OV - exec - Loop 679

	Loop Id: 679	Module: exec	Source: BsplineFunctor.h:305-336	Coverage: 0.01%

0x43c2c4 LDP	Q18, Q15, [X10], #32    [5]

0x43c2c8 MOVI	V20.4S, #2

0x43c2cc MOVI	V28.4S, #3

0x43c2d0 MOVI	V23.4S, #1

0x43c2d4 LDP	W2, W20, [X4, #4]    [14]

0x43c2d8 ADD	X4, X4, #16

0x43c2dc SBFM	X1, X2, #61, #31

0x43c2e0 SBFM	X5, X20, #61, #31

0x43c2e4 ADD	X17, X9, X1

0x43c2e8 ADD	X13, X1, X8

0x43c2ec FMUL	V19.2D, V18.2D, V6.2D

0x43c2f0 ADD	X3, X1, X7

0x43c2f4 FMUL	V31.2D, V15.2D, V6.2D

0x43c2f8 FDIV	V29.2D, V6.2D, V15.2D

0x43c2fc LDR	Q15, [SP, #224]    [4]

0x43c300 FDIV	V7.2D, V6.2D, V18.2D

0x43c304 FCVTZS	V16.2D, V19.2D

0x43c308 FCVTZS	V25.2D, V31.2D

0x43c30c STR	Q29, [SP, #512]    [4]

0x43c310 FRINTZ	V26.2D, V19.2D

0x43c314 FRINTZ	V29.2D, V31.2D

0x43c318 UZP1	V13.4S, V16.4S, V25.4S

0x43c31c FSUB	V30.2D, V19.2D, V26.2D

0x43c320 FSUB	V31.2D, V31.2D, V29.2D

0x43c324 ADD	V24.4S, V13.4S, V20.4S

0x43c328 ADD	V22.4S, V13.4S, V28.4S

0x43c32c ADD	V27.4S, V13.4S, V23.4S

0x43c330 SSHLL	V21.2D, V13.2S, #32

0x43c334 SSHLL2	V20.2D, V13.4S, #32

0x43c338 FMUL	V29.2D, V30.2D, V30.2D

0x43c33c SSHLL	V2.2D, V24.2S, #32

0x43c340 SSHLL	V14.2D, V22.2S, #32

0x43c344 FMOV	X6, D21

0x43c348 SSHLL2	V4.2D, V22.4S, #32

0x43c34c MOV	X21, V21.D[1]

0x43c350 SSHLL	V5.2D, V27.2S, #32

0x43c354 MOV	X18, V20.D[1]

0x43c358 MOV	X27, V2.D[1]

0x43c35c SSHLL2	V22.2D, V27.4S, #32

0x43c360 FMOV	X2, D14

0x43c364 SSHLL2	V3.2D, V24.4S, #32

0x43c368 MOV	X26, V4.D[1]

0x43c36c MOV	X1, V5.D[1]

0x43c370 MOV	X12, V14.D[1]

0x43c374 LDR	Q27, [SP, #640]    [4]

0x43c378 MOV	X30, V3.D[1]

0x43c37c LDR	D8, [X0, X27,LSL #3]    [8]

0x43c380 FMOV	X27, D4

0x43c384 LDR	D12, [X0, X2,LSL #3]    [8]

0x43c388 FMOV	X2, D5

0x43c38c LDP	Q5, Q4, [SP, #576]    [4]

0x43c390 ORR	V26.16B, V27.16B, V27.16B

0x43c394 FMOV	X16, D2

0x43c398 LDP	Q21, Q14, [SP, #608]    [4]

0x43c39c MOV	X20, V22.D[1]

0x43c3a0 LDR	D9, [X0, X12,LSL #3]    [8]

0x43c3a4 LDR	D18, [X0, X6,LSL #3]    [8]

0x43c3a8 FMOV	X6, D3

0x43c3ac LDP	Q19, Q24, [SP, #352]    [4]

0x43c3b0 ORR	V23.16B, V5.16B, V5.16B

0x43c3b4 LDR	D16, [X0, X1,LSL #3]    [8]

0x43c3b8 MOV	V12.D[1], V9.D[0]

0x43c3bc FMLA	V26.2D, V30.2D, V14.2D

0x43c3c0 ORR	V25.16B, V21.16B, V21.16B

0x43c3c4 LDR	D9, [X0, X30,LSL #3]    [8]

0x43c3c8 FMOV	X30, D20

0x43c3cc FMLA	V23.2D, V30.2D, V15.2D

0x43c3d0 LDR	D15, [X0, X2,LSL #3]    [8]

0x43c3d4 FMOV	X2, D22

0x43c3d8 LDR	D10, [X0, X16,LSL #3]    [8]

0x43c3dc FMLA	V25.2D, V30.2D, V4.2D

0x43c3e0 LDR	D13, [X0, X6,LSL #3]    [8]

0x43c3e4 FMLA	V26.2D, V29.2D, V24.2D

0x43c3e8 LDR	Q24, [SP, #368]    [4]

0x43c3ec MOV	V15.D[1], V16.D[0]

0x43c3f0 LDR	D28, [X0, X27,LSL #3]    [8]

0x43c3f4 MOV	V10.D[1], V8.D[0]

0x43c3f8 FMUL	V22.2D, V31.2D, V31.2D

0x43c3fc FMLA	V27.2D, V31.2D, V14.2D

0x43c400 LDR	D16, [X0, X26,LSL #3]    [8]

0x43c404 MOV	V13.D[1], V9.D[0]

0x43c408 LDR	D20, [X0, X30,LSL #3]    [8]

0x43c40c FMLA	V25.2D, V29.2D, V19.2D

0x43c410 LDR	D19, [X0, X2,LSL #3]    [8]

0x43c414 LDR	Q3, [SP, #352]    [4]

