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): 0.09% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/RealSpacePositionsOMPTarget.h: 163 - 163

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

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

/home/eoseret/qaas_runs_GNR/173-773-5521/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_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h: 242 - 249

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

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

[...]

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

/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_GNR/173-773-5521/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/unique_ptr.h: 193 - 193

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

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

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 248

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

223:     return X[i];

[...]

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

/home/eoseret/qaas_runs_GNR/173-773-5521/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:   }

0x56a940 PUSH	%RBP

0x56a941 MOV	%RSP,%RBP

0x56a944 PUSH	%R15

0x56a946 MOV	%RSI,%R15

0x56a949 PUSH	%R14

0x56a94b PUSH	%R13

0x56a94d PUSH	%R12

0x56a94f MOV	$0x1,%R12D

0x56a955 PUSH	%RBX

0x56a956 MOV	%RDI,%RBX

0x56a959 AND	$-0x20,%RSP

0x56a95d SUB	$0x20,%RSP

0x56a961 MOV	0x278(%RDI),%RDI

0x56a968 MOV	%RDI,(%RSP)

0x56a96c CALL	52c850 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>

0x56a971 MOV	0x18(%RBX),%RAX

0x56a975 VMOVQ	0x4f2b3(%RIP),%XMM10

0x56a97d MOV	%RAX,0x8(%RSP)

0x56a982 CMP	$0x1,%RAX

0x56a986 JBE	56aeaf

0x56a98c NOPL	(%RAX)

(2624) 0x56a990 MOV	0x278(%R15),%RDI

(2624) 0x56a997 MOV	0x60(%RBX),%R14

(2624) 0x56a99b MOV	(%RDI),%RSI

(2624) 0x56a99e MOV	0x48(%RBX),%RDX

(2624) 0x56a9a2 LEA	(%R12,%R12,4),%RCX

(2624) 0x56a9a6 MOV	0x48(%RSI),%RAX

(2624) 0x56a9aa SAL	$0x3,%RCX

(2624) 0x56a9ae MOV	0x18(%RDX,%RCX,1),%R13

(2624) 0x56a9b3 ADD	%RCX,%R14

(2624) 0x56a9b6 CMP	$0x528ce0,%RAX

(2624) 0x56a9bc JNE	56aed0

(2624) 0x56a9c2 LEA	0x40(%RDI),%RAX

(2624) 0x56a9c6 MOV	0x8(%RAX),%RSI

(2624) 0x56a9ca MOV	0x8(%R14),%RCX

(2624) 0x56a9ce MOV	0x18(%RAX),%R8

(2624) 0x56a9d2 MOV	0x18(%R14),%RDX

(2624) 0x56a9d6 MOV	0x40(%R15),%R10

(2624) 0x56a9da LEA	(%R12,%R12,2),%R9

(2624) 0x56a9de SAL	$0x3,%RSI

(2624) 0x56a9e2 SAL	$0x3,%RCX

(2624) 0x56a9e6 LEA	(%R10,%R9,8),%R11

(2624) 0x56a9ea LEA	(%R8,%RSI,1),%RDI

(2624) 0x56a9ee LEA	(%RDX,%RCX,1),%RAX

(2624) 0x56a9f2 LEA	-0x1(%R12),%R9D

(2624) 0x56a9f7 VMOVSD	(%R11),%XMM3

(2624) 0x56a9fc VMOVSD	0x8(%R11),%XMM2

(2624) 0x56aa02 VMOVSD	0x10(%R11),%XMM1

(2624) 0x56aa08 ADD	%RAX,%RCX

(2624) 0x56aa0b ADD	%RDI,%RSI

(2624) 0x56aa0e MOV	%R12D,%R14D

(2624) 0x56aa11 CMP	$0x2,%R9D

(2624) 0x56aa15 JBE	56aef0

(2624) 0x56aa1b MOV	%R12D,%R11D

(2624) 0x56aa1e SHR	$0x2,%R11D

(2624) 0x56aa22 VBROADCASTSD	0x4f205(%RIP),%YMM6

(2624) 0x56aa2b VBROADCASTSD	0x4b46c(%RIP),%YMM5

(2624) 0x56aa34 VBROADCASTSD	%XMM3,%YMM9

(2624) 0x56aa39 VBROADCASTSD	%XMM2,%YMM8

(2624) 0x56aa3e VBROADCASTSD	%XMM1,%YMM7

(2624) 0x56aa43 SAL	$0x5,%R11

(2624) 0x56aa47 XOR	%R9D,%R9D

(2624) 0x56aa4a NOPW	(%RAX,%RAX,1)

  (2625) 0x56aa50 VMOVAPD	(%RDI,%R9,1),%YMM4

  (2625) 0x56aa56 VMOVAPD	(%R8,%R9,1),%YMM0

  (2625) 0x56aa5c VSUBPD	%YMM8,%YMM4,%YMM4

  (2625) 0x56aa61 VSUBPD	%YMM9,%YMM0,%YMM12

  (2625) 0x56aa66 VMOVAPD	(%RSI,%R9,1),%YMM11

  (2625) 0x56aa6c VMULPD	0x168(%RBX){1to4},%YMM4,%YMM14

  (2625) 0x56aa73 VMULPD	0x198(%RBX){1to4},%YMM4,%YMM13

  (2625) 0x56aa7a VSUBPD	%YMM7,%YMM11,%YMM0

  (2625) 0x56aa7e VFMADD231PD	0x160(%RBX){1to4},%YMM12,%YMM14

  (2625) 0x56aa85 VFMADD231PD	0x190(%RBX){1to4},%YMM12,%YMM13

  (2625) 0x56aa8c VMOVAPD	%YMM14,%YMM15

  (2625) 0x56aa91 VMULPD	0x180(%RBX){1to4},%YMM4,%YMM14

  (2625) 0x56aa98 VFMADD231PD	0x170(%RBX){1to4},%YMM0,%YMM15

  (2625) 0x56aa9f VFMADD231PD	0x178(%RBX){1to4},%YMM12,%YMM14

  (2625) 0x56aaa6 VMOVAPD	%YMM6,%YMM12

  (2625) 0x56aaaa VPTERNLOGQ	$-0x8,%YMM5,%YMM15,%YMM12

  (2625) 0x56aab1 VADDPD	%YMM12,%YMM15,%YMM4

  (2625) 0x56aab6 VFMADD231PD	0x188(%RBX){1to4},%YMM0,%YMM14

  (2625) 0x56aabd VFMADD132PD	0x1a0(%RBX){1to4},%YMM13,%YMM0

  (2625) 0x56aac4 VMOVAPD	%YMM6,%YMM13

  (2625) 0x56aac8 VRNDSCALEPD	$0x3,%YMM4,%YMM11

  (2625) 0x56aacf VPTERNLOGQ	$-0x8,%YMM5,%YMM14,%YMM13

  (2625) 0x56aad6 VADDPD	%YMM13,%YMM14,%YMM12

  (2625) 0x56aadb VRNDSCALEPD	$0x3,%YMM12,%YMM4

  (2625) 0x56aae2 VSUBPD	%YMM11,%YMM15,%YMM15

  (2625) 0x56aae7 VMOVAPD	%YMM6,%YMM11

  (2625) 0x56aaeb VPTERNLOGQ	$-0x8,%YMM5,%YMM0,%YMM11

  (2625) 0x56aaf2 VADDPD	%YMM11,%YMM0,%YMM13

  (2625) 0x56aaf7 VSUBPD	%YMM4,%YMM14,%YMM14

  (2625) 0x56aafb VRNDSCALEPD	$0x3,%YMM13,%YMM12

  (2625) 0x56ab02 VMULPD	0x120(%RBX){1to4},%YMM14,%YMM4

  (2625) 0x56ab09 VSUBPD	%YMM12,%YMM0,%YMM0

  (2625) 0x56ab0e VFMADD231PD	0x118(%RBX){1to4},%YMM15,%YMM4

  (2625) 0x56ab15 VFMADD231PD	0x128(%RBX){1to4},%YMM0,%YMM4

  (2625) 0x56ab1c VMOVAPD	%YMM4,(%RDX,%R9,1)

