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

	Function: miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int ...	Module: exec	Source: einspline_spo_ref.hpp:203-230 [...]	Coverage (incl. loops): 0.27% \| (excl. loops): 0.00%

/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: 203 - 230

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

203:     ScopedTimer local_timer(timer);

204:

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

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

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

208:                                         nSplinesPerBlock);

209:   }

210:

211:   inline void evaluate(const ParticleSet& P,

[...]

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

220:     {

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

222:       const int first = i * nBlocks;

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

224:       {

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

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

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

228:       }

229:     }

230:   }

/home/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/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: 145 - 145

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

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

/cluster/comp/gcc/14.2.0/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/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 229

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

223:     return X[i];

[...]

229:     return X[i];

/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algobase.h: 238 - 238

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

238:       if (__b < __a)

/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]);

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 231 - 271

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

231:   inline const AoSElement_t operator[](size_t i) const { return AoSElement_t(myData + i, nGhosts); }

[...]

265:   inline T* data() { return myData; }

[...]

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

0x487ad0 PUSH	%RBP

0x487ad1 MOV	%RSP,%RBP

0x487ad4 PUSH	%R15

0x487ad6 PUSH	%R14

0x487ad8 PUSH	%R13

0x487ada PUSH	%R12

0x487adc PUSH	%RBX

0x487add MOV	%RSI,%R13

0x487ae0 MOV	%RDI,%RBX

0x487ae3 SUB	$0x48,%RSP

0x487ae7 MOV	0x358(%RDI),%R12

0x487aee MOV	%RCX,-0x60(%RBP)

0x487af2 MOVSXD	%EDX,%R15

0x487af5 MOV	%R8,-0x68(%RBP)

0x487af9 MOV	%R9,-0x70(%RBP)

0x487afd MOV	%R12,%RDI

0x487b00 CALL	531880 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>

0x487b05 LEA	0x128(%R13),%RCX

0x487b0c CMP	0x124(%R13),%R15D

0x487b13 JE	487b21

0x487b15 MOV	0x40(%R13),%RAX

0x487b19 LEA	(%R15,%R15,2),%RDX

0x487b1d LEA	(%RAX,%RDX,8),%RCX

0x487b21 VMOVUPD	(%RCX),%XMM0

0x487b25 VMOVSD	0x10(%RCX),%XMM1

0x487b2a VXORPD	%XMM9,%XMM9,%XMM9

0x487b2f VMOVDDUP	%XMM1,%XMM2

0x487b33 VMOVDDUP	0x138b85(%RIP),%XMM10

0x487b3b VMULSD	0x118(%RBX),%XMM1,%XMM6

0x487b43 VMOVSD	(%RCX),%XMM5

0x487b47 VFMADD231SD	0xe8(%RBX),%XMM5,%XMM6

0x487b50 VPERMILPD	$0x3,%XMM0,%XMM4

0x487b56 VMULPD	0xf0(%RBX),%XMM4,%XMM8

0x487b5e VPERMILPD	$0,%XMM0,%XMM3

0x487b64 VUNPCKHPD	%XMM0,%XMM0,%XMM7

0x487b68 VFMADD231PD	0xd8(%RBX),%XMM3,%XMM8

0x487b71 VFMADD132PD	0x108(%RBX),%XMM8,%XMM2

0x487b7a VCMPPD	$0x1,%XMM9,%XMM2,%K1

0x487b81 VFMADD132SD	0x100(%RBX),%XMM6,%XMM7

0x487b8a VRNDSCALEPD	$0x9,%XMM2,%XMM11

0x487b91 VCMPPD	$0xe,%XMM10,%XMM2,%K0{%K1}

0x487b98 KNOTB	%K0,%K2

0x487b9c KMOVB	%K2,%ESI

0x487ba0 AND	$0x3,%ESI

0x487ba3 VCOMISD	0x138b15(%RIP),%XMM7

0x487bab KMOVB	%ESI,%K3

0x487baf VSUBPD	%XMM11,%XMM2,%XMM12{%K3}{z}

0x487bb5 JBE	487bc6

0x487bb7 VXORPD	%XMM13,%XMM13,%XMM13

0x487bbc VCOMISD	%XMM7,%XMM13

0x487bc0 JA	487f9b

0x487bc6 VRNDSCALESD	$0x9,%XMM7,%XMM7,%XMM14

0x487bcd VSUBSD	%XMM14,%XMM7,%XMM15

0x487bd2 MOV	0x30(%RBX),%R8D

0x487bd6 VMOVHPD	%XMM12,-0x38(%RBP)

