e7c4 BL	4beb20

(960) 0x44e7c8 LDR	W13, [X25, #48]

(960) 0x44e7cc CMP	W13, #0

(960) 0x44e7d0 B.LE	44e834

  (964) 0x44e7d4 LDR	W3, [X25, #64]

  (964) 0x44e7d8 MADD	W14, W13, W19, WZR

  (964) 0x44e7dc LDR	W1, [X25, #8]

  (964) 0x44e7e0 MADD	W4, W3, W19, W3

  (964) 0x44e7e4 CMP	W4, W1

  (964) 0x44e7e8 CSEL	W8, W4, W1, #13

  (964) 0x44e7ec SUB	W12, W8, W14

  (964) 0x44e7f0 CMP	W12, #0

  (964) 0x44e7f4 B.LE	44e828

  (964) 0x44e7f8 LDR	X6, [SP, #208]

  (964) 0x44e7fc UMADDL	X1, W19, W20, XZR

  (964) 0x44e800 UBFM	X9, X14, #61, #31

  (964) 0x44e804 UBFM	X2, X12, #61, #31

  (964) 0x44e808 LDR	X7, [X25, #784]

  (964) 0x44e80c LDR	X21, [X6, #24]

  (964) 0x44e810 LDR	X1, [X7, X1]

  (964) 0x44e814 ADD	X0, X21, X9

  (964) 0x44e818 CMP	X2, #8

  (964) 0x44e81c B.EQ	44e904

  (964) 0x44e820 BL	403d60

  (964) 0x44e824 LDR	W13, [X25, #48]

  (964) 0x44e828 ADD	X19, X19, #1

  (964) 0x44e82c CMP	W13, W19

  (964) 0x44e830 B.GT	44e7d4

(960) 0x44e834 LDP	D12, D13, [SP, #128]

(960) 0x44e838 LDP	X19, X20, [SP, #16]

(960) 0x44e83c LDP	X21, X22, [SP, #32]

(960) 0x44e840 LDP	X25, X26, [SP, #64]

(960) 0x44e844 LDP	D14, D15, [SP, #144]

(960) 0x44e848 LDP	X29, X30, [SP], #288

(960) 0x44e84c RET

  (957) 0x44e850 LDR	D22, [X21, #152]

  (957) 0x44e854 FMOV	D21, D11

  (957) 0x44e858 MOVI	D4, #0

  (957) 0x44e85c MOVZ	X7, #0

  (957) 0x44e860 FMOV	D5, D12

  (957) 0x44e864 FMOV	D15, D11

  (957) 0x44e868 FMUL	D3, D3, D22

  (957) 0x44e86c FCMPE	D3, #0

  (957) 0x44e870 B.GE	44e508

    (958) 0x44e874 FMOV	D14, D11

    (958) 0x44e878 MOVI	D9, #0

    (958) 0x44e87c MOVZ	X6, #0

    (958) 0x44e880 FMOV	D8, D12

    (958) 0x44e884 FMOV	D10, D11

    (958) 0x44e888 B	44e56c

    (958) 0x44e88c FMOV	D29, D11

    (958) 0x44e890 MOVI	D0, #0

    (958) 0x44e894 MOVZ	X19, #0

    (958) 0x44e898 FMOV	D28, D12

    (958) 0x44e89c FMOV	D13, D11

    (958) 0x44e8a0 B	44e484

    (958) 0x44e8a4 ADRP	X17,

    (958) 0x44e8a8 ADRP	X18,

    (958) 0x44e8ac MOVI	D13, #0

    (958) 0x44e8b0 FMOV	D29, D12

    (958) 0x44e8b4 SBFM	X19, X15, #0, #31

    (958) 0x44e8b8 LDR	D0, [X17, #3896]

    (958) 0x44e8bc LDR	D28, [X18, #3904]

    (958) 0x44e8c0 B	44e484

    (958) 0x44e8c4 ADRP	X0,

    (958) 0x44e8c8 ADRP	X1,

    (958) 0x44e8cc MOVI	D15, #0

    (958) 0x44e8d0 FMOV	D21, D12

    (958) 0x44e8d4 SBFM	X7, X30, #0, #31

    (958) 0x44e8d8 LDR	D4, [X0, #3896]