0x43c418 FMLA	V21.2D, V31.2D, V4.2D

0x43c41c MOV	V28.D[1], V16.D[0]

0x43c420 LDP	Q2, Q8, [SP, #544]    [4]

0x43c424 FMLA	V27.2D, V22.2D, V24.2D

0x43c428 LDURSW	X12, [X4, #496]    [13]

0x43c42c ORR	V24.16B, V5.16B, V5.16B

0x43c430 LDUR	W16, [X4, #508]    [13]

0x43c434 FMUL	V25.2D, V10.2D, V25.2D

0x43c438 FMLA	V21.2D, V22.2D, V3.2D

0x43c43c LDR	D4, [X0, X21,LSL #3]    [8]

0x43c440 UBFM	X6, X12, #61, #60

0x43c444 LDR	Q9, [SP, #224]    [4]

0x43c448 FMUL	V3.2D, V29.2D, V1.2D

0x43c44c ORR	V11.16B, V8.16B, V8.16B

0x43c450 SBFM	X1, X16, #61, #31

0x43c454 LDP	Q14, Q16, [SP, #320]    [4]

0x43c458 ADD	X27, X9, X1

0x43c45c ADD	X12, X1, X8

0x43c460 FMUL	V26.2D, V12.2D, V26.2D

0x43c464 ADD	X16, X1, X7

0x43c468 MOV	V18.D[1], V4.D[0]

0x43c46c LDR	Q4, [SP, #720]    [4]

0x43c470 FMLA	V11.2D, V30.2D, V2.2D

0x43c474 LDR	Q5, [SP, #448]    [4]

0x43c478 FMLA	V24.2D, V31.2D, V9.2D

0x43c47c LDR	D9, [X0, X20,LSL #3]    [8]

0x43c480 FMLA	V16.2D, V30.2D, V14.2D

0x43c484 ORR	V14.16B, V8.16B, V8.16B

0x43c488 MOV	V19.D[1], V9.D[0]

0x43c48c LDR	Q9, [SP, #304]    [4]

0x43c490 FMUL	V8.2D, V30.2D, V29.2D

0x43c494 FMUL	V11.2D, V10.2D, V11.2D

0x43c498 FMLA	V14.2D, V31.2D, V2.2D

0x43c49c FMLA	V16.2D, V29.2D, V9.2D

0x43c4a0 STR	Q11, [SP, #528]    [4]

0x43c4a4 LDR	Q11, [SP, #256]    [4]

0x43c4a8 FMUL	V2.2D, V29.2D, V4.2D

0x43c4ac FMUL	V4.2D, V22.2D, V4.2D

0x43c4b0 FMLA	V25.2D, V15.2D, V16.2D

0x43c4b4 LDR	Q16, [SP, #480]    [4]

0x43c4b8 FMLA	V2.2D, V8.2D, V5.2D

0x43c4bc LDR	D5, [X0, X18,LSL #3]    [8]

0x43c4c0 FMLA	V3.2D, V8.2D, V16.2D

0x43c4c4 LDP	Q9, Q16, [SP, #272]    [4]

0x43c4c8 MOV	V20.D[1], V5.D[0]

0x43c4cc LDR	Q5, [SP, #448]    [4]

0x43c4d0 FMUL	V23.2D, V12.2D, V23.2D

0x43c4d4 FMUL	V21.2D, V13.2D, V21.2D

0x43c4d8 FMUL	V14.2D, V13.2D, V14.2D

0x43c4dc FMUL	V24.2D, V28.2D, V24.2D

0x43c4e0 FMUL	V27.2D, V28.2D, V27.2D

0x43c4e4 FMLA	V16.2D, V30.2D, V9.2D

0x43c4e8 FMUL	V9.2D, V31.2D, V22.2D

0x43c4ec FMLA	V16.2D, V29.2D, V11.2D

0x43c4f0 FMLA	V4.2D, V9.2D, V5.2D

0x43c4f4 FMLA	V26.2D, V18.2D, V16.2D

0x43c4f8 LDP	Q16, Q11, [SP, #464]    [4]

0x43c4fc FMUL	V5.2D, V22.2D, V1.2D

0x43c500 FADD	V25.2D, V26.2D, V25.2D

0x43c504 FMLA	V5.2D, V9.2D, V11.2D

0x43c508 FMUL	V26.2D, V25.2D, V7.2D

0x43c50c LDR	Q7, [SP, #432]    [4]

0x43c510 ORR	V25.16B, V0.16B, V0.16B

0x43c514 FMLA	V25.2D, V30.2D, V16.2D

0x43c518 FMUL	V16.2D, V29.2D, V7.2D

0x43c51c LDP	Q11, Q7, [SP, #192]    [4]

0x43c520 FADD	V2.2D, V25.2D, V2.2D

0x43c524 FMLA	V7.2D, V30.2D, V11.2D

0x43c528 FMUL	V25.2D, V2.2D, V10.2D

0x43c52c LDR	Q10, [SP, #400]    [4]

0x43c530 LDR	Q2, [SP, #496]    [4]

0x43c534 FMUL	V29.2D, V29.2D, V10.2D

0x43c538 LDP	Q11, Q10, [SP, #416]    [4]

0x43c53c FMLA	V16.2D, V8.2D, V11.2D

0x43c540 LDR	Q11, [SP, #384]    [4]

0x43c544 FMLA	V29.2D, V8.2D, V11.2D

0x43c548 LDR	Q11, [SP, #528]    [4]

0x43c54c FMLA	V11.2D, V15.2D, V7.2D

0x43c550 LDP	Q7, Q8, [SP, #160]    [4]

0x43c554 FMLA	V8.2D, V30.2D, V7.2D

0x43c558 ORR	V7.16B, V17.16B, V17.16B

0x43c55c FMLA	V7.2D, V30.2D, V2.2D

0x43c560 LDR	Q2, [SP, #464]    [4]

