OV - exec - Function sortAtomsInCell

	Function: sortAtomsInCell	Module: exec	Source: haloExchange.c:614-645	Coverage (incl. loops): 1.23% \| (excl. loops): 0.03%

/home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c: 614 - 645

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

614: {

615:    int nAtoms = boxes->nAtoms[iBox];

616:

617:    AtomMsg tmp[nAtoms];

618:

619:    int begin = iBox*MAXATOMS;

620:    int end = begin + nAtoms;

621:    for (int ii=begin, iTmp=0; ii<end; ++ii, ++iTmp)

622:    {

623:       tmp[iTmp].gid  = atoms->gid[ii];

624:       tmp[iTmp].type = atoms->iSpecies[ii];

625:       tmp[iTmp].rx =   atoms->r[ii][0];

626:       tmp[iTmp].ry =   atoms->r[ii][1];

627:       tmp[iTmp].rz =   atoms->r[ii][2];

628:       tmp[iTmp].px =   atoms->p[ii][0];

629:       tmp[iTmp].py =   atoms->p[ii][1];

630:       tmp[iTmp].pz =   atoms->p[ii][2];

631:    }

632:    qsort(&tmp, nAtoms, sizeof(AtomMsg), sortAtomsById);

633:    for (int ii=begin, iTmp=0; ii<end; ++ii, ++iTmp)

634:    {

635:       atoms->gid[ii]   = tmp[iTmp].gid;

636:       atoms->iSpecies[ii] = tmp[iTmp].type;

637:       atoms->r[ii][0]  = tmp[iTmp].rx;

638:       atoms->r[ii][1]  = tmp[iTmp].ry;

639:       atoms->r[ii][2]  = tmp[iTmp].rz;

640:       atoms->p[ii][0]  = tmp[iTmp].px;

641:       atoms->p[ii][1]  = tmp[iTmp].py;

642:       atoms->p[ii][2]  = tmp[iTmp].pz;

643:    }

644:

645: }

0x4086e0 PUSH	%RBP

0x4086e1 MOV	%RSP,%RBP

0x4086e4 PUSH	%R15

0x4086e6 PUSH	%R14

0x4086e8 PUSH	%R13

0x4086ea PUSH	%R12

0x4086ec PUSH	%RBX

0x4086ed SUB	$0x28,%RSP

0x4086f1 MOV	0x78(%RSI),%RAX

0x4086f5 MOVSXD	%EDX,%RCX

0x4086f8 MOVSXD	(%RAX,%RCX,4),%RAX

0x4086fc MOV	%EAX,%ESI

0x4086fe IMUL	$0x38,%RSI,%RCX

0x408702 ADD	$0xf,%RCX

0x408706 AND	$-0x10,%RCX

0x40870a MOV	%RSP,%RBX

0x40870d SUB	%RCX,%RBX

0x408710 MOV	%RBX,%RSP

0x408713 TEST	%RAX,%RAX

0x408716 JLE	4088fd

0x40871c MOV	%RDI,%R14

0x40871f SAL	$0x6,%EDX

0x408722 MOV	0x8(%RDI),%RDI

0x408726 MOV	0x10(%R14),%R10

0x40872a MOV	0x18(%R14),%RAX

0x40872e MOV	0x20(%R14),%RCX

0x408732 MOVSXD	%EDX,%R15

0x408735 MOV	%RSI,-0x38(%RBP)

0x408739 MOVSXD	%ESI,%RDX

0x40873c LEA	(%RDX,%R15,1),%RSI

0x408740 IMUL	$0x38,%RDX,%R8

0x408744 LEA	(%RDI,%RSI,4),%R9

0x408748 ADD	$-0x4,%R9

0x40874c CMP	%RBX,%R9

0x40874f SETAE	%R11B

0x408753 LEA	(%R8,%RBX,1),%R9

0x408757 ADD	$-0x4,%R9

0x40875b LEA	(%RDI,%R15,4),%RDI

0x40875f CMP	%RDI,%R9

0x408762 SETAE	%R13B

0x408766 LEA	(%R10,%R15,4),%R8

0x40876a MOV	%R9,-0x40(%RBP)

