OV - exec - Function miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)

	Function: miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcpl ...	Module: exec	Source: OneBodyJastrowRef.h:186-263 [...]	Coverage: 0.07%

/usr/lib/gcc/aarch64-linux-gnu/12/../../../../include/c++/12/bits/stl_vector.h: 1256 - 1256

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

1256:       { return _M_data_ptr(this->_M_impl._M_start); }

/home/hbollore/qaas-runs/171-284-6744/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 186 - 263

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

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;

[...]

256:   {

257:     UpdateMode = ORB_PBYP_PARTIAL;

258:

259:     computeU3(P, iat, P.getDistTableAB(myTableID).getTempDists().data());

260:     curLap = accumulateGL(dU.data(), d2U.data(), P.getDistTableAB(myTableID).getTempDispls(), curGrad);

261:     curAt  = std::accumulate(U.begin(), U.begin() + Nions, valT());

262:     grad_iat += curGrad;

263:     return std::exp(Vat[iat] - curAt);

/usr/lib/gcc/aarch64-linux-gnu/12/../../../../include/c++/12/bits/stl_numeric.h: 140 - 141

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

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

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

/home/hbollore/qaas-runs/171-284-6744/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 94

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

94:     (const_cast<T1&>(a) += b);

/home/hbollore/qaas-runs/171-284-6744/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 249

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

223:     return X[i];

[...]

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

0x415580 STP	X29, X30, [SP, #960]!

0x415584 STP	X24, X23, [SP, #16]

0x415588 STP	X22, X21, [SP, #32]

0x41558c STP	X20, X19, [SP, #48]

0x415590 ADD	X29, SP, #0

0x415594 ORR	X22, XZR, X1

0x415598 LDR	W1, [X0, #168]

0x41559c MOVZ	W8, #2

0x4155a0 ORR	X20, XZR, X0

0x4155a4 STR	W8, [X0, #12]

0x4155a8 ORR	X21, XZR, X3

0x4155ac ORR	W19, WZR, W2

0x4155b0 ORR	X0, XZR, X22

0x4155b4 BL	44a070

0x4155b8 LDR	X3, [X0, #144]

0x4155bc ORR	X0, XZR, X20

0x4155c0 ORR	X1, XZR, X22

0x4155c4 ORR	W2, WZR, W19

0x4155c8 BL	4177e0

0x4155cc LDR	W1, [X20, #168]

0x4155d0 LDR	X23, [X20, #280]

0x4155d4 LDR	X24, [X20, #304]

0x4155d8 ORR	X0, XZR, X22

0x4155dc BL	44a070

0x4155e0 LDR	W9, [X20, #144]

0x4155e4 CNTW	X8, ALL

0x4155e8 ADD	X13, X20, #192

0x4155ec CMP	W9, #1

0x4155f0 B.LT	415610

0x4155f4 UDIV	X11, X9, X8

0x4155f8 ADDVL	X10, X23, #1

0x4155fc CMP	X8, X9

0x415600 B.LS	415630

0x415604 ORR	X12, XZR, XZR

0x415608 MOVI	D0, #0

0x41560c B	415698

0x415610 MOVI	D1, #0

0x415614 MOVI	D0, #0

0x415618 STP	XZR, XZR, [X13]

0x41561c STR	XZR, [X13, #16]

0x415620 STR	D0, [X20, #184]

0x415624 CBNZ	W9, 4158a4

0x415628 MOVI	D0, #0

0x41562c B	41593c

0x415630 DUP	Z0.D, #0

0x415634 ORR	X15, XZR, XZR

0x415638 UMSUBL	X14, W11, W8, X9

0x41563c FDUP	Z1.D, #0

0x415640 ORR	Z2.D, Z0.D, Z0.D

0x415644 UMADDL	X12, W11, W8, XZR

0x415648 ADDVL	X16, X24, #1

0x41564c PTRUE	P0.D, ALL

0x415650 HINT	#0

0x415654 HINT	#0

0x415658 HINT	#0

0x41565c HINT	#0

(276) 0x415660 LD1D	{Z3.D}, P0/Z, [X24, X15,LSL #3]

(276) 0x415664 LD1D	{Z4.D}, P0/Z, [X16, X15,LSL #3]

(276) 0x415668 FADD	Z0.D, Z3.D, Z0.D

(276) 0x41566c LD1D	{Z5.D}, P0/Z, [X23, X15,LSL #3]

(276) 0x415670 LD1D	{Z6.D}, P0/Z, [X10, X15,LSL #3]

(276) 0x415674 FADD	Z2.D, Z4.D, Z2.D

(276) 0x415678 ADD	X15, X15, X8

(276) 0x41567c CMP	X12, X15

(276) 0x415680 FMLA	Z0.D, P0/M, Z5.D, Z1.D

(276) 0x415684 FMLA	Z2.D, P0/M, Z6.D, Z1.D

(276) 0x415688 B.NE	415660

0x41568c FADD	Z0.D, Z2.D, Z0.D

0x415690 FADDV	D0, P0, Z0.D

0x415694 CBZ	X14, 4156c4

0x415698 UBFM	X15, X12, #61, #60

0x41569c SUB	X14, X9, X12

0x4156a0 ADD	X12, X23, X15

0x4156a4 ADD	X15, X24, X15

(283) 0x4156a8 LDR	D1, [X15], #8

(283) 0x4156ac LDR	D2, [X12], #8

(283) 0x4156b0 FADD	D2, D2, D2

(283) 0x4156b4 FADD	D0, D1, D0

(283) 0x4156b8 SUBS	X14, X14, #1

(283) 0x4156bc FADD	D0, D0, D2

(283) 0x4156c0 B.NE	4156a8

0x4156c4 LDR	X12, [X0, #184]

0x4156c8 CMP	X8, X9

0x4156cc B.LS	4156dc

0x4156d0 ORR	X14, XZR, XZR

0x4156d4 MOVI	D1, #0

0x4156d8 B	415730

0x4156dc DUP	Z1.D, #0

0x4156e0 ORR	X16, XZR, XZR

0x4156e4 UMSUBL	X15, W11, W8, X9

0x4156e8 ORR	Z2.D, Z1.D, Z1.D

0x4156ec UMADDL	X14, W11, W8, XZR

0x4156f0 ADDVL	X17, X12, #1

0x4156f4 PTRUE	P0.D, ALL

0x4156f8 HINT	#0

0x4156fc HINT	#0

(277) 0x415700 LD1D	{Z3.D}, P0/Z, [X23, X16,LSL #3]

(277) 0x415704 LD1D	{Z4.D}, P0/Z, [X10, X16,LSL #3]

(277) 0x415708 LD1D	{Z5.D}, P0/Z, [X12, X16,LSL #3]

(277) 0x41570c FMLA	Z1.D, P0/M, Z5.D, Z3.D

(277) 0x415710 LD1D	{Z6.D}, P0/Z, [X17, X16,LSL #3]

(277) 0x415714 FMLA	Z2.D, P0/M, Z6.D, Z4.D

(277) 0x415718 ADD	X16, X16, X8

(277) 0x41571c CMP	X14, X16

(277) 0x415720 B.NE	415700

0x415724 FADD	Z1.D, Z2.D, Z1.D

0x415728 FADDV	D1, P0, Z1.D

0x41572c CBZ	X15, 415754

0x415730 UBFM	X16, X14, #61, #60

0x415734 SUB	X15, X9, X14

0x415738 ADD	X14, X12, X16

0x41573c ADD	X16, X23, X16

(282) 0x415740 LDR	D2, [X16], #8

(282) 0x415744 LDR	D3, [X14], #8

(282) 0x415748 FMADD	D1, D3, D2, D1

(282) 0x41574c SUBS	X15, X15, #1

(282) 0x415750 B.NE	415740

0x415754 LDR	X14, [X0, #168]

0x415758 CMP	X8, X9

0x41575c STR	D1, [X13]

0x415760 B.LS	415770

0x415764 ORR	X13, XZR, XZR

0x415768 MOVI	D2, #0

0x41576c B	4157d0

0x415770 ADD	X17, X12, X14,LSL #3

0x415774 DUP	Z2.D, #0

0x415778 ORR	X16, XZR, XZR

0x41577c ORR	Z3.D, Z2.D, Z2.D

0x415780 UMSUBL	X15, W11, W8, X9

0x415784 UMADDL	X13, W11, W8, XZR

0x415788 ADDVL	X18, X17, #1

0x41578c PTRUE	P0.D, ALL

0x415790 HINT	#0

0x415794 HINT	#0

0x415798 HINT	#0

0x41579c HINT	#0

(278) 0x4157a0 LD1D	{Z4.D}, P0/Z, [X23, X16,LSL #3]

(278) 0x4157a4 LD1D	{Z5.D}, P0/Z, [X10, X16,LSL #3]

(278) 0x4157a8 LD1D	{Z6.D}, P0/Z, [X17, X16,LSL #3]

(278) 0x4157ac FMLA	Z2.D, P0/M, Z6.D, Z4.D

(278) 0x4157b0 LD1D	{Z7.D}, P0/Z, [X18, X16,LSL #3]

(278) 0x4157b4 FMLA	Z3.D, P0/M, Z7.D, Z5.D

(278) 0x4157b8 ADD	X16, X16, X8

(278) 0x4157bc CMP	X13, X16

(278) 0x4157c0 B.NE	4157a0

0x4157c4 FADD	Z2.D, Z3.D, Z2.D

0x4157c8 FADDV	D2, P0, Z2.D

0x4157cc CBZ	X15, 4157f8

0x4157d0 UBFM	X16, X13, #61, #60

0x4157d4 SUB	X15, X9, X13

0x4157d8 ADD	X13, X16, X14,LSL #3

0x4157dc ADD	X16, X23, X16

0x4157e0 ADD	X13, X12, X13

(281) 0x4157e4 LDR	D3, [X16], #8

(281) 0x4157e8 LDR	D4, [X13], #8

(281) 0x4157ec FMADD	D2, D4, D3, D2

(281) 0x4157f0 SUBS	X15, X15, #1

(281) 0x4157f4 B.NE	4157e4

0x4157f8 CMP	X8, X9

0x4157fc STR	D2, [X20, #200]

0x415800 B.LS	415810

0x415804 ORR	X11, XZR, XZR

0x415808 MOVI	D2, #0

0x41580c B	415870

0x415810 ADD	X16, X12, X14,LSL #4

0x415814 DUP	Z2.D, #0

0x415818 ORR	X15, XZR, XZR

0x41581c ORR	Z3.D, Z2.D, Z2.D

0x415820 UMSUBL	X13, W11, W8, X9

0x415824 UMADDL	X11, W11, W8, XZR

0x415828 ADDVL	X17, X16, #1

0x41582c PTRUE	P0.D, ALL

0x415830 HINT	#0

0x415834 HINT	#0

0x415838 HINT	#0

0x41583c HINT	#0

(279) 0x415840 LD1D	{Z4.D}, P0/Z, [X23, X15,LSL #3]

(279) 0x415844 LD1D	{Z5.D}, P0/Z, [X10, X15,LSL #3]

(279) 0x415848 LD1D	{Z6.D}, P0/Z, [X16, X15,LSL #3]

(279) 0x41584c FMLA	Z2.D, P0/M, Z6.D, Z4.D

(279) 0x415850 LD1D	{Z7.D}, P0/Z, [X17, X15,LSL #3]

(279) 0x415854 FMLA	Z3.D, P0/M, Z7.D, Z5.D

(279) 0x415858 ADD	X15, X15, X8

(279) 0x41585c CMP	X11, X15

(279) 0x415860 B.NE	415840

0x415864 FADD	Z2.D, Z3.D, Z2.D

0x415868 FADDV	D2, P0, Z2.D

0x41586c CBZ	X13, 415898

0x415870 UBFM	X13, X11, #61, #60

0x415874 SUB	X10, X9, X11

0x415878 ADD	X11, X13, X14,LSL #4

0x41587c ADD	X11, X12, X11

0x415880 ADD	X12, X23, X13

(280) 0x415884 LDR	D3, [X12], #8

(280) 0x415888 LDR	D4, [X11], #8

(280) 0x41588c FMADD	D2, D4, D3, D2

(280) 0x415890 SUBS	X10, X10, #1

(280) 0x415894 B.NE	415884

0x415898 STR	D2, [X20, #208]

0x41589c STR	D0, [X20, #184]

0x4158a0 CBZ	W9, 415628

0x4158a4 SBFM	X9, X9, #0, #31

0x4158a8 LDR	X10, [X20, #256]

0x4158ac MOVI	D0, #0

0x4158b0 SUB	X11, X9, #1

0x4158b4 AND	X11, X11, #7936

0x4158b8 ADD	X11, X11, #1

0x4158bc CMP	X11, X8

0x4158c0 B.CS	4158cc

0x4158c4 ORR	X11, XZR, X10

0x4158c8 B	415928

0x4158cc UDIV	X12, X11, X8

0x4158d0 DUP	Z0.D, #0

0x4158d4 ORR	X13, XZR, XZR

0x4158d8 ADDVL	X15, X10, #1

0x4158dc PTRUE	P0.D, ALL

0x4158e0 ORR	Z2.D, Z0.D, Z0.D

0x4158e4 MADD	X14, X12, X8, XZR

0x4158e8 SUB	X12, X11, X14

0x4158ec ADD	X11, X10, X14,LSL #3

0x4158f0 HINT	#0

0x4158f4 HINT	#0

0x4158f8 HINT	#0

0x4158fc HINT	#0

(274) 0x415900 LD1D	{Z3.D}, P0/Z, [X10, X13,LSL #3]

(274) 0x415904 LD1D	{Z4.D}, P0/Z, [X15, X13,LSL #3]

(274) 0x415908 ADD	X13, X13, X8

(274) 0x41590c CMP	X14, X13

(274) 0x415910 FADD	Z0.D, Z3.D, Z0.D

(274) 0x415914 FADD	Z2.D, Z4.D, Z2.D

(274) 0x415918 B.NE	415900

0x41591c FADD	Z0.D, Z2.D, Z0.D

0x415920 FADDV	D0, P0, Z0.D

0x415924 CBZ	X12, 41593c

0x415928 ADD	X8, X10, X9,LSL #3

(275) 0x41592c LDR	D2, [X11], #8

(275) 0x415930 FADD	D0, D2, D0

(275) 0x415934 CMP	X11, X8

(275) 0x415938 B.NE	41592c

0x41593c STR	D0, [X20, #176]

0x415940 LDR	X8, [X20, #240]

0x415944 LDP	D0, D2, [X21]

0x415948 FADD	D0, D0, D1

0x41594c LDR	D1, [X21, #16]

0x415950 STR	D0, [X21]

0x415954 LDR	D0, [X20, #200]

0x415958 FADD	D0, D2, D0

0x41595c STR	D0, [X21, #8]

0x415960 LDR	D0, [X20, #208]

0x415964 FADD	D0, D1, D0

0x415968 STR	D0, [X21, #16]

0x41596c LDR	D0, [X8, X19,SXTW #3]

0x415970 LDR	D1, [X20, #176]

0x415974 FSUB	D0, D0, S1

0x415978 LDP	X20, X19, [SP, #48]

0x41597c LDP	X22, X21, [SP, #32]

0x415980 LDP	X24, X23, [SP, #16]

0x415984 LDP	X29, X30, [SP], #64

0x415988 B	404a20

0x41598c HINT	#0

0x415990 HINT	#0

0x415994 HINT	#0

0x415998 HINT	#0

0x41599c HINT	#0

Coverage (%)	Name	Source Location	Module

Path /

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

Source file and lines	OneBodyJastrowRef.h:186-263
Module	exec

The function is defined in:

/usr/lib/gcc/aarch64-linux-gnu/12/../../../../include/c++/12/bits/stl_vector.h:1256
/home/hbollore/qaas-runs/171-284-6744/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186-194,256-263
/usr/lib/gcc/aarch64-linux-gnu/12/../../../../include/c++/12/bits/stl_numeric.h:140-141
/home/hbollore/qaas-runs/171-284-6744/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/hbollore/qaas-runs/171-284-6744/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 40.00 to 15.00 cycles (2.67x speedup).

Workaround

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

Vectorization

Your function is not vectorized. Only 39% of vector register length is used (average across all VPU instructions). By fully vectorizing your function, you can lower the cost of an iteration from 40.00 to 20.00 cycles (2.00x speedup).

Details

16% of VPU instructions are used in vector version (process two or more data elements in vector registers):

16% of VPU loads are used in vector version.
0% of VPU stores are used in vector version.
28% of VPU addition or subtraction instructions are used in vector version.
0% of VPU fused multiply-add instructions are used in vector version.
0% of VPU divide and square root instructions are used in vector version.
13% 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 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 40.00 to 1.50 cycles (26.67x speedup).

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

The binary function is composed of 44 FP arithmetical operations:

44: addition or subtraction

The binary function is loading 188 bytes. The binary function is storing 164 bytes.

Arithmetic intensity

Arithmetic intensity is 0.12 FP operations per loaded or stored byte.

General properties

nb instructions	193
loop length	772
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

21.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	11.50	11.50	19.75	19.75	23.00	19.50	15.00	15.00	8.50	8.50	12.00	12.00	12.00	3.50	3.50
cycles	11.50	11.50	19.75	19.75	23.00	19.50	15.00	15.00	8.50	8.50	12.00	12.00	12.00	3.50	3.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

10.00-40.00

Cycles summary

Front-end	21.25
Overall L1	23.00-40.00

Vectorization ratios

INT

all	7%
load	16%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	0%
other	13%

all	90%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	16%
load	16%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	28%
fma	0%
div/sqrt	0%
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 40.00 cycles. At this rate:

4% of peak load performance is reached (4.70 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.10 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 415580

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
STP X29, X30, [SP, #960]!	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X24, X23, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X22, X21, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X20, X19, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ADD X29, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X22, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR W1, [X0, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
MOVZ W8, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X20, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STR W8, [X0, #12]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X21, XZR, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR W19, WZR, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 44a070 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR X3, [X0, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ORR X0, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X1, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR W2, WZR, W19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 4177e0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W1, [X20, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X23, [X20, #280]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X24, [X20, #304]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 44a070 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W9, [X20, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CNTW X8, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADD X13, X20, #192	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP W9, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LT 415610 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x90>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UDIV X11, X9, X8	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	5-20
ADDVL X10, X23, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
CMP X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LS 415630 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xb0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X12, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVI D0, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
B 415698 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x118>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOVI D1, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
MOVI D0, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
STP XZR, XZR, [X13]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR XZR, [X13, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D0, [X20, #184]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
CBNZ W9, 4158a4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x324>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOVI D0, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
B 41593c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3bc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
DUP Z0.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR X15, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
UMSUBL X14, W11, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
FDUP Z1.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR Z2.D, Z0.D, Z0.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
UMADDL X12, W11, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X16, X24, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
HINT #0
HINT #0
HINT #0
HINT #0
FADD Z0.D, Z2.D, Z0.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FADDV D0, P0, Z0.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2
CBZ X14, 4156c4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x144>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X15, X12, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X14, X9, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X12, X23, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X15, X24, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X12, [X0, #184]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LS 4156dc <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x15c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X14, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVI D1, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
B 415730 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1b0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
DUP Z1.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR X16, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
UMSUBL X15, W11, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ORR Z2.D, Z1.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
UMADDL X14, W11, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X17, X12, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
HINT #0
HINT #0
FADD Z1.D, Z2.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FADDV D1, P0, Z1.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2
CBZ X15, 415754 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1d4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X16, X14, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X15, X9, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X14, X12, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X16, X23, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X14, [X0, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
STR D1, [X13]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
B.LS 415770 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X13, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVI D2, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
B 4157d0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x250>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X17, X12, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
DUP Z2.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR X16, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR Z3.D, Z2.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
UMSUBL X15, W11, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
UMADDL X13, W11, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X18, X17, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
HINT #0
HINT #0
HINT #0
HINT #0
FADD Z2.D, Z3.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FADDV D2, P0, Z2.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2
CBZ X15, 4157f8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x278>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X16, X13, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X15, X9, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X13, X16, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X16, X23, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X13, X12, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
STR D2, [X20, #200]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
B.LS 415810 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x290>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X11, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVI D2, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
B 415870 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X16, X12, X14,LSL #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
DUP Z2.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR X15, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR Z3.D, Z2.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
UMSUBL X13, W11, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
UMADDL X11, W11, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X17, X16, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
HINT #0
HINT #0
HINT #0
HINT #0
FADD Z2.D, Z3.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FADDV D2, P0, Z2.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2
CBZ X13, 415898 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x318>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X13, X11, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X10, X9, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X11, X13, X14,LSL #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X11, X12, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X12, X23, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STR D2, [X20, #208]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
STR D0, [X20, #184]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
CBZ W9, 415628 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xa8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X9, X9, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X10, [X20, #256]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
MOVI D0, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
SUB X11, X9, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
AND X11, X11, #7936	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X11, X11, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X11, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.CS 4158cc <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x34c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X11, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
B 415928 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UDIV X12, X11, X8	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	5-20
DUP Z0.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR X13, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADDVL X15, X10, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ORR Z2.D, Z0.D, Z0.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
MADD X14, X12, X8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
SUB X12, X11, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X11, X10, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
HINT #0
HINT #0
HINT #0
HINT #0
FADD Z0.D, Z2.D, Z0.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FADDV D0, P0, Z0.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2
CBZ X12, 41593c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3bc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X8, X10, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STR D0, [X20, #176]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
LDR X8, [X20, #240]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDP D0, D2, [X21]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FADD D0, D0, D1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
LDR D1, [X21, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
STR D0, [X21]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
LDR D0, [X20, #200]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FADD D0, D2, D0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
STR D0, [X21, #8]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
LDR D0, [X20, #208]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FADD D0, D1, D0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
STR D0, [X21, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
LDR D0, [X8, X19,SXTW #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDR D1, [X20, #176]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FSUB D0, D0, S1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
LDP X20, X19, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X22, X21, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X24, X23, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X29, X30, [SP], #64	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
B 404a20 <@plt_start@+0x430>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
HINT #0
HINT #0
HINT #0
HINT #0
HINT #0

Source file and lines	OneBodyJastrowRef.h:186-263
Module	exec

The function is defined in:

/usr/lib/gcc/aarch64-linux-gnu/12/../../../../include/c++/12/bits/stl_vector.h:1256
/home/hbollore/qaas-runs/171-284-6744/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186-194,256-263
/usr/lib/gcc/aarch64-linux-gnu/12/../../../../include/c++/12/bits/stl_numeric.h:140-141
/home/hbollore/qaas-runs/171-284-6744/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/hbollore/qaas-runs/171-284-6744/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249

Warnings:
Ignoring paths for analysis

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

16% of VPU instructions are used in vector version (process two or more data elements in vector registers):

16% of VPU loads are used in vector version.
0% of VPU stores are used in vector version.
28% of VPU addition or subtraction instructions are used in vector version.
0% of VPU fused multiply-add instructions are used in vector version.
0% of VPU divide and square root instructions are used in vector version.
13% 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 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 40.00 to 1.50 cycles (26.67x speedup).

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

The binary function is composed of 44 FP arithmetical operations:

44: addition or subtraction

The binary function is loading 188 bytes. The binary function is storing 164 bytes.

Arithmetic intensity

Arithmetic intensity is 0.12 FP operations per loaded or stored byte.

General properties

nb instructions	193
loop length	772
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

21.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	11.50	11.50	19.75	19.75	23.00	19.50	15.00	15.00	8.50	8.50	12.00	12.00	12.00	3.50	3.50
cycles	11.50	11.50	19.75	19.75	23.00	19.50	15.00	15.00	8.50	8.50	12.00	12.00	12.00	3.50	3.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

10.00-40.00

Cycles summary

Front-end	21.25
Overall L1	23.00-40.00

Vectorization ratios

INT

all	7%
load	16%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	0%
other	13%

all	90%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	16%
load	16%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	28%
fma	0%
div/sqrt	0%
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 40.00 cycles. At this rate:

4% of peak load performance is reached (4.70 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.10 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 415580

