OV - exec - Loop 681

0x438e38 LDR	D30, [X15, X1,LSL #3]    [11]

0x438e3c ADD	X13, X1, #1

0x438e40 ADD	X11, X1, #2

0x438e44 ADD	X10, X1, #3

0x438e48 ADD	X9, X1, #4

0x438e4c LDR	D31, [X12, X1,LSL #3]    [1]

0x438e50 ADD	X8, X1, #5

0x438e54 ADD	X14, X1, #6

0x438e58 ADD	X16, X1, #7

0x438e5c ADD	X1, X1, #8

0x438e60 LDR	D7, [X15, X13,LSL #3]    [12]

0x438e64 LDR	D2, [X12, X13,LSL #3]    [4]

0x438e68 FMADD	D0, D30, D1, D31

0x438e6c LDR	D4, [X15, X11,LSL #3]    [10]

0x438e70 LDR	D6, [X12, X11,LSL #3]    [3]

0x438e74 FMADD	D17, D7, D1, D2

0x438e78 LDR	D3, [X15, X10,LSL #3]    [7]

0x438e7c LDR	D5, [X12, X10,LSL #3]    [2]

0x438e80 FMADD	D18, D4, D1, D6

0x438e84 LDR	D16, [X15, X9,LSL #3]    [8]

0x438e88 FADD	D19, D29, D0

0x438e8c LDR	D20, [X12, X9,LSL #3]    [16]

0x438e90 FMADD	D21, D3, D1, D5

0x438e94 LDR	D22, [X15, X8,LSL #3]    [6]

0x438e98 LDR	D23, [X12, X8,LSL #3]    [15]

0x438e9c FADD	D24, D19, D17

0x438ea0 FMADD	D25, D16, D1, D20

0x438ea4 LDR	D26, [X15, X14,LSL #3]    [13]

0x438ea8 LDR	D27, [X12, X14,LSL #3]    [5]

0x438eac FMADD	D28, D22, D1, D23

0x438eb0 LDR	D29, [X15, X16,LSL #3]    [14]

0x438eb4 FADD	D30, D24, D18

0x438eb8 LDR	D31, [X12, X16,LSL #3]    [9]

0x438ebc FMADD	D2, D26, D1, D27

0x438ec0 FADD	D0, D30, D21

0x438ec4 FMADD	D7, D29, D1, D31

0x438ec8 FADD	D4, D0, D25

0x438ecc FADD	D6, D4, D28

0x438ed0 FADD	D17, D6, D2

0x438ed4 FADD	D29, D17, D7

0x438ed8 CMP	W6, W1

0x438edc B.GT	438e38

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 190 - 191

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

190:     for (int jat = 0; jat < Nions; ++jat)

191:       lap += d2u[jat] + lapfac * du[jat];

Coverage (%)	Name	Source Location	Module
►66.67+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:207	exec
○	main._omp_fn.1	stl_vector.h:1043	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec
►33.33+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:207	exec
○	main._omp_fn.1	stl_vector.h:1043	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	3.00
Bottlenecks
Function	miniqmcreference::OneBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	OneBodyJastrowRef.h:190-191
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	16.00
CQA cycles if no scalar integer	16.00
CQA cycles if FP arith vectorized	16.00
CQA cycles if fully vectorized	4.00
Front-end cycles	5.25
DIV/SQRT cycles	0.50
P0 cycles	0.50
P1 cycles	2.25
P2 cycles	2.25
P3 cycles	2.25
P4 cycles	2.25
P5 cycles	4.00
P6 cycles	4.00
P7 cycles	4.00
P8 cycles	4.00
P9 cycles	5.33
P10 cycles	5.33
P11 cycles	5.33
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	16
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	42.00
Nb uops	42.00
Nb loads	NA
Nb stores	0.00
Nb stack references	0.00
FLOP/cycle	1.50
Nb FLOP add-sub	8.00
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	8.00
Bytes prefetched	0.00
Bytes loaded	128.00
Bytes stored	0.00
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	NA
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	NA
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	3.00
Bottlenecks
Function	miniqmcreference::OneBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	OneBodyJastrowRef.h:190-191
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	16.00
CQA cycles if no scalar integer	16.00
CQA cycles if FP arith vectorized	16.00
CQA cycles if fully vectorized	4.00
Front-end cycles	5.25
DIV/SQRT cycles	0.50
P0 cycles	0.50
P1 cycles	2.25
P2 cycles	2.25
P3 cycles	2.25
P4 cycles	2.25
P5 cycles	4.00
P6 cycles	4.00
P7 cycles	4.00
P8 cycles	4.00
P9 cycles	5.33
P10 cycles	5.33
P11 cycles	5.33
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	16
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	42.00
Nb uops	42.00
Nb loads	NA
Nb stores	0.00
Nb stack references	0.00
FLOP/cycle	1.50
Nb FLOP add-sub	8.00
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	8.00
Bytes prefetched	0.00
Bytes loaded	128.00
Bytes stored	0.00
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	NA
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	NA
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::OneBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source file and lines	OneBodyJastrowRef.h:190-191
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:190-191.

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 16.00 to 4.00 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 8 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:

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

The binary loop is loading 128 bytes.

Arithmetic intensity

Arithmetic intensity is 0.19 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	2.25	2.25	2.25	2.25	4.00	4.00	4.00	4.00	5.33	5.33	5.33	0.00	0.00
cycles	0.50	0.50	2.25	2.25	2.25	2.25	4.00	4.00	4.00	4.00	5.33	5.33	5.33	0.00	0.00

Cycles executing div or sqrt instructions	NA
Longest recurrence chain latency (RecMII)	16.00

Cycles summary

Front-end	5.25
Data deps.	16.00
Overall L1	16.00

Vectorization ratios

all	0%
load	0%
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)
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 16.00 cycles. At this rate:

8% of peak load performance is reached (8.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 438e38

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	Latency	Recip. throughput
LDR D30, [X15, X1,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD X13, X1, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X11, X1, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X10, X1, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X9, X1, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D31, [X12, X1,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD X8, X1, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X14, X1, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X16, X1, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D7, [X15, X13,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D2, [X12, X13,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D0, D30, D1, D31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D4, [X15, X11,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D6, [X12, X11,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D17, D7, D1, D2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D3, [X15, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D5, [X12, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D18, D4, D1, D6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D16, [X15, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D19, D29, D0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D20, [X12, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D21, D3, D1, D5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D22, [X15, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D23, [X12, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D24, D19, D17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D25, D16, D1, D20	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D26, [X15, X14,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D27, [X12, X14,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D28, D22, D1, D23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D29, [X15, X16,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D30, D24, D18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D31, [X12, X16,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D2, D26, D1, D27	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FADD D0, D30, D21	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D7, D29, D1, D31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FADD D4, D0, D25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D6, D4, D28	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D17, D6, D2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D29, D17, D7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
CMP W6, W1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.GT 438e38 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x118>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Function	miniqmcreference::OneBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source file and lines	OneBodyJastrowRef.h:190-191
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:190-191.

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 16.00 to 4.00 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 8 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:

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

The binary loop is loading 128 bytes.

Arithmetic intensity

Arithmetic intensity is 0.19 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	2.25	2.25	2.25	2.25	4.00	4.00	4.00	4.00	5.33	5.33	5.33	0.00	0.00
cycles	0.50	0.50	2.25	2.25	2.25	2.25	4.00	4.00	4.00	4.00	5.33	5.33	5.33	0.00	0.00

Cycles executing div or sqrt instructions	NA
Longest recurrence chain latency (RecMII)	16.00

Cycles summary

Front-end	5.25
Data deps.	16.00
Overall L1	16.00

Vectorization ratios

all	0%
load	0%
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)
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 16.00 cycles. At this rate:

8% of peak load performance is reached (8.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 438e38

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	Latency	Recip. throughput
LDR D30, [X15, X1,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD X13, X1, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X11, X1, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X10, X1, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X9, X1, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D31, [X12, X1,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD X8, X1, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X14, X1, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X16, X1, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD X1, X1, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D7, [X15, X13,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D2, [X12, X13,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D0, D30, D1, D31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D4, [X15, X11,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D6, [X12, X11,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D17, D7, D1, D2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D3, [X15, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D5, [X12, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D18, D4, D1, D6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D16, [X15, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D19, D29, D0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D20, [X12, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D21, D3, D1, D5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D22, [X15, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D23, [X12, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D24, D19, D17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D25, D16, D1, D20	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D26, [X15, X14,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
LDR D27, [X12, X14,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D28, D22, D1, D23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
LDR D29, [X15, X16,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FADD D30, D24, D18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
LDR D31, [X12, X16,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FMADD D2, D26, D1, D27	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FADD D0, D30, D21	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FMADD D7, D29, D1, D31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	4	0.25
FADD D4, D0, D25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D6, D4, D28	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D17, D6, D2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
FADD D29, D17, D7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25
CMP W6, W1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.GT 438e38 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x118>	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