    (958) 0x44e8dc LDR	D5, [X1, #3904]

    (958) 0x44e8e0 B	44e4f8

  (957) 0x44e8e4 ADRP	X9,

  (957) 0x44e8e8 ADRP	X10,

  (957) 0x44e8ec MOVI	D10, #0

  (957) 0x44e8f0 FMOV	D14, D12

  (957) 0x44e8f4 SBFM	X6, X4, #0, #31

  (957) 0x44e8f8 LDR	D9, [X9, #3896]

  (957) 0x44e8fc LDR	D8, [X10, #3904]

  (957) 0x44e900 B	44e56c

  (964) 0x44e904 LDR	D13, [X1]

  (964) 0x44e908 STR	D13, [X21, X9]

  (964) 0x44e90c B	44e828

0x44e910 HINT	#0

0x44e914 HINT	#0

0x44e918 HINT	#0

0x44e91c HINT	#0

Coverage (%)	Name	Source Location	Module
►50.19+	miniqmcreference::DiracDetermi[...]	SPOSet.h:86	exec
○	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:992	exec
○	main._omp_fn.1	NonLocalPP.hpp:126	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►48.77+	miniqmcreference::DiracDetermi[...]	SPOSet.h:86	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:266	exec
○	main._omp_fn.1	NonLocalPP.hpp:126	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6

min	med	avg	max

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

min	med	avg	max

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

Path /

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

The code analyzed by CQA in that panel excludes loops and represents 0.02% of application time for run gcc_4

Source file and lines	einspline_spo_ref.hpp:172-189
Module	exec

The function is defined in:

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp:42-49,57-71
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170-173
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/Tensor.h:213
/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h:1131,1263
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h:150-152
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp:172-189
/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_algo.h:683,709
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:229
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53,60-63
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:143
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineData.hpp:54-57
/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_algobase.h:238,413,451-452,951-952

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 10.25 to 5.00 cycles (2.05x 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 58% 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 10.25 to 8.08 cycles (1.27x 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.
35% of VPU stores are used in vector version.
0% of VPU addition or subtraction instructions are used in vector version.
0% of VPU multiply 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 10.25 to 0.50 cycles (20.50x 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 140 bytes. The binary function is storing 208 bytes.

Arithmetic intensity

Arithmetic intensity is 0.05 FP operations per loaded or stored byte.

General properties

nb instructions	86
loop length	344
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

10.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	1.50	1.50	4.17	4.17	4.17	4.17	4.17	4.17	8.50	8.50	8.50	8.50	9.33	9.33	9.33	4.00	4.00
cycles	1.50	1.50	4.17	4.17	4.17	4.17	4.17	4.17	8.50	8.50	8.50	8.50	9.33	9.33	9.33	4.00	4.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	10.25
Overall L1	10.25

Vectorization ratios

INT

all	23%
load	50%
store	35%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

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

INT+FP

all	14%
load	50%
store	35%
mul	0%
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 10.25 cycles. At this rate:

14% of peak load performance is reached (13.66 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
42% of peak store performance is reached (20.29 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 44e2a0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #736]!	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ADD X29, SP, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR W19, WZR, W2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR X22, XZR, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
STP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR X25, XZR, X0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
STP D12, D13, [SP, #128]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (100.0%)
STP D14, D15, [SP, #144]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (100.0%)
LDR X0, [X0, #856]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STP X3, X0, [SP, #208]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
BL 4be880 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR W0, [X22, #292]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X3, X22, #296	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP W19, W0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 44e2f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x50>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X2, [X22, #64]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
MOVZ W1, #24	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
SMADDL X3, W19, W1, X2	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
ADD X4, X25, #216	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LDP D25, D31, [X3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (100.0%)
MOVI D27, #0	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
MOVZ X5, #48304	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
LDP D29, D30, [X4, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (100.0%)
FMOV D28, X5	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
LDR D24, [X25, #216]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
LDR D26, [X3, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FMUL D0, D31, D29	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (50.0%)
LDP D21, D4, [X4, #40]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (100.0%)
FMUL D1, D31, D30	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (50.0%)
LDP D20, D23, [X4, #8]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (100.0%)
LDP D22, D6, [X4, #56]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (100.0%)
FMADD D3, D25, D24, D0	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FMUL D7, D31, D21	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (50.0%)
LDR W6, [X25, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
FMADD D2, D25, D20, D1	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FMADD D5, D26, D4, D3	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FRINTM D13, D5	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50	scal (50.0%)
FMADD D15, D25, D23, D7	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FMADD D12, D26, D22, D2	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FRINTM D14, D12	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50	scal (50.0%)
FMADD D17, D26, D6, D15	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FRINTM D18, D17	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50	scal (50.0%)
FCMPE D5, D27	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
FSUB D16, D5, S13	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
FSUB D19, D12, S14	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
FSUB D31, D17, S18	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
FCCMPE D5, D28, #4, #4	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
CSINC W7, WZR, WZR, #13	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
CMP W7, #0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
FCSEL D25, D16, D27, #0	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.25	scal (50.0%)
FCMPE D12, D27	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
FCCMPE D12, D28, #4, #4	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
CSINC W8, WZR, WZR, #13	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
CMP W8, #0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
FCSEL D29, D19, D27, #0	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.25	scal (50.0%)
FCMPE D17, D27	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
STP D29, D25, [SP, #192]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (100.0%)
FCCMPE D17, D28, #4, #4	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
CSINC W9, WZR, WZR, #13	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
CMP W9, #0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
FCSEL D27, D31, D27, #0	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.25	scal (50.0%)
STR D27, [SP, #176]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
CMP W6, #0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LE 44e7b8 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x518>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X10, XZR, #3840	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ORR X11, XZR, #3840	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STP D10, D11, [SP, #112]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (100.0%)
MOVK X10, #16325	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
MOVK X11, #16357	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
FMOV D11, X10	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
FMOV D12, X11	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
STP X27, X28, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
STP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (100.0%)
LDRSW X23, [X25, #64]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X27, [X25, #784]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR X26, [X25, #760]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X12, X26, W6,UXTW #3	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
UBFM X28, X23, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STR X12, [SP, #184]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A

The code analyzed by CQA in that panel excludes loops and represents 0.02% of application time for run gcc_4

Source file and lines	einspline_spo_ref.hpp:172-189
Module	exec

The function is defined in:

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp:42-49,57-71
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170-173
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/Tensor.h:213
/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h:1131,1263
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h:150-152
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp:172-189
/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_algo.h:683,709
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:229
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53,60-63
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:143
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineData.hpp:54-57
/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_algobase.h:238,413,451-452,951-952

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 10.25 to 5.00 cycles (2.05x 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.
35% of VPU stores are used in vector version.
0% of VPU addition or subtraction instructions are used in vector version.
0% of VPU multiply 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 10.25 to 0.50 cycles (20.50x 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 140 bytes. The binary function is storing 208 bytes.

Arithmetic intensity

Arithmetic intensity is 0.05 FP operations per loaded or stored byte.

General properties

nb instructions	86
loop length	344
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

10.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	1.50	1.50	4.17	4.17	4.17	4.17	4.17	4.17	8.50	8.50	8.50	8.50	9.33	9.33	9.33	4.00	4.00
cycles	1.50	1.50	4.17	4.17	4.17	4.17	4.17	4.17	8.50	8.50	8.50	8.50	9.33	9.33	9.33	4.00	4.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	10.25
Overall L1	10.25

Vectorization ratios

INT

all	23%
load	50%
store	35%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

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

INT+FP

all	14%
load	50%
store	35%
mul	0%
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 10.25 cycles. At this rate:

14% of peak load performance is reached (13.66 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
42% of peak store performance is reached (20.29 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 44e2a0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #736]!	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ADD X29, SP, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR W19, WZR, W2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR X22, XZR, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
STP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR X25, XZR, X0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
STP D12, D13, [SP, #128]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (100.0%)
STP D14, D15, [SP, #144]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (100.0%)
LDR X0, [X0, #856]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STP X3, X0, [SP, #208]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
BL 4be880 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR W0, [X22, #292]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X3, X22, #296	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP W19, W0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 44e2f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x50>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X2, [X22, #64]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
MOVZ W1, #24	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
SMADDL X3, W19, W1, X2	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
ADD X4, X25, #216	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LDP D25, D31, [X3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (100.0%)
MOVI D27, #0	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
MOVZ X5, #48304	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
LDP D29, D30, [X4, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (100.0%)
FMOV D28, X5	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
LDR D24, [X25, #216]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
LDR D26, [X3, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FMUL D0, D31, D29	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (50.0%)
LDP D21, D4, [X4, #40]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (100.0%)
FMUL D1, D31, D30	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (50.0%)
LDP D20, D23, [X4, #8]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (100.0%)
LDP D22, D6, [X4, #56]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (100.0%)
FMADD D3, D25, D24, D0	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FMUL D7, D31, D21	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (50.0%)
LDR W6, [X25, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
FMADD D2, D25, D20, D1	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FMADD D5, D26, D4, D3	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FRINTM D13, D5	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50	scal (50.0%)
FMADD D15, D25, D23, D7	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FMADD D12, D26, D22, D2	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FRINTM D14, D12	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50	scal (50.0%)
FMADD D17, D26, D6, D15	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.25	scal (50.0%)
FRINTM D18, D17	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	0	0	3	0.50	scal (50.0%)
FCMPE D5, D27	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
FSUB D16, D5, S13	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
FSUB D19, D12, S14	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
FSUB D31, D17, S18	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
FCCMPE D5, D28, #4, #4	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
CSINC W7, WZR, WZR, #13	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
CMP W7, #0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
FCSEL D25, D16, D27, #0	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.25	scal (50.0%)
FCMPE D12, D27	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
FCCMPE D12, D28, #4, #4	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
CSINC W8, WZR, WZR, #13	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
CMP W8, #0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
FCSEL D29, D19, D27, #0	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.25	scal (50.0%)
FCMPE D17, D27	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
STP D29, D25, [SP, #192]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (100.0%)
FCCMPE D17, D28, #4, #4	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (50.0%)
CSINC W9, WZR, WZR, #13	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
CMP W9, #0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
FCSEL D27, D31, D27, #0	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.25	scal (50.0%)
STR D27, [SP, #176]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
CMP W6, #0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LE 44e7b8 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x518>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X10, XZR, #3840	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ORR X11, XZR, #3840	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STP D10, D11, [SP, #112]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (100.0%)
MOVK X10, #16325	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
MOVK X11, #16357	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
FMOV D11, X10	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
FMOV D12, X11	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (50.0%)
STP X27, X28, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
STP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (100.0%)
LDRSW X23, [X25, #64]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X27, [X25, #784]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR X26, [X25, #760]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X12, X26, W6,UXTW #3	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	N/A
UBFM X28, X23, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STR X12, [SP, #184]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::einspline_spo_ref::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector >&)–	22.00	30.36
▼Loop 960 - einspline_spo_ref.hpp:175-189 - exec–	0.00	0.01
○Loop 964 - einspline_spo_ref.hpp:183-187 - exec	0.00	0.01
▼Loop 957 - MultiBsplineData.hpp:54-57 - exec–	0.00	0.00
▼Loop 958 - MultiBsplineEvalHelper.hpp:53-63 - exec–	0.00	0.01
▼Loop 962 - MultiBsplineRef.hpp:63-71 - exec–	0.00	0.01
▼Loop 963 - MultiBsplineRef.hpp:64-71 - exec–	0.00	0.01
○Loop 961 - MultiBsplineRef.hpp:68-71 - exec	21.98	30.02
○Loop 959 - MultiBsplineRef.hpp:49-49 - exec	0.00	0.00

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