OV - exec - Loop 1760

	Loop Id: 1760	Module: exec	Source: SoaDistanceTableABOMPTarget.h:215-228 [...]	Coverage: 0.03%

0x2cbd50 INC	%RDX

0x2cbd53 ADD	$0x200,%R14D

0x2cbd5a ADD	$0x200,%R10D

0x2cbd61 CMP	%RDX,-0xf0(%RBP)

0x2cbd68 JE	2cbbf0

0x2cbd6e MOV	-0x70(%RBP),%RDI

0x2cbd72 MOV	%EDX,%EAX

0x2cbd74 MOV	%R14D,%R14D

0x2cbd77 CMP	%EDI,%R10D

0x2cbd7a MOV	%EDI,%R13D

0x2cbd7d CMOVL	%R10D,%R13D

0x2cbd81 SAL	$0x9,%EAX

0x2cbd84 LEA	0x200(%RAX),%ESI

0x2cbd8a CMP	%EDI,%ESI

0x2cbd8c CMOVGE	%EDI,%ESI

0x2cbd8f CMP	%ESI,%EAX

0x2cbd91 JGE	2cbd50

0x2cbd93 MOV	-0xd0(%RBP),%RAX

0x2cbd9a MOV	-0xe0(%RBP),%RSI

0x2cbda1 MOV	%R13,%RDI

0x2cbda4 SUB	%R14,%RDI

0x2cbda7 VMOVSD	(%RAX,%RSI,8),%XMM18

0x2cbdae MOV	-0xd8(%RBP),%RSI

0x2cbdb5 VMOVSD	(%RAX,%RSI,8),%XMM19

0x2cbdbc MOV	-0xe8(%RBP),%RSI

0x2cbdc3 VMOVSD	(%RAX,%RSI,8),%XMM20

0x2cbdca CMP	$0x2,%RDI

0x2cbdce JAE	2cbf70

0x2cbdd4 MOV	%R14,%RAX

0x2cbdd7 MOV	-0x60(%RBP),%R8

0x2cbddb MOV	-0x48(%RBP),%RSI

0x2cbddf MOV	-0x30(%RBP),%RDI

0x2cbde3 MOV	-0x68(%RBP),%R9

0x2cbde7 LEA	(%RCX,%RAX,8),%R15

0x2cbdeb LEA	(%R11,%RAX,8),%R12

0x2cbdef SUB	%RAX,%R13

0x2cbdf2 LEA	(%R8,%RAX,8),%RBX

0x2cbdf6 MOV	-0x40(%RBP),%R8

0x2cbdfa LEA	(%RSI,%RAX,8),%RSI

0x2cbdfe LEA	(%RDI,%RAX,8),%RDI

0x2cbe02 LEA	(%R9,%RAX,8),%R9

0x2cbe06 LEA	(%R8,%RAX,8),%R8

0x2cbe0a XOR	%EAX,%EAX

0x2cbe0c NOPL	(%RAX)

  (1761) 0x2cbe10 VMOVSD	(%R8,%RAX,8),%XMM21

  (1761) 0x2cbe17 VMOVSD	(%R9,%RAX,8),%XMM22

  (1761) 0x2cbe1e VMOVSD	(%RBX,%RAX,8),%XMM23

  (1761) 0x2cbe25 VSUBSD	%XMM18,%XMM21,%XMM21

  (1761) 0x2cbe2b VSUBSD	%XMM19,%XMM22,%XMM22

  (1761) 0x2cbe31 VSUBSD	%XMM20,%XMM23,%XMM23

  (1761) 0x2cbe37 VMULSD	%XMM21,%XMM0,%XMM24

  (1761) 0x2cbe3d VMULSD	%XMM21,%XMM3,%XMM25

  (1761) 0x2cbe43 VMULSD	%XMM21,%XMM6,%XMM21

  (1761) 0x2cbe49 VFMADD231SD	%XMM22,%XMM1,%XMM24

  (1761) 0x2cbe4f VFMADD231SD	%XMM22,%XMM4,%XMM25

  (1761) 0x2cbe55 VFMADD231SD	%XMM22,%XMM7,%XMM21

  (1761) 0x2cbe5b VPBROADCASTQ	-0xc7ce5(%RIP),%XMM22

  (1761) 0x2cbe65 VFMADD231SD	%XMM23,%XMM2,%XMM24

  (1761) 0x2cbe6b VFMADD231SD	%XMM23,%XMM5,%XMM25

  (1761) 0x2cbe71 VFMADD231SD	%XMM23,%XMM8,%XMM21

  (1761) 0x2cbe77 VPBROADCASTQ	-0xc7d89(%RIP),%XMM23

  (1761) 0x2cbe81 VMOVDQA64	%XMM23,%XMM26

  (1761) 0x2cbe87 VPTERNLOGQ	$-0x8,%XMM22,%XMM24,%XMM26

  (1761) 0x2cbe8e VADDSD	%XMM26,%XMM24,%XMM26

  (1761) 0x2cbe94 VRNDSCALESD	$0xb,%XMM26,%XMM26,%XMM26

  (1761) 0x2cbe9b VSUBSD	%XMM26,%XMM24,%XMM24

  (1761) 0x2cbea1 VMOVDQA64	%XMM23,%XMM26

  (1761) 0x2cbea7 VPTERNLOGQ	$-0x8,%XMM22,%XMM25,%XMM26

  (1761) 0x2cbeae VPTERNLOGQ	$-0x8,%XMM22,%XMM21,%XMM23

  (1761) 0x2cbeb5 VADDSD	%XMM26,%XMM25,%XMM26

  (1761) 0x2cbebb VADDSD	%XMM23,%XMM21,%XMM22

  (1761) 0x2cbec1 VMULSD	%XMM24,%XMM12,%XMM23

  (1761) 0x2cbec7 VRNDSCALESD	$0xb,%XMM26,%XMM26,%XMM26

  (1761) 0x2cbece VRNDSCALESD	$0xb,%XMM22,%XMM22,%XMM22

  (1761) 0x2cbed5 VSUBSD	%XMM26,%XMM25,%XMM25

  (1761) 0x2cbedb VMULSD	%XMM24,%XMM9,%XMM26

  (1761) 0x2cbee1 VMULSD	%XMM24,%XMM15,%XMM24

  (1761) 0x2cbee7 VSUBSD	%XMM22,%XMM21,%XMM21

  (1761) 0x2cbeed VFMADD231SD	%XMM25,%XMM10,%XMM26

  (1761) 0x2cbef3 VFMADD231SD	%XMM25,%XMM13,%XMM23

  (1761) 0x2cbef9 VFMADD231SD	%XMM25,%XMM16,%XMM24

  (1761) 0x2cbeff VFMADD231SD	%XMM11,%XMM21,%XMM26

  (1761) 0x2cbf05 VFMADD231SD	%XMM21,%XMM14,%XMM23

  (1761) 0x2cbf0b VFMADD231SD	%XMM21,%XMM17,%XMM24

  (1761) 0x2cbf11 VMOVSD	%XMM26,(%R12,%RAX,8)

  (1761) 0x2cbf18 VMOVSD	%XMM23,(%R15,%RAX,8)

  (1761) 0x2cbf1f VMOVSD	%XMM24,(%RDI,%RAX,8)

  (1761) 0x2cbf26 VMOVSD	(%R12,%RAX,8),%XMM21

  (1761) 0x2cbf2d VMOVSD	(%R15,%RAX,8),%XMM23

  (1761) 0x2cbf34 VMULSD	%XMM21,%XMM21,%XMM21

  (1761) 0x2cbf3a VFMADD231SD	%XMM24,%XMM24,%XMM21

  (1761) 0x2cbf40 VFMADD231SD	%XMM23,%XMM23,%XMM21

  (1761) 0x2cbf46 VSQRTSD	%XMM21,%XMM21,%XMM21

  (1761) 0x2cbf4c VMOVSD	%XMM21,(%RSI,%RAX,8)

  (1761) 0x2cbf53 INC	%RAX

  (1761) 0x2cbf56 CMP	%RAX,%R13

  (1761) 0x2cbf59 JNE	2cbe10

0x2cbf5f JMP	2cbd50

0x2cbf70 MOV	-0xc0(%RBP),%RAX

0x2cbf77 MOV	-0xb8(%RBP),%RSI

0x2cbf7e LEA	(%RAX,%R14,8),%R8

0x2cbf82 LEA	(%RAX,%R13,8),%R9

0x2cbf86 MOV	-0xc8(%RBP),%RAX

0x2cbf8d LEA	(%RSI,%R13,8),%R15

0x2cbf91 LEA	(%RSI,%R14,8),%RBX

0x2cbf95 CMP	%R15,%R8

0x2cbf98 LEA	(%RAX,%R13,8),%RSI

0x2cbf9c LEA	(%RAX,%R14,8),%R12

0x2cbfa0 SETB	%AL

0x2cbfa3 CMP	%R9,%RBX

0x2cbfa6 SETBB	-0x38(%RBP)

0x2cbfaa CMP	%RSI,%R8

0x2cbfad SETB	%R8B

0x2cbfb1 CMP	%R9,%R12

0x2cbfb4 SETB	%R9B

0x2cbfb8 CMP	%RSI,%RBX

0x2cbfbb SETB	%SIL

0x2cbfbf CMP	%R15,%R12

0x2cbfc2 SETB	%BL

0x2cbfc5 TEST	%BL,%SIL

0x2cbfc8 JNE	2cbdd4

0x2cbfce AND	%R9B,%R8B

0x2cbfd1 JNE	2cbdd4

0x2cbfd7 AND	-0x38(%RBP),%AL

0x2cbfda MOV	%R14,%RAX

0x2cbfdd JNE	2cbdd7

0x2cbfe3 MOV	-0x40(%RBP),%R8

0x2cbfe7 MOV	-0x68(%RBP),%R9

0x2cbfeb MOV	-0x60(%RBP),%RBX

0x2cbfef MOV	-0x30(%RBP),%R15

0x2cbff3 MOV	-0x48(%RBP),%R12

0x2cbff7 MOV	%R13D,%EAX

0x2cbffa AND	$0x1,%EAX

0x2cbffd MOV	%R13,%RSI

0x2cc000 VMOVDDUP	%XMM18,%XMM21

0x2cc006 VMOVDDUP	%XMM19,%XMM22

0x2cc00c VMOVDDUP	%XMM20,%XMM23

0x2cc012 SUB	%RAX,%RSI

0x2cc015 MOV	%R13D,%EAX

0x2cc018 AND	$0x1,%EAX

0x2cc01b SUB	%RAX,%RDI

0x2cc01e MOV	%RAX,-0x38(%RBP)

0x2cc022 MOV	%RDI,%RAX

0x2cc025 ADD	%R14,%RAX

0x2cc028 MOV	%R14,%RDI

0x2cc02b NOPL	(%RAX,%RAX,1)

  (1762) 0x2cc030 VMOVUPD	(%R8,%RDI,8),%XMM24

  (1762) 0x2cc037 VMOVUPD	(%R9,%RDI,8),%XMM25

  (1762) 0x2cc03e VMOVUPD	(%RBX,%RDI,8),%XMM26

  (1762) 0x2cc045 VSUBPD	%XMM21,%XMM24,%XMM24

  (1762) 0x2cc04b VSUBPD	%XMM22,%XMM25,%XMM25

  (1762) 0x2cc051 VSUBPD	%XMM23,%XMM26,%XMM26

  (1762) 0x2cc057 VMULPD	%XMM24,%XMM0,%XMM27

  (1762) 0x2cc05d VMULPD	%XMM24,%XMM3,%XMM28

  (1762) 0x2cc063 VMULPD	%XMM24,%XMM6,%XMM24

  (1762) 0x2cc069 VFMADD231PD	%XMM25,%XMM1,%XMM27

  (1762) 0x2cc06f VFMADD231PD	%XMM25,%XMM4,%XMM28

  (1762) 0x2cc075 VFMADD231PD	%XMM25,%XMM7,%XMM24

  (1762) 0x2cc07b VPBROADCASTQ	-0xc7f05(%RIP),%XMM25

  (1762) 0x2cc085 VFMADD231PD	%XMM26,%XMM2,%XMM27

  (1762) 0x2cc08b VFMADD231PD	%XMM26,%XMM5,%XMM28

  (1762) 0x2cc091 VFMADD231PD	%XMM26,%XMM8,%XMM24

  (1762) 0x2cc097 VPBROADCASTQ	-0xc7fa9(%RIP),%XMM26

  (1762) 0x2cc0a1 VMOVDQA64	%XMM26,%XMM29

  (1762) 0x2cc0a7 VPTERNLOGQ	$-0x8,%XMM25,%XMM27,%XMM29

  (1762) 0x2cc0ae VADDPD	%XMM29,%XMM27,%XMM29

  (1762) 0x2cc0b4 VRNDSCALEPD	$0xb,%XMM29,%XMM29

  (1762) 0x2cc0bb VSUBPD	%XMM29,%XMM27,%XMM27

  (1762) 0x2cc0c1 VMOVDQA64	%XMM26,%XMM29

  (1762) 0x2cc0c7 VPTERNLOGQ	$-0x8,%XMM25,%XMM28,%XMM29

  (1762) 0x2cc0ce VPTERNLOGQ	$-0x8,%XMM25,%XMM24,%XMM26

  (1762) 0x2cc0d5 VADDPD	%XMM29,%XMM28,%XMM29

  (1762) 0x2cc0db VADDPD	%XMM26,%XMM24,%XMM25

  (1762) 0x2cc0e1 VMULPD	%XMM27,%XMM12,%XMM26

  (1762) 0x2cc0e7 VRNDSCALEPD	$0xb,%XMM29,%XMM29

  (1762) 0x2cc0ee VRNDSCALEPD	$0xb,%XMM25,%XMM25

  (1762) 0x2cc0f5 VSUBPD	%XMM29,%XMM28,%XMM28

  (1762) 0x2cc0fb VMULPD	%XMM27,%XMM9,%XMM29

  (1762) 0x2cc101 VMULPD	%XMM27,%XMM15,%XMM27

  (1762) 0x2cc107 VSUBPD	%XMM25,%XMM24,%XMM24

  (1762) 0x2cc10d VFMADD231PD	%XMM28,%XMM10,%XMM29

  (1762) 0x2cc113 VFMADD231PD	%XMM28,%XMM13,%XMM26

  (1762) 0x2cc119 VFMADD231PD	%XMM28,%XMM16,%XMM27

  (1762) 0x2cc11f VFMADD231PD	%XMM11,%XMM24,%XMM29

  (1762) 0x2cc125 VFMADD231PD	%XMM24,%XMM14,%XMM26

  (1762) 0x2cc12b VFMADD231PD	%XMM24,%XMM17,%XMM27

  (1762) 0x2cc131 VMOVUPD	%XMM29,(%R11,%RDI,8)

  (1762) 0x2cc138 VMOVUPD	%XMM26,(%RCX,%RDI,8)

  (1762) 0x2cc13f VMOVUPD	%XMM27,(%R15,%RDI,8)

  (1762) 0x2cc146 VMOVUPD	(%R11,%RDI,8),%XMM24

  (1762) 0x2cc14d VMOVUPD	(%RCX,%RDI,8),%XMM26

  (1762) 0x2cc154 VMULPD	%XMM24,%XMM24,%XMM24

  (1762) 0x2cc15a VFMADD231PD	%XMM27,%XMM27,%XMM24

  (1762) 0x2cc160 VFMADD231PD	%XMM26,%XMM26,%XMM24

  (1762) 0x2cc166 VSQRTPD	%XMM24,%XMM24

  (1762) 0x2cc16c VMOVUPD	%XMM24,(%R12,%RDI,8)

  (1762) 0x2cc173 ADD	$0x2,%RDI

  (1762) 0x2cc177 CMP	%RDI,%RSI

  (1762) 0x2cc17a JNE	2cc030

0x2cc180 CMPQ	$0,-0x38(%RBP)

0x2cc185 JE	2cbd50

0x2cc18b JMP	2cbdd7

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h: 280 - 298

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

280:     T displ_0 = px[iat] - x0;

281:     T displ_1 = py[iat] - y0;

282:     T displ_2 = pz[iat] - z0;

283:

284:     T ar_0 = displ_0 * g00 + displ_1 * g10 + displ_2 * g20;

285:     T ar_1 = displ_0 * g01 + displ_1 * g11 + displ_2 * g21;

286:     T ar_2 = displ_0 * g02 + displ_1 * g12 + displ_2 * g22;

287:

288:     //put them in the box

289:     ar_0 -= round(ar_0);

290:     ar_1 -= round(ar_1);

291:     ar_2 -= round(ar_2);

292:

293:     //unit2cart

294:     dx[iat] = ar_0 * r00 + ar_1 * r10 + ar_2 * r20;

295:     dy[iat] = ar_0 * r01 + ar_1 * r11 + ar_2 * r21;

296:     dz[iat] = ar_0 * r02 + ar_1 * r12 + ar_2 * r22;

297:

298:     temp_r[iat] = std::sqrt(dx[iat] * dx[iat] + dy[iat] * dy[iat] + dz[iat] * dz[iat]);

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Platforms/OMPTarget/OMPTargetMath.hpp: 38 - 38

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

38:   return a < b ? a : b;

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableABOMPTarget.h: 215 - 228

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

215:         for (int team_id = 0; team_id < num_teams; team_id++)

216:         {

217:           const int first = ChunkSizePerTeam * team_id;

218:           const int last  = omptarget::min(first + ChunkSizePerTeam, num_sources_local);

[...]

228:           for (int iel = first; iel < last; iel++)

Coverage (%)	Name	Source Location	Module

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

Path /

Metric	Value
CQA speedup if no scalar integer	5.14
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	13.71
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.22
Bottlenecks	micro-operation queue,
Function	qmcplusplus::SoaDistanceTableABOMPTarget::evaluate(qmcplusplus::ParticleSet&)
Source	OMPTargetMath.hpp:38-38,SoaDistanceTableABOMPTarget.h:215-218,SoaDistanceTableABOMPTarget.h:228-228
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	12.00
CQA cycles if no scalar integer	2.33
CQA cycles if FP arith vectorized	12.00
CQA cycles if fully vectorized	0.88
Front-end cycles	12.00
P0 cycles	9.83
P1 cycles	9.83
P2 cycles	9.83
P3 cycles	9.83
P4 cycles	9.83
P5 cycles	9.83
P6 cycles	6.50
P7 cycles	6.50
P8 cycles	6.50
P9 cycles	6.50
P10 cycles	0.75
P11 cycles	0.75
P12 cycles	0.75
P13 cycles	0.75
P14 cycles	0.00
P15 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	96.00
Nb uops	96.00
Nb loads	24.00
Nb stores	2.00
Nb stack references	15.00
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	16.17
Bytes prefetched	0.00
Bytes loaded	185.00
Bytes stored	9.00
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	11.41
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	9.38
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	11.16

Metric	Value
CQA speedup if no scalar integer	5.14
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	13.71
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.22
Bottlenecks	micro-operation queue,
Function	qmcplusplus::SoaDistanceTableABOMPTarget::evaluate(qmcplusplus::ParticleSet&)
Source	OMPTargetMath.hpp:38-38,SoaDistanceTableABOMPTarget.h:215-218,SoaDistanceTableABOMPTarget.h:228-228
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	12.00
CQA cycles if no scalar integer	2.33
CQA cycles if FP arith vectorized	12.00
CQA cycles if fully vectorized	0.88
Front-end cycles	12.00
P0 cycles	9.83
P1 cycles	9.83
P2 cycles	9.83
P3 cycles	9.83
P4 cycles	9.83
P5 cycles	9.83
P6 cycles	6.50
P7 cycles	6.50
P8 cycles	6.50
P9 cycles	6.50
P10 cycles	0.75
P11 cycles	0.75
P12 cycles	0.75
P13 cycles	0.75
P14 cycles	0.00
P15 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	96.00
Nb uops	96.00
Nb loads	24.00
Nb stores	2.00
Nb stack references	15.00
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	16.17
Bytes prefetched	0.00
Bytes loaded	185.00
Bytes stored	9.00
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	11.41
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	9.38
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	11.16

Path /

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

Function	qmcplusplus::SoaDistanceTableABOMPTarget::evaluate(qmcplusplus::ParticleSet&)
Source file and lines	SoaDistanceTableABOMPTarget.h:215-228
Module	exec

The loop is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:280-298
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Platforms/OMPTarget/OMPTargetMath.hpp:38
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableABOMPTarget.h:215-218,228

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=7
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 7 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 12.00 to 2.33 cycles (5.14x 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 12.00 to 0.87 cycles (13.71x 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.

CMOVGE: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Platforms/OMPTarget/OMPTargetMath.hpp:38
CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableABOMPTarget.h:217

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This loop is probably writing/copying data or processing integer elements.

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 185 bytes. The binary loop is storing 9 bytes.

General properties

nb instructions	96
nb uops	96
loop length	405
used x86 registers	15
used mmx registers	0
used xmm registers	6
used ymm registers	0
used zmm registers	0
nb stack references	15

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	12.00 cycles
front end	12.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	9.83	9.83	9.83	9.83	9.83	9.83	6.50	6.50	6.50	6.50	0.75	0.75	0.75	0.75	0.00	0.00
cycles	9.83	9.83	9.83	9.83	9.83	9.83	6.50	6.50	6.50	6.50	0.75	0.75	0.75	0.75	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	12.00
Dispatch	9.83
Overall L1	12.00

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	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	11%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	9%
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 12.00 cycles. At this rate:

6% of peak load performance is reached (15.42 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (0.75 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 12.00 to 9.83 cycles (1.22x speedup).

ASM code

In the binary file, the address of the loop is: 2cbd6e

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	Latency	Recip. throughput	Vectorization
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
ADD $0x200,%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD $0x200,%R10D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
CMP %RDX,-0xf0(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25	scal (12.5%)
JE 2cbbf0 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x2c0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x70(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %EDX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %EDI,%R10D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV %EDI,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMOVL %R10D,%R13D	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.33	N/A
SAL $0x9,%EAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA 0x200(%RAX),%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %EDI,%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
CMOVGE %EDI,%ESI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.33	N/A
CMP %ESI,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JGE 2cbd50 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x420>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0xd0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0xe0(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %R14,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD (%RAX,%RSI,8),%XMM18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
MOV -0xd8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
VMOVSD (%RAX,%RSI,8),%XMM19	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
MOV -0xe8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
VMOVSD (%RAX,%RSI,8),%XMM20	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
CMP $0x2,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 2cbf70 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x640>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %R14,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x60(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0x48(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0x68(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RCX,%RAX,8),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R11,%RAX,8),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
SUB %RAX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R8,%RAX,8),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x40(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RSI,%RAX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RDI,%RAX,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R9,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R8,%RAX,8),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
JMP 2cbd50 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x420>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0xc0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0xb8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RAX,%R14,8),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%R13,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0xc8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RSI,%R13,8),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RSI,%R14,8),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %R15,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA (%RAX,%R13,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%R14,8),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
SETB %AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R9,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETBB -0x38(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	N/A
CMP %RSI,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %R8B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R9,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %R9B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RSI,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R15,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %BL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
TEST %BL,%SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 2cbdd4 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x4a4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
AND %R9B,%R8B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 2cbdd4 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x4a4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
AND -0x38(%RBP),%AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25	N/A
MOV %R14,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JNE 2cbdd7 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x4a7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x40(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0x68(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0x60(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
MOV -0x30(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
MOV -0x48(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
MOV %R13D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $0x1,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVDDUP %XMM18,%XMM21	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
VMOVDDUP %XMM19,%XMM22	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
VMOVDDUP %XMM20,%XMM23	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
SUB %RAX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $0x1,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %RAX,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV %RDI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R14,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMPQ $0,-0x38(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25	N/A
JE 2cbd50 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x420>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 2cbdd7 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x4a7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	N/A

Function	qmcplusplus::SoaDistanceTableABOMPTarget::evaluate(qmcplusplus::ParticleSet&)
Source file and lines	SoaDistanceTableABOMPTarget.h:215-228
Module	exec

The loop is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:280-298
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Platforms/OMPTarget/OMPTargetMath.hpp:38
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableABOMPTarget.h:215-218,228

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=7
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

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 12.00 to 2.33 cycles (5.14x speedup).

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.

CMOVGE: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Platforms/OMPTarget/OMPTargetMath.hpp:38
CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableABOMPTarget.h:217

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This loop is probably writing/copying data or processing integer elements.

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 185 bytes. The binary loop is storing 9 bytes.

General properties

nb instructions	96
nb uops	96
loop length	405
used x86 registers	15
used mmx registers	0
used xmm registers	6
used ymm registers	0
used zmm registers	0
nb stack references	15

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	12.00 cycles
front end	12.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	9.83	9.83	9.83	9.83	9.83	9.83	6.50	6.50	6.50	6.50	0.75	0.75	0.75	0.75	0.00	0.00
cycles	9.83	9.83	9.83	9.83	9.83	9.83	6.50	6.50	6.50	6.50	0.75	0.75	0.75	0.75	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	12.00
Dispatch	9.83
Overall L1	12.00

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	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	11%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	9%
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 12.00 cycles. At this rate:

6% of peak load performance is reached (15.42 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (0.75 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: 2cbd6e

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	Latency	Recip. throughput	Vectorization
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
ADD $0x200,%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD $0x200,%R10D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
CMP %RDX,-0xf0(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25	scal (12.5%)
JE 2cbbf0 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x2c0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x70(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %EDX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %EDI,%R10D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV %EDI,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMOVL %R10D,%R13D	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.33	N/A
SAL $0x9,%EAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA 0x200(%RAX),%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %EDI,%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
CMOVGE %EDI,%ESI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.33	N/A
CMP %ESI,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JGE 2cbd50 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x420>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0xd0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0xe0(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %R14,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD (%RAX,%RSI,8),%XMM18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
MOV -0xd8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
VMOVSD (%RAX,%RSI,8),%XMM19	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
MOV -0xe8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
VMOVSD (%RAX,%RSI,8),%XMM20	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
CMP $0x2,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 2cbf70 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x640>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %R14,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x60(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0x48(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0x68(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RCX,%RAX,8),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R11,%RAX,8),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
SUB %RAX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R8,%RAX,8),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x40(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RSI,%RAX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RDI,%RAX,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R9,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R8,%RAX,8),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
JMP 2cbd50 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x420>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0xc0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0xb8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RAX,%R14,8),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%R13,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0xc8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RSI,%R13,8),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RSI,%R14,8),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %R15,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA (%RAX,%R13,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%R14,8),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
SETB %AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R9,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETBB -0x38(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	N/A
CMP %RSI,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %R8B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R9,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %R9B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RSI,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R15,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %BL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
TEST %BL,%SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 2cbdd4 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x4a4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
AND %R9B,%R8B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 2cbdd4 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x4a4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
AND -0x38(%RBP),%AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25	N/A
MOV %R14,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JNE 2cbdd7 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x4a7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x40(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0x68(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV -0x60(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
MOV -0x30(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
MOV -0x48(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
MOV %R13D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $0x1,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVDDUP %XMM18,%XMM21	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
VMOVDDUP %XMM19,%XMM22	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
VMOVDDUP %XMM20,%XMM23	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
SUB %RAX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $0x1,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %RAX,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV %RDI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R14,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMPQ $0,-0x38(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25	N/A
JE 2cbd50 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x420>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 2cbdd7 <_ZN11qmcplusplus27SoaDistanceTableABOMPTargetIdLj3ELi40EE8evaluateERNS_11ParticleSetE+0x4a7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	N/A

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

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code