0x40876e CMP	%R8,%R9

0x408771 SETB	%R9B

0x408775 LEA	(%R10,%RSI,4),%R10

0x408779 ADD	$-0x4,%R10

0x40877d CMP	%RBX,%R10

0x408780 LEA	0x1(%R15),%R12

0x408784 SETB	%R10B

0x408788 TEST	%R13B,%R11B

0x40878b JNE	408917

0x408791 OR	%R10B,%R9B

0x408794 JE	408917

0x40879a CMP	%R12,%RSI

0x40879d CMOVG	%RSI,%R12

0x4087a1 MOV	%R12,%RSI

0x4087a4 SUB	%R15,%RSI

0x4087a7 MOV	%RSI,%R9

0x4087aa AND	$-0x4,%R9

0x4087ae JE	40898e

0x4087b4 MOV	%RSI,-0x48(%RBP)

0x4087b8 LEA	-0x1(%R9),%R11

0x4087bc LEA	(,%R15,8),%RSI

0x4087c4 LEA	(%RSI,%RSI,2),%R13

0x4087c8 XOR	%R10D,%R10D

0x4087cb VPBROADCASTQ	0x1ac2c(%RIP),%YMM0

0x4087d4 VMOVDQU	0x1ac44(%RIP),%YMM1

0x4087dc MOV	$0xf,%SIL

0x4087df VMOVUPD	0x1ac59(%RIP),%YMM2

0x4087e7 VMOVUPD	0x1ac71(%RIP),%YMM3

0x4087ef VMOVUPD	0x1ac89(%RIP),%YMM4

0x4087f7 NOPW	(%RAX,%RAX,1)

(65) 0x408800 VMOVDQU	(%RDI,%R10,4),%XMM5

(65) 0x408806 VPBROADCASTQ	%R10,%YMM6

(65) 0x40880c VPMULLQ	%YMM0,%YMM6,%YMM6

(65) 0x408812 VPADDQ	%YMM1,%YMM6,%YMM6

(65) 0x408816 KXNORW	%K0,%K0,%K1

(65) 0x40881a VPSCATTERQD	%XMM5,(%RBX,%YMM6,1){%K1}

(65) 0x408821 VMOVDQU	(%R8,%R10,4),%XMM5

(65) 0x408827 KXNORW	%K0,%K0,%K1

(65) 0x40882b VPSCATTERQD	%XMM5,0x4(%RBX,%YMM6,1){%K1}

(65) 0x408833 KMOVD	%ESI,%K1

(65) 0x408837 VMOVUPD	0x40(%RAX,%R13,1),%ZMM5{%K1}{z}

(65) 0x40883f VMOVUPD	(%RAX,%R13,1),%ZMM7

(65) 0x408846 VMOVAPD	%ZMM7,%ZMM8

(65) 0x40884c VPERMT2PD	%ZMM5,%ZMM2,%ZMM8

(65) 0x408852 VMOVAPD	%ZMM7,%ZMM9

(65) 0x408858 VPERMT2PD	%ZMM5,%ZMM3,%ZMM9

(65) 0x40885e VPERMT2PD	%ZMM5,%ZMM4,%ZMM7

(65) 0x408864 KXNORW	%K0,%K0,%K2

(65) 0x408868 VSCATTERQPD	%YMM8,0x8(%RBX,%YMM6,1){%K2}

(65) 0x408870 KXNORW	%K0,%K0,%K2

(65) 0x408874 VSCATTERQPD	%YMM9,0x10(%RBX,%YMM6,1){%K2}

(65) 0x40887c KXNORW	%K0,%K0,%K2

(65) 0x408880 VSCATTERQPD	%YMM7,0x18(%RBX,%YMM6,1){%K2}

(65) 0x408888 VMOVUPD	0x40(%RCX,%R13,1),%ZMM5{%K1}{z}

(65) 0x408890 VMOVUPD	(%RCX,%R13,1),%ZMM7

(65) 0x408897 VMOVAPD	%ZMM7,%ZMM8

(65) 0x40889d VPERMT2PD	%ZMM5,%ZMM2,%ZMM8

(65) 0x4088a3 VMOVAPD	%ZMM7,%ZMM9

(65) 0x4088a9 VPERMT2PD	%ZMM5,%ZMM3,%ZMM9

(65) 0x4088af VPERMT2PD	%ZMM5,%ZMM4,%ZMM7

(65) 0x4088b5 KXNORW	%K0,%K0,%K1

(65) 0x4088b9 VSCATTERQPD	%YMM8,0x20(%RBX,%YMM6,1){%K1}

(65) 0x4088c1 KXNORW	%K0,%K0,%K1

(65) 0x4088c5 VSCATTERQPD	%YMM9,0x28(%RBX,%YMM6,1){%K1}

(65) 0x4088cd KXNORW	%K0,%K0,%K1

(65) 0x4088d1 VSCATTERQPD	%YMM7,0x30(%RBX,%YMM6,1){%K1}

(65) 0x4088d9 ADD	$0x4,%R10

(65) 0x4088dd ADD	$0x60,%R13

(65) 0x4088e1 CMP	%R11,%R10

(65) 0x4088e4 JLE	408800

0x4088ea CMP	%R9,-0x48(%RBP)

