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: 0.03%

/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];

0x4141a0 STP	X29, X30, [SP, #976]!

0x4141a4 STP	X22, X21, [SP, #16]

0x4141a8 STP	X20, X19, [SP, #32]

0x4141ac ADD	X29, SP, #0

0x4141b0 MOVZ	W8, #2

0x4141b4 LDR	X9, [X1, #2576]

0x4141b8 ORR	X21, XZR, X3

0x4141bc ORR	W19, WZR, W2

0x4141c0 STR	W8, [X0, #12]

0x4141c4 LDRSW	X8, [X0, #144]

0x4141c8 ORR	X22, XZR, X1

0x4141cc ORR	X20, XZR, X0

0x4141d0 LDR	X8, [X9, X8,LSL #3]

0x4141d4 LDR	X3, [X8, #104]

0x4141d8 BL	4164c0

0x4141dc LDR	W9, [X20, #148]

0x4141e0 CNTW	X8, ALL

0x4141e4 ADD	X14, X20, #184

0x4141e8 CMP	W9, #1

0x4141ec B.LT	414220

0x4141f0 LDRSW	X11, [X20, #144]

0x4141f4 LDR	X12, [X22, #2576]

0x4141f8 LDR	X10, [X20, #272]

0x4141fc CMP	X8, X9

0x414200 LDR	X13, [X20, #296]

0x414204 LDR	X15, [X12, X11,LSL #3]

0x414208 UDIV	X12, X9, X8

0x41420c ADDVL	X11, X10, #1

0x414210 B.LS	414240

0x414214 ORR	X16, XZR, XZR

0x414218 MOVI	D0, #0

0x41421c B	414298

0x414220 MOVI	D1, #0

0x414224 MOVI	D0, #0

0x414228 STP	XZR, XZR, [X14]

0x41422c STR	XZR, [X14, #16]

0x414230 STR	D0, [X20, #176]

0x414234 CBNZ	W9, 4144a4

0x414238 MOVI	D0, #0

0x41423c B	41453c

0x414240 DUP	Z0.D, #0

0x414244 ORR	X18, XZR, XZR

0x414248 UMSUBL	X17, W12, W8, X9

0x41424c FDUP	Z1.D, #0

0x414250 ORR	Z2.D, Z0.D, Z0.D

0x414254 UMADDL	X16, W12, W8, XZR

0x414258 ADDVL	X0, X13, #1

0x41425c PTRUE	P0.D, ALL

(257) 0x414260 LD1D	{Z3.D}, P0/Z, [X13, X18,LSL #3]

(257) 0x414264 LD1D	{Z4.D}, P0/Z, [X0, X18,LSL #3]

(257) 0x414268 FADD	Z0.D, Z3.D, Z0.D

(257) 0x41426c LD1D	{Z5.D}, P0/Z, [X10, X18,LSL #3]

(257) 0x414270 LD1D	{Z6.D}, P0/Z, [X11, X18,LSL #3]

(257) 0x414274 FADD	Z2.D, Z4.D, Z2.D

(257) 0x414278 ADD	X18, X18, X8

(257) 0x41427c CMP	X16, X18

(257) 0x414280 FMLA	Z0.D, P0/M, Z5.D, Z1.D

(257) 0x414284 FMLA	Z2.D, P0/M, Z6.D, Z1.D

(257) 0x414288 B.NE	414260

0x41428c FADD	Z0.D, Z2.D, Z0.D

0x414290 FADDV	D0, P0, Z0.D

0x414294 CBZ	X17, 4142c4

0x414298 UBFM	X18, X16, #61, #60

0x41429c SUB	X17, X9, X16

0x4142a0 ADD	X16, X10, X18

0x4142a4 ADD	X13, X13, X18

(264) 0x4142a8 LDR	D1, [X13], #8

(264) 0x4142ac LDR	D2, [X16], #8

(264) 0x4142b0 FADD	D2, D2, D2

(264) 0x4142b4 FADD	D0, D1, D0

(264) 0x4142b8 SUBS	X17, X17, #1

(264) 0x4142bc FADD	D0, D0, D2

(264) 0x4142c0 B.NE	4142a8

0x4142c4 LDR	X13, [X15, #152]

