OV - exec - Loop 306

	Loop Id: 306	Module: exec	Source: BsplineFunctor.h:302-336 [...]	Coverage: 0.04%

0x4170c0 LDP	Q0, Q2, [X2], #32    [19]

0x4170c4 ORR	V27.16B, V24.16B, V24.16B

0x4170c8 SUBS	X1, X1, #4

0x4170cc FMUL	V1.2D, V0.2D, V29.D[0]

0x4170d0 STP	Q2, Q0, [SP, #560]    [12]

0x4170d4 FMUL	V2.2D, V2.2D, V29.D[0]

0x4170d8 LDR	Q31, [SP, #192]    [12]

0x4170dc LDP	Q11, Q15, [SP, #240]    [12]

0x4170e0 LDR	Q30, [SP, #432]    [12]

0x4170e4 LDP	Q0, Q17, [SP, #352]    [12]

0x4170e8 LDR	Q20, [SP, #400]    [12]

0x4170ec FCVTZS	V5.2D, V1.2D

0x4170f0 FCVTZS	V4.2D, V2.2D

0x4170f4 FRINTZ	V16.2D, V2.2D

0x4170f8 XTN	V6.2S, V5.2D

0x4170fc XTN	V4.2S, V4.2D

0x417100 FRINTZ	V5.2D, V1.2D

0x417104 FSUB	V9.2D, V2.2D, V16.2D

0x417108 MOV	W3, V6.S[1]

0x41710c FMOV	W5, S6

0x417110 MOV	W4, V4.S[1]

0x417114 FMUL	V13.2D, V9.2D, V9.2D

0x417118 FSUB	V23.2D, V1.2D, V5.2D

0x41711c LDP	Q2, Q1, [SP, #592]    [12]

0x417120 SBFM	X6, X3, #61, #31

0x417124 FMOV	W3, S4

0x417128 LDR	D18, [X11, X5,SXTW #3]    [14]

0x41712c LDR	D19, [X12, X5,SXTW #3]    [15]

0x417130 LDP	Q3, Q4, [SP, #304]    [12]

0x417134 SBFM	X4, X4, #61, #31

0x417138 ADD	X7, X11, X6

0x41713c ADD	X19, X11, X4

0x417140 FMUL	V28.2D, V13.2D, V9.2D

0x417144 FMUL	V5.2D, V23.2D, V23.2D

0x417148 LDR	D22, [X11, X3,SXTW #3]    [14]

0x41714c LDR	D21, [X12, X3,SXTW #3]    [15]

0x417150 ORR	V6.16B, V4.16B, V4.16B

0x417154 FMLA	V4.2D, V9.2D, V24.D[0]

0x417158 FMUL	V26.2D, V5.2D, V23.2D

0x41715c FMLA	V6.2D, V23.2D, V24.D[0]

0x417160 ORR	V24.16B, V3.16B, V3.16B

0x417164 ORR	V16.16B, V3.16B, V3.16B

0x417168 ORR	V3.16B, V7.16B, V7.16B

0x41716c ORR	V7.16B, V10.16B, V10.16B

0x417170 LDP	Q12, Q10, [SP, #704]    [12]

0x417174 LD1	{V18.D[1]}, [X7]    [9]

0x417178 ADD	X7, X12, X6

0x41717c LD1	{V19.D[1]}, [X7]    [8]

0x417180 ADD	X7, X12, X4

0x417184 FMLA	V24.2D, V9.2D, V17.D[0]

0x417188 FMLA	V16.2D, V23.2D, V17.D[0]

0x41718c LDR	Q17, [SP, #464]    [12]

0x417190 LD1	{V22.D[1]}, [X19]    [23]

0x417194 LD1	{V21.D[1]}, [X7]    [7]

0x417198 ADD	X19, X13, X6

0x41719c ADD	X7, X13, X4

0x4171a0 ADD	X6, X14, X6

0x4171a4 ADD	X4, X14, X4

0x4171a8 FMUL	V6.2D, V6.2D, V18.2D

0x4171ac FMLA	V6.2D, V16.2D, V19.2D

0x4171b0 FMUL	V16.2D, V13.2D, V10.D[0]

0x4171b4 FMUL	V4.2D, V4.2D, V22.2D

0x4171b8 FMLA	V16.2D, V9.2D, V12.D[0]

0x4171bc FMLA	V4.2D, V24.2D, V21.2D

0x4171c0 FMUL	V24.2D, V28.2D, V2.D[0]

0x4171c4 FMLA	V24.2D, V13.2D, V1.D[0]

0x4171c8 FMLA	V24.2D, V9.2D, V17.D[0]

0x4171cc FADD	V16.2D, V16.2D, V15.2D

0x4171d0 FMUL	V16.2D, V16.2D, V22.2D

0x4171d4 FADD	V24.2D, V24.2D, V31.2D

0x4171d8 FMUL	V22.2D, V24.2D, V22.2D

0x4171dc FMUL	V24.2D, V13.2D, V30.D[0]

0x4171e0 FMLA	V24.2D, V9.2D, V0.D[0]

0x4171e4 FADD	V24.2D, V24.2D, V11.2D

0x4171e8 FMLA	V16.2D, V24.2D, V21.2D

0x4171ec FMUL	V24.2D, V28.2D, V20.D[0]

0x4171f0 FMLA	V24.2D, V13.2D, V25.D[0]

0x4171f4 FMLA	V24.2D, V9.2D, V14.D[0]

0x4171f8 FADD	V24.2D, V24.2D, V8.2D

0x4171fc FMLA	V22.2D, V24.2D, V21.2D

0x417200 FMUL	V21.2D, V5.2D, V10.D[0]

0x417204 FMUL	V24.2D, V5.2D, V30.D[0]

0x417208 FMLA	V21.2D, V23.2D, V12.D[0]

0x41720c FMLA	V24.2D, V23.2D, V0.D[0]

0x417210 LDR	Q0, [SP, #336]    [12]

0x417214 FADD	V21.2D, V21.2D, V15.2D

0x417218 FADD	V24.2D, V24.2D, V11.2D

0x41721c LDR	Q15, [SP, #288]    [12]

0x417220 LDR	Q11, [SP, #224]    [12]

0x417224 LDP	Q12, Q10, [SP, #672]    [12]

0x417228 FMUL	V21.2D, V21.2D, V18.2D

0x41722c FMLA	V21.2D, V24.2D, V19.2D

0x417230 FMUL	V24.2D, V26.2D, V2.D[0]

0x417234 FMLA	V24.2D, V5.2D, V1.D[0]

0x417238 LDR	Q1, [SP, #736]    [12]

0x41723c FMLA	V24.2D, V23.2D, V17.D[0]

0x417240 LDR	Q17, [SP, #448]    [12]

0x417244 FADD	V24.2D, V24.2D, V31.2D

0x417248 FMUL	V18.2D, V24.2D, V18.2D

0x41724c FMUL	V24.2D, V26.2D, V20.D[0]

0x417250 LDP	Q31, Q30, [SP, #640]    [12]

0x417254 LDR	Q20, [SP, #160]    [12]

0x417258 FMLA	V24.2D, V5.2D, V25.D[0]

0x41725c FMLA	V24.2D, V23.2D, V14.D[0]

0x417260 FADD	V24.2D, V24.2D, V8.2D

0x417264 FMLA	V18.2D, V24.2D, V19.2D

0x417268 LDR	D19, [X13, X5,SXTW #3]    [16]

0x41726c ORR	V24.16B, V15.16B, V15.16B

0x417270 FMLA	V15.2D, V9.2D, V30.D[0]

0x417274 FMLA	V24.2D, V23.2D, V30.D[0]

0x417278 LD1	{V19.D[1]}, [X19]    [22]

0x41727c FMLA	V6.2D, V24.2D, V19.2D

0x417280 FMUL	V24.2D, V5.2D, V0.D[0]

0x417284 FMLA	V24.2D, V23.2D, V31.D[0]

0x417288 FADD	V24.2D, V24.2D, V11.2D

0x41728c FMLA	V21.2D, V24.2D, V19.2D

0x417290 FMUL	V24.2D, V26.2D, V17.D[0]

0x417294 FMLA	V24.2D, V5.2D, V12.D[0]

0x417298 FMLA	V24.2D, V23.2D, V10.D[0]

0x41729c FADD	V24.2D, V24.2D, V20.2D

0x4172a0 FMLA	V18.2D, V24.2D, V19.2D

0x4172a4 LDR	D19, [X13, X3,SXTW #3]    [16]

0x4172a8 FMUL	V24.2D, V13.2D, V0.D[0]

0x4172ac FMLA	V24.2D, V9.2D, V31.D[0]

0x4172b0 FADD	V24.2D, V24.2D, V11.2D

0x4172b4 LDR	Q11, [SP, #208]    [12]

0x4172b8 LD1	{V19.D[1]}, [X7]    [6]

0x4172bc FMLA	V16.2D, V24.2D, V19.2D

0x4172c0 FMUL	V24.2D, V28.2D, V17.D[0]

0x4172c4 FMLA	V4.2D, V15.2D, V19.2D

0x4172c8 LDR	Q17, [SP, #384]    [12]

0x4172cc FMLA	V24.2D, V13.2D, V12.D[0]

0x4172d0 FMLA	V24.2D, V9.2D, V10.D[0]

0x4172d4 ORR	V10.16B, V7.16B, V7.16B

0x4172d8 ORR	V7.16B, V3.16B, V3.16B

0x4172dc LDR	Q3, [SP, #272]    [12]

0x4172e0 FADD	V24.2D, V24.2D, V20.2D

0x4172e4 FMLA	V22.2D, V24.2D, V19.2D

0x4172e8 LDR	D19, [X14, X5,SXTW #3]    [17]

0x4172ec ORR	V24.16B, V3.16B, V3.16B

0x4172f0 FMLA	V24.2D, V23.2D, V17.D[0]

0x4172f4 LD1	{V19.D[1]}, [X6]    [2]

0x4172f8 FMLA	V6.2D, V24.2D, V19.2D

0x4172fc FMUL	V24.2D, V5.2D, V7.D[0]

0x417300 FMLA	V24.2D, V23.2D, V10.D[0]

0x417304 FADD	V24.2D, V24.2D, V11.2D

0x417308 FMLA	V21.2D, V24.2D, V19.2D

0x41730c ORR	V24.16B, V27.16B, V27.16B

0x417310 LDP	Q27, Q0, [SP, #752]    [12]

0x417314 FMUL	V2.2D, V26.2D, V0.D[0]

0x417318 FMLA	V2.2D, V5.2D, V27.D[0]

0x41731c FMLA	V2.2D, V23.2D, V1.D[0]

0x417320 LDP	Q23, Q0, [SP, #128]    [12]

0x417324 FADD	V1.2D, V2.2D, V0.2D

0x417328 ORR	V2.16B, V3.16B, V3.16B

0x41732c LDP	Q5, Q3, [SP, #560]    [12]

0x417330 FMLA	V18.2D, V1.2D, V19.2D

0x417334 LDR	D1, [X14, X3,SXTW #3]    [17]

0x417338 FMLA	V2.2D, V9.2D, V17.D[0]

0x41733c LD1	{V1.D[1]}, [X4]    [24]

0x417340 FMLA	V4.2D, V2.2D, V1.2D

0x417344 FMUL	V2.2D, V6.2D, V23.D[0]

0x417348 LDPSW	W3, W4, [X0, #504]    [18]

0x41734c ADD	X5, X10, X4,LSL #3

0x417350 STR	D18, [X8, X3,LSL #3]    [10]

0x417354 STR	D2, [X10, X3,LSL #3]    [13]

0x417358 ST1	{V2.D[1]}, [X5]    [1]

0x41735c FMUL	V2.2D, V4.2D, V23.D[0]

0x417360 FMUL	V4.2D, V21.2D, V29.D[0]

0x417364 FDIV	V4.2D, V4.2D, V3.2D

0x417368 LDPSW	W5, W6, [X0], #16    [18]

0x41736c ADD	X7, X10, X6,LSL #3

0x417370 STR	D2, [X10, X5,LSL #3]    [13]

0x417374 ST1	{V2.D[1]}, [X7]    [5]

0x417378 FMUL	V2.2D, V13.2D, V7.D[0]

0x41737c ADD	X7, X9, X4,LSL #3

0x417380 FMLA	V2.2D, V9.2D, V10.D[0]

0x417384 FADD	V2.2D, V2.2D, V11.2D

0x417388 FMLA	V16.2D, V2.2D, V1.2D

0x41738c FMUL	V2.2D, V16.2D, V29.D[0]

0x417390 FDIV	V2.2D, V2.2D, V5.2D

0x417394 STR	D4, [X9, X3,LSL #3]    [11]

0x417398 ST1	{V4.D[1]}, [X7]    [4]

0x41739c ADD	X7, X9, X6,LSL #3

0x4173a0 ADD	X3, X8, X4,LSL #3

0x4173a4 ST1	{V18.D[1]}, [X3]    [21]

0x4173a8 ADD	X3, X8, X6,LSL #3

0x4173ac STR	D2, [X9, X5,LSL #3]    [11]

0x4173b0 ST1	{V2.D[1]}, [X7]    [3]

0x4173b4 LDP	Q4, Q2, [SP, #752]    [12]

0x4173b8 FMUL	V2.2D, V28.2D, V2.D[0]

0x4173bc FMLA	V2.2D, V13.2D, V4.D[0]

0x4173c0 LDR	Q4, [SP, #736]    [12]

0x4173c4 FMLA	V2.2D, V9.2D, V4.D[0]

0x4173c8 FADD	V2.2D, V2.2D, V0.2D

0x4173cc FMLA	V22.2D, V2.2D, V1.2D

0x4173d0 STR	D22, [X8, X5,LSL #3]    [10]

0x4173d4 ST1	{V22.D[1]}, [X3]    [20]

0x4173d8 B.NE	4170c0

/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h: 1150 - 1150

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

1150: 	return *(this->_M_impl._M_start + __n);

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 302 - 336

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

302:   #pragma omp simd

303:   for (int j = 0; j < iCount; j++)

304:   {

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];

[...]

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
►66.07+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►28.76+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►4.99+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:421	exec
○	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:411	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so

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	1.01
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	1.07
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.46
Bottlenecks	P8, P9, P10, P11,
Function	qmcplusplus::BsplineFunctor::evaluateVGL(int, int, int, double const, double, double, double, double, int) const
Source	stl_vector.h:1150-1150,BsplineFunctor.h:302-315,BsplineFunctor.h:321-336
Source loop unroll info	unrolled by 4
Source loop unroll confidence level	medium
Unroll/vectorization loop type	NA
Unroll factor	4
CQA cycles	36.25
CQA cycles if no scalar integer	35.75
CQA cycles if FP arith vectorized	36.25
CQA cycles if fully vectorized	33.75
Front-end cycles	24.88
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	3.42
P3 cycles	3.42
P4 cycles	3.33
P5 cycles	3.33
P6 cycles	3.25
P7 cycles	3.25
P8 cycles	36.25
P9 cycles	36.25
P10 cycles	36.25
P11 cycles	36.25
P12 cycles	19.17
P13 cycles	18.83
P14 cycles	19.00
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	6.99 - 13.99
Inter-iter dependencies cycles	4
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	199.00
Nb uops	199.00
Nb loads	NA
Nb stores	13.00
Nb stack references	0.00
FLOP/cycle	8.39
Nb FLOP add-sub	36.00
Nb FLOP mul	64.00
Nb FLOP fma	100.00
Nb FLOP div	4.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	25.60
Bytes prefetched	0.00
Bytes loaded	752.00
Bytes stored	176.00
Stride 0	3.00
Stride 1	0.00
Stride n	0.00
Stride unknown	14.00
Stride indirect	7.00
Vectorization ratio all	81.67
Vectorization ratio load	61.90
Vectorization ratio store	7.69
Vectorization ratio mul	100.00
Vectorization ratio add_sub	94.74
Vectorization ratio fma	100.00
Vectorization ratio div_sqrt	100.00
Vectorization ratio other	81.82
Vector-efficiency ratio all	90.28
Vector-efficiency ratio load	80.95
Vector-efficiency ratio store	53.85
Vector-efficiency ratio mul	100.00
Vector-efficiency ratio add_sub	97.37
Vector-efficiency ratio fma	100.00
Vector-efficiency ratio div_sqrt	100.00
Vector-efficiency ratio other	86.36

Metric	Value
CQA speedup if no scalar integer	1.01
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	1.07
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.46
Bottlenecks	P8, P9, P10, P11,
Function	qmcplusplus::BsplineFunctor::evaluateVGL(int, int, int, double const, double, double, double, double, int) const
Source	stl_vector.h:1150-1150,BsplineFunctor.h:302-315,BsplineFunctor.h:321-336
Source loop unroll info	unrolled by 4
Source loop unroll confidence level	medium
Unroll/vectorization loop type	NA
Unroll factor	4
CQA cycles	36.25
CQA cycles if no scalar integer	35.75
CQA cycles if FP arith vectorized	36.25
CQA cycles if fully vectorized	33.75
Front-end cycles	24.88
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	3.42
P3 cycles	3.42
P4 cycles	3.33
P5 cycles	3.33
P6 cycles	3.25
P7 cycles	3.25
P8 cycles	36.25
P9 cycles	36.25
P10 cycles	36.25
P11 cycles	36.25
P12 cycles	19.17
P13 cycles	18.83
P14 cycles	19.00
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	6.99 - 13.99
Inter-iter dependencies cycles	4
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	199.00
Nb uops	199.00
Nb loads	NA
Nb stores	13.00
Nb stack references	0.00
FLOP/cycle	8.39
Nb FLOP add-sub	36.00
Nb FLOP mul	64.00
Nb FLOP fma	100.00
Nb FLOP div	4.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	25.60
Bytes prefetched	0.00
Bytes loaded	752.00
Bytes stored	176.00
Stride 0	3.00
Stride 1	0.00
Stride n	0.00
Stride unknown	14.00
Stride indirect	7.00
Vectorization ratio all	81.67
Vectorization ratio load	61.90
Vectorization ratio store	7.69
Vectorization ratio mul	100.00
Vectorization ratio add_sub	94.74
Vectorization ratio fma	100.00
Vectorization ratio div_sqrt	100.00
Vectorization ratio other	81.82
Vector-efficiency ratio all	90.28
Vector-efficiency ratio load	80.95
Vector-efficiency ratio store	53.85
Vector-efficiency ratio mul	100.00
Vector-efficiency ratio add_sub	97.37
Vector-efficiency ratio fma	100.00
Vector-efficiency ratio div_sqrt	100.00
Vector-efficiency ratio other	86.36

Path /

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

Function	qmcplusplus::BsplineFunctor::evaluateVGL(int, int, int, double const, double, double, double, double, int) const
Source file and lines	BsplineFunctor.h:302-336
Module	exec

The loop is defined in:

/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h:1150
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:302-315,321-336

The related source loop is unrolled by 4 (including vectorization).

gain
potential
hint
expert

Vectorization

Your loop is partially vectorized. 90% 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 36.25 to 33.75 cycles (1.07x speedup).

Details

81% of VPU instructions are used in vector version (process two or more data elements in vector registers):

61% of VPU loads are used in vector version.
7% of VPU stores are used in vector version.
94% of VPU addition or subtraction instructions are used in vector version.
81% 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.

FMA

Detected 100 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 (100 inside FMA instructions)
164: multiply (100 inside FMA instructions)
4: divide

The binary loop is loading 752 bytes. The binary loop is storing 176 bytes.

Arithmetic intensity

Arithmetic intensity is 0.33 FP operations per loaded or stored byte.

General properties

nb instructions	199
loop length	796
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

24.88 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	3.42	3.42	3.33	3.33	3.25	3.25	36.25	36.25	36.25	36.25	19.17	18.83	19.00	0.00	0.00
cycles	0.50	0.50	3.42	3.42	3.33	3.33	3.25	3.25	36.25	36.25	36.25	36.25	19.17	18.83	19.00	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)	4.00

Cycles summary

Front-end	24.88
Data deps.	4.00
Overall L1	36.25

Vectorization ratios

INT

all	56%
load	61%
store	7%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	87%

all	98%
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	66%

INT+FP

all	81%
load	61%
store	7%
mul	100%
add-sub	94%
fma	100%
div/sqrt	100%
other	81%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 36.25 cycles. At this rate:

21% of peak load performance is reached (20.74 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (4.86 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 4170c0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDP Q0, Q2, [X2], #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%)
ORR V27.16B, V24.16B, V24.16B	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%)
SUBS X1, X1, #4	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (50.0%)
FMUL V1.2D, V0.2D, V29.D[0]	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%)
STP Q2, Q0, [SP, #560]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	1	vect (100.0%)
FMUL V2.2D, V2.2D, V29.D[0]	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 Q31, [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%)
LDP Q11, Q15, [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%)
LDR Q30, [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%)
LDP Q0, Q17, [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%)
LDR Q20, [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%)
FCVTZS V5.2D, V1.2D	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 V4.2D, V2.2D	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 V16.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
XTN V6.2S, 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%)
XTN V4.2S, 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%)
FRINTZ V5.2D, V1.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
FSUB V9.2D, V2.2D, 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%)
MOV W3, V6.S[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (25.0%)
FMOV W5, S6	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (25.0%)
MOV W4, V4.S[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (25.0%)
FMUL V13.2D, V9.2D, V9.2D	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%)
FSUB V23.2D, V1.2D, 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%)
LDP Q2, Q1, [SP, #592]	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%)
SBFM X6, X3, #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
FMOV W3, S4	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (25.0%)
LDR D18, [X11, X5,SXTW #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 D19, [X12, X5,SXTW #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 Q3, Q4, [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%)
SBFM X4, X4, #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 X7, X11, X6	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 X19, X11, X4	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 V28.2D, V13.2D, V9.2D	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 V5.2D, V23.2D, 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%)
LDR D22, [X11, X3,SXTW #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 D21, [X12, X3,SXTW #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 V6.16B, V4.16B, V4.16B	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 V4.2D, V9.2D, V24.D[0]	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, V5.2D, 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%)
FMLA V6.2D, V23.2D, V24.D[0]	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 V24.16B, 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%)
ORR V16.16B, 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%)
ORR V3.16B, V7.16B, V7.16B	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 V7.16B, 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%)
LDP Q12, Q10, [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%)
LD1 {V18.D[1]}, [X7]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
ADD X7, X12, X6	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
LD1 {V19.D[1]}, [X7]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
ADD X7, X12, X4	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, V9.2D, V17.D[0]	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, V23.2D, V17.D[0]	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, #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%)
LD1 {V22.D[1]}, [X19]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
LD1 {V21.D[1]}, [X7]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
ADD X19, X13, X6	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 X7, X13, X4	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 X6, X14, X6	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 X4, X14, X4	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 V6.2D, V6.2D, 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%)
FMLA V6.2D, V16.2D, 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%)
FMUL V16.2D, V13.2D, V10.D[0]	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, V4.2D, 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, V9.2D, V12.D[0]	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, V24.2D, 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%)
FMUL V24.2D, V28.2D, V2.D[0]	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 V24.2D, V13.2D, V1.D[0]	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, V9.2D, V17.D[0]	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 V16.2D, V16.2D, 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%)
FMUL V16.2D, V16.2D, 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%)
FADD V24.2D, V24.2D, V31.2D	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 V22.2D, V24.2D, 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 V24.2D, V13.2D, V30.D[0]	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 V24.2D, V9.2D, V0.D[0]	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, 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 V16.2D, V24.2D, 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%)
FMUL V24.2D, V28.2D, V20.D[0]	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 V24.2D, V13.2D, V25.D[0]	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, V9.2D, V14.D[0]	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, 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%)
FMLA V22.2D, V24.2D, 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%)
FMUL V21.2D, V5.2D, V10.D[0]	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, V5.2D, V30.D[0]	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, V23.2D, V12.D[0]	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, V23.2D, V0.D[0]	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 Q0, [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%)
FADD V21.2D, V21.2D, 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%)
FADD V24.2D, V24.2D, 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%)
LDR Q15, [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%)
LDR Q11, [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%)
LDP Q12, Q10, [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%)
FMUL V21.2D, V21.2D, 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%)
FMLA V21.2D, V24.2D, 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%)
FMUL V24.2D, V26.2D, V2.D[0]	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 V24.2D, V5.2D, V1.D[0]	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 Q1, [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%)
FMLA V24.2D, V23.2D, V17.D[0]	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, #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%)
FADD V24.2D, V24.2D, V31.2D	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 V18.2D, V24.2D, 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%)
FMUL V24.2D, V26.2D, V20.D[0]	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 Q31, Q30, [SP, #640]	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 Q20, [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%)
FMLA V24.2D, V5.2D, V25.D[0]	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, V23.2D, V14.D[0]	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, 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%)
FMLA V18.2D, V24.2D, 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, [X13, X5,SXTW #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 V24.16B, V15.16B, V15.16B	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, V9.2D, V30.D[0]	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, V23.2D, V30.D[0]	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%)
LD1 {V19.D[1]}, [X19]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
FMLA V6.2D, V24.2D, 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%)
FMUL V24.2D, V5.2D, V0.D[0]	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 V24.2D, V23.2D, V31.D[0]	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, 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 V21.2D, V24.2D, 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%)
FMUL V24.2D, V26.2D, V17.D[0]	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 V24.2D, V5.2D, V12.D[0]	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, V23.2D, V10.D[0]	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, V20.2D	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 V18.2D, V24.2D, 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, [X13, X3,SXTW #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 V24.2D, V13.2D, V0.D[0]	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 V24.2D, V9.2D, V31.D[0]	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, 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%)
LDR Q11, [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%)
LD1 {V19.D[1]}, [X7]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
FMLA V16.2D, V24.2D, 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%)
FMUL V24.2D, V28.2D, V17.D[0]	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 V4.2D, V15.2D, 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 Q17, [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 V24.2D, V13.2D, V12.D[0]	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, V9.2D, V10.D[0]	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, V7.16B, V7.16B	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 V7.16B, 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%)
LDR Q3, [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%)
FADD V24.2D, V24.2D, V20.2D	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 V22.2D, V24.2D, 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, [X14, X5,SXTW #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 V24.16B, 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%)
FMLA V24.2D, V23.2D, V17.D[0]	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%)
LD1 {V19.D[1]}, [X6]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
FMLA V6.2D, V24.2D, 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%)
FMUL V24.2D, V5.2D, V7.D[0]	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 V24.2D, V23.2D, V10.D[0]	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, 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 V21.2D, V24.2D, 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 V24.16B, 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%)
LDP Q27, Q0, [SP, #752]	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 V2.2D, V26.2D, V0.D[0]	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 V2.2D, V5.2D, V27.D[0]	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, V23.2D, V1.D[0]	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 Q23, Q0, [SP, #128]	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 V1.2D, V2.2D, V0.2D	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%)
ORR V2.16B, 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%)
LDP Q5, 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%)
FMLA V18.2D, V1.2D, 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 D1, [X14, X3,SXTW #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 V2.2D, V9.2D, V17.D[0]	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%)
LD1 {V1.D[1]}, [X4]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
FMLA V4.2D, V2.2D, V1.2D	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, V6.2D, V23.D[0]	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%)
LDPSW W3, W4, [X0, #504]	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	5	1	N/A
ADD X5, X10, X4,LSL #3	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
STR D18, [X8, X3,LSL #3]	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%)
STR D2, [X10, X3,LSL #3]	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 {V2.D[1]}, [X5]	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%)
FMUL V2.2D, V4.2D, V23.D[0]	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, V21.2D, V29.D[0]	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 V4.2D, V4.2D, V3.2D	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%)
LDPSW W5, W6, [X0], #16	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	5	1	N/A
ADD X7, X10, X6,LSL #3	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
STR D2, [X10, X5,LSL #3]	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 {V2.D[1]}, [X7]	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%)
FMUL V2.2D, V13.2D, V7.D[0]	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 X7, X9, X4,LSL #3	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 V2.2D, V9.2D, V10.D[0]	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 V2.2D, V2.2D, 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 V16.2D, V2.2D, V1.2D	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, V16.2D, V29.D[0]	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 V2.2D, V2.2D, V5.2D	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%)
STR D4, [X9, X3,LSL #3]	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 {V4.D[1]}, [X7]	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%)
ADD X7, X9, X6,LSL #3	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 X3, X8, X4,LSL #3	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
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%)
ADD X3, X8, X6,LSL #3	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
STR D2, [X9, X5,LSL #3]	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 {V2.D[1]}, [X7]	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, #752]	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 V2.2D, V28.2D, V2.D[0]	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 V2.2D, V13.2D, V4.D[0]	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, #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%)
FMLA V2.2D, V9.2D, V4.D[0]	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 V2.2D, V2.2D, V0.2D	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 V22.2D, V2.2D, V1.2D	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 D22, [X8, X5,LSL #3]	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 {V22.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%)
B.NE 4170c0 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x200>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	qmcplusplus::BsplineFunctor::evaluateVGL(int, int, int, double const, double, double, double, double, int) const
Source file and lines	BsplineFunctor.h:302-336
Module	exec

The loop is defined in:

/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h:1150
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:302-315,321-336

The related source loop is unrolled by 4 (including vectorization).

gain
potential
hint
expert

Vectorization

Details

81% of VPU instructions are used in vector version (process two or more data elements in vector registers):

61% of VPU loads are used in vector version.
7% of VPU stores are used in vector version.
94% of VPU addition or subtraction instructions are used in vector version.
81% 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.

FMA

Detected 100 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 (100 inside FMA instructions)
164: multiply (100 inside FMA instructions)
4: divide

The binary loop is loading 752 bytes. The binary loop is storing 176 bytes.

Arithmetic intensity

Arithmetic intensity is 0.33 FP operations per loaded or stored byte.

General properties

nb instructions	199
loop length	796
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

24.88 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	3.42	3.42	3.33	3.33	3.25	3.25	36.25	36.25	36.25	36.25	19.17	18.83	19.00	0.00	0.00
cycles	0.50	0.50	3.42	3.42	3.33	3.33	3.25	3.25	36.25	36.25	36.25	36.25	19.17	18.83	19.00	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)	4.00

Cycles summary

Front-end	24.88
Data deps.	4.00
Overall L1	36.25

Vectorization ratios

INT

all	56%
load	61%
store	7%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	87%

all	98%
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	66%

INT+FP

all	81%
load	61%
store	7%
mul	100%
add-sub	94%
fma	100%
div/sqrt	100%
other	81%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 36.25 cycles. At this rate:

21% of peak load performance is reached (20.74 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (4.86 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 4170c0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDP Q0, Q2, [X2], #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%)
ORR V27.16B, V24.16B, V24.16B	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%)
SUBS X1, X1, #4	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (50.0%)
FMUL V1.2D, V0.2D, V29.D[0]	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%)
STP Q2, Q0, [SP, #560]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	1	vect (100.0%)
FMUL V2.2D, V2.2D, V29.D[0]	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 Q31, [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%)
LDP Q11, Q15, [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%)
LDR Q30, [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%)
LDP Q0, Q17, [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%)
LDR Q20, [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%)
FCVTZS V5.2D, V1.2D	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 V4.2D, V2.2D	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 V16.2D, V2.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
XTN V6.2S, 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%)
XTN V4.2S, 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%)
FRINTZ V5.2D, V1.2D	1	0	0	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
FSUB V9.2D, V2.2D, 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%)
MOV W3, V6.S[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (25.0%)
FMOV W5, S6	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (25.0%)
MOV W4, V4.S[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	1	scal (25.0%)
FMUL V13.2D, V9.2D, V9.2D	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%)
FSUB V23.2D, V1.2D, 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%)
LDP Q2, Q1, [SP, #592]	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%)
SBFM X6, X3, #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
FMOV W3, S4	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	2	1	scal (25.0%)
LDR D18, [X11, X5,SXTW #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 D19, [X12, X5,SXTW #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 Q3, Q4, [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%)
SBFM X4, X4, #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 X7, X11, X6	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 X19, X11, X4	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 V28.2D, V13.2D, V9.2D	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 V5.2D, V23.2D, 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%)
LDR D22, [X11, X3,SXTW #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 D21, [X12, X3,SXTW #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 V6.16B, V4.16B, V4.16B	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 V4.2D, V9.2D, V24.D[0]	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, V5.2D, 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%)
FMLA V6.2D, V23.2D, V24.D[0]	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 V24.16B, 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%)
ORR V16.16B, 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%)
ORR V3.16B, V7.16B, V7.16B	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 V7.16B, 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%)
LDP Q12, Q10, [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%)
LD1 {V18.D[1]}, [X7]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
ADD X7, X12, X6	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
LD1 {V19.D[1]}, [X7]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
ADD X7, X12, X4	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, V9.2D, V17.D[0]	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, V23.2D, V17.D[0]	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, #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%)
LD1 {V22.D[1]}, [X19]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
LD1 {V21.D[1]}, [X7]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
ADD X19, X13, X6	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 X7, X13, X4	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 X6, X14, X6	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 X4, X14, X4	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 V6.2D, V6.2D, 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%)
FMLA V6.2D, V16.2D, 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%)
FMUL V16.2D, V13.2D, V10.D[0]	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, V4.2D, 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, V9.2D, V12.D[0]	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, V24.2D, 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%)
FMUL V24.2D, V28.2D, V2.D[0]	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 V24.2D, V13.2D, V1.D[0]	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, V9.2D, V17.D[0]	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 V16.2D, V16.2D, 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%)
FMUL V16.2D, V16.2D, 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%)
FADD V24.2D, V24.2D, V31.2D	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 V22.2D, V24.2D, 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 V24.2D, V13.2D, V30.D[0]	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 V24.2D, V9.2D, V0.D[0]	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, 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 V16.2D, V24.2D, 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%)
FMUL V24.2D, V28.2D, V20.D[0]	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 V24.2D, V13.2D, V25.D[0]	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, V9.2D, V14.D[0]	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, 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%)
FMLA V22.2D, V24.2D, 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%)
FMUL V21.2D, V5.2D, V10.D[0]	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, V5.2D, V30.D[0]	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, V23.2D, V12.D[0]	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, V23.2D, V0.D[0]	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 Q0, [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%)
FADD V21.2D, V21.2D, 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%)
FADD V24.2D, V24.2D, 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%)
LDR Q15, [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%)
LDR Q11, [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%)
LDP Q12, Q10, [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%)
FMUL V21.2D, V21.2D, 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%)
FMLA V21.2D, V24.2D, 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%)
FMUL V24.2D, V26.2D, V2.D[0]	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 V24.2D, V5.2D, V1.D[0]	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 Q1, [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%)
FMLA V24.2D, V23.2D, V17.D[0]	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, #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%)
FADD V24.2D, V24.2D, V31.2D	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 V18.2D, V24.2D, 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%)
FMUL V24.2D, V26.2D, V20.D[0]	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 Q31, Q30, [SP, #640]	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 Q20, [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%)
FMLA V24.2D, V5.2D, V25.D[0]	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, V23.2D, V14.D[0]	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, 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%)
FMLA V18.2D, V24.2D, 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, [X13, X5,SXTW #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 V24.16B, V15.16B, V15.16B	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, V9.2D, V30.D[0]	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, V23.2D, V30.D[0]	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%)
LD1 {V19.D[1]}, [X19]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
FMLA V6.2D, V24.2D, 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%)
FMUL V24.2D, V5.2D, V0.D[0]	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 V24.2D, V23.2D, V31.D[0]	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, 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 V21.2D, V24.2D, 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%)
FMUL V24.2D, V26.2D, V17.D[0]	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 V24.2D, V5.2D, V12.D[0]	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, V23.2D, V10.D[0]	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, V20.2D	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 V18.2D, V24.2D, 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, [X13, X3,SXTW #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 V24.2D, V13.2D, V0.D[0]	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 V24.2D, V9.2D, V31.D[0]	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, 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%)
LDR Q11, [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%)
LD1 {V19.D[1]}, [X7]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
FMLA V16.2D, V24.2D, 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%)
FMUL V24.2D, V28.2D, V17.D[0]	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 V4.2D, V15.2D, 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 Q17, [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 V24.2D, V13.2D, V12.D[0]	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, V9.2D, V10.D[0]	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, V7.16B, V7.16B	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 V7.16B, 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%)
LDR Q3, [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%)
FADD V24.2D, V24.2D, V20.2D	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 V22.2D, V24.2D, 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, [X14, X5,SXTW #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 V24.16B, 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%)
FMLA V24.2D, V23.2D, V17.D[0]	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%)
LD1 {V19.D[1]}, [X6]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
FMLA V6.2D, V24.2D, 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%)
FMUL V24.2D, V5.2D, V7.D[0]	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 V24.2D, V23.2D, V10.D[0]	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, 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 V21.2D, V24.2D, 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 V24.16B, 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%)
LDP Q27, Q0, [SP, #752]	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 V2.2D, V26.2D, V0.D[0]	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 V2.2D, V5.2D, V27.D[0]	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, V23.2D, V1.D[0]	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 Q23, Q0, [SP, #128]	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 V1.2D, V2.2D, V0.2D	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%)
ORR V2.16B, 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%)
LDP Q5, 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%)
FMLA V18.2D, V1.2D, 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 D1, [X14, X3,SXTW #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 V2.2D, V9.2D, V17.D[0]	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%)
LD1 {V1.D[1]}, [X4]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.33	0.33	0.33	8	0.33	scal (50.0%)
FMLA V4.2D, V2.2D, V1.2D	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, V6.2D, V23.D[0]	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%)
LDPSW W3, W4, [X0, #504]	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	5	1	N/A
ADD X5, X10, X4,LSL #3	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
STR D18, [X8, X3,LSL #3]	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%)
STR D2, [X10, X3,LSL #3]	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 {V2.D[1]}, [X5]	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%)
FMUL V2.2D, V4.2D, V23.D[0]	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, V21.2D, V29.D[0]	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 V4.2D, V4.2D, V3.2D	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%)
LDPSW W5, W6, [X0], #16	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	5	1	N/A
ADD X7, X10, X6,LSL #3	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
STR D2, [X10, X5,LSL #3]	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 {V2.D[1]}, [X7]	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%)
FMUL V2.2D, V13.2D, V7.D[0]	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 X7, X9, X4,LSL #3	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 V2.2D, V9.2D, V10.D[0]	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 V2.2D, V2.2D, 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 V16.2D, V2.2D, V1.2D	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, V16.2D, V29.D[0]	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 V2.2D, V2.2D, V5.2D	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%)
STR D4, [X9, X3,LSL #3]	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 {V4.D[1]}, [X7]	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%)
ADD X7, X9, X6,LSL #3	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 X3, X8, X4,LSL #3	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
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%)
ADD X3, X8, X6,LSL #3	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
STR D2, [X9, X5,LSL #3]	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 {V2.D[1]}, [X7]	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, #752]	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 V2.2D, V28.2D, V2.D[0]	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 V2.2D, V13.2D, V4.D[0]	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, #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%)
FMLA V2.2D, V9.2D, V4.D[0]	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 V2.2D, V2.2D, V0.2D	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 V22.2D, V2.2D, V1.2D	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 D22, [X8, X5,LSL #3]	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 {V22.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%)
B.NE 4170c0 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x200>	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

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

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