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): 24.62% \| (excl. loops): 0.01%

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 143 - 143

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

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

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

[...]

56:   const intptr_t xs = spline_m->x_stride;

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/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h: 242 - 249

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

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

[...]

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 61 - 61

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

61:     for (size_t d = 0; d < D; ++d)

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../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); }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h: 235 - 924

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

235:       if (__b < __a)

[...]

429: 	  const ptrdiff_t _Num = __last - __first;

430: 	  if (_Num)

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

[...]

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

924: 	*__first = __tmp;

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp: 45 - 47

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

45:   T sf = std::floor(x);

46:   T dx2 = x - sf;

47:   int ind2 = std::min(std::max(0, static_cast<int>(sf)), nmax);

/home/eoseret/qaas_runs_ZEN5/173-938-0042/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/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algo.h: 725 - 751

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

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

[...]

751:       if (__n2 <= 0)

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

0x44dd80 PUSH	%RBP

0x44dd81 MOV	%RSP,%RBP

0x44dd84 PUSH	%R15

0x44dd86 PUSH	%R14

0x44dd88 PUSH	%R13

0x44dd8a PUSH	%R12

0x44dd8c PUSH	%RBX

0x44dd8d SUB	$0x128,%RSP

0x44dd94 MOV	%RCX,%RBX

0x44dd97 MOV	%EDX,%R12D

0x44dd9a MOV	%RSI,%R13

0x44dd9d MOV	%RDI,%R14

0x44dda0 MOV	0x358(%RDI),%RDI

0x44dda7 MOV	%RDI,-0xd0(%RBP)

0x44ddae CALL	4a9a00 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>

0x44ddb3 MOVSXD	%R12D,%RAX

0x44ddb6 LEA	(%RAX,%RAX,2),%RCX

0x44ddba SAL	$0x3,%RCX

0x44ddbe ADD	0x40(%R13),%RCX

0x44ddc2 CMP	%EAX,0x124(%R13)

0x44ddc9 LEA	0x128(%R13),%RAX

0x44ddd0 CMOVNE	%RCX,%RAX

0x44ddd4 MOVSD	(%RAX),%XMM0

0x44ddd8 MOVSD	0x8(%RAX),%XMM3

0x44dddd MOVSD	0xd8(%R14),%XMM1

0x44dde6 MULSD	%XMM0,%XMM1

0x44ddea MOVSD	0xf0(%R14),%XMM2

0x44ddf3 MULSD	%XMM3,%XMM2

0x44ddf7 ADDSD	%XMM1,%XMM2

0x44ddfb MOVSD	0x10(%RAX),%XMM4

0x44de00 MOVSD	0x108(%R14),%XMM5

0x44de09 MULSD	%XMM4,%XMM5

0x44de0d ADDSD	%XMM2,%XMM5

0x44de11 MOVSD	0xe0(%R14),%XMM1

0x44de1a MULSD	%XMM0,%XMM1

0x44de1e MOVSD	0xf8(%R14),%XMM2

0x44de27 MULSD	%XMM3,%XMM2

0x44de2b ADDSD	%XMM1,%XMM2

0x44de2f MOVSD	0x110(%R14),%XMM1

0x44de38 MULSD	%XMM4,%XMM1

0x44de3c ADDSD	%XMM2,%XMM1

0x44de40 MULSD	0xe8(%R14),%XMM0

0x44de49 MULSD	0x100(%R14),%XMM3

0x44de52 MULSD	0x118(%R14),%XMM4

0x44de5b ADDSD	%XMM0,%XMM3

0x44de5f UCOMISD	0xdeea9(%RIP),%XMM5

0x44de67 MOVSD	%XMM1,-0x60(%RBP)

0x44de6c JBE	44de80

0x44de6e XORPD	%XMM0,%XMM0

0x44de72 MOVSD	%XMM0,-0xb0(%RBP)

0x44de7a UCOMISD	%XMM0,%XMM5

0x44de7e JB	44deb8

0x44de80 MOVAPD	%XMM5,%XMM0

0x44de84 MOVSD	%XMM3,-0x50(%RBP)

0x44de89 MOVSD	%XMM4,-0x38(%RBP)

0x44de8e MOVSD	%XMM5,-0x30(%RBP)

0x44de93 CALL	506a50 <floor>

0x44de98 MOVSD	-0x38(%RBP),%XMM4

0x44de9d MOVSD	-0x60(%RBP),%XMM1

0x44dea2 MOVSD	-0x50(%RBP),%XMM3

0x44dea7 MOVSD	-0x30(%RBP),%XMM2

0x44deac SUBSD	%XMM0,%XMM2

0x44deb0 MOVSD	%XMM2,-0xb0(%RBP)

0x44deb8 ADDSD	%XMM4,%XMM3

0x44debc UCOMISD	0xdee4c(%RIP),%XMM1

0x44dec4 MOVSD	%XMM3,-0x50(%RBP)

0x44dec9 JBE	44dedd

0x44decb XORPD	%XMM0,%XMM0

0x44decf MOVSD	%XMM0,-0xa8(%RBP)

0x44ded7 UCOMISD	%XMM0,%XMM1

0x44dedb JB	44defc

0x44dedd MOVAPD	%XMM1,%XMM0

0x44dee1 CALL	506a50 <floor>

0x44dee6 MOVSD	-0x50(%RBP),%XMM3

0x44deeb MOVSD	-0x60(%RBP),%XMM1

0x44def0 SUBSD	%XMM0,%XMM1

0x44def4 MOVSD	%XMM1,-0xa8(%RBP)

0x44defc MOV	%RBX,-0xc8(%RBP)

0x44df03 UCOMISD	0xdee05(%RIP),%XMM3

0x44df0b JBE	44df1f

0x44df0d XORPD	%XMM0,%XMM0

0x44df11 MOVSD	%XMM0,-0xa0(%RBP)

0x44df19 UCOMISD	%XMM0,%XMM3

0x44df1d JB	44df39

0x44df1f MOVAPD	%XMM3,%XMM0

0x44df23 CALL	506a50 <floor>

0x44df28 MOVSD	-0x50(%RBP),%XMM1

0x44df2d SUBSD	%XMM0,%XMM1

0x44df31 MOVSD	%XMM1,-0xa0(%RBP)

0x44df39 MOV	%R14,-0x98(%RBP)

0x44df40 MOV	0x30(%R14),%EAX

0x44df44 MOV	%RAX,-0xb8(%RBP)

0x44df4b TEST	%EAX,%EAX

0x44df4d JLE	44e574

0x44df53 MOV	-0x98(%RBP),%RAX

0x44df5a MOV	0x2f8(%RAX),%RCX

0x44df61 MOV	%RCX,-0xe8(%RBP)

0x44df68 MOV	0x310(%RAX),%RCX

0x44df6f MOV	%RCX,-0xe0(%RBP)

0x44df76 MOVSXD	0x40(%RAX),%R14

0x44df7a LEA	(,%R14,8),%RAX

0x44df82 MOV	%RAX,-0xd8(%RBP)

0x44df89 CMP	$0x1,%R14

0x44df8d MOV	%R14,%R15

0x44df90 ADC	$0,%R15

0x44df94 DECQ	-0xb8(%RBP)

0x44df9b MOV	%R15,%RAX

0x44df9e SHR	$0x1,%RAX

0x44dfa1 MOV	%RAX,-0x108(%RBP)

0x44dfa8 MOV	%R15,%RBX

0x44dfab AND	$-0x2,%RBX

0x44dfaf XOR	%R12D,%R12D

0x44dfb2 JMP	44dfd8

0x44dfb4 NOPW	%CS:(%RAX,%RAX,1)

(933) 0x44dfc0 MOV	-0xf0(%RBP),%RCX

(933) 0x44dfc7 LEA	0x1(%RCX),%R12

(933) 0x44dfcb CMP	-0xb8(%RBP),%RCX

(933) 0x44dfd2 JE	44e574

(933) 0x44dfd8 MOV	-0xe8(%RBP),%RAX

(933) 0x44dfdf MOV	(%RAX,%R12,8),%R13

(933) 0x44dfe3 MOVSD	-0xb0(%RBP),%XMM0

(933) 0x44dfeb SUBSD	0x28(%R13),%XMM0

(933) 0x44dff1 MOVSD	-0xa8(%RBP),%XMM1

(933) 0x44dff9 SUBSD	0x50(%R13),%XMM1

(933) 0x44dfff MOVAPD	%XMM1,-0x50(%RBP)

(933) 0x44e004 MOVSD	-0xa0(%RBP),%XMM1

(933) 0x44e00c SUBSD	0x78(%R13),%XMM1

(933) 0x44e012 MOVAPD	%XMM1,-0x60(%RBP)

(933) 0x44e017 MULSD	0x48(%R13),%XMM0

(933) 0x44e01d MOVAPD	%XMM0,-0x90(%RBP)

(933) 0x44e025 CALL	506a50 <floor>

(933) 0x44e02a MOVSD	%XMM0,-0x38(%RBP)

(933) 0x44e02f MOVAPD	-0x50(%RBP),%XMM0

(933) 0x44e034 MULSD	0x70(%R13),%XMM0

(933) 0x44e03a MOVAPD	%XMM0,-0x50(%RBP)

(933) 0x44e03f CALL	506a50 <floor>

(933) 0x44e044 MOVSD	%XMM0,-0x30(%RBP)

(933) 0x44e049 MOVAPD	-0x60(%RBP),%XMM0

(933) 0x44e04e MULSD	0x98(%R13),%XMM0

(933) 0x44e057 MOVAPD	%XMM0,-0x60(%RBP)

(933) 0x44e05c CALL	506a50 <floor>

(933) 0x44e061 MOV	%R12,-0xf0(%RBP)

(933) 0x44e068 LEA	(%R12,%R12,2),%RAX

(933) 0x44e06c MOV	%R13,%R12

(933) 0x44e06f MOV	-0xe0(%RBP),%RCX

(933) 0x44e076 MOV	(%RCX,%RAX,8),%R13

(933) 0x44e07a MOVSXD	0x38(%R12),%R9

(933) 0x44e07f MOVAPD	-0x90(%RBP),%XMM4

(933) 0x44e087 SUBSD	-0x38(%RBP),%XMM4

(933) 0x44e08c MOVSXD	0x60(%R12),%RAX

(933) 0x44e091 MOV	%RAX,-0x90(%RBP)

(933) 0x44e098 MOVAPD	-0x50(%RBP),%XMM12

(933) 0x44e09e SUBSD	-0x30(%RBP),%XMM12

(933) 0x44e0a4 MOVSXD	0x88(%R12),%R11

(933) 0x44e0ac MOVAPD	%XMM4,%XMM10

(933) 0x44e0b1 MOVSD	0xdec5f(%RIP),%XMM5

(933) 0x44e0b9 MULSD	%XMM5,%XMM10

(933) 0x44e0be MOVSD	0xdb042(%RIP),%XMM6

(933) 0x44e0c6 MOVAPD	%XMM6,%XMM1

(933) 0x44e0ca SUBSD	%XMM10,%XMM1

(933) 0x44e0cf MOVAPD	%XMM4,%XMM2

(933) 0x44e0d3 MULSD	%XMM4,%XMM2

(933) 0x44e0d7 MOVAPD	%XMM4,%XMM3

(933) 0x44e0db MOVAPD	%XMM4,%XMM11

(933) 0x44e0e0 UNPCKLPD	%XMM4,%XMM3

(933) 0x44e0e4 MOVAPD	0xdebb4(%RIP),%XMM7

(933) 0x44e0ec SHUFPD	$0x2,%XMM7,%XMM1

(933) 0x44e0f1 MULPD	%XMM3,%XMM1

(933) 0x44e0f5 MOVAPD	%XMM1,%XMM3

(933) 0x44e0f9 MOVAPD	0xdebae(%RIP),%XMM8

(933) 0x44e102 ADDPD	%XMM8,%XMM3

(933) 0x44e107 UNPCKLPD	%XMM2,%XMM4

(933) 0x44e10b MULPD	%XMM3,%XMM4

(933) 0x44e10f MOVAPD	0xdeba8(%RIP),%XMM9

(933) 0x44e118 ADDPD	%XMM9,%XMM4

(933) 0x44e11d MOVAPD	%XMM4,-0x150(%RBP)

(933) 0x44e125 UNPCKHPD	%XMM1,%XMM1

(933) 0x44e129 MOVAPD	%XMM6,%XMM3

(933) 0x44e12d SUBSD	%XMM1,%XMM3

(933) 0x44e131 MULSD	%XMM11,%XMM3

(933) 0x44e136 ADDSD	%XMM6,%XMM3

(933) 0x44e13a MULSD	%XMM11,%XMM3

(933) 0x44e13f ADDSD	%XMM5,%XMM3

(933) 0x44e143 MOVSD	%XMM3,-0x140(%RBP)

(933) 0x44e14b MULSD	%XMM10,%XMM2

(933) 0x44e150 MOVSD	%XMM2,-0x138(%RBP)

(933) 0x44e158 MOVAPD	%XMM12,%XMM4

(933) 0x44e15d MOVAPD	%XMM12,%XMM11

(933) 0x44e162 MULSD	%XMM5,%XMM11

(933) 0x44e167 MOVAPD	%XMM6,%XMM1

(933) 0x44e16b SUBSD	%XMM11,%XMM1

(933) 0x44e170 MOVAPD	%XMM12,%XMM2

(933) 0x44e175 MULSD	%XMM12,%XMM2

(933) 0x44e17a MOVAPD	%XMM12,%XMM3

(933) 0x44e17f MOVAPD	%XMM12,%XMM10

(933) 0x44e184 UNPCKLPD	%XMM12,%XMM3

(933) 0x44e189 SHUFPD	$0x2,%XMM7,%XMM1

(933) 0x44e18e MULPD	%XMM3,%XMM1

(933) 0x44e192 MOVAPD	%XMM1,%XMM3

(933) 0x44e196 ADDPD	%XMM8,%XMM3

(933) 0x44e19b UNPCKLPD	%XMM2,%XMM4

(933) 0x44e19f MULPD	%XMM3,%XMM4

(933) 0x44e1a3 ADDPD	%XMM9,%XMM4

(933) 0x44e1a8 MOVAPD	%XMM4,-0x130(%RBP)

(933) 0x44e1b0 UNPCKHPD	%XMM1,%XMM1

(933) 0x44e1b4 MOVAPD	%XMM6,%XMM3

(933) 0x44e1b8 SUBSD	%XMM1,%XMM3

(933) 0x44e1bc MULSD	%XMM12,%XMM3

(933) 0x44e1c1 ADDSD	%XMM6,%XMM3

(933) 0x44e1c5 MULSD	%XMM12,%XMM3

(933) 0x44e1ca ADDSD	%XMM5,%XMM3

(933) 0x44e1ce MOVSD	%XMM3,-0x120(%RBP)

(933) 0x44e1d6 MULSD	%XMM11,%XMM2

(933) 0x44e1db MOVSD	%XMM2,-0x118(%RBP)

(933) 0x44e1e3 MOV	0x10(%R12),%RAX

(933) 0x44e1e8 MOV	%RAX,-0xc0(%RBP)

(933) 0x44e1ef MOV	0x18(%R12),%RAX

(933) 0x44e1f4 MOV	%RAX,-0x50(%RBP)

(933) 0x44e1f8 MOV	0x20(%R12),%RAX

(933) 0x44e1fd MOV	%RAX,-0x80(%RBP)

(933) 0x44e201 MOV	-0xd8(%RBP),%RDX

(933) 0x44e208 TEST	%RDX,%RDX

(933) 0x44e20b JE	44e231

(933) 0x44e20d MOV	%R13,%RDI

(933) 0x44e210 XOR	%ESI,%ESI

(933) 0x44e212 MOV	%R9,-0x78(%RBP)

(933) 0x44e216 MOV	%R11,-0x70(%RBP)

(933) 0x44e21a MOVSD	%XMM0,-0x68(%RBP)

