OV - exec - Loop 614

	Loop Id: 614	Module: exec	Source: BsplineFunctor.h:291-298	Coverage: 0.24%

0x456347 VMOVSD	(%RSI,%RAX,8),%XMM10    [1]

0x45634c VCOMISD	%XMM10,%XMM2

0x456351 JBE	456369

0x456353 LEA	(%RDI,%RAX,1),%EDX

0x456356 CMP	%EDX,%EBX

0x456358 JE	456369

0x45635a MOVSXD	%ECX,%R9

0x45635d MOV	%EAX,(%R12,%R9,4)    [2]

0x456361 VMOVSD	%XMM10,(%R15,%R9,8)    [3]

0x456367 INC	%ECX

0x456369 INC	%RAX

0x45636c VMOVSD	(%RSI,%RAX,8),%XMM11    [1]

0x456371 VCOMISD	%XMM11,%XMM2

0x456376 JBE	45638e

0x456378 LEA	(%RDI,%RAX,1),%EDX

0x45637b CMP	%EDX,%EBX

0x45637d JE	45638e

0x45637f MOVSXD	%ECX,%R9

0x456382 MOV	%EAX,(%R12,%R9,4)    [2]

0x456386 VMOVSD	%XMM11,(%R15,%R9,8)    [3]

0x45638c INC	%ECX

0x45638e LEA	0x1(%RAX),%RDX

0x456392 VMOVSD	(%RSI,%RDX,8),%XMM12    [1]

0x456397 VCOMISD	%XMM12,%XMM2

0x45639c JBE	4563b6

0x45639e LEA	(%RDI,%RDX,1),%R9D

0x4563a2 CMP	%R9D,%EBX

0x4563a5 JE	4563b6

0x4563a7 MOVSXD	%ECX,%R9

0x4563aa MOV	%EDX,(%R12,%R9,4)    [2]

0x4563ae VMOVSD	%XMM12,(%R15,%R9,8)    [3]

0x4563b4 INC	%ECX

0x4563b6 LEA	0x2(%RAX),%RDX

0x4563ba VMOVSD	(%RSI,%RDX,8),%XMM13    [1]

0x4563bf VCOMISD	%XMM13,%XMM2

0x4563c4 JBE	4563de

0x4563c6 LEA	(%RDI,%RDX,1),%R9D

0x4563ca CMP	%R9D,%EBX

0x4563cd JE	4563de

0x4563cf MOVSXD	%ECX,%R9

0x4563d2 MOV	%EDX,(%R12,%R9,4)    [2]

0x4563d6 VMOVSD	%XMM13,(%R15,%R9,8)    [3]

0x4563dc INC	%ECX

0x4563de LEA	0x3(%RAX),%RDX

0x4563e2 VMOVSD	(%RSI,%RDX,8),%XMM14    [1]

0x4563e7 VCOMISD	%XMM14,%XMM2

0x4563ec JBE	456406

0x4563ee LEA	(%RDI,%RDX,1),%R9D

0x4563f2 CMP	%R9D,%EBX

0x4563f5 JE	456406

0x4563f7 MOVSXD	%ECX,%R9

0x4563fa MOV	%EDX,(%R12,%R9,4)    [2]

0x4563fe VMOVSD	%XMM14,(%R15,%R9,8)    [3]

0x456404 INC	%ECX

0x456406 LEA	0x4(%RAX),%RDX

0x45640a VMOVSD	(%RSI,%RDX,8),%XMM15    [1]

0x45640f VCOMISD	%XMM15,%XMM2

0x456414 JBE	45642e

0x456416 LEA	(%RDI,%RDX,1),%R9D

0x45641a CMP	%R9D,%EBX

0x45641d JE	45642e

0x45641f MOVSXD	%ECX,%R9

0x456422 MOV	%EDX,(%R12,%R9,4)    [2]

0x456426 VMOVSD	%XMM15,(%R15,%R9,8)    [3]

0x45642c INC	%ECX

0x45642e LEA	0x5(%RAX),%RDX

0x456432 VMOVSD	(%RSI,%RDX,8),%XMM3    [1]

0x456437 VCOMISD	%XMM3,%XMM2

0x45643b JBE	456455

0x45643d LEA	(%RDI,%RDX,1),%R9D

0x456441 CMP	%R9D,%EBX

0x456444 JE	456455

0x456446 MOVSXD	%ECX,%R9

0x456449 MOV	%EDX,(%R12,%R9,4)    [2]

0x45644d VMOVSD	%XMM3,(%R15,%R9,8)    [3]

0x456453 INC	%ECX

0x456455 LEA	0x6(%RAX),%RDX

0x456459 VMOVSD	(%RSI,%RDX,8),%XMM4    [1]

0x45645e VCOMISD	%XMM4,%XMM2

0x456462 JBE	45647c

0x456464 LEA	(%RDI,%RDX,1),%R9D

0x456468 CMP	%R9D,%EBX

0x45646b JE	45647c

0x45646d MOVSXD	%ECX,%R9

0x456470 MOV	%EDX,(%R12,%R9,4)    [2]

0x456474 VMOVSD	%XMM4,(%R15,%R9,8)    [3]

0x45647a INC	%ECX

0x45647c ADD	$0x7,%RAX

0x456480 CMP	%RAX,%R8

0x456483 JNE	456347

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 291 - 298

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

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

292:   {

293:     real_type r = distArray[jat];

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

295:     {

296:       distIndices[iCount]         = jat;

297:       distArrayCompressed[iCount] = r;

298:       iCount++;

Coverage (%)	Name	Source Location	Module
►97.64+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:315	exec
○	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	refwrap.h:350	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
►2.36+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:315	exec
○	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main._omp_fn.1	refwrap.h:350	exec
○	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0

Path /

Metric	Value
CQA speedup if no scalar integer	1.19
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	12.63
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.19
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
Source	BsplineFunctor.h:291-298
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	14.83
CQA cycles if no scalar integer	12.50
CQA cycles if FP arith vectorized	14.83
CQA cycles if fully vectorized	1.17
Front-end cycles	14.83
P0 cycles	12.50
P1 cycles	10.67
P2 cycles	2.67
P3 cycles	2.67
P4 cycles	8.00
P5 cycles	10.67
P6 cycles	12.50
P7 cycles	8.00
P8 cycles	8.00
P9 cycles	8.00
P10 cycles	10.67
P11 cycles	2.67
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	89.00
Nb loads	8.00
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	10.79
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	9.38
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	9.38
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	6.25
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	9.38

Metric	Value
CQA speedup if no scalar integer	1.19
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	12.63
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.19
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
Source	BsplineFunctor.h:291-298
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	14.83
CQA cycles if no scalar integer	12.50
CQA cycles if FP arith vectorized	14.83
CQA cycles if fully vectorized	1.17
Front-end cycles	14.83
P0 cycles	12.50
P1 cycles	10.67
P2 cycles	2.67
P3 cycles	2.67
P4 cycles	8.00
P5 cycles	10.67
P6 cycles	12.50
P7 cycles	8.00
P8 cycles	8.00
P9 cycles	8.00
P10 cycles	10.67
P11 cycles	2.67
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	89.00
Nb loads	8.00
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	10.79
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	9.38
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	9.38
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	6.25
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	9.38

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:291-298
Module	exec

The loop is defined in /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291-298.

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

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

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

This loop has 6561 execution paths.

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

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

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

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 14.83 to 12.50 cycles (1.19x 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 9% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your loop, you can lower the cost of an iteration from 14.83 to 1.17 cycles (12.63x speedup).

Details

All SSE/AVX 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)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

Type of elements and instruction set

8 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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 (8 double precision FP elements). The binary loop is storing 96 bytes (12 double precision FP elements).

Unroll opportunity

Loop is potentially data access bound.

Workaround

Unroll your loop if trip count is significantly higher than target unroll factor and if some data references are common to consecutive iterations. This can be done manually. Or by recompiling with -funroll-loops and/or -floop-unroll-and-jam. Or with the unroll (resp. unroll_and_jam) directive on top of the inner (resp. surrounding) loop. You can enforce an unroll factor: #pragma GCC unroll N

General properties

nb instructions	90
nb uops	89
loop length	322
used x86 registers	10
used mmx registers	0
used xmm registers	9
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	14.83 cycles
front end	14.83 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	12.50	10.67	2.67	2.67	8.00	10.67	12.50	8.00	8.00	8.00	10.67	2.67
cycles	12.50	10.67	2.67	2.67	8.00	10.67	12.50	8.00	8.00	8.00	10.67	2.67

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	14.83
Dispatch	12.50
Overall L1	14.83

Vectorization ratios

INT

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

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

INT+FP

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

Vector efficiency ratios

INT

all	6%
load	NA (no load vectorizable/vectorized instructions)
store	6%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
other	6%

all	12%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

INT+FP

all	9%
load	12%
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	9%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 14.83 cycles. At this rate:

2% of peak load performance is reached (4.31 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (6.47 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 14.83 to 12.50 cycles (1.19x speedup).

ASM code

In the binary file, the address of the loop is: 456347

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
VMOVSD (%RSI,%RAX,8),%XMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM10,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 456369 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2b9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RAX,1),%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %EDX,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 456369 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2b9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EAX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM10,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
INC %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD (%RSI,%RAX,8),%XMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM11,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 45638e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2de>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RAX,1),%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %EDX,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 45638e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2de>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EAX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM11,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x1(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM12,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 4563b6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x306>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 4563b6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x306>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM12,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x2(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM13,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 4563de <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x32e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 4563de <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x32e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM13,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x3(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM14,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 456406 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x356>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 456406 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x356>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM14,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x4(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM15,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 45642e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x37e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 45642e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x37e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM15,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x5(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM3,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 456455 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3a5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 456455 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3a5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM3,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x6(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM4,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 45647c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3cc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 45647c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3cc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM4,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
ADD $0x7,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RAX,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JNE 456347 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x297>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A

Function	miniqmcreference::TwoBodyJastrowRef >::computeU3(qmcplusplus::ParticleSet const&, int, double const, double, double, double, bool)
Source file and lines	BsplineFunctor.h:291-298
Module	exec

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

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

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

gain
potential
hint
expert

Code clean check

Workaround

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

Vectorization

Details

All SSE/AVX 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)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

Type of elements and instruction set

8 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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

Unroll opportunity

Loop is potentially data access bound.

Workaround

General properties

nb instructions	90
nb uops	89
loop length	322
used x86 registers	10
used mmx registers	0
used xmm registers	9
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	14.83 cycles
front end	14.83 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	12.50	10.67	2.67	2.67	8.00	10.67	12.50	8.00	8.00	8.00	10.67	2.67
cycles	12.50	10.67	2.67	2.67	8.00	10.67	12.50	8.00	8.00	8.00	10.67	2.67

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	14.83
Dispatch	12.50
Overall L1	14.83

Vectorization ratios

INT

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

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

INT+FP

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

Vector efficiency ratios

INT

all	6%
load	NA (no load vectorizable/vectorized instructions)
store	6%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
other	6%

all	12%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

INT+FP

all	9%
load	12%
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	9%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 14.83 cycles. At this rate:

2% of peak load performance is reached (4.31 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (6.47 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the loop is: 456347

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
VMOVSD (%RSI,%RAX,8),%XMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM10,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 456369 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2b9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RAX,1),%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %EDX,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 456369 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2b9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EAX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM10,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
INC %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD (%RSI,%RAX,8),%XMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM11,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 45638e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2de>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RAX,1),%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %EDX,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 45638e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x2de>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EAX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM11,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x1(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM12,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 4563b6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x306>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 4563b6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x306>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM12,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x2(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM13,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 4563de <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x32e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 4563de <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x32e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM13,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x3(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM14,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 456406 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x356>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 456406 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x356>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM14,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x4(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM15,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 45642e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x37e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 45642e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x37e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM15,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x5(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM3,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 456455 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3a5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 456455 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3a5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM3,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x6(%RAX),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%RSI,%RDX,8),%XMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VCOMISD %XMM4,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 45647c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3cc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDI,%RDX,1),%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %R9D,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 45647c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x3cc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %EDX,(%R12,%R9,4)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVSD %XMM4,(%R15,%R9,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
ADD $0x7,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RAX,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JNE 456347 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b+0x297>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Type of elements and instruction set

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

Unroll opportunity

Workaround

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Type of elements and instruction set

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

Unroll opportunity

Workaround

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code