OV - exec - Function miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int)

	Function: miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcp ...	Module: exec	Source: TwoBodyJastrowRef.h:310-355 [...]	Coverage (incl. loops): 0.94% \| (excl. loops): 0.01%

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 1128 - 1263

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

1128:       operator[](size_type __n) _GLIBCXX_NOEXCEPT

1129:       {

1130: 	__glibcxx_requires_subscript(__n);

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

[...]

1150: 	return *(this->_M_impl._M_start + __n);

[...]

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

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 249

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

223:     return X[i];

[...]

249:   inline const_pointer data() const { return X; }

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 310 - 355

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

310: void TwoBodyJastrowRef<FT>::acceptMove(ParticleSet& P, int iat)

311: {

312:   // get the old u, du, d2u

313:   const auto& d_table = P.getDistTableAA(myTableID);

314:   computeU3(P, iat, d_table.getDistRow(iat).data(), old_u.data(), old_du.data(), old_d2u.data());

315:   if (UpdateMode == ORB_PBYP_RATIO)

316:   { // ratio-only during the move; need to compute derivatives

317:     computeU3(P, iat, d_table.getTempDists().data(), cur_u.data(), cur_du.data(), cur_d2u.data());

318:   }

319:

320:   valT cur_d2Uat(0);

321:   const auto& new_dr    = d_table.getTempDispls();

322:   const auto& old_dr    = d_table.getDisplRow(iat);

323:   constexpr valT lapfac = OHMMS_DIM - RealType(1);

324:   for (int jat = 0; jat < N; jat++)

325:   {

326:     const valT du   = cur_u[jat] - old_u[jat];

327:     const valT newl = cur_d2u[jat] + lapfac * cur_du[jat];

328:     const valT dl   = old_d2u[jat] + lapfac * old_du[jat] - newl;

329:     Uat[jat] += du;

330:     d2Uat[jat] += dl;

331:     cur_d2Uat -= newl;

332:   }

333:   posT cur_dUat;

334:   for (int idim = 0; idim < OHMMS_DIM; ++idim)

[...]

341:     valT cur_g                     = cur_dUat[idim];

342:     for (int jat = 0; jat < N; jat++)

343:     {

344:       const valT newg = cur_du_pt[jat] * new_dX[jat];

345:       const valT dg   = newg - old_du_pt[jat] * old_dX[jat];

346:       save_g[jat] -= dg;

347:       cur_g += newg;

348:     }

349:     cur_dUat[idim] = cur_g;

350:   }

351:   LogValue += Uat[iat] - cur_Uat;

352:   Uat[iat]   = cur_Uat;

353:   dUat(iat)  = cur_dUat;

354:   d2Uat[iat] = cur_d2Uat;

355: }

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 243 - 271

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

243:       for (size_t i = 0; i < D; ++i)

244:         *(_base + M * i) = rhs[i];

[...]

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

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 61 - 62

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

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

62:       X[d] = T(0);

0x436100 STP	X29, X30, [SP, #912]!

0x436104 ADD	X29, SP, #0

0x436108 STP	X25, X26, [SP, #64]

0x43610c ORR	X25, XZR, X1

0x436110 MOVZ	W26, #40

0x436114 SMADDL	X26, W2, W26, XZR

0x436118 STP	X19, X20, [SP, #16]

0x43611c ORR	X20, XZR, X0

0x436120 STP	X21, X22, [SP, #32]

0x436124 ORR	W21, WZR, W2

0x436128 STP	X23, X24, [SP, #48]

0x43612c LDR	W1, [X0, #584]

0x436130 ORR	X0, XZR, X25

0x436134 BL	47e050

0x436138 LDR	X3, [X0, #72]

0x43613c ORR	X24, XZR, X0

0x436140 ORR	W2, WZR, W21

0x436144 ORR	X0, XZR, X20

0x436148 ORR	X1, XZR, X25

0x43614c LDR	X23, [X20, #392]

0x436150 MOVZ	W7, #0

0x436154 LDR	X19, [X20, #416]

0x436158 ADD	X4, X3, X26

0x43615c LDR	X22, [X20, #440]

0x436160 LDR	X3, [X4, #24]

0x436164 ORR	X4, XZR, X23

0x436168 ORR	X5, XZR, X19

0x43616c ORR	X6, XZR, X22

0x436170 BL	435240

0x436174 LDR	W0, [X20, #12]

0x436178 CBZ	W0, 4365e8

0x43617c LDR	X8, [X24, #96]

0x436180 LDR	X30, [X20, #144]

0x436184 LDR	X10, [X20, #216]

0x436188 ADD	X9, X8, X26

0x43618c LDR	X11, [X20, #296]

0x436190 LDR	X7, [X20, #344]

0x436194 CBZ	X30, 436628

(603) 0x436198 UBFM	X12, X30, #61, #60

(603) 0x43619c MOVI	D31, #0

(603) 0x4361a0 FMOV	D30, #2.0000000

(603) 0x4361a4 MOVZ	X1, #0

(603) 0x4361a8 SUB	X2, X12, #8

(603) 0x4361ac LDR	X14, [X20, #320]

(603) 0x4361b0 UBFM	X5, X2, #3, #63

(603) 0x4361b4 ADD	X6, X5, #1

(603) 0x4361b8 LDR	X15, [X20, #368]

(603) 0x4361bc ANDS	X13, X6, #4160

(603) 0x4361c0 B.EQ	4362b4

(603) 0x4361c4 CMP	X13, #1

(603) 0x4361c8 B.EQ	436264

(603) 0x4361cc CMP	X13, #2

(603) 0x4361d0 B.EQ	43621c

(603) 0x4361d4 LDR	D29, [X14]

(603) 0x4361d8 MOVZ	X1, #8

(603) 0x4361dc LDR	D23, [X10]

(603) 0x4361e0 LDR	D4, [X23]

(603) 0x4361e4 LDR	D26, [X15]

(603) 0x4361e8 FADD	D1, D29, D23

(603) 0x4361ec LDR	D27, [X7]

(603) 0x4361f0 LDR	D2, [X19]

(603) 0x4361f4 LDR	D25, [X22]

(603) 0x4361f8 FSUB	D3, D1, S4

(603) 0x4361fc FMADD	D0, D27, D30, D26

(603) 0x436200 FNMSUB	D5, D2, D30, D0

(603) 0x436204 STR	D3, [X10]

(603) 0x436208 LDR	D6, [X11]

(603) 0x43620c FNEG	D31, D0

(603) 0x436210 FADD	D7, D25, D6

(603) 0x436214 FADD	D16, D7, D5

(603) 0x436218 STR	D16, [X11]

(603) 0x43621c LDR	D28, [X14, X1]

(603) 0x436220 LDR	D20, [X10, X1]

(603) 0x436224 LDR	D17, [X23, X1]

(603) 0x436228 LDR	D18, [X7, X1]

(603) 0x43622c FADD	D19, D28, D20

(603) 0x436230 LDR	D21, [X15, X1]

(603) 0x436234 LDR	D24, [X19, X1]

(603) 0x436238 LDR	D22, [X22, X1]

(603) 0x43623c FSUB	D26, D19, S17

(603) 0x436240 FMADD	D29, D18, D30, D21

(603) 0x436244 FNMSUB	D27, D24, D30, D29

(603) 0x436248 STR	D26, [X10, X1]

(603) 0x43624c LDR	D0, [X11, X1]

(603) 0x436250 FSUB	D31, D31, S29

(603) 0x436254 FADD	D23, D22, D0

(603) 0x436258 FADD	D1, D23, D27

(603) 0x43625c STR	D1, [X11, X1]

(603) 0x436260 ADD	X1, X1, #8

(603) 0x436264 LDR	D2, [X14, X1]

(603) 0x436268 LDR	D5, [X10, X1]

(603) 0x43626c LDR	D25, [X23, X1]

(603) 0x436270 LDR	D3, [X7, X1]

(603) 0x436274 FADD	D7, D2, D5

(603) 0x436278 LDR	D6, [X15, X1]

(603) 0x43627c LDR	D4, [X19, X1]

(603) 0x436280 LDR	D16, [X22, X1]

(603) 0x436284 FSUB	D28, D7, S25

(603) 0x436288 FMADD	D20, D3, D30, D6

(603) 0x43628c FNMSUB	D17, D4, D30, D20

(603) 0x436290 STR	D28, [X10, X1]

(603) 0x436294 LDR	D18, [X11, X1]

(603) 0x436298 FSUB	D31, D31, S20

(603) 0x43629c FADD	D19, D16, D18

(603) 0x4362a0 FADD	D21, D19, D17

(603) 0x4362a4 STR	D21, [X11, X1]

(603) 0x4362a8 ADD	X1, X1, #8

(603) 0x4362ac CMP	X12, X1

(603) 0x4362b0 B.EQ	4363dc

  (602) 0x4362b4 LDR	D24, [X14, X1]

  (602) 0x4362b8 ADD	X16, X1, #8

  (602) 0x4362bc ADD	X18, X1, #16

  (602) 0x4362c0 ADD	X17, X1, #24

  (602) 0x4362c4 LDR	D22, [X10, X1]

  (602) 0x4362c8 LDR	D26, [X23, X1]

  (602) 0x4362cc LDR	D29, [X7, X1]

  (602) 0x4362d0 FADD	D27, D24, D22

  (602) 0x4362d4 LDR	D23, [X15, X1]

  (602) 0x4362d8 LDR	D0, [X19, X1]

  (602) 0x4362dc LDR	D2, [X22, X1]

  (602) 0x4362e0 FSUB	D1, D27, S26

  (602) 0x4362e4 FMADD	D5, D29, D30, D23

  (602) 0x4362e8 FNMSUB	D25, D0, D30, D5

  (602) 0x4362ec STR	D1, [X10, X1]

  (602) 0x4362f0 LDR	D3, [X11, X1]

  (602) 0x4362f4 FSUB	D7, D31, S5

  (602) 0x4362f8 FADD	D6, D2, D3

  (602) 0x4362fc FADD	D4, D6, D25

  (602) 0x436300 STR	D4, [X11, X1]

  (602) 0x436304 ADD	X1, X1, #32

  (602) 0x436308 LDR	D16, [X14, X16]

  (602) 0x43630c LDR	D28, [X10, X16]

  (602) 0x436310 LDR	D17, [X23, X16]

  (602) 0x436314 LDR	D31, [X7, X16]

  (602) 0x436318 FADD	D18, D16, D28

  (602) 0x43631c LDR	D20, [X15, X16]

  (602) 0x436320 LDR	D21, [X19, X16]

  (602) 0x436324 LDR	D19, [X22, X16]

  (602) 0x436328 FSUB	D24, D18, S17

  (602) 0x43632c FMADD	D22, D31, D30, D20

  (602) 0x436330 FNMSUB	D26, D21, D30, D22

  (602) 0x436334 STR	D24, [X10, X16]

  (602) 0x436338 LDR	D29, [X11, X16]

  (602) 0x43633c FSUB	D0, D7, S22

  (602) 0x436340 FADD	D27, D19, D29

  (602) 0x436344 FADD	D23, D27, D26

  (602) 0x436348 STR	D23, [X11, X16]

  (602) 0x43634c LDR	D2, [X14, X18]

  (602) 0x436350 LDR	D1, [X10, X18]

  (602) 0x436354 LDR	D25, [X23, X18]

  (602) 0x436358 LDR	D5, [X7, X18]

  (602) 0x43635c FADD	D7, D2, D1

  (602) 0x436360 LDR	D6, [X15, X18]

  (602) 0x436364 LDR	D3, [X19, X18]

  (602) 0x436368 LDR	D16, [X22, X18]

  (602) 0x43636c FSUB	D28, D7, S25

  (602) 0x436370 FMADD	D4, D5, D30, D6

  (602) 0x436374 FNMSUB	D17, D3, D30, D4

  (602) 0x436378 STR	D28, [X10, X18]

  (602) 0x43637c LDR	D18, [X11, X18]

  (602) 0x436380 FSUB	D31, D0, S4

  (602) 0x436384 FADD	D20, D16, D18

  (602) 0x436388 FADD	D21, D20, D17

  (602) 0x43638c STR	D21, [X11, X18]

  (602) 0x436390 LDR	D19, [X14, X17]

  (602) 0x436394 LDR	D24, [X23, X17]

  (602) 0x436398 LDR	D22, [X7, X17]

  (602) 0x43639c LDR	D26, [X10, X17]

  (602) 0x4363a0 LDR	D29, [X15, X17]

  (602) 0x4363a4 LDR	D27, [X19, X17]

  (602) 0x4363a8 FADD	D23, D19, D26

  (602) 0x4363ac LDR	D0, [X22, X17]

  (602) 0x4363b0 FMADD	D2, D22, D30, D29

  (602) 0x4363b4 FSUB	D1, D23, S24

  (602) 0x4363b8 FNMSUB	D25, D27, D30, D2

  (602) 0x4363bc STR	D1, [X10, X17]

  (602) 0x4363c0 FSUB	D31, D31, S2

  (602) 0x4363c4 LDR	D5, [X11, X17]

  (602) 0x4363c8 FADD	D7, D0, D5

  (602) 0x4363cc FADD	D6, D7, D25

  (602) 0x4363d0 STR	D6, [X11, X17]

  (602) 0x4363d4 CMP	X12, X1

  (602) 0x4363d8 B.NE	4362b4

(603) 0x4363dc LDR	X3, [X9, #8]

(603) 0x4363e0 MOVI	D28, #0

(603) 0x4363e4 ADD	X25, SP, #88

(603) 0x4363e8 ORR	X26, XZR, X25

(603) 0x4363ec LDR	X4, [X24, #168]

(603) 0x4363f0 LDR	X22, [X20, #240]

(603) 0x4363f4 UBFM	X23, X3, #61, #60

(603) 0x4363f8 STR	D28, [SP, #104]

(603) 0x4363fc LDR	X13, [X20, #256]

(603) 0x436400 LDR	X8, [X9, #24]

(603) 0x436404 UBFM	X2, X22, #61, #60

(603) 0x436408 LDR	X9, [X24, #184]

(603) 0x43640c UBFM	X24, X4, #61, #60

(603) 0x436410 ORR	X3, XZR, X13

(603) 0x436414 STP	D28, D28, [SP, #88]

  (604) 0x436418 CBZ	X30, 43656c

  (604) 0x43641c SUB	X0, X12, #8

  (604) 0x436420 MOVZ	X15, #0

  (604) 0x436424 UBFM	X5, X0, #3, #63

  (604) 0x436428 ADD	X6, X5, #1

  (604) 0x43642c ANDS	X14, X6, #4160

  (604) 0x436430 B.EQ	4364c4

  (604) 0x436434 CMP	X14, #1

  (604) 0x436438 B.EQ	436494

  (604) 0x43643c CMP	X14, #2

  (604) 0x436440 B.EQ	43646c

  (604) 0x436444 LDR	D30, [X3]

  (604) 0x436448 MOVZ	X15, #8

  (604) 0x43644c LDR	D16, [X8]

  (604) 0x436450 LDR	D17, [X19]

  (604) 0x436454 LDR	D3, [X7]

  (604) 0x436458 LDR	D4, [X9]

  (604) 0x43645c FMADD	D18, D17, D16, D30

  (604) 0x436460 FMADD	D28, D3, D4, D28

  (604) 0x436464 FMSUB	D20, D3, D4, D18

  (604) 0x436468 STR	D20, [X3]

  (604) 0x43646c LDR	D21, [X19, X15]

  (604) 0x436470 LDR	D19, [X8, X15]

  (604) 0x436474 LDR	D24, [X3, X15]

  (604) 0x436478 LDR	D22, [X7, X15]

  (604) 0x43647c LDR	D26, [X9, X15]

  (604) 0x436480 FMADD	D29, D21, D19, D24

  (604) 0x436484 FMADD	D28, D22, D26, D28

  (604) 0x436488 FMSUB	D27, D22, D26, D29

  (604) 0x43648c STR	D27, [X3, X15]

  (604) 0x436490 ADD	X15, X15, #8

  (604) 0x436494 LDR	D0, [X19, X15]

  (604) 0x436498 LDR	D2, [X8, X15]

  (604) 0x43649c LDR	D23, [X3, X15]

  (604) 0x4364a0 LDR	D1, [X7, X15]

  (604) 0x4364a4 LDR	D25, [X9, X15]

  (604) 0x4364a8 FMADD	D5, D0, D2, D23

  (604) 0x4364ac FMADD	D28, D1, D25, D28

  (604) 0x4364b0 FMSUB	D7, D1, D25, D5

  (604) 0x4364b4 STR	D7, [X3, X15]

