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:190-267 [...]	Coverage: 0.04%

/usr/lib/gcc/aarch64-linux-gnu/11/../../../../include/c++/11/bits/stl_numeric.h: 140 - 141

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

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

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

/usr/lib/gcc/aarch64-linux-gnu/11/../../../../include/c++/11/bits/stl_vector.h: 1046 - 1169

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

1046: 	return *(this->_M_impl._M_start + __n);

[...]

1169:       { return _M_data_ptr(this->_M_impl._M_start); }

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 94

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

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

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 190 - 267

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

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

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

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

193:     {

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

195:       valT s                  = valT();

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

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

198:       grad[idim] = s;

[...]

260:   {

261:     UpdateMode = ORB_PBYP_PARTIAL;

262:

263:     computeU3(P, iat, P.DistTables[myTableID]->Temp_r.data());

264:     curLap = accumulateGL(dU.data(), d2U.data(), P.DistTables[myTableID]->Temp_dr, curGrad);

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

266:     grad_iat += curGrad;

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

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 223

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

223:     return X[i];

0x414280 STP	X29, X30, [SP, #976]!

0x414284 STP	X22, X21, [SP, #16]

0x414288 STP	X20, X19, [SP, #32]

0x41428c ADD	X29, SP, #0

0x414290 MOVZ	W8, #2

0x414294 LDR	X9, [X1, #2576]

0x414298 ORR	X21, XZR, X3

0x41429c ORR	W19, WZR, W2

0x4142a0 STR	W8, [X0, #12]

0x4142a4 LDRSW	X8, [X0, #144]

0x4142a8 ORR	X22, XZR, X1

0x4142ac ORR	X20, XZR, X0

0x4142b0 LDR	X8, [X9, X8,LSL #3]

0x4142b4 LDR	X3, [X8, #104]

0x4142b8 BL	4165a0

0x4142bc LDR	W9, [X20, #148]

0x4142c0 CNTW	X8, ALL

0x4142c4 ADD	X14, X20, #184

0x4142c8 CMP	W9, #1

0x4142cc B.LT	414300

0x4142d0 LDRSW	X11, [X20, #144]

0x4142d4 LDR	X12, [X22, #2576]

0x4142d8 LDR	X10, [X20, #272]

0x4142dc CMP	X8, X9

0x4142e0 LDR	X13, [X20, #296]

0x4142e4 LDR	X15, [X12, X11,LSL #3]

0x4142e8 UDIV	X12, X9, X8

0x4142ec ADDVL	X11, X10, #1

0x4142f0 B.LS	414320

0x4142f4 ORR	X16, XZR, XZR

0x4142f8 MOVI	D0, #0

0x4142fc B	414378

0x414300 MOVI	D1, #0

0x414304 MOVI	D0, #0

0x414308 STP	XZR, XZR, [X14]

0x41430c STR	XZR, [X14, #16]

0x414310 STR	D0, [X20, #176]

0x414314 CBNZ	W9, 414584

0x414318 MOVI	D0, #0

0x41431c B	41461c

0x414320 DUP	Z0.D, #0

0x414324 ORR	X18, XZR, XZR

0x414328 UMSUBL	X17, W12, W8, X9

0x41432c FDUP	Z1.D, #0

0x414330 ORR	Z2.D, Z0.D, Z0.D

0x414334 UMADDL	X16, W12, W8, XZR

0x414338 ADDVL	X0, X13, #1

0x41433c PTRUE	P0.D, ALL

(257) 0x414340 LD1D	{Z3.D}, P0/Z, [X13, X18,LSL #3]

(257) 0x414344 LD1D	{Z4.D}, P0/Z, [X0, X18,LSL #3]

(257) 0x414348 FADD	Z0.D, Z3.D, Z0.D

(257) 0x41434c LD1D	{Z5.D}, P0/Z, [X10, X18,LSL #3]

(257) 0x414350 LD1D	{Z6.D}, P0/Z, [X11, X18,LSL #3]

(257) 0x414354 FADD	Z2.D, Z4.D, Z2.D

(257) 0x414358 ADD	X18, X18, X8

(257) 0x41435c CMP	X16, X18

(257) 0x414360 FMLA	Z0.D, P0/M, Z5.D, Z1.D

(257) 0x414364 FMLA	Z2.D, P0/M, Z6.D, Z1.D

(257) 0x414368 B.NE	414340

0x41436c FADD	Z0.D, Z2.D, Z0.D

0x414370 FADDV	D0, P0, Z0.D

0x414374 CBZ	X17, 4143a4

0x414378 UBFM	X18, X16, #61, #60

0x41437c SUB	X17, X9, X16

0x414380 ADD	X16, X10, X18

0x414384 ADD	X13, X13, X18

(264) 0x414388 LDR	D1, [X13], #8

(264) 0x41438c LDR	D2, [X16], #8

(264) 0x414390 FADD	D2, D2, D2

(264) 0x414394 FADD	D0, D1, D0

(264) 0x414398 SUBS	X17, X17, #1

(264) 0x41439c FADD	D0, D0, D2

(264) 0x4143a0 B.NE	414388

0x4143a4 LDR	X13, [X15, #152]

0x4143a8 CMP	X8, X9

0x4143ac B.LS	4143bc

0x4143b0 ORR	X16, XZR, XZR

0x4143b4 MOVI	D1, #0

0x4143b8 B	414410

0x4143bc DUP	Z1.D, #0

0x4143c0 ORR	X18, XZR, XZR

0x4143c4 UMSUBL	X17, W12, W8, X9

0x4143c8 ORR	Z2.D, Z1.D, Z1.D

0x4143cc UMADDL	X16, W12, W8, XZR

0x4143d0 ADDVL	X0, X13, #1

0x4143d4 PTRUE	P0.D, ALL

0x4143d8 HINT	#0

0x4143dc HINT	#0

(258) 0x4143e0 LD1D	{Z3.D}, P0/Z, [X10, X18,LSL #3]

(258) 0x4143e4 LD1D	{Z4.D}, P0/Z, [X11, X18,LSL #3]

(258) 0x4143e8 LD1D	{Z5.D}, P0/Z, [X13, X18,LSL #3]

(258) 0x4143ec FMLA	Z1.D, P0/M, Z5.D, Z3.D

(258) 0x4143f0 LD1D	{Z6.D}, P0/Z, [X0, X18,LSL #3]

(258) 0x4143f4 FMLA	Z2.D, P0/M, Z6.D, Z4.D

(258) 0x4143f8 ADD	X18, X18, X8

(258) 0x4143fc CMP	X16, X18

(258) 0x414400 B.NE	4143e0

0x414404 FADD	Z1.D, Z2.D, Z1.D

0x414408 FADDV	D1, P0, Z1.D

0x41440c CBZ	X17, 414434

0x414410 UBFM	X18, X16, #61, #60

0x414414 SUB	X17, X9, X16

0x414418 ADD	X16, X13, X18

0x41441c ADD	X18, X10, X18

(263) 0x414420 LDR	D2, [X18], #8

(263) 0x414424 LDR	D3, [X16], #8

(263) 0x414428 FMADD	D1, D3, D2, D1

(263) 0x41442c SUBS	X17, X17, #1

(263) 0x414430 B.NE	414420

0x414434 LDR	X15, [X15, #136]

0x414438 CMP	X8, X9

0x41443c STR	D1, [X14]

0x414440 B.LS	414450

0x414444 ORR	X14, XZR, XZR

0x414448 MOVI	D2, #0

0x41444c B	4144b0

0x414450 ADD	X18, X13, X15,LSL #3

0x414454 DUP	Z2.D, #0

0x414458 ORR	X17, XZR, XZR

0x41445c ORR	Z3.D, Z2.D, Z2.D

0x414460 UMSUBL	X16, W12, W8, X9

0x414464 UMADDL	X14, W12, W8, XZR

0x414468 ADDVL	X0, X18, #1

0x41446c PTRUE	P0.D, ALL

0x414470 HINT	#0

0x414474 HINT	#0

0x414478 HINT	#0

0x41447c HINT	#0

(259) 0x414480 LD1D	{Z4.D}, P0/Z, [X10, X17,LSL #3]

(259) 0x414484 LD1D	{Z5.D}, P0/Z, [X11, X17,LSL #3]

(259) 0x414488 LD1D	{Z6.D}, P0/Z, [X18, X17,LSL #3]

(259) 0x41448c FMLA	Z2.D, P0/M, Z6.D, Z4.D

(259) 0x414490 LD1D	{Z7.D}, P0/Z, [X0, X17,LSL #3]

(259) 0x414494 FMLA	Z3.D, P0/M, Z7.D, Z5.D

(259) 0x414498 ADD	X17, X17, X8

(259) 0x41449c CMP	X14, X17

(259) 0x4144a0 B.NE	414480

0x4144a4 FADD	Z2.D, Z3.D, Z2.D

0x4144a8 FADDV	D2, P0, Z2.D

0x4144ac CBZ	X16, 4144d8

0x4144b0 UBFM	X17, X14, #61, #60

0x4144b4 SUB	X16, X9, X14

0x4144b8 ADD	X14, X17, X15,LSL #3

0x4144bc ADD	X17, X10, X17

0x4144c0 ADD	X14, X13, X14

(262) 0x4144c4 LDR	D3, [X17], #8

(262) 0x4144c8 LDR	D4, [X14], #8

(262) 0x4144cc FMADD	D2, D4, D3, D2

(262) 0x4144d0 SUBS	X16, X16, #1

(262) 0x4144d4 B.NE	4144c4

0x4144d8 CMP	X8, X9

0x4144dc STR	D2, [X20, #192]

0x4144e0 B.LS	4144f0

0x4144e4 ORR	X12, XZR, XZR

0x4144e8 MOVI	D2, #0

0x4144ec B	414550

0x4144f0 ADD	X17, X13, X15,LSL #4

0x4144f4 DUP	Z2.D, #0

0x4144f8 ORR	X16, XZR, XZR

0x4144fc ORR	Z3.D, Z2.D, Z2.D

0x414500 UMSUBL	X14, W12, W8, X9

0x414504 UMADDL	X12, W12, W8, XZR

0x414508 ADDVL	X18, X17, #1

0x41450c PTRUE	P0.D, ALL

0x414510 HINT	#0

0x414514 HINT	#0

0x414518 HINT	#0

0x41451c HINT	#0

(260) 0x414520 LD1D	{Z4.D}, P0/Z, [X10, X16,LSL #3]

(260) 0x414524 LD1D	{Z5.D}, P0/Z, [X11, X16,LSL #3]

(260) 0x414528 LD1D	{Z6.D}, P0/Z, [X17, X16,LSL #3]

(260) 0x41452c FMLA	Z2.D, P0/M, Z6.D, Z4.D

(260) 0x414530 LD1D	{Z7.D}, P0/Z, [X18, X16,LSL #3]

(260) 0x414534 FMLA	Z3.D, P0/M, Z7.D, Z5.D

(260) 0x414538 ADD	X16, X16, X8

(260) 0x41453c CMP	X12, X16

(260) 0x414540 B.NE	414520

0x414544 FADD	Z2.D, Z3.D, Z2.D

0x414548 FADDV	D2, P0, Z2.D

0x41454c CBZ	X14, 414578

0x414550 UBFM	X14, X12, #61, #60

0x414554 SUB	X11, X9, X12

0x414558 ADD	X12, X14, X15,LSL #4

0x41455c ADD	X10, X10, X14

0x414560 ADD	X12, X13, X12

(261) 0x414564 LDR	D3, [X10], #8

(261) 0x414568 LDR	D4, [X12], #8

(261) 0x41456c FMADD	D2, D4, D3, D2

(261) 0x414570 SUBS	X11, X11, #1

(261) 0x414574 B.NE	414564

0x414578 STR	D2, [X20, #200]

0x41457c STR	D0, [X20, #176]

0x414580 CBZ	W9, 414318

0x414584 SBFM	X9, X9, #0, #31

0x414588 LDR	X10, [X20, #248]

0x41458c MOVI	D0, #0

0x414590 SUB	X11, X9, #1

0x414594 AND	X11, X11, #7936

0x414598 ADD	X11, X11, #1

0x41459c CMP	X11, X8

0x4145a0 B.CS	4145ac

0x4145a4 ORR	X11, XZR, X10

0x4145a8 B	414608

0x4145ac UDIV	X12, X11, X8

0x4145b0 DUP	Z0.D, #0

0x4145b4 ORR	X13, XZR, XZR

0x4145b8 ADDVL	X15, X10, #1

0x4145bc PTRUE	P0.D, ALL

0x4145c0 ORR	Z2.D, Z0.D, Z0.D

0x4145c4 MADD	X14, X12, X8, XZR

0x4145c8 SUB	X12, X11, X14

0x4145cc ADD	X11, X10, X14,LSL #3

0x4145d0 HINT	#0

0x4145d4 HINT	#0

0x4145d8 HINT	#0

0x4145dc HINT	#0

(255) 0x4145e0 LD1D	{Z3.D}, P0/Z, [X10, X13,LSL #3]

(255) 0x4145e4 LD1D	{Z4.D}, P0/Z, [X15, X13,LSL #3]

(255) 0x4145e8 ADD	X13, X13, X8

(255) 0x4145ec CMP	X14, X13

(255) 0x4145f0 FADD	Z0.D, Z3.D, Z0.D

(255) 0x4145f4 FADD	Z2.D, Z4.D, Z2.D

(255) 0x4145f8 B.NE	4145e0

0x4145fc FADD	Z0.D, Z2.D, Z0.D

0x414600 FADDV	D0, P0, Z0.D

0x414604 CBZ	X12, 41461c

0x414608 ADD	X8, X10, X9,LSL #3

(256) 0x41460c LDR	D2, [X11], #8

(256) 0x414610 FADD	D0, D2, D0

(256) 0x414614 CMP	X11, X8

(256) 0x414618 B.NE	41460c

0x41461c STR	D0, [X20, #168]

0x414620 LDR	X8, [X20, #232]

0x414624 LDP	D0, D2, [X21]

0x414628 FADD	D0, D0, D1

0x41462c LDR	D1, [X21, #16]

0x414630 STR	D0, [X21]

0x414634 LDR	D0, [X20, #192]

0x414638 FADD	D0, D2, D0

0x41463c STR	D0, [X21, #8]

0x414640 LDR	D0, [X20, #200]

0x414644 FADD	D0, D1, D0

0x414648 STR	D0, [X21, #16]

0x41464c LDR	D0, [X8, X19,SXTW #3]

0x414650 LDR	D1, [X20, #168]

0x414654 FSUB	D0, D0, S1

0x414658 LDP	X20, X19, [SP, #32]

0x41465c LDP	X22, X21, [SP, #16]

0x414660 LDP	X29, X30, [SP], #48

0x414664 B	403e50

0x414668 HINT	#0

0x41466c HINT	#0

0x414670 HINT	#0

0x414674 HINT	#0

0x414678 HINT	#0

0x41467c HINT	#0

Coverage (%)	Name	Source Location	Module
►100.00+	qmcplusplus::WaveFunction::rat[...]	NewTimer.h:249	exec
○	.omp_outlined..62	miniqmc.cpp:437	exec
○	__kmp_invoke_microtask		libomp.so

Path /

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

Source file and lines	OneBodyJastrowRef.h:190-267
Module	exec

The function is defined in:

/usr/lib/gcc/aarch64-linux-gnu/11/../../../../include/c++/11/bits/stl_numeric.h:140-141
/usr/lib/gcc/aarch64-linux-gnu/11/../../../../include/c++/11/bits/stl_vector.h:1046,1169
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:190-198,260-267
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223

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 23.00 to 15.00 cycles (1.53x speedup).

Workaround

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

Vectorization

Your function is poorly vectorized. Only 43% 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 23.00 to 18.50 cycles (1.24x speedup).

Details

21% 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.
43% of VPU addition or subtraction instructions are used in vector version.
0% of VPU fused multiply-add instructions are used in vector version.
16% 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 23.00 to 0.50 cycles (46.00x 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 204 bytes. The binary function is storing 148 bytes.

Arithmetic intensity

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

General properties

nb instructions	185
loop length	740
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

20.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	10.50	10.50	17.50	17.25	23.00	17.25	15.00	15.00	8.50	8.50	12.83	12.50	12.67	3.00	3.00
cycles	10.50	10.50	17.50	17.25	23.00	17.25	15.00	15.00	8.50	8.50	12.83	12.50	12.67	3.00	3.00

Cycles executing div or sqrt instructions

2.00-1.00

Cycles summary

Front-end	20.63
Overall L1	23.00

Vectorization ratios

INT

all	9%
load	16%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	0%
other	16%

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	21%
load	16%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	43%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 23.00 cycles. At this rate:

9% of peak load performance is reached (8.87 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
13% of peak store performance is reached (6.43 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 414280

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, #976]!	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 X22, X21, [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 X20, X19, [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
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
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
LDR X9, [X1, #2576]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
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
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
LDRSW X8, [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 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
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
LDR X8, [X9, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X3, [X8, #104]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
BL 4165a0 <_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 W9, [X20, #148]	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 X14, X20, #184	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 414300 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x80>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDRSW X11, [X20, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X12, [X22, #2576]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X10, [X20, #272]	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
LDR X13, [X20, #296]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X15, [X12, X11,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
UDIV X12, X9, X8	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	1-0.50
ADDVL X11, X10, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
B.LS 414320 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xa0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	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
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 414378 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xf8>	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, [X14]	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, [X14, #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, #176]	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, 414584 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x304>	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 41461c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x39c>	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 X18, 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 X17, W12, 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 X16, W12, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X0, X13, #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
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 X17, 4143a4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x124>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X18, X16, #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 X17, X9, 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, X10, X18	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, X13, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X13, [X15, #152]	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 4143bc <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	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
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 414410 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x190>	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 X18, 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 X17, W12, 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 X16, W12, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X0, X13, #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 X17, 414434 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1b4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X18, X16, #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 X17, X9, 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, X13, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X18, X10, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X15, [X15, #136]	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, [X14]	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 414450 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1d0>	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 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 4144b0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x230>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X18, X13, X15,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 X17, 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 X16, W12, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
UMADDL X14, W12, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X0, X18, #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 X16, 4144d8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x258>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X17, 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 X16, 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, X17, X15,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 X17, X10, X17	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, X13, X14	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, #192]	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 4144f0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x270>	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 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 414550 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X17, X13, X15,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 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 X14, W12, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
UMADDL X12, W12, 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 X14, 414578 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X14, 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 X11, 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, X14, X15,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 X10, X10, 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 X12, X13, X12	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, #200]	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, #176]	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, 414318 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x98>	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, #248]	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 4145ac <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x32c>	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 414608 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x388>	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	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 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, 41461c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x39c>	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, #168]	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, #232]	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, #192]	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, #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, 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, #168]	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, #32]	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, #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], #48	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
B 403e50 <@plt_start@+0x450>	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
HINT #0

Source file and lines	OneBodyJastrowRef.h:190-267
Module	exec

The function is defined in:

/usr/lib/gcc/aarch64-linux-gnu/11/../../../../include/c++/11/bits/stl_numeric.h:140-141
/usr/lib/gcc/aarch64-linux-gnu/11/../../../../include/c++/11/bits/stl_vector.h:1046,1169
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:190-198,260-267
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223

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

21% 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.
43% of VPU addition or subtraction instructions are used in vector version.
0% of VPU fused multiply-add instructions are used in vector version.
16% 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 23.00 to 0.50 cycles (46.00x 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 204 bytes. The binary function is storing 148 bytes.

Arithmetic intensity

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

General properties

nb instructions	185
loop length	740
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

20.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	10.50	10.50	17.50	17.25	23.00	17.25	15.00	15.00	8.50	8.50	12.83	12.50	12.67	3.00	3.00
cycles	10.50	10.50	17.50	17.25	23.00	17.25	15.00	15.00	8.50	8.50	12.83	12.50	12.67	3.00	3.00

Cycles executing div or sqrt instructions

2.00-1.00

Cycles summary

Front-end	20.63
Overall L1	23.00

Vectorization ratios

INT

all	9%
load	16%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	0%
other	16%

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	21%
load	16%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	43%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 23.00 cycles. At this rate:

9% of peak load performance is reached (8.87 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
13% of peak store performance is reached (6.43 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 414280

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, #976]!	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 X22, X21, [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 X20, X19, [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
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
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
LDR X9, [X1, #2576]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
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
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
LDRSW X8, [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 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
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
LDR X8, [X9, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X3, [X8, #104]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
BL 4165a0 <_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 W9, [X20, #148]	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 X14, X20, #184	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 414300 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x80>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDRSW X11, [X20, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X12, [X22, #2576]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X10, [X20, #272]	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
LDR X13, [X20, #296]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X15, [X12, X11,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
UDIV X12, X9, X8	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	1-0.50
ADDVL X11, X10, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
B.LS 414320 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xa0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	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
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 414378 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xf8>	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, [X14]	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, [X14, #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, #176]	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, 414584 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x304>	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 41461c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x39c>	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 X18, 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 X17, W12, 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 X16, W12, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X0, X13, #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
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 X17, 4143a4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x124>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X18, X16, #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 X17, X9, 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, X10, X18	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, X13, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X13, [X15, #152]	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 4143bc <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	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
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 414410 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x190>	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 X18, 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 X17, W12, 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 X16, W12, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X0, X13, #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 X17, 414434 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1b4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X18, X16, #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 X17, X9, 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, X13, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X18, X10, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X15, [X15, #136]	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, [X14]	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 414450 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1d0>	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 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 4144b0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x230>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X18, X13, X15,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 X17, 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 X16, W12, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
UMADDL X14, W12, W8, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADDVL X0, X18, #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 X16, 4144d8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x258>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X17, 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 X16, 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, X17, X15,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 X17, X10, X17	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, X13, X14	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, #192]	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 4144f0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x270>	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 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 414550 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X17, X13, X15,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 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 X14, W12, W8, X9	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
UMADDL X12, W12, 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 X14, 414578 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X14, 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 X11, 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, X14, X15,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 X10, X10, 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 X12, X13, X12	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, #200]	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, #176]	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, 414318 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x98>	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, #248]	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 4145ac <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x32c>	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 414608 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x388>	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	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 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, 41461c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x39c>	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, #168]	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, #232]	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, #192]	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, #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, 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, #168]	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, #32]	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, #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], #48	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
B 403e50 <@plt_start@+0x450>	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
HINT #0

Name	Coverage (%)	Time (s)
▼miniqmcreference::OneBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)–	0.04	0.02
○Loop 258 - OneBodyJastrowRef.h:196-197 - exec	0.01	0
○Loop 255 - stl_numeric.h:141-141 - exec	0.01	0
○Loop 257 - OneBodyJastrowRef.h:190-191 - exec	0.01	0
○Loop 259 - OneBodyJastrowRef.h:196-197 - exec	0	0
○Loop 256 - stl_numeric.h:140-141 - exec	0	0
○Loop 261 - OneBodyJastrowRef.h:196-197 - exec	0	0
○Loop 260 - OneBodyJastrowRef.h:196-197 - exec	0	0
○Loop 263 - OneBodyJastrowRef.h:196-197 - exec	0	0
○Loop 262 - OneBodyJastrowRef.h:196-197 - exec	0	0
○Loop 264 - OneBodyJastrowRef.h:190-191 - exec	0	0

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