(933) 0x44e21f CALL	519fe0 <_intel_fast_memset>

(933) 0x44e224 MOVSD	-0x68(%RBP),%XMM0

(933) 0x44e229 MOV	-0x70(%RBP),%R11

(933) 0x44e22d MOV	-0x78(%RBP),%R9

(933) 0x44e231 CVTTSD2SI	-0x38(%RBP),%EDX

(933) 0x44e236 CVTTSD2SI	-0x30(%RBP),%ESI

(933) 0x44e23b MOVAPD	-0x60(%RBP),%XMM7

(933) 0x44e240 SUBSD	%XMM0,%XMM7

(933) 0x44e244 CVTTSD2SI	%XMM0,%ECX

(933) 0x44e248 MOVAPD	%XMM7,%XMM3

(933) 0x44e24c MOVSD	0xdeac4(%RIP),%XMM5

(933) 0x44e254 MULSD	%XMM5,%XMM3

(933) 0x44e258 MOVSD	0xdaea8(%RIP),%XMM6

(933) 0x44e260 MOVAPD	%XMM6,%XMM4

(933) 0x44e264 SUBSD	%XMM3,%XMM4

(933) 0x44e268 MOVAPD	%XMM7,%XMM0

(933) 0x44e26c MULSD	%XMM7,%XMM0

(933) 0x44e270 MOVAPD	%XMM7,%XMM1

(933) 0x44e274 UNPCKLPD	%XMM7,%XMM1

(933) 0x44e278 SHUFPD	$0x2,0xdea1f(%RIP),%XMM4

(933) 0x44e281 MULPD	%XMM1,%XMM4

(933) 0x44e285 MOVAPD	%XMM4,%XMM2

(933) 0x44e289 ADDPD	0xdea1f(%RIP),%XMM2

(933) 0x44e291 MOVAPD	%XMM7,%XMM1

(933) 0x44e295 UNPCKLPD	%XMM0,%XMM1

(933) 0x44e299 MULPD	%XMM2,%XMM1

(933) 0x44e29d ADDPD	0xdea1b(%RIP),%XMM1

(933) 0x44e2a5 UNPCKHPD	%XMM4,%XMM4

(933) 0x44e2a9 MOVAPD	%XMM6,%XMM2

(933) 0x44e2ad SUBSD	%XMM4,%XMM2

(933) 0x44e2b1 MULSD	%XMM7,%XMM2

(933) 0x44e2b5 ADDSD	%XMM6,%XMM2

(933) 0x44e2b9 MULSD	%XMM7,%XMM2

(933) 0x44e2bd ADDSD	%XMM5,%XMM2

(933) 0x44e2c1 MOV	0x8(%R12),%RAX

(933) 0x44e2c6 MULSD	%XMM3,%XMM0

(933) 0x44e2ca MOVAPD	%XMM1,%XMM3

(933) 0x44e2ce UNPCKHPD	%XMM1,%XMM3

(933) 0x44e2d2 MOVAPD	%XMM1,%XMM4

(933) 0x44e2d6 UNPCKLPD	%XMM1,%XMM4

(933) 0x44e2da MOVAPD	%XMM2,%XMM5

(933) 0x44e2de UNPCKLPD	%XMM2,%XMM5

(933) 0x44e2e2 MOVAPD	%XMM0,%XMM6

(933) 0x44e2e6 MOV	-0x90(%RBP),%R12

(933) 0x44e2ed DEC	%R12

(933) 0x44e2f0 TEST	%ESI,%ESI

(933) 0x44e2f2 MOV	$0,%EDI

(933) 0x44e2f7 CMOVLE	%EDI,%ESI

(933) 0x44e2fa CMP	%RSI,%R12

(933) 0x44e2fd CMOVGE	%RSI,%R12

(933) 0x44e301 IMUL	-0x50(%RBP),%R12

(933) 0x44e306 DEC	%R9

(933) 0x44e309 TEST	%EDX,%EDX

(933) 0x44e30b CMOVLE	%EDI,%EDX

(933) 0x44e30e CMP	%RDX,%R9

(933) 0x44e311 CMOVGE	%RDX,%R9

(933) 0x44e315 MOV	-0xc0(%RBP),%R8

(933) 0x44e31c IMUL	%R8,%R9

(933) 0x44e320 DEC	%R11

(933) 0x44e323 TEST	%ECX,%ECX

(933) 0x44e325 CMOVLE	%EDI,%ECX

(933) 0x44e328 UNPCKLPD	%XMM0,%XMM6

(933) 0x44e32c CMP	%RCX,%R11

(933) 0x44e32f CMOVGE	%RCX,%R11

(933) 0x44e333 MOV	-0x80(%RBP),%RCX

(933) 0x44e337 MOV	%RCX,%RSI

(933) 0x44e33a IMUL	%R11,%RSI

(933) 0x44e33e LEA	(%RBX,%RSI,1),%RDI

(933) 0x44e342 ADD	%R9,%RDI

(933) 0x44e345 LEA	(%RDI,%R12,1),%R10

(933) 0x44e349 ADD	%RCX,%RDI

(933) 0x44e34c ADD	%R12,%RDI

(933) 0x44e34f MOV	%RDI,-0x60(%RBP)

(933) 0x44e353 LEA	(%R10,%RCX,2),%RDX

(933) 0x44e357 MOV	%RDX,-0x30(%RBP)

