OV - exec - Function qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::move(qmcplusplus::ParticleSet const&, qmcplusplus::TinyVector<double, 3u> const&, int, bool)

	Function: qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::move(qmcplusplus::ParticleSet co ...	Module: exec	Source: SoaDistanceTableABOMPTarget.h:358-368 [...]	Coverage: 0.13%

/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/unique_ptr.h: 193 - 193

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

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

/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Particle/RealSpacePositionsOMPTarget.h: 163 - 163

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

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

/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h: 242 - 249

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

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

[...]

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

/home/hbollore/qaas-runs/171-275-7410/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]);

/home/hbollore/qaas-runs/171-275-7410/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/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 229 - 248

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

229:     return X[i];

[...]

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

/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_vector.h: 1131 - 1131

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

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

/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableABOMPTarget.h: 358 - 368

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

358:   inline void move(const ParticleSet& P, const PosType& rnew, const IndexType iat, bool prepare_old) override

359:   {

360:     ScopedTimer local_timer(move_timer_);

361:     DTD_BConds<T, D, SC>::computeDistances(rnew, origin_.getCoordinates().getAllParticlePos(), temp_r_.data(), temp_dr_,

362:                                            0, num_sources_);

363:     // If the full table is not ready all the time, overwrite the current value.

364:     // If this step is missing, DT values can be undefined in case a move is rejected.

365:     if (!(modes_ & DTModes::NEED_FULL_TABLE_ANYTIME) && prepare_old)

366:       DTD_BConds<T, D, SC>::computeDistances(P.R[iat], origin_.getCoordinates().getAllParticlePos(),

367:                                              distances_[iat].data(), displacements_[iat], 0, num_sources_);

368:   }

0x50fb40 STP	X29, X30, [SP, #944]!

0x50fb44 ADD	X29, SP, #0

0x50fb48 STP	X19, X20, [SP, #16]

0x50fb4c ORR	X19, XZR, X0

0x50fb50 ORR	W20, WZR, W3

0x50fb54 STP	X21, X22, [SP, #32]

0x50fb58 ORR	X22, XZR, X1

0x50fb5c STP	X23, X24, [SP, #48]

0x50fb60 ORR	X24, XZR, X2

0x50fb64 AND	W23, W4, #448

0x50fb68 LDR	X21, [X0, #448]

0x50fb6c STR	X25, [SP, #64]

0x50fb70 ADRP	X25,

0x50fb74 ADD	X25, X25, #2208

0x50fb78 ORR	X0, XZR, X21

0x50fb7c BL	4c43c0

0x50fb80 LDR	X0, [X19, #8]

0x50fb84 LDR	X0, [X0, #632]

0x50fb88 LDR	X1, [X0]

0x50fb8c LDR	X2, [X1, #72]

0x50fb90 CMP	X2, X25

0x50fb94 B.NE	50fee4

0x50fb98 ADD	X0, X0, #64

(3891) 0x50fb9c LDR	X7, [X0, #8]

(3891) 0x50fba0 LDR	X12, [X19, #16]

(3891) 0x50fba4 LDR	X8, [X0, #24]

(3891) 0x50fba8 LDR	X6, [X19, #168]

(3891) 0x50fbac ORR	W11, WZR, W12

(3891) 0x50fbb0 LDR	X15, [X19, #184]

(3891) 0x50fbb4 ADD	X9, X8, X7,LSL #3

(3891) 0x50fbb8 LDR	D29, [X24, #16]

(3891) 0x50fbbc ADD	X13, X8, X7,LSL #4

(3891) 0x50fbc0 LDR	X14, [X19, #144]

(3891) 0x50fbc4 ADD	X5, X15, X6,LSL #3

(3891) 0x50fbc8 LDP	D31, D30, [X24]

(3891) 0x50fbcc ADD	X16, X15, X6,LSL #4

(3891) 0x50fbd0 CMP	W12, #0

(3891) 0x50fbd4 B.LE	50fd00

(3891) 0x50fbd8 MOVZ	X4, #0

(3891) 0x50fbdc ORR	W3, WZR, W12

(3891) 0x50fbe0 DUP	Z31.D, Z31.D[0]

(3891) 0x50fbe4 ADD	X17, X19, #200

(3891) 0x50fbe8 CNTD	X10, ALL

(3891) 0x50fbec DUP	Z30.D, Z30.D[0]

