OV - exec - Loop 640

	Loop Id: 640	Module: exec	Source: TwoBodyJastrowRef.h:322-329 [...]	Coverage: 0.29%

0x43581c LDR	D29, [X13, X15]    [31]

0x435820 ADD	X16, X15, #8

0x435824 ADD	X18, X15, #16

0x435828 ADD	X17, X15, #24

0x43582c LDR	D30, [X30, X15]    [32]

0x435830 LDR	D31, [X24, X15]    [10]

0x435834 LDR	D7, [X8, X15]    [23]

0x435838 FADD	D3, D29, D30

0x43583c LDR	D16, [X14, X15]    [1]

0x435840 LDR	D1, [X23, X15]    [30]

0x435844 LDR	D5, [X19, X15]    [8]

0x435848 FSUB	D17, D3, S31

0x43584c FMADD	D4, D7, D0, D16

0x435850 STR	D17, [X30, X15]    [32]

0x435854 LDR	D18, [X9, X15]    [3]

0x435858 FSUB	D19, D2, S4

0x43585c FADD	D6, D1, D18

0x435860 FMADD	D20, D5, D0, D6

0x435864 FSUB	D21, D20, S4

0x435868 STR	D21, [X9, X15]    [3]

0x43586c ADD	X15, X15, #32

0x435870 LDR	D22, [X13, X16]    [11]

0x435874 LDR	D23, [X30, X16]    [7]

0x435878 LDR	D24, [X24, X16]    [16]

0x43587c LDR	D25, [X8, X16]    [5]

0x435880 FADD	D2, D22, D23

0x435884 LDR	D26, [X14, X16]    [18]

0x435888 LDR	D27, [X23, X16]    [27]

0x43588c LDR	D28, [X19, X16]    [17]

0x435890 FSUB	D29, D2, S24

0x435894 FMADD	D30, D25, D0, D26

0x435898 STR	D29, [X30, X16]    [7]

0x43589c LDR	D31, [X9, X16]    [2]

0x4358a0 FSUB	D16, D19, S30

0x4358a4 FADD	D7, D27, D31

0x4358a8 FMADD	D3, D28, D0, D7

0x4358ac FSUB	D1, D3, S30

0x4358b0 STR	D1, [X9, X16]    [2]

0x4358b4 LDR	D5, [X13, X18]    [19]

0x4358b8 LDR	D17, [X30, X18]    [15]

0x4358bc LDR	D18, [X24, X18]    [24]

0x4358c0 LDR	D19, [X8, X18]    [13]

0x4358c4 FADD	D6, D5, D17

0x4358c8 LDR	D4, [X14, X18]    [26]

0x4358cc LDR	D20, [X23, X18]    [29]

0x4358d0 LDR	D21, [X19, X18]    [25]

0x4358d4 FSUB	D22, D6, S18

0x4358d8 FMADD	D23, D19, D0, D4

0x4358dc STR	D22, [X30, X18]    [15]

0x4358e0 LDR	D24, [X9, X18]    [6]

0x4358e4 FSUB	D25, D16, S23

0x4358e8 FADD	D2, D20, D24

0x4358ec FMADD	D26, D21, D0, D2

0x4358f0 FSUB	D27, D26, S23

0x4358f4 STR	D27, [X9, X18]    [6]

0x4358f8 LDR	D28, [X13, X17]    [14]

0x4358fc LDR	D29, [X24, X17]    [20]

0x435900 LDR	D30, [X8, X17]    [9]

0x435904 LDR	D31, [X30, X17]    [12]

0x435908 LDR	D16, [X14, X17]    [22]

0x43590c LDR	D7, [X23, X17]    [28]

0x435910 FADD	D3, D28, D31

0x435914 LDR	D5, [X19, X17]    [21]

0x435918 FMADD	D17, D30, D0, D16

0x43591c FSUB	D1, D3, S29

0x435920 STR	D1, [X30, X17]    [12]

0x435924 FSUB	D2, D25, S17

0x435928 LDR	D18, [X9, X17]    [4]

0x43592c FADD	D19, D7, D18

0x435930 FMADD	D6, D5, D0, D19

0x435934 FSUB	D4, D6, S17

0x435938 STR	D4, [X9, X17]    [4]

0x43593c CMP	X10, X15

0x435940 B.NE	43581c

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

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

1043:       operator[](size_type __n) _GLIBCXX_NOEXCEPT

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 322 - 329

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

322:   for (int jat = 0; jat < N; jat++)

323:   {

324:     const valT du   = cur_u[jat] - old_u[jat];

325:     const valT newl = cur_d2u[jat] + lapfac * cur_du[jat];

326:     const valT dl   = old_d2u[jat] + lapfac * old_du[jat] - newl;

327:     Uat[jat] += du;

328:     d2Uat[jat] += dl;

329:     cur_d2Uat -= newl;

Coverage (%)	Name	Source Location	Module
►30.56+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►27.78+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►27.78+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►13.89+	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:402	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec

Path /

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	4.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.44
Bottlenecks	P10, P11, P12,
Function	miniqmcreference::TwoBodyJastrowRef >::acceptMove(qmcplusplus::ParticleSet&, int)
Source	stl_vector.h:1043-1043,TwoBodyJastrowRef.h:322-329
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	13.33
CQA cycles if no scalar integer	13.33
CQA cycles if FP arith vectorized	13.33
CQA cycles if fully vectorized	3.33
Front-end cycles	9.25
DIV/SQRT cycles	0.50
P0 cycles	0.50
P1 cycles	1.25
P2 cycles	1.25
P3 cycles	1.25
P4 cycles	1.25
P5 cycles	9.00
P6 cycles	9.00
P7 cycles	9.00
P8 cycles	9.00
P9 cycles	13.33
P10 cycles	13.33
P11 cycles	13.33
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	8
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	74.00
Nb uops	74.00
Nb loads	NA
Nb stores	8.00
Nb stack references	0.00
FLOP/cycle	2.70
Nb FLOP add-sub	20.00
Nb FLOP mul	0.00
Nb FLOP fma	8.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	24.00
Bytes prefetched	0.00
Bytes loaded	256.00
Bytes stored	64.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	NA
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	NA
Vector-efficiency ratio all	25.00
Vector-efficiency ratio load	25.00
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	NA
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	NA

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	4.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.44
Bottlenecks	P10, P11, P12,
Function	miniqmcreference::TwoBodyJastrowRef >::acceptMove(qmcplusplus::ParticleSet&, int)
Source	stl_vector.h:1043-1043,TwoBodyJastrowRef.h:322-329
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	13.33
CQA cycles if no scalar integer	13.33
CQA cycles if FP arith vectorized	13.33
CQA cycles if fully vectorized	3.33
Front-end cycles	9.25
DIV/SQRT cycles	0.50
P0 cycles	0.50
P1 cycles	1.25
P2 cycles	1.25
P3 cycles	1.25
P4 cycles	1.25
P5 cycles	9.00
P6 cycles	9.00
P7 cycles	9.00
P8 cycles	9.00
P9 cycles	13.33
P10 cycles	13.33
P11 cycles	13.33
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	8
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	74.00
Nb uops	74.00
Nb loads	NA
Nb stores	8.00
Nb stack references	0.00
FLOP/cycle	2.70
Nb FLOP add-sub	20.00
Nb FLOP mul	0.00
Nb FLOP fma	8.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	24.00
Bytes prefetched	0.00
Bytes loaded	256.00
Bytes stored	64.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	NA
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	NA
Vector-efficiency ratio all	25.00
Vector-efficiency ratio load	25.00
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	NA
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	NA

Path /

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

Function	miniqmcreference::TwoBodyJastrowRef >::acceptMove(qmcplusplus::ParticleSet&, int)
Source file and lines	TwoBodyJastrowRef.h:322-329
Module	exec

The loop is defined in:

/usr/include/c++/11/bits/stl_vector.h:1043
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:322-329

The related source loop is not unrolled or unrolled with no peel/tail loop.

gain
potential
hint
expert

Vectorization

Your loop is not vectorized. 4 data elements could be processed at once in vector registers. By vectorizing your loop, you can lower the cost of an iteration from 13.33 to 3.33 cycles (4.00x speedup).

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one:
- recompile with ftree-vectorize (included in O3) to enable loop vectorization (including FP reductions).
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

FMA

Detected 8 FMA (fused multiply-add) operations.

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

The binary loop is composed of 36 FP arithmetical operations:

28: addition or subtraction (8 inside FMA instructions)
8: multiply (all inside FMA instructions)

The binary loop is loading 256 bytes. The binary loop is storing 64 bytes.

Arithmetic intensity

Arithmetic intensity is 0.11 FP operations per loaded or stored byte.

General properties

nb instructions	74
loop length	296
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

9.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	0.50	0.50	1.25	1.25	1.25	1.25	9.00	9.00	9.00	9.00	13.33	13.33	13.33	0.00	0.00
cycles	0.50	0.50	1.25	1.25	1.25	1.25	9.00	9.00	9.00	9.00	13.33	13.33	13.33	0.00	0.00

Cycles executing div or sqrt instructions	NA
Longest recurrence chain latency (RecMII)	8.00

Cycles summary

Front-end	9.25
Data deps.	8.00
Overall L1	13.33

Vectorization ratios

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 13.33 cycles. At this rate:

19% of peak load performance is reached (19.20 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (4.80 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 43581c

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	Latency	Recip. throughput
LDR D29, [X13, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD X16, X15, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X18, X15, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X17, X15, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D30, [X30, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D31, [X24, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D7, [X8, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D3, D29, D30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D16, [X14, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D1, [X23, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D5, [X19, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D17, D3, S31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D4, D7, D0, D16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D17, [X30, X15]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D18, [X9, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D19, D2, S4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D6, D1, D18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D20, D5, D0, D6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FSUB D21, D20, S4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
STR D21, [X9, X15]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
ADD X15, X15, #32	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D22, [X13, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D23, [X30, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D24, [X24, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D25, [X8, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D2, D22, D23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D26, [X14, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D27, [X23, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D28, [X19, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D29, D2, S24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D30, D25, D0, D26	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D29, [X30, X16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D31, [X9, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D16, D19, S30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D7, D27, D31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D3, D28, D0, D7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FSUB D1, D3, S30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
STR D1, [X9, X16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D5, [X13, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D17, [X30, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D18, [X24, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D19, [X8, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D6, D5, D17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D4, [X14, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D20, [X23, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D21, [X19, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D22, D6, S18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D23, D19, D0, D4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D22, [X30, X18]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D24, [X9, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D25, D16, S23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D2, D20, D24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D26, D21, D0, D2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FSUB D27, D26, S23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
STR D27, [X9, X18]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D28, [X13, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D29, [X24, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D30, [X8, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D31, [X30, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D16, [X14, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D7, [X23, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D3, D28, D31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D5, [X19, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D17, D30, D0, D16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FSUB D1, D3, S29	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
STR D1, [X30, X17]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
FSUB D2, D25, S17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D18, [X9, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D19, D7, D18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D6, D5, D0, D19	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FSUB D4, D6, S17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
STR D4, [X9, X17]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
CMP X10, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.NE 43581c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x1bc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Function	miniqmcreference::TwoBodyJastrowRef >::acceptMove(qmcplusplus::ParticleSet&, int)
Source file and lines	TwoBodyJastrowRef.h:322-329
Module	exec

The loop is defined in:

/usr/include/c++/11/bits/stl_vector.h:1043
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:322-329

The related source loop is not unrolled or unrolled with no peel/tail loop.

gain
potential
hint
expert

Vectorization

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one:
- recompile with ftree-vectorize (included in O3) to enable loop vectorization (including FP reductions).
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

FMA

Detected 8 FMA (fused multiply-add) operations.

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

The binary loop is composed of 36 FP arithmetical operations:

28: addition or subtraction (8 inside FMA instructions)
8: multiply (all inside FMA instructions)

The binary loop is loading 256 bytes. The binary loop is storing 64 bytes.

Arithmetic intensity

Arithmetic intensity is 0.11 FP operations per loaded or stored byte.

General properties

nb instructions	74
loop length	296
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

9.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	0.50	0.50	1.25	1.25	1.25	1.25	9.00	9.00	9.00	9.00	13.33	13.33	13.33	0.00	0.00
cycles	0.50	0.50	1.25	1.25	1.25	1.25	9.00	9.00	9.00	9.00	13.33	13.33	13.33	0.00	0.00

Cycles executing div or sqrt instructions	NA
Longest recurrence chain latency (RecMII)	8.00

Cycles summary

Front-end	9.25
Data deps.	8.00
Overall L1	13.33

Vectorization ratios

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 13.33 cycles. At this rate:

19% of peak load performance is reached (19.20 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (4.80 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 43581c

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	Latency	Recip. throughput
LDR D29, [X13, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD X16, X15, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X18, X15, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X17, X15, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D30, [X30, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D31, [X24, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D7, [X8, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D3, D29, D30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D16, [X14, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D1, [X23, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D5, [X19, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D17, D3, S31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D4, D7, D0, D16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D17, [X30, X15]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D18, [X9, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D19, D2, S4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D6, D1, D18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D20, D5, D0, D6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FSUB D21, D20, S4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
STR D21, [X9, X15]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
ADD X15, X15, #32	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D22, [X13, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D23, [X30, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D24, [X24, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D25, [X8, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D2, D22, D23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D26, [X14, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D27, [X23, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D28, [X19, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D29, D2, S24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D30, D25, D0, D26	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D29, [X30, X16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D31, [X9, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D16, D19, S30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D7, D27, D31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D3, D28, D0, D7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FSUB D1, D3, S30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
STR D1, [X9, X16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D5, [X13, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D17, [X30, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D18, [X24, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D19, [X8, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D6, D5, D17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D4, [X14, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D20, [X23, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D21, [X19, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D22, D6, S18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D23, D19, D0, D4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D22, [X30, X18]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D24, [X9, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FSUB D25, D16, S23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D2, D20, D24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D26, D21, D0, D2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FSUB D27, D26, S23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
STR D27, [X9, X18]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D28, [X13, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D29, [X24, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D30, [X8, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D31, [X30, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D16, [X14, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D7, [X23, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D3, D28, D31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D5, [X19, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D17, D30, D0, D16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FSUB D1, D3, S29	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
STR D1, [X30, X17]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
FSUB D2, D25, S17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D18, [X9, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D19, D7, D18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D6, D5, D0, D19	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FSUB D4, D6, S17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
STR D4, [X9, X17]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
CMP X10, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.NE 43581c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x1bc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Report Configuration

Vectorization

Details

Workaround

FMA

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Vectorization

Details

Workaround

FMA

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