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:184-264 [...]	Coverage (incl. loops): 0.05% \| (excl. loops): 0.01%

/usr/include/c++/14/bits/stl_iterator.h: 1068 - 1139

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

1068:       : _M_current(__i) { }

[...]

1139:       { return __normal_iterator(_M_current + __n); }

/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 94

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

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

/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 184 - 264

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

184:     valT lap(0);

185:     constexpr valT lapfac = OHMMS_DIM - RealType(1);

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

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

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

189:     {

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

191:       valT s                  = valT();

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

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

194:       grad[idim] = s;

[...]

255:   ValueType ratioGrad(ParticleSet& P, int iat, GradType& grad_iat)

256:   {

257:     UpdateMode = ORB_PBYP_PARTIAL;

258:

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

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

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

262:     grad_iat += curGrad;

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

264:   }

/usr/include/c++/14/bits/stl_vector.h: 1263 - 1263

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

1263:       { return _M_data_ptr(this->_M_impl._M_start); }

/usr/include/c++/14/bits/stl_numeric.h: 140 - 141

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

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

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

0x451e80 STP	X29, X30, [SP, #960]!

0x451e84 ADD	X29, SP, #0

0x451e88 MOVZ	W4, #2

0x451e8c STP	X19, X20, [SP, #16]

0x451e90 ORR	X19, XZR, X0

0x451e94 ORR	X20, XZR, X3

0x451e98 STP	X21, X22, [SP, #32]

0x451e9c ORR	X22, XZR, X1

0x451ea0 ORR	W21, WZR, W2

0x451ea4 LDR	W1, [X0, #168]

0x451ea8 ORR	X0, XZR, X22

0x451eac STR	X23, [SP, #48]

0x451eb0 STR	W4, [X19, #12]

0x451eb4 BL	48fde0

0x451eb8 ORR	X1, XZR, X0

0x451ebc ORR	X0, XZR, X19

0x451ec0 LDR	X1, [X1, #144]

0x451ec4 BL	421a6c

0x451ec8 ORR	X0, XZR, X22

0x451ecc LDR	W1, [X19, #168]

0x451ed0 LDR	X23, [X19, #280]

0x451ed4 LDR	X22, [X19, #304]

0x451ed8 BL	48fde0

0x451edc LDR	W7, [X19, #144]

0x451ee0 LDR	X3, [X0, #168]

0x451ee4 LDR	X11, [X0, #184]

0x451ee8 CMP	W7, #0

0x451eec B.LE	4521bc

0x451ef0 CNTW	X2, ALL

0x451ef4 SUB	W10, W7, #1

0x451ef8 ADD	W0, W2, #3

0x451efc MOVZ	W9, #0

0x451f00 CMP	W10, W0

0x451f04 B.CC	4521d0

0x451f08 SUB	W6, W7, W2

0x451f0c ORR	X5, XZR, X22

0x451f10 DUP	Z30.D, #0

0x451f14 ORR	X12, XZR, X23

0x451f18 CNTB	X8, ALL, MUL #2

0x451f1c PTRUE	P7.B, ALL

0x451f20 ORR	Z0.D, Z30.D, Z30.D

0x451f24 FDUP	Z18.D, #0

(754) 0x451f28 ADD	W9, W9, W2

(754) 0x451f2c LD1D	{Z17.D}, P7/Z, [X5, #1, MUL VL]

(754) 0x451f30 LD1D	{Z6.D}, P7/Z, [X12, #1, MUL VL]

(754) 0x451f34 LD1D	{Z16.D}, P7/Z, [X12, MUL VL]

(754) 0x451f38 LD1D	{Z7.D}, P7/Z, [X5, MUL VL]

(754) 0x451f3c FMAD	Z6.D, P7/M, Z18.D, Z17.D

(754) 0x451f40 FMLA	Z7.D, P7/M, Z16.D, Z18.D

(754) 0x451f44 ADD	X12, X12, X8

(754) 0x451f48 ADD	X5, X5, X8

(754) 0x451f4c FADD	Z30.D, Z6.D, Z30.D

(754) 0x451f50 FADD	Z0.D, Z7.D, Z0.D

(754) 0x451f54 CMP	W6, W9

(754) 0x451f58 B.CS	451f28

0x451f5c FADD	Z5.D, Z0.D, Z30.D

0x451f60 CMP	W7, W9

0x451f64 B.EQ	451fa4

0x451f68 UBFM	X13, X9, #61, #31

0x451f6c MOVZ	X18, #0

0x451f70 FDUP	Z4.D, #0

0x451f74 CNTD	X14, ALL

0x451f78 ADD	X15, X22, X13

0x451f7c ADD	X16, X23, X13

0x451f80 SUB	W17, W7, W9

0x451f84 WHILELO	P0.D, WZR, W17

(753) 0x451f88 LD1D	{Z3.D}, P0/Z, [X15, X18,LSL #3]

(753) 0x451f8c LD1D	{Z2.D}, P0/Z, [X16, X18,LSL #3]

(753) 0x451f90 FADD	Z5.D, P0/M, Z5.D, Z3.D

(753) 0x451f94 ADD	X18, X18, X14

(753) 0x451f98 FMLA	Z5.D, P0/M, Z2.D, Z4.D

(753) 0x451f9c WHILELO	P0.D, W18, W17

(753) 0x451fa0 B.NE	451f88

0x451fa4 PTRUE	P1.B, ALL

0x451fa8 FADDV	D31, P1, Z5.D

0x451fac ADD	X13, X19, #192

0x451fb0 MOVZ	X22, #0

0x451fb4 UBFM	X17, X3, #61, #60

0x451fb8 ORR	X14, XZR, X13

0x451fbc ORR	X30, XZR, X11

0x451fc0 ADD	X12, X19, #216

(747) 0x451fc4 CMP	W7, #0

(747) 0x451fc8 B.LE	452188

0x451fcc CNTW	X9, ALL

0x451fd0 CNTD	X2, ALL

0x451fd4 PTRUE	P2.B, ALL

0x451fd8 ADD	W18, W9, #3

0x451fdc SUB	W0, W7, W9

0x451fe0 CNTB	X6, ALL, MUL #2

(751) 0x451fe4 MOVZ	W4, #0

(751) 0x451fe8 CMP	W10, W18

(751) 0x451fec B.CC	4521b4

(751) 0x451ff0 ORR	X8, XZR, X23

(751) 0x451ff4 ORR	X1, XZR, X30

(751) 0x451ff8 DUP	Z24.D, #0

(751) 0x451ffc ORR	Z19.D, Z24.D, Z24.D

  (752) 0x452000 ADD	W4, W4, W9

  (752) 0x452004 LD1D	{Z29.D}, P2/Z, [X8, #1, MUL VL]

  (752) 0x452008 LD1D	{Z28.D}, P2/Z, [X1, #1, MUL VL]

  (752) 0x45200c LD1D	{Z1.D}, P2/Z, [X8, MUL VL]

  (752) 0x452010 LD1D	{Z20.D}, P2/Z, [X1, MUL VL]

  (752) 0x452014 ADD	X8, X8, X6

  (752) 0x452018 ADD	X1, X1, X6

  (752) 0x45201c FMLA	Z24.D, P2/M, Z29.D, Z28.D

  (752) 0x452020 FMLA	Z19.D, P2/M, Z1.D, Z20.D

  (752) 0x452024 CMP	W0, W4

  (752) 0x452028 B.CS	452000

(751) 0x45202c FADD	Z26.D, Z19.D, Z24.D

(751) 0x452030 CMP	W7, W4

(751) 0x452034 B.EQ	452068

(751) 0x452038 ADD	X5, X22, W4,UXTW

(751) 0x45203c ADD	X15, X11, X5,LSL #3

(751) 0x452040 MOVZ	X8, #0

(751) 0x452044 SUB	W16, W7, W4

(751) 0x452048 ADD	X4, X23, W4,UXTW #3

(751) 0x45204c WHILELO	P6.D, WZR, W16

  (750) 0x452050 LD1D	{Z27.D}, P6/Z, [X4, X8,LSL #3]