0x4142c8 CMP	X8, X9

0x4142cc B.LS	4142dc

0x4142d0 ORR	X16, XZR, XZR

0x4142d4 MOVI	D1, #0

0x4142d8 B	414330

0x4142dc DUP	Z1.D, #0

0x4142e0 ORR	X18, XZR, XZR

0x4142e4 UMSUBL	X17, W12, W8, X9

0x4142e8 ORR	Z2.D, Z1.D, Z1.D

0x4142ec UMADDL	X16, W12, W8, XZR

0x4142f0 ADDVL	X0, X13, #1

0x4142f4 PTRUE	P0.D, ALL

0x4142f8 HINT	#0

0x4142fc HINT	#0

(258) 0x414300 LD1D	{Z3.D}, P0/Z, [X10, X18,LSL #3]

(258) 0x414304 LD1D	{Z4.D}, P0/Z, [X11, X18,LSL #3]

(258) 0x414308 LD1D	{Z5.D}, P0/Z, [X13, X18,LSL #3]

(258) 0x41430c FMLA	Z1.D, P0/M, Z5.D, Z3.D

(258) 0x414310 LD1D	{Z6.D}, P0/Z, [X0, X18,LSL #3]

(258) 0x414314 FMLA	Z2.D, P0/M, Z6.D, Z4.D

(258) 0x414318 ADD	X18, X18, X8

(258) 0x41431c CMP	X16, X18

(258) 0x414320 B.NE	414300

0x414324 FADD	Z1.D, Z2.D, Z1.D

0x414328 FADDV	D1, P0, Z1.D

0x41432c CBZ	X17, 414354

0x414330 UBFM	X18, X16, #61, #60

0x414334 SUB	X17, X9, X16

0x414338 ADD	X16, X13, X18

0x41433c ADD	X18, X10, X18

(263) 0x414340 LDR	D2, [X18], #8

(263) 0x414344 LDR	D3, [X16], #8

(263) 0x414348 FMADD	D1, D3, D2, D1

(263) 0x41434c SUBS	X17, X17, #1

(263) 0x414350 B.NE	414340

0x414354 LDR	X15, [X15, #136]

0x414358 CMP	X8, X9

0x41435c STR	D1, [X14]

0x414360 B.LS	414370

0x414364 ORR	X14, XZR, XZR

0x414368 MOVI	D2, #0

0x41436c B	4143d0

0x414370 ADD	X18, X13, X15,LSL #3

0x414374 DUP	Z2.D, #0

0x414378 ORR	X17, XZR, XZR

0x41437c ORR	Z3.D, Z2.D, Z2.D

0x414380 UMSUBL	X16, W12, W8, X9

0x414384 UMADDL	X14, W12, W8, XZR

0x414388 ADDVL	X0, X18, #1

0x41438c PTRUE	P0.D, ALL

0x414390 HINT	#0

0x414394 HINT	#0

0x414398 HINT	#0

0x41439c HINT	#0

(259) 0x4143a0 LD1D	{Z4.D}, P0/Z, [X10, X17,LSL #3]

(259) 0x4143a4 LD1D	{Z5.D}, P0/Z, [X11, X17,LSL #3]

(259) 0x4143a8 LD1D	{Z6.D}, P0/Z, [X18, X17,LSL #3]

(259) 0x4143ac FMLA	Z2.D, P0/M, Z6.D, Z4.D

(259) 0x4143b0 LD1D	{Z7.D}, P0/Z, [X0, X17,LSL #3]