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
STP X29, X30, [SP, #960]!	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X24, X23, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X22, X21, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X20, X19, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ADD X29, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X22, XZR, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR W1, [X0, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
MOVZ W8, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X20, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STR W8, [X0, #12]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ORR X21, XZR, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR W19, WZR, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 44a070 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR X3, [X0, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ORR X0, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X1, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR W2, WZR, W19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 4177e0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W1, [X20, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X23, [X20, #280]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X24, [X20, #304]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 44a070 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W9, [X20, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CNTW X8, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADD X13, X20, #192	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP W9, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LT 415610 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x90>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UDIV X11, X9, X8	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	5-20
ADDVL X10, X23, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
CMP X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LS 415630 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xb0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X12, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVI D0, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
B 415698 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x118>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOVI D1, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
MOVI D0, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
STP XZR, XZR, [X13]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR XZR, [X13, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D0, [X20, #184]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
CBNZ W9, 4158a4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x324>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOVI D0, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
B 41593c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3bc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
DUP Z0.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR X15, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
UMSUBL X14, W11, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
FDUP Z1.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR Z2.D, Z0.D, Z0.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
UMADDL X12, W11, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X16, X24, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
HINT #0
HINT #0
HINT #0
HINT #0
FADD Z0.D, Z2.D, Z0.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FADDV D0, P0, Z0.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2
CBZ X14, 4156c4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x144>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X15, X12, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X14, X9, X12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X12, X23, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X15, X24, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X12, [X0, #184]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LS 4156dc <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x15c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X14, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVI D1, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
B 415730 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1b0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
DUP Z1.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR X16, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
UMSUBL X15, W11, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ORR Z2.D, Z1.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
UMADDL X14, W11, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X17, X12, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
HINT #0
HINT #0
FADD Z1.D, Z2.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FADDV D1, P0, Z1.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2
CBZ X15, 415754 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1d4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X16, X14, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X15, X9, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X14, X12, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X16, X23, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X14, [X0, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
STR D1, [X13]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
B.LS 415770 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X13, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVI D2, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
B 4157d0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x250>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X17, X12, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
DUP Z2.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR X16, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR Z3.D, Z2.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
UMSUBL X15, W11, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
UMADDL X13, W11, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X18, X17, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
HINT #0
HINT #0
HINT #0
HINT #0
FADD Z2.D, Z3.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FADDV D2, P0, Z2.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2
CBZ X15, 4157f8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x278>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X16, X13, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X15, X9, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X13, X16, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X16, X23, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X13, X12, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
STR D2, [X20, #200]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
B.LS 415810 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x290>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X11, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVI D2, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
B 415870 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X16, X12, X14,LSL #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
DUP Z2.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR X15, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR Z3.D, Z2.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
UMSUBL X13, W11, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
UMADDL X11, W11, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X17, X16, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
HINT #0
HINT #0
HINT #0
HINT #0
FADD Z2.D, Z3.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FADDV D2, P0, Z2.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2
CBZ X13, 415898 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x318>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X13, X11, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X10, X9, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X11, X13, X14,LSL #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X11, X12, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X12, X23, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STR D2, [X20, #208]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
STR D0, [X20, #184]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
CBZ W9, 415628 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xa8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X9, X9, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X10, [X20, #256]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
MOVI D0, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
SUB X11, X9, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
AND X11, X11, #7936	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X11, X11, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X11, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.CS 4158cc <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x34c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X11, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
B 415928 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UDIV X12, X11, X8	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	5-20
DUP Z0.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
ORR X13, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADDVL X15, X10, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ORR Z2.D, Z0.D, Z0.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
MADD X14, X12, X8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
SUB X12, X11, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X11, X10, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
HINT #0
HINT #0
HINT #0
HINT #0
FADD Z0.D, Z2.D, Z0.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50
FADDV D0, P0, Z0.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2
CBZ X12, 41593c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3bc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X8, X10, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STR D0, [X20, #176]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
LDR X8, [X20, #240]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDP D0, D2, [X21]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FADD D0, D0, D1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
LDR D1, [X21, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
STR D0, [X21]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
LDR D0, [X20, #200]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FADD D0, D2, D0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
STR D0, [X21, #8]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
LDR D0, [X20, #208]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FADD D0, D1, D0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
STR D0, [X21, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
LDR D0, [X8, X19,SXTW #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
LDR D1, [X20, #176]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FSUB D0, D0, S1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25
LDP X20, X19, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X22, X21, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X24, X23, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X29, X30, [SP], #64	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
B 404a20 <@plt_start@+0x430>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
HINT #0
HINT #0
HINT #0
HINT #0
HINT #0

Name	Coverage (%)	Time (s)
▼miniqmcreference::OneBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)–	0.07	0.11
○Loop 278 - OneBodyJastrowRef.h:192-193 - exec	0.02	0.02
○Loop 277 - OneBodyJastrowRef.h:192-193 - exec	0.02	0.03
○Loop 279 - OneBodyJastrowRef.h:192-193 - exec	0.01	0.02
○Loop 274 - stl_numeric.h:141-141 - exec	0	0.01
○Loop 283 - OneBodyJastrowRef.h:186-187 - exec	0	0
○Loop 281 - OneBodyJastrowRef.h:192-193 - exec	0	0
○Loop 282 - OneBodyJastrowRef.h:192-193 - exec	0	0
○Loop 280 - OneBodyJastrowRef.h:192-193 - exec	0	0
○Loop 275 - stl_numeric.h:140-141 - exec	0	0
○Loop 276 - OneBodyJastrowRef.h:186-187 - exec	0	0.01

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code