OV - exec - Loop 298

	Loop Id: 298	Module: exec	Source: BsplineFunctor.h:305-336	Coverage: 0.03%

0x41a108 LDP	Q18, Q15, [X13], #32    [7]

0x41a10c MOVI	V24.4S, #3

0x41a110 MOVI	V26.4S, #2

0x41a114 MOVI	V28.4S, #1

0x41a118 LDP	W16, W24, [X4, #4]    [14]

0x41a11c ADD	X4, X4, #16

0x41a120 SBFM	X25, X16, #61, #31

0x41a124 SBFM	X5, X24, #61, #31

0x41a128 ADD	X23, X12, X25

0x41a12c ADD	X20, X25, X11

0x41a130 FMUL	V30.2D, V7.2D, V18.2D

0x41a134 ADD	X3, X25, X7

0x41a138 FMUL	V31.2D, V15.2D, V7.2D

0x41a13c FDIV	V29.2D, V7.2D, V15.2D

0x41a140 FDIV	V8.2D, V7.2D, V18.2D

0x41a144 FCVTZS	V19.2D, V30.2D

0x41a148 FCVTZS	V22.2D, V31.2D

0x41a14c STR	Q29, [SP, #448]    [3]

0x41a150 FRINTZ	V16.2D, V30.2D

0x41a154 FRINTZ	V29.2D, V31.2D

0x41a158 UZP1	V27.4S, V19.4S, V22.4S

0x41a15c FSUB	V30.2D, V30.2D, V16.2D

0x41a160 LDR	Q16, [SP, #320]    [3]

0x41a164 FSUB	V31.2D, V31.2D, V29.2D

0x41a168 ADD	V23.4S, V27.4S, V24.4S

0x41a16c SSHLL2	V9.2D, V27.4S, #32

0x41a170 ADD	V25.4S, V27.4S, V26.4S

0x41a174 ADD	V5.4S, V27.4S, V28.4S

0x41a178 SSHLL	V6.2D, V27.2S, #32

0x41a17c FMUL	V29.2D, V30.2D, V30.2D

0x41a180 SSHLL	V12.2D, V23.2S, #32

0x41a184 FMOV	X30, D9

0x41a188 SSHLL	V10.2D, V25.2S, #32

0x41a18c SSHLL2	V17.2D, V25.4S, #32

0x41a190 FMOV	X6, D6

0x41a194 SSHLL2	V21.2D, V23.4S, #32

0x41a198 MOV	X1, V12.D[1]

0x41a19c SSHLL	V22.2D, V5.2S, #32

0x41a1a0 FMOV	X16, D12

0x41a1a4 SSHLL2	V28.2D, V5.4S, #32

0x41a1a8 MOV	X18, V10.D[1]

0x41a1ac FMOV	X21, D10

0x41a1b0 LDR	D20, [X0, X30,LSL #3]    [9]

0x41a1b4 MOV	X30, V17.D[1]

0x41a1b8 MOV	X24, V21.D[1]

0x41a1bc LDR	D3, [X0, X1,LSL #3]    [9]

0x41a1c0 MOV	X25, V22.D[1]

0x41a1c4 LDR	D13, [X0, X16,LSL #3]    [9]

0x41a1c8 MOV	X16, V9.D[1]

0x41a1cc LDR	Q9, [SP, #592]    [3]

0x41a1d0 FMOV	X1, D21

0x41a1d4 LDR	D11, [X0, X21,LSL #3]    [9]

0x41a1d8 MOV	V13.D[1], V3.D[0]

0x41a1dc LDP	Q10, Q3, [SP, #560]    [3]

0x41a1e0 LDR	D2, [X0, X18,LSL #3]    [9]

0x41a1e4 ORR	V27.16B, V9.16B, V9.16B

0x41a1e8 MOV	X18, V6.D[1]

0x41a1ec LDR	D21, [X0, X30,LSL #3]    [9]

0x41a1f0 FMOV	X30, D22

0x41a1f4 LDR	D18, [X0, X6,LSL #3]    [9]

0x41a1f8 FMOV	X6, D17

0x41a1fc LDR	D22, [X0, X24,LSL #3]    [9]

0x41a200 FMLA	V27.2D, V30.2D, V3.2D

0x41a204 FMOV	X24, D28

0x41a208 LDR	D23, [X0, X1,LSL #3]    [9]

0x41a20c ORR	V26.16B, V10.16B, V10.16B

0x41a210 STP	D11, D2, [SP, #160]    [3]

0x41a214 LDP	Q2, Q4, [SP, #528]    [3]

0x41a218 FMLA	V27.2D, V29.2D, V16.2D

0x41a21c LDR	D15, [X0, X25,LSL #3]    [9]

0x41a220 MOV	V23.D[1], V22.D[0]

0x41a224 MOV	X25, V28.D[1]

0x41a228 ORR	V28.16B, V9.16B, V9.16B

0x41a22c LDR	D16, [X0, X30,LSL #3]    [9]

0x41a230 FMUL	V22.2D, V31.2D, V31.2D

0x41a234 LDP	Q11, Q6, [SP, #464]    [3]

0x41a238 FMLA	V28.2D, V31.2D, V3.2D

0x41a23c LDR	D9, [X0, X18,LSL #3]    [9]

0x41a240 LDR	D14, [X0, X6,LSL #3]    [9]

0x41a244 MOV	V16.D[1], V15.D[0]

0x41a248 FMLA	V10.2D, V31.2D, V4.2D

0x41a24c LDR	D19, [X0, X24,LSL #3]    [9]

0x41a250 LDP	Q17, Q5, [SP, #496]    [3]

0x41a254 MOV	V18.D[1], V9.D[0]

0x41a258 ORR	V25.16B, V11.16B, V11.16B

0x41a25c ORR	V12.16B, V6.16B, V6.16B

0x41a260 LDURSW	X21, [X4, #496]    [10]

0x41a264 FMLA	V10.2D, V22.2D, V2.2D

0x41a268 MOV	V14.D[1], V21.D[0]

0x41a26c LDUR	W1, [X4, #508]    [10]

0x41a270 FMLA	V26.2D, V30.2D, V4.2D

0x41a274 LDR	Q15, [SP, #320]    [3]

0x41a278 UBFM	X6, X21, #61, #60

0x41a27c LDR	Q4, [SP, #368]    [3]

0x41a280 FMUL	V9.2D, V30.2D, V29.2D

0x41a284 ORR	V24.16B, V5.16B, V5.16B

0x41a288 SBFM	X1, X1, #61, #31

0x41a28c FMLA	V26.2D, V29.2D, V2.2D

0x41a290 LDR	D2, [X0, X25,LSL #3]    [9]

0x41a294 ADD	X21, X12, X1

0x41a298 ADD	X18, X1, X11

0x41a29c FMLA	V28.2D, V22.2D, V15.2D

0x41a2a0 ORR	V15.16B, V6.16B, V6.16B

0x41a2a4 LDR	D6, [X0, X16,LSL #3]    [9]

0x41a2a8 ADD	X16, X1, X7

0x41a2ac FMLA	V24.2D, V30.2D, V17.2D

0x41a2b0 MOV	V19.D[1], V2.D[0]

0x41a2b4 FMLA	V15.2D, V31.2D, V25.2D

0x41a2b8 ORR	V25.16B, V5.16B, V5.16B

0x41a2bc MOV	V20.D[1], V6.D[0]

0x41a2c0 LDR	Q6, [SP, #272]    [3]

0x41a2c4 FMUL	V21.2D, V14.2D, V10.2D

0x41a2c8 LDP	Q3, Q10, [SP, #288]    [3]

0x41a2cc FMLA	V25.2D, V31.2D, V17.2D

0x41a2d0 LDP	Q5, Q17, [SP, #704]    [3]

0x41a2d4 FMLA	V12.2D, V30.2D, V11.2D

0x41a2d8 LDR	Q11, [SP, #160]    [3]

0x41a2dc FMUL	V27.2D, V13.2D, V27.2D

0x41a2e0 FMUL	V24.2D, V13.2D, V24.2D

0x41a2e4 FMLA	V10.2D, V30.2D, V3.2D

0x41a2e8 FMUL	V2.2D, V29.2D, V5.2D

0x41a2ec FMUL	V26.2D, V11.2D, V26.2D

0x41a2f0 FMLA	V10.2D, V29.2D, V6.2D

0x41a2f4 FMLA	V2.2D, V9.2D, V4.2D

0x41a2f8 LDP	Q4, Q6, [SP, #240]    [3]

0x41a2fc FMLA	V26.2D, V16.2D, V10.2D

0x41a300 FMUL	V12.2D, V11.2D, V12.2D

0x41a304 LDR	Q11, [SP, #736]    [3]

0x41a308 FMUL	V10.2D, V31.2D, V22.2D

0x41a30c FMUL	V15.2D, V14.2D, V15.2D

0x41a310 FMUL	V25.2D, V23.2D, V25.2D

0x41a314 FMLA	V6.2D, V30.2D, V4.2D

0x41a318 LDR	Q4, [SP, #224]    [3]

0x41a31c FMUL	V3.2D, V29.2D, V11.2D

0x41a320 FMUL	V28.2D, V23.2D, V28.2D

0x41a324 FMLA	V6.2D, V29.2D, V4.2D

0x41a328 FMUL	V4.2D, V22.2D, V5.2D

0x41a32c FMLA	V3.2D, V9.2D, V17.2D

0x41a330 FMLA	V27.2D, V18.2D, V6.2D

0x41a334 LDP	Q5, Q6, [SP, #368]    [3]

0x41a338 FADD	V27.2D, V27.2D, V26.2D

0x41a33c FMLA	V4.2D, V10.2D, V5.2D

0x41a340 ORR	V26.16B, V17.16B, V17.16B

0x41a344 LDR	Q17, [SP, #608]    [3]

0x41a348 FMUL	V5.2D, V22.2D, V11.2D

0x41a34c LDR	Q11, [SP, #192]    [3]

0x41a350 FMUL	V27.2D, V27.2D, V8.2D

0x41a354 ORR	V8.16B, V1.16B, V1.16B

0x41a358 FMLA	V5.2D, V10.2D, V26.2D

0x41a35c LDR	Q26, [SP, #400]    [3]

0x41a360 FMLA	V8.2D, V30.2D, V11.2D

0x41a364 LDR	Q11, [SP, #656]    [3]

0x41a368 FMLA	V26.2D, V30.2D, V6.2D

0x41a36c FMLA	V12.2D, V16.2D, V8.2D

0x41a370 LDR	Q8, [SP, #176]    [3]

0x41a374 FADD	V26.2D, V26.2D, V2.2D

0x41a378 LDP	Q2, Q6, [SP, #336]    [3]

0x41a37c FMUL	V6.2D, V29.2D, V6.2D

0x41a380 FMUL	V29.2D, V29.2D, V2.2D

0x41a384 FMLA	V6.2D, V9.2D, V11.2D

0x41a388 FMLA	V29.2D, V9.2D, V17.2D

0x41a38c ORR	V9.16B, V0.16B, V0.16B

0x41a390 FMLA	V9.2D, V30.2D, V8.2D

0x41a394 LDP	Q2, Q8, [SP, #416]    [3]

0x41a398 FMLA	V24.2D, V18.2D, V9.2D

0x41a39c FMLA	V8.2D, V30.2D, V2.2D

0x41a3a0 FADD	V24.2D, V24.2D, V12.2D

0x41a3a4 LDR	Q12, [SP, #352]    [3]

0x41a3a8 FADD	V3.2D, V8.2D, V3.2D

0x41a3ac FMUL	V12.2D, V22.2D, V12.2D

0x41a3b0 FMUL	V8.2D, V3.2D, V13.2D

0x41a3b4 LDP	Q13, Q9, [SP, #384]    [3]

0x41a3b8 FMLA	V12.2D, V10.2D, V11.2D

0x41a3bc LDP	Q3, Q2, [SP, #192]    [3]

0x41a3c0 FMLA	V9.2D, V31.2D, V13.2D

0x41a3c4 FMUL	V24.2D, V24.2D, V2.2D

0x41a3c8 STR	D24, [X12, X6]    [6]

0x41a3cc FADD	V4.2D, V9.2D, V4.2D

0x41a3d0 FMUL	V9.2D, V14.2D, V4.2D

0x41a3d4 LDR	Q14, [SP, #160]    [3]

0x41a3d8 ORR	V4.16B, V1.16B, V1.16B

0x41a3dc LDR	Q13, [SP, #336]    [3]

0x41a3e0 ST1	{V24.D[1]}, [X23]    [8]

0x41a3e4 FMLA	V4.2D, V31.2D, V3.2D

0x41a3e8 LDR	Q3, [SP, #176]    [3]

0x41a3ec FMUL	V26.2D, V26.2D, V14.2D

0x41a3f0 ORR	V14.16B, V0.16B, V0.16B

0x41a3f4 FMLA	V15.2D, V19.2D, V4.2D

0x41a3f8 FMLA	V14.2D, V31.2D, V3.2D

0x41a3fc LDR	Q3, [SP, #640]    [3]

0x41a400 FMUL	V11.2D, V22.2D, V13.2D

0x41a404 LDR	Q13, [SP, #304]    [3]

0x41a408 FMLA	V25.2D, V20.2D, V14.2D

0x41a40c FMLA	V11.2D, V10.2D, V17.2D

0x41a410 LDR	Q17, [SP, #208]    [3]

0x41a414 LDP	Q10, Q2, [SP, #272]    [3]

0x41a418 FADD	V15.2D, V25.2D, V15.2D

0x41a41c FMLA	V13.2D, V31.2D, V2.2D

0x41a420 FMUL	V25.2D, V15.2D, V17.2D

0x41a424 LDR	Q15, [SP, #224]    [3]

0x41a428 FMLA	V13.2D, V22.2D, V10.2D

0x41a42c ORR	V10.16B, V3.16B, V3.16B

0x41a430 STR	D25, [X12, X5]    [6]

0x41a434 ST1	{V25.D[1]}, [X21]    [5]

0x41a438 STR	D27, [X6, X11]    [2]

0x41a43c FMLA	V21.2D, V19.2D, V13.2D

0x41a440 ST1	{V27.D[1]}, [X20]    [4]

0x41a444 LDP	Q4, Q2, [SP, #240]    [3]

0x41a448 LDP	Q17, Q14, [SP, #672]    [3]

0x41a44c LDP	Q27, Q24, [SP, #416]    [3]

0x41a450 FMLA	V2.2D, V31.2D, V4.2D

0x41a454 FMLA	V24.2D, V31.2D, V27.2D

0x41a458 FMLA	V2.2D, V22.2D, V15.2D

0x41a45c ORR	V22.16B, V14.16B, V14.16B

0x41a460 FMLA	V14.2D, V31.2D, V17.2D

0x41a464 FMLA	V22.2D, V30.2D, V17.2D

0x41a468 FMLA	V28.2D, V20.2D, V2.2D

0x41a46c FADD	V12.2D, V14.2D, V12.2D

0x41a470 FADD	V5.2D, V24.2D, V5.2D

0x41a474 FADD	V6.2D, V22.2D, V6.2D

0x41a478 FMLA	V9.2D, V19.2D, V12.2D

0x41a47c LDR	Q19, [SP, #624]    [3]

0x41a480 FMLA	V26.2D, V16.2D, V6.2D

0x41a484 FMLA	V10.2D, V30.2D, V19.2D

0x41a488 ORR	V30.16B, V3.16B, V3.16B

0x41a48c FADD	V16.2D, V28.2D, V21.2D

0x41a490 LDR	Q28, [SP, #448]    [3]

0x41a494 FMUL	V23.2D, V23.2D, V5.2D

0x41a498 FMLA	V30.2D, V31.2D, V19.2D

0x41a49c FADD	V31.2D, V29.2D, V10.2D

0x41a4a0 FMUL	V29.2D, V16.2D, V28.2D

0x41a4a4 FADD	V21.2D, V30.2D, V11.2D

0x41a4a8 FMLA	V8.2D, V18.2D, V31.2D

0x41a4ac STR	D29, [X5, X11]    [1]

0x41a4b0 ST1	{V29.D[1]}, [X18]    [12]

0x41a4b4 FMLA	V23.2D, V20.2D, V21.2D

0x41a4b8 FADD	V18.2D, V26.2D, V8.2D

0x41a4bc FADD	V20.2D, V9.2D, V23.2D

0x41a4c0 STR	D18, [X6, X7]    [2]

0x41a4c4 ST1	{V18.D[1]}, [X3]    [13]

0x41a4c8 STR	D20, [X5, X7]    [1]

0x41a4cc ST1	{V20.D[1]}, [X16]    [11]

0x41a4d0 CMP	X28, X4

0x41a4d4 B.NE	41a108

/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
►99.01+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main._omp_fn.1	stl_vector.h:1128	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	1.41
Bottlenecks	P8, P9, P10, P11,
Function	miniqmcreference::TwoBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	BsplineFunctor.h:305-336
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	43.00
CQA cycles if no scalar integer	41.00
CQA cycles if FP arith vectorized	43.00
CQA cycles if fully vectorized	40.50
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	43.00
P9 cycles	43.00
P10 cycles	43.00
P11 cycles	43.00
P12 cycles	24.33
P13 cycles	24.33
P14 cycles	24.33
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	7.07
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	28.65
Bytes prefetched	0.00
Bytes loaded	1056.00
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	76.32
Vectorization ratio load	71.43
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	52.73
Vector-efficiency ratio all	86.07
Vector-efficiency ratio load	85.71
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	67.73

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	1.41
Bottlenecks	P8, P9, P10, P11,
Function	miniqmcreference::TwoBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	BsplineFunctor.h:305-336
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	43.00
CQA cycles if no scalar integer	41.00
CQA cycles if FP arith vectorized	43.00
CQA cycles if fully vectorized	40.50
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	43.00
P9 cycles	43.00
P10 cycles	43.00
P11 cycles	43.00
P12 cycles	24.33
P13 cycles	24.33
P14 cycles	24.33
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	7.07
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	28.65
Bytes prefetched	0.00
Bytes loaded	1056.00
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	76.32
Vectorization ratio load	71.43
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	52.73
Vector-efficiency ratio all	86.07
Vector-efficiency ratio load	85.71
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	67.73

Path /

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

Function	miniqmcreference::TwoBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
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 not unrolled or unrolled with no peel/tail loop.

gain
potential
hint
expert

Vectorization

Your loop is partially vectorized. 86% 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 43.00 to 40.50 cycles (1.06x speedup).

Details

76% of VPU instructions are used in vector version (process two or more data elements in vector registers):

71% of VPU loads are used in vector version.
14% of VPU stores are used in vector version.
52% 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 1056 bytes. The binary loop is storing 176 bytes.

Arithmetic intensity

Arithmetic intensity is 0.25 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	43.00	43.00	43.00	43.00	24.33	24.33	24.33	0.00	0.00
cycles	0.50	0.50	2.25	2.25	2.17	2.17	2.08	2.08	43.00	43.00	43.00	43.00	24.33	24.33	24.33	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	43.00

Vectorization ratios

INT

all	60%
load	71%
store	14%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
other	58%

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	76%
load	71%
store	14%
mul	100%
add-sub	100%
fma	100%
div/sqrt	100%
other	52%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 43.00 cycles. At this rate:

25% of peak load performance is reached (24.56 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.09 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 41a108

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, [X13], #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 V24.4S, #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 V26.4S, #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, #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 W16, W24, [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 X25, 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
SBFM X5, X24, #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 X23, X12, X25	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 X20, X25, X11	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 V30.2D, V7.2D, V18.2D	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, X25, 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, 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%)
FDIV V29.2D, V7.2D, 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%)
FDIV V8.2D, V7.2D, 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 V19.2D, V30.2D	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 V22.2D, 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, #448]	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 V16.2D, V30.2D	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 V27.4S, V19.4S, V22.4S	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, V30.2D, V16.2D	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 Q16, [SP, #320]	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%)
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 V23.4S, V27.4S, V24.4S	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%)
SSHLL2 V9.2D, 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%)
ADD V25.4S, V27.4S, V26.4S	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 V5.4S, V27.4S, 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%)
SSHLL V6.2D, 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%)
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 V12.2D, V23.2S, #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 X30, D9	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
SSHLL V10.2D, V25.2S, #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 V17.2D, V25.4S, #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 X6, D6	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
SSHLL2 V21.2D, V23.4S, #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 X1, V12.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 V22.2D, V5.2S, #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 X16, D12	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
SSHLL2 V28.2D, V5.4S, #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 X18, V10.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%)
FMOV X21, D10	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	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%)
MOV X30, V17.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 X24, 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%)
LDR D3, [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 X25, 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 D13, [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%)
MOV X16, V9.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 Q9, [SP, #592]	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%)
FMOV X1, D21	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDR D11, [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%)
MOV V13.D[1], V3.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 Q10, Q3, [SP, #560]	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%)
LDR D2, [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%)
ORR V27.16B, V9.16B, V9.16B	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 X18, V6.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 D21, [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, D22	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	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, D17	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDR D22, [X0, X24,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 V27.2D, 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%)
FMOV X24, D28	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDR D23, [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%)
ORR V26.16B, V10.16B, V10.16B	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%)
STP D11, D2, [SP, #160]	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%)
LDP Q2, Q4, [SP, #528]	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, V29.2D, 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 D15, [X0, X25,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 V23.D[1], V22.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%)
MOV X25, V28.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%)
ORR V28.16B, V9.16B, V9.16B	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, 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%)
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%)
LDP Q11, Q6, [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%)
FMLA V28.2D, 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%)
LDR D9, [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%)
LDR D14, [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%)
MOV V16.D[1], V15.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 V10.2D, 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%)
LDR D19, [X0, X24,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%)
LDP Q17, Q5, [SP, #496]	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 V18.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%)
ORR V25.16B, V11.16B, V11.16B	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%)
ORR V12.16B, V6.16B, V6.16B	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%)
LDURSW X21, [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
FMLA V10.2D, V22.2D, 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%)
MOV V14.D[1], V21.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%)
LDUR W1, [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
FMLA V26.2D, 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 Q15, [SP, #320]	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%)
UBFM X6, X21, #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 Q4, [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%)
FMUL V9.2D, 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%)
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%)
SBFM X1, X1, #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
FMLA V26.2D, V29.2D, 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 D2, [X0, X25,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%)
ADD X21, X12, 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 X18, X1, X11	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
FMLA V28.2D, V22.2D, 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%)
ORR V15.16B, V6.16B, V6.16B	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 D6, [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%)
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
FMLA V24.2D, V30.2D, V17.2D	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 V19.D[1], V2.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 V15.2D, V31.2D, V25.2D	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, 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%)
MOV V20.D[1], V6.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 Q6, [SP, #272]	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 V21.2D, V14.2D, 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 Q3, Q10, [SP, #288]	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 V25.2D, V31.2D, V17.2D	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 Q5, Q17, [SP, #704]	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 V12.2D, 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%)
LDR Q11, [SP, #160]	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 V27.2D, V13.2D, 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%)
FMUL V24.2D, V13.2D, 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%)
FMLA V10.2D, 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%)
FMUL V2.2D, V29.2D, 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%)
FMUL V26.2D, V11.2D, 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%)
FMLA V10.2D, V29.2D, V6.2D	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 V2.2D, V9.2D, 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%)
LDP Q4, Q6, [SP, #240]	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 V26.2D, V16.2D, V10.2D	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 V12.2D, V11.2D, 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 Q11, [SP, #736]	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 V10.2D, 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%)
FMUL V15.2D, V14.2D, V15.2D	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 V25.2D, V23.2D, 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 V6.2D, 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 Q4, [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, 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%)
FMUL V28.2D, V23.2D, V28.2D	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 V6.2D, V29.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL V4.2D, V22.2D, 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 V3.2D, V9.2D, V17.2D	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, V18.2D, V6.2D	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 Q5, Q6, [SP, #368]	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 V27.2D, V27.2D, 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%)
FMLA V4.2D, V10.2D, 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%)
ORR V26.16B, 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%)
LDR Q17, [SP, #608]	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 V5.2D, V22.2D, 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%)
LDR Q11, [SP, #192]	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 V27.2D, V27.2D, V8.2D	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 V8.16B, V1.16B, V1.16B	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 V5.2D, V10.2D, V26.2D	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 Q26, [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%)
FMLA V8.2D, 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%)
LDR Q11, [SP, #656]	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 V26.2D, V30.2D, V6.2D	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 V12.2D, V16.2D, 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%)
LDR Q8, [SP, #176]	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 V26.2D, V26.2D, 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%)
LDP Q2, Q6, [SP, #336]	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 V6.2D, V29.2D, 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%)
FMUL V29.2D, V29.2D, V2.2D	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 V6.2D, 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%)
FMLA V29.2D, V9.2D, V17.2D	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 V9.16B, 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 V9.2D, V30.2D, 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%)
LDP Q2, Q8, [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 V24.2D, V18.2D, 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 V8.2D, 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%)
FADD V24.2D, V24.2D, V12.2D	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 Q12, [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%)
FADD V3.2D, V8.2D, V3.2D	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 V12.2D, V22.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V8.2D, V3.2D, V13.2D	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 Q13, Q9, [SP, #384]	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 V12.2D, V10.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q3, Q2, [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%)
FMLA V9.2D, 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%)
FMUL V24.2D, V24.2D, V2.2D	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 D24, [X12, 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%)
FADD V4.2D, V9.2D, 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%)
FMUL V9.2D, V14.2D, 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 Q14, [SP, #160]	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 V4.16B, V1.16B, V1.16B	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 Q13, [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%)
ST1 {V24.D[1]}, [X23]	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%)
FMLA V4.2D, 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%)
LDR Q3, [SP, #176]	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 V26.2D, V26.2D, 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%)
ORR V14.16B, 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 V15.2D, V19.2D, 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 V14.2D, 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%)
LDR Q3, [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%)
FMUL V11.2D, V22.2D, V13.2D	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 Q13, [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%)
FMLA V25.2D, V20.2D, 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%)
FMLA V11.2D, V10.2D, V17.2D	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 Q17, [SP, #208]	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 Q10, Q2, [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%)
FADD V15.2D, V25.2D, V15.2D	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 V13.2D, 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%)
FMUL V25.2D, V15.2D, V17.2D	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 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%)
FMLA V13.2D, V22.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V10.16B, V3.16B, V3.16B	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%)
STR D25, [X12, 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%)
ST1 {V25.D[1]}, [X21]	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 D27, [X6, X11]	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%)
FMLA V21.2D, V19.2D, 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%)
ST1 {V27.D[1]}, [X20]	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 Q4, Q2, [SP, #240]	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%)
LDP Q17, Q14, [SP, #672]	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%)
LDP Q27, Q24, [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 V2.2D, 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, 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 V2.2D, V22.2D, 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%)
ORR V22.16B, V14.16B, V14.16B	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 V14.2D, V31.2D, V17.2D	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 V22.2D, V30.2D, V17.2D	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 V28.2D, V20.2D, 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 V12.2D, V14.2D, V12.2D	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 V5.2D, V24.2D, V5.2D	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 V6.2D, V22.2D, V6.2D	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 V9.2D, V19.2D, 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%)
LDR Q19, [SP, #624]	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 V26.2D, V16.2D, V6.2D	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, V30.2D, 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%)
ORR V30.16B, V3.16B, V3.16B	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%)
FADD V16.2D, V28.2D, 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 Q28, [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, V23.2D, 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 V30.2D, V31.2D, 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%)
FADD V31.2D, V29.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMUL V29.2D, V16.2D, V28.2D	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 V21.2D, V30.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V8.2D, V18.2D, 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%)
STR D29, [X5, X11]	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 {V29.D[1]}, [X18]	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%)
FMLA V23.2D, V20.2D, V21.2D	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, V26.2D, 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%)
FADD V20.2D, V9.2D, 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%)
STR D18, [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 {V18.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 D20, [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 {V20.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 X28, X4	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 41a108 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x648>	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 >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source file and lines	BsplineFunctor.h:305-336
Module	exec

gain
potential
hint
expert

Vectorization

Details

76% of VPU instructions are used in vector version (process two or more data elements in vector registers):

71% of VPU loads are used in vector version.
14% of VPU stores are used in vector version.
52% 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 1056 bytes. The binary loop is storing 176 bytes.

Arithmetic intensity

Arithmetic intensity is 0.25 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	43.00	43.00	43.00	43.00	24.33	24.33	24.33	0.00	0.00
cycles	0.50	0.50	2.25	2.25	2.17	2.17	2.08	2.08	43.00	43.00	43.00	43.00	24.33	24.33	24.33	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	43.00

Vectorization ratios

INT

all	60%
load	71%
store	14%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
other	58%

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	76%
load	71%
store	14%
mul	100%
add-sub	100%
fma	100%
div/sqrt	100%
other	52%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 43.00 cycles. At this rate:

25% of peak load performance is reached (24.56 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.09 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 41a108

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, [X13], #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 V24.4S, #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 V26.4S, #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, #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 W16, W24, [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 X25, 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
SBFM X5, X24, #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 X23, X12, X25	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 X20, X25, X11	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 V30.2D, V7.2D, V18.2D	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, X25, 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, 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%)
FDIV V29.2D, V7.2D, 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%)
FDIV V8.2D, V7.2D, 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 V19.2D, V30.2D	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 V22.2D, 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, #448]	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 V16.2D, V30.2D	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 V27.4S, V19.4S, V22.4S	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, V30.2D, V16.2D	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 Q16, [SP, #320]	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%)
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 V23.4S, V27.4S, V24.4S	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%)
SSHLL2 V9.2D, 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%)
ADD V25.4S, V27.4S, V26.4S	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 V5.4S, V27.4S, 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%)
SSHLL V6.2D, 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%)
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 V12.2D, V23.2S, #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 X30, D9	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
SSHLL V10.2D, V25.2S, #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 V17.2D, V25.4S, #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 X6, D6	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
SSHLL2 V21.2D, V23.4S, #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 X1, V12.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 V22.2D, V5.2S, #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 X16, D12	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
SSHLL2 V28.2D, V5.4S, #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 X18, V10.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%)
FMOV X21, D10	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	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%)
MOV X30, V17.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 X24, 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%)
LDR D3, [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 X25, 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 D13, [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%)
MOV X16, V9.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 Q9, [SP, #592]	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%)
FMOV X1, D21	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDR D11, [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%)
MOV V13.D[1], V3.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 Q10, Q3, [SP, #560]	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%)
LDR D2, [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%)
ORR V27.16B, V9.16B, V9.16B	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 X18, V6.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 D21, [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, D22	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	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, D17	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDR D22, [X0, X24,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 V27.2D, 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%)
FMOV X24, D28	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (50.0%)
LDR D23, [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%)
ORR V26.16B, V10.16B, V10.16B	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%)
STP D11, D2, [SP, #160]	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%)
LDP Q2, Q4, [SP, #528]	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, V29.2D, 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 D15, [X0, X25,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 V23.D[1], V22.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%)
MOV X25, V28.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%)
ORR V28.16B, V9.16B, V9.16B	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, 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%)
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%)
LDP Q11, Q6, [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%)
FMLA V28.2D, 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%)
LDR D9, [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%)
LDR D14, [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%)
MOV V16.D[1], V15.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 V10.2D, 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%)
LDR D19, [X0, X24,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%)
LDP Q17, Q5, [SP, #496]	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 V18.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%)
ORR V25.16B, V11.16B, V11.16B	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%)
ORR V12.16B, V6.16B, V6.16B	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%)
LDURSW X21, [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
FMLA V10.2D, V22.2D, 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%)
MOV V14.D[1], V21.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%)
LDUR W1, [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
FMLA V26.2D, 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 Q15, [SP, #320]	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%)
UBFM X6, X21, #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 Q4, [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%)
FMUL V9.2D, 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%)
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%)
SBFM X1, X1, #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
FMLA V26.2D, V29.2D, 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 D2, [X0, X25,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%)
ADD X21, X12, 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 X18, X1, X11	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
FMLA V28.2D, V22.2D, 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%)
ORR V15.16B, V6.16B, V6.16B	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 D6, [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%)
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
FMLA V24.2D, V30.2D, V17.2D	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 V19.D[1], V2.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 V15.2D, V31.2D, V25.2D	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, 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%)
MOV V20.D[1], V6.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 Q6, [SP, #272]	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 V21.2D, V14.2D, 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 Q3, Q10, [SP, #288]	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 V25.2D, V31.2D, V17.2D	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 Q5, Q17, [SP, #704]	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 V12.2D, 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%)
LDR Q11, [SP, #160]	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 V27.2D, V13.2D, 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%)
FMUL V24.2D, V13.2D, 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%)
FMLA V10.2D, 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%)
FMUL V2.2D, V29.2D, 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%)
FMUL V26.2D, V11.2D, 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%)
FMLA V10.2D, V29.2D, V6.2D	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 V2.2D, V9.2D, 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%)
LDP Q4, Q6, [SP, #240]	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 V26.2D, V16.2D, V10.2D	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 V12.2D, V11.2D, 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 Q11, [SP, #736]	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 V10.2D, 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%)
FMUL V15.2D, V14.2D, V15.2D	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 V25.2D, V23.2D, 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 V6.2D, 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 Q4, [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, 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%)
FMUL V28.2D, V23.2D, V28.2D	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 V6.2D, V29.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL V4.2D, V22.2D, 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 V3.2D, V9.2D, V17.2D	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, V18.2D, V6.2D	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 Q5, Q6, [SP, #368]	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 V27.2D, V27.2D, 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%)
FMLA V4.2D, V10.2D, 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%)
ORR V26.16B, 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%)
LDR Q17, [SP, #608]	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 V5.2D, V22.2D, 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%)
LDR Q11, [SP, #192]	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 V27.2D, V27.2D, V8.2D	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 V8.16B, V1.16B, V1.16B	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 V5.2D, V10.2D, V26.2D	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 Q26, [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%)
FMLA V8.2D, 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%)
LDR Q11, [SP, #656]	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 V26.2D, V30.2D, V6.2D	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 V12.2D, V16.2D, 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%)
LDR Q8, [SP, #176]	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 V26.2D, V26.2D, 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%)
LDP Q2, Q6, [SP, #336]	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 V6.2D, V29.2D, 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%)
FMUL V29.2D, V29.2D, V2.2D	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 V6.2D, 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%)
FMLA V29.2D, V9.2D, V17.2D	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 V9.16B, 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 V9.2D, V30.2D, 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%)
LDP Q2, Q8, [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 V24.2D, V18.2D, 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 V8.2D, 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%)
FADD V24.2D, V24.2D, V12.2D	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 Q12, [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%)
FADD V3.2D, V8.2D, V3.2D	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 V12.2D, V22.2D, V12.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL V8.2D, V3.2D, V13.2D	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 Q13, Q9, [SP, #384]	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 V12.2D, V10.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q3, Q2, [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%)
FMLA V9.2D, 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%)
FMUL V24.2D, V24.2D, V2.2D	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 D24, [X12, 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%)
FADD V4.2D, V9.2D, 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%)
FMUL V9.2D, V14.2D, 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 Q14, [SP, #160]	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 V4.16B, V1.16B, V1.16B	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 Q13, [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%)
ST1 {V24.D[1]}, [X23]	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%)
FMLA V4.2D, 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%)
LDR Q3, [SP, #176]	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 V26.2D, V26.2D, 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%)
ORR V14.16B, 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 V15.2D, V19.2D, 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 V14.2D, 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%)
LDR Q3, [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%)
FMUL V11.2D, V22.2D, V13.2D	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 Q13, [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%)
FMLA V25.2D, V20.2D, 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%)
FMLA V11.2D, V10.2D, V17.2D	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 Q17, [SP, #208]	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 Q10, Q2, [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%)
FADD V15.2D, V25.2D, V15.2D	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 V13.2D, 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%)
FMUL V25.2D, V15.2D, V17.2D	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 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%)
FMLA V13.2D, V22.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
ORR V10.16B, V3.16B, V3.16B	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%)
STR D25, [X12, 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%)
ST1 {V25.D[1]}, [X21]	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 D27, [X6, X11]	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%)
FMLA V21.2D, V19.2D, 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%)
ST1 {V27.D[1]}, [X20]	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 Q4, Q2, [SP, #240]	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%)
LDP Q17, Q14, [SP, #672]	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%)
LDP Q27, Q24, [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 V2.2D, 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, 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 V2.2D, V22.2D, 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%)
ORR V22.16B, V14.16B, V14.16B	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 V14.2D, V31.2D, V17.2D	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 V22.2D, V30.2D, V17.2D	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 V28.2D, V20.2D, 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 V12.2D, V14.2D, V12.2D	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 V5.2D, V24.2D, V5.2D	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 V6.2D, V22.2D, V6.2D	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 V9.2D, V19.2D, 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%)
LDR Q19, [SP, #624]	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 V26.2D, V16.2D, V6.2D	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, V30.2D, 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%)
ORR V30.16B, V3.16B, V3.16B	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%)
FADD V16.2D, V28.2D, 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 Q28, [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, V23.2D, 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 V30.2D, V31.2D, 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%)
FADD V31.2D, V29.2D, V10.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMUL V29.2D, V16.2D, V28.2D	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 V21.2D, V30.2D, V11.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA V8.2D, V18.2D, 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%)
STR D29, [X5, X11]	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 {V29.D[1]}, [X18]	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%)
FMLA V23.2D, V20.2D, V21.2D	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, V26.2D, 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%)
FADD V20.2D, V9.2D, 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%)
STR D18, [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 {V18.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 D20, [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 {V20.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 X28, X4	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 41a108 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x648>	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