(933) 0x44e35b LEA	(%RCX,%RCX,2),%RDX

(933) 0x44e35f MOV	%R10,-0x38(%RBP)

(933) 0x44e363 ADD	%R10,%RDX

(933) 0x44e366 MOV	%RDX,-0x90(%RBP)

(933) 0x44e36d ADD	%R12,%R9

(933) 0x44e370 LEA	0x3(%R11),%RDX

(933) 0x44e374 IMUL	%RCX,%RDX

(933) 0x44e378 ADD	%R9,%RDX

(933) 0x44e37b LEA	(%RAX,%RDX,8),%RDI

(933) 0x44e37f LEA	(,%R8,8),%RDX

(933) 0x44e387 MOV	%RDX,-0xf8(%RBP)

(933) 0x44e38e LEA	0x2(%R11),%RDX

(933) 0x44e392 IMUL	%RCX,%RDX

(933) 0x44e396 INC	%R11

(933) 0x44e399 IMUL	%RCX,%R11

(933) 0x44e39d MOV	-0x50(%RBP),%RCX

(933) 0x44e3a1 LEA	(,%RCX,8),%R10

(933) 0x44e3a9 ADD	%R9,%RDX

(933) 0x44e3ac LEA	(%RAX,%RDX,8),%R8

(933) 0x44e3b0 MOV	%RDI,%RDX

(933) 0x44e3b3 ADD	%R9,%R11

(933) 0x44e3b6 LEA	(%RAX,%R11,8),%RCX

(933) 0x44e3ba ADD	%RSI,%R9

(933) 0x44e3bd LEA	(%RAX,%R9,8),%R12

(933) 0x44e3c1 MOV	%RCX,%R9

(933) 0x44e3c4 XOR	%ECX,%ECX

(933) 0x44e3c6 JMP	44e408

0x44e3c8 NOPL	(%RAX,%RAX,1)

  (934) 0x44e3d0 MOV	-0x100(%RBP),%RDI

  (934) 0x44e3d7 LEA	0x1(%RDI),%RCX

  (934) 0x44e3db MOV	-0x80(%RBP),%RDX

  (934) 0x44e3df MOV	-0xf8(%RBP),%RSI

  (934) 0x44e3e6 ADD	%RSI,%RDX

  (934) 0x44e3e9 MOV	-0x78(%RBP),%R8

  (934) 0x44e3ed ADD	%RSI,%R8

  (934) 0x44e3f0 MOV	-0x70(%RBP),%R9

  (934) 0x44e3f4 ADD	%RSI,%R9

  (934) 0x44e3f7 MOV	-0x68(%RBP),%R12

  (934) 0x44e3fb ADD	%RSI,%R12

  (934) 0x44e3fe CMP	$0x3,%RDI

  (934) 0x44e402 JE	44dfc0

  (934) 0x44e408 MOVSD	-0x150(%RBP,%RCX,8),%XMM7

  (934) 0x44e411 MOV	-0xc0(%RBP),%R11

  (934) 0x44e418 MOV	%RCX,-0x100(%RBP)

  (934) 0x44e41f IMUL	%RCX,%R11

  (934) 0x44e423 MOV	%R12,-0x68(%RBP)

  (934) 0x44e427 MOV	%R9,-0x70(%RBP)

  (934) 0x44e42b MOV	%R8,-0x78(%RBP)

  (934) 0x44e42f MOV	%RDX,-0x80(%RBP)

  (934) 0x44e433 MOV	%RDX,%RCX

  (934) 0x44e436 XOR	%EDX,%EDX

  (934) 0x44e438 JMP	44e45d

0x44e43a NOPW	(%RAX,%RAX,1)

    (935) 0x44e440 LEA	0x1(%RDX),%RSI

    (935) 0x44e444 ADD	%R10,%RCX

    (935) 0x44e447 ADD	%R10,%R8

    (935) 0x44e44a ADD	%R10,%R9

    (935) 0x44e44d ADD	%R10,%R12

    (935) 0x44e450 CMP	$0x3,%RDX

    (935) 0x44e454 MOV	%RSI,%RDX

    (935) 0x44e457 JE	44e3d0

    (935) 0x44e45d TEST	%R14D,%R14D

    (935) 0x44e460 JE	44e440

    (935) 0x44e462 MOVSD	-0x130(%RBP,%RDX,8),%XMM8

    (935) 0x44e46c MULSD	%XMM7,%XMM8

    (935) 0x44e471 CMP	$0x2,%R15

    (935) 0x44e475 JB	44e4ec

    (935) 0x44e477 MOVAPD	%XMM8,%XMM9

    (935) 0x44e47c UNPCKLPD	%XMM8,%XMM9

    (935) 0x44e481 MOV	-0x108(%RBP),%RSI

    (935) 0x44e488 XOR	%EDI,%EDI

    (935) 0x44e48a NOPW	(%RAX,%RAX,1)

      (936) 0x44e490 MOVUPD	(%R12,%RDI,1),%XMM10

      (936) 0x44e496 MULPD	%XMM4,%XMM10

      (936) 0x44e49b MOVUPD	(%R9,%RDI,1),%XMM11

      (936) 0x44e4a1 MULPD	%XMM3,%XMM11

      (936) 0x44e4a6 ADDPD	%XMM10,%XMM11

      (936) 0x44e4ab MOVUPD	(%R8,%RDI,1),%XMM10

      (936) 0x44e4b1 MULPD	%XMM5,%XMM10

      (936) 0x44e4b6 MOVUPD	(%RCX,%RDI,1),%XMM12

      (936) 0x44e4bc MULPD	%XMM6,%XMM12

      (936) 0x44e4c1 ADDPD	%XMM10,%XMM12

      (936) 0x44e4c6 ADDPD	%XMM11,%XMM12

      (936) 0x44e4cb MULPD	%XMM9,%XMM12

      (936) 0x44e4d0 MOVUPD	(%R13,%RDI,1),%XMM10

      (936) 0x44e4d7 ADDPD	%XMM12,%XMM10

      (936) 0x44e4dc MOVUPD	%XMM10,(%R13,%RDI,1)

      (936) 0x44e4e3 ADD	$0x10,%RDI

      (936) 0x44e4e7 DEC	%RSI

      (936) 0x44e4ea JNE	44e490

    (935) 0x44e4ec CMP	%R15,%RBX

    (935) 0x44e4ef JAE	44e440

    (935) 0x44e4f5 MOV	-0x50(%RBP),%RSI

    (935) 0x44e4f9 IMUL	%RDX,%RSI

    (935) 0x44e4fd ADD	%R11,%RSI

    (935) 0x44e500 MOV	-0x38(%RBP),%RDI

    (935) 0x44e504 ADD	%RSI,%RDI

    (935) 0x44e507 MOVSD	(%RAX,%RDI,8),%XMM9

    (935) 0x44e50d MOV	-0x60(%RBP),%RDI

    (935) 0x44e511 ADD	%RSI,%RDI

    (935) 0x44e514 MOVHPD	(%RAX,%RDI,8),%XMM9

    (935) 0x44e51a MOV	-0x30(%RBP),%RDI

    (935) 0x44e51e ADD	%RSI,%RDI

    (935) 0x44e521 ADD	-0x90(%RBP),%RSI

    (935) 0x44e528 MOVAPD	%XMM2,%XMM10

    (935) 0x44e52d MOVHPD	(%RAX,%RSI,8),%XMM10

    (935) 0x44e533 MOVSD	(%RAX,%RDI,8),%XMM11

    (935) 0x44e539 UNPCKLPD	%XMM0,%XMM11

    (935) 0x44e53e MULPD	%XMM11,%XMM10

    (935) 0x44e543 MULPD	%XMM1,%XMM9

    (935) 0x44e548 ADDPD	%XMM10,%XMM9

    (935) 0x44e54d MOVAPD	%XMM9,%XMM10

    (935) 0x44e552 UNPCKHPD	%XMM9,%XMM10

    (935) 0x44e557 ADDSD	%XMM9,%XMM10

    (935) 0x44e55c MULSD	%XMM10,%XMM8

    (935) 0x44e561 ADDSD	(%R13,%RBX,8),%XMM8

    (935) 0x44e568 MOVSD	%XMM8,(%R13,%RBX,8)

    (935) 0x44e56f JMP	44e440

0x44e574 MOV	-0xd0(%RBP),%RDI

0x44e57b CALL	4a9bd0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>

0x44e580 MOV	-0x98(%RBP),%R12

0x44e587 MOV	0x30(%R12),%EAX

0x44e58c TEST	%EAX,%EAX

0x44e58e MOV	-0xc8(%RBP),%R15

0x44e595 JLE	44e5f5

0x44e597 XOR	%EBX,%EBX

0x44e599 XOR	%R14D,%R14D

0x44e59c JMP	44e5ac

0x44e59e XCHG	%AX,%AX

(932) 0x44e5a0 MOVSXD	%EAX,%RCX

(932) 0x44e5a3 ADD	$0x18,%RBX

(932) 0x44e5a7 CMP	%RCX,%R14

(932) 0x44e5aa JGE	44e5f5

(932) 0x44e5ac MOV	%R14D,%EDX

(932) 0x44e5af IMUL	%EAX,%EDX

(932) 0x44e5b2 INC	%R14

(932) 0x44e5b5 MOV	0x40(%R12),%ECX

(932) 0x44e5ba IMUL	%R14D,%ECX

(932) 0x44e5be MOV	0x8(%R12),%ESI

(932) 0x44e5c3 CMP	%ECX,%ESI

(932) 0x44e5c5 CMOVL	%ESI,%ECX

(932) 0x44e5c8 SUB	%EDX,%ECX

(932) 0x44e5ca JLE	44e5a0

(932) 0x44e5cc MOVSXD	%EDX,%RDI

(932) 0x44e5cf SAL	$0x3,%RDI

(932) 0x44e5d3 ADD	0x18(%R15),%RDI

(932) 0x44e5d7 MOV	0x310(%R12),%RAX

(932) 0x44e5df MOV	(%RAX,%RBX,1),%RSI

(932) 0x44e5e3 MOV	%ECX,%EDX

(932) 0x44e5e5 SAL	$0x3,%RDX

(932) 0x44e5e9 CALL	4050d0 <memmove@plt>

(932) 0x44e5ee MOV	0x30(%R12),%EAX

(932) 0x44e5f3 JMP	44e5a0

0x44e5f5 ADD	$0x128,%RSP

0x44e5fc POP	%RBX

0x44e5fd POP	%R12

0x44e5ff POP	%R13

0x44e601 POP	%R14

0x44e603 POP	%R15

0x44e605 POP	%RBP

0x44e606 RET

0x44e607 MOV	%RAX,%RDI

0x44e60a CALL	413600 <__clang_call_terminate>

0x44e60f NOP

Coverage (%)	Name	Source Location	Module
►95.20+	qmcplusplus::SPOSet::evaluateD[...]	OhmmsVector.h:178	exec
○	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:217	exec
○	_ZN11qmcplusplus12WaveFunction[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:126	exec
○	main.extracted.107	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►2.66+	qmcplusplus::SPOSet::evaluateD[...]	OhmmsVector.h:178	exec
○	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:217	exec
○	_ZN11qmcplusplus12WaveFunction[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:126	exec
○	main.extracted.107	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	stl_uninitialized.h:99	exec

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 0.01% of application time for run icx_3

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

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:143
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp:172-189
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170-173
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp:42-49,56-71
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:61
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1046,1169
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:235,429-431,923-924
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:45-47
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineData.hpp:54-57
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algo.h:725,751
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h:150-152

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 18.13 to 9.38 cycles (1.93x speedup).

Workaround

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

Vectorization

Your function is probably not vectorized. Only 13% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 18.13 to 1.69 cycles (10.72x speedup).

Details

Store and arithmetical SSE/AVX instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized function can use their full power.

Workaround

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

Execution units bottlenecks

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

FMA

Presence of both ADD/SUB and MUL operations.

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
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).

CALL instructions

Detected function call instructions.

Details

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

__clang_call_terminate: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249
floor: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:173
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:173
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:173
qmcplusplus::TimerType
::start(): 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242
qmcplusplus::TimerType
::stop(): 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

UCOMISD: 6 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170

Type of elements and instruction set

24 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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
9: multiply

The binary function is loading 264 bytes (33 double precision FP elements). The binary function is storing 160 bytes (20 double precision FP elements).

Arithmetic intensity

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

General properties

nb instructions	138
nb uops	145
loop length	661
used x86 registers	12
used mmx registers	0
used xmm registers	6
used ymm registers	0
used zmm registers	0
nb stack references	15
ADD-SUB / MUL ratio	1.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	18.13 cycles
front end	18.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	5.33	5.33	5.33	6.33	6.33	6.33	15.00	15.00	15.00	15.00	4.50	4.50	7.50	7.50	8.50	8.50
cycles	5.33	5.33	5.33	6.33	6.33	6.33	15.00	15.00	15.00	15.00	4.50	4.50	7.50	7.50	8.50	8.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	18.13
Dispatch	15.00
Overall L1	18.13

Vectorization ratios

INT

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

all	10%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	50%

INT+FP

all	7%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	27%

Vector efficiency ratios

INT

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

all	13%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	18%

INT+FP

all	13%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	14%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 18.13 cycles. At this rate:

5% of peak load performance is reached (14.57 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.83 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 18.13 to 15.00 cycles (1.21x speedup).

ASM code

In the binary file, the address of the function is: 44dd80

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x128,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %EDX,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RSI,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x358(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RDI,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CALL 4a9a00 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOVSXD %R12D,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%RAX,%RAX,2),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD 0x40(%R13),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP %EAX,0x124(%R13)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (6.3%)
LEA 0x128(%R13),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMOVNE %RCX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVSD (%RAX),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x8(%RAX),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0xd8(%R14),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
MOVSD 0xf0(%R14),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM3,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
ADDSD %XMM1,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD 0x10(%RAX),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x108(%R14),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM4,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
ADDSD %XMM2,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD 0xe0(%R14),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
MOVSD 0xf8(%R14),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM3,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
ADDSD %XMM1,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD 0x110(%R14),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
ADDSD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MULSD 0xe8(%R14),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
MULSD 0x100(%R14),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
MULSD 0x118(%R14),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
ADDSD %XMM0,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
UCOMISD 0xdeea9(%RIP),%XMM5	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
MOVSD %XMM1,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
JBE 44de80 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x100>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVSD %XMM0,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
UCOMISD %XMM0,%XMM5	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
JB 44deb8 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x138>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVAPD %XMM5,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVSD %XMM3,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOVSD %XMM4,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOVSD %XMM5,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
CALL 506a50 <floor>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOVSD -0x38(%RBP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD -0x60(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD -0x50(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD -0x30(%RBP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
SUBSD %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM2,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
ADDSD %XMM4,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
UCOMISD 0xdee4c(%RIP),%XMM1	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
MOVSD %XMM3,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
JBE 44dedd <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x15d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVSD %XMM0,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
UCOMISD %XMM0,%XMM1	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
JB 44defc <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x17c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVAPD %XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CALL 506a50 <floor>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOVSD -0x50(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD -0x60(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
SUBSD %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM1,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV %RBX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
UCOMISD 0xdee05(%RIP),%XMM3	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
JBE 44df1f <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x19f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVSD %XMM0,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
UCOMISD %XMM0,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
JB 44df39 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x1b9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVAPD %XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CALL 506a50 <floor>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOVSD -0x50(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
SUBSD %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM1,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV %R14,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x30(%R14),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
TEST %EAX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JLE 44e574 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x7f4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x98(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x2f8(%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV %RCX,-0xe8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x310(%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV %RCX,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOVSXD 0x40(%RAX),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
LEA (,%R14,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMP $0x1,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R14,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
ADC $0,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
DECQ -0xb8(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV %R15,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x1,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV %RAX,-0x108(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R15,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x2,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 44dfd8 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x258>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xd0(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CALL 4a9bd0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV -0x98(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x30(%R12),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %EAX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV -0xc8(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
JLE 44e5f5 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x875>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %EBX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 44e5ac <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x82c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x128,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 413600 <__clang_call_terminate>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run icx_3

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

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:143
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp:172-189
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170-173
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp:42-49,56-71
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:61
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1046,1169
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:235,429-431,923-924
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:45-47
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineData.hpp:54-57
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algo.h:725,751
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h:150-152

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 18.13 to 9.38 cycles (1.93x speedup).

