OV - exec - Loop 262

0x416d60 LD1D	{Z23.D}, P0/Z, [X15, X18,LSL #3]    [9]

0x416d64 LDR	Z30, [SP, #39, MUL VL]    [3]

0x416d68 LDR	Z31, [SP, #38, MUL VL]    [3]

0x416d6c FMUL	Z24.D, Z23.D, Z7.D

0x416d70 LDR	Z8, [SP, #37, MUL VL]    [3]

0x416d74 LDR	Z9, [SP, #26, MUL VL]    [3]

0x416d78 MOVPRFX	Z25, Z24

0x416d7c FCVTZS	Z25.D, P0/M, Z24.D

0x416d80 LD1D	{Z27.D}, P0/Z, [X11, Z25.D,LSL #3]    [5]

0x416d84 MOVPRFX	Z26, Z25

0x416d88 SCVTF	Z26.D, P0/M, Z25.D

0x416d8c FSUB	Z24.D, Z24.D, Z26.D

0x416d90 FMLA	Z30.D, P0/M, Z0.D, Z24.D

0x416d94 FMAD	Z31.D, P0/M, Z24.D, Z8.D

0x416d98 LD1D	{Z28.D}, P0/Z, [X12, Z25.D,LSL #3]    [6]

0x416d9c LDR	Z8, [SP, #29, MUL VL]    [3]

0x416da0 FMUL	Z26.D, Z24.D, Z24.D

0x416da4 FMUL	Z29.D, Z26.D, Z24.D

0x416da8 FMUL	Z30.D, Z30.D, Z27.D

0x416dac FMLA	Z30.D, P0/M, Z31.D, Z28.D

0x416db0 LDR	Z31, [SP, #31, MUL VL]    [3]

0x416db4 FMAD	Z31.D, P0/M, Z26.D, Z8.D

0x416db8 LDR	Z8, [SP, #30, MUL VL]    [3]

0x416dbc FMLA	Z31.D, P0/M, Z8.D, Z24.D

0x416dc0 LDR	Z8, [SP, #28, MUL VL]    [3]

0x416dc4 FMUL	Z31.D, Z31.D, Z27.D

0x416dc8 FMAD	Z8.D, P0/M, Z26.D, Z9.D

0x416dcc LDR	Z9, [SP, #27, MUL VL]    [3]

0x416dd0 FMLA	Z8.D, P0/M, Z9.D, Z24.D

0x416dd4 LDR	Z9, [SP, #35, MUL VL]    [3]

0x416dd8 FMLA	Z31.D, P0/M, Z8.D, Z28.D

0x416ddc MOVPRFX	Z8, Z1

0x416de0 FMLA	Z8.D, P0/M, Z13.D, Z29.D

0x416de4 FMLA	Z8.D, P0/M, Z14.D, Z26.D

0x416de8 FMLA	Z8.D, P0/M, Z15.D, Z24.D

0x416dec FMUL	Z27.D, Z8.D, Z27.D

0x416df0 MOVPRFX	Z8, Z5

0x416df4 FMLA	Z8.D, P0/M, Z2.D, Z29.D

0x416df8 FMLA	Z8.D, P0/M, Z3.D, Z26.D

0x416dfc FMLA	Z8.D, P0/M, Z4.D, Z24.D

0x416e00 FMLA	Z27.D, P0/M, Z8.D, Z28.D

0x416e04 LDR	Z8, [SP, #36, MUL VL]    [3]

0x416e08 FMAD	Z8.D, P0/M, Z24.D, Z9.D

0x416e0c LDR	Z9, [SP, #23, MUL VL]    [3]

0x416e10 LD1D	{Z28.D}, P0/Z, [X13, Z25.D,LSL #3]    [7]

0x416e14 LD1D	{Z25.D}, P0/Z, [X14, Z25.D,LSL #3]    [8]

0x416e18 FMLA	Z30.D, P0/M, Z8.D, Z28.D

0x416e1c LDR	Z8, [SP, #25, MUL VL]    [3]

0x416e20 FMAD	Z8.D, P0/M, Z26.D, Z9.D

0x416e24 LDR	Z9, [SP, #24, MUL VL]    [3]

0x416e28 FMLA	Z8.D, P0/M, Z9.D, Z24.D

0x416e2c FMLA	Z31.D, P0/M, Z8.D, Z28.D

0x416e30 MOVPRFX	Z8, Z18

0x416e34 FMLA	Z8.D, P0/M, Z6.D, Z29.D

0x416e38 FMAD	Z29.D, P0/M, Z19.D, Z22.D

0x416e3c FMLA	Z8.D, P0/M, Z16.D, Z26.D

0x416e40 FMLA	Z8.D, P0/M, Z17.D, Z24.D

0x416e44 FMLA	Z27.D, P0/M, Z8.D, Z28.D

0x416e48 LDR	Z28, [SP, #34, MUL VL]    [3]

0x416e4c LDR	Z8, [SP, #33, MUL VL]    [3]

0x416e50 FMAD	Z28.D, P0/M, Z24.D, Z8.D

0x416e54 FMAD	Z28.D, P0/M, Z25.D, Z30.D

0x416e58 MOVPRFX	Z30, Z12

0x416e5c FMLA	Z30.D, P0/M, Z10.D, Z26.D

0x416e60 FMAD	Z26.D, P0/M, Z20.D, Z29.D

0x416e64 FMLA	Z30.D, P0/M, Z11.D, Z24.D

0x416e68 FMAD	Z24.D, P0/M, Z21.D, Z26.D

0x416e6c LDR	Z26, [SP, #32, MUL VL]    [3]

0x416e70 FMAD	Z30.D, P0/M, Z25.D, Z31.D

0x416e74 FMAD	Z24.D, P0/M, Z25.D, Z27.D

0x416e78 LD1SW	{Z25.D}, P0/Z, [X16, X18,LSL #2]    [10]

0x416e7c INCD	X18, ALL

0x416e80 FMUL	Z26.D, Z26.D, Z28.D

0x416e84 ST1D	{Z26.D}, P0, [X10, Z25.D,LSL #3]    [4]

0x416e88 FMUL	Z26.D, Z30.D, Z7.D

0x416e8c FDIVR	Z23.D, P0/M, Z23.D, Z26.D

0x416e90 ST1D	{Z23.D}, P0, [X9, Z25.D,LSL #3]    [2]

0x416e94 ST1D	{Z24.D}, P0, [X8, Z25.D,LSL #3]    [1]

0x416e98 CMP	X0, X18

0x416e9c B.NE	416d60

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 303 - 336

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

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];

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
►85.71+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►14.29+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►75.00+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►12.50+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►12.50+	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

Coverage (%)	Name	Source Location	Module
►50.00+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►38.46+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►11.54+	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

Coverage (%)	Name	Source Location	Module
►58.93+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►35.71+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►5.36+	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

Coverage (%)	Name	Source Location	Module
►64.60+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►28.32+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►7.08+	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

Coverage (%)	Name	Source Location	Module
►63.69+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►26.82+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►8.94+	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

Coverage (%)	Name	Source Location	Module
►62.14+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►30.86+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►6.17+	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

Coverage (%)	Name	Source Location	Module
►64.48+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►31.04+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►4.18+	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

Coverage (%)	Name	Source Location	Module
►64.65+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►28.41+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►6.26+	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

Coverage (%)	Name	Source Location	Module
►62.11+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►30.64+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►6.21+	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

Coverage (%)	Name	Source Location	Module
►61.89+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►33.38+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►4.27+	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

Coverage (%)	Name	Source Location	Module
►64.58+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►29.95+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►4.43+	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
►1.04+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:260	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►65.12+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►29.55+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►3.94+	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
►1.39+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:260	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►65.42+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►29.95+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►3.15+	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
►1.48+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:260	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
►66.67+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.63	miniqmc.cpp:442	exec
○	__kmp_invoke_microtask		libomp.so
►28.21+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.63	miniqmc.cpp:450	exec
○	__kmp_invoke_microtask		libomp.so
►4.19+	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	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	1.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.35
Bottlenecks	P8, P9, P10, P11,
Function	qmcplusplus::BsplineFunctor::evaluateVGL(int, int, int, double const, double, double, double, double, int) const
Source	BsplineFunctor.h:303-336
Source loop unroll info	unrolled by 2
Source loop unroll confidence level	high
Unroll/vectorization loop type	NA
Unroll factor	2
CQA cycles	13.50
CQA cycles if no scalar integer	13.50
CQA cycles if FP arith vectorized	13.50
CQA cycles if fully vectorized	13.50
Front-end cycles	10.00
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	0.50
P3 cycles	0.50
P4 cycles	0.00
P5 cycles	0.00
P6 cycles	0.50
P7 cycles	0.50
P8 cycles	13.50
P9 cycles	13.50
P10 cycles	13.50
P11 cycles	13.50
P12 cycles	8.83
P13 cycles	8.50
P14 cycles	8.67
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	3.50 - 6.99
Inter-iter dependencies cycles	2
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	80.00
Nb uops	80.00
Nb loads	NA
Nb stores	3.00
Nb stack references	0.00
FLOP/cycle	11.26
Nb FLOP add-sub	2.00
Nb FLOP mul	16.00
Nb FLOP fma	66.00
Nb FLOP div	2.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	30.81
Bytes prefetched	0.00
Bytes loaded	368.00
Bytes stored	48.00
Stride 0	1.00
Stride 1	0.00
Stride n	0.00
Stride unknown	0.00
Stride indirect	7.00
Vectorization ratio all	92.21
Vectorization ratio load	100.00
Vectorization ratio store	100.00
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	25.00
Vector-efficiency ratio all	100.00
Vector-efficiency ratio load	100.00
Vector-efficiency ratio store	100.00
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	100.00

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	1.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.35
Bottlenecks	P8, P9, P10, P11,
Function	qmcplusplus::BsplineFunctor::evaluateVGL(int, int, int, double const, double, double, double, double, int) const
Source	BsplineFunctor.h:303-336
Source loop unroll info	unrolled by 2
Source loop unroll confidence level	high
Unroll/vectorization loop type	NA
Unroll factor	2
CQA cycles	13.50
CQA cycles if no scalar integer	13.50
CQA cycles if FP arith vectorized	13.50
CQA cycles if fully vectorized	13.50
Front-end cycles	10.00
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	0.50
P3 cycles	0.50
P4 cycles	0.00
P5 cycles	0.00
P6 cycles	0.50
P7 cycles	0.50
P8 cycles	13.50
P9 cycles	13.50
P10 cycles	13.50
P11 cycles	13.50
P12 cycles	8.83
P13 cycles	8.50
P14 cycles	8.67
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	3.50 - 6.99
Inter-iter dependencies cycles	2
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	80.00
Nb uops	80.00
Nb loads	NA
Nb stores	3.00
Nb stack references	0.00
FLOP/cycle	11.26
Nb FLOP add-sub	2.00
Nb FLOP mul	16.00
Nb FLOP fma	66.00
Nb FLOP div	2.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	30.81
Bytes prefetched	0.00
Bytes loaded	368.00
Bytes stored	48.00
Stride 0	1.00
Stride 1	0.00
Stride n	0.00
Stride unknown	0.00
Stride indirect	7.00
Vectorization ratio all	92.21
Vectorization ratio load	100.00
Vectorization ratio store	100.00
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	25.00
Vector-efficiency ratio all	100.00
Vector-efficiency ratio load	100.00
Vector-efficiency ratio store	100.00
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	100.00

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:303-336
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:303-336.

The related source loop is unrolled by 2 (including vectorization).

gain
potential
hint
expert

Vectorization

Your loop is highly vectorized. 100% of vector register length is used (average across all VPU instructions).

Details

92% of VPU instructions are used in vector version (process two or more data elements in vector registers):

25% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

FMA

Detected 66 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: 1 occurrences►
- /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:309
SCVTF: 1 occurrences►
- /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:310

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 152 FP arithmetical operations:

68: addition or subtraction (66 inside FMA instructions)
82: multiply (66 inside FMA instructions)
2: divide

The binary loop is loading 368 bytes. The binary loop is storing 48 bytes.

Arithmetic intensity

Arithmetic intensity is 0.37 FP operations per loaded or stored byte.

General properties

nb instructions	80
loop length	320
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

10.00 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	0.50	0.50	0.00	0.00	0.50	0.50	13.50	13.50	13.50	13.50	8.83	8.50	8.67	0.00	0.00
cycles	0.50	0.50	0.50	0.50	0.00	0.00	0.50	0.50	13.50	13.50	13.50	13.50	8.83	8.50	8.67	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	3.50-6.99
Longest recurrence chain latency (RecMII)	2.00

Cycles summary

Front-end	10.00
Data deps.	2.00
Overall L1	13.50

Vectorization ratios

INT

all	81%
load	100%
store	100%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	14%

FP

all	100%
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	100%

INT+FP

all	92%
load	100%
store	100%
mul	100%
add-sub	100%
fma	100%
div/sqrt	100%
other	25%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 13.50 cycles. At this rate:

28% of peak load performance is reached (27.26 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
7% of peak store performance is reached (3.56 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 416d60

Instruction	Nb FU	P0	P1	P2	P3	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
LD1D {Z23.D}, P0/Z, [X15, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Z30, [SP, #39, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Z31, [SP, #38, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL Z24.D, Z23.D, Z7.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDR Z8, [SP, #37, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Z9, [SP, #26, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
MOVPRFX Z25, Z24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
FCVTZS Z25.D, P0/M, Z24.D	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
LD1D {Z27.D}, P0/Z, [X11, Z25.D,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
MOVPRFX Z26, Z25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
SCVTF Z26.D, P0/M, Z25.D	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
FSUB Z24.D, Z24.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA Z30.D, P0/M, Z0.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z31.D, P0/M, Z24.D, Z8.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LD1D {Z28.D}, P0/Z, [X12, Z25.D,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Z8, [SP, #29, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL Z26.D, Z24.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL Z29.D, Z26.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL Z30.D, Z30.D, Z27.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA Z30.D, P0/M, Z31.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z31, [SP, #31, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMAD Z31.D, P0/M, Z26.D, Z8.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z8, [SP, #30, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA Z31.D, P0/M, Z8.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z8, [SP, #28, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL Z31.D, Z31.D, Z27.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMAD Z8.D, P0/M, Z26.D, Z9.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z9, [SP, #27, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA Z8.D, P0/M, Z9.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z9, [SP, #35, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA Z31.D, P0/M, Z8.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
MOVPRFX Z8, Z1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
FMLA Z8.D, P0/M, Z13.D, Z29.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z14.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z15.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL Z27.D, Z8.D, Z27.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
MOVPRFX Z8, Z5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
FMLA Z8.D, P0/M, Z2.D, Z29.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z3.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z4.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z27.D, P0/M, Z8.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z8, [SP, #36, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMAD Z8.D, P0/M, Z24.D, Z9.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z9, [SP, #23, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LD1D {Z28.D}, P0/Z, [X13, Z25.D,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LD1D {Z25.D}, P0/Z, [X14, Z25.D,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA Z30.D, P0/M, Z8.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z8, [SP, #25, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMAD Z8.D, P0/M, Z26.D, Z9.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z9, [SP, #24, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA Z8.D, P0/M, Z9.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z31.D, P0/M, Z8.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
MOVPRFX Z8, Z18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
FMLA Z8.D, P0/M, Z6.D, Z29.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z29.D, P0/M, Z19.D, Z22.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z16.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z17.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z27.D, P0/M, Z8.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z28, [SP, #34, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Z8, [SP, #33, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMAD Z28.D, P0/M, Z24.D, Z8.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z28.D, P0/M, Z25.D, Z30.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
MOVPRFX Z30, Z12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
FMLA Z30.D, P0/M, Z10.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z26.D, P0/M, Z20.D, Z29.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z30.D, P0/M, Z11.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z24.D, P0/M, Z21.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z26, [SP, #32, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMAD Z30.D, P0/M, Z25.D, Z31.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z24.D, P0/M, Z25.D, Z27.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LD1SW {Z25.D}, P0/Z, [X16, X18,LSL #2]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
INCD X18, ALL	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	N/A
FMUL Z26.D, Z26.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
ST1D {Z26.D}, P0, [X10, Z25.D,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
FMUL Z26.D, Z30.D, Z7.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FDIVR Z23.D, P0/M, Z23.D, Z26.D	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	7-15	3.50-6.99	vect (100.0%)
ST1D {Z23.D}, P0, [X9, Z25.D,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
ST1D {Z24.D}, P0, [X8, Z25.D,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
CMP X0, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	N/A
B.NE 416d60 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x320>	1	0.50	0.50	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:303-336
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:303-336.

The related source loop is unrolled by 2 (including vectorization).

gain
potential
hint
expert

Vectorization

Your loop is highly vectorized. 100% of vector register length is used (average across all VPU instructions).

Details

92% of VPU instructions are used in vector version (process two or more data elements in vector registers):

25% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

FMA

Detected 66 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: 1 occurrences►
- /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:309
SCVTF: 1 occurrences►
- /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:310

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 152 FP arithmetical operations:

68: addition or subtraction (66 inside FMA instructions)
82: multiply (66 inside FMA instructions)
2: divide

The binary loop is loading 368 bytes. The binary loop is storing 48 bytes.

Arithmetic intensity

Arithmetic intensity is 0.37 FP operations per loaded or stored byte.

General properties

nb instructions	80
loop length	320
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

10.00 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	0.50	0.50	0.00	0.00	0.50	0.50	13.50	13.50	13.50	13.50	8.83	8.50	8.67	0.00	0.00
cycles	0.50	0.50	0.50	0.50	0.00	0.00	0.50	0.50	13.50	13.50	13.50	13.50	8.83	8.50	8.67	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	3.50-6.99
Longest recurrence chain latency (RecMII)	2.00

Cycles summary

Front-end	10.00
Data deps.	2.00
Overall L1	13.50

Vectorization ratios

INT

all	81%
load	100%
store	100%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	14%

FP

all	100%
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	100%

INT+FP

all	92%
load	100%
store	100%
mul	100%
add-sub	100%
fma	100%
div/sqrt	100%
other	25%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 13.50 cycles. At this rate:

28% of peak load performance is reached (27.26 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
7% of peak store performance is reached (3.56 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 416d60

Instruction	Nb FU	P0	P1	P2	P3	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
LD1D {Z23.D}, P0/Z, [X15, X18,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Z30, [SP, #39, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Z31, [SP, #38, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL Z24.D, Z23.D, Z7.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
LDR Z8, [SP, #37, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Z9, [SP, #26, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
MOVPRFX Z25, Z24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
FCVTZS Z25.D, P0/M, Z24.D	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
LD1D {Z27.D}, P0/Z, [X11, Z25.D,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
MOVPRFX Z26, Z25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
SCVTF Z26.D, P0/M, Z25.D	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	3	0.50	vect (100.0%)
FSUB Z24.D, Z24.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FMLA Z30.D, P0/M, Z0.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z31.D, P0/M, Z24.D, Z8.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LD1D {Z28.D}, P0/Z, [X12, Z25.D,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Z8, [SP, #29, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL Z26.D, Z24.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL Z29.D, Z26.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMUL Z30.D, Z30.D, Z27.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMLA Z30.D, P0/M, Z31.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z31, [SP, #31, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMAD Z31.D, P0/M, Z26.D, Z8.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z8, [SP, #30, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA Z31.D, P0/M, Z8.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z8, [SP, #28, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMUL Z31.D, Z31.D, Z27.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FMAD Z8.D, P0/M, Z26.D, Z9.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z9, [SP, #27, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA Z8.D, P0/M, Z9.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z9, [SP, #35, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA Z31.D, P0/M, Z8.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
MOVPRFX Z8, Z1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
FMLA Z8.D, P0/M, Z13.D, Z29.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z14.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z15.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMUL Z27.D, Z8.D, Z27.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
MOVPRFX Z8, Z5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
FMLA Z8.D, P0/M, Z2.D, Z29.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z3.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z4.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z27.D, P0/M, Z8.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z8, [SP, #36, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMAD Z8.D, P0/M, Z24.D, Z9.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z9, [SP, #23, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LD1D {Z28.D}, P0/Z, [X13, Z25.D,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LD1D {Z25.D}, P0/Z, [X14, Z25.D,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA Z30.D, P0/M, Z8.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z8, [SP, #25, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMAD Z8.D, P0/M, Z26.D, Z9.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z9, [SP, #24, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA Z8.D, P0/M, Z9.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z31.D, P0/M, Z8.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
MOVPRFX Z8, Z18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
FMLA Z8.D, P0/M, Z6.D, Z29.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z29.D, P0/M, Z19.D, Z22.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z16.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z8.D, P0/M, Z17.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z27.D, P0/M, Z8.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z28, [SP, #34, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Z8, [SP, #33, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMAD Z28.D, P0/M, Z24.D, Z8.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z28.D, P0/M, Z25.D, Z30.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
MOVPRFX Z30, Z12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (100.0%)
FMLA Z30.D, P0/M, Z10.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z26.D, P0/M, Z20.D, Z29.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA Z30.D, P0/M, Z11.D, Z24.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z24.D, P0/M, Z21.D, Z26.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Z26, [SP, #32, MUL VL]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMAD Z30.D, P0/M, Z25.D, Z31.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMAD Z24.D, P0/M, Z25.D, Z27.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LD1SW {Z25.D}, P0/Z, [X16, X18,LSL #2]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
INCD X18, ALL	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	N/A
FMUL Z26.D, Z26.D, Z28.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
ST1D {Z26.D}, P0, [X10, Z25.D,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
FMUL Z26.D, Z30.D, Z7.D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	3	0.25	vect (100.0%)
FDIVR Z23.D, P0/M, Z23.D, Z26.D	1	0	0	0	0	0	0	0.50	0	0.50	0	0	0	0	7-15	3.50-6.99	vect (100.0%)
ST1D {Z23.D}, P0, [X9, Z25.D,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
ST1D {Z24.D}, P0, [X8, Z25.D,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
CMP X0, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33	N/A
B.NE 416d60 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x320>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

▶Scalability Runs Description

Run 1x1	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_NUM_THREADS: 1OMP_PLACES: threads
Run 1x2	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 2OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x4	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 4OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x8	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 8OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x16	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 16OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x24	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 24OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x32	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 32OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x40	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 40OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x48	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 48OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x56	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 56OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x64	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 64OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x72	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 72OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x80	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 80OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x88	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 88OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x96	Number processes: 1Number nodes: 1Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/run/oneview_runs/multicore/armclang/oneview_run_1741388363OMP_NUM_THREADS: 96OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

(1x1) Efficiency	(1x1) Potential Speed-Up (%)	(1x2) Efficiency	(1x2) Potential Speed-Up (%)	(1x4) Efficiency	(1x4) Potential Speed-Up (%)	(1x8) Efficiency	(1x8) Potential Speed-Up (%)	(1x16) Efficiency	(1x16) Potential Speed-Up (%)	(1x24) Efficiency	(1x24) Potential Speed-Up (%)	(1x32) Efficiency	(1x32) Potential Speed-Up (%)	(1x40) Efficiency	(1x40) Potential Speed-Up (%)	(1x48) Efficiency	(1x48) Potential Speed-Up (%)	(1x56) Efficiency	(1x56) Potential Speed-Up (%)	(1x64) Efficiency	(1x64) Potential Speed-Up (%)	(1x72) Efficiency	(1x72) Potential Speed-Up (%)	(1x80) Efficiency	(1x80) Potential Speed-Up (%)	(1x88) Efficiency	(1x88) Potential Speed-Up (%)	(1x96) Efficiency	(1x96) Potential Speed-Up (%)
1	0	1.75	0	1.08	0	1	0	0.99	0	0.94	0	0.91	0	0.83	0.01	0.75	0.01	0.81	0.01	0.68	0.02	0.65	0.02	0.64	0.02	0.6	0.02	0.62	0.02

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency

Run	Number of threads	Efficiency (ideal is 1)	Speedup	Ideal Speedup	Time (s)	Coverage (%)
1x1	1	1	1	1	0.035000000149012	0.081329345703125
1x2	2	1.75	1.75	2	0.024999998509884	0.045753169804811
1x4	4	1.08	1.08	4	0.044999994337559	0.072401225566864
1x8	8	1	1	8	0.049999997019768	0.072956033051014
1x16	16	0.99	0.99	16	0.064999997615814	0.062429845333099
1x24	24	0.94	0.94	24	0.054999995976686	0.059636615216732
1x32	32	0.91	0.91	32	0.064999997615814	0.053443938493729
1x40	40	0.83	0.83	40	0.094999991357327	0.053473249077797
1x48	48	0.75	0.75	48	0.084999978542328	0.05469885841012
1x56	56	0.81	0.81	56	0.079999998211861	0.046465311199427
1x64	64	0.68	0.68	64	0.084999985992908	0.050583992153406
1x72	72	0.65	0.65	72	0.094999991357327	0.048562049865723
1x80	80	0.64	0.64	80	0.10499998182058	0.045351661741734
1x88	88	0.6	0.6	88	0.10500001162291	0.045558113604784
1x96	96	0.62	0.62	96	0.10500000417233	0.041047409176826

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

▶Scalability Runs Description

▼Columns Filter

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency