OV - exec - Loop 320

	Loop Id: 320	Module: exec	Source: BsplineFunctor.h:291-298	Coverage: 0.20%

0x41b5ec LDR	D6, [X30, X0,LSL #3]    [2]

0x41b5f0 FCMPE	D29, D6

0x41b5f4 B.LS	41b610

0x41b5f8 ADD	W28, W13, W0

0x41b5fc CMP	W19, W28

0x41b600 B.EQ	41b610

0x41b604 STR	W0, [X10, X8,UXTW #2]    [1]

0x41b608 STR	D6, [X14, X8,UXTW #3]    [3]

0x41b60c ADD	W8, W8, #1

0x41b610 ADD	X0, X0, #1

0x41b614 LDR	D7, [X30, X0,LSL #3]    [2]

0x41b618 FCMPE	D29, D7

0x41b61c B.LS	41b638

0x41b620 ADD	W1, W13, W0

0x41b624 CMP	W19, W1

0x41b628 B.EQ	41b638

0x41b62c STR	W0, [X10, X8,UXTW #2]    [1]

0x41b630 STR	D7, [X14, X8,UXTW #3]    [3]

0x41b634 ADD	W8, W8, #1

0x41b638 ADD	X5, X0, #1

0x41b63c LDR	D8, [X30, X5,LSL #3]    [2]

0x41b640 FCMPE	D29, D8

0x41b644 B.LS	41b660

0x41b648 ADD	W3, W13, W5

0x41b64c CMP	W19, W3

0x41b650 B.EQ	41b660

0x41b654 STR	W5, [X10, X8,UXTW #2]    [1]

0x41b658 STR	D8, [X14, X8,UXTW #3]    [3]

0x41b65c ADD	W8, W8, #1

0x41b660 ADD	X6, X0, #2

0x41b664 LDR	D9, [X30, X6,LSL #3]    [2]

0x41b668 FCMPE	D29, D9

0x41b66c B.LS	41b688

0x41b670 ADD	W7, W13, W6

0x41b674 CMP	W19, W7

0x41b678 B.EQ	41b688

0x41b67c STR	W6, [X10, X8,UXTW #2]    [1]

0x41b680 STR	D9, [X14, X8,UXTW #3]    [3]

0x41b684 ADD	W8, W8, #1

0x41b688 ADD	X28, X0, #3

0x41b68c LDR	D10, [X30, X28,LSL #3]    [2]

0x41b690 FCMPE	D29, D10

0x41b694 B.LS	41b6b0

0x41b698 ADD	W11, W13, W28

0x41b69c CMP	W19, W11

0x41b6a0 B.EQ	41b6b0

0x41b6a4 STR	W28, [X10, X8,UXTW #2]    [1]

0x41b6a8 STR	D10, [X14, X8,UXTW #3]    [3]

0x41b6ac ADD	W8, W8, #1

0x41b6b0 ADD	X1, X0, #4

0x41b6b4 LDR	D11, [X30, X1,LSL #3]    [2]

0x41b6b8 FCMPE	D29, D11

0x41b6bc B.LS	41b6d8

0x41b6c0 ADD	W5, W13, W1

0x41b6c4 CMP	W19, W5

0x41b6c8 B.EQ	41b6d8

0x41b6cc STR	W1, [X10, X8,UXTW #2]    [1]

0x41b6d0 STR	D11, [X14, X8,UXTW #3]    [3]

0x41b6d4 ADD	W8, W8, #1

0x41b6d8 ADD	X3, X0, #5

0x41b6dc LDR	D12, [X30, X3,LSL #3]    [2]

0x41b6e0 FCMPE	D29, D12

0x41b6e4 B.LS	41b700

0x41b6e8 ADD	W6, W13, W3

0x41b6ec CMP	W19, W6

0x41b6f0 B.EQ	41b700

0x41b6f4 STR	W3, [X10, X8,UXTW #2]    [1]

0x41b6f8 STR	D12, [X14, X8,UXTW #3]    [3]

0x41b6fc ADD	W8, W8, #1

0x41b700 ADD	X7, X0, #6

0x41b704 LDR	D13, [X30, X7,LSL #3]    [2]

0x41b708 FCMPE	D29, D13

0x41b70c B.LS	41b728

0x41b710 ADD	W28, W13, W7

0x41b714 CMP	W19, W28

0x41b718 B.EQ	41b728

0x41b71c STR	W7, [X10, X8,UXTW #2]    [1]

0x41b720 STR	D13, [X14, X8,UXTW #3]    [3]

0x41b724 ADD	W8, W8, #1

0x41b728 ADD	X0, X0, #7

0x41b72c CMP	X4, X0

0x41b730 B.NE	41b5ec

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 291 - 298

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

291:   for (int jat = 0; jat < iLimit; jat++)

292:   {

293:     real_type r = distArray[jat];

294:     if (r < cutoff_radius && iStart + jat != iat)

295:     {

296:       distIndices[iCount]         = jat;

297:       distArrayCompressed[iCount] = r;

298:       iCount++;

Coverage (%)	Name	Source Location	Module
►98.83+	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	1.92
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	2.56
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.21
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	BsplineFunctor.h:291-298
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	10.25
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	10.25
CQA cycles if fully vectorized	4.00
Front-end cycles	10.25
P0 cycles	8.50
P1 cycles	8.50
P2 cycles	5.58
P3 cycles	5.58
P4 cycles	5.50
P5 cycles	5.50
P6 cycles	5.42
P7 cycles	5.42
P8 cycles	8.00
P9 cycles	8.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	8.00
P13 cycles	8.00
P14 cycles	8.00
P15 cycles	4.00
P16 cycles	4.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	82.00
Nb uops	82.00
Nb loads	NA
Nb stores	16.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
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	15.61
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	96.00
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	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	39.63
Vector-efficiency ratio load	50.00
Vector-efficiency ratio store	37.50
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	25.00
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	37.50

Metric	Value
CQA speedup if no scalar integer	1.92
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	2.56
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.21
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	BsplineFunctor.h:291-298
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	10.25
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	10.25
CQA cycles if fully vectorized	4.00
Front-end cycles	10.25
P0 cycles	8.50
P1 cycles	8.50
P2 cycles	5.58
P3 cycles	5.58
P4 cycles	5.50
P5 cycles	5.50
P6 cycles	5.42
P7 cycles	5.42
P8 cycles	8.00
P9 cycles	8.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	8.00
P13 cycles	8.00
P14 cycles	8.00
P15 cycles	4.00
P16 cycles	4.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	82.00
Nb uops	82.00
Nb loads	NA
Nb stores	16.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
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	15.61
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	96.00
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	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	39.63
Vector-efficiency ratio load	50.00
Vector-efficiency ratio store	37.50
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	25.00
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	37.50

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	BsplineFunctor.h:291-298
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291-298.

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

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 6561 paths individually, rerun with max-paths=6561
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This loop has 6561 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside loop: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 10.25 to 5.33 cycles (1.92x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your loop is not vectorized. Only 39% of vector register length is used (average across all VPU instructions). By vectorizing your loop, you can lower the cost of an iteration from 10.25 to 4.00 cycles (2.56x 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
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)

No data for this section

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

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 64 bytes. The binary loop is storing 96 bytes.

General properties

nb instructions	82
loop length	328
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

10.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	8.50	8.50	5.58	5.58	5.50	5.50	5.42	5.42	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00
cycles	8.50	8.50	5.58	5.58	5.50	5.50	5.42	5.42	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00

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

Cycles summary

Front-end	10.25
Overall L1	10.25

Vectorization ratios

INT

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

all	0%
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	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 10.25 cycles. At this rate:

6% of peak load performance is reached (6.24 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
19% of peak store performance is reached (9.37 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 41b5ec

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
LDR D6, [X30, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D6	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b610 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x290>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W28, W13, W0	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
CMP W19, W28	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b610 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x290>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W0, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D6, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X0, X0, #1	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 D7, [X30, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D7	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b638 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W1, W13, W0	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
CMP W19, W1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b638 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W0, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D7, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X5, X0, #1	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 D8, [X30, X5,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D8	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b660 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W3, W13, W5	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
CMP W19, W3	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b660 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W5, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D8, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X6, X0, #2	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 D9, [X30, X6,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D9	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b688 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W7, W13, W6	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
CMP W19, W7	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b688 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W6, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D9, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X28, X0, #3	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 D10, [X30, X28,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D10	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b6b0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x330>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W11, W13, W28	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	scal (25.0%)
CMP W19, W11	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b6b0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x330>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W28, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D10, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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, X0, #4	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 D11, [X30, X1,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D11	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b6d8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x358>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W5, W13, W1	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
CMP W19, W5	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b6d8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x358>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W1, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D11, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X3, X0, #5	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 D12, [X30, X3,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D12	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b700 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x380>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W6, W13, W3	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
CMP W19, W6	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b700 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x380>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W3, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D12, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X7, X0, #6	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 D13, [X30, X7,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D13	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b728 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W28, W13, W7	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
CMP W19, W28	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b728 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W7, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D13, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X0, X0, #7	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
CMP X4, 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 41b5ec <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x26c>	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	BsplineFunctor.h:291-298
Module	exec

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 6561 paths individually, rerun with max-paths=6561
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 10.25 to 5.33 cycles (1.92x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

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
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)

No data for this section

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

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 64 bytes. The binary loop is storing 96 bytes.

General properties

nb instructions	82
loop length	328
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

10.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	8.50	8.50	5.58	5.58	5.50	5.50	5.42	5.42	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00
cycles	8.50	8.50	5.58	5.58	5.50	5.50	5.42	5.42	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00

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

Cycles summary

Front-end	10.25
Overall L1	10.25

Vectorization ratios

INT

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

all	0%
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	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 10.25 cycles. At this rate:

6% of peak load performance is reached (6.24 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
19% of peak store performance is reached (9.37 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 41b5ec

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
LDR D6, [X30, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D6	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b610 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x290>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W28, W13, W0	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
CMP W19, W28	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b610 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x290>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W0, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D6, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X0, X0, #1	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 D7, [X30, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D7	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b638 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W1, W13, W0	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
CMP W19, W1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b638 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W0, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D7, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X5, X0, #1	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 D8, [X30, X5,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D8	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b660 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W3, W13, W5	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
CMP W19, W3	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b660 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W5, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D8, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X6, X0, #2	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 D9, [X30, X6,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D9	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b688 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W7, W13, W6	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
CMP W19, W7	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b688 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W6, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D9, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X28, X0, #3	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 D10, [X30, X28,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D10	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b6b0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x330>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W11, W13, W28	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	scal (25.0%)
CMP W19, W11	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b6b0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x330>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W28, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D10, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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, X0, #4	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 D11, [X30, X1,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D11	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b6d8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x358>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W5, W13, W1	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
CMP W19, W5	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b6d8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x358>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W1, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D11, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X3, X0, #5	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 D12, [X30, X3,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D12	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b700 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x380>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W6, W13, W3	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
CMP W19, W6	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b700 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x380>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W3, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D12, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X7, X0, #6	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 D13, [X30, X7,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
FCMPE D29, D13	1	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	scal (50.0%)
B.LS 41b728 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W28, W13, W7	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
CMP W19, W28	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 41b728 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR W7, [X10, X8,UXTW #2]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STR D13, [X14, X8,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50	scal (50.0%)
ADD W8, W8, #1	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 X0, X0, #7	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
CMP X4, 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 41b5ec <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x26c>	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

Code clean check

Workaround

Vectorization

Details

Workaround

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code