OV - exec - Loop 1339

	Loop Id: 1339	Module: exec	Source: inner_product.hpp:155-155 [...]	Coverage: 0.04%

0x472100 ORR	X15, XZR, X13

0x472104 LDP	Q25, Q0, [X1]    [4]

0x472108 ORR	X18, XZR, X1

0x47210c ADD	X1, X1, #64

0x472110 LDR	Q16, [X15], #96    [2]

0x472114 LDP	Q1, Q2, [X13, #16]    [1]

0x472118 LDP	Q19, Q4, [X13, #48]    [1]

0x47211c LDP	Q3, Q5, [X13, #80]    [1]

0x472120 ADD	X13, X13, #192

0x472124 FMLA	V20.2D, V16.2D, V25.D[0]

0x472128 LDP	Q17, Q6, [X15, #16]    [2]

0x47212c LDP	Q7, Q26, [X15, #48]    [2]

0x472130 FMLA	V21.2D, V1.2D, V25.2D

0x472134 LDUR	Q18, [X1, #480]    [3]

0x472138 LDR	Q24, [X18, #48]    [5]

0x47213c FMLA	V22.2D, V2.2D, V25.D[1]

0x472140 LDR	Q23, [X15, #80]    [2]

0x472144 FMLA	V30.2D, V19.2D, V0.D[0]

0x472148 FMLA	V29.2D, V0.2D, V4.2D

0x47214c FMLA	V28.2D, V3.2D, V0.D[1]

0x472150 FMLA	V20.2D, V5.2D, V18.D[0]

0x472154 FMLA	V21.2D, V17.2D, V18.2D

0x472158 FMLA	V22.2D, V6.2D, V18.D[1]

0x47215c FMLA	V30.2D, V7.2D, V24.D[0]

0x472160 FMLA	V29.2D, V24.2D, V26.2D

0x472164 FMLA	V28.2D, V23.2D, V24.D[1]

0x472168 CMP	X12, X13

0x47216c B.NE	472100

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp: 155 - 155

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

155:   for (int i = 0; i < n; i++)

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 63 - 94

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

63:     return (a * b);

[...]

94:     (const_cast<T1&>(a) += b);

Coverage (%)	Name	Source Location	Module
►53.85+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:196	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
►45.36+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:196	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	1.14
Bottlenecks
Function	miniqmcreference::DiracDeterminantRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	inner_product.hpp:155-155,OperatorTags.h:63-63,OperatorTags.h:94-94
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	4.00
CQA cycles if no scalar integer	4.00
CQA cycles if FP arith vectorized	4.00
CQA cycles if fully vectorized	4.00
Front-end cycles	3.50
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	1.08
P3 cycles	1.08
P4 cycles	1.00
P5 cycles	1.00
P6 cycles	0.92
P7 cycles	0.92
P8 cycles	3.00
P9 cycles	3.00
P10 cycles	3.00
P11 cycles	3.00
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	4
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	28.00
Nb uops	28.00
Nb loads	NA
Nb stores	0.00
Nb stack references	0.00
FLOP/cycle	12.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	24.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	64.00
Bytes prefetched	0.00
Bytes loaded	256.00
Bytes stored	0.00
Stride 0	0.00
Stride 1	0.00
Stride n	3.00
Stride unknown	2.00
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	NA
Vectorization ratio fma	100.00
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	NA
Vector-efficiency ratio fma	100.00
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	1.14
Bottlenecks
Function	miniqmcreference::DiracDeterminantRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	inner_product.hpp:155-155,OperatorTags.h:63-63,OperatorTags.h:94-94
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	4.00
CQA cycles if no scalar integer	4.00
CQA cycles if FP arith vectorized	4.00
CQA cycles if fully vectorized	4.00
Front-end cycles	3.50
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	1.08
P3 cycles	1.08
P4 cycles	1.00
P5 cycles	1.00
P6 cycles	0.92
P7 cycles	0.92
P8 cycles	3.00
P9 cycles	3.00
P10 cycles	3.00
P11 cycles	3.00
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	4
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	28.00
Nb uops	28.00
Nb loads	NA
Nb stores	0.00
Nb stack references	0.00
FLOP/cycle	12.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	24.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	64.00
Bytes prefetched	0.00
Bytes loaded	256.00
Bytes stored	0.00
Stride 0	0.00
Stride 1	0.00
Stride n	3.00
Stride unknown	2.00
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	NA
Vectorization ratio fma	100.00
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	NA
Vector-efficiency ratio fma	100.00
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::DiracDeterminantRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source file and lines	inner_product.hpp:155-155
Module	exec

The loop is defined in:

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:155
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63,94

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

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).

FMA

Detected 24 FMA (fused multiply-add) operations.

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

The binary loop is composed of 48 FP arithmetical operations:

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

The binary loop is loading 256 bytes.

Arithmetic intensity

Arithmetic intensity is 0.19 FP operations per loaded or stored byte.

General properties

nb instructions	28
loop length	112
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

3.50 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	1.08	1.08	1.00	1.00	0.92	0.92	3.00	3.00	3.00	3.00	3.33	3.33	3.33	0.00	0.00
cycles	0.50	0.50	1.08	1.08	1.00	1.00	0.92	0.92	3.00	3.00	3.00	3.00	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)	4.00

Cycles summary

Front-end	3.50
Data deps.	4.00
Overall L1	4.00

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	NA (no add-sub vectorizable/vectorized instructions)
fma	100%
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	NA (no add-sub vectorizable/vectorized instructions)
fma	100%
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 4.00 cycles. At this rate:

66% of peak load performance is reached (64.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 472100

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
ORR X15, XZR, X13	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 Q25, Q0, [X1]	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%)
ORR X18, XZR, X1	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 X1, X1, #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
LDR Q16, [X15], #96	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDP Q1, Q2, [X13, #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 Q19, Q4, [X13, #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 Q3, Q5, [X13, #80]	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 X13, X13, #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
FMLA V20.2D, V16.2D, V25.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q17, Q6, [X15, #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 Q7, Q26, [X15, #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%)
FMLA V21.2D, V1.2D, V25.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDUR Q18, [X1, #480]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Q24, [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%)
FMLA V22.2D, V2.2D, V25.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q23, [X15, #80]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V30.2D, V19.2D, V0.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V29.2D, V0.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V28.2D, V3.2D, V0.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V20.2D, V5.2D, V18.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V21.2D, V17.2D, V18.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V22.2D, V6.2D, V18.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V30.2D, V7.2D, V24.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V29.2D, V24.2D, V26.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V28.2D, V23.2D, V24.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
CMP X12, X13	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 472100 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x320>	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::DiracDeterminantRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source file and lines	inner_product.hpp:155-155
Module	exec

The loop is defined in:

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:155
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63,94

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

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).

FMA

Detected 24 FMA (fused multiply-add) operations.

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

The binary loop is composed of 48 FP arithmetical operations:

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

The binary loop is loading 256 bytes.

Arithmetic intensity

Arithmetic intensity is 0.19 FP operations per loaded or stored byte.

General properties

nb instructions	28
loop length	112
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

3.50 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	1.08	1.08	1.00	1.00	0.92	0.92	3.00	3.00	3.00	3.00	3.33	3.33	3.33	0.00	0.00
cycles	0.50	0.50	1.08	1.08	1.00	1.00	0.92	0.92	3.00	3.00	3.00	3.00	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)	4.00

Cycles summary

Front-end	3.50
Data deps.	4.00
Overall L1	4.00

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	NA (no add-sub vectorizable/vectorized instructions)
fma	100%
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	NA (no add-sub vectorizable/vectorized instructions)
fma	100%
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 4.00 cycles. At this rate:

66% of peak load performance is reached (64.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 472100

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
ORR X15, XZR, X13	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 Q25, Q0, [X1]	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%)
ORR X18, XZR, X1	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 X1, X1, #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
LDR Q16, [X15], #96	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDP Q1, Q2, [X13, #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 Q19, Q4, [X13, #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 Q3, Q5, [X13, #80]	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 X13, X13, #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
FMLA V20.2D, V16.2D, V25.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDP Q17, Q6, [X15, #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 Q7, Q26, [X15, #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%)
FMLA V21.2D, V1.2D, V25.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDUR Q18, [X1, #480]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDR Q24, [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%)
FMLA V22.2D, V2.2D, V25.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
LDR Q23, [X15, #80]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
FMLA V30.2D, V19.2D, V0.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V29.2D, V0.2D, V4.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V28.2D, V3.2D, V0.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V20.2D, V5.2D, V18.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V21.2D, V17.2D, V18.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V22.2D, V6.2D, V18.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V30.2D, V7.2D, V24.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V29.2D, V24.2D, V26.2D	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
FMLA V28.2D, V23.2D, V24.D[1]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25	vect (100.0%)
CMP X12, X13	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 472100 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x320>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Report Configuration

Vectorization

Details

FMA

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

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