(259) 0x4143b4 FMLA	Z3.D, P0/M, Z7.D, Z5.D

(259) 0x4143b8 ADD	X17, X17, X8

(259) 0x4143bc CMP	X14, X17

(259) 0x4143c0 B.NE	4143a0

0x4143c4 FADD	Z2.D, Z3.D, Z2.D

0x4143c8 FADDV	D2, P0, Z2.D

0x4143cc CBZ	X16, 4143f8

0x4143d0 UBFM	X17, X14, #61, #60

0x4143d4 SUB	X16, X9, X14

0x4143d8 ADD	X14, X17, X15,LSL #3

0x4143dc ADD	X17, X10, X17

0x4143e0 ADD	X14, X13, X14

(262) 0x4143e4 LDR	D3, [X17], #8

(262) 0x4143e8 LDR	D4, [X14], #8

(262) 0x4143ec FMADD	D2, D4, D3, D2

(262) 0x4143f0 SUBS	X16, X16, #1

(262) 0x4143f4 B.NE	4143e4

0x4143f8 CMP	X8, X9

0x4143fc STR	D2, [X20, #192]

0x414400 B.LS	414410

0x414404 ORR	X12, XZR, XZR

0x414408 MOVI	D2, #0

0x41440c B	414470

0x414410 ADD	X17, X13, X15,LSL #4

0x414414 DUP	Z2.D, #0

0x414418 ORR	X16, XZR, XZR

0x41441c ORR	Z3.D, Z2.D, Z2.D

0x414420 UMSUBL	X14, W12, W8, X9

0x414424 UMADDL	X12, W12, W8, XZR

0x414428 ADDVL	X18, X17, #1

0x41442c PTRUE	P0.D, ALL

0x414430 HINT	#0

0x414434 HINT	#0

0x414438 HINT	#0

0x41443c HINT	#0

(260) 0x414440 LD1D	{Z4.D}, P0/Z, [X10, X16,LSL #3]

(260) 0x414444 LD1D	{Z5.D}, P0/Z, [X11, X16,LSL #3]

(260) 0x414448 LD1D	{Z6.D}, P0/Z, [X17, X16,LSL #3]

(260) 0x41444c FMLA	Z2.D, P0/M, Z6.D, Z4.D

(260) 0x414450 LD1D	{Z7.D}, P0/Z, [X18, X16,LSL #3]

(260) 0x414454 FMLA	Z3.D, P0/M, Z7.D, Z5.D

(260) 0x414458 ADD	X16, X16, X8

(260) 0x41445c CMP	X12, X16

(260) 0x414460 B.NE	414440

0x414464 FADD	Z2.D, Z3.D, Z2.D

0x414468 FADDV	D2, P0, Z2.D

0x41446c CBZ	X14, 414498

0x414470 UBFM	X14, X12, #61, #60

0x414474 SUB	X11, X9, X12

0x414478 ADD	X12, X14, X15,LSL #4

0x41447c ADD	X10, X10, X14

0x414480 ADD	X12, X13, X12

(261) 0x414484 LDR	D3, [X10], #8

(261) 0x414488 LDR	D4, [X12], #8

(261) 0x41448c FMADD	D2, D4, D3, D2

(261) 0x414490 SUBS	X11, X11, #1

(261) 0x414494 B.NE	414484

0x414498 STR	D2, [X20, #200]

0x41449c STR	D0, [X20, #176]

0x4144a0 CBZ	W9, 414238

0x4144a4 SBFM	X9, X9, #0, #31

0x4144a8 LDR	X10, [X20, #248]

0x4144ac MOVI	D0, #0

0x4144b0 SUB	X11, X9, #1

0x4144b4 AND	X11, X11, #7936

0x4144b8 ADD	X11, X11, #1

0x4144bc CMP	X11, X8

0x4144c0 B.CS	4144cc

0x4144c4 ORR	X11, XZR, X10

0x4144c8 B	414528

0x4144cc UDIV	X12, X11, X8

0x4144d0 DUP	Z0.D, #0

0x4144d4 ORR	X13, XZR, XZR

0x4144d8 ADDVL	X15, X10, #1

0x4144dc PTRUE	P0.D, ALL

0x4144e0 ORR	Z2.D, Z0.D, Z0.D

0x4144e4 MADD	X14, X12, X8, XZR

0x4144e8 SUB	X12, X11, X14

0x4144ec ADD	X11, X10, X14,LSL #3

0x4144f0 HINT	#0

0x4144f4 HINT	#0

0x4144f8 HINT	#0

0x4144fc HINT	#0

(255) 0x414500 LD1D	{Z3.D}, P0/Z, [X10, X13,LSL #3]

(255) 0x414504 LD1D	{Z4.D}, P0/Z, [X15, X13,LSL #3]

(255) 0x414508 ADD	X13, X13, X8

(255) 0x41450c CMP	X14, X13

(255) 0x414510 FADD	Z0.D, Z3.D, Z0.D

(255) 0x414514 FADD	Z2.D, Z4.D, Z2.D

(255) 0x414518 B.NE	414500

0x41451c FADD	Z0.D, Z2.D, Z0.D

0x414520 FADDV	D0, P0, Z0.D

0x414524 CBZ	X12, 41453c

0x414528 ADD	X8, X10, X9,LSL #3

(256) 0x41452c LDR	D2, [X11], #8

(256) 0x414530 FADD	D0, D2, D0

(256) 0x414534 CMP	X11, X8

(256) 0x414538 B.NE	41452c

0x41453c STR	D0, [X20, #168]

0x414540 LDR	X8, [X20, #232]

0x414544 LDP	D0, D2, [X21]

0x414548 FADD	D0, D0, D1

0x41454c LDR	D1, [X21, #16]

0x414550 STR	D0, [X21]

0x414554 LDR	D0, [X20, #192]

0x414558 FADD	D0, D2, D0

0x41455c STR	D0, [X21, #8]

0x414560 LDR	D0, [X20, #200]

0x414564 FADD	D0, D1, D0

0x414568 STR	D0, [X21, #16]

0x41456c LDR	D0, [X8, X19,SXTW #3]

0x414570 LDR	D1, [X20, #168]

0x414574 FSUB	D0, D0, S1

0x414578 LDP	X20, X19, [SP, #32]

0x41457c LDP	X22, X21, [SP, #16]

0x414580 LDP	X29, X30, [SP], #48

0x414584 B	403d80

0x414588 HINT	#0

0x41458c HINT	#0

0x414590 HINT	#0

0x414594 HINT	#0

0x414598 HINT	#0

0x41459c 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: 4141a0

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 4164c0 <_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 414220 <_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 414240 <_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 414298 <_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, 4144a4 <_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 41453c <_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, 4142c4 <_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 4142dc <_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 414330 <_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, 414354 <_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 414370 <_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 4143d0 <_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, 4143f8 <_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 414410 <_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 414470 <_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, 414498 <_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, 414238 <_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 4144cc <_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 414528 <_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, 41453c <_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 403d80 <@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: 4141a0

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 4164c0 <_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 414220 <_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 414240 <_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 414298 <_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, 4144a4 <_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 41453c <_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, 4142c4 <_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 4142dc <_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 414330 <_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, 414354 <_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 414370 <_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 4143d0 <_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, 4143f8 <_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 414410 <_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 414470 <_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, 414498 <_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, 414238 <_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 4144cc <_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 414528 <_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, 41453c <_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 403d80 <@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&)–	0.03	0.01
○Loop 258 - OneBodyJastrowRef.h:196-197 - exec	0.01	0
○Loop 260 - OneBodyJastrowRef.h:196-197 - exec	0.01	0
○Loop 257 - OneBodyJastrowRef.h:190-191 - exec	0	0
○Loop 259 - OneBodyJastrowRef.h:196-197 - exec	0	0
○Loop 255 - stl_numeric.h:141-141 - exec	0	0
○Loop 261 - OneBodyJastrowRef.h:196-197 - exec	0	0
○Loop 263 - OneBodyJastrowRef.h:196-197 - exec	0	0
○Loop 256 - stl_numeric.h:140-141 - 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