(3891) 0x50fbf0 DUP	Z29.D, Z29.D[0]

(3891) 0x50fbf4 WHILELO	P6.D, WZR, W12

(3891) 0x50fbf8 PTRUE	P7.B, ALL

(3891) 0x50fbfc HINT	#0

  (3892) 0x50fc00 LD1D	{Z27.D}, P6/Z, [X9, X4,LSL #3]

  (3892) 0x50fc04 LD1D	{Z28.D}, P6/Z, [X8, X4,LSL #3]

  (3892) 0x50fc08 LD1D	{Z26.D}, P6/Z, [X13, X4,LSL #3]

  (3892) 0x50fc0c LD1RD	{Z1.D}, P7/Z, [X17, #13]

  (3892) 0x50fc10 LD1RD	{Z2.D}, P7/Z, [X17, #12]

  (3892) 0x50fc14 LD1RD	{Z24.D}, P7/Z, [X17, #10]

  (3892) 0x50fc18 LD1RD	{Z25.D}, P7/Z, [X17, #9]

  (3892) 0x50fc1c LD1RD	{Z17.D}, P7/Z, [X17, #16]

  (3892) 0x50fc20 LD1RD	{Z18.D}, P7/Z, [X17, #15]

  (3892) 0x50fc24 FSUB	Z3.D, Z27.D, Z30.D

  (3892) 0x50fc28 FSUB	Z5.D, Z28.D, Z31.D

  (3892) 0x50fc2c FSUB	Z6.D, Z26.D, Z29.D

  (3892) 0x50fc30 LD1RD	{Z0.D}, P7/Z, [X17, #14]

  (3892) 0x50fc34 LD1RD	{Z23.D}, P7/Z, [X17, #11]

  (3892) 0x50fc38 LD1RD	{Z16.D}, P7/Z, [X17, #17]

  (3892) 0x50fc3c FMUL	Z4.D, Z1.D, Z3.D

  (3892) 0x50fc40 FMUL	Z7.D, Z24.D, Z3.D

  (3892) 0x50fc44 FMLA	Z4.D, P7/M, Z2.D, Z5.D

  (3892) 0x50fc48 FMLA	Z7.D, P7/M, Z25.D, Z5.D

  (3892) 0x50fc4c FMAD	Z0.D, P7/M, Z6.D, Z4.D

  (3892) 0x50fc50 FMAD	Z23.D, P7/M, Z6.D, Z7.D

  (3892) 0x50fc54 FMUL	Z19.D, Z17.D, Z3.D

  (3892) 0x50fc58 FMLA	Z19.D, P7/M, Z18.D, Z5.D

  (3892) 0x50fc5c FMAD	Z16.D, P7/M, Z6.D, Z19.D

  (3892) 0x50fc60 LD1RD	{Z20.D}, P7/Z, [X17, #1]

  (3892) 0x50fc64 LD1RD	{Z3.D}, P7/Z, [X17]

  (3892) 0x50fc68 LD1RD	{Z5.D}, P7/Z, [X17, #2]

  (3892) 0x50fc6c MOVPRFX	Z21, Z0

  (3892) 0x50fc70 FRINTA	Z21.D, P7/M, Z0.D

  (3892) 0x50fc74 MOVPRFX	Z22, Z23

  (3892) 0x50fc78 FRINTA	Z22.D, P7/M, Z23.D

  (3892) 0x50fc7c FSUB	Z27.D, Z0.D, Z21.D

  (3892) 0x50fc80 FSUB	Z28.D, Z23.D, Z22.D

  (3892) 0x50fc84 MOVPRFX	Z4, Z16

  (3892) 0x50fc88 FRINTA	Z4.D, P7/M, Z16.D

  (3892) 0x50fc8c FMUL	Z1.D, Z20.D, Z27.D

  (3892) 0x50fc90 FSUB	Z26.D, Z16.D, Z4.D

  (3892) 0x50fc94 FMLA	Z1.D, P7/M, Z3.D, Z28.D

  (3892) 0x50fc98 FMAD	Z5.D, P7/M, Z26.D, Z1.D

  (3892) 0x50fc9c ST1D	{Z5.D}, P6, [X15, X4,LSL #3]

  (3892) 0x50fca0 LD1RD	{Z6.D}, P7/Z, [X17, #3]

  (3892) 0x50fca4 LD1RD	{Z0.D}, P7/Z, [X17, #4]

  (3892) 0x50fca8 LD1RD	{Z2.D}, P7/Z, [X17, #5]

  (3892) 0x50fcac FMUL	Z24.D, Z0.D, Z27.D

  (3892) 0x50fcb0 FMLA	Z24.D, P7/M, Z6.D, Z28.D

  (3892) 0x50fcb4 FMAD	Z2.D, P7/M, Z26.D, Z24.D

  (3892) 0x50fcb8 ST1D	{Z2.D}, P6, [X5, X4,LSL #3]

  (3892) 0x50fcbc LD1RD	{Z7.D}, P7/Z, [X17, #7]

  (3892) 0x50fcc0 LD1RD	{Z25.D}, P7/Z, [X17, #6]

  (3892) 0x50fcc4 LD1RD	{Z17.D}, P7/Z, [X17, #8]

  (3892) 0x50fcc8 FMUL	Z23.D, Z7.D, Z27.D

  (3892) 0x50fccc FMLA	Z23.D, P7/M, Z25.D, Z28.D

  (3892) 0x50fcd0 FMAD	Z17.D, P7/M, Z26.D, Z23.D

  (3892) 0x50fcd4 ST1D	{Z17.D}, P6, [X16, X4,LSL #3]

  (3892) 0x50fcd8 LD1D	{Z18.D}, P6/Z, [X5, X4,LSL #3]

  (3892) 0x50fcdc LD1D	{Z19.D}, P6/Z, [X15, X4,LSL #3]

  (3892) 0x50fce0 FMUL	Z16.D, Z18.D, Z18.D

  (3892) 0x50fce4 FMLA	Z16.D, P7/M, Z19.D, Z19.D

  (3892) 0x50fce8 FMLA	Z16.D, P7/M, Z17.D, Z17.D

  (3892) 0x50fcec FSQRT	Z16.D, P7/M, Z16.D

  (3892) 0x50fcf0 ST1D	{Z16.D}, P6, [X14, X4,LSL #3]

  (3892) 0x50fcf4 ADD	X4, X4, X10

  (3892) 0x50fcf8 WHILELO	P6.D, W4, W3

  (3892) 0x50fcfc B.NE	50fc00

(3891) 0x50fd00 LDRB	W18, [X19, #64]

(3891) 0x50fd04 BIC	X30, X23, X18

(3891) 0x50fd08 TBNZ	W30, #0, 50fd2c

  (3889) 0x50fd0c ORR	X0, XZR, X21

  (3889) 0x50fd10 BL	4c4660

  (3889) 0x50fd14 LDR	X25, [SP, #64]

  (3889) 0x50fd18 LDP	X19, X20, [SP, #16]

  (3889) 0x50fd1c LDP	X21, X22, [SP, #32]

  (3889) 0x50fd20 LDP	X23, X24, [SP, #48]

  (3889) 0x50fd24 LDP	X29, X30, [SP], #80

  (3889) 0x50fd28 RET

  (3889) 0x50fd2c LDR	X0, [X19, #8]

  (3889) 0x50fd30 MOVZ	W23, #24

  (3889) 0x50fd34 LDR	X24, [X22, #64]

  (3889) 0x50fd38 SMADDL	X22, W20, W23, XZR

  (3889) 0x50fd3c LDR	X0, [X0, #632]

  (3889) 0x50fd40 ADD	X23, X24, X22

  (3889) 0x50fd44 LDR	X1, [X0]

  (3889) 0x50fd48 LDR	X2, [X1, #72]

  (3889) 0x50fd4c CMP	X2, X25

  (3889) 0x50fd50 B.NE	50feec

  (3889) 0x50fd54 ADD	X0, X0, #64

  (3889) 0x50fd58 LDR	X14, [X19, #96]

  (3889) 0x50fd5c MOVZ	W25, #40

  (3889) 0x50fd60 SMADDL	X20, W20, W25, XZR

  (3889) 0x50fd64 LDR	X12, [X19, #72]

  (3889) 0x50fd68 LDR	X9, [X0, #8]

  (3889) 0x50fd6c ADD	X6, X14, X20

  (3889) 0x50fd70 LDR	X5, [X6, #8]

  (3889) 0x50fd74 ADD	X15, X12, X20

  (3889) 0x50fd78 LDR	X7, [X0, #24]

  (3889) 0x50fd7c LDR	X16, [X6, #24]

  (3889) 0x50fd80 LDR	D31, [X24, X22]

  (3889) 0x50fd84 ADD	X8, X7, X9,LSL #3

  (3889) 0x50fd88 LDR	X10, [X15, #24]

  (3889) 0x50fd8c ADD	X13, X7, X9,LSL #4

  (3889) 0x50fd90 ADD	X3, X16, X5,LSL #3

  (3889) 0x50fd94 LDP	D30, D29, [X23, #8]

  (3889) 0x50fd98 ADD	X17, X16, X5,LSL #4

  (3889) 0x50fd9c CMP	W11, #0

  (3889) 0x50fda0 B.LE	50fd0c

(3891) 0x50fda4 MOVZ	X30, #0

(3891) 0x50fda8 ADD	X4, X19, #200

(3891) 0x50fdac DUP	Z31.D, Z31.D[0]

(3891) 0x50fdb0 CNTD	X18, ALL

(3891) 0x50fdb4 DUP	Z30.D, Z30.D[0]

(3891) 0x50fdb8 DUP	Z29.D, Z29.D[0]

(3891) 0x50fdbc WHILELO	P1.D, WZR, W11

(3891) 0x50fdc0 PTRUE	P0.B, ALL

  (3890) 0x50fdc4 LD1D	{Z21.D}, P1/Z, [X8, X30,LSL #3]

  (3890) 0x50fdc8 LD1D	{Z22.D}, P1/Z, [X7, X30,LSL #3]

  (3890) 0x50fdcc LD1D	{Z4.D}, P1/Z, [X13, X30,LSL #3]

  (3890) 0x50fdd0 LD1RD	{Z20.D}, P0/Z, [X4, #13]

  (3890) 0x50fdd4 LD1RD	{Z3.D}, P0/Z, [X4, #12]

  (3890) 0x50fdd8 LD1RD	{Z6.D}, P0/Z, [X4, #10]

  (3890) 0x50fddc LD1RD	{Z2.D}, P0/Z, [X4, #9]

  (3890) 0x50fde0 LD1RD	{Z7.D}, P0/Z, [X4, #16]

  (3890) 0x50fde4 LD1RD	{Z23.D}, P0/Z, [X4, #15]

  (3890) 0x50fde8 FSUB	Z27.D, Z21.D, Z30.D

  (3890) 0x50fdec FSUB	Z28.D, Z22.D, Z31.D

  (3890) 0x50fdf0 FSUB	Z26.D, Z4.D, Z29.D

  (3890) 0x50fdf4 LD1RD	{Z5.D}, P0/Z, [X4, #14]

  (3890) 0x50fdf8 LD1RD	{Z24.D}, P0/Z, [X4, #11]

  (3890) 0x50fdfc LD1RD	{Z17.D}, P0/Z, [X4, #17]

  (3890) 0x50fe00 FMUL	Z1.D, Z20.D, Z27.D

  (3890) 0x50fe04 FMUL	Z0.D, Z6.D, Z27.D

  (3890) 0x50fe08 FMLA	Z1.D, P0/M, Z3.D, Z28.D

  (3890) 0x50fe0c FMLA	Z0.D, P0/M, Z2.D, Z28.D

  (3890) 0x50fe10 FMAD	Z5.D, P0/M, Z26.D, Z1.D

  (3890) 0x50fe14 FMAD	Z24.D, P0/M, Z26.D, Z0.D

  (3890) 0x50fe18 FMUL	Z25.D, Z7.D, Z27.D

  (3890) 0x50fe1c FMLA	Z25.D, P0/M, Z23.D, Z28.D

  (3890) 0x50fe20 FMAD	Z17.D, P0/M, Z26.D, Z25.D

  (3890) 0x50fe24 LD1RD	{Z16.D}, P0/Z, [X4, #1]

  (3890) 0x50fe28 LD1RD	{Z1.D}, P0/Z, [X4]

  (3890) 0x50fe2c LD1RD	{Z3.D}, P0/Z, [X4, #2]

  (3890) 0x50fe30 MOVPRFX	Z18, Z5

  (3890) 0x50fe34 FRINTA	Z18.D, P0/M, Z5.D

  (3890) 0x50fe38 MOVPRFX	Z21, Z24

  (3890) 0x50fe3c FRINTA	Z21.D, P0/M, Z24.D

  (3890) 0x50fe40 FSUB	Z19.D, Z5.D, Z18.D

  (3890) 0x50fe44 FSUB	Z22.D, Z24.D, Z21.D

  (3890) 0x50fe48 MOVPRFX	Z20, Z17

  (3890) 0x50fe4c FRINTA	Z20.D, P0/M, Z17.D

  (3890) 0x50fe50 FMUL	Z27.D, Z16.D, Z19.D

  (3890) 0x50fe54 FSUB	Z28.D, Z17.D, Z20.D

  (3890) 0x50fe58 FMLA	Z27.D, P0/M, Z1.D, Z22.D

  (3890) 0x50fe5c FMAD	Z3.D, P0/M, Z28.D, Z27.D

  (3890) 0x50fe60 ST1D	{Z3.D}, P1, [X16, X30,LSL #3]

  (3890) 0x50fe64 LD1RD	{Z4.D}, P0/Z, [X4, #3]

  (3890) 0x50fe68 LD1RD	{Z26.D}, P0/Z, [X4, #4]

  (3890) 0x50fe6c LD1RD	{Z5.D}, P0/Z, [X4, #5]

  (3890) 0x50fe70 FMUL	Z6.D, Z26.D, Z19.D

  (3890) 0x50fe74 FMLA	Z6.D, P0/M, Z4.D, Z22.D

  (3890) 0x50fe78 FMAD	Z5.D, P0/M, Z28.D, Z6.D

  (3890) 0x50fe7c ST1D	{Z5.D}, P1, [X3, X30,LSL #3]

  (3890) 0x50fe80 LD1RD	{Z0.D}, P0/Z, [X4, #7]

  (3890) 0x50fe84 LD1RD	{Z2.D}, P0/Z, [X4, #6]

  (3890) 0x50fe88 LD1RD	{Z24.D}, P0/Z, [X4, #8]

  (3890) 0x50fe8c FMUL	Z7.D, Z0.D, Z19.D

  (3890) 0x50fe90 FMLA	Z7.D, P0/M, Z2.D, Z22.D

  (3890) 0x50fe94 FMAD	Z24.D, P0/M, Z28.D, Z7.D

  (3890) 0x50fe98 ST1D	{Z24.D}, P1, [X17, X30,LSL #3]

  (3890) 0x50fe9c LD1D	{Z25.D}, P1/Z, [X3, X30,LSL #3]

  (3890) 0x50fea0 LD1D	{Z23.D}, P1/Z, [X16, X30,LSL #3]

  (3890) 0x50fea4 FMUL	Z17.D, Z25.D, Z25.D

  (3890) 0x50fea8 FMLA	Z17.D, P0/M, Z23.D, Z23.D

  (3890) 0x50feac FMLA	Z17.D, P0/M, Z24.D, Z24.D

  (3890) 0x50feb0 FSQRT	Z17.D, P0/M, Z17.D

  (3890) 0x50feb4 ST1D	{Z17.D}, P1, [X10, X30,LSL #3]

  (3890) 0x50feb8 ADD	X30, X30, X18

  (3890) 0x50febc WHILELO	P1.D, W30, W11

  (3890) 0x50fec0 B.NE	50fdc4

(3891) 0x50fec4 ORR	X0, XZR, X21

(3891) 0x50fec8 BL	4c4660

(3891) 0x50fecc LDR	X25, [SP, #64]

(3891) 0x50fed0 LDP	X19, X20, [SP, #16]

(3891) 0x50fed4 LDP	X21, X22, [SP, #32]

(3891) 0x50fed8 LDP	X23, X24, [SP, #48]

(3891) 0x50fedc LDP	X29, X30, [SP], #80

(3891) 0x50fee0 RET

(3891) 0x50fee4 BLR	X2

(3891) 0x50fee8 B	50fb9c

  (3889) 0x50feec BLR	X2

  (3889) 0x50fef0 LDR	W11, [X19, #16]

  (3889) 0x50fef4 B	50fd58

0x50fef8 ORR	X19, XZR, X0

0x50fefc ORR	X0, XZR, X21

0x50ff00 BL	4c4660

0x50ff04 ORR	X0, XZR, X19

0x50ff08 BL	403e10

0x50ff0c HINT	#0

0x50ff10 HINT	#0

0x50ff14 HINT	#0

0x50ff18 HINT	#0

0x50ff1c HINT	#0

Coverage (%)	Name	Source Location	Module

Path /

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

Source file and lines	SoaDistanceTableABOMPTarget.h:358-368
Module	exec

The function is defined in:

/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/unique_ptr.h:193
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Particle/RealSpacePositionsOMPTarget.h:163
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:222-224,234-255
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:271-273
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:229,248
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_vector.h:1131
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableABOMPTarget.h:358-368

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 21% of vector register length is used (average across all VPU instructions). By vectorizing your function, you can lower the cost of an iteration from 4.50 to 0.75 cycles (6.00x 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 4.50 to 1.50 cycles (3.00x 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 40 bytes. The binary function is storing 72 bytes.

General properties

nb instructions	33
loop length	132
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

3.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	2.00	2.00	4.50	4.50	4.50	4.50	0.00	0.00	0.00	0.00	3.50	3.17	3.33	2.50	2.50
cycles	2.00	2.00	4.50	4.50	4.50	4.50	0.00	0.00	0.00	0.00	3.50	3.17	3.33	2.50	2.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	3.50
Overall L1	4.50

Vectorization ratios

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
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 4.50 cycles. At this rate:

9% of peak load performance is reached (8.89 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
33% of peak store performance is reached (16.00 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 50fb40

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
STP X29, X30, [SP, #944]!	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ADD X29, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X19, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR W20, WZR, W3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X22, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X24, XZR, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
AND W23, W4, #448	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X21, [X0, #448]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STR X25, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ADRP X25, <2004c1b70>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X25, X25, #2208	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X0, XZR, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 4c43c0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR X0, [X19, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X0, [X0, #632]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X1, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X2, [X1, #72]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X2, X25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.NE 50fee4 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE4moveERKNS_11ParticleSetERKNS_10TinyVectorIdLj3EEEib+0x3a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X0, X0, #64	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X19, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X0, XZR, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 4c4660 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 403e10 <@plt_start@+0x420>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
HINT #0
HINT #0
HINT #0
HINT #0
HINT #0

Source file and lines	SoaDistanceTableABOMPTarget.h:358-368
Module	exec

The function is defined in:

/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/unique_ptr.h:193
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Particle/RealSpacePositionsOMPTarget.h:163
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:222-224,234-255
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:271-273
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:229,248
/home/hbollore/gnu/unknow_version/include/c++/14.0.1/bits/stl_vector.h:1131
/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableABOMPTarget.h:358-368

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

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 4.50 to 1.50 cycles (3.00x 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 40 bytes. The binary function is storing 72 bytes.

General properties

nb instructions	33
loop length	132
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

3.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	2.00	2.00	4.50	4.50	4.50	4.50	0.00	0.00	0.00	0.00	3.50	3.17	3.33	2.50	2.50
cycles	2.00	2.00	4.50	4.50	4.50	4.50	0.00	0.00	0.00	0.00	3.50	3.17	3.33	2.50	2.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	3.50
Overall L1	4.50

Vectorization ratios

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
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 4.50 cycles. At this rate:

9% of peak load performance is reached (8.89 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
33% of peak store performance is reached (16.00 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 50fb40

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
STP X29, X30, [SP, #944]!	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ADD X29, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X19, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR W20, WZR, W3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X22, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X24, XZR, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
AND W23, W4, #448	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X21, [X0, #448]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
STR X25, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ADRP X25, <2004c1b70>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X25, X25, #2208	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X0, XZR, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 4c43c0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR X0, [X19, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X0, [X0, #632]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X1, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X2, [X1, #72]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X2, X25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.NE 50fee4 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE4moveERKNS_11ParticleSetERKNS_10TinyVectorIdLj3EEEib+0x3a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X0, X0, #64	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X19, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X0, XZR, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 4c4660 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 403e10 <@plt_start@+0x420>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
HINT #0
HINT #0
HINT #0
HINT #0
HINT #0

Name	Coverage (%)	Time (s)
▼qmcplusplus::SoaDistanceTableABOMPTarget::move(qmcplusplus::ParticleSet const&, qmcplusplus::TinyVector const&, int, bool)–	0.13	0.21
▼Loop 3891 - SoaDistanceTableABOMPTarget.h:361-368 - exec–	0	0.01
○Loop 3890 - ParticleBConds3DSoa.h:237-255 - exec	0.06	0.09
○Loop 3892 - ParticleBConds3DSoa.h:237-255 - exec	0.05	0.07
○Loop 3889 - VectorSoAContainer.h:271-273 - exec	0.01	0.01

Report Configuration

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

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