  (750) 0x452054 LD1D	{Z25.D}, P6/Z, [X15, X8,LSL #3]

  (750) 0x452058 ADD	X8, X8, X2

  (750) 0x45205c FMLA	Z26.D, P6/M, Z27.D, Z25.D

  (750) 0x452060 WHILELO	P6.D, W8, W16

  (750) 0x452064 B.NE	452050

(751) 0x452068 FADDV	D21, P2, Z26.D

(751) 0x45206c ADD	X30, X30, X17

(751) 0x452070 ADD	X22, X22, X3

(751) 0x452074 STR	D21, [X14], #8

(751) 0x452078 CMP	X14, X12

(751) 0x45207c B.NE	451fe4

0x452080 SBFM	X30, X7, #61, #31

0x452084 STR	D31, [X19, #184]

0x452088 LDR	X22, [X19, #256]

0x45208c CBZ	X30, 4521ac

0x452090 UBFM	X15, X30, #3, #63

0x452094 CNTH	X16, ALL

0x452098 SUB	X4, X15, #1

0x45209c ADD	X1, X16, #7

0x4520a0 MOVZ	X5, #0

0x4520a4 CMP	X4, X1

0x4520a8 B.CC	4521c8

0x4520ac SUB	X8, X15, X16

0x4520b0 ORR	X2, XZR, X22

0x4520b4 DUP	Z30.D, #0

0x4520b8 CNTB	X0, ALL, MUL #4

0x4520bc PTRUE	P3.B, ALL

0x4520c0 ORR	Z0.D, Z30.D, Z30.D

0x4520c4 ORR	Z6.D, Z30.D, Z30.D

0x4520c8 ORR	Z17.D, Z30.D, Z30.D

(749) 0x4520cc ADD	X5, X5, X16

(749) 0x4520d0 LD1D	{Z5.D}, P3/Z, [X2, MUL VL]

(749) 0x4520d4 LD1D	{Z18.D}, P3/Z, [X2, #1, MUL VL]

(749) 0x4520d8 LD1D	{Z16.D}, P3/Z, [X2, #2, MUL VL]

(749) 0x4520dc LD1D	{Z7.D}, P3/Z, [X2, #3, MUL VL]

(749) 0x4520e0 FADD	Z17.D, Z17.D, Z5.D

(749) 0x4520e4 ADD	X2, X2, X0

(749) 0x4520e8 FADD	Z6.D, Z6.D, Z18.D

(749) 0x4520ec FADD	Z0.D, Z0.D, Z16.D

(749) 0x4520f0 FADD	Z30.D, Z30.D, Z7.D

(749) 0x4520f4 CMP	X8, X5

(749) 0x4520f8 B.CS	4520cc

0x4520fc FADD	Z4.D, Z17.D, Z6.D

0x452100 FADD	Z3.D, Z0.D, Z30.D

0x452104 FADD	Z23.D, Z4.D, Z3.D

0x452108 CMP	X5, X15

0x45210c B.EQ	452138

0x452110 ADD	X3, X22, X5,LSL #3

0x452114 MOVZ	X9, #0

0x452118 CNTD	X6, ALL

0x45211c SUB	X7, X15, X5

0x452120 WHILELO	P4.D, XZR, X7

(748) 0x452124 LD1D	{Z2.D}, P4/Z, [X3, X9,LSL #3]

(748) 0x452128 ADD	X9, X9, X6

(748) 0x45212c FADD	Z23.D, P4/M, Z23.D, Z2.D

(748) 0x452130 WHILELO	P4.D, X9, X7

(748) 0x452134 B.NE	452124

0x452138 PTRUE	P5.B, ALL

0x45213c FADDV	D22, P5, Z23.D

0x452140 LDR	X10, [X12, #24]

0x452144 LDR	X23, [SP, #48]

0x452148 STR	D22, [X19, #176]

0x45214c LDR	Q24, [X20]

0x452150 LDR	Q26, [X19, #192]

0x452154 LDR	D19, [X20, #16]

0x452158 FADD	V29.2D, V26.2D, V24.2D

0x45215c STR	Q29, [X20]

0x452160 LDR	D28, [X13, #16]

0x452164 FADD	D1, D19, D28

0x452168 STR	D1, [X20, #16]

0x45216c LDR	D20, [X10, W21,SXTW #3]

0x452170 LDP	X21, X22, [SP, #32]

0x452174 LDR	D27, [X19, #176]

0x452178 LDP	X19, X20, [SP, #16]

0x45217c LDP	X29, X30, [SP], #64

0x452180 FSUB	D0, D20, S27

0x452184 B	4100e0

(747) 0x452188 ADD	X30, X30, X17

(747) 0x45218c ADD	X22, X22, X3

(747) 0x452190 STR	XZR, [X14], #8

(747) 0x452194 CMP	X14, X12

(747) 0x452198 B.NE	451fc4

0x45219c SBFM	X30, X7, #61, #31

0x4521a0 STR	D31, [X19, #184]

0x4521a4 LDR	X22, [X19, #256]

0x4521a8 CBNZ	X30, 452090

0x4521ac MOVI	D22, #0

0x4521b0 B	452140

(751) 0x4521b4 DUP	Z26.D, #0

(751) 0x4521b8 B	452038

0x4521bc MOVI	D31, #0

0x4521c0 SUB	W10, W7, #1

0x4521c4 B	451fac

0x4521c8 DUP	Z23.D, #0

0x4521cc B	452110

0x4521d0 DUP	Z5.D, #0

0x4521d4 B	451f68

0x4521d8 HINT	#0

0x4521dc HINT	#0

Coverage (%)	Name	Source Location	Module
►98.05+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main._omp_fn.1	miniqmc.cpp:443	exec
○	omp_fulfill_event		libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6

min	med	avg	max

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

min	med	avg	max

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

Path /

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

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run gcc_0

Source file and lines	OneBodyJastrowRef.h:184-264
Module	exec

The function is defined in:

/usr/include/c++/14/bits/stl_iterator.h:1068,1139
/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:184-194,255-264
/usr/include/c++/14/bits/stl_vector.h:1263
/usr/include/c++/14/bits/stl_numeric.h:140-141

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 16.50 to 10.50 cycles (1.57x speedup).

Workaround

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

Vectorization

Your function is not vectorized. Only 39% of vector register length is used (average across all VPU instructions). By fully vectorizing your function, you can lower the cost of an iteration from 16.50 to 10.91 cycles (1.51x speedup).

Details

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

14% of VPU loads are used in vector version.
10% of VPU stores are used in vector version.
38% of VPU addition or subtraction instructions are used in vector version.
8% 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)

No data for this section

CALL instructions

Detected function call instructions.

Details

Calling (and then returning from) a function prevents many compiler optimizations (like vectorization), breaks control flow (which reduces pipeline performance) and executes extra instructions to save/restore the registers used inside it, which is very expensive (dozens of cycles). Consider to inline small functions.

miniqmcreference::OneBodyJastrowRef
>::computeU3(qmcplusplus::ParticleSet&, int, double const*) [clone .isra.0]: 1 occurrences►
- /home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
qmcplusplus::ParticleSet::getDistTableAB(int) const: 2 occurrences►
- /home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
- /home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:260

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

The binary function is composed of 28 FP arithmetical operations:

28: addition or subtraction

The binary function is loading 9 bytes. The binary function is storing 3 bytes.

Arithmetic intensity

Arithmetic intensity is 2.33 FP operations per loaded or stored byte.

General properties

nb instructions	131
nb uops	129
loop length	524
used w registers	12
used x registers	27
used b registers	0
used h registers	0
used s registers	2
used d registers	8
used q registers	3
used v registers	3
used z registers	9
nb stack references	8

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	16.13 cycles
front end	16.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	7.50	7.50	16.50	16.50	16.50	16.50	10.50	10.50	3.50	3.50	10.33	10.33	10.33	2.50	2.50
cycles	7.50	7.50	16.50	16.50	16.50	16.50	10.50	10.50	4.75	4.75	10.33	10.33	10.33	2.50	2.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	16.13
Dispatch	16.50
Overall L1	16.50

Vectorization ratios

INT

all	9%
load	14%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	9%

all	63%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	77%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	16%
load	14%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	38%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	8%

Vector efficiency ratios

INT

all	35%
load	30%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	20%
fma	NA (no fma vectorizable/vectorized instructions)
other	40%

all	64%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	77%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	3%

INT+FP

all	39%
load	30%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	49%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	39%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 16.50 cycles. At this rate:

0% of peak load performance is reached (0.55 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (0.18 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 451e80

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #960]!	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
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	scal (25.0%)
MOVZ W4, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
STP X19, X20, [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	scal (50.0%)
ORR X19, 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	N/A
ORR X20, 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	N/A
STP X21, X22, [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	scal (50.0%)
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	scal (25.0%)
ORR W21, 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	N/A
LDR W1, [X0, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X23, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR W4, [X19, #12]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (12.5%)
BL 48fde0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X1, 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	N/A
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X1, [X1, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
BL 421a6c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd.isra.0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR W1, [X19, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X23, [X19, #280]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X22, [X19, #304]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
BL 48fde0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR W7, [X19, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X3, [X0, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X11, [X0, #184]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CMP W7, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.LE 4521bc <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x33c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CNTW X2, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
SUB W10, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD W0, W2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ W9, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP W10, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.CC 4521d0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x350>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB W6, W7, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ORR X5, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
DUP Z30.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
ORR X12, XZR, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CNTB X8, ALL, MUL #2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
PTRUE P7.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
ORR Z0.D, Z30.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
FDUP Z18.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
FADD Z5.D, Z0.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
CMP W7, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 451fa4 <_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	N/A
UBFM X13, X9, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ X18, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
FDUP Z4.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
CNTD X14, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
ADD X15, X22, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X16, X23, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB W17, W7, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
WHILELO P0.D, WZR, W17	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	2	N/A
PTRUE P1.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
FADDV D31, P1, Z5.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2	vect (100.0%)
ADD X13, X19, #192	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ X22, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
UBFM X17, X3, #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	scal (25.0%)
ORR X14, XZR, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X30, XZR, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X12, X19, #216	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CNTW X9, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
CNTD X2, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
PTRUE P2.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
ADD W18, W9, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
SUB W0, W7, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CNTB X6, ALL, MUL #2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
SBFM X30, X7, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
STR D31, [X19, #184]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
LDR X22, [X19, #256]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CBZ X30, 4521ac <_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	N/A
UBFM X15, X30, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CNTH X16, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
SUB X4, X15, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X1, X16, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ X5, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CMP X4, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CC 4521c8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x348>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB X8, X15, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X2, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
DUP Z30.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
CNTB X0, ALL, MUL #4	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
PTRUE P3.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
ORR Z0.D, Z30.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
ORR Z6.D, Z30.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
ORR Z17.D, Z30.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
FADD Z4.D, Z17.D, Z6.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
FADD Z3.D, Z0.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
FADD Z23.D, Z4.D, Z3.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
CMP X5, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 452138 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X3, X22, X5,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	scal (25.0%)
MOVZ X9, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CNTD X6, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
SUB X7, X15, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
WHILELO P4.D, XZR, X7	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	2	N/A
PTRUE P5.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
FADDV D22, P5, Z23.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2	vect (100.0%)
LDR X10, [X12, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X23, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
STR D22, [X19, #176]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
LDR Q24, [X20]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (50.0%)
LDR Q26, [X19, #192]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (50.0%)
LDR D19, [X20, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
FADD V29.2D, V26.2D, V24.2D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	vect (50.0%)
STR Q29, [X20]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (50.0%)
LDR D28, [X13, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
FADD D1, D19, D28	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
STR D1, [X20, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
LDR D20, [X10, W21,SXTW #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
LDP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR D27, [X19, #176]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X29, X30, [SP], #64	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
FSUB D0, D20, S27	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
B 4100e0 <@plt_start@+0xc0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SBFM X30, X7, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
STR D31, [X19, #184]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
LDR X22, [X19, #256]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CBNZ X30, 452090 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x210>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVI D22, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
B 452140 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2c0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVI D31, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
SUB W10, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
B 451fac <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x12c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
DUP Z23.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
B 452110 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x290>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
DUP Z5.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
B 451f68 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xe8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
HINT #0																			N/A
HINT #0																			N/A

