OV - exec - Loop 294

	Loop Id: 294	Module: exec	Source: TwoBodyJastrowRef.h:127-132 [...]	Coverage: 0.01%

0x42bf60 LDR	X16, [X12, X8,LSL #3]

0x42bf64 LDR	W17, [X11, X8,LSL #2]

0x42bf68 ADD	X8, X8, #1

0x42bf6c LDR	W18, [X11, X8,LSL #2]

0x42bf70 CMP	W18, W17

0x42bf74 B.LE	42c3cc

0x42bf78 SUB	W30, W18, W17

0x42bf7c SBFM	X15, X17, #61, #31

0x42bf80 LDR	D31, [X16, #8]

0x42bf84 ANDS	W3, W30, #0x7

0x42bf88 ADD	X0, X14, X15

0x42bf8c MOVZ	W2, #0

0x42bf90 ORR	W30, WZR, W17

0x42bf94 B.EQ	42c0cc

0x42bf98 CMP	W3, #1

0x42bf9c B.EQ	42c0a0

0x42bfa0 CMP	W3, #2

0x42bfa4 B.EQ	42c07c

0x42bfa8 CMP	W3, #3

0x42bfac B.EQ	42c058

0x42bfb0 CMP	W3, #4

0x42bfb4 B.EQ	42c034

0x42bfb8 CMP	W3, #5

0x42bfbc B.EQ	42c010

0x42bfc0 CMP	W3, #6

0x42bfc4 B.EQ	42bfec

0x42bfc8 LDR	D30, [X14, X15]

0x42bfcc FCMPE	D31, D30

0x42bfd0 B.LS	42bfe4

0x42bfd4 CMP	W24, W17

0x42bfd8 B.EQ	42bfe4

0x42bfdc MOVZ	W2, #1

0x42bfe0 STR	D30, [X4]

0x42bfe4 ADD	X0, X0, #8

0x42bfe8 ADD	W30, W17, #1

0x42bfec LDR	D0, [X0]

0x42bff0 FCMPE	D31, D0

0x42bff4 B.LS	42c008

0x42bff8 CMP	W24, W30

0x42bffc B.EQ	42c008

0x42c000 STR	D0, [X4, W2,UXTW #3]

0x42c004 ADD	W2, W2, #1

0x42c008 ADD	X0, X0, #8

0x42c00c ADD	W30, W30, #1

0x42c010 LDR	D1, [X0]

0x42c014 FCMPE	D31, D1

0x42c018 B.LS	42c02c

0x42c01c CMP	W24, W30

0x42c020 B.EQ	42c02c

0x42c024 STR	D1, [X4, W2,UXTW #3]

0x42c028 ADD	W2, W2, #1

0x42c02c ADD	X0, X0, #8

0x42c030 ADD	W30, W30, #1

0x42c034 LDR	D3, [X0]

0x42c038 FCMPE	D31, D3

0x42c03c B.LS	42c050

0x42c040 CMP	W24, W30

0x42c044 B.EQ	42c050

0x42c048 STR	D3, [X4, W2,UXTW #3]

0x42c04c ADD	W2, W2, #1

0x42c050 ADD	X0, X0, #8

0x42c054 ADD	W30, W30, #1

0x42c058 LDR	D4, [X0]

0x42c05c FCMPE	D31, D4

0x42c060 B.LS	42c074

0x42c064 CMP	W24, W30

0x42c068 B.EQ	42c074

0x42c06c STR	D4, [X4, W2,UXTW #3]

0x42c070 ADD	W2, W2, #1

0x42c074 ADD	X0, X0, #8

0x42c078 ADD	W30, W30, #1

0x42c07c LDR	D5, [X0]

0x42c080 FCMPE	D31, D5

0x42c084 B.LS	42c098

0x42c088 CMP	W24, W30

0x42c08c B.EQ	42c098

0x42c090 STR	D5, [X4, W2,UXTW #3]

0x42c094 ADD	W2, W2, #1

0x42c098 ADD	X0, X0, #8

0x42c09c ADD	W30, W30, #1

0x42c0a0 LDR	D6, [X0]

0x42c0a4 FCMPE	D31, D6

0x42c0a8 B.LS	42c0bc

0x42c0ac CMP	W24, W30

0x42c0b0 B.EQ	42c0bc

0x42c0b4 STR	D6, [X4, W2,UXTW #3]