  (604) 0x4364b8 ADD	X15, X15, #8

  (604) 0x4364bc CMP	X15, X12

  (604) 0x4364c0 B.EQ	43656c

    (605) 0x4364c4 LDR	D6, [X19, X15]

    (605) 0x4364c8 ADD	X1, X15, #8

    (605) 0x4364cc ADD	X17, X15, #16

    (605) 0x4364d0 ADD	X16, X15, #24

    (605) 0x4364d4 LDR	D30, [X8, X15]

    (605) 0x4364d8 LDR	D3, [X3, X15]

    (605) 0x4364dc LDR	D16, [X7, X15]

    (605) 0x4364e0 LDR	D4, [X9, X15]

    (605) 0x4364e4 FMADD	D17, D6, D30, D3

    (605) 0x4364e8 FMADD	D24, D16, D4, D28

    (605) 0x4364ec FMSUB	D18, D16, D4, D17

    (605) 0x4364f0 STR	D18, [X3, X15]

    (605) 0x4364f4 ADD	X15, X15, #32

    (605) 0x4364f8 LDR	D21, [X19, X1]

    (605) 0x4364fc LDR	D22, [X8, X1]

    (605) 0x436500 LDR	D26, [X3, X1]

    (605) 0x436504 LDR	D20, [X7, X1]

    (605) 0x436508 LDR	D19, [X9, X1]

    (605) 0x43650c FMADD	D29, D21, D22, D26

    (605) 0x436510 FMADD	D27, D20, D19, D24

    (605) 0x436514 FMSUB	D0, D20, D19, D29

    (605) 0x436518 STR	D0, [X3, X1]

    (605) 0x43651c LDR	D2, [X19, X17]

    (605) 0x436520 LDR	D23, [X8, X17]

    (605) 0x436524 LDR	D1, [X3, X17]

    (605) 0x436528 LDR	D25, [X7, X17]

    (605) 0x43652c LDR	D5, [X9, X17]

    (605) 0x436530 FMADD	D7, D2, D23, D1

    (605) 0x436534 FMADD	D28, D25, D5, D27

    (605) 0x436538 FMSUB	D6, D25, D5, D7

    (605) 0x43653c STR	D6, [X3, X17]

    (605) 0x436540 LDR	D30, [X19, X16]

    (605) 0x436544 LDR	D3, [X8, X16]

    (605) 0x436548 LDR	D16, [X3, X16]

    (605) 0x43654c LDR	D4, [X7, X16]

    (605) 0x436550 LDR	D17, [X9, X16]

    (605) 0x436554 FMADD	D24, D30, D3, D16

    (605) 0x436558 FMADD	D28, D4, D17, D28

    (605) 0x43655c FMSUB	D18, D4, D17, D24

    (605) 0x436560 STR	D18, [X3, X16]

    (605) 0x436564 CMP	X15, X12

    (605) 0x436568 B.NE	4364c4

  (604) 0x43656c ADD	X18, SP, #112

  (604) 0x436570 STR	D28, [X26], #8

  (604) 0x436574 CMP	X18, X26

  (604) 0x436578 B.EQ	436590

  (604) 0x43657c LDR	D28, [X26]

  (604) 0x436580 ADD	X9, X9, X24

  (604) 0x436584 ADD	X8, X8, X23

  (604) 0x436588 ADD	X3, X3, X2

  (604) 0x43658c B	436418

(603) 0x436590 LDR	D22, [X20, #16]

(603) 0x436594 SBFM	X21, X21, #61, #31

(603) 0x436598 LDR	D26, [X20, #312]

(603) 0x43659c LDR	D21, [X10, X21]

(603) 0x4365a0 FSUB	D20, D22, S26

(603) 0x4365a4 FADD	D19, D20, D21

(603) 0x4365a8 STR	D19, [X20, #16]

(603) 0x4365ac STR	D26, [X10, X21]

(603) 0x4365b0 CMP	X22, #1

(603) 0x4365b4 B.NE	436634

(603) 0x4365b8 LDR	X10, [X25, #16]

(603) 0x4365bc ADD	X30, X13, X21

(603) 0x4365c0 LDP	X8, X9, [SP, #88]

(603) 0x4365c4 STR	X10, [X30, #16]

(603) 0x4365c8 STP	X8, X9, [X30]

(603) 0x4365cc STR	D31, [X11, X21]

(603) 0x4365d0 LDP	X19, X20, [SP, #16]

(603) 0x4365d4 LDP	X21, X22, [SP, #32]

(603) 0x4365d8 LDP	X23, X24, [SP, #48]

(603) 0x4365dc LDP	X25, X26, [SP, #64]

(603) 0x4365e0 LDP	X29, X30, [SP], #112

(603) 0x4365e4 RET

(603) 0x4365e8 LDR	X3, [X24, #144]

(603) 0x4365ec MOVZ	W7, #0

(603) 0x4365f0 ORR	X1, XZR, X25

(603) 0x4365f4 ORR	W2, WZR, W21

(603) 0x4365f8 ORR	X0, XZR, X20

(603) 0x4365fc LDR	X4, [X20, #320]

(603) 0x436600 LDR	X5, [X20, #344]

(603) 0x436604 LDR	X6, [X20, #368]

(603) 0x436608 BL	435240

(603) 0x43660c LDR	X8, [X24, #96]

(603) 0x436610 LDR	X30, [X20, #144]

(603) 0x436614 LDR	X10, [X20, #216]

(603) 0x436618 ADD	X9, X8, X26

(603) 0x43661c LDR	X11, [X20, #296]

(603) 0x436620 LDR	X7, [X20, #344]

(603) 0x436624 CBNZ	X30, 436198

(603) 0x436628 MOVI	D31, #0

(603) 0x43662c MOVZ	X12, #0

(603) 0x436630 B	4363dc

0x436634 LDR	D29, [SP, #88]

0x436638 ADD	X20, X13, X22,LSL #4

0x43663c ADD	X19, X13, X21

0x436640 LDR	D27, [SP, #96]

0x436644 LDR	D0, [SP, #104]

0x436648 STR	D29, [X13, X21]

0x43664c STR	D27, [X19, X2]

0x436650 STR	D0, [X20, X21]

0x436654 STR	D31, [X11, X21]

0x436658 LDP	X19, X20, [SP, #16]

0x43665c LDP	X21, X22, [SP, #32]

0x436660 LDP	X23, X24, [SP, #48]

0x436664 LDP	X25, X26, [SP, #64]

0x436668 LDP	X29, X30, [SP], #112

0x43666c RET

0x436670 HINT	#0

0x436674 HINT	#0

0x436678 HINT	#0

0x43667c HINT	#0

Coverage (%)	Name	Source Location	Module
►98.86+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	miniqmc.cpp:451	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6

min	med	avg	max

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

min	med	avg	max

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

Path /

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

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run gcc_4

Source file and lines	TwoBodyJastrowRef.h:310-355
Module	exec

The function is defined in:

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h:1128-1131,1150,1263
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:310-334,341-355
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:243-244,271
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:61-62

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 9.83 to 3.33 cycles (2.95x speedup).

Workaround

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

Vectorization

Your function is not vectorized. Only 57% of vector register length is used (average across all VPU instructions). By vectorizing your function, you can lower the cost of an iteration from 9.83 to 7.00 cycles (1.40x speedup).

Details

All VPU 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)

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 9.83 to 1.00 cycles (9.83x speedup).

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 192 bytes. The binary function is storing 112 bytes.

General properties

nb instructions	57
loop length	228
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

6.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	2.50	2.50	3.67	3.67	3.67	3.67	3.67	3.67	2.00	2.00	0.00	0.00	9.83	9.50	9.67	2.50	2.50
cycles	2.50	2.50	3.67	3.67	3.67	3.67	3.67	3.67	2.00	2.00	0.00	0.00	9.83	9.50	9.67	2.50	2.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	6.63
Overall L1	9.83

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 9.83 cycles. At this rate:

20% of peak load performance is reached (19.53 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
23% of peak store performance is reached (11.39 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 436100

