OV - exec - Loop 637

	Loop Id: 637	Module: exec	Source: BsplineFunctor.h:291-297	Coverage: 0.33%

0x434ebc LDR	D8, [X11, X0,LSL #3]    [15]

0x434ec0 FCMPE	D8, D0

0x434ec4 B.GE	434ee4

0x434ec8 ADD	W25, W17, W0

0x434ecc CMP	W19, W25

0x434ed0 B.EQ	434ee4

0x434ed4 SBFM	X26, X8, #0, #31

0x434ed8 ADD	W8, W8, #1

0x434edc STR	W0, [X13, X26,LSL #2]    [3]

0x434ee0 STR	D8, [X12, X26,LSL #3]    [12]

0x434ee4 ADD	X0, X0, #1

0x434ee8 LDR	D9, [X11, X0,LSL #3]    [7]

0x434eec FCMPE	D9, D0

0x434ef0 B.GE	434f10

0x434ef4 ADD	W1, W17, W0

0x434ef8 CMP	W19, W1

0x434efc B.EQ	434f10

0x434f00 SBFM	X5, X8, #0, #31

0x434f04 ADD	W8, W8, #1

0x434f08 STR	W0, [X13, X5,LSL #2]    [10]

0x434f0c STR	D9, [X12, X5,LSL #3]    [17]

0x434f10 ADD	X10, X0, #1

0x434f14 LDR	D10, [X11, X10,LSL #3]    [19]

0x434f18 FCMPE	D10, D0

0x434f1c B.GE	434f3c

0x434f20 ADD	W16, W17, W10

0x434f24 CMP	W19, W16

0x434f28 B.EQ	434f3c

0x434f2c SBFM	X9, X8, #0, #31

0x434f30 ADD	W8, W8, #1

0x434f34 STR	W10, [X13, X9,LSL #2]    [18]

0x434f38 STR	D10, [X12, X9,LSL #3]    [20]

0x434f3c ADD	X25, X0, #2

0x434f40 LDR	D11, [X11, X25,LSL #3]    [1]

0x434f44 FCMPE	D11, D0

0x434f48 B.GE	434f68

0x434f4c ADD	W26, W17, W25

0x434f50 CMP	W19, W26

0x434f54 B.EQ	434f68

0x434f58 SBFM	X1, X8, #0, #31

0x434f5c ADD	W8, W8, #1

0x434f60 STR	W25, [X13, X1,LSL #2]    [5]

0x434f64 STR	D11, [X12, X1,LSL #3]    [9]

0x434f68 ADD	X5, X0, #3

0x434f6c LDR	D12, [X11, X5,LSL #3]    [8]

0x434f70 FCMPE	D12, D0

0x434f74 B.GE	434f94

0x434f78 ADD	W10, W17, W5

0x434f7c CMP	W19, W10

0x434f80 B.EQ	434f94

0x434f84 SBFM	X16, X8, #0, #31

0x434f88 ADD	W8, W8, #1

0x434f8c STR	W5, [X13, X16,LSL #2]    [2]

0x434f90 STR	D12, [X12, X16,LSL #3]    [11]

0x434f94 ADD	X9, X0, #4

0x434f98 LDR	D13, [X11, X9,LSL #3]    [14]

0x434f9c FCMPE	D13, D0

0x434fa0 B.GE	434fc0

0x434fa4 ADD	W25, W17, W9

0x434fa8 CMP	W19, W25

0x434fac B.EQ	434fc0

0x434fb0 SBFM	X26, X8, #0, #31

0x434fb4 ADD	W8, W8, #1

0x434fb8 STR	W9, [X13, X26,LSL #2]    [3]

0x434fbc STR	D13, [X12, X26,LSL #3]    [12]

0x434fc0 ADD	X1, X0, #5

0x434fc4 LDR	D15, [X11, X1,LSL #3]    [4]

0x434fc8 FCMPE	D15, D0

0x434fcc B.GE	434fec

0x434fd0 ADD	W5, W17, W1

0x434fd4 CMP	W19, W5

0x434fd8 B.EQ	434fec

0x434fdc SBFM	X10, X8, #0, #31

0x434fe0 ADD	W8, W8, #1

0x434fe4 STR	W1, [X13, X10,LSL #2]    [16]

