OV - exec - Function qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::evaluate(qmcplusplus::ParticleSet&)

	Function: qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::evaluate(qmcplusplus::ParticleSe ...	Module: exec	Source: SoaDistanceTableAAOMPTarget.h:179-187 [...]	Coverage (incl. loops): 0.16% \| (excl. loops): 0.00%

/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/Particle/Lattice/ParticleBConds3DSoa.h: 222 - 255

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

222:     const T x0 = pos[0];

223:     const T y0 = pos[1];

224:     const T z0 = pos[2];

[...]

234: #pragma omp simd aligned(temp_r, px, py, pz, dx, dy, dz: QMC_SIMD_ALIGNMENT)

235:     for (int iat = first; iat < last; ++iat)

236:     {

237:       T displ_0 = px[iat] - x0;

238:       T displ_1 = py[iat] - y0;

239:       T displ_2 = pz[iat] - z0;

240:

241:       T ar_0 = displ_0 * g00 + displ_1 * g10 + displ_2 * g20;

242:       T ar_1 = displ_0 * g01 + displ_1 * g11 + displ_2 * g21;

243:       T ar_2 = displ_0 * g02 + displ_1 * g12 + displ_2 * g22;

244:

245:       //put them in the box

246:       ar_0 -= round(ar_0);

247:       ar_1 -= round(ar_1);

248:       ar_2 -= round(ar_2);

249:

250:       //unit2cart

251:       dx[iat] = ar_0 * r00 + ar_1 * r10 + ar_2 * r20;

252:       dy[iat] = ar_0 * r01 + ar_1 * r11 + ar_2 * r21;

253:       dz[iat] = ar_0 * r02 + ar_1 * r12 + ar_2 * r22;

254:

255:       temp_r[iat] = std::sqrt(dx[iat] * dx[iat] + dy[iat] * dy[iat] + dz[iat] * dz[iat]);

/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_vector.h: 1131 - 1131

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

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 248

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

223:     return X[i];

[...]

248:   inline pointer data() { return X; }

/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/unique_ptr.h: 193 - 193

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

193:       pointer    _M_ptr() const noexcept { return std::get<0>(_M_t); }

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableAAOMPTarget.h: 179 - 187

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

179:   inline void evaluate(ParticleSet& P) override

180:   {

181:     ScopedTimer local_timer(evaluate_timer_);

182:

183:     constexpr T BigR = std::numeric_limits<T>::max();

184:     for (int iat = 1; iat < num_targets_; ++iat)

185:       DTD_BConds<T, D, SC>::computeDistances(P.R[iat], P.getCoordinates().getAllParticlePos(), distances_[iat].data(),

186:                                              displacements_[iat], 0, iat, iat);

187:   }

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 271 - 273

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

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

272:   ///return the const pointer of the i-th components

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/RealSpacePositionsOMPTarget.h: 163 - 163

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

163:   const PosVectorSoa& getAllParticlePos() const override { return RSoA_hostview; }

0x5703d0 PUSH	%RBP

0x5703d1 MOV	%RSP,%RBP

0x5703d4 PUSH	%R15

0x5703d6 PUSH	%R14

0x5703d8 PUSH	%R13

0x5703da PUSH	%R12

0x5703dc PUSH	%RBX

0x5703dd MOV	%RDI,%RBX

0x5703e0 MOV	%RSI,%R15

0x5703e3 AND	$-0x20,%RSP

0x5703e7 MOV	$0x1,%R13D

0x5703ed SUB	$0x20,%RSP

0x5703f1 MOV	0x278(%RDI),%RDI

0x5703f8 MOV	%RDI,0x8(%RSP)

0x5703fd CALL	531880 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>

0x570402 MOV	0x18(%RBX),%RAX

0x570406 VMOVQ	0x527a2(%RIP),%XMM11

0x57040e MOV	%RAX,0x10(%RSP)

0x570413 CMP	$0x1,%RAX

0x570417 JBE	57091f

0x57041d NOPL	(%RAX)