0x4088ee MOV	-0x38(%RBP),%RSI

0x4088f2 JNE	408995

0x4088f8 JMP	408a02

0x4088fd MOV	$0x38,%EDX

0x408902 MOV	$0x408ed0,%ECX

0x408907 MOV	%RBX,%RDI

0x40890a MOV	%RAX,%RSI

0x40890d CALL	403280 <qsort@plt>

0x408912 JMP	408eb9

0x408917 LEA	(,%R15,8),%R9

0x40891f LEA	(%R9,%R9,2),%R9

0x408923 XOR	%R10D,%R10D

0x408926 MOV	%RBX,%R11

0x408929 NOPL	(%RAX)

(60) 0x408930 MOV	(%RDI,%R10,4),%R13D

(60) 0x408934 MOV	%R13D,(%R11)

(60) 0x408937 MOV	(%R8,%R10,4),%R13D

(60) 0x40893b MOV	%R13D,0x4(%R11)

(60) 0x40893f VPBROADCASTQ	0x10(%RAX,%R9,1),%YMM0

(60) 0x408946 VMOVDQU	(%RAX,%R9,1),%XMM1

(60) 0x40894c VPBLENDD	$0x30,%YMM0,%YMM1,%YMM0

(60) 0x408952 VPBROADCASTQ	(%RCX,%R9,1),%YMM1

(60) 0x408958 VPBLENDD	$-0x40,%YMM1,%YMM0,%YMM0

(60) 0x40895e VMOVDQU	%YMM0,0x8(%R11)

(60) 0x408964 VMOVDQU	0x8(%RCX,%R9,1),%XMM0

(60) 0x40896b VMOVDQU	%XMM0,0x28(%R11)

(60) 0x408971 INC	%R10

(60) 0x408974 ADD	$0x38,%R11

(60) 0x408978 ADD	$0x18,%R9

(60) 0x40897c CMP	%R10,%RDX

(60) 0x40897f JNE	408930

0x408981 CMP	%R12,%RSI

0x408984 CMOVG	%RSI,%R12

0x408988 MOV	-0x38(%RBP),%RSI

0x40898c JMP	408a02

0x40898e XOR	%R9D,%R9D

0x408991 MOV	-0x38(%RBP),%RSI

0x408995 IMUL	$0x38,%R9,%R13

0x408999 ADD	%RBX,%R13

0x40899c LEA	(%R9,%R15,1),%R10

0x4089a0 ADD	%R10,%R10

0x4089a3 LEA	(%R10,%R10,2),%R10

0x4089a7 NOPW	(%RAX,%RAX,1)

(64) 0x4089b0 MOV	(%RDI,%R9,4),%R11D

(64) 0x4089b4 MOV	%R11D,(%R13)

(64) 0x4089b8 MOV	(%R8,%R9,4),%R11D

(64) 0x4089bc MOV	%R11D,0x4(%R13)

(64) 0x4089c0 VPBROADCASTQ	0x10(%RAX,%R10,4),%YMM0

(64) 0x4089c7 VMOVDQU	(%RAX,%R10,4),%XMM1

(64) 0x4089cd VPBLENDD	$0x30,%YMM0,%YMM1,%YMM0

(64) 0x4089d3 VPBROADCASTQ	(%RCX,%R10,4),%YMM1

(64) 0x4089d9 VPBLENDD	$-0x40,%YMM1,%YMM0,%YMM0

(64) 0x4089df VMOVDQU	%YMM0,0x8(%R13)

(64) 0x4089e5 VMOVDQU	0x8(%RCX,%R10,4),%XMM0

(64) 0x4089ec VMOVDQU	%XMM0,0x28(%R13)

(64) 0x4089f2 INC	%R9

(64) 0x4089f5 ADD	$0x38,%R13

(64) 0x4089f9 ADD	$0x6,%R10

(64) 0x4089fd CMP	%R9,%RDX

(64) 0x408a00 JNE	4089b0

0x408a02 MOV	-0x40(%RBP),%R13

0x408a06 MOV	$0x38,%EDX

0x408a0b MOV	$0x408ed0,%ECX

0x408a10 MOV	%RBX,%RDI

0x408a13 VZEROUPPER

0x408a16 CALL	403280 <qsort@plt>

0x408a1b MOV	0x8(%R14),%RAX

0x408a1f MOV	0x10(%R14),%RCX

0x408a23 MOV	0x18(%R14),%RDX

0x408a27 MOV	0x20(%R14),%RSI

0x408a2b LEA	(%RAX,%R15,4),%RDI

0x408a2f CMP	%RDI,%R13

0x408a32 SETAEB	-0x40(%RBP)

0x408a36 LEA	-0x1(%R12),%R8

0x408a3b LEA	(%RAX,%R12,4),%R9

0x408a3f ADD	$-0x4,%R9

0x408a43 CMP	%RBX,%R9

0x408a46 SETAEB	-0x38(%RBP)

0x408a4a SUB	%R15,%R8

0x408a4d IMUL	$0x38,%R8,%R8

0x408a51 LEA	(%RBX,%R8,1),%R10

0x408a55 ADD	$0x34,%R10

0x408a59 LEA	(%RCX,%R15,4),%R8

0x408a5d CMP	%R8,%R10

0x408a60 SETB	%R11B

0x408a64 LEA	(%RCX,%R12,4),%R10

0x408a68 ADD	$-0x4,%R10

0x408a6c CMP	%RBX,%R10

0x408a6f SETBB	-0x48(%RBP)

0x408a73 CMP	%R8,%R9

0x408a76 SETBB	-0x2a(%RBP)

0x408a7a CMP	%RDI,%R10

0x408a7d SETBB	-0x29(%RBP)

0x408a81 LEA	-0x8(,%R12,8),%R9

0x408a89 LEA	(%R9,%R9,2),%R10

0x408a8d LEA	(%RDX,%R10,1),%R13

0x408a91 ADD	$0x10,%R13

0x408a95 LEA	(,%R15,8),%R9

0x408a9d LEA	(%R9,%R9,2),%R9

0x408aa1 LEA	(%RSI,%R9,1),%R14

0x408aa5 CMP	%R14,%R13

0x408aa8 SETB	%R13B

0x408aac ADD	%RSI,%R10

0x408aaf ADD	$0x10,%R10

0x408ab3 LEA	(%RDX,%R9,1),%R14

0x408ab7 CMP	%R14,%R10

0x408aba SETB	%R10B

0x408abe MOVZX	-0x38(%RBP),%R14D

0x408ac3 TEST	%R14B,-0x40(%RBP)

0x408ac7 JNE	408def

0x408acd OR	-0x48(%RBP),%R11B

0x408ad1 JE	408def

0x408ad7 MOVZX	-0x29(%RBP),%R11D

0x408adc OR	%R11B,-0x2a(%RBP)

0x408ae0 JE	408def

0x408ae6 OR	%R10B,%R13B

0x408ae9 JE	408def

0x408aef MOV	%R12,%R11

0x408af2 SUB	%R15,%R11

0x408af5 MOV	%R11,%R10

0x408af8 AND	$-0x10,%R10

0x408afc JE	408e4b

0x408b02 LEA	-0x1(%R10),%R14

0x408b06 XOR	%R13D,%R13D

0x408b09 VPBROADCASTQ	0x1a8ed(%RIP),%ZMM0

0x408b13 VMOVDQU64	0x1a6e3(%RIP),%ZMM1

0x408b1d VMOVDQU64	0x1a719(%RIP),%ZMM2

0x408b27 VMOVUPD	0x1a74f(%RIP),%ZMM3

0x408b31 VMOVUPD	0x1a785(%RIP),%ZMM4

0x408b3b VMOVUPD	0x1a7bb(%RIP),%ZMM5

0x408b45 VMOVUPD	0x1a7f1(%RIP),%ZMM6

0x408b4f VMOVUPD	0x1a827(%RIP),%ZMM7

0x408b59 VMOVUPD	0x1a85d(%RIP),%ZMM8

0x408b63 NOPW	%CS:(%RAX,%RAX,1)

(63) 0x408b70 VPBROADCASTQ	%R13,%ZMM9

(63) 0x408b76 VPMULLQ	%ZMM0,%ZMM9,%ZMM9

(63) 0x408b7c VPADDQ	%ZMM1,%ZMM9,%ZMM10

(63) 0x408b82 VPADDQ	%ZMM2,%ZMM9,%ZMM9

(63) 0x408b88 KXNORW	%K0,%K0,%K1

(63) 0x408b8c VPXOR	%XMM11,%XMM11,%XMM11

(63) 0x408b91 VPGATHERQD	(%RBX,%ZMM9,1),%YMM11{%K1}

(63) 0x408b98 KXNORW	%K0,%K0,%K1

(63) 0x408b9c VPXOR	%XMM12,%XMM12,%XMM12

(63) 0x408ba1 VPGATHERQD	(%RBX,%ZMM10,1),%YMM12{%K1}

(63) 0x408ba8 VINSERTI64X4	$0x1,%YMM11,%ZMM12,%ZMM11

(63) 0x408baf VMOVDQU64	%ZMM11,(%RDI,%R13,4)

(63) 0x408bb6 KXNORW	%K0,%K0,%K1

(63) 0x408bba VPXOR	%XMM11,%XMM11,%XMM11

(63) 0x408bbf VPGATHERQD	0x4(%RBX,%ZMM9,1),%YMM11{%K1}

(63) 0x408bc7 KXNORW	%K0,%K0,%K1

(63) 0x408bcb VPXOR	%XMM12,%XMM12,%XMM12

(63) 0x408bd0 VPGATHERQD	0x4(%RBX,%ZMM10,1),%YMM12{%K1}

(63) 0x408bd8 VINSERTI64X4	$0x1,%YMM11,%ZMM12,%ZMM11

(63) 0x408bdf VMOVDQU64	%ZMM11,(%R8,%R13,4)

(63) 0x408be6 VPXOR	%XMM11,%XMM11,%XMM11

(63) 0x408beb KXNORW	%K0,%K0,%K1

(63) 0x408bef VGATHERQPD	0x8(%RBX,%ZMM9,1),%ZMM11{%K1}

(63) 0x408bf7 VPXOR	%XMM12,%XMM12,%XMM12

(63) 0x408bfc KXNORW	%K0,%K0,%K1

(63) 0x408c00 VGATHERQPD	0x8(%RBX,%ZMM10,1),%ZMM12{%K1}

(63) 0x408c08 VXORPD	%XMM13,%XMM13,%XMM13

(63) 0x408c0d KXNORW	%K0,%K0,%K1

(63) 0x408c11 VGATHERQPD	0x10(%RBX,%ZMM9,1),%ZMM13{%K1}

(63) 0x408c19 VXORPD	%XMM14,%XMM14,%XMM14

(63) 0x408c1e KXNORW	%K0,%K0,%K1

(63) 0x408c22 VGATHERQPD	0x10(%RBX,%ZMM10,1),%ZMM14{%K1}

(63) 0x408c2a VXORPD	%XMM15,%XMM15,%XMM15

(63) 0x408c2f KXNORW	%K0,%K0,%K1

(63) 0x408c33 VGATHERQPD	0x18(%RBX,%ZMM10,1),%ZMM15{%K1}

(63) 0x408c3b VXORPD	%XMM16,%XMM16,%XMM16

(63) 0x408c41 KXNORW	%K0,%K0,%K1

(63) 0x408c45 VGATHERQPD	0x18(%RBX,%ZMM9,1),%ZMM16{%K1}

(63) 0x408c4d VMOVAPD	%ZMM14,%ZMM17

(63) 0x408c53 VPERMT2PD	%ZMM12,%ZMM3,%ZMM17

(63) 0x408c59 VMOVAPD	%ZMM12,%ZMM18

(63) 0x408c5f VPERMT2PD	%ZMM14,%ZMM4,%ZMM18

(63) 0x408c65 VMOVAPD	%ZMM13,%ZMM19

(63) 0x408c6b VPERMT2PD	%ZMM11,%ZMM3,%ZMM19

(63) 0x408c71 VMOVAPD	%ZMM11,%ZMM20

(63) 0x408c77 VPERMT2PD	%ZMM13,%ZMM4,%ZMM20

(63) 0x408c7d VPERMT2PD	%ZMM14,%ZMM5,%ZMM12

(63) 0x408c83 VPERMT2PD	%ZMM13,%ZMM5,%ZMM11

(63) 0x408c89 VPERMT2PD	%ZMM16,%ZMM6,%ZMM11

(63) 0x408c8f VPERMT2PD	%ZMM15,%ZMM6,%ZMM12

(63) 0x408c95 VPERMT2PD	%ZMM16,%ZMM7,%ZMM20

(63) 0x408c9b VPERMT2PD	%ZMM16,%ZMM8,%ZMM19

(63) 0x408ca1 VPERMT2PD	%ZMM15,%ZMM7,%ZMM18

(63) 0x408ca7 VPERMT2PD	%ZMM15,%ZMM8,%ZMM17

(63) 0x408cad VMOVUPD	%ZMM17,0x80(%RDX,%R9,1)

(63) 0x408cb5 VMOVUPD	%ZMM18,(%RDX,%R9,1)

(63) 0x408cbc VMOVUPD	%ZMM19,0x140(%RDX,%R9,1)

(63) 0x408cc4 VMOVUPD	%ZMM20,0xc0(%RDX,%R9,1)

(63) 0x408ccc VMOVUPD	%ZMM12,0x40(%RDX,%R9,1)

(63) 0x408cd4 VMOVUPD	%ZMM11,0x100(%RDX,%R9,1)

(63) 0x408cdc VXORPD	%XMM11,%XMM11,%XMM11

(63) 0x408ce1 KXNORW	%K0,%K0,%K1

(63) 0x408ce5 VGATHERQPD	0x20(%RBX,%ZMM9,1),%ZMM11{%K1}

(63) 0x408ced VXORPD	%XMM12,%XMM12,%XMM12

(63) 0x408cf2 KXNORW	%K0,%K0,%K1

(63) 0x408cf6 VGATHERQPD	0x20(%RBX,%ZMM10,1),%ZMM12{%K1}

(63) 0x408cfe VXORPD	%XMM13,%XMM13,%XMM13

(63) 0x408d03 KXNORW	%K0,%K0,%K1

(63) 0x408d07 VGATHERQPD	0x28(%RBX,%ZMM9,1),%ZMM13{%K1}

(63) 0x408d0f VXORPD	%XMM14,%XMM14,%XMM14

(63) 0x408d14 KXNORW	%K0,%K0,%K1

(63) 0x408d18 VGATHERQPD	0x28(%RBX,%ZMM10,1),%ZMM14{%K1}

(63) 0x408d20 VXORPD	%XMM15,%XMM15,%XMM15

(63) 0x408d25 KXNORW	%K0,%K0,%K1

(63) 0x408d29 VGATHERQPD	0x30(%RBX,%ZMM10,1),%ZMM15{%K1}

(63) 0x408d31 VXORPD	%XMM10,%XMM10,%XMM10

(63) 0x408d36 KXNORW	%K0,%K0,%K1

(63) 0x408d3a VGATHERQPD	0x30(%RBX,%ZMM9,1),%ZMM10{%K1}

(63) 0x408d42 VMOVAPD	%ZMM14,%ZMM9

(63) 0x408d48 VPERMT2PD	%ZMM12,%ZMM3,%ZMM9

(63) 0x408d4e VMOVAPD	%ZMM12,%ZMM16

(63) 0x408d54 VPERMT2PD	%ZMM14,%ZMM4,%ZMM16

(63) 0x408d5a VMOVAPD	%ZMM13,%ZMM17

(63) 0x408d60 VPERMT2PD	%ZMM11,%ZMM3,%ZMM17

(63) 0x408d66 VMOVAPD	%ZMM11,%ZMM18

(63) 0x408d6c VPERMT2PD	%ZMM13,%ZMM4,%ZMM18

(63) 0x408d72 VPERMT2PD	%ZMM14,%ZMM5,%ZMM12

(63) 0x408d78 VPERMT2PD	%ZMM13,%ZMM5,%ZMM11

(63) 0x408d7e VPERMT2PD	%ZMM10,%ZMM6,%ZMM11

(63) 0x408d84 VPERMT2PD	%ZMM15,%ZMM6,%ZMM12

(63) 0x408d8a VPERMT2PD	%ZMM10,%ZMM7,%ZMM18

(63) 0x408d90 VPERMT2PD	%ZMM10,%ZMM8,%ZMM17

(63) 0x408d96 VPERMT2PD	%ZMM15,%ZMM7,%ZMM16

(63) 0x408d9c VPERMT2PD	%ZMM15,%ZMM8,%ZMM9

(63) 0x408da2 VMOVUPD	%ZMM9,0x80(%RSI,%R9,1)

(63) 0x408daa VMOVUPD	%ZMM16,(%RSI,%R9,1)

(63) 0x408db1 VMOVUPD	%ZMM17,0x140(%RSI,%R9,1)

(63) 0x408db9 VMOVUPD	%ZMM18,0xc0(%RSI,%R9,1)

(63) 0x408dc1 VMOVUPD	%ZMM12,0x40(%RSI,%R9,1)

(63) 0x408dc9 VMOVUPD	%ZMM11,0x100(%RSI,%R9,1)

(63) 0x408dd1 ADD	$0x10,%R13

(63) 0x408dd5 ADD	$0x180,%R9

(63) 0x408ddc CMP	%R14,%R13

(63) 0x408ddf JLE	408b70

0x408de5 CMP	%R10,%R11

0x408de8 JNE	408e4e

0x408dea JMP	408eb9

0x408def LEA	(%R15,%R15,2),%RDI

0x408df3 LEA	0x2(,%RDI,2),%RDI

0x408dfb NOPL	(%RAX,%RAX,1)

(61) 0x408e00 MOV	(%RBX),%R8D

(61) 0x408e03 MOV	%R8D,(%RAX,%R15,4)

(61) 0x408e07 MOV	0x4(%RBX),%R8D

(61) 0x408e0b MOV	%R8D,(%RCX,%R15,4)

(61) 0x408e0f VMOVSD	0x8(%RBX),%XMM0

(61) 0x408e14 VMOVSD	%XMM0,-0x8(%RDX,%RDI,4)

(61) 0x408e1a VMOVUPS	0x10(%RBX),%XMM0

(61) 0x408e1f VMOVUPS	%XMM0,(%RDX,%RDI,4)

(61) 0x408e24 VMOVSD	0x20(%RBX),%XMM0

(61) 0x408e29 VMOVSD	%XMM0,-0x8(%RSI,%RDI,4)

(61) 0x408e2f VMOVDQU	0x28(%RBX),%XMM0

(61) 0x408e34 VMOVDQU	%XMM0,(%RSI,%RDI,4)

(61) 0x408e39 ADD	$0x6,%RDI

(61) 0x408e3d INC	%R15

(61) 0x408e40 ADD	$0x38,%RBX

(61) 0x408e44 CMP	%R15,%R12

(61) 0x408e47 JNE	408e00

0x408e49 JMP	408eb9

0x408e4b XOR	%R10D,%R10D

0x408e4e LEA	(%R10,%R10,2),%RDI

0x408e52 LEA	(%R15,%R15,2),%R8

0x408e56 SAL	$0x3,%R8

0x408e5a LEA	(%R8,%RDI,8),%RDI

0x408e5e ADD	%RDI,%RSI

0x408e61 ADD	%RDI,%RDX

0x408e64 ADD	%R10,%R15

0x408e67 IMUL	$0x38,%R10,%RDI

0x408e6b ADD	%RDI,%RBX

0x408e6e XOR	%EDI,%EDI

(62) 0x408e70 MOV	(%RBX),%R8D

(62) 0x408e73 MOV	%R8D,(%RAX,%R15,4)

(62) 0x408e77 MOV	0x4(%RBX),%R8D

(62) 0x408e7b MOV	%R8D,(%RCX,%R15,4)

(62) 0x408e7f VMOVSD	0x8(%RBX),%XMM0

(62) 0x408e84 VMOVSD	%XMM0,(%RDX,%RDI,1)

(62) 0x408e89 VMOVUPS	0x10(%RBX),%XMM0

(62) 0x408e8e VMOVUPS	%XMM0,0x8(%RDX,%RDI,1)

(62) 0x408e94 VMOVSD	0x20(%RBX),%XMM0

(62) 0x408e99 VMOVSD	%XMM0,(%RSI,%RDI,1)

(62) 0x408e9e VMOVDQU	0x28(%RBX),%XMM0

(62) 0x408ea3 VMOVDQU	%XMM0,0x8(%RSI,%RDI,1)

(62) 0x408ea9 ADD	$0x18,%RDI

(62) 0x408ead INC	%R15

(62) 0x408eb0 ADD	$0x38,%RBX

(62) 0x408eb4 CMP	%R15,%R12

(62) 0x408eb7 JNE	408e70

0x408eb9 LEA	-0x28(%RBP),%RSP

0x408ebd POP	%RBX

0x408ebe POP	%R12

0x408ec0 POP	%R13

0x408ec2 POP	%R14

0x408ec4 POP	%R15

0x408ec6 POP	%RBP

0x408ec7 VZEROUPPER

0x408eca RET

0x408ecb NOPL	(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
►12.72+	redistributeAtoms.extracted	timestep.c:154	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►12.38+	redistributeAtoms.extracted	timestep.c:154	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►12.33+	redistributeAtoms.extracted	timestep.c:154	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►11.98+	redistributeAtoms.extracted	timestep.c:154	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►11.97+	redistributeAtoms.extracted	timestep.c:154	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►11.85+	redistributeAtoms.extracted	timestep.c:154	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►11.72+	redistributeAtoms.extracted	timestep.c:154	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►11.45+	redistributeAtoms.extracted	timestep.c:153	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6

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 /

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

The code analyzed by CQA in that panel excludes loops and represents 0.03% of application time for run icx_0

Source file and lines	haloExchange.c:614-645
Module	exec

The function is defined in /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:614-645.

