OV - exec - Loop 321

	Loop Id: 321	Module: exec	Source: TwoBodyJastrowRef.h:125-127 [...]	Coverage: 0.02%

0x41a3a0 ORR	W17, WZR, W10

0x41a3a4 LDR	W10, [X14, X11,LSL #2]

0x41a3a8 LDR	X18, [X13, X11,LSL #3]

0x41a3ac CMP	W10, W17

0x41a3b0 B.LE	41a854

0x41a3b4 SUB	W3, W10, W17

0x41a3b8 SBFM	X4, X17, #0, #31

0x41a3bc ADD	X1, X15, W17,SXTW #3

0x41a3c0 ANDS	W6, W3, #128

0x41a3c4 ORR	W7, WZR, W17

0x41a3c8 LDR	D0, [X18, #8]

0x41a3cc MOVZ	W5, #0

0x41a3d0 B.EQ	41a4f8

0x41a3d4 CMP	W6, #1

0x41a3d8 B.EQ	41a4cc

0x41a3dc CMP	W6, #2

0x41a3e0 B.EQ	41a4a8

0x41a3e4 CMP	W6, #3

0x41a3e8 B.EQ	41a484

0x41a3ec CMP	W6, #4

0x41a3f0 B.EQ	41a460

0x41a3f4 CMP	W6, #5

0x41a3f8 B.EQ	41a43c

0x41a3fc CMP	W6, #6

0x41a400 B.EQ	41a418

0x41a404 LDR	D1, [X15, X4,LSL #3]

0x41a408 FCMPE	D1, D0

0x41a40c B.MI	41a890

0x41a410 ADD	X1, X1, #8

0x41a414 ADD	W7, W17, #1

0x41a418 LDR	D2, [X1]

0x41a41c FCMPE	D2, D0

0x41a420 B.GE	41a434

0x41a424 CMP	W2, W7

0x41a428 B.EQ	41a434

0x41a42c STR	D2, [X9, X5,SXTW #3]

0x41a430 ADD	W5, W5, #1

0x41a434 ADD	X1, X1, #8

0x41a438 ADD	W7, W7, #1

0x41a43c LDR	D3, [X1]

0x41a440 FCMPE	D3, D0

0x41a444 B.GE	41a458

0x41a448 CMP	W2, W7

0x41a44c B.EQ	41a458

0x41a450 STR	D3, [X9, X5,SXTW #3]

0x41a454 ADD	W5, W5, #1

0x41a458 ADD	X1, X1, #8

0x41a45c ADD	W7, W7, #1

0x41a460 LDR	D4, [X1]

0x41a464 FCMPE	D4, D0

0x41a468 B.GE	41a47c

0x41a46c CMP	W2, W7

0x41a470 B.EQ	41a47c

0x41a474 STR	D4, [X9, X5,SXTW #3]

0x41a478 ADD	W5, W5, #1

0x41a47c ADD	X1, X1, #8

0x41a480 ADD	W7, W7, #1

0x41a484 LDR	D5, [X1]

0x41a488 FCMPE	D5, D0

0x41a48c B.GE	41a4a0

0x41a490 CMP	W2, W7

0x41a494 B.EQ	41a4a0

0x41a498 STR	D5, [X9, X5,SXTW #3]

0x41a49c ADD	W5, W5, #1

0x41a4a0 ADD	X1, X1, #8

0x41a4a4 ADD	W7, W7, #1

0x41a4a8 LDR	D6, [X1]

0x41a4ac FCMPE	D6, D0

0x41a4b0 B.GE	41a4c4

0x41a4b4 CMP	W2, W7

0x41a4b8 B.EQ	41a4c4

0x41a4bc STR	D6, [X9, X5,SXTW #3]

0x41a4c0 ADD	W5, W5, #1

0x41a4c4 ADD	X1, X1, #8

0x41a4c8 ADD	W7, W7, #1

0x41a4cc LDR	D7, [X1]

0x41a4d0 FCMPE	D7, D0

0x41a4d4 B.GE	41a4e8

0x41a4d8 CMP	W2, W7

0x41a4dc B.EQ	41a4e8

0x41a4e0 STR	D7, [X9, X5,SXTW #3]

0x41a4e4 ADD	W5, W5, #1

0x41a4e8 ADD	W7, W7, #1

0x41a4ec ADD	X1, X1, #8

0x41a4f0 CMP	W10, W7

0x41a4f4 B.EQ	41a608

  (322) 0x41a4f8 LDR	D8, [X1]

