OV - exec - Loop 683

	Loop Id: 683	Module: exec	Source: BsplineFunctor.h:291-297	Coverage: 0.11%

0x435f1c LDR	D6, [X26, X0,LSL #3]    [24]

0x435f20 FCMPE	D31, D6

0x435f24 B.LS	435f44

0x435f28 ADD	W11, W18, W0

0x435f2c CMP	W19, W11

0x435f30 B.EQ	435f44

0x435f34 ORR	W16, WZR, W8

0x435f38 ADD	W8, W8, #1

0x435f3c STR	W0, [X13, X16,LSL #2]    [12]

0x435f40 STR	D6, [X12, X16,LSL #3]    [20]

0x435f44 ADD	X0, X0, #1

0x435f48 LDR	D7, [X26, X0,LSL #3]    [16]

0x435f4c FCMPE	D31, D7

0x435f50 B.LS	435f70

0x435f54 ADD	W1, W18, W0

0x435f58 CMP	W19, W1

0x435f5c B.EQ	435f70

0x435f60 ORR	W2, WZR, W8

0x435f64 ADD	W8, W8, #1

0x435f68 STR	W0, [X13, X2,LSL #2]    [22]

0x435f6c STR	D7, [X12, X2,LSL #3]    [9]

0x435f70 ADD	X7, X0, #1

0x435f74 LDR	D8, [X26, X7,LSL #3]    [23]

0x435f78 FCMPE	D31, D8

0x435f7c B.LS	435f9c

0x435f80 ADD	W9, W18, W7

0x435f84 CMP	W19, W9

0x435f88 B.EQ	435f9c

0x435f8c ORR	W10, WZR, W8

0x435f90 ADD	W8, W8, #1

0x435f94 STR	W7, [X13, X10,LSL #2]    [7]

0x435f98 STR	D8, [X12, X10,LSL #3]    [18]

0x435f9c ADD	X11, X0, #2

0x435fa0 LDR	D9, [X26, X11,LSL #3]    [5]

0x435fa4 FCMPE	D31, D9

0x435fa8 B.LS	435fc8

0x435fac ADD	W16, W18, W11

0x435fb0 CMP	W19, W16

0x435fb4 B.EQ	435fc8

0x435fb8 ORR	W1, WZR, W8

0x435fbc ADD	W8, W8, #1

0x435fc0 STR	W11, [X13, X1,LSL #2]    [21]

0x435fc4 STR	D9, [X12, X1,LSL #3]    [8]

0x435fc8 ADD	X2, X0, #3

0x435fcc LDR	D10, [X26, X2,LSL #3]    [15]

0x435fd0 FCMPE	D31, D10

0x435fd4 B.LS	435ff4

0x435fd8 ADD	W7, W18, W2

0x435fdc CMP	W19, W7

0x435fe0 B.EQ	435ff4

0x435fe4 ORR	W9, WZR, W8

0x435fe8 ADD	W8, W8, #1

0x435fec STR	W2, [X13, X9,LSL #2]    [4]

0x435ff0 STR	D10, [X12, X9,LSL #3]    [14]

0x435ff4 ADD	X10, X0, #4

0x435ff8 LDR	D11, [X26, X10,LSL #3]    [2]

0x435ffc FCMPE	D31, D11

0x436000 B.LS	436020

0x436004 ADD	W11, W18, W10

0x436008 CMP	W19, W11

0x43600c B.EQ	436020

0x436010 ORR	W16, WZR, W8

0x436014 ADD	W8, W8, #1

0x436018 STR	W10, [X13, X16,LSL #2]    [11]

0x43601c STR	D11, [X12, X16,LSL #3]    [19]

0x436020 ADD	X1, X0, #5

0x436024 LDR	D13, [X26, X1,LSL #3]    [10]

