OV - exec - Function miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::recompute(qmcplusplus::ParticleSet&)

	Function: miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::recompute(qmcpl ...	Module: exec	Source: OneBodyJastrowRef.h:107-194 [...]	Coverage (incl. loops): 0.01% \| (excl. loops): 0.00%

/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_numeric.h: 140 - 141

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

140:       for (; __first != __last; ++__first)

141: 	__init = _GLIBCXX_MOVE_IF_20(__init) + *__first;

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 107 - 194

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

107:   {

108:     const auto& d_ie = P.getDistTableAB(myTableID);

109:     for (int iat = 0; iat < Nelec; ++iat)

110:     {

111:       computeU3(P, iat, d_ie.getDistRow(iat).data());

112:       Vat[iat] = std::accumulate(U.begin(), U.begin() + Nions, valT());

113:       Lap[iat] = accumulateGL(dU.data(), d2U.data(), d_ie.getDisplRow(iat), Grad[iat]);

114:     }

115:   }

[...]

186:     for (int jat = 0; jat < Nions; ++jat)

187:       lap += d2u[jat] + lapfac * du[jat];

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

189:     {

190:       const valT* restrict dX = displ.data(idim);

191:       valT s                  = valT();

192:       for (int jat = 0; jat < Nions; ++jat)

193:         s += du[jat] * dX[jat];

194:       grad[idim] = s;

/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; }

/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h: 1150 - 1150

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

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

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 273 - 273

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

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

0x417620 STP	X29, X30, [SP, #960]!

0x417624 STP	X24, X23, [SP, #16]

0x417628 STP	X22, X21, [SP, #32]

0x41762c STP	X20, X19, [SP, #48]

0x417630 ADD	X29, SP, #0

0x417634 ORR	X19, XZR, X1

0x417638 LDR	W1, [X0, #168]

0x41763c ORR	X20, XZR, X0

0x417640 ORR	X0, XZR, X19

0x417644 BL	447230

0x417648 LDR	W8, [X20, #148]

0x41764c CMP	W8, #1

0x417650 B.LT	4179f0

0x417654 MOVZ	W23, #40

0x417658 MOVZ	W24, #24

0x41765c ORR	X21, XZR, X0

0x417660 ORR	X22, XZR, XZR

0x417664 B	41768c

    (270) 0x417668 MOVI	D0, #0

    (270) 0x41766c STP	XZR, XZR, [X9]

    (270) 0x417670 STR	XZR, [X9, #16]

    (270) 0x417674 LDR	X8, [X20, #440]

    (270) 0x417678 STR	D0, [X8, X22,LSL #3]

    (270) 0x41767c LDRSW	X8, [X20, #148]

    (270) 0x417680 ADD	X22, X22, #1

    (270) 0x417684 CMP	X22, X8

    (270) 0x417688 B.GE	4179f0

    (270) 0x41768c LDR	X8, [X21, #72]

    (270) 0x417690 ORR	X0, XZR, X20

    (270) 0x417694 ORR	X1, XZR, X19

    (270) 0x417698 ORR	W2, WZR, W22

    (270) 0x41769c MADD	X8, X22, X23, X8

    (270) 0x4176a0 LDR	X3, [X8, #24]

    (270) 0x4176a4 BL	4168c0

    (270) 0x4176a8 LDRSW	X8, [X20, #144]

    (270) 0x4176ac CBZ	W8, 4176e0

    (270) 0x4176b0 LDR	X10, [X20, #256]

    (270) 0x4176b4 SUB	X9, X8, #1

    (270) 0x4176b8 AND	X9, X9, #7936

    (270) 0x4176bc CMP	X9, #3

    (270) 0x4176c0 B.CS	4176e8

    (270) 0x4176c4 MOVI	D0, #0

    (270) 0x4176c8 ORR	X9, XZR, X10

    (270) 0x4176cc B	41772c

0x4176d0 HINT	#0

0x4176d4 HINT	#0

0x4176d8 HINT	#0

0x4176dc HINT	#0

    (270) 0x4176e0 MOVI	D0, #0

    (270) 0x4176e4 B	417750

    (270) 0x4176e8 ADD	X11, X9, #1

    (270) 0x4176ec ADD	X13, X10, #16

    (270) 0x4176f0 MOVI	V0.2D, #0

    (270) 0x4176f4 MOVI	V1.2D, #0

    (270) 0x4176f8 AND	X12, X11, #7934

    (270) 0x4176fc ADD	X9, X10, X12,LSL #3

    (270) 0x417700 ORR	X14, XZR, X12

      (280) 0x417704 LDP	Q2, Q3, [X13, #2032]

