OV - exec - Loop 822 - libqmcwfs.so

	Loop Id: 822	Module: libqmcwfs.so	Source: MultiBsplineRef.hpp:63-71 [...]	Coverage: 0.04%

0x444f0 MOV	0x68(%RSP),%RSI

0x444f5 INC	%R10

0x444f8 ADD	%RSI,0x38(%RSP)

0x444fd ADD	%RSI,0x30(%RSP)

0x44502 ADD	%RSI,0x50(%RSP)

0x44507 ADD	%RSI,0x70(%RSP)

0x4450c ADD	%RSI,0x28(%RSP)

0x44511 ADD	%RSI,0x20(%RSP)

0x44516 ADD	%RSI,0x18(%RSP)

0x4451b ADD	%RSI,%RBX

0x4451e ADD	%RSI,%R11

0x44521 ADD	%RSI,%RAX

0x44524 ADD	%RSI,%R14

0x44527 ADD	%RSI,%RCX

0x4452a ADD	%RSI,%RDX

0x4452d ADD	%RSI,%RDI

0x44530 ADD	%RSI,%R8

0x44533 ADD	%RSI,%R13

0x44536 CMP	$0x4,%R10

0x4453a JE	43ff0

0x44540 TEST	%R15D,%R15D

0x44543 JE	444f0

0x44545 VMOVSD	0x120(%RSP,%R10,8),%XMM14

0x4454f MOV	%RAX,0x48(%RSP)

0x44554 MOV	%R11,0x98(%RSP)

0x4455c MOV	%RCX,0x10(%RSP)

0x44561 MOV	%RBX,0x8(%RSP)

0x44566 MOV	%R14,0x90(%RSP)

0x4456e VMULSD	%XMM14,%XMM22,%XMM15

0x44574 CMP	$0x4,%R15D

0x44578 JAE	445a0

0x4457a MOV	0x38(%RSP),%R11

0x4457f MOV	0x30(%RSP),%R14

0x44584 MOV	0x70(%RSP),%RAX

0x44589 MOV	0x50(%RSP),%RCX

0x4458e XOR	%R9D,%R9D

0x44591 JMP	44680

0x445a0 CMP	$0x8,%R15D

0x445a4 JAE	445be

0x445a6 MOV	0x38(%RSP),%R11

0x445ab MOV	0x30(%RSP),%R14

0x445b0 MOV	0x70(%RSP),%RAX

0x445b5 MOV	0x50(%RSP),%RCX

0x445ba XOR	%ESI,%ESI

0x445bc JMP	44629

0x445be MOV	0x38(%RSP),%R11

0x445c3 MOV	0x30(%RSP),%R14

0x445c8 MOV	0x70(%RSP),%RAX

0x445cd MOV	0x50(%RSP),%RCX

0x445d2 MOV	(%RSP),%R9

0x445d6 VBROADCASTSD	%XMM15,%ZMM16

0x445dc XOR	%ESI,%ESI

0x445de XCHG	%AX,%AX

  (823) 0x445e0 VMULPD	(%RAX,%RSI,8),%ZMM5,%ZMM17

  (823) 0x445e7 VFMADD231PD	(%RCX,%RSI,8),%ZMM4,%ZMM17

  (823) 0x445ee VFMADD231PD	(%R14,%RSI,8),%ZMM7,%ZMM17

  (823) 0x445f5 VFMADD231PD	(%R11,%RSI,8),%ZMM8,%ZMM17

  (823) 0x445fc VFMADD213PD	(%R12,%RSI,8),%ZMM16,%ZMM17

  (823) 0x44603 VMOVUPD	%ZMM17,(%R12,%RSI,8)

  (823) 0x4460a ADD	$0x8,%RSI

  (823) 0x4460e CMP	%RSI,%R9

  (823) 0x44611 JNE	445e0

0x44613 CMP	%R15,%R9

0x44616 JE	446d9

0x4461c MOV	(%RSP),%R9

0x44620 MOV	%R9,%RSI

0x44623 TEST	$0x4,%R15B

0x44627 JE	44680

0x44629 MOV	0x40(%RSP),%R9

0x4462e VBROADCASTSD	%XMM15,%YMM16

0x44634 NOPW	%CS:(%RAX,%RAX,1)

  (834) 0x44640 VMULPD	(%RAX,%RSI,8),%YMM5,%YMM17

  (834) 0x44647 VFMADD231PD	(%RCX,%RSI,8),%YMM9,%YMM17

  (834) 0x4464e VFMADD231PD	(%R14,%RSI,8),%YMM10,%YMM17

  (834) 0x44655 VFMADD231PD	(%R11,%RSI,8),%YMM11,%YMM17

  (834) 0x4465c VFMADD213PD	(%R12,%RSI,8),%YMM16,%YMM17

  (834) 0x44663 VMOVUPD	%YMM17,(%R12,%RSI,8)

  (834) 0x4466a ADD	$0x4,%RSI

  (834) 0x4466e CMP	%RSI,%R9

  (834) 0x44671 JNE	44640

0x44673 MOV	%R9,%RSI

0x44676 CMP	%R15,%R9

0x44679 JE	446d9

0x4467b NOPL	(%RAX,%RAX,1)

  (833) 0x44680 VMOVSD	(%R14,%R9,8),%XMM16

  (833) 0x44687 VMOVSD	(%RAX,%R9,8),%XMM17

  (833) 0x4468e VMOVHPD	(%R11,%R9,8),%XMM16,%XMM16

  (833) 0x44695 VMOVHPD	(%RCX,%R9,8),%XMM17,%XMM17

  (833) 0x4469c VINSERTF32X4	$0x1,%XMM16,%YMM17,%YMM16

  (833) 0x446a3 VMULPD	%YMM16,%YMM3,%YMM16

  (833) 0x446a9 VEXTRACTF32X4	$0x1,%YMM16,%XMM17

  (833) 0x446b0 VADDPD	%XMM17,%XMM16,%XMM16

  (833) 0x446b6 VPERMILPD	$0x1,%XMM16,%XMM17

  (833) 0x446bd VADDSD	%XMM17,%XMM16,%XMM16

  (833) 0x446c3 VFMADD213SD	(%R12,%R9,8),%XMM15,%XMM16

  (833) 0x446ca VMOVSD	%XMM16,(%R12,%R9,8)

  (833) 0x446d1 INC	%R9

  (833) 0x446d4 CMP	%R9,%R15

  (833) 0x446d7 JNE	44680

0x446d9 VMULSD	%XMM14,%XMM23,%XMM15

0x446df CMP	$0x4,%R15D

0x446e3 JAE	44710

0x446e5 MOV	0x48(%RSP),%RAX

0x446ea MOV	0x98(%RSP),%R11

0x446f2 MOV	0x10(%RSP),%RCX

0x446f7 MOV	0x8(%RSP),%RBX

0x446fc MOV	0x28(%RSP),%R14

0x44701 XOR	%R9D,%R9D

0x44704 JMP	447f0

0x44710 MOV	0x48(%RSP),%RAX

0x44715 MOV	0x98(%RSP),%R11

0x4471d MOV	0x10(%RSP),%RCX

0x44722 MOV	0x8(%RSP),%RBX

0x44727 CMP	$0x8,%R15D

0x4472b JAE	44736

0x4472d MOV	0x28(%RSP),%R14

0x44732 XOR	%ESI,%ESI

0x44734 JMP	44799

0x44736 MOV	0x28(%RSP),%R14

0x4473b MOV	(%RSP),%R9

0x4473f VBROADCASTSD	%XMM15,%ZMM16

0x44745 XOR	%ESI,%ESI

0x44747 NOPW	(%RAX,%RAX,1)

  (824) 0x44750 VMULPD	(%RAX,%RSI,8),%ZMM5,%ZMM17

  (824) 0x44757 VFMADD231PD	(%R11,%RSI,8),%ZMM4,%ZMM17

  (824) 0x4475e VFMADD231PD	(%R14,%RSI,8),%ZMM7,%ZMM17

  (824) 0x44765 VFMADD231PD	(%RBX,%RSI,8),%ZMM8,%ZMM17

  (824) 0x4476c VFMADD213PD	(%R12,%RSI,8),%ZMM16,%ZMM17

  (824) 0x44773 VMOVUPD	%ZMM17,(%R12,%RSI,8)

  (824) 0x4477a ADD	$0x8,%RSI

  (824) 0x4477e CMP	%RSI,%R9

  (824) 0x44781 JNE	44750

0x44783 CMP	%R15,%R9

0x44786 JE	44822

0x4478c MOV	(%RSP),%R9

0x44790 MOV	%R9,%RSI

0x44793 TEST	$0x4,%R15B

0x44797 JE	447f0

0x44799 MOV	0x40(%RSP),%R9

0x4479e VBROADCASTSD	%XMM15,%YMM16

0x447a4 NOPW	%CS:(%RAX,%RAX,1)

  (832) 0x447b0 VMULPD	(%RAX,%RSI,8),%YMM5,%YMM17

  (832) 0x447b7 VFMADD231PD	(%R11,%RSI,8),%YMM9,%YMM17

  (832) 0x447be VFMADD231PD	(%R14,%RSI,8),%YMM10,%YMM17

  (832) 0x447c5 VFMADD231PD	(%RBX,%RSI,8),%YMM11,%YMM17

  (832) 0x447cc VFMADD213PD	(%R12,%RSI,8),%YMM16,%YMM17

  (832) 0x447d3 VMOVUPD	%YMM17,(%R12,%RSI,8)

  (832) 0x447da ADD	$0x4,%RSI

  (832) 0x447de CMP	%RSI,%R9

  (832) 0x447e1 JNE	447b0

0x447e3 MOV	%R9,%RSI

0x447e6 CMP	%R15,%R9

0x447e9 JE	44822

0x447eb NOPL	(%RAX,%RAX,1)

  (831) 0x447f0 VMULSD	(%RAX,%R9,8),%XMM2,%XMM16

  (831) 0x447f7 VFMADD231SD	(%R11,%R9,8),%XMM12,%XMM16

  (831) 0x447fe VFMADD231SD	(%R14,%R9,8),%XMM6,%XMM16

  (831) 0x44805 VFMADD231SD	(%RBX,%R9,8),%XMM13,%XMM16

  (831) 0x4480c VFMADD213SD	(%R12,%R9,8),%XMM15,%XMM16

  (831) 0x44813 VMOVSD	%XMM16,(%R12,%R9,8)

  (831) 0x4481a INC	%R9

  (831) 0x4481d CMP	%R9,%R15

  (831) 0x44820 JNE	447f0

0x44822 VMULSD	%XMM0,%XMM14,%XMM15

0x44826 MOV	%R10,0x88(%RSP)

0x4482e CMP	$0x4,%R15D

0x44832 JAE	44850

0x44834 MOV	0x90(%RSP),%R14

0x4483c MOV	0x20(%RSP),%R10

0x44841 MOV	0x18(%RSP),%RBX

0x44846 XOR	%R9D,%R9D

0x44849 JMP	44930

0x44850 MOV	0x90(%RSP),%R14

0x44858 CMP	$0x8,%R15D

0x4485c JAE	4486c

0x4485e MOV	0x20(%RSP),%R10

0x44863 MOV	0x18(%RSP),%RBX

0x44868 XOR	%ESI,%ESI

0x4486a JMP	448d9

0x4486c MOV	0x20(%RSP),%R10

0x44871 MOV	0x18(%RSP),%RBX

0x44876 MOV	(%RSP),%R9

0x4487a VBROADCASTSD	%XMM15,%ZMM16

0x44880 XOR	%ESI,%ESI

0x44882 NOPW	%CS:(%RAX,%RAX,1)

  (825) 0x44890 VMULPD	(%RCX,%RSI,8),%ZMM5,%ZMM17

  (825) 0x44897 VFMADD231PD	(%R14,%RSI,8),%ZMM4,%ZMM17

  (825) 0x4489e VFMADD231PD	(%RBX,%RSI,8),%ZMM7,%ZMM17

  (825) 0x448a5 VFMADD231PD	(%R10,%RSI,8),%ZMM8,%ZMM17

  (825) 0x448ac VFMADD213PD	(%R12,%RSI,8),%ZMM16,%ZMM17

  (825) 0x448b3 VMOVUPD	%ZMM17,(%R12,%RSI,8)

  (825) 0x448ba ADD	$0x8,%RSI

  (825) 0x448be CMP	%RSI,%R9

  (825) 0x448c1 JNE	44890

0x448c3 CMP	%R15,%R9

0x448c6 JE	44962

0x448cc MOV	(%RSP),%R9

0x448d0 MOV	%R9,%RSI

0x448d3 TEST	$0x4,%R15B

0x448d7 JE	44930

0x448d9 MOV	0x40(%RSP),%R9

0x448de VBROADCASTSD	%XMM15,%YMM16

0x448e4 NOPW	%CS:(%RAX,%RAX,1)

  (830) 0x448f0 VMULPD	(%RCX,%RSI,8),%YMM5,%YMM17

  (830) 0x448f7 VFMADD231PD	(%R14,%RSI,8),%YMM9,%YMM17

  (830) 0x448fe VFMADD231PD	(%RBX,%RSI,8),%YMM10,%YMM17

  (830) 0x44905 VFMADD231PD	(%R10,%RSI,8),%YMM11,%YMM17

  (830) 0x4490c VFMADD213PD	(%R12,%RSI,8),%YMM16,%YMM17

  (830) 0x44913 VMOVUPD	%YMM17,(%R12,%RSI,8)

  (830) 0x4491a ADD	$0x4,%RSI

  (830) 0x4491e CMP	%RSI,%R9

  (830) 0x44921 JNE	448f0

0x44923 MOV	%R9,%RSI

0x44926 CMP	%R15,%R9

0x44929 JE	44962

0x4492b NOPL	(%RAX,%RAX,1)

  (829) 0x44930 VMULSD	(%RCX,%R9,8),%XMM2,%XMM16

  (829) 0x44937 VFMADD231SD	(%R14,%R9,8),%XMM12,%XMM16

  (829) 0x4493e VFMADD231SD	(%RBX,%R9,8),%XMM6,%XMM16

  (829) 0x44945 VFMADD231SD	(%R10,%R9,8),%XMM13,%XMM16

  (829) 0x4494c VFMADD213SD	(%R12,%R9,8),%XMM15,%XMM16

  (829) 0x44953 VMOVSD	%XMM16,(%R12,%R9,8)

  (829) 0x4495a INC	%R9

  (829) 0x4495d CMP	%R9,%R15

  (829) 0x44960 JNE	44930

0x44962 MOV	0x8(%RSP),%RBX

0x44967 VMULSD	%XMM1,%XMM14,%XMM14

0x4496b CMP	$0x4,%R15D

0x4496f JAE	44990

0x44971 MOV	0x88(%RSP),%R10

0x44979 XOR	%R9D,%R9D

0x4497c JMP	44a50

0x44990 MOV	0x88(%RSP),%R10

0x44998 CMP	$0x8,%R15D

0x4499c JAE	449a2

0x4499e XOR	%ESI,%ESI

0x449a0 JMP	449fa

0x449a2 MOV	(%RSP),%R9

0x449a6 VBROADCASTSD	%XMM14,%ZMM15

0x449ac XOR	%ESI,%ESI

0x449ae XCHG	%AX,%AX

  (826) 0x449b0 VMULPD	(%R13,%RSI,8),%ZMM5,%ZMM16

  (826) 0x449b8 VFMADD231PD	(%R8,%RSI,8),%ZMM4,%ZMM16

  (826) 0x449bf VFMADD231PD	(%RDI,%RSI,8),%ZMM7,%ZMM16

  (826) 0x449c6 VFMADD231PD	(%RDX,%RSI,8),%ZMM8,%ZMM16

  (826) 0x449cd VFMADD213PD	(%R12,%RSI,8),%ZMM15,%ZMM16

  (826) 0x449d4 VMOVUPD	%ZMM16,(%R12,%RSI,8)

  (826) 0x449db ADD	$0x8,%RSI

  (826) 0x449df CMP	%RSI,%R9

  (826) 0x449e2 JNE	449b0

0x449e4 CMP	%R15,%R9

0x449e7 JE	444f0

0x449ed MOV	(%RSP),%R9

0x449f1 MOV	%R9,%RSI

0x449f4 TEST	$0x4,%R15B

0x449f8 JE	44a50

0x449fa MOV	0x40(%RSP),%R9

0x449ff VBROADCASTSD	%XMM14,%YMM15

0x44a04 NOPW	%CS:(%RAX,%RAX,1)

  (828) 0x44a10 VMULPD	(%R13,%RSI,8),%YMM5,%YMM16

  (828) 0x44a18 VFMADD231PD	(%R8,%RSI,8),%YMM9,%YMM16

  (828) 0x44a1f VFMADD231PD	(%RDI,%RSI,8),%YMM10,%YMM16

  (828) 0x44a26 VFMADD231PD	(%RDX,%RSI,8),%YMM11,%YMM16

  (828) 0x44a2d VFMADD213PD	(%R12,%RSI,8),%YMM15,%YMM16

  (828) 0x44a34 VMOVUPD	%YMM16,(%R12,%RSI,8)

  (828) 0x44a3b ADD	$0x4,%RSI

  (828) 0x44a3f CMP	%RSI,%R9

  (828) 0x44a42 JNE	44a10

0x44a44 MOV	%R9,%RSI

0x44a47 CMP	%R15,%R9

0x44a4a JE	444f0

  (827) 0x44a50 VMULSD	(%R13,%R9,8),%XMM2,%XMM15

  (827) 0x44a57 VFMADD231SD	(%R8,%R9,8),%XMM12,%XMM15

  (827) 0x44a5d VFMADD231SD	(%RDI,%R9,8),%XMM6,%XMM15

  (827) 0x44a63 VFMADD231SD	(%RDX,%R9,8),%XMM13,%XMM15

  (827) 0x44a69 VFMADD213SD	(%R12,%R9,8),%XMM14,%XMM15

  (827) 0x44a6f VMOVSD	%XMM15,(%R12,%R9,8)

  (827) 0x44a75 INC	%R9

  (827) 0x44a78 CMP	%R9,%R15

  (827) 0x44a7b JNE	44a50

0x44a7d JMP	444f0

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h: 923 - 923

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

923:       for (; __first != __last; ++__first)

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp: 63 - 71

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

63:   for (size_t i = 0; i < 4; i++)

64:     for (size_t j = 0; j < 4; j++)

65:     {

66:       const T pre00           = a[i] * b[j];

67:       const T* restrict coefs = spline_m->coefs + (ix + i) * xs + (iy + j) * ys + iz * zs;

68:       for (size_t n = 0; n < num_splines; n++)

69:         vals[n] += pre00 *

70:             (c[0] * coefs[n] + c[1] * coefs[n + zs] + c[2] * coefs[n + 2 * zs] +

71:              c[3] * coefs[n + 3 * zs]);

Path /

Metric	Value
CQA speedup if no scalar integer	2.47
CQA speedup if FP arith vectorized	1.83
CQA speedup if fully vectorized	5.98
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.34
Bottlenecks	micro-operation queue,
Function	_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE
Source	stl_algobase.h:923-923,MultiBsplineRef.hpp:63-63,MultiBsplineRef.hpp:66-68
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	27.17
CQA cycles if no scalar integer	11.00
CQA cycles if FP arith vectorized	14.83
CQA cycles if fully vectorized	4.54
Front-end cycles	27.17
DIV/SQRT cycles	15.50
P0 cycles	13.00
P1 cycles	13.00
P2 cycles	13.00
P3 cycles	15.50
P4 cycles	20.33
P5 cycles	20.33
P6 cycles	20.33
P7 cycles	3.50
P8 cycles	4.50
P9 cycles	4.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	0.00
P13 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	167.00
Nb uops	163.00
Nb loads	55.00
Nb stores	13.00
Nb stack references	16.00
FLOP/cycle	0.15
Nb FLOP add-sub	0.00
Nb FLOP mul	4.00
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	20.02
Bytes prefetched	0.00
Bytes loaded	440.00
Bytes stored	104.00
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	0.00
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	11.35
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
Vector-efficiency ratio mul	12.50
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	9.91

Metric	Value
CQA speedup if no scalar integer	2.47
CQA speedup if FP arith vectorized	1.83
CQA speedup if fully vectorized	5.98
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.34
Bottlenecks	micro-operation queue,
Function	_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE
Source	stl_algobase.h:923-923,MultiBsplineRef.hpp:63-63,MultiBsplineRef.hpp:66-68
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	27.17
CQA cycles if no scalar integer	11.00
CQA cycles if FP arith vectorized	14.83
CQA cycles if fully vectorized	4.54
Front-end cycles	27.17
DIV/SQRT cycles	15.50
P0 cycles	13.00
P1 cycles	13.00
P2 cycles	13.00
P3 cycles	15.50
P4 cycles	20.33
P5 cycles	20.33
P6 cycles	20.33
P7 cycles	3.50
P8 cycles	4.50
P9 cycles	4.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	0.00
P13 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	167.00
Nb uops	163.00
Nb loads	55.00
Nb stores	13.00
Nb stack references	16.00
FLOP/cycle	0.15
Nb FLOP add-sub	0.00
Nb FLOP mul	4.00
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	20.02
Bytes prefetched	0.00
Bytes loaded	440.00
Bytes stored	104.00
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	0.00
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	11.35
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
Vector-efficiency ratio mul	12.50
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	9.91

Path /

Average path: Display a virtual path defined by average values of all real paths

Function	_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE
Source file and lines	MultiBsplineRef.hpp:63-71
Module	libqmcwfs.so

The loop is defined in:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:923
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp:63-71

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 2402 paths individually, rerun with max-paths=2402
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 2402 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 27.17 to 11.00 cycles (2.47x 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 11% 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 27.17 to 4.54 cycles (5.98x 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

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

ADD: 7 occurrences

Type of elements and instruction set

4 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 is composed of 4 FP arithmetical operations:

4: multiply

The binary loop is loading 440 bytes (55 double precision FP elements). The binary loop is storing 104 bytes (13 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	167
nb uops	163
loop length	748
used x86 registers	14
used mmx registers	0
used xmm registers	6
used ymm registers	2
used zmm registers	2
nb stack references	16

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	27.17 cycles
front end	27.17 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	15.50	13.00	13.00	13.00	15.50	20.33	20.33	20.33	3.50	4.50	4.00	0.00	0.00	0.00
cycles	15.50	13.00	13.00	13.00	15.50	20.33	20.33	20.33	3.50	4.50	4.00	0.00	0.00	0.00

Execution ports to units layout:

ALU0/BRU0: ALU
ALU1: ALU
ALU2: ALU
ALU3: ALU
BRU1:
AGU0 (256 bits): store address, load
AGU1 (256 bits): store address, load
AGU2 (256 bits): store address, load
FP0 (256 bits): VPU, DIV/SQRT
FP1 (256 bits): VPU, DIV/SQRT
FP2 (256 bits): VPU
FP3 (256 bits): VPU
FP4 (256 bits): FP store data
FP5 (256 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	27.17
Dispatch	20.33
Overall L1	27.17

Vectorization ratios

INT

all	0%
load	0%
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	NA (no store vectorizable/vectorized instructions)
mul	0%
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	0%
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	11%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	9%

all	12%
load	12%
store	NA (no store vectorizable/vectorized instructions)
mul	12%
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	11%
load	12%
store	12%
mul	12%
add-sub	12%
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 27.17 cycles. At this rate:

16% of peak load performance is reached (16.20 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (3.83 out of 64.00 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 27.17 to 20.33 cycles (1.34x speedup).

ASM code

In the binary file, the address of the loop is: 44540

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	Latency	Recip. throughput
MOV 0x68(%RSP),%RSI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
INC %R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,0x38(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x30(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x50(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x70(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x28(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x20(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x18(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,%RBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%R11	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%R14	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP $0x4,%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 43ff0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x1c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
TEST %R15D,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 444f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x6c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
VMOVSD 0x120(%RSP,%R10,8),%XMM14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	1	0.50
MOV %RAX,0x48(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
MOV %R11,0x98(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
MOV %RCX,0x10(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
MOV %RBX,0x8(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
MOV %R14,0x90(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
VMULSD %XMM14,%XMM22,%XMM15	1	0	0	0	0	0	0	0	0	0.50	0.50	0	3	0.50
CMP $0x4,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 445a0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x770>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x38(%RSP),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x30(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x70(%RSP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x50(%RSP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 44680 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x850>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
CMP $0x8,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 445be <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x78e>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x38(%RSP),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x30(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x70(%RSP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x50(%RSP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 44629 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x7f9>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x38(%RSP),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x30(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x70(%RSP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x50(%RSP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%ZMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 446d9 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x8a9>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
TEST $0x4,%R15B	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44680 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x850>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x40(%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%YMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 446d9 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x8a9>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
VMULSD %XMM14,%XMM23,%XMM15	1	0	0	0	0	0	0	0	0	0.50	0.50	0	3	0.50
CMP $0x4,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 44710 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x8e0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x48(%RSP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x98(%RSP),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x10(%RSP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x8(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x28(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 447f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x9c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x48(%RSP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x98(%RSP),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x10(%RSP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x8(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
CMP $0x8,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 44736 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x906>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x28(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 44799 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x969>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x28(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%ZMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44822 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x9f2>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
TEST $0x4,%R15B	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 447f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x9c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x40(%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%YMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44822 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x9f2>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
VMULSD %XMM0,%XMM14,%XMM15	1	0	0	0	0	0	0	0	0	0.50	0.50	0	3	0.50
MOV %R10,0x88(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
CMP $0x4,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 44850 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xa20>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x90(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x20(%RSP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x18(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 44930 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb00>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x90(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
CMP $0x8,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 4486c <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xa3c>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x20(%RSP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x18(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 448d9 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xaa9>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x20(%RSP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x18(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%ZMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44962 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb32>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
TEST $0x4,%R15B	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44930 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb00>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x40(%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%YMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44962 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb32>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV 0x8(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VMULSD %XMM1,%XMM14,%XMM14	1	0	0	0	0	0	0	0	0	0.50	0.50	0	3	0.50
CMP $0x4,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 44990 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb60>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x88(%RSP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 44a50 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xc20>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x88(%RSP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
CMP $0x8,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 449a2 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb72>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 449fa <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xbca>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM14,%ZMM15	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 444f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x6c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
TEST $0x4,%R15B	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44a50 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xc20>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x40(%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM14,%YMM15	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 444f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x6c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
JMP 444f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x6c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1

Function	_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE
Source file and lines	MultiBsplineRef.hpp:63-71
Module	libqmcwfs.so

The loop is defined in:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:923
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp:63-71

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 2402 paths individually, rerun with max-paths=2402
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

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

ADD: 7 occurrences

Type of elements and instruction set

4 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 is composed of 4 FP arithmetical operations:

4: multiply

The binary loop is loading 440 bytes (55 double precision FP elements). The binary loop is storing 104 bytes (13 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	167
nb uops	163
loop length	748
used x86 registers	14
used mmx registers	0
used xmm registers	6
used ymm registers	2
used zmm registers	2
nb stack references	16

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	27.17 cycles
front end	27.17 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	15.50	13.00	13.00	13.00	15.50	20.33	20.33	20.33	3.50	4.50	4.00	0.00	0.00	0.00
cycles	15.50	13.00	13.00	13.00	15.50	20.33	20.33	20.33	3.50	4.50	4.00	0.00	0.00	0.00

Execution ports to units layout:

ALU0/BRU0: ALU
ALU1: ALU
ALU2: ALU
ALU3: ALU
BRU1:
AGU0 (256 bits): store address, load
AGU1 (256 bits): store address, load
AGU2 (256 bits): store address, load
FP0 (256 bits): VPU, DIV/SQRT
FP1 (256 bits): VPU, DIV/SQRT
FP2 (256 bits): VPU
FP3 (256 bits): VPU
FP4 (256 bits): FP store data
FP5 (256 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	27.17
Dispatch	20.33
Overall L1	27.17

Vectorization ratios

INT

all	0%
load	0%
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	NA (no store vectorizable/vectorized instructions)
mul	0%
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	0%
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	11%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	9%

all	12%
load	12%
store	NA (no store vectorizable/vectorized instructions)
mul	12%
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	11%
load	12%
store	12%
mul	12%
add-sub	12%
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 27.17 cycles. At this rate:

16% of peak load performance is reached (16.20 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (3.83 out of 64.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the loop is: 44540

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	Latency	Recip. throughput
MOV 0x68(%RSP),%RSI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
INC %R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,0x38(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x30(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x50(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x70(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x28(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x20(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,0x18(%RSP)	2	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	1	0.50
ADD %RSI,%RBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%R11	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%R14	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
ADD %RSI,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
CMP $0x4,%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 43ff0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x1c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
TEST %R15D,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 444f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x6c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
VMOVSD 0x120(%RSP,%R10,8),%XMM14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	1	0.50
MOV %RAX,0x48(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
MOV %R11,0x98(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
MOV %RCX,0x10(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
MOV %RBX,0x8(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
MOV %R14,0x90(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
VMULSD %XMM14,%XMM22,%XMM15	1	0	0	0	0	0	0	0	0	0.50	0.50	0	3	0.50
CMP $0x4,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 445a0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x770>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x38(%RSP),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x30(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x70(%RSP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x50(%RSP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 44680 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x850>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
CMP $0x8,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 445be <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x78e>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x38(%RSP),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x30(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x70(%RSP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x50(%RSP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 44629 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x7f9>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x38(%RSP),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x30(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x70(%RSP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x50(%RSP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%ZMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 446d9 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x8a9>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
TEST $0x4,%R15B	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44680 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x850>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x40(%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%YMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 446d9 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x8a9>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
VMULSD %XMM14,%XMM23,%XMM15	1	0	0	0	0	0	0	0	0	0.50	0.50	0	3	0.50
CMP $0x4,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 44710 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x8e0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x48(%RSP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x98(%RSP),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x10(%RSP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x8(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x28(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 447f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x9c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x48(%RSP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x98(%RSP),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x10(%RSP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x8(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
CMP $0x8,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 44736 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x906>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x28(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 44799 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x969>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x28(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%ZMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44822 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x9f2>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
TEST $0x4,%R15B	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 447f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x9c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x40(%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%YMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44822 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x9f2>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
VMULSD %XMM0,%XMM14,%XMM15	1	0	0	0	0	0	0	0	0	0.50	0.50	0	3	0.50
MOV %R10,0x88(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	4	0.50
CMP $0x4,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 44850 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xa20>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x90(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x20(%RSP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x18(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 44930 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb00>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x90(%RSP),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
CMP $0x8,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 4486c <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xa3c>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x20(%RSP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x18(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 448d9 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xaa9>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x20(%RSP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV 0x18(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%ZMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44962 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb32>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
TEST $0x4,%R15B	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44930 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb00>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x40(%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM15,%YMM16	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44962 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb32>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV 0x8(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VMULSD %XMM1,%XMM14,%XMM14	1	0	0	0	0	0	0	0	0	0.50	0.50	0	3	0.50
CMP $0x4,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 44990 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb60>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x88(%RSP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 44a50 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xc20>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV 0x88(%RSP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
CMP $0x8,%R15D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JAE 449a2 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xb72>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 449fa <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xbca>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM14,%ZMM15	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 444f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x6c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV (%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
TEST $0x4,%R15B	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 44a50 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0xc20>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
MOV 0x40(%RSP),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	3	0.33
VBROADCASTSD %XMM14,%YMM15	1	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CMP %R15,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	1	0.25
JE 444f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x6c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50-1
JMP 444f0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x6c0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

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

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code