0x487bdb VMOVLPD	%XMM12,-0x40(%RBP)

0x487be0 XOR	%R14D,%R14D

0x487be3 TEST	%R8D,%R8D

0x487be6 JLE	487cb8

0x487bec VMOVSD	%XMM15,-0x48(%RBP)

(1005) 0x487bf1 MOV	0x310(%RBX),%R13

(1005) 0x487bf8 MOV	0x340(%RBX),%R9

(1005) 0x487bff MOV	0x328(%RBX),%R10

(1005) 0x487c06 MOV	0x2f8(%RBX),%RAX

(1005) 0x487c0d LEA	(%R14,%R14,4),%RDI

(1005) 0x487c11 LEA	(%R14,%R14,2),%R11

(1005) 0x487c15 MOVSXD	0x40(%RBX),%R8

(1005) 0x487c19 VMOVSD	-0x48(%RBP),%XMM2

(1005) 0x487c1e VMOVSD	-0x38(%RBP),%XMM1

(1005) 0x487c23 VMOVSD	-0x40(%RBP),%XMM0

(1005) 0x487c28 SAL	$0x3,%RDI

(1005) 0x487c2c LEA	(%R13,%R11,8),%R15

(1005) 0x487c31 MOV	0x18(%R9,%RDI,1),%RCX

(1005) 0x487c36 MOV	0x18(%R10,%RDI,1),%RDX

(1005) 0x487c3b MOV	(%RAX,%R14,8),%RDI

(1005) 0x487c3f MOV	(%R15),%RSI

(1005) 0x487c42 CALL	486e10 <_ZN16miniqmcreference19MultiBsplineEvalRef12evaluate_vghIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_S9_S9_m>

(1005) 0x487c47 LEA	0x1(%R14),%R8

(1005) 0x487c4b CMP	%R8D,0x30(%RBX)

(1005) 0x487c4f JLE	487cb8

(1005) 0x487c51 MOV	0x328(%RBX),%RSI

(1005) 0x487c58 MOV	0x310(%RBX),%R10

(1005) 0x487c5f MOV	0x340(%RBX),%RCX

(1005) 0x487c66 LEA	(%R8,%R8,4),%RDX

(1005) 0x487c6a MOV	0x2f8(%RBX),%R13

(1005) 0x487c71 LEA	(%R8,%R8,2),%RDI

(1005) 0x487c75 VMOVSD	-0x48(%RBP),%XMM2

(1005) 0x487c7a VMOVSD	-0x38(%RBP),%XMM1

(1005) 0x487c7f VMOVSD	-0x40(%RBP),%XMM0

(1005) 0x487c84 ADD	$0x2,%R14

(1005) 0x487c88 SAL	$0x3,%RDX

(1005) 0x487c8c LEA	(%R10,%RDI,8),%R11

(1005) 0x487c90 MOV	0x18(%RSI,%RDX,1),%R9

(1005) 0x487c95 MOV	0x18(%RCX,%RDX,1),%RCX

(1005) 0x487c9a MOV	(%R13,%R8,8),%RDI

(1005) 0x487c9f MOV	(%R11),%RSI

(1005) 0x487ca2 MOVSXD	0x40(%RBX),%R8

(1005) 0x487ca6 MOV	%R9,%RDX

(1005) 0x487ca9 CALL	486e10 <_ZN16miniqmcreference19MultiBsplineEvalRef12evaluate_vghIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_S9_S9_m>

(1005) 0x487cae CMP	%R14D,0x30(%RBX)

(1005) 0x487cb2 JG	487bf1

0x487cb8 MOV	%R12,%RDI

0x487cbb CALL	531ac0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>

0x487cc0 MOV	0x30(%RBX),%R12D

0x487cc4 MOV	%R12D,-0x4c(%RBP)

0x487cc8 TEST	%R12D,%R12D

0x487ccb JLE	487f8c

0x487cd1 MOVSXD	-0x4c(%RBP),%R14

0x487cd5 VMOVD	0x40(%RBX),%XMM4

0x487cda VMOVD	0x8(%RBX),%XMM3

0x487cdf XOR	%R10D,%R10D

0x487ce2 VMOVDQA	%XMM4,%XMM7

0x487ce6 XOR	%R11D,%R11D

0x487ce9 MOVQ	$0,-0x40(%RBP)

0x487cf1 MOVQ	$0,-0x48(%RBP)

0x487cf9 MOVL	$0,-0x38(%RBP)

0x487d00 LEA	(,%R14,8),%R15

0x487d08 LEA	(%R14,%R14,2),%RAX

0x487d0c LEA	(,%RAX,8),%R8

0x487d14 VMOVQ	%R15,%XMM1

0x487d19 MOV	%R8,-0x58(%RBP)

0x487d1d NOPL	(%RAX)

(1003) 0x487d20 VPMINSD	%XMM3,%XMM7,%XMM0

(1003) 0x487d25 VMOVD	%XMM0,%ESI

(1003) 0x487d29 CMP	%ESI,-0x38(%RBP)

(1003) 0x487d2c JGE	487f60

(1003) 0x487d32 MOV	-0x48(%RBP),%RDI

(1003) 0x487d36 MOV	0x340(%RBX),%R13

(1003) 0x487d3d MOV	0x328(%RBX),%RCX

(1003) 0x487d44 MOV	-0x38(%RBP),%EAX

(1003) 0x487d47 MOV	0x310(%RBX),%RDX

(1003) 0x487d4e MOV	-0x68(%RBP),%R14

(1003) 0x487d52 MOV	-0x60(%RBP),%R8

(1003) 0x487d56 ADD	%RDI,%RCX

(1003) 0x487d59 MOV	0x18(%R13,%RDI,1),%R15

(1003) 0x487d5e MOV	-0x70(%RBP),%RDI

(1003) 0x487d62 SUB	%EAX,%ESI

(1003) 0x487d64 MOV	0x18(%RCX),%R12

(1003) 0x487d68 MOVSXD	0x8(%RCX),%RCX

(1003) 0x487d6c MOV	(%RDX,%R10,1),%R9

(1003) 0x487d70 MOV	-0x40(%RBP),%RDX

(1003) 0x487d74 ADD	0x18(%R14),%RDX

(1003) 0x487d78 MOV	0x18(%R8),%R8

(1003) 0x487d7c XOR	%EAX,%EAX

(1003) 0x487d7e SAL	$0x3,%RSI

(1003) 0x487d82 MOV	0x18(%RDI),%R14

(1003) 0x487d86 LEA	-0x8(%RSI),%RDI

(1003) 0x487d8a LEA	(%R12,%RCX,8),%R13

(1003) 0x487d8e ADD	%R11,%R8

(1003) 0x487d91 SHR	$0x3,%RDI

(1003) 0x487d95 SAL	$0x4,%RCX

(1003) 0x487d99 INC	%RDI

(1003) 0x487d9c ADD	%R12,%RCX

(1003) 0x487d9f ADD	%R11,%R14

(1003) 0x487da2 AND	$0x3,%EDI

(1003) 0x487da5 JE	487e6e

(1003) 0x487dab CMP	$0x1,%RDI

(1003) 0x487daf JE	487e2a

(1003) 0x487db1 CMP	$0x2,%RDI

(1003) 0x487db5 JE	487dee

(1003) 0x487db7 VMOVSD	(%R9),%XMM2

(1003) 0x487dbc VMOVSD	%XMM2,(%R8)

(1003) 0x487dc1 VMOVSD	(%R12),%XMM6

(1003) 0x487dc7 VMOVHPD	(%R13),%XMM6,%XMM8

(1003) 0x487dcd VMOVSD	(%RCX),%XMM5

(1003) 0x487dd1 ADD	$0x18,%RDX

(1003) 0x487dd5 MOV	$0x8,%EAX

(1003) 0x487dda VMOVUPD	%XMM8,-0x18(%RDX)

(1003) 0x487ddf VMOVSD	%XMM5,-0x8(%RDX)

(1003) 0x487de4 VMOVSD	(%R15),%XMM9

(1003) 0x487de9 VMOVSD	%XMM9,(%R14)

(1003) 0x487dee VMOVSD	(%R9,%RAX,1),%XMM10

(1003) 0x487df4 VMOVSD	%XMM10,(%R8,%RAX,1)

(1003) 0x487dfa VMOVSD	(%R12,%RAX,1),%XMM12

(1003) 0x487e00 VMOVHPD	(%R13,%RAX,1),%XMM12,%XMM13

(1003) 0x487e07 VMOVSD	(%RCX,%RAX,1),%XMM11

(1003) 0x487e0c ADD	$0x18,%RDX

(1003) 0x487e10 VMOVUPD	%XMM13,-0x18(%RDX)

(1003) 0x487e15 VMOVSD	%XMM11,-0x8(%RDX)

(1003) 0x487e1a VMOVSD	(%R15,%RAX,1),%XMM14

(1003) 0x487e20 VMOVSD	%XMM14,(%R14,%RAX,1)

(1003) 0x487e26 ADD	$0x8,%RAX

(1003) 0x487e2a VMOVSD	(%R9,%RAX,1),%XMM15

(1003) 0x487e30 VMOVSD	%XMM15,(%R8,%RAX,1)

(1003) 0x487e36 VMOVSD	(%R12,%RAX,1),%XMM2

(1003) 0x487e3c VMOVHPD	(%R13,%RAX,1),%XMM2,%XMM5

(1003) 0x487e43 VMOVSD	(%RCX,%RAX,1),%XMM0

(1003) 0x487e48 VMOVUPD	%XMM5,(%RDX)

(1003) 0x487e4c VMOVSD	%XMM0,0x10(%RDX)

(1003) 0x487e51 VMOVSD	(%R15,%RAX,1),%XMM6

(1003) 0x487e57 VMOVSD	%XMM6,(%R14,%RAX,1)

(1003) 0x487e5d ADD	$0x8,%RAX

(1003) 0x487e61 ADD	$0x18,%RDX

(1003) 0x487e65 CMP	%RSI,%RAX

(1003) 0x487e68 JE	487f60

  (1004) 0x487e6e VMOVSD	(%R9,%RAX,1),%XMM8

  (1004) 0x487e74 VMOVSD	%XMM8,(%R8,%RAX,1)

  (1004) 0x487e7a VMOVSD	(%R12,%RAX,1),%XMM10

  (1004) 0x487e80 VMOVHPD	(%R13,%RAX,1),%XMM10,%XMM11

  (1004) 0x487e87 VMOVSD	(%RCX,%RAX,1),%XMM9

  (1004) 0x487e8c VMOVUPD	%XMM11,(%RDX)

  (1004) 0x487e90 VMOVSD	%XMM9,0x10(%RDX)

  (1004) 0x487e95 VMOVSD	(%R15,%RAX,1),%XMM12

  (1004) 0x487e9b VMOVSD	%XMM12,(%R14,%RAX,1)

  (1004) 0x487ea1 VMOVSD	0x8(%R9,%RAX,1),%XMM13

  (1004) 0x487ea8 VMOVSD	%XMM13,0x8(%RAX,%R8,1)

  (1004) 0x487eaf VMOVSD	0x8(%R12,%RAX,1),%XMM15

  (1004) 0x487eb6 VMOVHPD	0x8(%R13,%RAX,1),%XMM15,%XMM0

  (1004) 0x487ebd VMOVSD	0x8(%RCX,%RAX,1),%XMM14

  (1004) 0x487ec3 VMOVSD	%XMM14,0x28(%RDX)

  (1004) 0x487ec8 ADD	$0x60,%RDX

  (1004) 0x487ecc VMOVUPD	%XMM0,-0x48(%RDX)

  (1004) 0x487ed1 VMOVSD	0x8(%R15,%RAX,1),%XMM2

  (1004) 0x487ed8 VMOVSD	%XMM2,0x8(%RAX,%R14,1)

  (1004) 0x487edf VMOVSD	0x10(%R9,%RAX,1),%XMM5

  (1004) 0x487ee6 VMOVSD	%XMM5,0x10(%RAX,%R8,1)

  (1004) 0x487eed VMOVSD	0x10(%R12,%RAX,1),%XMM6

  (1004) 0x487ef4 VMOVHPD	0x10(%R13,%RAX,1),%XMM6,%XMM9

  (1004) 0x487efb VMOVSD	0x10(%RCX,%RAX,1),%XMM8

  (1004) 0x487f01 VMOVUPD	%XMM9,-0x30(%RDX)

  (1004) 0x487f06 VMOVSD	%XMM8,-0x20(%RDX)

  (1004) 0x487f0b VMOVSD	0x10(%R15,%RAX,1),%XMM10

  (1004) 0x487f12 VMOVSD	%XMM10,0x10(%RAX,%R14,1)

  (1004) 0x487f19 VMOVSD	0x18(%R9,%RAX,1),%XMM11

  (1004) 0x487f20 VMOVSD	%XMM11,0x18(%RAX,%R8,1)

  (1004) 0x487f27 VMOVSD	0x18(%R12,%RAX,1),%XMM13

  (1004) 0x487f2e VMOVHPD	0x18(%R13,%RAX,1),%XMM13,%XMM14

  (1004) 0x487f35 VMOVSD	0x18(%RCX,%RAX,1),%XMM12

  (1004) 0x487f3b VMOVUPD	%XMM14,-0x18(%RDX)

  (1004) 0x487f40 VMOVSD	%XMM12,-0x8(%RDX)

  (1004) 0x487f45 VMOVSD	0x18(%R15,%RAX,1),%XMM15

  (1004) 0x487f4c ADD	$0x20,%RAX

  (1004) 0x487f50 VMOVSD	%XMM15,-0x8(%RAX,%R14,1)

  (1004) 0x487f57 CMP	%RSI,%RAX

  (1004) 0x487f5a JNE	487e6e

(1003) 0x487f60 MOV	-0x58(%RBP),%R12

(1003) 0x487f64 MOV	-0x4c(%RBP),%ESI

(1003) 0x487f67 VMOVQ	%XMM1,%R9

(1003) 0x487f6c ADD	$0x18,%R10

(1003) 0x487f70 VPADDD	%XMM4,%XMM7,%XMM7

(1003) 0x487f74 ADD	%R9,%R11

(1003) 0x487f77 ADD	%ESI,-0x38(%RBP)

(1003) 0x487f7a ADDQ	$0x28,-0x48(%RBP)

(1003) 0x487f7f ADD	%R12,-0x40(%RBP)

(1003) 0x487f83 CMP	%R10,%R12

(1003) 0x487f86 JNE	487d20

0x487f8c ADD	$0x48,%RSP

0x487f90 POP	%RBX

0x487f91 POP	%R12

0x487f93 POP	%R13

0x487f95 POP	%R14

0x487f97 POP	%R15

0x487f99 POP	%RBP

0x487f9a RET

0x487f9b VMOVAPD	%XMM13,%XMM15

0x487fa0 JMP	487bd2

0x487fa5 NOPW	%CS:(%RAX,%RAX,1)

0x487faf NOP

Coverage (%)	Name	Source Location	Module
►36.33+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:100	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:196	exec
○	main._omp_fn.1	stl_vector.h:1131	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►24.78+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:100	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:196	exec
○	main._omp_fn.1	stl_vector.h:1131	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►17.84+	miniqmcreference::DiracDetermi[...]	OhmmsVector.h:210	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:171	exec
○	main._omp_fn.0	miniqmc.cpp:397	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►17.58+	miniqmcreference::DiracDetermi[...]	OhmmsVector.h:210	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:172	exec
○	main._omp_fn.0	miniqmc.cpp:397	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	__GI___clone3		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 0.00% of application time for run gcc_3

Source file and lines	einspline_spo_ref.hpp:203-230
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:203-211,219-230
/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/Utilities/NewTimer.h:242,249
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:145
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_vector.h:1131,1263
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algobase.h:238
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h:150-152
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:231,265,271

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 12.00 to 5.50 cycles (2.18x speedup).

Workaround

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

Vectorization

Your function is poorly vectorized. Only 14% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your function, you can lower the cost of an iteration from 12.00 to 1.15 cycles (10.48x speedup).

Details

28% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

23% of SSE/AVX loads are used in vector version.
0% of SSE/AVX stores are used in vector version.
50% of SSE/AVX addition or subtraction instructions are used in vector version.
50% of SSE/AVX multiply instructions are used in vector version.
50% of SSE/AVX fused multiply-add instructions are used in vector version.
42% of SSE/AVX 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)

Execution units bottlenecks

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

Masked instructions

Detected masked instructions.

Details

Vector registers are partially exploited, which is expected if your function is irregular or mixes elements of different sizes.

Workaround

If your function is irregular, try to remove or hoist conditional structures out of your function. If it mixes elements of different sizes, try to uniformize them.

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).

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.

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.

