OV - exec - Loop 321

	Loop Id: 321	Module: exec	Source: BsplineFunctor.h:291-297	Coverage: 0.2%

0x41a128 LDR	D6, [X5, X4,LSL #3]    [10]

0x41a12c FCMPE	D31, D6

0x41a130 B.LS	41a150

0x41a134 ADD	W8, W10, W4

0x41a138 CMP	W19, W8

0x41a13c B.EQ	41a150

0x41a140 ORR	W9, WZR, W7

0x41a144 ADD	W7, W7, #1

0x41a148 STR	W4, [X12, X9,LSL #2]    [3]

0x41a14c STR	D6, [X11, X9,LSL #3]    [14]

0x41a150 ADD	X4, X4, #1

0x41a154 LDR	D7, [X5, X4,LSL #3]    [4]

0x41a158 FCMPE	D31, D7

0x41a15c B.LS	41a17c

0x41a160 ADD	W16, W10, W4

0x41a164 CMP	W19, W16

0x41a168 B.EQ	41a17c

0x41a16c ORR	W17, WZR, W7

0x41a170 ADD	W7, W7, #1

0x41a174 STR	W4, [X12, X17,LSL #2]    [22]

0x41a178 STR	D7, [X11, X17,LSL #3]    [8]

0x41a17c ADD	X8, X4, #1

0x41a180 LDR	D8, [X5, X8,LSL #3]    [15]

0x41a184 FCMPE	D31, D8

0x41a188 B.LS	41a1a8

0x41a18c ADD	W9, W10, W8

0x41a190 CMP	W19, W9

0x41a194 B.EQ	41a1a8

0x41a198 ORR	W16, WZR, W7

0x41a19c ADD	W7, W7, #1

0x41a1a0 STR	W8, [X12, X16,LSL #2]    [19]

0x41a1a4 STR	D8, [X11, X16,LSL #3]    [5]

0x41a1a8 ADD	X8, X4, #2

0x41a1ac LDR	D9, [X5, X8,LSL #3]    [24]

0x41a1b0 FCMPE	D31, D9

0x41a1b4 B.LS	41a1d4

0x41a1b8 ADD	W17, W10, W8

0x41a1bc CMP	W19, W17

0x41a1c0 B.EQ	41a1d4

0x41a1c4 ORR	W9, WZR, W7

0x41a1c8 ADD	W7, W7, #1

0x41a1cc STR	W8, [X12, X9,LSL #2]    [2]

0x41a1d0 STR	D9, [X11, X9,LSL #3]    [13]

0x41a1d4 ADD	X16, X4, #3

0x41a1d8 LDR	D10, [X5, X16,LSL #3]    [9]

0x41a1dc FCMPE	D31, D10

0x41a1e0 B.LS	41a200

0x41a1e4 ADD	W8, W10, W16

0x41a1e8 CMP	W19, W8

0x41a1ec B.EQ	41a200

0x41a1f0 ORR	W17, WZR, W7

0x41a1f4 ADD	W7, W7, #1

0x41a1f8 STR	W16, [X12, X17,LSL #2]    [21]

0x41a1fc STR	D10, [X11, X17,LSL #3]    [7]

0x41a200 ADD	X9, X4, #4

0x41a204 LDR	D11, [X5, X9,LSL #3]    [17]

0x41a208 FCMPE	D31, D11

0x41a20c B.LS	41a22c

0x41a210 ADD	W16, W10, W9

0x41a214 CMP	W19, W16

0x41a218 B.EQ	41a22c

0x41a21c ORR	W8, WZR, W7

0x41a220 ADD	W7, W7, #1

0x41a224 STR	W9, [X12, X8,LSL #2]    [1]

0x41a228 STR	D11, [X11, X8,LSL #3]    [12]

0x41a22c ADD	X9, X4, #5

0x41a230 LDR	D13, [X5, X9,LSL #3]    [18]

0x41a234 FCMPE	D31, D13

0x41a238 B.LS	41a258

0x41a23c ADD	W17, W10, W9

0x41a240 CMP	W19, W17

0x41a244 B.EQ	41a258

0x41a248 ORR	W16, WZR, W7

0x41a24c ADD	W7, W7, #1

0x41a250 STR	W9, [X12, X16,LSL #2]    [11]

0x41a254 STR	D13, [X11, X16,LSL #3]    [23]

0x41a258 ADD	X8, X4, #6

0x41a25c LDR	D14, [X5, X8,LSL #3]    [16]

0x41a260 FCMPE	D31, D14

0x41a264 B.LS	41a284

0x41a268 ADD	W9, W10, W8

0x41a26c CMP	W19, W9

0x41a270 B.EQ	41a284

0x41a274 ORR	W17, WZR, W7

0x41a278 ADD	W7, W7, #1

0x41a27c STR	W8, [X12, X17,LSL #2]    [20]

0x41a280 STR	D14, [X11, X17,LSL #3]    [6]

0x41a284 ADD	X4, X4, #7

0x41a288 CMP	X4, X18

0x41a28c B.NE	41a128

/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 291 - 297

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

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;

Coverage (%)	Name	Source Location	Module

Path /

Metric	Value
CQA speedup if no scalar integer	2.11
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	6.75
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.10
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	BsplineFunctor.h:291-297
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	11.25
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	11.25
CQA cycles if fully vectorized	1.67
Front-end cycles	11.25
DIV/SQRT cycles	8.50
P0 cycles	8.50
P1 cycles	10.25
P2 cycles	10.25
P3 cycles	10.25
P4 cycles	10.25
P5 cycles	8.00
P6 cycles	8.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	8.00
P10 cycles	8.00
P11 cycles	8.00
P12 cycles	4.00
P13 cycles	4.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	90.00
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	14.22
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	18.75
Vector-efficiency ratio load	25.00
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	12.50

Metric	Value
CQA speedup if no scalar integer	2.11
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	6.75
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.10
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source	BsplineFunctor.h:291-297
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	11.25
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	11.25
CQA cycles if fully vectorized	1.67
Front-end cycles	11.25
DIV/SQRT cycles	8.50
P0 cycles	8.50
P1 cycles	10.25
P2 cycles	10.25
P3 cycles	10.25
P4 cycles	10.25
P5 cycles	8.00
P6 cycles	8.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	8.00
P10 cycles	8.00
P11 cycles	8.00
P12 cycles	4.00
P13 cycles	4.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	90.00
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	14.22
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	18.75
Vector-efficiency ratio load	25.00
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	12.50

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:291-297
Module	exec

The loop is defined in /home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291-297.

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

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 11.25 to 5.33 cycles (2.11x 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 18% of vector register length is used (average across all VPU instructions). By vectorizing your loop, you can lower the cost of an iteration from 11.25 to 1.67 cycles (6.75x 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	90
loop length	360
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

11.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00
cycles	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.25
Overall L1	11.25

Vectorization ratios

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 11.25 cycles. At this rate:

5% of peak load performance is reached (5.69 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
17% of peak store performance is reached (8.53 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 41a128

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR D6, [X5, X4,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D6	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a150 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W8, W10, W4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a150 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W9, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W4, [X12, X9,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D6, [X11, X9,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X4, X4, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D7, [X5, X4,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D7	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a17c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2dc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W16, W10, W4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a17c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2dc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W17, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W4, [X12, X17,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D7, [X11, X17,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X8, X4, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D8, [X5, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D8	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a1a8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W9, W10, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a1a8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W16, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W8, [X12, X16,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D8, [X11, X16,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X8, X4, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D9, [X5, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D9	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a1d4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x334>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W17, W10, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a1d4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x334>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W9, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W8, [X12, X9,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D9, [X11, X9,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X16, X4, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D10, [X5, X16,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D10	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a200 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x360>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W8, W10, W16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a200 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x360>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W17, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W16, [X12, X17,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D10, [X11, X17,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X9, X4, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D11, [X5, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D11	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a22c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x38c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W16, W10, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a22c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x38c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W8, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W9, [X12, X8,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D11, [X11, X8,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X9, X4, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D13, [X5, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D13	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a258 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W17, W10, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a258 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W16, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W9, [X12, X16,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D13, [X11, X16,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X8, X4, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D14, [X5, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D14	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a284 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W9, W10, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a284 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W17, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W8, [X12, X17,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D14, [X11, X17,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X4, X4, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP X4, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.NE 41a128 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x288>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Function	miniqmcreference::TwoBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)
Source file and lines	BsplineFunctor.h:291-297
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

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 11.25 to 5.33 cycles (2.11x 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	90
loop length	360
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

11.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00
cycles	8.50	8.50	10.25	10.25	10.25	10.25	8.00	8.00	0.00	0.00	8.00	8.00	8.00	4.00	4.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.25
Overall L1	11.25

Vectorization ratios

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 11.25 cycles. At this rate:

5% of peak load performance is reached (5.69 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
17% of peak store performance is reached (8.53 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 41a128

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR D6, [X5, X4,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D6	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a150 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W8, W10, W4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a150 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W9, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W4, [X12, X9,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D6, [X11, X9,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X4, X4, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D7, [X5, X4,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D7	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a17c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2dc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W16, W10, W4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a17c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2dc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W17, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W4, [X12, X17,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D7, [X11, X17,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X8, X4, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D8, [X5, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D8	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a1a8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W9, W10, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a1a8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W16, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W8, [X12, X16,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D8, [X11, X16,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X8, X4, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D9, [X5, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D9	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a1d4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x334>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W17, W10, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a1d4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x334>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W9, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W8, [X12, X9,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D9, [X11, X9,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X16, X4, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D10, [X5, X16,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D10	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a200 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x360>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W8, W10, W16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a200 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x360>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W17, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W16, [X12, X17,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D10, [X11, X17,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X9, X4, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D11, [X5, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D11	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a22c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x38c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W16, W10, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a22c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x38c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W8, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W9, [X12, X8,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D11, [X11, X8,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X9, X4, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D13, [X5, X9,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D13	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a258 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W17, W10, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a258 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W16, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W9, [X12, X16,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D13, [X11, X16,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X8, X4, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D14, [X5, X8,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D31, D14	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 41a284 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W9, W10, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 41a284 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W17, WZR, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W7, W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W8, [X12, X17,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D14, [X11, X17,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X4, X4, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP X4, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.NE 41a128 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x288>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50

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