Workaround

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

Vectorization

Details

Workaround

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

Execution units bottlenecks

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

FMA

Presence of both ADD/SUB and MUL operations.

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
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).

CALL instructions

Detected function call instructions.

Details

__clang_call_terminate: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249
floor: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:173
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:173
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:173
qmcplusplus::TimerType
::start(): 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242
qmcplusplus::TimerType
::stop(): 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

UCOMISD: 6 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170

Type of elements and instruction set

24 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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
9: multiply

The binary function is loading 264 bytes (33 double precision FP elements). The binary function is storing 160 bytes (20 double precision FP elements).

Arithmetic intensity

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

General properties

nb instructions	138
nb uops	145
loop length	661
used x86 registers	12
used mmx registers	0
used xmm registers	6
used ymm registers	0
used zmm registers	0
nb stack references	15
ADD-SUB / MUL ratio	1.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	18.13 cycles
front end	18.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	5.33	5.33	5.33	6.33	6.33	6.33	15.00	15.00	15.00	15.00	4.50	4.50	7.50	7.50	8.50	8.50
cycles	5.33	5.33	5.33	6.33	6.33	6.33	15.00	15.00	15.00	15.00	4.50	4.50	7.50	7.50	8.50	8.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	18.13
Dispatch	15.00
Overall L1	18.13

Vectorization ratios

INT

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

all	10%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	50%

INT+FP

all	7%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	27%

Vector efficiency ratios

INT

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

all	13%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	18%

INT+FP

all	13%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	14%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 18.13 cycles. At this rate:

5% of peak load performance is reached (14.57 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.83 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 44dd80

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x128,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %EDX,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RSI,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x358(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RDI,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CALL 4a9a00 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOVSXD %R12D,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%RAX,%RAX,2),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD 0x40(%R13),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP %EAX,0x124(%R13)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (6.3%)
LEA 0x128(%R13),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMOVNE %RCX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVSD (%RAX),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x8(%RAX),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0xd8(%R14),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
MOVSD 0xf0(%R14),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM3,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
ADDSD %XMM1,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD 0x10(%RAX),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x108(%R14),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM4,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
ADDSD %XMM2,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD 0xe0(%R14),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
MOVSD 0xf8(%R14),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM3,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
ADDSD %XMM1,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD 0x110(%R14),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
ADDSD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MULSD 0xe8(%R14),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
MULSD 0x100(%R14),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
MULSD 0x118(%R14),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
ADDSD %XMM0,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
UCOMISD 0xdeea9(%RIP),%XMM5	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
MOVSD %XMM1,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
JBE 44de80 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x100>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVSD %XMM0,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
UCOMISD %XMM0,%XMM5	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
JB 44deb8 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x138>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVAPD %XMM5,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVSD %XMM3,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOVSD %XMM4,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOVSD %XMM5,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
CALL 506a50 <floor>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOVSD -0x38(%RBP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD -0x60(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD -0x50(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD -0x30(%RBP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
SUBSD %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM2,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
ADDSD %XMM4,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
UCOMISD 0xdee4c(%RIP),%XMM1	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
MOVSD %XMM3,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
JBE 44dedd <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x15d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVSD %XMM0,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
UCOMISD %XMM0,%XMM1	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
JB 44defc <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x17c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVAPD %XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CALL 506a50 <floor>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOVSD -0x50(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD -0x60(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
SUBSD %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM1,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV %RBX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
UCOMISD 0xdee05(%RIP),%XMM3	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
JBE 44df1f <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x19f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVSD %XMM0,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
UCOMISD %XMM0,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
JB 44df39 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x1b9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVAPD %XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CALL 506a50 <floor>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOVSD -0x50(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
SUBSD %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM1,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV %R14,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x30(%R14),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
TEST %EAX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JLE 44e574 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x7f4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x98(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x2f8(%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV %RCX,-0xe8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x310(%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV %RCX,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOVSXD 0x40(%RAX),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
LEA (,%R14,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMP $0x1,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R14,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
ADC $0,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
DECQ -0xb8(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV %R15,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x1,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV %RAX,-0x108(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R15,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x2,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 44dfd8 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x258>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xd0(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CALL 4a9bd0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV -0x98(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x30(%R12),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %EAX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV -0xc8(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
JLE 44e5f5 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x875>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %EBX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 44e5ac <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x82c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x128,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 413600 <__clang_call_terminate>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::einspline_spo_ref::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector >&)–	24.62	41.13
▼Loop 933 - MultiBsplineRef.hpp:42-71 - exec–	0.00	0.01
▼Loop 934 - MultiBsplineRef.hpp:63-71 - exec–	0.00	0.01
▼Loop 935 - MultiBsplineRef.hpp:64-71 - exec–	0.01	0.01
○Loop 936 - MultiBsplineRef.hpp:68-71 - exec	24.60	40.88
○Loop 932 - einspline_spo_ref.hpp:183-187 - exec	0.00	0.01

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

FMA

Workaround

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

FMA

Workaround

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code