OV - exec - Loop 639

0x435a2c LDR	D20, [X19, X15]    [7]

0x435a30 ADD	X16, X15, #8

0x435a34 ADD	X18, X15, #16

0x435a38 ADD	X17, X15, #24

0x435a3c LDR	D21, [X6, X15]    [3]

0x435a40 LDR	D22, [X2, X15]    [19]

0x435a44 LDR	D4, [X8, X15]    [16]

0x435a48 LDR	D23, [X7, X15]    [20]

0x435a4c FMADD	D24, D20, D21, D22

0x435a50 FMADD	D25, D4, D23, D0

0x435a54 FMSUB	D26, D4, D23, D24

0x435a58 STR	D26, [X2, X15]    [19]

0x435a5c ADD	X15, X15, #32

0x435a60 LDR	D27, [X19, X16]    [12]

0x435a64 LDR	D28, [X6, X16]    [15]

0x435a68 LDR	D29, [X2, X16]    [5]

0x435a6c LDR	D30, [X8, X16]    [9]

0x435a70 LDR	D31, [X7, X16]    [1]

0x435a74 FMADD	D16, D27, D28, D29

0x435a78 FMADD	D7, D30, D31, D25

0x435a7c FMSUB	D17, D30, D31, D16

0x435a80 STR	D17, [X2, X16]    [5]

0x435a84 LDR	D18, [X19, X18]    [14]

0x435a88 LDR	D5, [X6, X18]    [18]

0x435a8c LDR	D1, [X2, X18]    [8]

0x435a90 LDR	D19, [X8, X18]    [11]

0x435a94 LDR	D3, [X7, X18]    [4]

0x435a98 FMADD	D6, D18, D5, D1

0x435a9c FMADD	D0, D19, D3, D7

0x435aa0 FMSUB	D20, D19, D3, D6

0x435aa4 STR	D20, [X2, X18]    [8]

0x435aa8 LDR	D21, [X19, X17]    [13]

0x435aac LDR	D22, [X6, X17]    [17]

0x435ab0 LDR	D23, [X2, X17]    [6]

0x435ab4 LDR	D4, [X8, X17]    [10]

0x435ab8 LDR	D24, [X7, X17]    [2]

0x435abc FMADD	D25, D21, D22, D23

0x435ac0 FMADD	D0, D4, D24, D0

0x435ac4 FMSUB	D26, D4, D24, D25

0x435ac8 STR	D26, [X2, X17]    [6]

0x435acc CMP	X15, X10

0x435ad0 B.NE	435a2c

/home/hbollore/qaas/qaas-runs/169-816-7419/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 340 - 345

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

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

341:     {

342:       const valT newg = cur_du_pt[jat] * new_dX[jat];

343:       const valT dg   = newg - old_du_pt[jat] * old_dX[jat];

344:       save_g[jat] -= dg;

345:       cur_g += newg;

Coverage (%)	Name	Source Location	Module
►100.00+	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	1.52
Bottlenecks
Function	miniqmcreference::TwoBodyJastrowRef >::acceptMove(qmcplusplus::ParticleSet&, int)
Source	TwoBodyJastrowRef.h:340-345
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	8.00
CQA cycles if no scalar integer	8.00
CQA cycles if FP arith vectorized	8.00
CQA cycles if fully vectorized	2.00
Front-end cycles	5.25
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	4.00
P6 cycles	4.00
P7 cycles	4.00
P8 cycles	4.00
P9 cycles	8.00
P10 cycles	8.00
P11 cycles	8.00
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	42.00
Nb uops	42.00
Nb loads	NA
Nb stores	4.00
Nb stack references	0.00
FLOP/cycle	3.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	12.00
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	160.00
Bytes stored	32.00
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	1.52
Bottlenecks
Function	miniqmcreference::TwoBodyJastrowRef >::acceptMove(qmcplusplus::ParticleSet&, int)
Source	TwoBodyJastrowRef.h:340-345
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	8.00
CQA cycles if no scalar integer	8.00
CQA cycles if FP arith vectorized	8.00
CQA cycles if fully vectorized	2.00
Front-end cycles	5.25
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	4.00
P6 cycles	4.00
P7 cycles	4.00
P8 cycles	4.00
P9 cycles	8.00
P10 cycles	8.00
P11 cycles	8.00
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	42.00
Nb uops	42.00
Nb loads	NA
Nb stores	4.00
Nb stack references	0.00
FLOP/cycle	3.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	12.00
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	160.00
Bytes stored	32.00
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:340-345
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/169-816-7419/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:340-345.

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 8.00 to 2.00 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 12 FMA (fused multiply-add) operations.

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

The binary loop is composed of 24 FP arithmetical operations:

12: addition or subtraction (all inside FMA instructions)
12: multiply (all inside FMA instructions)

The binary loop is loading 160 bytes. The binary loop is storing 32 bytes.

Arithmetic intensity

Arithmetic intensity is 0.12 FP operations per loaded or stored byte.

General properties

nb instructions	42
loop length	168
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

5.25 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	4.00	4.00	4.00	4.00	8.00	8.00	8.00	0.00	0.00
cycles	0.50	0.50	1.25	1.25	1.25	1.25	4.00	4.00	4.00	4.00	8.00	8.00	8.00	0.00	0.00

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

Cycles summary

Front-end	5.25
Data deps.	8.00
Overall L1	8.00

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 8.00 cycles. At this rate:

20% of peak load performance is reached (20.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.00 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 435a2c

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	Latency	Recip. throughput
LDR D20, [X19, 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 D21, [X6, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D22, [X2, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D4, [X8, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D23, [X7, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D24, D20, D21, D22	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMADD D25, D4, D23, D0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMSUB D26, D4, D23, D24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D26, [X2, 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 D27, [X19, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D28, [X6, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D29, [X2, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D30, [X8, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D31, [X7, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D16, D27, D28, D29	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMADD D7, D30, D31, D25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMSUB D17, D30, D31, D16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D17, [X2, X16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D18, [X19, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D5, [X6, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D1, [X2, 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
LDR D3, [X7, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D6, D18, D5, D1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMADD D0, D19, D3, D7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMSUB D20, D19, D3, D6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D20, [X2, X18]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D21, [X19, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D22, [X6, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D23, [X2, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D4, [X8, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D24, [X7, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D25, D21, D22, D23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMADD D0, D4, D24, D0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMSUB D26, D4, D24, D25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D26, [X2, X17]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
CMP X15, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.NE 435a2c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x3cc>	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:340-345
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/169-816-7419/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:340-345.

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 8.00 to 2.00 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 12 FMA (fused multiply-add) operations.

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

The binary loop is composed of 24 FP arithmetical operations:

12: addition or subtraction (all inside FMA instructions)
12: multiply (all inside FMA instructions)

The binary loop is loading 160 bytes. The binary loop is storing 32 bytes.

Arithmetic intensity

Arithmetic intensity is 0.12 FP operations per loaded or stored byte.

General properties

nb instructions	42
loop length	168
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

5.25 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	4.00	4.00	4.00	4.00	8.00	8.00	8.00	0.00	0.00
cycles	0.50	0.50	1.25	1.25	1.25	1.25	4.00	4.00	4.00	4.00	8.00	8.00	8.00	0.00	0.00

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

Cycles summary

Front-end	5.25
Data deps.	8.00
Overall L1	8.00

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 8.00 cycles. At this rate:

20% of peak load performance is reached (20.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.00 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 435a2c

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	Latency	Recip. throughput
LDR D20, [X19, 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 D21, [X6, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D22, [X2, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D4, [X8, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D23, [X7, X15]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D24, D20, D21, D22	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMADD D25, D4, D23, D0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMSUB D26, D4, D23, D24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D26, [X2, 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 D27, [X19, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D28, [X6, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D29, [X2, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D30, [X8, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D31, [X7, X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D16, D27, D28, D29	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMADD D7, D30, D31, D25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMSUB D17, D30, D31, D16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D17, [X2, X16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D18, [X19, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D5, [X6, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D1, [X2, 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
LDR D3, [X7, X18]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D6, D18, D5, D1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMADD D0, D19, D3, D7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMSUB D20, D19, D3, D6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D20, [X2, X18]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
LDR D21, [X19, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D22, [X6, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D23, [X2, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D4, [X8, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D24, [X7, X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D25, D21, D22, D23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMADD D0, D4, D24, D0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FMSUB D26, D4, D24, D25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
STR D26, [X2, X17]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50
CMP X15, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.NE 435a2c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x3cc>	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