0x42c0b8 ADD	W2, W2, #1

0x42c0bc ADD	W30, W30, #1

0x42c0c0 ADD	X0, X0, #8

0x42c0c4 CMP	W18, W30

0x42c0c8 B.EQ	42c1dc

  (295) 0x42c0cc LDR	D7, [X0]

  (295) 0x42c0d0 FCMPE	D31, D7

  (295) 0x42c0d4 B.LS	42c0e8

  (295) 0x42c0d8 CMP	W24, W30

  (295) 0x42c0dc B.EQ	42c0e8

  (295) 0x42c0e0 STR	D7, [X4, W2,UXTW #3]

  (295) 0x42c0e4 ADD	W2, W2, #1

  (295) 0x42c0e8 LDR	D8, [X0, #8]

  (295) 0x42c0ec ADD	W28, W30, #1

  (295) 0x42c0f0 ADD	X0, X0, #8

  (295) 0x42c0f4 FCMPE	D31, D8

  (295) 0x42c0f8 B.LS	42c10c

  (295) 0x42c0fc CMP	W24, W28

  (295) 0x42c100 B.EQ	42c10c

  (295) 0x42c104 STR	D8, [X4, W2,UXTW #3]

  (295) 0x42c108 ADD	W2, W2, #1

  (295) 0x42c10c LDR	D9, [X0, #8]

  (295) 0x42c110 ADD	W1, W28, #1

  (295) 0x42c114 FCMPE	D31, D9

  (295) 0x42c118 B.LS	42c12c

  (295) 0x42c11c CMP	W24, W1

  (295) 0x42c120 B.EQ	42c12c

  (295) 0x42c124 STR	D9, [X4, W2,UXTW #3]

  (295) 0x42c128 ADD	W2, W2, #1

  (295) 0x42c12c LDR	D10, [X0, #16]

  (295) 0x42c130 ADD	W27, W28, #2

  (295) 0x42c134 FCMPE	D31, D10

  (295) 0x42c138 B.LS	42c14c

  (295) 0x42c13c CMP	W24, W27

  (295) 0x42c140 B.EQ	42c14c

  (295) 0x42c144 STR	D10, [X4, W2,UXTW #3]

  (295) 0x42c148 ADD	W2, W2, #1

  (295) 0x42c14c LDR	D11, [X0, #24]

  (295) 0x42c150 ADD	W5, W28, #3

  (295) 0x42c154 FCMPE	D31, D11

  (295) 0x42c158 B.LS	42c16c

  (295) 0x42c15c CMP	W24, W5

  (295) 0x42c160 B.EQ	42c16c

  (295) 0x42c164 STR	D11, [X4, W2,UXTW #3]

  (295) 0x42c168 ADD	W2, W2, #1

  (295) 0x42c16c LDR	D12, [X0, #32]

  (295) 0x42c170 ADD	W9, W28, #4

  (295) 0x42c174 FCMPE	D31, D12

  (295) 0x42c178 B.LS	42c18c

  (295) 0x42c17c CMP	W24, W9

  (295) 0x42c180 B.EQ	42c18c

  (295) 0x42c184 STR	D12, [X4, W2,UXTW #3]

  (295) 0x42c188 ADD	W2, W2, #1

  (295) 0x42c18c LDR	D13, [X0, #40]

  (295) 0x42c190 ADD	W10, W28, #5

  (295) 0x42c194 FCMPE	D31, D13

  (295) 0x42c198 B.LS	42c1ac

  (295) 0x42c19c CMP	W24, W10

  (295) 0x42c1a0 B.EQ	42c1ac

  (295) 0x42c1a4 STR	D13, [X4, W2,UXTW #3]

  (295) 0x42c1a8 ADD	W2, W2, #1

  (295) 0x42c1ac LDR	D14, [X0, #48]

  (295) 0x42c1b0 ADD	W17, W28, #6

  (295) 0x42c1b4 FCMPE	D31, D14

  (295) 0x42c1b8 B.LS	42c1cc

  (295) 0x42c1bc CMP	W24, W17

  (295) 0x42c1c0 B.EQ	42c1cc

  (295) 0x42c1c4 STR	D14, [X4, W2,UXTW #3]

  (295) 0x42c1c8 ADD	W2, W2, #1

  (295) 0x42c1cc ADD	W30, W28, #7

  (295) 0x42c1d0 ADD	X0, X0, #56

  (295) 0x42c1d4 CMP	W18, W30

  (295) 0x42c1d8 B.NE	42c0cc

0x42c1dc CBZ	W2, 42c3cc

0x42c1e0 ADD	X18, X16, #568

0x42c1e4 LD1RD	{Z4.D}, P7/Z, [X16, #3]

0x42c1e8 LD1RD	{Z5.D}, P7/Z, [X16, #4]

0x42c1ec LD1RD	{Z6.D}, P7/Z, [X16, #5]

0x42c1f0 LD1RD	{Z7.D}, P7/Z, [X16, #6]

0x42c1f4 LD1RD	{Z16.D}, P7/Z, [X16, #7]

0x42c1f8 LD1RD	{Z17.D}, P7/Z, [X16, #8]

0x42c1fc LD1RD	{Z18.D}, P7/Z, [X16, #9]

0x42c200 LD1RD	{Z19.D}, P7/Z, [X16, #10]

0x42c204 LD1RD	{Z20.D}, P7/Z, [X16, #11]

0x42c208 LD1RD	{Z21.D}, P7/Z, [X16, #12]

0x42c20c LD1RD	{Z22.D}, P7/Z, [X16, #13]

0x42c210 LD1RD	{Z23.D}, P7/Z, [X16, #14]

0x42c214 LD1RD	{Z24.D}, P7/Z, [X16, #15]

0x42c218 LD1RD	{Z25.D}, P7/Z, [X16, #16]

0x42c21c LD1RD	{Z26.D}, P7/Z, [X16, #17]

0x42c220 LD1RD	{Z27.D}, P7/Z, [X16, #18]

0x42c224 LDR	X16, [X16, #536]

0x42c228 MOVZ	X3, #0

0x42c22c ORR	W15, WZR, W2

0x42c230 DUP	Z1.D, #0

0x42c234 UQDECD	W15, ALL

0x42c238 LD1RD	{Z3.D}, P7/Z, [X18]

0x42c23c WHILELO	P5.D, WZR, W15

0x42c240 ORR	Z28.D, Z1.D, Z1.D

0x42c244 WHILELO	P6.D, WZR, W2

  (296) 0x42c248 LD1D	{Z29.D}, P5/Z, [X6, X3,LSL #3]

  (296) 0x42c24c LD1D	{Z30.D}, P6/Z, [X4, X3,LSL #3]

  (296) 0x42c250 FMUL	Z31.D, Z3.D, Z29.D

  (296) 0x42c254 FMUL	Z13.D, Z3.D, Z30.D

  (296) 0x42c258 MOVPRFX	Z8, Z31

  (296) 0x42c25c FCVTZS	Z8.S, P7/M, Z31.D

  (296) 0x42c260 MOVPRFX	Z9, Z13

  (296) 0x42c264 FCVTZS	Z9.S, P7/M, Z13.D

  (296) 0x42c268 MOVPRFX	Z0, Z31

  (296) 0x42c26c FRINTZ	Z0.D, P7/M, Z31.D

  (296) 0x42c270 UZP1	Z30.S, Z9.S, Z8.S

  (296) 0x42c274 FSUB	Z31.D, Z31.D, Z0.D

  (296) 0x42c278 MOVPRFX	Z12, Z30

  (296) 0x42c27c ADD	Z12.S, Z12.S, #1

  (296) 0x42c280 FMUL	Z29.D, Z31.D, Z31.D

  (296) 0x42c284 SUNPKHI	Z8.D, Z12

  (296) 0x42c288 FMUL	Z14.D, Z29.D, Z31.D

  (296) 0x42c28c LD1D	{Z9.D}, P5/Z, [X16, Z8.D,LSL #3]

  (296) 0x42c290 FMUL	Z10.D, Z17.D, Z29.D

  (296) 0x42c294 FMLA	Z10.D, P7/M, Z16.D, Z14.D

  (296) 0x42c298 MOVPRFX	Z11, Z19

  (296) 0x42c29c FMLA	Z11.D, P7/M, Z18.D, Z31.D

  (296) 0x42c2a0 FADD	Z0.D, Z10.D, Z11.D

  (296) 0x42c2a4 FMUL	Z10.D, Z5.D, Z29.D

  (296) 0x42c2a8 FMUL	Z0.D, Z0.D, Z9.D

  (296) 0x42c2ac FMLA	Z10.D, P7/M, Z4.D, Z14.D

  (296) 0x42c2b0 SUNPKHI	Z9.D, Z30

  (296) 0x42c2b4 LD1D	{Z8.D}, P5/Z, [X16, Z9.D,LSL #3]

  (296) 0x42c2b8 MOVPRFX	Z11, Z7

  (296) 0x42c2bc FMLA	Z11.D, P7/M, Z6.D, Z31.D

  (296) 0x42c2c0 FADD	Z11.D, Z11.D, Z10.D

  (296) 0x42c2c4 FMUL	Z10.D, Z21.D, Z29.D

  (296) 0x42c2c8 FMAD	Z11.D, P7/M, Z8.D, Z0.D

  (296) 0x42c2cc FMLA	Z10.D, P7/M, Z14.D, Z20.D

  (296) 0x42c2d0 MOVPRFX	Z0, Z23

  (296) 0x42c2d4 FMLA	Z0.D, P7/M, Z31.D, Z22.D

  (296) 0x42c2d8 FMUL	Z29.D, Z29.D, Z25.D

  (296) 0x42c2dc FADD	Z8.D, Z10.D, Z0.D

  (296) 0x42c2e0 FMAD	Z14.D, P7/M, Z24.D, Z29.D

  (296) 0x42c2e4 MOVPRFX	Z10, Z30

  (296) 0x42c2e8 ADD	Z10.S, Z10.S, #2

  (296) 0x42c2ec FADD	Z1.D, P5/M, Z1.D, Z11.D

  (296) 0x42c2f0 FMAD	Z31.D, P7/M, Z26.D, Z27.D

  (296) 0x42c2f4 MOVPRFX	Z11, Z30

  (296) 0x42c2f8 ADD	Z11.S, Z11.S, #3

  (296) 0x42c2fc FADD	Z31.D, Z31.D, Z14.D

  (296) 0x42c300 SUNPKHI	Z0.D, Z11

  (296) 0x42c304 SUNPKHI	Z14.D, Z10

  (296) 0x42c308 LD1D	{Z29.D}, P5/Z, [X16, Z0.D,LSL #3]

  (296) 0x42c30c LD1D	{Z9.D}, P5/Z, [X16, Z14.D,LSL #3]

  (296) 0x42c310 SUNPKLO	Z30.D, Z30

  (296) 0x42c314 FMLA	Z1.D, P5/M, Z9.D, Z8.D

  (296) 0x42c318 SUNPKLO	Z8.D, Z10

  (296) 0x42c31c FMLA	Z1.D, P5/M, Z29.D, Z31.D

  (296) 0x42c320 LD1D	{Z14.D}, P6/Z, [X16, Z8.D,LSL #3]

  (296) 0x42c324 SUNPKLO	Z31.D, Z11

  (296) 0x42c328 MOVPRFX	Z9, Z13

  (296) 0x42c32c FRINTZ	Z9.D, P7/M, Z13.D

  (296) 0x42c330 LD1D	{Z11.D}, P6/Z, [X16, Z30.D,LSL #3]

  (296) 0x42c334 FSUB	Z8.D, Z13.D, Z9.D

  (296) 0x42c338 SUNPKLO	Z12.D, Z12

  (296) 0x42c33c FMUL	Z29.D, Z8.D, Z8.D

  (296) 0x42c340 FMUL	Z30.D, Z29.D, Z8.D

  (296) 0x42c344 FMUL	Z13.D, Z17.D, Z29.D

  (296) 0x42c348 FMLA	Z13.D, P7/M, Z16.D, Z30.D

  (296) 0x42c34c LD1D	{Z10.D}, P6/Z, [X16, Z12.D,LSL #3]

  (296) 0x42c350 ADD	X3, X3, X7

  (296) 0x42c354 MOVPRFX	Z12, Z19

  (296) 0x42c358 FMLA	Z12.D, P7/M, Z18.D, Z8.D

  (296) 0x42c35c WHILELO	P5.D, W3, W15

  (296) 0x42c360 FADD	Z9.D, Z12.D, Z13.D

  (296) 0x42c364 MOVPRFX	Z13, Z7

  (296) 0x42c368 FMLA	Z13.D, P7/M, Z6.D, Z8.D

  (296) 0x42c36c LD1D	{Z0.D}, P6/Z, [X16, Z31.D,LSL #3]

  (296) 0x42c370 FMUL	Z12.D, Z9.D, Z10.D

  (296) 0x42c374 FMUL	Z31.D, Z5.D, Z29.D

  (296) 0x42c378 FMUL	Z10.D, Z21.D, Z29.D

  (296) 0x42c37c FMLA	Z31.D, P7/M, Z4.D, Z30.D

  (296) 0x42c380 MOVPRFX	Z9, Z23

  (296) 0x42c384 FMLA	Z9.D, P7/M, Z8.D, Z22.D

  (296) 0x42c388 FADD	Z31.D, Z13.D, Z31.D

  (296) 0x42c38c FMUL	Z29.D, Z29.D, Z25.D

  (296) 0x42c390 FMAD	Z31.D, P7/M, Z11.D, Z12.D

  (296) 0x42c394 FMAD	Z8.D, P7/M, Z26.D, Z27.D

  (296) 0x42c398 MOVPRFX	Z11, Z10

  (296) 0x42c39c FMLA	Z11.D, P7/M, Z30.D, Z20.D

  (296) 0x42c3a0 FADD	Z28.D, P6/M, Z28.D, Z31.D

  (296) 0x42c3a4 FMAD	Z30.D, P7/M, Z24.D, Z29.D

  (296) 0x42c3a8 FADD	Z13.D, Z9.D, Z11.D

  (296) 0x42c3ac FMLA	Z28.D, P6/M, Z14.D, Z13.D

  (296) 0x42c3b0 FADD	Z14.D, Z30.D, Z8.D

  (296) 0x42c3b4 FMLA	Z28.D, P6/M, Z0.D, Z14.D

  (296) 0x42c3b8 WHILELO	P6.D, W3, W2

  (296) 0x42c3bc B.NE	42c248

0x42c3c0 FADD	Z3.D, Z28.D, Z1.D

0x42c3c4 FADDV	D1, P7, Z3.D

0x42c3c8 FADD	D2, D2, D1

0x42c3cc CMP	X13, X8

0x42c3d0 B.NE	42bf60

/usr/include/c++/14/bits/stl_vector.h: 1147 - 1147

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

1147:       operator[](size_type __n) const _GLIBCXX_NOEXCEPT

/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 127 - 132

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

127:     for (int jg = 0; jg < NumGroups; ++jg)

128:     {

129:       const FuncType& f2(*F[igt + jg]);

130:       int iStart = P.first(jg);

131:       int iEnd   = P.last(jg);

132:       curUat += f2.evaluateV(iat, iStart, iEnd, dist, DistCompressed.data());

/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 313 - 316

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

313:   inline int first(int igroup) const { return (*group_offsets_)[igroup]; }

314:

315:   ///return the last index of a group i

316:   inline int last(int igroup) const { return (*group_offsets_)[igroup + 1]; }

/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 232 - 260

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

232:   int iCount       = 0;

233:   const int iLimit = iEnd - iStart;

234:

235: #pragma vector always

236:   for (int jat = 0; jat < iLimit; jat++)

237:   {

238:     real_type r = distArray[jat];

239:     // pick the distances smaller than the cutoff and avoid the reference atom

240:     if (r < cutoff_radius && iStart + jat != iat)

241:       distArrayCompressed[iCount++] = distArray[jat];

242:   }

243:

244:   real_type d = 0.0;

245:   //#pragma omp simd reduction(+:d)

246:   for (int jat = 0; jat < iCount; jat++)

247:   {

248:     real_type r = distArrayCompressed[jat];

249:     r *= DeltaRInv;

250:     int i         = (int)r;

251:     real_type t   = r - real_type(i);

252:     real_type tp0 = t * t * t;

253:     real_type tp1 = t * t;

254:     real_type tp2 = t;

255:

256:     real_type d1 = SplineCoefs[i + 0] * (A[0] * tp0 + A[1] * tp1 + A[2] * tp2 + A[3]);

257:     real_type d2 = SplineCoefs[i + 1] * (A[4] * tp0 + A[5] * tp1 + A[6] * tp2 + A[7]);

258:     real_type d3 = SplineCoefs[i + 2] * (A[8] * tp0 + A[9] * tp1 + A[10] * tp2 + A[11]);

259:     real_type d4 = SplineCoefs[i + 3] * (A[12] * tp0 + A[13] * tp1 + A[14] * tp2 + A[15]);

260:     d += (d1 + d2 + d3 + d4);

Coverage (%)	Name	Source Location	Module
►97.98+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:993	exec
○	main._omp_fn.1	NonLocalPP.hpp:126	exec
○	omp_fulfill_event		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 /

Metric	Value
CQA speedup if no scalar integer	1.28
CQA speedup if FP arith vectorized	1.01
CQA speedup if fully vectorized	1.23
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.23
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	TwoBodyJastrowRef.h:127-129,TwoBodyJastrowRef.h:132-132,ParticleSet.h:313-313,ParticleSet.h:316-316,BsplineFunctor.h:232-232,BsplineFunctor.h:236-241,BsplineFunctor.h:246-246,BsplineFunctor.h:259-260
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	15.38
CQA cycles if no scalar integer	12.00
CQA cycles if FP arith vectorized	15.28
CQA cycles if fully vectorized	12.50
Front-end cycles	15.38
P0 cycles	12.50
P1 cycles	12.50
P2 cycles	12.50
P3 cycles	12.50
P4 cycles	12.50
P5 cycles	12.50
P6 cycles	9.00
P7 cycles	9.00
P8 cycles	1.75
P9 cycles	1.75
P10 cycles	12.00
P11 cycles	12.00
P12 cycles	12.00
P13 cycles	0.00
P14 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	123.00
Nb uops	123.00
Nb loads	NA
Nb stores	7.00
Nb stack references	0.00
FLOP/cycle	0.59
Nb FLOP add-sub	9.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	0.39
Bytes prefetched	0.00
Bytes loaded	6.00
Bytes stored	0.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	4.23
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	18.18
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	3.70
Vector-efficiency ratio all	23.28
Vector-efficiency ratio load	24.52
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	29.55
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	19.10

Metric	Value
CQA speedup if no scalar integer	1.28
CQA speedup if FP arith vectorized	1.01
CQA speedup if fully vectorized	1.23
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.23
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	TwoBodyJastrowRef.h:127-129,TwoBodyJastrowRef.h:132-132,ParticleSet.h:313-313,ParticleSet.h:316-316,BsplineFunctor.h:232-232,BsplineFunctor.h:236-241,BsplineFunctor.h:246-246,BsplineFunctor.h:259-260
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	15.38
CQA cycles if no scalar integer	12.00
CQA cycles if FP arith vectorized	15.28
CQA cycles if fully vectorized	12.50
Front-end cycles	15.38
P0 cycles	12.50
P1 cycles	12.50
P2 cycles	12.50
P3 cycles	12.50
P4 cycles	12.50
P5 cycles	12.50
P6 cycles	9.00
P7 cycles	9.00
P8 cycles	1.75
P9 cycles	1.75
P10 cycles	12.00
P11 cycles	12.00
P12 cycles	12.00
P13 cycles	0.00
P14 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	123.00
Nb uops	123.00
Nb loads	NA
Nb stores	7.00
Nb stack references	0.00
FLOP/cycle	0.59
Nb FLOP add-sub	9.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	0.39
Bytes prefetched	0.00
Bytes loaded	6.00
Bytes stored	0.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	4.23
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	18.18
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	3.70
Vector-efficiency ratio all	23.28
Vector-efficiency ratio load	24.52
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	29.55
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	19.10

Path /

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

Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source file and lines	TwoBodyJastrowRef.h:127-132
Module	exec

The loop is defined in:

/usr/include/c++/14/bits/stl_vector.h:1147
/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:127-132
/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316
/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:232-260

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths (too many, greater than internal limit = 100000)
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is very high. Force analysis with --force-loop-streams-analysis: expect potentially high RAM/CPU footprint

Try to simplify control.

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 15.38 to 12.00 cycles (1.28x speedup).

Workaround

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

Vectorization

Your loop is not vectorized. Only 23% of vector register length is used (average across all VPU instructions). By fully vectorizing your loop, you can lower the cost of an iteration from 15.38 to 12.50 cycles (1.23x speedup).

Details

4% of VPU instructions are used in vector version (process two or more data elements in vector registers):

0% of VPU loads are used in vector version.
0% of VPU stores are used in vector version.
18% of VPU addition or subtraction instructions are used in vector version.
3% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop 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)

No data for this section

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

The binary loop is composed of 9 FP arithmetical operations:

9: addition or subtraction

The binary loop is loading 6 bytes.

Arithmetic intensity

Arithmetic intensity is 1.50 FP operations per loaded or stored byte.

General properties

nb instructions	123
nb uops	123
loop length	492
used w registers	8
used x registers	12
used b registers	0
used h registers	0
used s registers	0
used d registers	9
used q registers	0
used v registers	0
used z registers	19
nb stack references	0

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	15.38 cycles
front end	15.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	12.50	12.50	12.50	12.50	12.50	12.50	9.00	9.00	1.00	1.00	12.00	12.00	12.00	0.00	0.00
cycles	12.50	12.50	12.50	12.50	12.50	12.50	9.00	9.00	1.75	1.75	12.00	12.00	12.00	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
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	15.38
Dispatch	12.50
Overall L1	15.38

Vectorization ratios

INT

all	1%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	5%

all	20%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	66%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	4%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	18%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	3%

Vector efficiency ratios

INT

all	20%
load	24%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	17%

all	40%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	75%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	23%
load	24%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	29%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	19%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 15.38 cycles. At this rate:

0% of peak load performance is reached (0.39 out of 96.00 bytes loaded 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 15.38 to 12.50 cycles (1.23x speedup).

ASM code

In the binary file, the address of the loop is: 42bf60

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	Latency	Recip. throughput	Vectorization
LDR X16, [X12, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
LDR W17, [X11, X8,LSL #2]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	scal (12.5%)
ADD X8, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
LDR W18, [X11, X8,LSL #2]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
CMP W18, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.LE 42c3cc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x54c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB W30, W18, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
SBFM X15, X17, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
LDR D31, [X16, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
ANDS W3, W30, #0x7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD X0, X14, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ W2, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ORR W30, WZR, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
B.EQ 42c0cc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x24c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c0a0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x220>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c07c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c058 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c034 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1b4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c010 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x190>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42bfec <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x16c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR D30, [X14, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D30	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42bfe4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x164>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42bfe4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x164>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVZ W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
STR D30, [X4]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D0, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c008 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x188>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c008 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x188>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D0, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D1, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D1	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c02c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1ac>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c02c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1ac>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D1, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D3, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D3	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c050 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c050 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D3, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D4, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c074 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c074 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D4, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D5, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D5	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c098 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x218>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c098 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x218>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D5, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D6, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D6	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c0bc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x23c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c0bc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x23c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D6, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
CMP W18, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c1dc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x35c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CBZ W2, 42c3cc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x54c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X18, X16, #568	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
LD1RD {Z4.D}, P7/Z, [X16, #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z5.D}, P7/Z, [X16, #4]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z6.D}, P7/Z, [X16, #5]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z7.D}, P7/Z, [X16, #6]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z16.D}, P7/Z, [X16, #7]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z17.D}, P7/Z, [X16, #8]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z18.D}, P7/Z, [X16, #9]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z19.D}, P7/Z, [X16, #10]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z20.D}, P7/Z, [X16, #11]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z21.D}, P7/Z, [X16, #12]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z22.D}, P7/Z, [X16, #13]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z23.D}, P7/Z, [X16, #14]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z24.D}, P7/Z, [X16, #15]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z25.D}, P7/Z, [X16, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z26.D}, P7/Z, [X16, #17]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z27.D}, P7/Z, [X16, #18]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LDR X16, [X16, #536]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
MOVZ X3, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W15, WZR, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
DUP Z1.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	2	0.50	scal (3.1%)
UQDECD W15, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	N/A
LD1RD {Z3.D}, P7/Z, [X18]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
WHILELO P5.D, WZR, W15	1	0	0	0	0	1	0	0	0	0	0	0	0	0	3	2	N/A
ORR Z28.D, Z1.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	2	0.50	vect (100.0%)
WHILELO P6.D, WZR, W2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	3	2	N/A
FADD Z3.D, Z28.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	2	0.50	vect (100.0%)
FADDV D1, P7, Z3.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	9	2	vect (100.0%)
FADD D2, D2, D1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (25.0%)
CMP X13, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	N/A
B.NE 42bf60 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0xe0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source file and lines	TwoBodyJastrowRef.h:127-132
Module	exec

The loop is defined in:

/usr/include/c++/14/bits/stl_vector.h:1147
/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:127-132
/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316
/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:232-260

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths (too many, greater than internal limit = 100000)
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is very high. Force analysis with --force-loop-streams-analysis: expect potentially high RAM/CPU footprint

Try to simplify control.

gain
potential
hint
expert

Code clean check

Workaround

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

Vectorization

Details

4% of VPU instructions are used in vector version (process two or more data elements in vector registers):

0% of VPU loads are used in vector version.
0% of VPU stores are used in vector version.
18% of VPU addition or subtraction instructions are used in vector version.
3% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop 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)

No data for this section

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

The binary loop is composed of 9 FP arithmetical operations:

9: addition or subtraction

The binary loop is loading 6 bytes.

Arithmetic intensity

Arithmetic intensity is 1.50 FP operations per loaded or stored byte.

General properties

nb instructions	123
nb uops	123
loop length	492
used w registers	8
used x registers	12
used b registers	0
used h registers	0
used s registers	0
used d registers	9
used q registers	0
used v registers	0
used z registers	19
nb stack references	0

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	15.38 cycles
front end	15.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	12.50	12.50	12.50	12.50	12.50	12.50	9.00	9.00	1.00	1.00	12.00	12.00	12.00	0.00	0.00
cycles	12.50	12.50	12.50	12.50	12.50	12.50	9.00	9.00	1.75	1.75	12.00	12.00	12.00	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
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	15.38
Dispatch	12.50
Overall L1	15.38

Vectorization ratios

INT

all	1%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	5%

all	20%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	66%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	4%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	18%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	3%

Vector efficiency ratios

INT

all	20%
load	24%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	17%

all	40%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	75%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	23%
load	24%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	29%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	19%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 15.38 cycles. At this rate:

0% of peak load performance is reached (0.39 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the loop is: 42bf60

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	Latency	Recip. throughput	Vectorization
LDR X16, [X12, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
LDR W17, [X11, X8,LSL #2]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	scal (12.5%)
ADD X8, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
LDR W18, [X11, X8,LSL #2]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
CMP W18, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.LE 42c3cc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x54c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB W30, W18, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
SBFM X15, X17, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
LDR D31, [X16, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
ANDS W3, W30, #0x7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD X0, X14, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ W2, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ORR W30, WZR, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
B.EQ 42c0cc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x24c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c0a0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x220>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c07c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c058 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c034 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1b4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c010 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x190>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W3, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42bfec <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x16c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR D30, [X14, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D30	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42bfe4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x164>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42bfe4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x164>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVZ W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
STR D30, [X4]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D0, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c008 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x188>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c008 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x188>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D0, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D1, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D1	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c02c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1ac>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c02c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1ac>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D1, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D3, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D3	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c050 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c050 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D3, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D4, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D4	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c074 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c074 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D4, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D5, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D5	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c098 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x218>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c098 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x218>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D5, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
LDR D6, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (25.0%)
FCMPE D31, D6	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (25.0%)
B.LS 42c0bc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x23c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W24, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c0bc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x23c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D6, [X4, W2,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (25.0%)
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
ADD W30, W30, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD X0, X0, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
CMP W18, W30	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 42c1dc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x35c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CBZ W2, 42c3cc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x54c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X18, X16, #568	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
LD1RD {Z4.D}, P7/Z, [X16, #3]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z5.D}, P7/Z, [X16, #4]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z6.D}, P7/Z, [X16, #5]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z7.D}, P7/Z, [X16, #6]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z16.D}, P7/Z, [X16, #7]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z17.D}, P7/Z, [X16, #8]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z18.D}, P7/Z, [X16, #9]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z19.D}, P7/Z, [X16, #10]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z20.D}, P7/Z, [X16, #11]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z21.D}, P7/Z, [X16, #12]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z22.D}, P7/Z, [X16, #13]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z23.D}, P7/Z, [X16, #14]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z24.D}, P7/Z, [X16, #15]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z25.D}, P7/Z, [X16, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z26.D}, P7/Z, [X16, #17]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LD1RD {Z27.D}, P7/Z, [X16, #18]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
LDR X16, [X16, #536]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
MOVZ X3, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W15, WZR, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25	N/A
DUP Z1.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	2	0.50	scal (3.1%)
UQDECD W15, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	N/A
LD1RD {Z3.D}, P7/Z, [X18]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	6	0.50	scal (25.0%)
WHILELO P5.D, WZR, W15	1	0	0	0	0	1	0	0	0	0	0	0	0	0	3	2	N/A
ORR Z28.D, Z1.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	2	0.50	vect (100.0%)
WHILELO P6.D, WZR, W2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	3	2	N/A
FADD Z3.D, Z28.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	2	0.50	vect (100.0%)
FADDV D1, P7, Z3.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	9	2	vect (100.0%)
FADD D2, D2, D1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (25.0%)
CMP X13, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	N/A
B.NE 42bf60 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0xe0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code