0x434fe8 STR	D15, [X12, X10,LSL #3]    [22]

0x434fec ADD	X9, X0, #6

0x434ff0 LDR	D17, [X11, X9,LSL #3]    [13]

0x434ff4 FCMPE	D17, D0

0x434ff8 B.GE	435018

0x434ffc ADD	W16, W17, W9

0x435000 CMP	W19, W16

0x435004 B.EQ	435018

0x435008 SBFM	X25, X8, #0, #31

0x43500c ADD	W8, W8, #1

0x435010 STR	W9, [X13, X25,LSL #2]    [21]

0x435014 STR	D17, [X12, X25,LSL #3]    [6]

0x435018 ADD	X0, X0, #7

0x43501c CMP	W18, W0

0x435020 B.GT	434ebc

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 291 - 297

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

291:   for (int jat = 0; jat < iLimit; jat++)

292:   {

293:     real_type r = distArray[jat];

294:     if (r < cutoff_radius && iStart + jat != iat)

295:     {

296:       distIndices[iCount]         = jat;

297:       distArrayCompressed[iCount] = r;

Coverage (%)	Name	Source Location	Module
►21.95+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:312	exec
○	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►14.63+	miniqmcreference::TwoBodyJastr[...]	stl_iterator.h:1007	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:207	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►14.63+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:312	exec
○	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►14.63+	miniqmcreference::TwoBodyJastr[...]	stl_iterator.h:1007	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:207	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►9.76+	miniqmcreference::TwoBodyJastr[...]	stl_iterator.h:1007	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:207	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►9.76+	miniqmcreference::TwoBodyJastr[...]	stl_iterator.h:1007	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:207	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►7.32+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:312	exec
○	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►7.32+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:312	exec
○	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec

Path /

Metric	Value
CQA speedup if no scalar integer	2.11
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	6.75
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.10
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
Source	BsplineFunctor.h:291-297
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	11.25
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	11.25
CQA cycles if fully vectorized	1.67
Front-end cycles	11.25
DIV/SQRT cycles	8.50
P0 cycles	8.50
P1 cycles	10.25
P2 cycles	10.25
P3 cycles	10.25
P4 cycles	10.25
P5 cycles	8.00
P6 cycles	8.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	8.00
P10 cycles	8.00
P11 cycles	8.00
P12 cycles	4.00
P13 cycles	4.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	90.00
Nb loads	NA
Nb stores	16.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	14.22
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	96.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	18.75
Vector-efficiency ratio load	25.00
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	12.50

Metric	Value
CQA speedup if no scalar integer	2.11
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	6.75
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.10
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
Source	BsplineFunctor.h:291-297
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	11.25
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	11.25
CQA cycles if fully vectorized	1.67
Front-end cycles	11.25
DIV/SQRT cycles	8.50
P0 cycles	8.50
P1 cycles	10.25
P2 cycles	10.25
P3 cycles	10.25
P4 cycles	10.25
P5 cycles	8.00
P6 cycles	8.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	8.00
P10 cycles	8.00
P11 cycles	8.00
P12 cycles	4.00
P13 cycles	4.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	90.00
Nb loads	NA
Nb stores	16.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	14.22
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	96.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	18.75
Vector-efficiency ratio load	25.00
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	12.50

Path /

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

Function	miniqmcreference::TwoBodyJastrowRef >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
Source file and lines	BsplineFunctor.h:291-297
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291-297.

The related source loop is not unrolled or unrolled with no peel/tail loop.
Warnings:

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 6561 paths individually, rerun with max-paths=6561
RecMII not computed since number of paths is unknown or > max_paths

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This loop has 6561 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside loop: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

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 11.25 to 5.33 cycles (2.11x speedup).

Workaround

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

Vectorization

Your loop is not vectorized. Only 18% of vector register length is used (average across all VPU instructions). By vectorizing your loop, you can lower the cost of an iteration from 11.25 to 1.67 cycles (6.75x speedup).

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one:
- recompile with ftree-vectorize (included in O3) to enable loop vectorization (including FP reductions).
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop 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

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

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 64 bytes. The binary loop is storing 96 bytes.

General properties

nb instructions	90
loop length	360
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

11.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00
cycles	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.25
Overall L1	11.25

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 11.25 cycles. At this rate:

5% of peak load performance is reached (5.69 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
17% of peak store performance is reached (8.53 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 434ebc

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR D8, [X11, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434ee4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W25, W17, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434ee4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X26, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X13, X26,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D8, [X12, X26,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X0, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D9, [X11, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D9, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434f10 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W1, W17, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434f10 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X5, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X13, X5,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D9, [X12, X5,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X10, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D10, [X11, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D10, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434f3c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x31c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W16, W17, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434f3c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x31c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X9, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W10, [X13, X9,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D10, [X12, X9,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X25, X0, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D11, [X11, X25,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D11, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434f68 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x348>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W26, W17, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W26	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434f68 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x348>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X1, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W25, [X13, X1,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D11, [X12, X1,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X5, X0, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D12, [X11, X5,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D12, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434f94 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x374>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W10, W17, W5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434f94 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x374>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X16, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W5, [X13, X16,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D12, [X12, X16,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X9, X0, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D13, [X11, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D13, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434fc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3a0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W25, W17, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434fc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3a0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X26, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W9, [X13, X26,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D13, [X12, X26,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X1, X0, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D15, [X11, X1,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D15, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434fec <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3cc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W5, W17, W1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434fec <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3cc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X10, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W1, [X13, X10,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D15, [X12, X10,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X9, X0, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D17, [X11, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D17, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 435018 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W16, W17, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 435018 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X25, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W9, [X13, X25,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D17, [X12, X25,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X0, X0, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W18, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.GT 434ebc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x29c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Function	miniqmcreference::TwoBodyJastrowRef >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
Source file and lines	BsplineFunctor.h:291-297
Module	exec

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 6561 paths individually, rerun with max-paths=6561
RecMII not computed since number of paths is unknown or > max_paths

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

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 11.25 to 5.33 cycles (2.11x speedup).

Workaround

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

Vectorization

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one:
- recompile with ftree-vectorize (included in O3) to enable loop vectorization (including FP reductions).
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop 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

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

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 64 bytes. The binary loop is storing 96 bytes.

General properties

nb instructions	90
loop length	360
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

11.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00
cycles	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.25
Overall L1	11.25

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 11.25 cycles. At this rate:

5% of peak load performance is reached (5.69 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
17% of peak store performance is reached (8.53 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 434ebc

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR D8, [X11, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434ee4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W25, W17, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434ee4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X26, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X13, X26,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D8, [X12, X26,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X0, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D9, [X11, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D9, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434f10 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W1, W17, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434f10 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X5, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X13, X5,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D9, [X12, X5,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X10, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D10, [X11, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D10, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434f3c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x31c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W16, W17, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434f3c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x31c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X9, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W10, [X13, X9,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D10, [X12, X9,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X25, X0, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D11, [X11, X25,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D11, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434f68 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x348>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W26, W17, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W26	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434f68 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x348>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X1, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W25, [X13, X1,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D11, [X12, X1,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X5, X0, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D12, [X11, X5,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D12, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434f94 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x374>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W10, W17, W5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434f94 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x374>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X16, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W5, [X13, X16,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D12, [X12, X16,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X9, X0, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D13, [X11, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D13, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434fc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3a0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W25, W17, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434fc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3a0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X26, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W9, [X13, X26,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D13, [X12, X26,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X1, X0, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D15, [X11, X1,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D15, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 434fec <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3cc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W5, W17, W1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 434fec <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3cc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X10, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W1, [X13, X10,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D15, [X12, X10,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X9, X0, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D17, [X11, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D17, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 435018 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W16, W17, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 435018 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X25, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W9, [X13, X25,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D17, [X12, X25,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X0, X0, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W18, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.GT 434ebc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x29c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code