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #912]!	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ADD X29, SP, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR X25, XZR, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
MOVZ W26, #40	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
SMADDL X26, W2, W26, XZR	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR X20, XZR, X0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR W21, WZR, W2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
LDR W1, [X0, #584]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ORR X0, XZR, X25	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
BL 47e050 <_ZNK11qmcplusplus11ParticleSet14getDistTableAAEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X3, [X0, #72]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ORR X24, XZR, X0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ORR W2, WZR, W21	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ORR X0, XZR, X20	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ORR X1, XZR, X25	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
LDR X23, [X20, #392]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
MOVZ W7, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
LDR X19, [X20, #416]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X4, X3, X26	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LDR X22, [X20, #440]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR X3, [X4, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ORR X4, XZR, X23	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ORR X5, XZR, X19	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ORR X6, XZR, X22	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
BL 435240 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR W0, [X20, #12]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ W0, 4365e8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x4e8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [X24, #96]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR X30, [X20, #144]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR X10, [X20, #216]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X9, X8, X26	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
LDR X11, [X20, #296]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X7, [X20, #344]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBZ X30, 436628 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x528>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR D29, [SP, #88]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
ADD X20, X13, X22,LSL #4	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD X19, X13, X21	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LDR D27, [SP, #96]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
LDR D0, [SP, #104]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
STR D29, [X13, X21]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
STR D27, [X19, X2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
STR D0, [X20, X21]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
STR D31, [X11, X21]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	N/A
LDP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	N/A
LDP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	N/A
LDP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	scal (100.0%)
LDP X29, X30, [SP], #112	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	scal (100.0%)
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run gcc_4

Source file and lines	TwoBodyJastrowRef.h:310-355
Module	exec

The function is defined in:

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h:1128-1131,1150,1263
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:310-334,341-355
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:243-244,271
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:61-62

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 9.83 to 3.33 cycles (2.95x speedup).

Workaround

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

Vectorization

Details

All VPU 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)

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 9.83 to 1.00 cycles (9.83x speedup).

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 192 bytes. The binary function is storing 112 bytes.

General properties

nb instructions	57
loop length	228
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

6.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	2.50	2.50	3.67	3.67	3.67	3.67	3.67	3.67	2.00	2.00	0.00	0.00	9.83	9.50	9.67	2.50	2.50
cycles	2.50	2.50	3.67	3.67	3.67	3.67	3.67	3.67	2.00	2.00	0.00	0.00	9.83	9.50	9.67	2.50	2.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	6.63
Overall L1	9.83

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 9.83 cycles. At this rate:

20% of peak load performance is reached (19.53 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
23% of peak store performance is reached (11.39 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 436100

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #912]!	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ADD X29, SP, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR X25, XZR, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
MOVZ W26, #40	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
SMADDL X26, W2, W26, XZR	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR X20, XZR, X0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR W21, WZR, W2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
LDR W1, [X0, #584]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ORR X0, XZR, X25	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
BL 47e050 <_ZNK11qmcplusplus11ParticleSet14getDistTableAAEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X3, [X0, #72]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ORR X24, XZR, X0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ORR W2, WZR, W21	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ORR X0, XZR, X20	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ORR X1, XZR, X25	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
LDR X23, [X20, #392]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
MOVZ W7, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
LDR X19, [X20, #416]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X4, X3, X26	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LDR X22, [X20, #440]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR X3, [X4, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ORR X4, XZR, X23	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ORR X5, XZR, X19	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ORR X6, XZR, X22	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
BL 435240 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR W0, [X20, #12]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ W0, 4365e8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x4e8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [X24, #96]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR X30, [X20, #144]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
LDR X10, [X20, #216]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X9, X8, X26	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
LDR X11, [X20, #296]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X7, [X20, #344]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBZ X30, 436628 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x528>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR D29, [SP, #88]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
ADD X20, X13, X22,LSL #4	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD X19, X13, X21	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LDR D27, [SP, #96]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
LDR D0, [SP, #104]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
STR D29, [X13, X21]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
STR D27, [X19, X2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
STR D0, [X20, X21]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
STR D31, [X11, X21]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	N/A
LDP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	N/A
LDP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	N/A
LDP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	scal (100.0%)
LDP X29, X30, [SP], #112	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	scal (100.0%)
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::TwoBodyJastrowRef >::acceptMove(qmcplusplus::ParticleSet&, int)–	0.94	1.30
▼Loop 603 - TwoBodyJastrowRef.h:317-355 - exec–	0.01	0.01
○Loop 602 - TwoBodyJastrowRef.h:324-331 - exec	0.23	0.32
▼Loop 604 - TwoBodyJastrowRef.h:334-349 - exec–	0.00	0.01
○Loop 605 - TwoBodyJastrowRef.h:342-347 - exec	0.69	0.95

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code