OV - exec - Loop 282

	Loop Id: 282	Module: exec	Source: BsplineFunctor.h:236-241	Coverage: 0.03%

0x416d44 LDR	D12, [X6]    [9]

0x416d48 FCMPE	D6, D12

0x416d4c B.LS	416d60

0x416d50 CMN	W5, #1

0x416d54 B.EQ	416d60

0x416d58 STR	D12, [X28, X17,UXTW #3]    [8]

0x416d5c ADD	W17, W17, #1

0x416d60 LDR	D13, [X6, #8]    [9]

0x416d64 ADD	W1, W5, #1

0x416d68 ADD	X16, X6, #8

0x416d6c FCMPE	D6, D13

0x416d70 B.LS	416d84

0x416d74 CMN	W1, #1

0x416d78 B.EQ	416d84

0x416d7c STR	D13, [X28, X17,UXTW #3]    [7]

0x416d80 ADD	W17, W17, #1

0x416d84 LDR	D16, [X16, #8]    [10]

0x416d88 ADD	W25, W1, #1

0x416d8c FCMPE	D6, D16

0x416d90 B.LS	416da4

0x416d94 CMN	W25, #1

0x416d98 B.EQ	416da4

0x416d9c STR	D16, [X28, X17,UXTW #3]    [6]

0x416da0 ADD	W17, W17, #1

0x416da4 LDR	D17, [X16, #16]    [10]

0x416da8 ADD	W3, W1, #2

0x416dac FCMPE	D6, D17

0x416db0 B.LS	416dc4

0x416db4 CMN	W3, #1

0x416db8 B.EQ	416dc4

0x416dbc STR	D17, [X28, X17,UXTW #3]    [5]

0x416dc0 ADD	W17, W17, #1

0x416dc4 LDR	D18, [X16, #24]    [10]

0x416dc8 ADD	W0, W1, #3

0x416dcc FCMPE	D6, D18

0x416dd0 B.LS	416de4

0x416dd4 CMN	W0, #1

0x416dd8 B.EQ	416de4

0x416ddc STR	D18, [X28, X17,UXTW #3]    [4]

0x416de0 ADD	W17, W17, #1

0x416de4 LDR	D22, [X16, #32]    [10]

0x416de8 ADD	W4, W1, #4

0x416dec FCMPE	D6, D22

0x416df0 B.LS	416e04

0x416df4 CMN	W4, #1

0x416df8 B.EQ	416e04

0x416dfc STR	D22, [X28, X17,UXTW #3]    [3]

0x416e00 ADD	W17, W17, #1

0x416e04 LDR	D30, [X16, #40]    [10]

0x416e08 ADD	W2, W1, #5

0x416e0c FCMPE	D6, D30

0x416e10 B.LS	416e24

0x416e14 CMN	W2, #1

0x416e18 B.EQ	416e24

0x416e1c STR	D30, [X28, X17,UXTW #3]    [2]

0x416e20 ADD	W17, W17, #1

0x416e24 LDR	D31, [X16, #48]    [10]

0x416e28 ADD	W24, W1, #6

0x416e2c FCMPE	D6, D31

0x416e30 B.LS	416e44

0x416e34 CMN	W24, #1

0x416e38 B.EQ	416e44

0x416e3c STR	D31, [X28, X17,UXTW #3]    [1]

0x416e40 ADD	W17, W17, #1

0x416e44 ADD	W5, W1, #7

0x416e48 ADD	X6, X16, #56

0x416e4c CMP	W14, W5

0x416e50 B.NE	416d44

/home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 236 - 241

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

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

237:   {

238:     real_type r = distArray[jat];

239:     // pick the distances smaller than the cutoff and avoid the reference atom

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

241:       distArrayCompressed[iCount++] = distArray[jat];

Coverage (%)	Name	Source Location	Module

Path /

Metric	Value
CQA speedup if no scalar integer	1.59
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	5.67
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.06
Bottlenecks	micro-operation queue, P0, P1,
Function	miniqmcreference::OneBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	BsplineFunctor.h:236-241
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	8.50
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	8.50
CQA cycles if fully vectorized	1.50
Front-end cycles	8.50
DIV/SQRT cycles	8.50
P0 cycles	8.50
P1 cycles	6.75
P2 cycles	6.75
P3 cycles	6.75
P4 cycles	6.75
P5 cycles	8.00
P6 cycles	8.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	5.33
P10 cycles	5.33
P11 cycles	5.33
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	68.00
Nb uops	68.00
Nb loads	NA
Nb stores	8.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	15.06
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	64.00
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	18.95
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	1.59
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	5.67
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.06
Bottlenecks	micro-operation queue, P0, P1,
Function	miniqmcreference::OneBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	BsplineFunctor.h:236-241
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	8.50
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	8.50
CQA cycles if fully vectorized	1.50
Front-end cycles	8.50
DIV/SQRT cycles	8.50
P0 cycles	8.50
P1 cycles	6.75
P2 cycles	6.75
P3 cycles	6.75
P4 cycles	6.75
P5 cycles	8.00
P6 cycles	8.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	5.33
P10 cycles	5.33
P11 cycles	5.33
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	68.00
Nb uops	68.00
Nb loads	NA
Nb stores	8.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	15.06
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	64.00
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	18.95
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::OneBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source file and lines	BsplineFunctor.h:236-241
Module	exec

The loop is defined in /home/hbollore/qaas-runs/171-275-7410/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236-241.

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 8.50 to 5.33 cycles (1.59x 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 8.50 to 1.50 cycles (5.67x 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 64 bytes.

General properties

nb instructions	68
loop length	272
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

8.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	8.50	8.50	6.75	6.75	6.75	6.75	8.00	8.00	0.00	0.00	5.33	5.33	5.33	0.00	0.00
cycles	8.50	8.50	6.75	6.75	6.75	6.75	8.00	8.00	0.00	0.00	5.33	5.33	5.33	0.00	0.00

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	8.50
Overall L1	8.50

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 8.50 cycles. At this rate:

7% of peak load performance is reached (7.53 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
15% of peak store performance is reached (7.53 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 416d44

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	Latency	Recip. throughput
LDR D12, [X6]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D6, D12	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416d60 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x240>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416d60 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x240>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D12, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D13, [X6, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W1, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X16, X6, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D13	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416d84 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x264>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W1, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416d84 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x264>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D13, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D16, [X16, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W25, W1, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D16	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416da4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x284>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W25, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416da4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x284>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D16, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D17, [X16, #16]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W3, W1, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D17	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416dc4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416dc4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D17, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D18, [X16, #24]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W0, W1, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D18	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416de4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416de4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D18, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D22, [X16, #32]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W4, W1, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D22	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416e04 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W4, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416e04 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D22, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D30, [X16, #40]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W2, W1, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D30	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416e24 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x304>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416e24 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x304>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D30, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D31, [X16, #48]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W24, W1, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D31	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416e44 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x324>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W24, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416e44 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x324>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D31, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W5, W1, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X6, X16, #56	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
CMP W14, W5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.NE 416d44 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x224>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50

Function	miniqmcreference::OneBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source file and lines	BsplineFunctor.h:236-241
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 8.50 to 5.33 cycles (1.59x 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 64 bytes.

General properties

nb instructions	68
loop length	272
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

8.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	8.50	8.50	6.75	6.75	6.75	6.75	8.00	8.00	0.00	0.00	5.33	5.33	5.33	0.00	0.00
cycles	8.50	8.50	6.75	6.75	6.75	6.75	8.00	8.00	0.00	0.00	5.33	5.33	5.33	0.00	0.00

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	8.50
Overall L1	8.50

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 8.50 cycles. At this rate:

7% of peak load performance is reached (7.53 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
15% of peak store performance is reached (7.53 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 416d44

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P10	P11	P12	Latency	Recip. throughput
LDR D12, [X6]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
FCMPE D6, D12	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416d60 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x240>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416d60 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x240>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D12, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D13, [X6, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W1, W5, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X16, X6, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D13	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416d84 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x264>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W1, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416d84 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x264>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D13, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D16, [X16, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W25, W1, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D16	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416da4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x284>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W25, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416da4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x284>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D16, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D17, [X16, #16]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W3, W1, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D17	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416dc4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W3, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416dc4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D17, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D18, [X16, #24]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W0, W1, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D18	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416de4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416de4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D18, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D22, [X16, #32]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W4, W1, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D22	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416e04 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W4, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416e04 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D22, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D30, [X16, #40]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W2, W1, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D30	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416e24 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x304>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416e24 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x304>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D30, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
LDR D31, [X16, #48]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33
ADD W24, W1, #6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
FCMPE D6, D31	1	0	0	0	0	0	0	1	0	0	0	0	2	1
B.LS 416e44 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x324>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
CMN W24, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.EQ 416e44 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x324>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50
STR D31, [X28, X17,UXTW #3]	1	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50
ADD W17, W17, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD W5, W1, #7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
ADD X6, X16, #56	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25
CMP W14, W5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33
B.NE 416d44 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x224>	1	0.50	0.50	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