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run gcc_0

Source file and lines	OneBodyJastrowRef.h:184-264
Module	exec

The function is defined in:

/usr/include/c++/14/bits/stl_iterator.h:1068,1139
/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:184-194,255-264
/usr/include/c++/14/bits/stl_vector.h:1263
/usr/include/c++/14/bits/stl_numeric.h:140-141

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Workaround

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

Vectorization

Details

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

14% of VPU loads are used in vector version.
10% of VPU stores are used in vector version.
38% of VPU addition or subtraction instructions are used in vector version.
8% 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)

No data for this section

CALL instructions

Detected function call instructions.

Details

miniqmcreference::OneBodyJastrowRef
>::computeU3(qmcplusplus::ParticleSet&, int, double const*) [clone .isra.0]: 1 occurrences►
- /home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
qmcplusplus::ParticleSet::getDistTableAB(int) const: 2 occurrences►
- /home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
- /home/eoseret/qaas/qaas_runs/178-212-9071/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:260

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

The binary function is composed of 28 FP arithmetical operations:

28: addition or subtraction

The binary function is loading 9 bytes. The binary function is storing 3 bytes.

Arithmetic intensity

Arithmetic intensity is 2.33 FP operations per loaded or stored byte.

General properties

nb instructions	131
nb uops	129
loop length	524
used w registers	12
used x registers	27
used b registers	0
used h registers	0
used s registers	2
used d registers	8
used q registers	3
used v registers	3
used z registers	9
nb stack references	8

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	16.13 cycles
front end	16.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	7.50	7.50	16.50	16.50	16.50	16.50	10.50	10.50	3.50	3.50	10.33	10.33	10.33	2.50	2.50
cycles	7.50	7.50	16.50	16.50	16.50	16.50	10.50	10.50	4.75	4.75	10.33	10.33	10.33	2.50	2.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	16.13
Dispatch	16.50
Overall L1	16.50

Vectorization ratios

INT

all	9%
load	14%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	9%

all	63%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	77%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	16%
load	14%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	38%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	8%

Vector efficiency ratios

INT

all	35%
load	30%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	20%
fma	NA (no fma vectorizable/vectorized instructions)
other	40%

all	64%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	77%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	3%

INT+FP

all	39%
load	30%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	49%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	39%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 16.50 cycles. At this rate:

0% of peak load performance is reached (0.55 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (0.18 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 451e80

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #960]!	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
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	scal (25.0%)
MOVZ W4, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
STP X19, X20, [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	scal (50.0%)
ORR X19, 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	N/A
ORR X20, 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	N/A
STP X21, X22, [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	scal (50.0%)
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	scal (25.0%)
ORR W21, 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	N/A
LDR W1, [X0, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X23, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR W4, [X19, #12]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (12.5%)
BL 48fde0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X1, 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	N/A
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X1, [X1, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
BL 421a6c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd.isra.0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR W1, [X19, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X23, [X19, #280]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X22, [X19, #304]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
BL 48fde0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR W7, [X19, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X3, [X0, #168]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X11, [X0, #184]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CMP W7, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.LE 4521bc <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x33c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CNTW X2, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
SUB W10, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD W0, W2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ W9, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP W10, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.CC 4521d0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x350>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB W6, W7, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ORR X5, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
DUP Z30.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
ORR X12, XZR, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CNTB X8, ALL, MUL #2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
PTRUE P7.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
ORR Z0.D, Z30.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
FDUP Z18.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
FADD Z5.D, Z0.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
CMP W7, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 451fa4 <_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	N/A
UBFM X13, X9, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ X18, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
FDUP Z4.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
CNTD X14, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
ADD X15, X22, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X16, X23, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB W17, W7, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
WHILELO P0.D, WZR, W17	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	2	N/A
PTRUE P1.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
FADDV D31, P1, Z5.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2	vect (100.0%)
ADD X13, X19, #192	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ X22, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
UBFM X17, X3, #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	scal (25.0%)
ORR X14, XZR, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X30, XZR, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X12, X19, #216	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CNTW X9, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
CNTD X2, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
PTRUE P2.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
ADD W18, W9, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
SUB W0, W7, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CNTB X6, ALL, MUL #2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
SBFM X30, X7, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
STR D31, [X19, #184]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
LDR X22, [X19, #256]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CBZ X30, 4521ac <_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	N/A
UBFM X15, X30, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CNTH X16, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
SUB X4, X15, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X1, X16, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ X5, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CMP X4, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CC 4521c8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x348>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB X8, X15, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X2, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
DUP Z30.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
CNTB X0, ALL, MUL #4	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
PTRUE P3.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
ORR Z0.D, Z30.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
ORR Z6.D, Z30.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
ORR Z17.D, Z30.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
FADD Z4.D, Z17.D, Z6.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
FADD Z3.D, Z0.D, Z30.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
FADD Z23.D, Z4.D, Z3.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
CMP X5, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 452138 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X3, X22, X5,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	scal (25.0%)
MOVZ X9, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CNTD X6, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
SUB X7, X15, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
WHILELO P4.D, XZR, X7	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	2	N/A
PTRUE P5.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
FADDV D22, P5, Z23.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2	vect (100.0%)
LDR X10, [X12, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X23, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
STR D22, [X19, #176]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
LDR Q24, [X20]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (50.0%)
LDR Q26, [X19, #192]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (50.0%)
LDR D19, [X20, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
FADD V29.2D, V26.2D, V24.2D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	vect (50.0%)
STR Q29, [X20]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (50.0%)
LDR D28, [X13, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
FADD D1, D19, D28	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
STR D1, [X20, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
LDR D20, [X10, W21,SXTW #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
LDP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR D27, [X19, #176]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X29, X30, [SP], #64	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
FSUB D0, D20, S27	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
B 4100e0 <@plt_start@+0xc0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SBFM X30, X7, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
STR D31, [X19, #184]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
LDR X22, [X19, #256]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CBNZ X30, 452090 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x210>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVI D22, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
B 452140 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2c0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOVI D31, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
SUB W10, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
B 451fac <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x12c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
DUP Z23.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
B 452110 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x290>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
DUP Z5.D, #0	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	scal (3.1%)
B 451f68 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xe8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
HINT #0																			N/A
HINT #0																			N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::OneBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)–	0.05	0.08
○Loop 754 - OneBodyJastrowRef.h:186-187 - exec	0.00	0.02
○Loop 749 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 747 - OneBodyJastrowRef.h:188-194 - exec	0.00	0.00
▼Loop 751 - OneBodyJastrowRef.h:184-194 - exec–	0.00	0.00
○Loop 752 - OneBodyJastrowRef.h:192-193 - exec	0.04	0.06
○Loop 750 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 748 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 753 - OneBodyJastrowRef.h:186-187 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

CALL instructions

Details

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

CALL instructions

Details

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code