  (2625) 0x56ab22 VMULPD	0x138(%RBX){1to4},%YMM14,%YMM11

  (2625) 0x56ab29 VFMADD231PD	0x130(%RBX){1to4},%YMM15,%YMM11

  (2625) 0x56ab30 VFMADD231PD	0x140(%RBX){1to4},%YMM0,%YMM11

  (2625) 0x56ab37 VMOVAPD	%YMM11,(%RAX,%R9,1)

  (2625) 0x56ab3d VMULPD	0x150(%RBX){1to4},%YMM14,%YMM14

  (2625) 0x56ab44 VFMADD231PD	0x148(%RBX){1to4},%YMM15,%YMM14

  (2625) 0x56ab4b VFMADD132PD	0x158(%RBX){1to4},%YMM14,%YMM0

  (2625) 0x56ab52 VMOVAPD	%YMM0,(%RCX,%R9,1)

  (2625) 0x56ab58 VMOVAPD	(%RAX,%R9,1),%YMM13

  (2625) 0x56ab5e VMOVAPD	(%RDX,%R9,1),%YMM15

  (2625) 0x56ab64 VMULPD	%YMM13,%YMM13,%YMM12

  (2625) 0x56ab69 VFMADD132PD	%YMM15,%YMM12,%YMM15

  (2625) 0x56ab6e VFMADD132PD	%YMM0,%YMM15,%YMM0

  (2625) 0x56ab73 VSQRTPD	%YMM0,%YMM0

  (2625) 0x56ab77 VMOVAPD	%YMM0,(%R13,%R9,1)

  (2625) 0x56ab7e ADD	$0x20,%R9

  (2625) 0x56ab82 CMP	%R9,%R11

  (2625) 0x56ab85 JNE	56aa50

(2624) 0x56ab8b MOV	%R14D,%R9D

(2624) 0x56ab8e AND	$-0x4,%R9D

(2624) 0x56ab92 MOV	%R9D,%R10D

(2624) 0x56ab95 TEST	$0x3,%R14B

(2624) 0x56ab99 JE	56ae9b

(2624) 0x56ab9f SUB	%R9D,%R14D

(2624) 0x56aba2 MOV	%R14D,0x1c(%RSP)

(2624) 0x56aba7 VMOVDDUP	0x4b2f1(%RIP),%XMM7

(2624) 0x56abaf CMP	$0x1,%R14D

(2624) 0x56abb3 JE	56ad4b

(2624) 0x56abb9 VMOVAPD	(%R8,%R9,8),%XMM6

(2624) 0x56abbf VMOVAPD	(%RDI,%R9,8),%XMM4

(2624) 0x56abc5 VMOVDDUP	%XMM3,%XMM7

(2624) 0x56abc9 VMOVDDUP	%XMM2,%XMM5

(2624) 0x56abcd VSUBPD	%XMM7,%XMM6,%XMM15

(2624) 0x56abd1 VSUBPD	%XMM5,%XMM4,%XMM7

(2624) 0x56abd5 VMOVAPD	(%RSI,%R9,8),%XMM0

(2624) 0x56abdb VMOVDDUP	%XMM1,%XMM6

(2624) 0x56abdf VMULPD	0x168(%RBX){1to2},%XMM7,%XMM4

(2624) 0x56abe6 VMULPD	0x180(%RBX){1to2},%XMM7,%XMM5

(2624) 0x56abed VMULPD	0x198(%RBX){1to2},%XMM7,%XMM7

(2624) 0x56abf4 VSUBPD	%XMM6,%XMM0,%XMM0

(2624) 0x56abf8 VMOVDDUP	0x4f030(%RIP),%XMM6

(2624) 0x56ac00 VFMADD231PD	0x160(%RBX){1to2},%XMM15,%XMM4

(2624) 0x56ac07 VFMADD231PD	0x178(%RBX){1to2},%XMM15,%XMM5

(2624) 0x56ac0e VFMADD132PD	0x190(%RBX){1to2},%XMM7,%XMM15

(2624) 0x56ac15 VMOVDDUP	0x4b283(%RIP),%XMM7

(2624) 0x56ac1d VMOVDDUP	0x138(%RBX),%XMM11

(2624) 0x56ac25 VFMADD231PD	0x170(%RBX){1to2},%XMM0,%XMM4

(2624) 0x56ac2c VFMADD231PD	0x188(%RBX){1to2},%XMM0,%XMM5

(2624) 0x56ac33 VFMADD132PD	0x1a0(%RBX){1to2},%XMM15,%XMM0

(2624) 0x56ac3a VMOVAPD	%XMM6,%XMM15

(2624) 0x56ac3e VMOVDDUP	0x130(%RBX),%XMM9

(2624) 0x56ac46 VPTERNLOGQ	$-0x8,%XMM7,%XMM4,%XMM15

(2624) 0x56ac4d VADDPD	%XMM15,%XMM4,%XMM15

(2624) 0x56ac52 VMOVDDUP	0x150(%RBX),%XMM14

(2624) 0x56ac5a VMOVDDUP	0x140(%RBX),%XMM8

(2624) 0x56ac62 VRNDSCALEPD	$0x3,%XMM15,%XMM15

(2624) 0x56ac69 VMOVDDUP	0x148(%RBX),%XMM13

(2624) 0x56ac71 LEA	(,%R9,8),%R11

(2624) 0x56ac79 VMOVDDUP	0x158(%RBX),%XMM12

(2624) 0x56ac81 LEA	(%RDX,%R11,1),%R14

(2624) 0x56ac85 MOV	%R14,0x10(%RSP)

(2624) 0x56ac8a VSUBPD	%XMM15,%XMM4,%XMM4

(2624) 0x56ac8f VMOVAPD	%XMM6,%XMM15

(2624) 0x56ac93 VPTERNLOGQ	$-0x8,%XMM7,%XMM5,%XMM15

(2624) 0x56ac9a VADDPD	%XMM15,%XMM5,%XMM15

(2624) 0x56ac9f VPTERNLOGQ	$-0x8,%XMM7,%XMM0,%XMM6

(2624) 0x56aca6 VADDPD	%XMM6,%XMM0,%XMM6

(2624) 0x56acaa VRNDSCALEPD	$0x3,%XMM15,%XMM15

(2624) 0x56acb1 MOV	0x10(%RSP),%R9

(2624) 0x56acb6 LEA	(%RAX,%R11,1),%R14

(2624) 0x56acba VSUBPD	%XMM15,%XMM5,%XMM5

(2624) 0x56acbf VRNDSCALEPD	$0x3,%XMM6,%XMM15

(2624) 0x56acc6 VMULPD	%XMM11,%XMM5,%XMM11

(2624) 0x56accb VMULPD	0x120(%RBX){1to2},%XMM5,%XMM6

(2624) 0x56acd2 VSUBPD	%XMM15,%XMM0,%XMM0

(2624) 0x56acd7 VFMADD132PD	%XMM4,%XMM11,%XMM9

(2624) 0x56acdc VFMADD231PD	0x118(%RBX){1to2},%XMM4,%XMM6

(2624) 0x56ace3 VFMADD132PD	%XMM0,%XMM9,%XMM8

(2624) 0x56ace8 VMULPD	%XMM14,%XMM5,%XMM9

(2624) 0x56aced VFMADD231PD	0x128(%RBX){1to2},%XMM0,%XMM6

(2624) 0x56acf4 VFMADD132PD	%XMM13,%XMM9,%XMM4

(2624) 0x56acf9 VMOVAPD	%XMM6,(%R9)

(2624) 0x56acfe VMOVAPD	%XMM8,(%R14)

(2624) 0x56ad03 VFMADD132PD	%XMM12,%XMM4,%XMM0

(2624) 0x56ad08 VMOVAPD	%XMM0,(%RCX,%R11,1)

(2624) 0x56ad0e VMOVAPD	(%R14),%XMM13

(2624) 0x56ad13 VMOVAPD	(%R9),%XMM8

(2624) 0x56ad18 VMULPD	%XMM13,%XMM13,%XMM14

(2624) 0x56ad1d VFMADD132PD	%XMM8,%XMM14,%XMM8

(2624) 0x56ad22 VFMADD132PD	%XMM0,%XMM8,%XMM0

(2624) 0x56ad27 VSQRTPD	%XMM0,%XMM12

(2624) 0x56ad2b VMOVAPD	%XMM12,(%R13,%R11,1)

(2624) 0x56ad32 MOV	0x1c(%RSP),%R11D

(2624) 0x56ad37 TEST	$0x1,%R11B

(2624) 0x56ad3b JE	56ae9b

(2624) 0x56ad41 MOV	%R11D,%R14D

(2624) 0x56ad44 AND	$-0x2,%R14D

(2624) 0x56ad48 ADD	%R14D,%R10D

(2624) 0x56ad4b MOVSXD	%R10D,%R10

(2624) 0x56ad4e VMOVSD	(%RDI,%R10,8),%XMM5

(2624) 0x56ad54 VMOVSD	(%R8,%R10,8),%XMM4

(2624) 0x56ad5a VSUBSD	%XMM2,%XMM5,%XMM15

(2624) 0x56ad5e VMOVSD	(%RSI,%R10,8),%XMM2

(2624) 0x56ad64 VSUBSD	%XMM3,%XMM4,%XMM3

(2624) 0x56ad68 VMULSD	0x180(%RBX),%XMM15,%XMM6

(2624) 0x56ad70 VSUBSD	%XMM1,%XMM2,%XMM0

(2624) 0x56ad74 VMULSD	0x168(%RBX),%XMM15,%XMM1

(2624) 0x56ad7c VMULSD	0x198(%RBX),%XMM15,%XMM11

(2624) 0x56ad84 VMOVAPD	%XMM10,%XMM12

(2624) 0x56ad89 VFMADD231SD	0x178(%RBX),%XMM3,%XMM6

(2624) 0x56ad92 VMOVAPD	%XMM10,%XMM9

(2624) 0x56ad97 VFMADD231SD	0x160(%RBX),%XMM3,%XMM1

(2624) 0x56ada0 VFMADD132SD	0x190(%RBX),%XMM11,%XMM3

(2624) 0x56ada9 VMOVAPD	%XMM10,%XMM15

(2624) 0x56adae VFMADD231SD	0x188(%RBX),%XMM0,%XMM6

(2624) 0x56adb7 LEA	(,%R10,8),%R9

(2624) 0x56adbf VFMADD231SD	0x170(%RBX),%XMM0,%XMM1

(2624) 0x56adc8 VFMADD132SD	0x1a0(%RBX),%XMM3,%XMM0

(2624) 0x56add1 ADD	%R9,%RDX

(2624) 0x56add4 VPTERNLOGQ	$-0x8,%XMM7,%XMM6,%XMM12

(2624) 0x56addb VADDSD	%XMM12,%XMM6,%XMM4

(2624) 0x56ade0 VPTERNLOGQ	$-0x8,%XMM7,%XMM1,%XMM9

(2624) 0x56ade7 VADDSD	%XMM9,%XMM1,%XMM8

(2624) 0x56adec VRNDSCALESD	$0x3,%XMM4,%XMM4,%XMM3

(2624) 0x56adf3 VSUBSD	%XMM3,%XMM6,%XMM5

(2624) 0x56adf7 VRNDSCALESD	$0x3,%XMM8,%XMM8,%XMM13

(2624) 0x56adfe VSUBSD	%XMM13,%XMM1,%XMM14

(2624) 0x56ae03 VMULSD	0x120(%RBX),%XMM5,%XMM1

(2624) 0x56ae0b VPTERNLOGQ	$-0x8,%XMM7,%XMM0,%XMM15

(2624) 0x56ae12 VADDSD	%XMM15,%XMM0,%XMM7

(2624) 0x56ae17 ADD	%R9,%RAX

(2624) 0x56ae1a VFMADD231SD	0x118(%RBX),%XMM14,%XMM1

(2624) 0x56ae23 VRNDSCALESD	$0x3,%XMM7,%XMM7,%XMM2

(2624) 0x56ae2a VSUBSD	%XMM2,%XMM0,%XMM0

(2624) 0x56ae2e VFMADD231SD	0x128(%RBX),%XMM0,%XMM1

(2624) 0x56ae37 VMOVSD	%XMM1,(%RDX)

(2624) 0x56ae3b VMULSD	0x138(%RBX),%XMM5,%XMM6

(2624) 0x56ae43 VFMADD231SD	0x130(%RBX),%XMM14,%XMM6

(2624) 0x56ae4c VFMADD231SD	0x140(%RBX),%XMM0,%XMM6

(2624) 0x56ae55 VMOVSD	%XMM6,(%RAX)

(2624) 0x56ae59 VMULSD	0x150(%RBX),%XMM5,%XMM11

(2624) 0x56ae61 VFMADD132SD	0x148(%RBX),%XMM11,%XMM14

(2624) 0x56ae6a VFMADD132SD	0x158(%RBX),%XMM14,%XMM0

(2624) 0x56ae73 VMOVSD	%XMM0,(%RCX,%R9,1)

(2624) 0x56ae79 VMOVSD	(%RAX),%XMM8

(2624) 0x56ae7d VMOVSD	(%RDX),%XMM9

(2624) 0x56ae81 VMULSD	%XMM8,%XMM8,%XMM13

(2624) 0x56ae86 VFMADD132SD	%XMM9,%XMM13,%XMM9

(2624) 0x56ae8b VFMADD132SD	%XMM0,%XMM9,%XMM0

(2624) 0x56ae90 VSQRTSD	%XMM0,%XMM0,%XMM0

(2624) 0x56ae94 VMOVSD	%XMM0,(%R13,%R10,8)

(2624) 0x56ae9b MOV	0x8(%RSP),%R13

(2624) 0x56aea0 INC	%R12

(2624) 0x56aea3 CMP	%R13,%R12

(2624) 0x56aea6 JB	56a990

0x56aeac VZEROUPPER

0x56aeaf MOV	(%RSP),%RDI

0x56aeb3 CALL	52ca80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>

0x56aeb8 LEA	-0x28(%RBP),%RSP

0x56aebc POP	%RBX

0x56aebd POP	%R12

0x56aebf POP	%R13

0x56aec1 POP	%R14

0x56aec3 POP	%R15

0x56aec5 POP	%RBP

0x56aec6 RET

0x56aec7 NOPW	(%RAX,%RAX,1)

(2624) 0x56aed0 VZEROUPPER

(2624) 0x56aed3 CALL	%RAX

(2624) 0x56aed5 MOV	0x18(%RBX),%R8

(2624) 0x56aed9 VMOVQ	0x4ed4f(%RIP),%XMM10

(2624) 0x56aee1 MOV	%R8,0x8(%RSP)

(2624) 0x56aee6 JMP	56a9c6

0x56aeeb NOPL	(%RAX,%RAX,1)

(2624) 0x56aef0 XOR	%R9D,%R9D

(2624) 0x56aef3 XOR	%R10D,%R10D

(2624) 0x56aef6 JMP	56ab9f

0x56aefb MOV	%RAX,%RBX

0x56aefe MOV	(%RSP),%RDI

0x56af02 VZEROUPPER

0x56af05 CALL	52ca80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>

0x56af0a MOV	%RBX,%RDI

0x56af0d CALL	404260 <_Unwind_Resume@plt>

0x56af12 NOPW	%CS:(%RAX,%RAX,1)

0x56af1c NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►98.25+	qmcplusplus::ParticleSet::upda[...]	stl_vector.h:992	exec
○	main._omp_fn.0	miniqmc.cpp:397	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
►1.75+	qmcplusplus::ParticleSet::upda[...]	stl_vector.h:992	exec
○	main._omp_fn.0	miniqmc.cpp:397	exec
○	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0

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_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/RealSpacePositionsOMPTarget.h:163
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:271-273
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_vector.h:1131
/home/eoseret/qaas_runs_GNR/173-773-5521/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/unique_ptr.h:193
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,248
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableAAOMPTarget.h:179-187

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 8.00 to 1.33 cycles (6.00x 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 8.00 to 0.61 cycles (13.18x 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_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249
qmcplusplus::TimerType
::start(): 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242
qmcplusplus::TimerType
::stop(): 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249
- /home/eoseret/qaas_runs_GNR/173-773-5521/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.

VZEROUPPER: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableAAOMPTarget.h:184
- /home/eoseret/qaas_runs_GNR/173-773-5521/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	42
nb uops	48
loop length	158
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	8.00 cycles
front end	8.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	1.00	1.00	4.00	4.00	6.00	1.00	1.00	6.00	6.00	6.00	1.00	4.00
cycles	1.00	1.00	4.00	4.00	6.00	1.00	1.00	6.00	6.00	6.00	1.00	4.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	8.00
Dispatch	6.00
Overall L1	8.00

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 8.00 cycles. At this rate:

2% of peak load performance is reached (5.00 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (2.00 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 8.00 to 6.00 cycles (1.33x speedup).

ASM code

In the binary file, the address of the function is: 56a940

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSI,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV $0x1,%R12D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x20,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
SUB $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x278(%RDI),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 52c850 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x18(%RBX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVQ 0x4f2b3(%RIP),%XMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %RAX,0x8(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP $0x1,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JBE 56aeaf <_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x56f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
MOV (%RSP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 52ca80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
LEA -0x28(%RBP),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV (%RSP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 52ca80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 404260 <_Unwind_Resume@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/RealSpacePositionsOMPTarget.h:163
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:271-273
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_vector.h:1131
/home/eoseret/qaas_runs_GNR/173-773-5521/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/unique_ptr.h:193
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,248
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableAAOMPTarget.h:179-187

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 8.00 to 1.33 cycles (6.00x 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_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249
qmcplusplus::TimerType
::start(): 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242
qmcplusplus::TimerType
::stop(): 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:249
- /home/eoseret/qaas_runs_GNR/173-773-5521/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.

VZEROUPPER: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableAAOMPTarget.h:184
- /home/eoseret/qaas_runs_GNR/173-773-5521/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	42
nb uops	48
loop length	158
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	8.00 cycles
front end	8.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	1.00	1.00	4.00	4.00	6.00	1.00	1.00	6.00	6.00	6.00	1.00	4.00
cycles	1.00	1.00	4.00	4.00	6.00	1.00	1.00	6.00	6.00	6.00	1.00	4.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	8.00
Dispatch	6.00
Overall L1	8.00

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 8.00 cycles. At this rate:

2% of peak load performance is reached (5.00 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (2.00 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: 56a940

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSI,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV $0x1,%R12D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x20,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
SUB $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x278(%RDI),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 52c850 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x18(%RBX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVQ 0x4f2b3(%RIP),%XMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %RAX,0x8(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP $0x1,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JBE 56aeaf <_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x56f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
MOV (%RSP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 52ca80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
LEA -0x28(%RBP),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV (%RSP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 52ca80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 404260 <_Unwind_Resume@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼qmcplusplus::SoaDistanceTableAAOMPTarget::evaluate(qmcplusplus::ParticleSet&)–	0.09	0.07
▼Loop 2624 - SoaDistanceTableAAOMPTarget.h:184-185 - exec–	0.00	0.01
○Loop 2625 - ParticleBConds3DSoa.h:237-255 - exec	0.08	0.07

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex 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

Complex 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