  (322) 0x41a4fc FCMPE	D8, D0

  (322) 0x41a500 B.GE	41a514

  (322) 0x41a504 CMP	W2, W7

  (322) 0x41a508 B.EQ	41a514

  (322) 0x41a50c STR	D8, [X9, X5,SXTW #3]

  (322) 0x41a510 ADD	W5, W5, #1

  (322) 0x41a514 LDR	D9, [X1, #8]

  (322) 0x41a518 ADD	W7, W7, #1

  (322) 0x41a51c ADD	X1, X1, #8

  (322) 0x41a520 FCMPE	D9, D0

  (322) 0x41a524 B.GE	41a538

  (322) 0x41a528 CMP	W2, W7

  (322) 0x41a52c B.EQ	41a538

  (322) 0x41a530 STR	D9, [X9, X5,SXTW #3]

  (322) 0x41a534 ADD	W5, W5, #1

  (322) 0x41a538 LDR	D10, [X1, #8]

  (322) 0x41a53c ADD	W8, W7, #1

  (322) 0x41a540 FCMPE	D10, D0

  (322) 0x41a544 B.GE	41a558

  (322) 0x41a548 CMP	W2, W8

  (322) 0x41a54c B.EQ	41a558

  (322) 0x41a550 STR	D10, [X9, X5,SXTW #3]

  (322) 0x41a554 ADD	W5, W5, #1

  (322) 0x41a558 LDR	D11, [X1, #16]

  (322) 0x41a55c ADD	W17, W7, #2

  (322) 0x41a560 FCMPE	D11, D0

  (322) 0x41a564 B.GE	41a578

  (322) 0x41a568 CMP	W2, W17

  (322) 0x41a56c B.EQ	41a578

  (322) 0x41a570 STR	D11, [X9, X5,SXTW #3]

  (322) 0x41a574 ADD	W5, W5, #1

  (322) 0x41a578 LDR	D12, [X1, #24]

  (322) 0x41a57c ADD	W3, W7, #3

  (322) 0x41a580 FCMPE	D12, D0

  (322) 0x41a584 B.GE	41a598

  (322) 0x41a588 CMP	W2, W3

  (322) 0x41a58c B.EQ	41a598

  (322) 0x41a590 STR	D12, [X9, X5,SXTW #3]

  (322) 0x41a594 ADD	W5, W5, #1

  (322) 0x41a598 LDR	D13, [X1, #32]

  (322) 0x41a59c ADD	W4, W7, #4

  (322) 0x41a5a0 FCMPE	D13, D0

  (322) 0x41a5a4 B.GE	41a5b8

  (322) 0x41a5a8 CMP	W2, W4

  (322) 0x41a5ac B.EQ	41a5b8

  (322) 0x41a5b0 STR	D13, [X9, X5,SXTW #3]

  (322) 0x41a5b4 ADD	W5, W5, #1

  (322) 0x41a5b8 LDR	D14, [X1, #40]

  (322) 0x41a5bc ADD	W6, W7, #5

  (322) 0x41a5c0 FCMPE	D14, D0

  (322) 0x41a5c4 B.GE	41a5d8

  (322) 0x41a5c8 CMP	W2, W6

  (322) 0x41a5cc B.EQ	41a5d8

  (322) 0x41a5d0 STR	D14, [X9, X5,SXTW #3]

  (322) 0x41a5d4 ADD	W5, W5, #1

  (322) 0x41a5d8 LDR	D15, [X1, #48]

  (322) 0x41a5dc ADD	W8, W7, #6

  (322) 0x41a5e0 FCMPE	D15, D0

  (322) 0x41a5e4 B.GE	41a5f8

  (322) 0x41a5e8 CMP	W2, W8

  (322) 0x41a5ec B.EQ	41a5f8

  (322) 0x41a5f0 STR	D15, [X9, X5,SXTW #3]

  (322) 0x41a5f4 ADD	W5, W5, #1

  (322) 0x41a5f8 ADD	W7, W7, #7

  (322) 0x41a5fc ADD	X1, X1, #56

  (322) 0x41a600 CMP	W10, W7

  (322) 0x41a604 B.NE	41a4f8

0x41a608 CBZ	W5, 41a854

0x41a854 ADD	X5, X11, #1

0x41a858 CMP	X12, X11

0x41a85c B.EQ	41a868

0x41a860 ORR	X11, XZR, X5

0x41a864 B	41a3a0

0x41a890 CMP	W2, W17

0x41a894 B.EQ	41a410

0x41a898 MOVZ	W5, #1

0x41a89c STR	D1, [X9]

0x41a8a0 B	41a410

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 232 - 246

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

232:   int iCount       = 0;

233:   const int iLimit = iEnd - iStart;

234:

235: #pragma vector always

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

237:   {

238:     real_type r = distArray[jat];

239:     // pick the distances smaller than the cutoff and avoid the reference atom

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

241:       distArrayCompressed[iCount++] = distArray[jat];

242:   }

243:

244:   real_type d = 0.0;

245:   //#pragma omp simd reduction(+:d)

246:   for (int jat = 0; jat < iCount; jat++)

/usr/include/c++/11/bits/stl_vector.h: 1043 - 1043

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

1043:       operator[](size_type __n) _GLIBCXX_NOEXCEPT

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 125 - 127

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

125:     for (int jg = 0; jg < NumGroups; ++jg)

126:     {

127:       const FuncType& f2(*F[igt + jg]);

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 305 - 305

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

305:   inline int last(int igroup) const { return SubPtcl[igroup + 1]; }

Coverage (%)	Name	Source Location	Module
►50.00+	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
►50.00+	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	2.61
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	7.65
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.11
Bottlenecks	P0, P1,
Function	miniqmcreference::TwoBodyJastrowRef >::ratio(qmcplusplus::ParticleSet&, int)
Source	BsplineFunctor.h:232-232,BsplineFunctor.h:236-241,BsplineFunctor.h:246-246,stl_vector.h:1043-1043,TwoBodyJastrowRef.h:125-127,ParticleSet.h:305-305
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	13.50
CQA cycles if no scalar integer	5.17
CQA cycles if FP arith vectorized	13.50
CQA cycles if fully vectorized	1.77
Front-end cycles	12.13
DIV/SQRT cycles	13.50
P0 cycles	13.50
P1 cycles	11.50
P2 cycles	11.50
P3 cycles	11.50
P4 cycles	11.50
P5 cycles	7.00
P6 cycles	7.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	5.83
P10 cycles	5.50
P11 cycles	5.67
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	97.00
Nb uops	97.00
Nb loads	NA
Nb stores	7.00
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	9.78
Bytes prefetched	0.00
Bytes loaded	76.00
Bytes stored	56.00
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	17.50
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	13.24

Metric	Value
CQA speedup if no scalar integer	2.61
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	7.65
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.11
Bottlenecks	P0, P1,
Function	miniqmcreference::TwoBodyJastrowRef >::ratio(qmcplusplus::ParticleSet&, int)
Source	BsplineFunctor.h:232-232,BsplineFunctor.h:236-241,BsplineFunctor.h:246-246,stl_vector.h:1043-1043,TwoBodyJastrowRef.h:125-127,ParticleSet.h:305-305
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	13.50
CQA cycles if no scalar integer	5.17
CQA cycles if FP arith vectorized	13.50
CQA cycles if fully vectorized	1.77
Front-end cycles	12.13
DIV/SQRT cycles	13.50
P0 cycles	13.50
P1 cycles	11.50
P2 cycles	11.50
P3 cycles	11.50
P4 cycles	11.50
P5 cycles	7.00
P6 cycles	7.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	5.83
P10 cycles	5.50
P11 cycles	5.67
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	97.00
Nb uops	97.00
Nb loads	NA
Nb stores	7.00
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	9.78
Bytes prefetched	0.00
Bytes loaded	76.00
Bytes stored	56.00
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	17.50
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	13.24

Path /

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

Function	miniqmcreference::TwoBodyJastrowRef >::ratio(qmcplusplus::ParticleSet&, int)
Source file and lines	TwoBodyJastrowRef.h:125-127
Module	exec

The loop is defined in:

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:232-246
/usr/include/c++/11/bits/stl_vector.h:1043
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:125-127
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:305

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths
RecMII not computed since number of paths is unknown or > max_paths

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 13.50 to 5.17 cycles (2.61x 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 17% of vector register length is used (average across all VPU instructions). By vectorizing your loop, you can lower the cost of an iteration from 13.50 to 1.77 cycles (7.65x 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 76 bytes. The binary loop is storing 56 bytes.

General properties

nb instructions	97
loop length	388
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

12.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	13.50	13.50	11.50	11.50	11.50	11.50	7.00	7.00	0.00	0.00	5.83	5.50	5.67	0.00	0.00
cycles	13.50	13.50	11.50	11.50	11.50	11.50	7.00	7.00	0.00	0.00	5.83	5.50	5.67	0.00	0.00

Cycles executing div or sqrt instructions

Cycles summary

Front-end	12.13
Overall L1	13.50

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 13.50 cycles. At this rate:

5% of peak load performance is reached (5.63 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.15 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 41a854

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	Latency	Recip. throughput
ORR W17, WZR, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR W10, [X14, X11,LSL #2]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33
LDR X18, [X13, X11,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33
CMP W10, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.LE 41a854 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
SUB W3, W10, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
SBFM X4, X17, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X15, W17,SXTW #3	1	0	0	0	0	0.50	0.50	0	0	0	0	0	2	0.50
ANDS W6, W3, #128	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
ORR W7, WZR, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D0, [X18, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
MOVZ W5, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
B.EQ 41a4f8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x1b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a4cc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x18c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a4a8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x168>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a484 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x144>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a460 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x120>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a43c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xfc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a418 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xd8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDR D1, [X15, X4,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D1, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.MI 41a890 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x550>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D2, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D2, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a434 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xf4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a434 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xf4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D2, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D3, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D3, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a458 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x118>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a458 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x118>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D3, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D4, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D4, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a47c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a47c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D4, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D5, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D5, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a4a0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x160>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a4a0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x160>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D5, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D6, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D6, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a4c4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x184>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a4c4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x184>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D6, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D7, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D7, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a4e8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x1a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a4e8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x1a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D7, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
CMP W10, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a608 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x2c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CBZ W5, 41a854 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ADD X5, X11, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
CMP X12, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a868 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x528>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ORR X11, XZR, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
B 41a3a0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x60>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a410 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xd0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
MOVZ W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR D1, [X9]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
B 41a410 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xd0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50

Function	miniqmcreference::TwoBodyJastrowRef >::ratio(qmcplusplus::ParticleSet&, int)
Source file and lines	TwoBodyJastrowRef.h:125-127
Module	exec

The loop is defined in:

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:232-246
/usr/include/c++/11/bits/stl_vector.h:1043
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:125-127
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:305

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths
RecMII not computed since number of paths is unknown or > max_paths

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 13.50 to 5.17 cycles (2.61x 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 76 bytes. The binary loop is storing 56 bytes.

General properties

nb instructions	97
loop length	388
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

12.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	13.50	13.50	11.50	11.50	11.50	11.50	7.00	7.00	0.00	0.00	5.83	5.50	5.67	0.00	0.00
cycles	13.50	13.50	11.50	11.50	11.50	11.50	7.00	7.00	0.00	0.00	5.83	5.50	5.67	0.00	0.00

Cycles executing div or sqrt instructions

Cycles summary

Front-end	12.13
Overall L1	13.50

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 13.50 cycles. At this rate:

5% of peak load performance is reached (5.63 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.15 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 41a854

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	Latency	Recip. throughput
ORR W17, WZR, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR W10, [X14, X11,LSL #2]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33
LDR X18, [X13, X11,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33
CMP W10, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.LE 41a854 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
SUB W3, W10, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
SBFM X4, X17, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X15, W17,SXTW #3	1	0	0	0	0	0.50	0.50	0	0	0	0	0	2	0.50
ANDS W6, W3, #128	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
ORR W7, WZR, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D0, [X18, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
MOVZ W5, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
B.EQ 41a4f8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x1b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a4cc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x18c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a4a8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x168>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a484 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x144>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a460 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x120>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a43c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xfc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W6, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a418 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xd8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
LDR D1, [X15, X4,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D1, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.MI 41a890 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x550>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D2, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D2, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a434 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xf4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a434 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xf4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D2, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D3, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D3, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a458 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x118>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a458 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x118>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D3, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D4, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D4, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a47c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a47c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D4, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D5, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D5, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a4a0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x160>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a4a0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x160>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D5, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D6, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D6, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a4c4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x184>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a4c4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x184>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D6, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D7, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D7, D0	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.GE 41a4e8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x1a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a4e8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x1a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D7, [X9, X5,SXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W5, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
CMP W10, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a608 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x2c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CBZ W5, 41a854 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ADD X5, X11, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
CMP X12, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a868 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x528>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
ORR X11, XZR, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
B 41a3a0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0x60>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMP W2, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 41a410 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xd0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
MOVZ W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
STR D1, [X9]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
B 41a410 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE5ratioERNS1_11ParticleSetEi+0xd0>	1	0.50	0.50	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