OV - exec - Loop 318

	Loop Id: 318	Module: exec	Source: stl_numeric.h:140-141	Coverage: 0.02%

0x41c2ac LDP	Q28, Q31, [X0]    [2]

0x41c2b0 ADD	X1, X0, #64

0x41c2b4 ADD	X18, X0, #128

0x41c2b8 ADD	X30, X0, #192

0x41c2bc LDP	Q26, Q17, [X0, #32]    [2]

0x41c2c0 ADD	X0, X0, #256

0x41c2c4 LDP	Q22, Q19, [X1, #16]    [3]

0x41c2c8 LDP	Q30, Q16, [X1, #48]    [3]

0x41c2cc LDP	Q25, Q24, [X18, #16]    [5]

0x41c2d0 FADD	V29.2D, V20.2D, V28.2D

0x41c2d4 FADD	V0.2D, V7.2D, V31.2D

0x41c2d8 LDUR	Q28, [X0, #448]    [1]

0x41c2dc FADD	V18.2D, V2.2D, V26.2D

0x41c2e0 FADD	V1.2D, V6.2D, V17.2D

0x41c2e4 LDUR	Q6, [X0, #320]    [1]

0x41c2e8 LDP	Q4, Q3, [X30, #16]    [4]

0x41c2ec FADD	V27.2D, V0.2D, V22.2D

0x41c2f0 LDR	Q17, [X30, #48]    [4]

0x41c2f4 FADD	V21.2D, V18.2D, V19.2D

0x41c2f8 FADD	V31.2D, V29.2D, V6.2D

0x41c2fc LDR	Q29, [X18, #48]    [5]

0x41c300 FADD	V23.2D, V1.2D, V30.2D

0x41c304 FADD	V5.2D, V27.2D, V25.2D

0x41c308 FADD	V20.2D, V21.2D, V24.2D

0x41c30c FADD	V26.2D, V31.2D, V16.2D

0x41c310 FADD	V0.2D, V23.2D, V29.2D

0x41c314 FADD	V7.2D, V5.2D, V4.2D

0x41c318 FADD	V2.2D, V20.2D, V3.2D

0x41c31c FADD	V20.2D, V26.2D, V28.2D

0x41c320 FADD	V6.2D, V0.2D, V17.2D

0x41c324 CMP	X21, X0

0x41c328 B.NE	41c2ac

/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_numeric.h: 140 - 141

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

140:       for (; __first != __last; ++__first)

141: 	__init = _GLIBCXX_MOVE_IF_20(__init) + *__first;

Coverage (%)	Name	Source Location	Module
►99.16+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main._omp_fn.1	stl_vector.h:1128	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

Path /

Metric	Value
CQA speedup if no scalar integer	1.00
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	2.00
Bottlenecks
Function	miniqmcreference::TwoBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	stl_numeric.h:140-141
Source loop unroll info	unrolled by 16
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	16
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	8.00
Front-end cycles	4.00
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	0.92
P3 cycles	0.92
P4 cycles	0.83
P5 cycles	0.83
P6 cycles	0.75
P7 cycles	0.75
P8 cycles	4.00
P9 cycles	4.00
P10 cycles	4.00
P11 cycles	4.00
P12 cycles	3.33
P13 cycles	3.33
P14 cycles	3.33
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	8
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	32.00
Nb uops	32.00
Nb loads	NA
Nb stores	0.00
Nb stack references	0.00
FLOP/cycle	4.00
Nb FLOP add-sub	32.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	32.00
Bytes prefetched	0.00
Bytes loaded	256.00
Bytes stored	0.00
Stride 0	0.00
Stride 1	0.00
Stride n	2.00
Stride unknown	3.00
Stride indirect	0.00
Vectorization ratio all	100.00
Vectorization ratio load	100.00
Vectorization ratio store	NA
Vectorization ratio mul	NA
Vectorization ratio add_sub	100.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	NA
Vector-efficiency ratio all	100.00
Vector-efficiency ratio load	100.00
Vector-efficiency ratio store	NA
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	100.00
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	1.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	2.00
Bottlenecks
Function	miniqmcreference::TwoBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	stl_numeric.h:140-141
Source loop unroll info	unrolled by 16
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	16
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	8.00
Front-end cycles	4.00
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	0.92
P3 cycles	0.92
P4 cycles	0.83
P5 cycles	0.83
P6 cycles	0.75
P7 cycles	0.75
P8 cycles	4.00
P9 cycles	4.00
P10 cycles	4.00
P11 cycles	4.00
P12 cycles	3.33
P13 cycles	3.33
P14 cycles	3.33
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	8
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	32.00
Nb uops	32.00
Nb loads	NA
Nb stores	0.00
Nb stack references	0.00
FLOP/cycle	4.00
Nb FLOP add-sub	32.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	32.00
Bytes prefetched	0.00
Bytes loaded	256.00
Bytes stored	0.00
Stride 0	0.00
Stride 1	0.00
Stride n	2.00
Stride unknown	3.00
Stride indirect	0.00
Vectorization ratio all	100.00
Vectorization ratio load	100.00
Vectorization ratio store	NA
Vectorization ratio mul	NA
Vectorization ratio add_sub	100.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	NA
Vector-efficiency ratio all	100.00
Vector-efficiency ratio load	100.00
Vector-efficiency ratio store	NA
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	100.00
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 >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source file and lines	stl_numeric.h:140-141
Module	exec

The loop is defined in /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_numeric.h:140-141.

The related source loop is unrolled by 16 (including vectorization).

gain
potential
hint
expert

Vectorization

Your loop is fully vectorized, using full register length.

Details

All VPU instructions are used in vector version (process two or more data elements in vector registers).

No data for this section

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

The binary loop is composed of 32 FP arithmetical operations:

32: addition or subtraction

The binary loop is loading 256 bytes.

Arithmetic intensity

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

General properties

nb instructions	32
loop length	128
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

4.00 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	0.92	0.92	0.83	0.83	0.75	0.75	4.00	4.00	4.00	4.00	3.33	3.33	3.33	0.00	0.00
cycles	0.50	0.50	0.92	0.92	0.83	0.83	0.75	0.75	4.00	4.00	4.00	4.00	3.33	3.33	3.33	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

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

Cycles summary

Front-end	4.00
Data deps.	8.00
Overall L1	8.00

Vectorization ratios

INT

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

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

INT+FP

all	100%
load	100%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
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:

33% of peak load performance is reached (32.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 41c2ac

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDP Q28, Q31, [X0]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ADD X1, X0, #64	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
ADD X18, X0, #128	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
ADD X30, X0, #192	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
LDP Q26, Q17, [X0, #32]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ADD X0, X0, #256	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
LDP Q22, Q19, [X1, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
LDP Q30, Q16, [X1, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
LDP Q25, Q24, [X18, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FADD V29.2D, V20.2D, V28.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V0.2D, V7.2D, V31.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDUR Q28, [X0, #448]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V18.2D, V2.2D, V26.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V1.2D, V6.2D, V17.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDUR Q6, [X0, #320]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDP Q4, Q3, [X30, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FADD V27.2D, V0.2D, V22.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR Q17, [X30, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V21.2D, V18.2D, V19.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V31.2D, V29.2D, V6.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR Q29, [X18, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V23.2D, V1.2D, V30.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V5.2D, V27.2D, V25.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V20.2D, V21.2D, V24.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V26.2D, V31.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V0.2D, V23.2D, V29.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V7.2D, V5.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V2.2D, V20.2D, V3.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V20.2D, V26.2D, V28.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V6.2D, V0.2D, V17.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
CMP X21, X0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	N/A
B.NE 41c2ac <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xf2c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	miniqmcreference::TwoBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source file and lines	stl_numeric.h:140-141
Module	exec

The loop is defined in /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_numeric.h:140-141.

The related source loop is unrolled by 16 (including vectorization).

gain
potential
hint
expert

Vectorization

Your loop is fully vectorized, using full register length.

Details

All VPU instructions are used in vector version (process two or more data elements in vector registers).

No data for this section

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

The binary loop is composed of 32 FP arithmetical operations:

32: addition or subtraction

The binary loop is loading 256 bytes.

Arithmetic intensity

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

General properties

nb instructions	32
loop length	128
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

4.00 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	0.92	0.92	0.83	0.83	0.75	0.75	4.00	4.00	4.00	4.00	3.33	3.33	3.33	0.00	0.00
cycles	0.50	0.50	0.92	0.92	0.83	0.83	0.75	0.75	4.00	4.00	4.00	4.00	3.33	3.33	3.33	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

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

Cycles summary

Front-end	4.00
Data deps.	8.00
Overall L1	8.00

Vectorization ratios

INT

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

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

INT+FP

all	100%
load	100%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
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:

33% of peak load performance is reached (32.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 41c2ac

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDP Q28, Q31, [X0]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ADD X1, X0, #64	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
ADD X18, X0, #128	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
ADD X30, X0, #192	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
LDP Q26, Q17, [X0, #32]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
ADD X0, X0, #256	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
LDP Q22, Q19, [X1, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
LDP Q30, Q16, [X1, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
LDP Q25, Q24, [X18, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FADD V29.2D, V20.2D, V28.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V0.2D, V7.2D, V31.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDUR Q28, [X0, #448]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V18.2D, V2.2D, V26.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V1.2D, V6.2D, V17.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDUR Q6, [X0, #320]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDP Q4, Q3, [X30, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.67	vect (100.0%)
FADD V27.2D, V0.2D, V22.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR Q17, [X30, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V21.2D, V18.2D, V19.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V31.2D, V29.2D, V6.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
LDR Q29, [X18, #48]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FADD V23.2D, V1.2D, V30.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V5.2D, V27.2D, V25.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V20.2D, V21.2D, V24.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V26.2D, V31.2D, V16.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V0.2D, V23.2D, V29.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V7.2D, V5.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V2.2D, V20.2D, V3.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V20.2D, V26.2D, V28.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
FADD V6.2D, V0.2D, V17.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	vect (100.0%)
CMP X21, X0	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	N/A
B.NE 41c2ac <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xf2c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Report Configuration

Vectorization

Details

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

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