0x43c564 FMLA	V23.2D, V18.2D, V8.2D

0x43c568 ORR	V8.16B, V0.16B, V0.16B

0x43c56c FMLA	V8.2D, V31.2D, V2.2D

0x43c570 FADD	V3.2D, V3.2D, V7.2D

0x43c574 FADD	V23.2D, V23.2D, V11.2D

0x43c578 FMUL	V11.2D, V22.2D, V10.2D

0x43c57c FMUL	V7.2D, V3.2D, V12.2D

0x43c580 LDR	Q12, [SP, #240]    [4]

0x43c584 FADD	V4.2D, V8.2D, V4.2D

0x43c588 LDP	Q10, Q8, [SP, #400]    [4]

0x43c58c FMUL	V23.2D, V23.2D, V12.2D

0x43c590 FMLA	V11.2D, V9.2D, V8.2D

0x43c594 STR	D23, [X9, X6]    [3]

0x43c598 LDR	Q12, [SP, #384]    [4]

0x43c59c FMUL	V8.2D, V13.2D, V4.2D

0x43c5a0 LDR	Q2, [SP, #496]    [4]

0x43c5a4 ST1	{V23.D[1]}, [X17]    [10]

0x43c5a8 LDP	Q13, Q3, [SP, #192]    [4]

0x43c5ac ORR	V23.16B, V17.16B, V17.16B

0x43c5b0 FMUL	V10.2D, V22.2D, V10.2D

0x43c5b4 FMLA	V23.2D, V31.2D, V2.2D

0x43c5b8 FMLA	V10.2D, V9.2D, V12.2D

0x43c5bc LDP	Q9, Q12, [SP, #304]    [4]

0x43c5c0 FMLA	V3.2D, V31.2D, V13.2D

0x43c5c4 LDP	Q4, Q13, [SP, #160]    [4]

0x43c5c8 FADD	V5.2D, V5.2D, V23.2D

0x43c5cc FMLA	V14.2D, V19.2D, V3.2D

0x43c5d0 LDP	Q3, Q2, [SP, #656]    [4]

0x43c5d4 FMUL	V28.2D, V28.2D, V5.2D

0x43c5d8 FMLA	V13.2D, V31.2D, V4.2D

0x43c5dc FMLA	V24.2D, V20.2D, V13.2D

0x43c5e0 LDR	Q13, [SP, #288]    [4]

0x43c5e4 FADD	V14.2D, V24.2D, V14.2D

0x43c5e8 LDR	Q24, [SP, #336]    [4]

0x43c5ec FMLA	V24.2D, V31.2D, V12.2D

0x43c5f0 FMLA	V24.2D, V22.2D, V9.2D

0x43c5f4 LDP	Q12, Q9, [SP, #256]    [4]

0x43c5f8 FMLA	V21.2D, V19.2D, V24.2D

0x43c5fc FMLA	V13.2D, V31.2D, V9.2D

0x43c600 FMLA	V13.2D, V22.2D, V12.2D

0x43c604 ORR	V22.16B, V2.16B, V2.16B

0x43c608 FMLA	V22.2D, V30.2D, V3.2D

0x43c60c FMLA	V27.2D, V20.2D, V13.2D

0x43c610 FADD	V29.2D, V29.2D, V22.2D

0x43c614 FMLA	V7.2D, V18.2D, V29.2D

0x43c618 FADD	V18.2D, V27.2D, V21.2D

0x43c61c LDR	Q21, [SP, #512]    [4]

0x43c620 LDP	Q27, Q13, [SP, #688]    [4]

0x43c624 ORR	V23.16B, V13.16B, V13.16B

0x43c628 FMLA	V13.2D, V31.2D, V27.2D

0x43c62c FMLA	V23.2D, V30.2D, V27.2D

0x43c630 ORR	V30.16B, V2.16B, V2.16B

0x43c634 FMLA	V30.2D, V31.2D, V3.2D

0x43c638 FADD	V31.2D, V11.2D, V13.2D

0x43c63c LDR	Q11, [SP, #240]    [4]

0x43c640 FADD	V16.2D, V16.2D, V23.2D

0x43c644 FMLA	V8.2D, V19.2D, V31.2D

0x43c648 FMLA	V25.2D, V15.2D, V16.2D

0x43c64c FADD	V15.2D, V10.2D, V30.2D

0x43c650 FMUL	V19.2D, V18.2D, V21.2D

0x43c654 FMLA	V28.2D, V20.2D, V15.2D

0x43c658 FADD	V20.2D, V25.2D, V7.2D

0x43c65c FMUL	V7.2D, V14.2D, V11.2D

0x43c660 STR	D7, [X9, X5]    [3]

0x43c664 FADD	V25.2D, V28.2D, V8.2D

0x43c668 ST1	{V7.D[1]}, [X27]    [11]

0x43c66c STR	D26, [X6, X8]    [2]

0x43c670 ST1	{V26.D[1]}, [X13]    [7]

0x43c674 STR	D19, [X5, X8]    [1]

0x43c678 ST1	{V19.D[1]}, [X12]    [6]

0x43c67c STR	D20, [X6, X7]    [2]

0x43c680 ST1	{V20.D[1]}, [X3]    [12]

0x43c684 STR	D25, [X5, X7]    [1]

0x43c688 ST1	{V25.D[1]}, [X16]    [9]

0x43c68c CMP	X4, X28

0x43c690 B.NE	43c2c4

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 305 - 336

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

305:     real_type r    = distArrayCompressed[j];

306:     int iScatter   = distIndices[j];

307:     real_type rinv = cOne / r;

308:     r *= DeltaRInv;

309:     int iGather   = (int)r;

310:     real_type t   = r - real_type(iGather);

311:     real_type tp0 = t * t * t;

312:     real_type tp1 = t * t;

313:     real_type tp2 = t;

314:

315:     real_type sCoef0 = SplineCoefs[iGather + 0];

316:     real_type sCoef1 = SplineCoefs[iGather + 1];

317:     real_type sCoef2 = SplineCoefs[iGather + 2];

318:     real_type sCoef3 = SplineCoefs[iGather + 3];

319:

320:     // clang-format off

321:     laplArray[iScatter] = dSquareDeltaRinv *

322:       (sCoef0*( d2A[ 2]*tp2 + d2A[ 3])+

323:        sCoef1*( d2A[ 6]*tp2 + d2A[ 7])+

324:        sCoef2*( d2A[10]*tp2 + d2A[11])+

325:        sCoef3*( d2A[14]*tp2 + d2A[15]));

326:

327:     gradArray[iScatter] = DeltaRInv * rinv *

328:       (sCoef0*( dA[ 1]*tp1 + dA[ 2]*tp2 + dA[ 3])+

329:        sCoef1*( dA[ 5]*tp1 + dA[ 6]*tp2 + dA[ 7])+

330:        sCoef2*( dA[ 9]*tp1 + dA[10]*tp2 + dA[11])+

331:        sCoef3*( dA[13]*tp1 + dA[14]*tp2 + dA[15]));

332:

333:     valArray[iScatter] = (sCoef0*(A[ 0]*tp0 + A[ 1]*tp1 + A[ 2]*tp2 + A[ 3])+

334:         sCoef1*(A[ 4]*tp0 + A[ 5]*tp1 + A[ 6]*tp2 + A[ 7])+

335:         sCoef2*(A[ 8]*tp0 + A[ 9]*tp1 + A[10]*tp2 + A[11])+

336:         sCoef3*(A[12]*tp0 + A[13]*tp1 + A[14]*tp2 + A[15]));

Coverage (%)	Name	Source Location	Module
►99.21+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:315	exec
○	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	refwrap.h:350	exec
○	gomp_thread_start	team.c:130	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 /

Metric	Value
CQA speedup if no scalar integer	1.05
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	1.06
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.39
Bottlenecks	P8, P9, P10, P11,
Function	miniqmcreference::TwoBodyJastrowRef >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
Source	BsplineFunctor.h:305-336
Source loop unroll info	multi-versionned
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	42.50
CQA cycles if no scalar integer	40.50
CQA cycles if FP arith vectorized	42.50
CQA cycles if fully vectorized	40.00
Front-end cycles	30.50
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	2.25
P3 cycles	2.25
P4 cycles	2.17
P5 cycles	2.17
P6 cycles	2.08
P7 cycles	2.08
P8 cycles	42.50
P9 cycles	42.50
P10 cycles	42.50
P11 cycles	42.50
P12 cycles	25.00
P13 cycles	25.00
P14 cycles	25.00
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	6.99 - 13.99
Inter-iter dependencies cycles	1
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	244.00
Nb uops	244.00
Nb loads	NA
Nb stores	14.00
Nb stack references	0.00
FLOP/cycle	7.15
Nb FLOP add-sub	32.00
Nb FLOP mul	60.00
Nb FLOP fma	104.00
Nb FLOP div	4.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	30.12
Bytes prefetched	0.00
Bytes loaded	1104.00
Bytes stored	176.00
Stride 0	2.00
Stride 1	1.00
Stride n	1.00
Stride unknown	8.00
Stride indirect	2.00
Vectorization ratio all	75.88
Vectorization ratio load	72.41
Vectorization ratio store	14.29
Vectorization ratio mul	100.00
Vectorization ratio add_sub	100.00
Vectorization ratio fma	100.00
Vectorization ratio div_sqrt	100.00
Vectorization ratio other	49.06
Vector-efficiency ratio all	85.86
Vector-efficiency ratio load	86.21
Vector-efficiency ratio store	57.14
Vector-efficiency ratio mul	100.00
Vector-efficiency ratio add_sub	100.00
Vector-efficiency ratio fma	100.00
Vector-efficiency ratio div_sqrt	100.00
Vector-efficiency ratio other	65.57

Metric	Value
CQA speedup if no scalar integer	1.05
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	1.06
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.39
Bottlenecks	P8, P9, P10, P11,
Function	miniqmcreference::TwoBodyJastrowRef >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
Source	BsplineFunctor.h:305-336
Source loop unroll info	multi-versionned
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	42.50
CQA cycles if no scalar integer	40.50
CQA cycles if FP arith vectorized	42.50
CQA cycles if fully vectorized	40.00
Front-end cycles	30.50
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	2.25
P3 cycles	2.25
P4 cycles	2.17
P5 cycles	2.17
P6 cycles	2.08
P7 cycles	2.08
P8 cycles	42.50
P9 cycles	42.50
P10 cycles	42.50
P11 cycles	42.50
P12 cycles	25.00
P13 cycles	25.00
P14 cycles	25.00
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	6.99 - 13.99
Inter-iter dependencies cycles	1
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	244.00
Nb uops	244.00
Nb loads	NA
Nb stores	14.00
Nb stack references	0.00
FLOP/cycle	7.15
Nb FLOP add-sub	32.00
Nb FLOP mul	60.00
Nb FLOP fma	104.00
Nb FLOP div	4.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	30.12
Bytes prefetched	0.00
Bytes loaded	1104.00
Bytes stored	176.00
Stride 0	2.00
Stride 1	1.00
Stride n	1.00
Stride unknown	8.00
Stride indirect	2.00
Vectorization ratio all	75.88
Vectorization ratio load	72.41
Vectorization ratio store	14.29
Vectorization ratio mul	100.00
Vectorization ratio add_sub	100.00
Vectorization ratio fma	100.00
Vectorization ratio div_sqrt	100.00
Vectorization ratio other	49.06
Vector-efficiency ratio all	85.86
Vector-efficiency ratio load	86.21
Vector-efficiency ratio store	57.14
Vector-efficiency ratio mul	100.00
Vector-efficiency ratio add_sub	100.00
Vector-efficiency ratio fma	100.00
Vector-efficiency ratio div_sqrt	100.00
Vector-efficiency ratio other	65.57

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:305-336
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:305-336.

The related source loop is multi-versionned.

gain
potential
hint
expert

Vectorization

Your loop is partially vectorized. 85% of vector register length is used (average across all VPU instructions). By fully vectorizing your loop, you can lower the cost of an iteration from 42.50 to 40.00 cycles (1.06x speedup).

Details

75% of VPU instructions are used in vector version (process two or more data elements in vector registers):

72% of VPU loads are used in vector version.
14% of VPU stores are used in vector version.
49% 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 loop can use their full power.

Workaround

Try another compiler or update/tune your current one
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)

FMA

Detected 104 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

Conversion instructions

Detected expensive conversion instructions.

Details

FCVTZS: 2 occurrences►
- /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:309
- /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:309

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

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

The binary loop is composed of 304 FP arithmetical operations:

136: addition or subtraction (104 inside FMA instructions)
164: multiply (104 inside FMA instructions)
4: divide

The binary loop is loading 1104 bytes. The binary loop is storing 176 bytes.

Arithmetic intensity

Arithmetic intensity is 0.24 FP operations per loaded or stored byte.

General properties

nb instructions	244
loop length	976
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

30.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	0.50	0.50	2.25	2.25	2.17	2.17	2.08	2.08	42.50	42.50	42.50	42.50	25.00	25.00	25.00	0.00	0.00
cycles	0.50	0.50	2.25	2.25	2.17	2.17	2.08	2.08	42.50	42.50	42.50	42.50	25.00	25.00	25.00	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions	6.99-13.99
Longest recurrence chain latency (RecMII)	1.00

Cycles summary

Front-end	30.50
Data deps.	1.00
Overall L1	42.50

Vectorization ratios

INT

all	59%
load	72%
store	14%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
other	53%

all	92%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	100%
add-sub	100%
fma	100%
div/sqrt	100%
other	33%

INT+FP

all	75%
load	72%
store	14%
mul	100%
add-sub	100%
fma	100%
div/sqrt	100%
other	49%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 42.50 cycles. At this rate:

27% of peak load performance is reached (25.98 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.14 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 43c2c4

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDP Q18, Q15, [X10], #32	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
MOVI V20.4S, #2	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (25.0%)
MOVI V28.4S, #3	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (25.0%)
MOVI V23.4S, #1	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (25.0%)
LDP W2, W20, [X4, #4]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ADD X4, X4, #16	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
SBFM X1, X2, #61, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
SBFM X5, X20, #61, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
ADD X17, X9, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
ADD X13, X1, X8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
FMUL V19.2D, V18.2D, V6.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
ADD X3, X1, X7	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
FMUL V31.2D, V15.2D, V6.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FDIV V29.2D, V6.2D, V15.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	7-15	3.50-6.99	vect (100.0%)
LDR Q15, [SP, #224]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FDIV V7.2D, V6.2D, V18.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	7-15	3.50-6.99	vect (100.0%)
FCVTZS V16.2D, V19.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
FCVTZS V25.2D, V31.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
STR Q29, [SP, #512]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
FRINTZ V26.2D, V19.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
FRINTZ V29.2D, V31.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
UZP1 V13.4S, V16.4S, V25.4S	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FSUB V30.2D, V19.2D, V26.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FSUB V31.2D, V31.2D, V29.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
ADD V24.4S, V13.4S, V20.4S	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
ADD V22.4S, V13.4S, V28.4S	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
ADD V27.4S, V13.4S, V23.4S	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
SSHLL V21.2D, V13.2S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
SSHLL2 V20.2D, V13.4S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
FMUL V29.2D, V30.2D, V30.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
SSHLL V2.2D, V24.2S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
SSHLL V14.2D, V22.2S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
FMOV X6, D21	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
SSHLL2 V4.2D, V22.4S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
MOV X21, V21.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
SSHLL V5.2D, V27.2S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
MOV X18, V20.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
MOV X27, V2.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
SSHLL2 V22.2D, V27.4S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
FMOV X2, D14	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
SSHLL2 V3.2D, V24.4S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
MOV X26, V4.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
MOV X1, V5.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
MOV X12, V14.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
LDR Q27, [SP, #640]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
MOV X30, V3.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
LDR D8, [X0, X27,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMOV X27, D4	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDR D12, [X0, X2,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMOV X2, D5	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDP Q5, Q4, [SP, #576]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ORR V26.16B, V27.16B, V27.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMOV X16, D2	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDP Q21, Q14, [SP, #608]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
MOV X20, V22.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
LDR D9, [X0, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
LDR D18, [X0, X6,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMOV X6, D3	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDP Q19, Q24, [SP, #352]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ORR V23.16B, V5.16B, V5.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR D16, [X0, X1,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
MOV V12.D[1], V9.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FMLA V26.2D, V30.2D, V14.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V25.16B, V21.16B, V21.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR D9, [X0, X30,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMOV X30, D20	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
FMLA V23.2D, V30.2D, V15.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D15, [X0, X2,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMOV X2, D22	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDR D10, [X0, X16,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMLA V25.2D, V30.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D13, [X0, X6,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMLA V26.2D, V29.2D, V24.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q24, [SP, #368]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
MOV V15.D[1], V16.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDR D28, [X0, X27,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
MOV V10.D[1], V8.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FMUL V22.2D, V31.2D, V31.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V27.2D, V31.2D, V14.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D16, [X0, X26,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
MOV V13.D[1], V9.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDR D20, [X0, X30,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMLA V25.2D, V29.2D, V19.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D19, [X0, X2,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
LDR Q3, [SP, #352]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V21.2D, V31.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
MOV V28.D[1], V16.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDP Q2, Q8, [SP, #544]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMLA V27.2D, V22.2D, V24.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDURSW X12, [X4, #496]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ORR V24.16B, V5.16B, V5.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDUR W16, [X4, #508]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
FMUL V25.2D, V10.2D, V25.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V21.2D, V22.2D, V3.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D4, [X0, X21,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
UBFM X6, X12, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
LDR Q9, [SP, #224]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V3.2D, V29.2D, V1.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
ORR V11.16B, V8.16B, V8.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
SBFM X1, X16, #61, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
LDP Q14, Q16, [SP, #320]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ADD X27, X9, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
ADD X12, X1, X8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
FMUL V26.2D, V12.2D, V26.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
ADD X16, X1, X7	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
MOV V18.D[1], V4.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDR Q4, [SP, #720]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V11.2D, V30.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q5, [SP, #448]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V24.2D, V31.2D, V9.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D9, [X0, X20,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMLA V16.2D, V30.2D, V14.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V14.16B, V8.16B, V8.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
MOV V19.D[1], V9.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDR Q9, [SP, #304]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V8.2D, V30.2D, V29.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V11.2D, V10.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V14.2D, V31.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V16.2D, V29.2D, V9.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
STR Q11, [SP, #528]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
LDR Q11, [SP, #256]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V2.2D, V29.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V4.2D, V22.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V25.2D, V15.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q16, [SP, #480]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V2.2D, V8.2D, V5.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D5, [X0, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMLA V3.2D, V8.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q9, Q16, [SP, #272]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
MOV V20.D[1], V5.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDR Q5, [SP, #448]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V23.2D, V12.2D, V23.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V21.2D, V13.2D, V21.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V14.2D, V13.2D, V14.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V24.2D, V28.2D, V24.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V27.2D, V28.2D, V27.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V16.2D, V30.2D, V9.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL V9.2D, V31.2D, V22.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V16.2D, V29.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V4.2D, V9.2D, V5.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V26.2D, V18.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q16, Q11, [SP, #464]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMUL V5.2D, V22.2D, V1.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FADD V25.2D, V26.2D, V25.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V5.2D, V9.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL V26.2D, V25.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDR Q7, [SP, #432]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
ORR V25.16B, V0.16B, V0.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V25.2D, V30.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL V16.2D, V29.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDP Q11, Q7, [SP, #192]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FADD V2.2D, V25.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V7.2D, V30.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL V25.2D, V2.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDR Q10, [SP, #400]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Q2, [SP, #496]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V29.2D, V29.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDP Q11, Q10, [SP, #416]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMLA V16.2D, V8.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q11, [SP, #384]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V29.2D, V8.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q11, [SP, #528]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V11.2D, V15.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q7, Q8, [SP, #160]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMLA V8.2D, V30.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V7.16B, V17.16B, V17.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V7.2D, V30.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q2, [SP, #464]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V23.2D, V18.2D, V8.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V8.16B, V0.16B, V0.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V8.2D, V31.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V3.2D, V3.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V23.2D, V23.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMUL V11.2D, V22.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V7.2D, V3.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDR Q12, [SP, #240]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V4.2D, V8.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDP Q10, Q8, [SP, #400]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMUL V23.2D, V23.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V11.2D, V9.2D, V8.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
STR D23, [X9, X6]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
LDR Q12, [SP, #384]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V8.2D, V13.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDR Q2, [SP, #496]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
ST1 {V23.D[1]}, [X17]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
LDP Q13, Q3, [SP, #192]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ORR V23.16B, V17.16B, V17.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMUL V10.2D, V22.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V23.2D, V31.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V10.2D, V9.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q9, Q12, [SP, #304]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMLA V3.2D, V31.2D, V13.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q4, Q13, [SP, #160]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FADD V5.2D, V5.2D, V23.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V14.2D, V19.2D, V3.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q3, Q2, [SP, #656]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMUL V28.2D, V28.2D, V5.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V13.2D, V31.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V24.2D, V20.2D, V13.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q13, [SP, #288]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V14.2D, V24.2D, V14.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR Q24, [SP, #336]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V24.2D, V31.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V24.2D, V22.2D, V9.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q12, Q9, [SP, #256]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMLA V21.2D, V19.2D, V24.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V13.2D, V31.2D, V9.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V13.2D, V22.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V22.16B, V2.16B, V2.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V22.2D, V30.2D, V3.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V27.2D, V20.2D, V13.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V29.2D, V29.2D, V22.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V7.2D, V18.2D, V29.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V18.2D, V27.2D, V21.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR Q21, [SP, #512]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDP Q27, Q13, [SP, #688]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ORR V23.16B, V13.16B, V13.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V13.2D, V31.2D, V27.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V23.2D, V30.2D, V27.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V30.16B, V2.16B, V2.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V30.2D, V31.2D, V3.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V31.2D, V11.2D, V13.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR Q11, [SP, #240]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V16.2D, V16.2D, V23.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V8.2D, V19.2D, V31.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V25.2D, V15.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V15.2D, V10.2D, V30.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMUL V19.2D, V18.2D, V21.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V28.2D, V20.2D, V15.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V20.2D, V25.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMUL V7.2D, V14.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
STR D7, [X9, X5]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
FADD V25.2D, V28.2D, V8.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
ST1 {V7.D[1]}, [X27]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
STR D26, [X6, X8]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
ST1 {V26.D[1]}, [X13]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
STR D19, [X5, X8]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
ST1 {V19.D[1]}, [X12]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
STR D20, [X6, X7]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
ST1 {V20.D[1]}, [X3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
STR D25, [X5, X7]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
ST1 {V25.D[1]}, [X16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
CMP X4, X28	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	N/A
B.NE 43c2c4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x624>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	miniqmcreference::TwoBodyJastrowRef >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
Source file and lines	BsplineFunctor.h:305-336
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:305-336.

The related source loop is multi-versionned.

gain
potential
hint
expert

Vectorization

Details

75% of VPU instructions are used in vector version (process two or more data elements in vector registers):

72% of VPU loads are used in vector version.
14% of VPU stores are used in vector version.
49% 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 loop can use their full power.

Workaround

Try another compiler or update/tune your current one
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)

FMA

Detected 104 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

Conversion instructions

Detected expensive conversion instructions.

Details

FCVTZS: 2 occurrences►
- /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:309
- /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:309

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

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

The binary loop is composed of 304 FP arithmetical operations:

136: addition or subtraction (104 inside FMA instructions)
164: multiply (104 inside FMA instructions)
4: divide

The binary loop is loading 1104 bytes. The binary loop is storing 176 bytes.

Arithmetic intensity

Arithmetic intensity is 0.24 FP operations per loaded or stored byte.

General properties

nb instructions	244
loop length	976
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

30.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	0.50	0.50	2.25	2.25	2.17	2.17	2.08	2.08	42.50	42.50	42.50	42.50	25.00	25.00	25.00	0.00	0.00
cycles	0.50	0.50	2.25	2.25	2.17	2.17	2.08	2.08	42.50	42.50	42.50	42.50	25.00	25.00	25.00	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions	6.99-13.99
Longest recurrence chain latency (RecMII)	1.00

Cycles summary

Front-end	30.50
Data deps.	1.00
Overall L1	42.50

Vectorization ratios

INT

all	59%
load	72%
store	14%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
other	53%

all	92%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	100%
add-sub	100%
fma	100%
div/sqrt	100%
other	33%

INT+FP

all	75%
load	72%
store	14%
mul	100%
add-sub	100%
fma	100%
div/sqrt	100%
other	49%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 42.50 cycles. At this rate:

27% of peak load performance is reached (25.98 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.14 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 43c2c4

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDP Q18, Q15, [X10], #32	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
MOVI V20.4S, #2	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (25.0%)
MOVI V28.4S, #3	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (25.0%)
MOVI V23.4S, #1	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (25.0%)
LDP W2, W20, [X4, #4]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ADD X4, X4, #16	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
SBFM X1, X2, #61, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
SBFM X5, X20, #61, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
ADD X17, X9, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
ADD X13, X1, X8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
FMUL V19.2D, V18.2D, V6.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
ADD X3, X1, X7	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
FMUL V31.2D, V15.2D, V6.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FDIV V29.2D, V6.2D, V15.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	7-15	3.50-6.99	vect (100.0%)
LDR Q15, [SP, #224]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FDIV V7.2D, V6.2D, V18.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	7-15	3.50-6.99	vect (100.0%)
FCVTZS V16.2D, V19.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
FCVTZS V25.2D, V31.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
STR Q29, [SP, #512]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
FRINTZ V26.2D, V19.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
FRINTZ V29.2D, V31.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
UZP1 V13.4S, V16.4S, V25.4S	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FSUB V30.2D, V19.2D, V26.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FSUB V31.2D, V31.2D, V29.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
ADD V24.4S, V13.4S, V20.4S	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
ADD V22.4S, V13.4S, V28.4S	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
ADD V27.4S, V13.4S, V23.4S	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
SSHLL V21.2D, V13.2S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
SSHLL2 V20.2D, V13.4S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
FMUL V29.2D, V30.2D, V30.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
SSHLL V2.2D, V24.2S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
SSHLL V14.2D, V22.2S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
FMOV X6, D21	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
SSHLL2 V4.2D, V22.4S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
MOV X21, V21.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
SSHLL V5.2D, V27.2S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
MOV X18, V20.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
MOV X27, V2.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
SSHLL2 V22.2D, V27.4S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
FMOV X2, D14	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
SSHLL2 V3.2D, V24.4S, #32	1	0	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	2	0.50	vect (50.0%)
MOV X26, V4.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
MOV X1, V5.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
MOV X12, V14.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
LDR Q27, [SP, #640]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
MOV X30, V3.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
LDR D8, [X0, X27,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMOV X27, D4	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDR D12, [X0, X2,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMOV X2, D5	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDP Q5, Q4, [SP, #576]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ORR V26.16B, V27.16B, V27.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMOV X16, D2	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDP Q21, Q14, [SP, #608]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
MOV X20, V22.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (50.0%)
LDR D9, [X0, X12,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
LDR D18, [X0, X6,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMOV X6, D3	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDP Q19, Q24, [SP, #352]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ORR V23.16B, V5.16B, V5.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR D16, [X0, X1,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
MOV V12.D[1], V9.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FMLA V26.2D, V30.2D, V14.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V25.16B, V21.16B, V21.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR D9, [X0, X30,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMOV X30, D20	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
FMLA V23.2D, V30.2D, V15.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D15, [X0, X2,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMOV X2, D22	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDR D10, [X0, X16,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMLA V25.2D, V30.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D13, [X0, X6,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMLA V26.2D, V29.2D, V24.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q24, [SP, #368]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
MOV V15.D[1], V16.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDR D28, [X0, X27,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
MOV V10.D[1], V8.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FMUL V22.2D, V31.2D, V31.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V27.2D, V31.2D, V14.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D16, [X0, X26,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
MOV V13.D[1], V9.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDR D20, [X0, X30,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMLA V25.2D, V29.2D, V19.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D19, [X0, X2,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
LDR Q3, [SP, #352]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V21.2D, V31.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
MOV V28.D[1], V16.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDP Q2, Q8, [SP, #544]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMLA V27.2D, V22.2D, V24.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDURSW X12, [X4, #496]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ORR V24.16B, V5.16B, V5.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDUR W16, [X4, #508]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
FMUL V25.2D, V10.2D, V25.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V21.2D, V22.2D, V3.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D4, [X0, X21,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
UBFM X6, X12, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
LDR Q9, [SP, #224]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V3.2D, V29.2D, V1.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
ORR V11.16B, V8.16B, V8.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
SBFM X1, X16, #61, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
LDP Q14, Q16, [SP, #320]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ADD X27, X9, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
ADD X12, X1, X8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
FMUL V26.2D, V12.2D, V26.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
ADD X16, X1, X7	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
MOV V18.D[1], V4.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDR Q4, [SP, #720]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V11.2D, V30.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q5, [SP, #448]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V24.2D, V31.2D, V9.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D9, [X0, X20,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMLA V16.2D, V30.2D, V14.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V14.16B, V8.16B, V8.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
MOV V19.D[1], V9.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDR Q9, [SP, #304]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V8.2D, V30.2D, V29.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V11.2D, V10.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V14.2D, V31.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V16.2D, V29.2D, V9.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
STR Q11, [SP, #528]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
LDR Q11, [SP, #256]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V2.2D, V29.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V4.2D, V22.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V25.2D, V15.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q16, [SP, #480]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V2.2D, V8.2D, V5.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR D5, [X0, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FMLA V3.2D, V8.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q9, Q16, [SP, #272]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
MOV V20.D[1], V5.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
LDR Q5, [SP, #448]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V23.2D, V12.2D, V23.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V21.2D, V13.2D, V21.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V14.2D, V13.2D, V14.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V24.2D, V28.2D, V24.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V27.2D, V28.2D, V27.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V16.2D, V30.2D, V9.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL V9.2D, V31.2D, V22.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V16.2D, V29.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V4.2D, V9.2D, V5.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V26.2D, V18.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q16, Q11, [SP, #464]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMUL V5.2D, V22.2D, V1.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FADD V25.2D, V26.2D, V25.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V5.2D, V9.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL V26.2D, V25.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDR Q7, [SP, #432]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
ORR V25.16B, V0.16B, V0.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V25.2D, V30.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL V16.2D, V29.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDP Q11, Q7, [SP, #192]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FADD V2.2D, V25.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V7.2D, V30.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL V25.2D, V2.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDR Q10, [SP, #400]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Q2, [SP, #496]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V29.2D, V29.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDP Q11, Q10, [SP, #416]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMLA V16.2D, V8.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q11, [SP, #384]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V29.2D, V8.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q11, [SP, #528]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V11.2D, V15.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q7, Q8, [SP, #160]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMLA V8.2D, V30.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V7.16B, V17.16B, V17.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V7.2D, V30.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q2, [SP, #464]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V23.2D, V18.2D, V8.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V8.16B, V0.16B, V0.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V8.2D, V31.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V3.2D, V3.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V23.2D, V23.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMUL V11.2D, V22.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V7.2D, V3.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDR Q12, [SP, #240]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V4.2D, V8.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDP Q10, Q8, [SP, #400]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMUL V23.2D, V23.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V11.2D, V9.2D, V8.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
STR D23, [X9, X6]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
LDR Q12, [SP, #384]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL V8.2D, V13.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDR Q2, [SP, #496]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
ST1 {V23.D[1]}, [X17]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
LDP Q13, Q3, [SP, #192]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ORR V23.16B, V17.16B, V17.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMUL V10.2D, V22.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V23.2D, V31.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V10.2D, V9.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q9, Q12, [SP, #304]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMLA V3.2D, V31.2D, V13.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q4, Q13, [SP, #160]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FADD V5.2D, V5.2D, V23.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V14.2D, V19.2D, V3.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q3, Q2, [SP, #656]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMUL V28.2D, V28.2D, V5.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V13.2D, V31.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V24.2D, V20.2D, V13.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q13, [SP, #288]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V14.2D, V24.2D, V14.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR Q24, [SP, #336]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V24.2D, V31.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V24.2D, V22.2D, V9.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q12, Q9, [SP, #256]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FMLA V21.2D, V19.2D, V24.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V13.2D, V31.2D, V9.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V13.2D, V22.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V22.16B, V2.16B, V2.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V22.2D, V30.2D, V3.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V27.2D, V20.2D, V13.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V29.2D, V29.2D, V22.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V7.2D, V18.2D, V29.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V18.2D, V27.2D, V21.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR Q21, [SP, #512]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDP Q27, Q13, [SP, #688]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ORR V23.16B, V13.16B, V13.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V13.2D, V31.2D, V27.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V23.2D, V30.2D, V27.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V30.16B, V2.16B, V2.16B	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V30.2D, V31.2D, V3.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V31.2D, V11.2D, V13.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR Q11, [SP, #240]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V16.2D, V16.2D, V23.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V8.2D, V19.2D, V31.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V25.2D, V15.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V15.2D, V10.2D, V30.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMUL V19.2D, V18.2D, V21.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA V28.2D, V20.2D, V15.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FADD V20.2D, V25.2D, V7.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMUL V7.2D, V14.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
STR D7, [X9, X5]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
FADD V25.2D, V28.2D, V8.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
ST1 {V7.D[1]}, [X27]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
STR D26, [X6, X8]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
ST1 {V26.D[1]}, [X13]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
STR D19, [X5, X8]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
ST1 {V19.D[1]}, [X12]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
STR D20, [X6, X7]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
ST1 {V20.D[1]}, [X3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
STR D25, [X5, X7]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
ST1 {V25.D[1]}, [X16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	4	1	scal (50.0%)
CMP X4, X28	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	N/A
B.NE 43c2c4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x624>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Report Configuration

Vectorization

Details

Workaround

FMA

Workaround

Conversion instructions

Details

Workaround

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Vectorization

Details

Workaround

FMA

Workaround

Conversion instructions

Details

Workaround

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code