KMOVB: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
VCOMISD: 2 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
VMOVHPD: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp:206

Type of elements and instruction set

7 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 7 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (two 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 (6 inside FMA instructions)
9: multiply (6 inside FMA instructions)

The binary function is loading 160 bytes (20 double precision FP elements). The binary function is storing 80 bytes (10 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.07 FP operations per loaded or stored byte.

General properties

nb instructions	93
nb uops	96
loop length	429
used x86 registers	16
used mmx registers	0
used xmm registers	16
used ymm registers	0
used zmm registers	0
nb stack references	8
ADD-SUB / MUL ratio	1.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	12.00 cycles
front end	12.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.00	4.00	4.00	4.00	4.00	4.00	8.00	8.00	8.00	8.00	5.50	5.50	5.50	5.50	3.00	3.00
cycles	4.00	4.00	4.00	4.00	4.00	4.00	8.00	8.00	8.00	8.00	5.50	5.50	5.50	5.50	3.00	3.00

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	12.00
Dispatch	8.00
Overall L1	12.00

Vectorization ratios

INT

all	4%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	12%

all	46%
load	36%
store	0%
mul	50%
add-sub	50%
fma	50%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	61%

INT+FP

all	28%
load	23%
store	0%
mul	50%
add-sub	50%
fma	50%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	42%

Vector efficiency ratios

INT

all	8%
load	7%
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	9%

all	18%
load	17%
store	12%
mul	18%
add-sub	18%
fma	18%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	20%

INT+FP

all	14%
load	13%
store	10%
mul	18%
add-sub	18%
fma	18%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

Cycles and memory resources usage

Detected masked instructions: assuming all mask elements are active. Assuming all data fit into the L1 cache, each call to the function takes 12.00 cycles. At this rate:

5% of peak load performance is reached (13.33 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (6.67 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 12.00 to 8.00 cycles (1.50x speedup).

ASM code

In the binary file, the address of the function is: 487ad0

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
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,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB $0x48,%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 0x358(%RDI),%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	scal (12.5%)
MOV %RCX,-0x60(%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 %EDX,%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	N/A
MOV %R8,-0x68(%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 %R9,-0x70(%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 %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 531880 <_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
LEA 0x128(%R13),%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
CMP 0x124(%R13),%R15D	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%)
JE 487b21 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x51>	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 0x40(%R13),%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
LEA (%R15,%R15,2),%RDX	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
LEA (%RAX,%RDX,8),%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
VMOVUPD (%RCX),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVSD 0x10(%RCX),%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%)
VXORPD %XMM9,%XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM1,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP 0x138b85(%RIP),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMULSD 0x118(%RBX),%XMM1,%XMM6	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%)
VMOVSD (%RCX),%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%)
VFMADD231SD 0xe8(%RBX),%XMM5,%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VPERMILPD $0x3,%XMM0,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
VMULPD 0xf0(%RBX),%XMM4,%XMM8	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	vect (25.0%)
VPERMILPD $0,%XMM0,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
VUNPCKHPD %XMM0,%XMM0,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VFMADD231PD 0xd8(%RBX),%XMM3,%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	vect (25.0%)
VFMADD132PD 0x108(%RBX),%XMM8,%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	vect (25.0%)
VCMPPD $0x1,%XMM9,%XMM2,%K1	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	3	0.50	vect (25.0%)
VFMADD132SD 0x100(%RBX),%XMM6,%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VRNDSCALEPD $0x9,%XMM2,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50	vect (25.0%)
VCMPPD $0xe,%XMM10,%XMM2,%K0{%K1}	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	3	0.50	vect (25.0%)
KNOTB %K0,%K2	1	0	0	0	0	0	0	0	0	0	0	0.50	0	0	0.50	0	0	1	0.50	N/A
KMOVB %K2,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	4	1	N/A
AND $0x3,%ESI	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%)
VCOMISD 0x138b15(%RIP),%XMM7	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	6	0.50	scal (12.5%)
KMOVB %ESI,%K3	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	N/A
VSUBPD %XMM11,%XMM2,%XMM12{%K3}{z}	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	vect (25.0%)
JBE 487bc6 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0xf6>	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
VXORPD %XMM13,%XMM13,%XMM13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VCOMISD %XMM7,%XMM13	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JA 487f9b <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x4cb>	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
VRNDSCALESD $0x9,%XMM7,%XMM7,%XMM14	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
VSUBSD %XMM14,%XMM7,%XMM15	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%)
MOV 0x30(%RBX),%R8D	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 (6.3%)
VMOVHPD %XMM12,-0x38(%RBP)	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.50	0.50	9-11	0.50	scal (12.5%)
VMOVLPD %XMM12,-0x40(%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%)
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
TEST %R8D,%R8D	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 487cb8 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x1e8>	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
VMOVSD %XMM15,-0x48(%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 %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 531ac0 <_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 0x30(%RBX),%R12D	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 (6.3%)
MOV %R12D,-0x4c(%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 (6.3%)
TEST %R12D,%R12D	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 487f8c <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x4bc>	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
MOVSXD -0x4c(%RBP),%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
VMOVD 0x40(%RBX),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	8	0.50	scal (6.3%)
VMOVD 0x8(%RBX),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	8	0.50	scal (6.3%)
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
VMOVDQA %XMM4,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOVQ $0,-0x40(%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 (6.3%)
MOVQ $0,-0x48(%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 (6.3%)
MOVL $0,-0x38(%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 (6.3%)
LEA (,%R14,8),%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	0.25	N/A
LEA (%R14,%R14,2),%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
LEA (,%RAX,8),%R8	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
VMOVQ %R15,%XMM1	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
MOV %R8,-0x58(%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%)
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x48,%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
VMOVAPD %XMM13,%XMM15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 487bd2 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x102>	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
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 0.00% of application time for run gcc_3