      (280) 0x417708 ADD	X13, X13, #32

      (280) 0x41770c SUBS	X14, X14, #4

      (280) 0x417710 FADD	V1.2D, V3.2D, V1.2D

      (280) 0x417714 FADD	V0.2D, V2.2D, V0.2D

      (280) 0x417718 B.NE	417704

    (270) 0x41771c FADD	V0.2D, V1.2D, V0.2D

    (270) 0x417720 FADDP	D0, V0.2D

    (270) 0x417724 CMP	X11, X12

    (270) 0x417728 B.EQ	417750

    (270) 0x41772c ADD	X10, X10, X8,LSL #3

    (270) 0x417730 HINT	#0

    (270) 0x417734 HINT	#0

    (270) 0x417738 HINT	#0

    (270) 0x41773c HINT	#0

      (281) 0x417740 LDR	D1, [X9], #8

      (281) 0x417744 FADD	D0, D1, D0

      (281) 0x417748 CMP	X9, X10

      (281) 0x41774c B.NE	417740

    (270) 0x417750 LDR	X9, [X20, #240]

    (270) 0x417754 STR	D0, [X9, X22,LSL #3]

    (270) 0x417758 LDR	X9, [X20, #400]

    (270) 0x41775c MADD	X9, X22, X24, X9

    (270) 0x417760 CMP	W8, #1

    (270) 0x417764 B.LT	417668

  (276) 0x417768 LDR	X10, [X20, #280]

  (276) 0x41776c LDR	X11, [X20, #304]

  (276) 0x417770 CMP	W8, #3

  (276) 0x417774 B.HI	417784

  (276) 0x417778 MOVI	D0, #0

  (276) 0x41777c ORR	X12, XZR, XZR

  (276) 0x417780 B	4177e0

  (276) 0x417784 AND	X12, X8, #5950

  (276) 0x417788 ADD	X13, X11, #16

  (276) 0x41778c ADD	X14, X10, #16

  (276) 0x417790 MOVI	V0.2D, #0

  (276) 0x417794 MOVI	V1.2D, #0

  (276) 0x417798 ORR	X15, XZR, X12

  (276) 0x41779c HINT	#0

    (271) 0x4177a0 LDP	Q2, Q3, [X13, #2032]

    (271) 0x4177a4 LDP	Q4, Q5, [X14, #2032]

    (271) 0x4177a8 ADD	X13, X13, #32

    (271) 0x4177ac ADD	X14, X14, #32

    (271) 0x4177b0 SUBS	X15, X15, #4

    (271) 0x4177b4 FADD	V5.2D, V5.2D, V5.2D

    (271) 0x4177b8 FADD	V1.2D, V3.2D, V1.2D

    (271) 0x4177bc FADD	V4.2D, V4.2D, V4.2D

    (271) 0x4177c0 FADD	V0.2D, V2.2D, V0.2D

    (271) 0x4177c4 FADD	V1.2D, V1.2D, V5.2D

    (271) 0x4177c8 FADD	V0.2D, V0.2D, V4.2D

    (271) 0x4177cc B.NE	4177a0

  (276) 0x4177d0 FADD	V0.2D, V1.2D, V0.2D

  (276) 0x4177d4 FADDP	D0, V0.2D

  (276) 0x4177d8 CMP	X12, X8

  (276) 0x4177dc B.EQ	417808

  (276) 0x4177e0 SUB	X13, X8, X12

  (276) 0x4177e4 ADD	X14, X10, X12,LSL #3

  (276) 0x4177e8 ADD	X11, X11, X12,LSL #3

    (279) 0x4177ec LDR	D1, [X11], #8

    (279) 0x4177f0 LDR	D2, [X14], #8

    (279) 0x4177f4 SUBS	X13, X13, #1

    (279) 0x4177f8 FADD	D2, D2, D2

    (279) 0x4177fc FADD	D0, D1, D0

    (279) 0x417800 FADD	D0, D0, D2

    (279) 0x417804 B.NE	4177ec

  (276) 0x417808 LDR	X11, [X21, #96]

  (276) 0x41780c MADD	X12, X22, X23, X11

  (276) 0x417810 LDR	X11, [X12, #24]

  (276) 0x417814 CMP	W8, #4

  (276) 0x417818 B.CS	417828

  (276) 0x41781c ORR	X13, XZR, XZR

  (276) 0x417820 MOVI	D1, #0

  (276) 0x417824 B	417870

  (276) 0x417828 AND	X13, X8, #5950

  (276) 0x41782c ADD	X14, X10, #16

  (276) 0x417830 ADD	X15, X11, #16

  (276) 0x417834 MOVI	V1.2D, #0

  (276) 0x417838 MOVI	V2.2D, #0

  (276) 0x41783c ORR	X16, XZR, X13

    (272) 0x417840 LDP	Q3, Q4, [X14, #2032]

    (272) 0x417844 LDP	Q5, Q6, [X15, #2032]

    (272) 0x417848 ADD	X14, X14, #32

    (272) 0x41784c ADD	X15, X15, #32

    (272) 0x417850 SUBS	X16, X16, #4

    (272) 0x417854 FMLA	V2.2D, V6.2D, V4.2D

    (272) 0x417858 FMLA	V1.2D, V5.2D, V3.2D

    (272) 0x41785c B.NE	417840

  (276) 0x417860 FADD	V1.2D, V2.2D, V1.2D

  (276) 0x417864 FADDP	D1, V1.2D

  (276) 0x417868 CMP	X13, X8

  (276) 0x41786c B.EQ	417894

  (276) 0x417870 SUB	X14, X8, X13

  (276) 0x417874 ADD	X15, X11, X13,LSL #3

  (276) 0x417878 ADD	X13, X10, X13,LSL #3

  (276) 0x41787c HINT	#0

    (278) 0x417880 LDR	D2, [X13], #8

    (278) 0x417884 LDR	D3, [X15], #8

    (278) 0x417888 SUBS	X14, X14, #1

    (278) 0x41788c FMADD	D1, D3, D2, D1

    (278) 0x417890 B.NE	417880

  (276) 0x417894 LDR	X12, [X12, #8]

  (276) 0x417898 STR	D1, [X9]

  (276) 0x41789c CMP	W8, #4

  (276) 0x4178a0 B.CS	4178c0

  (276) 0x4178a4 ORR	X13, XZR, XZR

  (276) 0x4178a8 MOVI	D1, #0

  (276) 0x4178ac B	417910

0x4178b0 HINT	#0

0x4178b4 HINT	#0

0x4178b8 HINT	#0

0x4178bc HINT	#0

  (276) 0x4178c0 ADD	X15, X11, X12,LSL #3

  (276) 0x4178c4 AND	X13, X8, #5950

  (276) 0x4178c8 ADD	X14, X10, #16

  (276) 0x4178cc MOVI	V1.2D, #0

  (276) 0x4178d0 MOVI	V2.2D, #0

  (276) 0x4178d4 ADD	X15, X15, #16

  (276) 0x4178d8 ORR	X16, XZR, X13

  (276) 0x4178dc HINT	#0

    (273) 0x4178e0 LDP	Q3, Q4, [X14, #2032]

    (273) 0x4178e4 LDP	Q5, Q6, [X15, #2032]

    (273) 0x4178e8 ADD	X14, X14, #32

    (273) 0x4178ec ADD	X15, X15, #32

    (273) 0x4178f0 SUBS	X16, X16, #4

    (273) 0x4178f4 FMLA	V2.2D, V6.2D, V4.2D

    (273) 0x4178f8 FMLA	V1.2D, V5.2D, V3.2D

    (273) 0x4178fc B.NE	4178e0

  (276) 0x417900 FADD	V1.2D, V2.2D, V1.2D

  (276) 0x417904 FADDP	D1, V1.2D

  (276) 0x417908 CMP	X13, X8

  (276) 0x41790c B.EQ	417938

  (276) 0x417910 UBFM	X15, X13, #61, #60

  (276) 0x417914 SUB	X14, X8, X13

  (276) 0x417918 ADD	X13, X10, X13,LSL #3

  (276) 0x41791c ADD	X15, X15, X12,LSL #3

  (276) 0x417920 ADD	X15, X11, X15

    (277) 0x417924 LDR	D2, [X13], #8

    (277) 0x417928 LDR	D3, [X15], #8

    (277) 0x41792c SUBS	X14, X14, #1

    (277) 0x417930 FMADD	D1, D3, D2, D1

    (277) 0x417934 B.NE	417924

  (276) 0x417938 UBFM	X12, X12, #60, #59

  (276) 0x41793c STR	D1, [X9, #8]

  (276) 0x417940 CMP	W8, #4

  (276) 0x417944 B.CS	417960

  (276) 0x417948 ORR	X13, XZR, XZR

  (276) 0x41794c MOVI	D1, #0

  (276) 0x417950 B	4179b0

0x417954 HINT	#0

0x417958 HINT	#0

0x41795c HINT	#0

(274) 0x417960 ADD	X15, X11, X12

(274) 0x417964 AND	X13, X8, #5950

(274) 0x417968 ADD	X14, X10, #16

(274) 0x41796c MOVI	V1.2D, #0

(274) 0x417970 MOVI	V2.2D, #0

(274) 0x417974 ADD	X15, X15, #16

(274) 0x417978 ORR	X16, XZR, X13

(274) 0x41797c HINT	#0

  (269) 0x417980 LDP	Q3, Q4, [X14, #2032]

  (269) 0x417984 LDP	Q5, Q6, [X15, #2032]

  (269) 0x417988 ADD	X14, X14, #32

  (269) 0x41798c ADD	X15, X15, #32

  (269) 0x417990 SUBS	X16, X16, #4

  (269) 0x417994 FMLA	V2.2D, V6.2D, V4.2D

  (269) 0x417998 FMLA	V1.2D, V5.2D, V3.2D

  (269) 0x41799c B.NE	417980

(274) 0x4179a0 FADD	V1.2D, V2.2D, V1.2D

(274) 0x4179a4 FADDP	D1, V1.2D

(274) 0x4179a8 CMP	X13, X8

(274) 0x4179ac B.EQ	4179d4

  (276) 0x4179b0 ADD	X12, X12, X13,LSL #3

  (276) 0x4179b4 SUB	X8, X8, X13

  (276) 0x4179b8 ADD	X10, X10, X13,LSL #3

  (276) 0x4179bc ADD	X11, X11, X12

    (275) 0x4179c0 LDR	D2, [X10], #8

    (275) 0x4179c4 LDR	D3, [X11], #8

    (275) 0x4179c8 SUBS	X8, X8, #1

    (275) 0x4179cc FMADD	D1, D3, D2, D1

    (275) 0x4179d0 B.NE	4179c0

  (276) 0x4179d4 STR	D1, [X9, #16]

  (276) 0x4179d8 LDR	X8, [X20, #440]

  (276) 0x4179dc STR	D0, [X8, X22,LSL #3]

  (276) 0x4179e0 LDRSW	X8, [X20, #148]

  (276) 0x4179e4 ADD	X22, X22, #1

  (276) 0x4179e8 CMP	X22, X8

  (276) 0x4179ec B.LT	41768c

0x4179f0 LDP	X20, X19, [SP, #48]

0x4179f4 LDP	X22, X21, [SP, #32]

0x4179f8 LDP	X24, X23, [SP, #16]

0x4179fc LDP	X29, X30, [SP], #64

0x417a00 RET

0x417a04 HINT	#0

0x417a08 HINT	#0

0x417a0c HINT	#0

0x417a10 HINT	#0

0x417a14 HINT	#0

0x417a18 HINT	#0

0x417a1c HINT	#0

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:167	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:167	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:167	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:167	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:167	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:167	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:167	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:167	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:167	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:167	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:167	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

min	med	avg	max

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

min	med	avg	max

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

Path /

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

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run 1x1

Source file and lines	OneBodyJastrowRef.h:107-194
Module	exec

The function is defined in:

/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_numeric.h:140-141
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:107-115,186-194
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249
/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h:1150
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:273

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 69% of vector register length is used (average across all VPU instructions). By vectorizing your function, you can lower the cost of an iteration from 3.33 to 3.25 cycles (1.03x 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 3.33 to 0.50 cycles (6.67x 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 72 bytes. The binary function is storing 64 bytes.

General properties

nb instructions	41
loop length	164
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

2.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	2.00	2.00	1.83	1.83	1.83	1.83	1.83	1.83	0.00	0.00	0.00	0.00	3.33	3.33	3.33	2.00	2.00
cycles	2.00	2.00	1.83	1.83	1.83	1.83	1.83	1.83	0.00	0.00	0.00	0.00	3.33	3.33	3.33	2.00	2.00

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	2.88
Overall L1	3.33

Vectorization ratios

all	0%
load	0%
store	0%
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 3.33 cycles. At this rate:

22% of peak load performance is reached (21.60 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
39% of peak store performance is reached (19.20 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 417620

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, #960]!	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%)
STP X24, X23, [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%)
STP X22, X21, [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%)
STP X20, X19, [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%)
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%)
ORR X19, 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%)
LDR W1, [X0, #168]	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 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
ORR X0, 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	N/A
BL 447230 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	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 W8, [X20, #148]	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
CMP W8, #1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	N/A
B.LT 4179f0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3d0>	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
MOVZ W23, #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%)
MOVZ W24, #24	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%)
ORR X21, 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	scal (50.0%)
ORR X22, XZR, XZR	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%)
B 41768c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x6c>	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
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
LDP X20, X19, [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 X22, X21, [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	scal (100.0%)
LDP X24, X23, [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	scal (100.0%)
LDP X29, X30, [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%)
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
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run 1x1

Source file and lines	OneBodyJastrowRef.h:107-194
Module	exec

The function is defined in:

/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_numeric.h:140-141
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:107-115,186-194
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249
/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h:1150
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:273

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 3.33 to 0.50 cycles (6.67x 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 72 bytes. The binary function is storing 64 bytes.

General properties

nb instructions	41
loop length	164
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

2.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	2.00	2.00	1.83	1.83	1.83	1.83	1.83	1.83	0.00	0.00	0.00	0.00	3.33	3.33	3.33	2.00	2.00
cycles	2.00	2.00	1.83	1.83	1.83	1.83	1.83	1.83	0.00	0.00	0.00	0.00	3.33	3.33	3.33	2.00	2.00

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	2.88
Overall L1	3.33

Vectorization ratios

all	0%
load	0%
store	0%
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 3.33 cycles. At this rate:

22% of peak load performance is reached (21.60 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
39% of peak store performance is reached (19.20 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 417620

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, #960]!	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%)
STP X24, X23, [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%)
STP X22, X21, [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%)
STP X20, X19, [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%)
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%)
ORR X19, 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%)
LDR W1, [X0, #168]	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 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
ORR X0, 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	N/A
BL 447230 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	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 W8, [X20, #148]	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
CMP W8, #1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	N/A
B.LT 4179f0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3d0>	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
MOVZ W23, #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%)
MOVZ W24, #24	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%)
ORR X21, 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	scal (50.0%)
ORR X22, XZR, XZR	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%)
B 41768c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x6c>	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
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A
LDP X20, X19, [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 X22, X21, [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	scal (100.0%)
LDP X24, X23, [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	scal (100.0%)
LDP X29, X30, [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%)
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
HINT #0																					N/A
HINT #0																					N/A
HINT #0																					N/A

▶Scalability Runs Description

Run 1x1	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_NUM_THREADS: 1OMP_PLACES: threads
Run 1x2	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 2OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x4	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 4OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x8	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 8OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x16	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 16OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x24	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 24OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x32	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 32OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x40	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 40OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x48	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 48OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x56	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 56OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x64	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 64OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x72	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 72OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x80	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 80OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x88	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 88OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x96	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 96OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

(1x1) Efficiency	(1x1) Potential Speed-Up (%)	(1x2) Efficiency	(1x2) Potential Speed-Up (%)	(1x4) Efficiency	(1x4) Potential Speed-Up (%)	(1x8) Efficiency	(1x8) Potential Speed-Up (%)	(1x16) Efficiency	(1x16) Potential Speed-Up (%)	(1x24) Efficiency	(1x24) Potential Speed-Up (%)	(1x32) Efficiency	(1x32) Potential Speed-Up (%)	(1x40) Efficiency	(1x40) Potential Speed-Up (%)	(1x48) Efficiency	(1x48) Potential Speed-Up (%)	(1x56) Efficiency	(1x56) Potential Speed-Up (%)	(1x64) Efficiency	(1x64) Potential Speed-Up (%)	(1x72) Efficiency	(1x72) Potential Speed-Up (%)	(1x80) Efficiency	(1x80) Potential Speed-Up (%)	(1x88) Efficiency	(1x88) Potential Speed-Up (%)	(1x96) Efficiency	(1x96) Potential Speed-Up (%)
1	0	0.67	0.01	1.33	0	1	0	1	0	0.85	0	0.65	0	0.66	0	0.53	0.01	0.5	0.01	0.49	0.01	0.43	0.01	0.4	0.01	0.36	0.01	0.33	0.01

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency

Run	Number of threads	Efficiency (ideal is 1)	Speedup	Ideal Speedup	Time (s)	Coverage (%)
1x1	1	1	1	1	0.0049999998882413	0.011618477292359
1x2	2	0.67	0.67	2	0.00999999884516	0.01715743727982
1x4	3	1.33	1.33	4	0.0049999998882413	0.0083539877086878
1x8	7	1	1	8	0.00999999884516	0.01042228937149
1x16	13	1	1	16	0.0099999997764826	0.0088396240025759
1x24	22	0.85	0.85	24	0.00999999884516	0.0093286316841841
1x32	31	0.65	0.65	32	0.014999997802079	0.01077676191926
1x40	39	0.66	0.66	40	0.014999998733401	0.0095772985368967
1x48	48	0.53	0.53	48	0.014999998733401	0.01101319398731
1x56	55	0.5	0.5	56	0.014999999664724	0.010678363032639
1x64	64	0.49	0.49	64	0.019999995827675	0.010101376101375
1x72	72	0.43	0.43	72	0.02000000141561	0.010496485047042
1x80	78	0.4	0.4	80	0.01999999769032	0.010510233230889
1x88	84	0.36	0.36	88	0.024999996647239	0.010817245580256
1x96	96	0.33	0.33	96	0.024999998509884	0.011121783405542

Name	Coverage (%)	Time (s)
▼miniqmcreference::OneBodyJastrowRef >::recompute(qmcplusplus::ParticleSet&)–	0.01	0.00
▼Loop 274 - OneBodyJastrowRef.h:109-194 - exec–	0.00	0.00
▼Loop 276 - OneBodyJastrowRef.h:109-194 - exec–	0.00	0.00
○Loop 273 - OneBodyJastrowRef.h:192-193 - exec	0.01	0.00
○Loop 277 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 279 - OneBodyJastrowRef.h:186-187 - exec	0.00	0.00
○Loop 272 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
▼Loop 270 - OneBodyJastrowRef.h:109-194 - exec–	0.00	0.00
○Loop 280 - stl_numeric.h:141-141 - exec	0.00	0.00
○Loop 281 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 275 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 278 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 271 - OneBodyJastrowRef.h:186-187 - exec	0.00	0.00
○Loop 269 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00

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

▶Scalability Runs Description

▼Columns Filter

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency