OV - exec - Loop 647

	Loop Id: 647	Module: exec	Source: BsplineFunctor.h:291-297	Coverage: 0.03%

0x4362e0 LDR	D8, [X1, X0,LSL #3]    [1]

0x4362e4 FCMPE	D8, D0

0x4362e8 B.GE	436308

0x4362ec ADD	W30, W14, W0

0x4362f0 CMP	W30, W20

0x4362f4 B.EQ	436308

0x4362f8 SBFM	X17, X3, #0, #31

0x4362fc ADD	W3, W3, #1

0x436300 STR	W0, [X13, X17,LSL #2]    [6]

0x436304 STR	D8, [X6, X17,LSL #3]    [14]

0x436308 ADD	X0, X0, #1

0x43630c LDR	D9, [X1, X0,LSL #3]    [19]

0x436310 FCMPE	D9, D0

0x436314 B.GE	436334

0x436318 ADD	W30, W14, W0

0x43631c CMP	W30, W20

0x436320 B.EQ	436334

0x436324 SBFM	X17, X3, #0, #31

0x436328 ADD	W3, W3, #1

0x43632c STR	W0, [X13, X17,LSL #2]    [6]

0x436330 STR	D9, [X6, X17,LSL #3]    [14]

0x436334 ADD	X17, X0, #1

0x436338 LDR	D10, [X1, X17,LSL #3]    [8]

0x43633c FCMPE	D10, D0

0x436340 B.GE	436360

0x436344 ADD	W30, W14, W17

0x436348 CMP	W30, W20

0x43634c B.EQ	436360

0x436350 SBFM	X30, X3, #0, #31

0x436354 ADD	W3, W3, #1

0x436358 STR	W17, [X13, X30,LSL #2]    [22]

0x43635c STR	D10, [X6, X30,LSL #3]    [4]

0x436360 ADD	X17, X0, #2

0x436364 LDR	D11, [X1, X17,LSL #3]    [13]

0x436368 FCMPE	D11, D0

0x43636c B.GE	43638c

0x436370 ADD	W30, W14, W17

0x436374 CMP	W30, W20

0x436378 B.EQ	43638c

0x43637c SBFM	X30, X3, #0, #31

0x436380 ADD	W3, W3, #1

0x436384 STR	W17, [X13, X30,LSL #2]    [21]

0x436388 STR	D11, [X6, X30,LSL #3]    [3]

0x43638c ADD	X17, X0, #3

0x436390 LDR	D12, [X1, X17,LSL #3]    [5]

0x436394 FCMPE	D12, D0

0x436398 B.GE	4363b8

0x43639c ADD	W30, W14, W17

0x4363a0 CMP	W30, W20

0x4363a4 B.EQ	4363b8

0x4363a8 SBFM	X30, X3, #0, #31

0x4363ac ADD	W3, W3, #1

0x4363b0 STR	W17, [X13, X30,LSL #2]    [20]

0x4363b4 STR	D12, [X6, X30,LSL #3]    [2]

0x4363b8 ADD	X17, X0, #4

0x4363bc LDR	D13, [X1, X17,LSL #3]    [7]

0x4363c0 FCMPE	D13, D0

0x4363c4 B.GE	4363e4

0x4363c8 ADD	W30, W14, W17

0x4363cc CMP	W30, W20

0x4363d0 B.EQ	4363e4

0x4363d4 SBFM	X30, X3, #0, #31

0x4363d8 ADD	W3, W3, #1

0x4363dc STR	W17, [X13, X30,LSL #2]    [12]

0x4363e0 STR	D13, [X6, X30,LSL #3]    [17]

0x4363e4 ADD	X17, X0, #5

0x4363e8 LDR	D15, [X1, X17,LSL #3]    [18]

0x4363ec FCMPE	D15, D0

0x4363f0 B.GE	436410

0x4363f4 ADD	W30, W14, W17

0x4363f8 CMP	W30, W20

0x4363fc B.EQ	436410

0x436400 SBFM	X30, X3, #0, #31

0x436404 ADD	W3, W3, #1

0x436408 STR	W17, [X13, X30,LSL #2]    [11]

0x43640c STR	D15, [X6, X30,LSL #3]    [16]

0x436410 ADD	X17, X0, #6

0x436414 LDR	D17, [X1, X17,LSL #3]    [9]

0x436418 FCMPE	D17, D0

0x43641c B.GE	43643c

0x436420 ADD	W30, W14, W17

0x436424 CMP	W30, W20

0x436428 B.EQ	43643c

0x43642c SBFM	X30, X3, #0, #31

0x436430 ADD	W3, W3, #1

0x436434 STR	W17, [X13, X30,LSL #2]    [10]

0x436438 STR	D17, [X6, X30,LSL #3]    [15]

0x43643c ADD	X0, X0, #7

0x436440 CMP	W5, W0

0x436444 B.GT	4362e0

/home/hbollore/qaas/qaas-runs/169-816-8620/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
►100.00+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:420	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:181	exec
○	main._omp_fn.0	miniqmc.cpp:390	exec
○	GOMP_parallel		libomp.so
○	main	stl_vector.h:1043	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec

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 >::recompute(qmcplusplus::ParticleSet&)
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 >::recompute(qmcplusplus::ParticleSet&)
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 >::recompute(qmcplusplus::ParticleSet&)
Source file and lines	BsplineFunctor.h:291-297
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/169-816-8620/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:
- recompile with ftree-vectorize (included in O3) to enable loop vectorization (including FP reductions).
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

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

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: 4362e0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR D8, [X1, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 436308 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436308 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X17, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #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, 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 D8, [X6, 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 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 D9, [X1, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D9, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 436334 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436334 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X17, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #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, 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 D9, [X6, 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 X17, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D10, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D10, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 436360 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x420>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436360 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x420>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,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, [X6, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X17, X0, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D11, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D11, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 43638c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x44c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43638c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x44c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,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, [X6, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X17, X0, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D12, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D12, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 4363b8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x478>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 4363b8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x478>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D12, [X6, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X17, X0, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D13, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D13, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 4363e4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 4363e4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,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, [X6, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X17, X0, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D15, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D15, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 436410 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436410 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D15, [X6, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X17, X0, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D17, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D17, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 43643c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43643c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D17, [X6, X30,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 W5, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.GT 4362e0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3a0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Function	miniqmcreference::TwoBodyJastrowRef >::recompute(qmcplusplus::ParticleSet&)
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:
- recompile with ftree-vectorize (included in O3) to enable loop vectorization (including FP reductions).
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

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

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: 4362e0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR D8, [X1, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D8, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 436308 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436308 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X17, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #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, 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 D8, [X6, 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 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 D9, [X1, X0,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D9, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 436334 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436334 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X17, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #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, 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 D9, [X6, 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 X17, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D10, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D10, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 436360 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x420>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436360 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x420>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,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, [X6, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X17, X0, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D11, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D11, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 43638c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x44c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43638c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x44c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,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, [X6, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X17, X0, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D12, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D12, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 4363b8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x478>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 4363b8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x478>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D12, [X6, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X17, X0, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D13, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D13, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 4363e4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 4363e4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,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, [X6, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X17, X0, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D15, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D15, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 436410 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 436410 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D15, [X6, X30,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	0	0	2	0.50
ADD X17, X0, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
LDR D17, [X1, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
FCMPE D17, D0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1
B.GE 43643c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD W30, W14, W17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP W30, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.EQ 43643c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x4fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SBFM X30, X3, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD W3, W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
STR W17, [X13, X30,LSL #2]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR D17, [X6, X30,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 W5, W0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.33
B.GT 4362e0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x3a0>	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