(2595) 0x570420 MOV	0x278(%R15),%RDI

(2595) 0x570427 MOV	0x60(%RBX),%R9

(2595) 0x57042b MOV	0x48(%RBX),%RDX

(2595) 0x57042f LEA	(%R13,%R13,4),%RCX

(2595) 0x570434 SAL	$0x3,%RCX

(2595) 0x570438 MOV	(%RDI),%R8

(2595) 0x57043b MOV	0x18(%RDX,%RCX,1),%R14

(2595) 0x570440 ADD	%RCX,%R9

(2595) 0x570443 MOV	0x48(%R8),%R12

(2595) 0x570447 CMP	$0x52db10,%R12

(2595) 0x57044e JNE	570940

(2595) 0x570454 LEA	0x40(%RDI),%RAX

(2595) 0x570458 MOV	0x40(%R15),%R11

(2595) 0x57045c LEA	(%R13,%R13,2),%R10

(2595) 0x570461 MOV	0x8(%R9),%RSI

(2595) 0x570465 MOV	0x18(%RAX),%R12

(2595) 0x570469 MOV	0x18(%R9),%RCX

(2595) 0x57046d MOV	%R13D,%R9D

(2595) 0x570470 LEA	(%R11,%R10,8),%RDI

(2595) 0x570474 VMOVSD	(%RDI),%XMM3

(2595) 0x570478 VMOVSD	0x8(%RDI),%XMM2

(2595) 0x57047d VMOVSD	0x10(%RDI),%XMM1

(2595) 0x570482 MOV	0x8(%RAX),%RDI

(2595) 0x570486 LEA	-0x1(%R13),%EAX

(2595) 0x57048a SAL	$0x3,%RSI

(2595) 0x57048e LEA	(%RCX,%RSI,1),%RDX

(2595) 0x570492 SAL	$0x3,%RDI

(2595) 0x570496 LEA	(%R12,%RDI,1),%R11

(2595) 0x57049a ADD	%RDX,%RSI

(2595) 0x57049d ADD	%R11,%RDI

(2595) 0x5704a0 CMP	$0x2,%EAX

(2595) 0x5704a3 JBE	570970

(2595) 0x5704a9 VBROADCASTSD	0x526fe(%RIP),%YMM6

(2595) 0x5704b2 VBROADCASTSD	0x4e9d5(%RIP),%YMM5

(2595) 0x5704bb MOV	%R13D,%R8D

(2595) 0x5704be VBROADCASTSD	%XMM3,%YMM10

(2595) 0x5704c3 SHR	$0x2,%R8D

(2595) 0x5704c7 VBROADCASTSD	%XMM2,%YMM9

(2595) 0x5704cc VBROADCASTSD	%XMM1,%YMM8

(2595) 0x5704d1 SAL	$0x5,%R8

(2595) 0x5704d5 XOR	%R10D,%R10D

(2595) 0x5704d8 NOPL	(%RAX,%RAX,1)

  (2596) 0x5704e0 VMOVAPD	(%R11,%R10,1),%YMM4

  (2596) 0x5704e6 VMOVAPD	(%R12,%R10,1),%YMM7

  (2596) 0x5704ec VMOVAPD	(%RDI,%R10,1),%YMM0

  (2596) 0x5704f2 VSUBPD	%YMM9,%YMM4,%YMM12

  (2596) 0x5704f7 VSUBPD	%YMM10,%YMM7,%YMM14

  (2596) 0x5704fc VSUBPD	%YMM8,%YMM0,%YMM0

  (2596) 0x570501 VMULPD	0x168(%RBX){1to4},%YMM12,%YMM15

  (2596) 0x570508 VMULPD	0x180(%RBX){1to4},%YMM12,%YMM7

  (2596) 0x57050f VMULPD	0x198(%RBX){1to4},%YMM12,%YMM13

  (2596) 0x570516 VFMADD231PD	0x160(%RBX){1to4},%YMM14,%YMM15

  (2596) 0x57051d VFMADD231PD	0x178(%RBX){1to4},%YMM14,%YMM7

  (2596) 0x570524 VFMADD231PD	0x190(%RBX){1to4},%YMM14,%YMM13

  (2596) 0x57052b VMOVAPD	%YMM6,%YMM14

  (2596) 0x57052f VFMADD231PD	0x170(%RBX){1to4},%YMM0,%YMM15

  (2596) 0x570536 VFMADD231PD	0x188(%RBX){1to4},%YMM0,%YMM7

  (2596) 0x57053d VFMADD132PD	0x1a0(%RBX){1to4},%YMM13,%YMM0

  (2596) 0x570544 VMOVAPD	%YMM6,%YMM13

  (2596) 0x570548 VPTERNLOGQ	$-0x8,%YMM5,%YMM15,%YMM14

  (2596) 0x57054f VPTERNLOGQ	$-0x8,%YMM5,%YMM7,%YMM13

  (2596) 0x570556 VADDPD	%YMM14,%YMM15,%YMM4

  (2596) 0x57055b VADDPD	%YMM13,%YMM7,%YMM14

  (2596) 0x570560 VRNDSCALEPD	$0x3,%YMM4,%YMM12

  (2596) 0x570567 VRNDSCALEPD	$0x3,%YMM14,%YMM4

  (2596) 0x57056e VSUBPD	%YMM12,%YMM15,%YMM15

  (2596) 0x570573 VMOVAPD	%YMM6,%YMM12

  (2596) 0x570577 VPTERNLOGQ	$-0x8,%YMM5,%YMM0,%YMM12

  (2596) 0x57057e VADDPD	%YMM12,%YMM0,%YMM13

  (2596) 0x570583 VSUBPD	%YMM4,%YMM7,%YMM7

  (2596) 0x570587 VRNDSCALEPD	$0x3,%YMM13,%YMM14

  (2596) 0x57058e VMULPD	0x120(%RBX){1to4},%YMM7,%YMM4

  (2596) 0x570595 VFMADD231PD	0x118(%RBX){1to4},%YMM15,%YMM4

  (2596) 0x57059c VSUBPD	%YMM14,%YMM0,%YMM0

  (2596) 0x5705a1 VFMADD231PD	0x128(%RBX){1to4},%YMM0,%YMM4

  (2596) 0x5705a8 VMOVAPD	%YMM4,(%RCX,%R10,1)

  (2596) 0x5705ae VMULPD	0x138(%RBX){1to4},%YMM7,%YMM12

  (2596) 0x5705b5 VFMADD231PD	0x130(%RBX){1to4},%YMM15,%YMM12

  (2596) 0x5705bc VFMADD231PD	0x140(%RBX){1to4},%YMM0,%YMM12

  (2596) 0x5705c3 VMOVAPD	%YMM12,(%RDX,%R10,1)

  (2596) 0x5705c9 VMULPD	0x150(%RBX){1to4},%YMM7,%YMM7

  (2596) 0x5705d0 VFMADD231PD	0x148(%RBX){1to4},%YMM15,%YMM7

  (2596) 0x5705d7 VFMADD132PD	0x158(%RBX){1to4},%YMM7,%YMM0

  (2596) 0x5705de VMOVAPD	%YMM0,(%RSI,%R10,1)

  (2596) 0x5705e4 VMOVAPD	(%RDX,%R10,1),%YMM13

  (2596) 0x5705ea VMOVAPD	(%RCX,%R10,1),%YMM15

  (2596) 0x5705f0 VMULPD	%YMM13,%YMM13,%YMM14

  (2596) 0x5705f5 VFMADD132PD	%YMM15,%YMM14,%YMM15

  (2596) 0x5705fa VFMADD132PD	%YMM0,%YMM15,%YMM0

  (2596) 0x5705ff VSQRTPD	%YMM0,%YMM0

  (2596) 0x570603 VMOVAPD	%YMM0,(%R14,%R10,1)

  (2596) 0x570609 ADD	$0x20,%R10

  (2596) 0x57060d CMP	%R10,%R8

  (2596) 0x570610 JNE	5704e0

(2595) 0x570616 MOV	%R9D,%EAX

(2595) 0x570619 AND	$-0x4,%EAX

(2595) 0x57061c MOV	%EAX,0x18(%RSP)

(2595) 0x570620 TEST	$0x3,%R9B

(2595) 0x570624 JE	57090b

(2595) 0x57062a SUB	%EAX,%R9D

(2595) 0x57062d VMOVDDUP	0x4e85b(%RIP),%XMM14

(2595) 0x570635 CMP	$0x1,%R9D

(2595) 0x570639 JE	5707c4

(2595) 0x57063f SAL	$0x3,%RAX

(2595) 0x570643 VMOVDDUP	%XMM2,%XMM5

(2595) 0x570647 VMOVDDUP	%XMM3,%XMM8

(2595) 0x57064b VMOVDDUP	0x138(%RBX),%XMM12

(2595) 0x570653 VMOVDDUP	0x130(%RBX),%XMM10

(2595) 0x57065b VMOVDDUP	0x140(%RBX),%XMM9

(2595) 0x570663 VMOVDDUP	0x150(%RBX),%XMM17

(2595) 0x57066a VMOVDDUP	0x148(%RBX),%XMM16

(2595) 0x570671 VMOVAPD	(%R11,%RAX,1),%XMM4

(2595) 0x570677 VMOVAPD	(%R12,%RAX,1),%XMM6

(2595) 0x57067d VMOVAPD	(%RDI,%RAX,1),%XMM0

(2595) 0x570682 VMOVDDUP	0x158(%RBX),%XMM15

(2595) 0x57068a LEA	(%RCX,%RAX,1),%R8

(2595) 0x57068e LEA	(%RDX,%RAX,1),%R10

(2595) 0x570692 VSUBPD	%XMM5,%XMM4,%XMM14

(2595) 0x570696 VSUBPD	%XMM8,%XMM6,%XMM13

(2595) 0x57069b VMOVDDUP	%XMM1,%XMM8

(2595) 0x57069f VSUBPD	%XMM8,%XMM0,%XMM0

(2595) 0x5706a4 VMULPD	0x168(%RBX){1to2},%XMM14,%XMM4

(2595) 0x5706ab VMULPD	0x180(%RBX){1to2},%XMM14,%XMM5

(2595) 0x5706b2 VMULPD	0x198(%RBX){1to2},%XMM14,%XMM6

(2595) 0x5706b9 VMOVDDUP	0x4e7cf(%RIP),%XMM14

(2595) 0x5706c1 VFMADD231PD	0x160(%RBX){1to2},%XMM13,%XMM4

(2595) 0x5706c8 VFMADD231PD	0x178(%RBX){1to2},%XMM13,%XMM5

(2595) 0x5706cf VFMADD132PD	0x190(%RBX){1to2},%XMM6,%XMM13

(2595) 0x5706d6 VFMADD231PD	0x170(%RBX){1to2},%XMM0,%XMM4

(2595) 0x5706dd VFMADD231PD	0x188(%RBX){1to2},%XMM0,%XMM5

(2595) 0x5706e4 VFMADD132PD	0x1a0(%RBX){1to2},%XMM13,%XMM0

(2595) 0x5706eb VMOVDDUP	0x524bd(%RIP),%XMM13

(2595) 0x5706f3 VMOVAPD	%XMM13,%XMM18

(2595) 0x5706f9 VMOVAPD	%XMM13,%XMM21

(2595) 0x5706ff VPTERNLOGQ	$-0x8,%XMM14,%XMM4,%XMM18

(2595) 0x570706 VPTERNLOGQ	$-0x8,%XMM14,%XMM5,%XMM21

(2595) 0x57070d VADDPD	%XMM18,%XMM4,%XMM19

(2595) 0x570713 VADDPD	%XMM21,%XMM5,%XMM22

(2595) 0x570719 VPTERNLOGQ	$-0x8,%XMM14,%XMM0,%XMM13

(2595) 0x570720 VRNDSCALEPD	$0x3,%XMM19,%XMM20

(2595) 0x570727 VRNDSCALEPD	$0x3,%XMM22,%XMM23

(2595) 0x57072e VSUBPD	%XMM20,%XMM4,%XMM8

(2595) 0x570734 VSUBPD	%XMM23,%XMM5,%XMM4

(2595) 0x57073a VADDPD	%XMM13,%XMM0,%XMM5

(2595) 0x57073f VRNDSCALEPD	$0x3,%XMM5,%XMM6

(2595) 0x570746 VMULPD	%XMM12,%XMM4,%XMM7

(2595) 0x57074b VMULPD	0x120(%RBX){1to2},%XMM4,%XMM13

(2595) 0x570752 VFMADD132PD	%XMM8,%XMM7,%XMM10

(2595) 0x570757 VFMADD231PD	0x118(%RBX){1to2},%XMM8,%XMM13

(2595) 0x57075e VSUBPD	%XMM6,%XMM0,%XMM0

(2595) 0x570762 VFMADD132PD	%XMM0,%XMM10,%XMM9

(2595) 0x570767 VMULPD	%XMM17,%XMM4,%XMM10

(2595) 0x57076d VFMADD231PD	0x128(%RBX){1to2},%XMM0,%XMM13

(2595) 0x570774 VFMADD132PD	%XMM16,%XMM10,%XMM8

(2595) 0x57077a VMOVAPD	%XMM13,(%R8)

(2595) 0x57077f VMOVAPD	%XMM9,(%R10)

(2595) 0x570784 VFMADD132PD	%XMM15,%XMM8,%XMM0

(2595) 0x570789 VMOVAPD	%XMM0,(%RSI,%RAX,1)

(2595) 0x57078e VMOVAPD	(%R10),%XMM9

(2595) 0x570793 VMOVAPD	(%R8),%XMM12

(2595) 0x570798 VMULPD	%XMM9,%XMM9,%XMM15

(2595) 0x57079d VFMADD132PD	%XMM12,%XMM15,%XMM12

(2595) 0x5707a2 VFMADD132PD	%XMM0,%XMM12,%XMM0

(2595) 0x5707a7 VSQRTPD	%XMM0,%XMM8

(2595) 0x5707ab VMOVAPD	%XMM8,(%R14,%RAX,1)

(2595) 0x5707b1 TEST	$0x1,%R9B

(2595) 0x5707b5 JE	57090b

(2595) 0x5707bb AND	$-0x2,%R9D

(2595) 0x5707bf ADD	%R9D,0x18(%RSP)

(2595) 0x5707c4 MOVSXD	0x18(%RSP),%R9

(2595) 0x5707c9 SAL	$0x3,%R9

(2595) 0x5707cd VMOVSD	(%R12,%R9,1),%XMM4

(2595) 0x5707d3 VMOVSD	(%R11,%R9,1),%XMM5

(2595) 0x5707d9 VSUBSD	%XMM3,%XMM4,%XMM3

(2595) 0x5707dd VSUBSD	%XMM2,%XMM5,%XMM6

(2595) 0x5707e1 VMOVSD	(%RDI,%R9,1),%XMM2

(2595) 0x5707e7 VMULSD	0x198(%RBX),%XMM6,%XMM7

(2595) 0x5707ef VSUBSD	%XMM1,%XMM2,%XMM0

(2595) 0x5707f3 VMULSD	0x180(%RBX),%XMM6,%XMM13

(2595) 0x5707fb VMULSD	0x168(%RBX),%XMM6,%XMM1

(2595) 0x570803 VFMADD231SD	0x178(%RBX),%XMM3,%XMM13

(2595) 0x57080c VFMADD231SD	0x160(%RBX),%XMM3,%XMM1

(2595) 0x570815 VFMADD231SD	0x188(%RBX),%XMM0,%XMM13

(2595) 0x57081e VFMADD231SD	0x170(%RBX),%XMM0,%XMM1

(2595) 0x570827 VFMADD132SD	0x190(%RBX),%XMM7,%XMM3

(2595) 0x570830 VFMADD132SD	0x1a0(%RBX),%XMM3,%XMM0

(2595) 0x570839 VMOVAPD	%XMM11,%XMM3

(2595) 0x57083d VPTERNLOGQ	$-0x8,%XMM14,%XMM1,%XMM3

(2595) 0x570844 ADD	%R9,%RCX

(2595) 0x570847 ADD	%R9,%RDX

(2595) 0x57084a VADDSD	%XMM3,%XMM1,%XMM10

(2595) 0x57084e VMOVAPD	%XMM11,%XMM3

(2595) 0x570852 VRNDSCALESD	$0x3,%XMM10,%XMM10,%XMM12

(2595) 0x570859 VSUBSD	%XMM12,%XMM1,%XMM9

(2595) 0x57085e VPTERNLOGQ	$-0x8,%XMM14,%XMM13,%XMM3

(2595) 0x570865 VADDSD	%XMM3,%XMM13,%XMM15

(2595) 0x570869 VMOVAPD	%XMM11,%XMM3

(2595) 0x57086d VRNDSCALESD	$0x3,%XMM15,%XMM15,%XMM8

(2595) 0x570874 VSUBSD	%XMM8,%XMM13,%XMM4

(2595) 0x570879 VPTERNLOGQ	$-0x8,%XMM14,%XMM0,%XMM3

(2595) 0x570880 VMULSD	0x120(%RBX),%XMM4,%XMM2

(2595) 0x570888 VFMADD231SD	0x118(%RBX),%XMM9,%XMM2

(2595) 0x570891 VADDSD	%XMM3,%XMM0,%XMM14

(2595) 0x570895 VRNDSCALESD	$0x3,%XMM14,%XMM14,%XMM5

(2595) 0x57089c VSUBSD	%XMM5,%XMM0,%XMM6

(2595) 0x5708a0 VFMADD231SD	0x128(%RBX),%XMM6,%XMM2

(2595) 0x5708a9 VMOVSD	%XMM2,(%RCX)

(2595) 0x5708ad VMULSD	0x138(%RBX),%XMM4,%XMM0

(2595) 0x5708b5 VFMADD231SD	0x130(%RBX),%XMM9,%XMM0

(2595) 0x5708be VFMADD231SD	0x140(%RBX),%XMM6,%XMM0

(2595) 0x5708c7 VMOVSD	%XMM0,(%RDX)

(2595) 0x5708cb VMULSD	0x150(%RBX),%XMM4,%XMM1

(2595) 0x5708d3 VFMADD132SD	0x148(%RBX),%XMM1,%XMM9

(2595) 0x5708dc VFMADD132SD	0x158(%RBX),%XMM9,%XMM6

(2595) 0x5708e5 VMOVSD	%XMM6,(%RSI,%R9,1)

(2595) 0x5708eb VMOVSD	(%RCX),%XMM13

(2595) 0x5708ef VMOVSD	(%RDX),%XMM7

(2595) 0x5708f3 VMULSD	%XMM7,%XMM7,%XMM10

(2595) 0x5708f7 VFMADD132SD	%XMM13,%XMM10,%XMM13

(2595) 0x5708fc VFMADD132SD	%XMM6,%XMM13,%XMM6

(2595) 0x570901 VSQRTSD	%XMM6,%XMM6,%XMM6

(2595) 0x570905 VMOVSD	%XMM6,(%R14,%R9,1)

(2595) 0x57090b MOV	0x10(%RSP),%R14

(2595) 0x570910 INC	%R13

(2595) 0x570913 CMP	%R14,%R13

(2595) 0x570916 JB	570420

0x57091c VZEROUPPER

0x57091f MOV	0x8(%RSP),%RDI

0x570924 CALL	531ac0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>

0x570929 LEA	-0x28(%RBP),%RSP

0x57092d POP	%RBX

0x57092e POP	%R12

0x570930 POP	%R13

0x570932 POP	%R14

0x570934 POP	%R15

0x570936 POP	%RBP

0x570937 RET

0x570938 NOPL	(%RAX,%RAX,1)

(2595) 0x570940 MOV	%R9,0x18(%RSP)

(2595) 0x570945 VZEROUPPER

(2595) 0x570948 CALL	%R12

(2595) 0x57094b MOV	0x18(%RBX),%RSI

(2595) 0x57094f MOV	0x18(%RSP),%R9

(2595) 0x570954 VMOVQ	0x52254(%RIP),%XMM11

(2595) 0x57095c MOV	%RSI,0x10(%RSP)

(2595) 0x570961 JMP	570458

0x570966 NOPW	%CS:(%RAX,%RAX,1)

(2595) 0x570970 XOR	%EAX,%EAX

(2595) 0x570972 MOVL	$0,0x18(%RSP)

(2595) 0x57097a JMP	57062a

0x57097f MOV	%RAX,%RBX

0x570982 MOV	0x8(%RSP),%RDI

0x570987 VZEROUPPER

0x57098a CALL	531ac0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>

0x57098f MOV	%RBX,%RDI

0x570992 CALL	404240 <_Unwind_Resume@plt>

0x570997 NOPW	(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
►97.29+	qmcplusplus::ParticleSet::upda[...]	ParticleSet.cpp:242	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
►2.71+	qmcplusplus::ParticleSet::upda[...]	ParticleSet.cpp:242	exec
○	main._omp_fn.0	miniqmc.cpp:397	exec
○	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0
○	main	refwrap.h:350	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	miniqmc.cpp:321	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 0.00% of application time for run gcc_3

Source file and lines	SoaDistanceTableAAOMPTarget.h:179-187
Module	exec

The function is defined in:

/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/Particle/Lattice/ParticleBConds3DSoa.h:222-224,234-255
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_vector.h:1131
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,248
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/unique_ptr.h:193
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableAAOMPTarget.h:179-187
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:271-273
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/RealSpacePositionsOMPTarget.h:163

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 5.13 to 0.75 cycles (6.83x 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 15% 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 5.13 to 0.39 cycles (13.12x 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.

No data for this section

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.

_Unwind_Resume@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249
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(): 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 40 bytes. The binary function is storing 16 bytes.

General properties

nb instructions	41
nb uops	41
loop length	159
used x86 registers	10
used mmx registers	0
used xmm registers	1
used ymm registers	0
used zmm registers	0
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	5.13 cycles
front end	5.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	1.67	1.67	1.67	2.00	2.00	2.00	2.75	2.75	2.75	2.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	1.67	1.67	1.67	2.00	2.00	2.00	2.75	2.75	2.75	2.75	0.00	0.00	0.00	0.00	0.00	0.00

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	5.13
Dispatch	2.75
Overall L1	5.13

Vectorization ratios

all	28%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	50%

Vector efficiency ratios

all	15%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	17%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 5.13 cycles. At this rate:

3% of peak load performance is reached (7.80 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (3.12 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 5.13 to 2.75 cycles (1.86x speedup).

ASM code

In the binary file, the address of the function is: 5703d0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	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	0.17	N/A
PUSH %R15	1	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	1	0.50	N/A
PUSH %R13	1	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	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RSI,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
SUB $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x278(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,0x8(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CALL 531880 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV 0x18(%RBX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
VMOVQ 0x527a2(%RIP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
MOV %RAX,0x10(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP $0x1,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JBE 57091f <_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x54f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
MOV 0x8(%RSP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	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	0.50	N/A
LEA -0x28(%RBP),%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
POP %RBX	1	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	1	0.33	N/A
POP %R13	1	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	1	0.33	N/A
POP %R15	1	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	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x8(%RSP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 531ac0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 404240 <_Unwind_Resume@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
NOPW (%RAX,%RAX,1)	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	SoaDistanceTableAAOMPTarget.h:179-187
Module	exec

The function is defined in:

/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/Particle/Lattice/ParticleBConds3DSoa.h:222-224,234-255
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_vector.h:1131
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,248
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/unique_ptr.h:193
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableAAOMPTarget.h:179-187
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:271-273
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/RealSpacePositionsOMPTarget.h:163

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 5.13 to 0.75 cycles (6.83x 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.

No data for this section

CALL instructions

Detected function call instructions.

Details

_Unwind_Resume@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249
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(): 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 40 bytes. The binary function is storing 16 bytes.

General properties

nb instructions	41
nb uops	41
loop length	159
used x86 registers	10
used mmx registers	0
used xmm registers	1
used ymm registers	0
used zmm registers	0
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	5.13 cycles
front end	5.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	1.67	1.67	1.67	2.00	2.00	2.00	2.75	2.75	2.75	2.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	1.67	1.67	1.67	2.00	2.00	2.00	2.75	2.75	2.75	2.75	0.00	0.00	0.00	0.00	0.00	0.00

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	5.13
Dispatch	2.75
Overall L1	5.13

Vectorization ratios

all	28%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	50%

Vector efficiency ratios

all	15%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	17%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 5.13 cycles. At this rate:

3% of peak load performance is reached (7.80 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (3.12 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: 5703d0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	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	0.17	N/A
PUSH %R15	1	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	1	0.50	N/A
PUSH %R13	1	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	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RSI,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
SUB $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x278(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,0x8(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CALL 531880 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV 0x18(%RBX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
VMOVQ 0x527a2(%RIP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
MOV %RAX,0x10(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP $0x1,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JBE 57091f <_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x54f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
MOV 0x8(%RSP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	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	0.50	N/A
LEA -0x28(%RBP),%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
POP %RBX	1	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	1	0.33	N/A
POP %R13	1	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	1	0.33	N/A
POP %R15	1	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	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x8(%RSP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 531ac0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 404240 <_Unwind_Resume@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼qmcplusplus::SoaDistanceTableAAOMPTarget::evaluate(qmcplusplus::ParticleSet&)–	0.16	0.26
▼Loop 2595 - SoaDistanceTableAAOMPTarget.h:184-187 - exec–	0.00	0.01
○Loop 2596 - ParticleBConds3DSoa.h:237-255 - exec	0.16	0.26

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Type of elements and instruction set

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

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

CALL instructions

Details

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code