0x436028 FCMPE	D31, D13

0x43602c B.LS	43604c

0x436030 ADD	W2, W18, W1

0x436034 CMP	W19, W2

0x436038 B.EQ	43604c

0x43603c ORR	W7, WZR, W8

0x436040 ADD	W8, W8, #1

0x436044 STR	W1, [X13, X7,LSL #2]    [1]

0x436048 STR	D13, [X12, X7,LSL #3]    [13]

0x43604c ADD	X9, X0, #6

0x436050 LDR	D14, [X26, X9,LSL #3]    [3]

0x436054 FCMPE	D31, D14

0x436058 B.LS	436078

0x43605c ADD	W10, W18, W9

0x436060 CMP	W19, W10

0x436064 B.EQ	436078

0x436068 ORR	W11, WZR, W8

0x43606c ADD	W8, W8, #1

0x436070 STR	W9, [X13, X11,LSL #2]    [17]

0x436074 STR	D14, [X12, X11,LSL #3]    [6]

0x436078 ADD	X0, X0, #7

0x43607c CMP	X30, X0

0x436080 B.NE	435f1c

/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 >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
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 >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
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 >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
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: 435f1c

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR D6, [X26, X0,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 435f44 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W11, W18, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 435f44 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W16, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X13, 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 D6, [X12, 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 X0, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D7, [X26, X0,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 435f70 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W1, W18, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 435f70 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W2, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X13, X2,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, [X12, X2,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X7, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D8, [X26, X7,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 435f9c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W9, W18, W7	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 435f9c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W10, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W7, [X13, X10,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, [X12, X10,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X11, X0, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D9, [X26, X11,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 435fc8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x328>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W16, W18, W11	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 435fc8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x328>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W1, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W11, [X13, X1,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, [X12, X1,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X2, X0, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D10, [X26, X2,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 435ff4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x354>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W7, W18, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 435ff4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x354>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W9, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W2, [X13, 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 D10, [X12, 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 X10, X0, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D11, [X26, X10,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 436020 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x380>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W11, W18, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436020 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x380>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W16, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W10, [X13, 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 D11, [X12, 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 X1, X0, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D13, [X26, X1,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 43604c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3ac>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W2, W18, W1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43604c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3ac>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W7, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W1, [X13, X7,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, [X12, X7,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, X0, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D14, [X26, 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, D14	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 436078 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W10, W18, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436078 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W11, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W9, [X13, X11,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, [X12, X11,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X0, X0, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP X30, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.NE 435f1c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x27c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Function	miniqmcreference::TwoBodyJastrowRef >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
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: 435f1c

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR D6, [X26, X0,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 435f44 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W11, W18, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 435f44 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W16, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X13, 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 D6, [X12, 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 X0, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D7, [X26, X0,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 435f70 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W1, W18, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 435f70 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W2, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W0, [X13, X2,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, [X12, X2,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X7, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D8, [X26, X7,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 435f9c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W9, W18, W7	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 435f9c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W10, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W7, [X13, X10,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, [X12, X10,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X11, X0, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D9, [X26, X11,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 435fc8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x328>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W16, W18, W11	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 435fc8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x328>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W1, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W11, [X13, X1,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, [X12, X1,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X2, X0, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D10, [X26, X2,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 435ff4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x354>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W7, W18, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 435ff4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x354>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W9, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W2, [X13, 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 D10, [X12, 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 X10, X0, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D11, [X26, X10,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 436020 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x380>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W11, W18, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436020 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x380>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W16, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W10, [X13, 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 D11, [X12, 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 X1, X0, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D13, [X26, X1,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 43604c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3ac>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W2, W18, W1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43604c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3ac>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W7, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W1, [X13, X7,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, [X12, X7,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, X0, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D14, [X26, 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, D14	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.LS 436078 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W10, W18, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W19, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436078 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR W11, WZR, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W8, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W9, [X13, X11,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, [X12, X11,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X0, X0, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP X30, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.NE 435f1c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x27c>	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