Source file and lines	einspline_spo_ref.hpp:203-230
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:203-211,219-230
/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/Utilities/NewTimer.h:242,249
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:145
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_vector.h:1131,1263
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algobase.h:238
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorTensorOps.h:150-152
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:231,265,271

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 12.00 to 5.50 cycles (2.18x speedup).

Workaround

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

Vectorization

Details

28% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

23% of SSE/AVX loads are used in vector version.
0% of SSE/AVX stores are used in vector version.
50% of SSE/AVX addition or subtraction instructions are used in vector version.
50% of SSE/AVX multiply instructions are used in vector version.
50% of SSE/AVX fused multiply-add instructions are used in vector version.
42% of SSE/AVX 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)

Execution units bottlenecks

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

Masked instructions

Detected masked instructions.

Details

Vector registers are partially exploited, which is expected if your function is irregular or mixes elements of different sizes.

Workaround

If your function is irregular, try to remove or hoist conditional structures out of your function. If it mixes elements of different sizes, try to uniformize them.

FMA

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

Workaround

CALL instructions

Detected function call instructions.

Details

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.

KMOVB: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/CrystalLattice.h:170
VCOMISD: 2 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
VMOVHPD: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp:206

Type of elements and instruction set

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 160 bytes (20 double precision FP elements). The binary function is storing 80 bytes (10 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.07 FP operations per loaded or stored byte.

General properties

nb instructions	93
nb uops	96
loop length	429
used x86 registers	16
used mmx registers	0
used xmm registers	16
used ymm registers	0
used zmm registers	0
nb stack references	8
ADD-SUB / MUL ratio	1.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	12.00 cycles
front end	12.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.00	4.00	4.00	4.00	4.00	4.00	8.00	8.00	8.00	8.00	5.50	5.50	5.50	5.50	3.00	3.00
cycles	4.00	4.00	4.00	4.00	4.00	4.00	8.00	8.00	8.00	8.00	5.50	5.50	5.50	5.50	3.00	3.00

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	12.00
Dispatch	8.00
Overall L1	12.00

Vectorization ratios

INT

all	4%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	12%

all	46%
load	36%
store	0%
mul	50%
add-sub	50%
fma	50%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	61%

INT+FP

all	28%
load	23%
store	0%
mul	50%
add-sub	50%
fma	50%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	42%

Vector efficiency ratios

INT

all	8%
load	7%
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	9%

all	18%
load	17%
store	12%
mul	18%
add-sub	18%
fma	18%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	20%

INT+FP

all	14%
load	13%
store	10%
mul	18%
add-sub	18%
fma	18%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

Cycles and memory resources usage

Detected masked instructions: assuming all mask elements are active. Assuming all data fit into the L1 cache, each call to the function takes 12.00 cycles. At this rate:

5% of peak load performance is reached (13.33 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (6.67 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: 487ad0

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
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,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB $0x48,%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 0x358(%RDI),%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	scal (12.5%)
MOV %RCX,-0x60(%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 %EDX,%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	N/A
MOV %R8,-0x68(%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 %R9,-0x70(%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 %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 531880 <_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
LEA 0x128(%R13),%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
CMP 0x124(%R13),%R15D	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%)
JE 487b21 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x51>	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 0x40(%R13),%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
LEA (%R15,%R15,2),%RDX	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
LEA (%RAX,%RDX,8),%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
VMOVUPD (%RCX),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVSD 0x10(%RCX),%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%)
VXORPD %XMM9,%XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM1,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP 0x138b85(%RIP),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMULSD 0x118(%RBX),%XMM1,%XMM6	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%)
VMOVSD (%RCX),%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%)
VFMADD231SD 0xe8(%RBX),%XMM5,%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VPERMILPD $0x3,%XMM0,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
VMULPD 0xf0(%RBX),%XMM4,%XMM8	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	vect (25.0%)
VPERMILPD $0,%XMM0,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
VUNPCKHPD %XMM0,%XMM0,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VFMADD231PD 0xd8(%RBX),%XMM3,%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	vect (25.0%)
VFMADD132PD 0x108(%RBX),%XMM8,%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	vect (25.0%)
VCMPPD $0x1,%XMM9,%XMM2,%K1	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	3	0.50	vect (25.0%)
VFMADD132SD 0x100(%RBX),%XMM6,%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VRNDSCALEPD $0x9,%XMM2,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50	vect (25.0%)
VCMPPD $0xe,%XMM10,%XMM2,%K0{%K1}	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	3	0.50	vect (25.0%)
KNOTB %K0,%K2	1	0	0	0	0	0	0	0	0	0	0	0.50	0	0	0.50	0	0	1	0.50	N/A
KMOVB %K2,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	4	1	N/A
AND $0x3,%ESI	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%)
VCOMISD 0x138b15(%RIP),%XMM7	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	6	0.50	scal (12.5%)
KMOVB %ESI,%K3	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	N/A
VSUBPD %XMM11,%XMM2,%XMM12{%K3}{z}	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	vect (25.0%)
JBE 487bc6 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0xf6>	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
VXORPD %XMM13,%XMM13,%XMM13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VCOMISD %XMM7,%XMM13	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JA 487f9b <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x4cb>	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
VRNDSCALESD $0x9,%XMM7,%XMM7,%XMM14	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
VSUBSD %XMM14,%XMM7,%XMM15	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%)
MOV 0x30(%RBX),%R8D	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 (6.3%)
VMOVHPD %XMM12,-0x38(%RBP)	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.50	0.50	9-11	0.50	scal (12.5%)
VMOVLPD %XMM12,-0x40(%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%)
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
TEST %R8D,%R8D	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 487cb8 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x1e8>	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
VMOVSD %XMM15,-0x48(%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 %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 531ac0 <_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 0x30(%RBX),%R12D	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 (6.3%)
MOV %R12D,-0x4c(%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 (6.3%)
TEST %R12D,%R12D	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 487f8c <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x4bc>	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
MOVSXD -0x4c(%RBP),%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
VMOVD 0x40(%RBX),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	8	0.50	scal (6.3%)
VMOVD 0x8(%RBX),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	8	0.50	scal (6.3%)
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
VMOVDQA %XMM4,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOVQ $0,-0x40(%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 (6.3%)
MOVQ $0,-0x48(%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 (6.3%)
MOVL $0,-0x38(%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 (6.3%)
LEA (,%R14,8),%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	0.25	N/A
LEA (%R14,%R14,2),%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
LEA (,%RAX,8),%R8	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
VMOVQ %R15,%XMM1	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
MOV %R8,-0x58(%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%)
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x48,%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
VMOVAPD %XMM13,%XMM15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 487bd2 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0x102>	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
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 >&, qmcplusplus::Vector, std::allocator >...–	0.27	0.45
○Loop 1005 - einspline_spo_ref.hpp:206-207 - exec	0.00	0.01
▼Loop 1003 - einspline_spo_ref.hpp:219-227 - exec–	0.00	0.01
○Loop 1004 - einspline_spo_ref.hpp:223-227 - exec	0.27	0.44

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Masked instructions

Details

Workaround

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

Masked instructions

Details

Workaround

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