Warnings:
Ignoring paths for analysis

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 24.88 to 5.63 cycles (4.42x speedup).

Workaround

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

Vectorization

Your function is probably not vectorized. Only 30% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 24.88 to 21.29 cycles (1.17x speedup).

Details

Store and arithmetical 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 function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function 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

CALL instructions

Detected function call instructions.

Details

Calling (and then returning from) a function prevents many compiler optimizations (like vectorization), breaks control flow (which reduces pipeline performance) and executes extra instructions to save/restore the registers used inside it, which is very expensive (dozens of cycles). Consider to inline small functions.

qsort@plt: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:632
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:632

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.

CMOVG: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:621
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:635

Vector unaligned load/store instructions

Detected 6 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 6 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639

Workaround

Use vector aligned instructions:

align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Conversion instructions

Detected expensive conversion instructions.

Details

MOVZX: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:621
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:621

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

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

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 777 bytes. The binary function is storing 30 bytes.

General properties

nb instructions	201
nb uops	199
loop length	860
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	5
used zmm registers	9
nb stack references	6

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	24.88 cycles
front end	24.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	22.33	22.33	22.33	22.33	22.33	22.33	11.00	11.00	11.00	11.00	0.00	1.00	1.00	0.00	0.00	0.00
cycles	22.33	22.33	22.33	22.33	22.33	22.33	11.00	11.00	11.00	11.00	0.00	1.00	1.00	0.00	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	24.88
Dispatch	22.33
Overall L1	24.88

Vectorization ratios

INT

all	13%
load	37%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	8%

all	100%
load	100%
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	NA (no other vectorizable/vectorized instructions)

INT+FP

all	29%
load	70%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	8%

Vector efficiency ratios

INT

all	18%
load	37%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	13%

all	83%
load	83%
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	NA (no other vectorizable/vectorized instructions)

INT+FP

all	30%
load	61%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 24.88 cycles. At this rate:

12% of peak load performance is reached (31.24 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (1.21 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 24.88 to 22.33 cycles (1.11x speedup).

ASM code

In the binary file, the address of the function is: 4086e0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P11	P12	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x28,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x78(%RSI),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOVSXD %EDX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOVSXD (%RAX,%RCX,4),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	N/A
MOV %EAX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL $0x38,%RSI,%RCX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	3	0.33	N/A
ADD $0xf,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
AND $-0x10,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RSP,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RCX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
JLE 4088fd <sortAtomsInCell+0x21d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x6,%EDX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33	N/A
MOV 0x8(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x10(%R14),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x18(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x20(%R14),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOVSXD %EDX,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.50	scal (12.5%)
MOVSXD %ESI,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%RDX,%R15,1),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
IMUL $0x38,%RDX,%R8	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	3	0.33	N/A
LEA (%RDI,%RSI,4),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $-0x4,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
CMP %RBX,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETAE %R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%R8,%RBX,1),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $-0x4,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%RDI,%R15,4),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
CMP %RDI,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETAE %R13B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%R10,%R15,4),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
MOV %R9,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.50	scal (12.5%)
CMP %R8,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	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	1	0.17	N/A
LEA (%R10,%RSI,4),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $-0x4,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
CMP %RBX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA 0x1(%R15),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
SETB %R10B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
TEST %R13B,%R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
JNE 408917 <sortAtomsInCell+0x237>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
OR %R10B,%R9B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
JE 408917 <sortAtomsInCell+0x237>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
CMP %R12,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %RSI,%R12	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33	N/A
MOV %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %R15,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
JE 40898e <sortAtomsInCell+0x2ae>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RSI,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.50	scal (12.5%)
LEA -0x1(%R9),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (,%R15,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%RSI,%RSI,2),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VPBROADCASTQ 0x1ac2c(%RIP),%YMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	1	0.50	scal (12.5%)
VMOVDQU 0x1ac44(%RIP),%YMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (50.0%)
MOV $0xf,%SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD 0x1ac59(%RIP),%YMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (50.0%)
VMOVUPD 0x1ac71(%RIP),%YMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (50.0%)
VMOVUPD 0x1ac89(%RIP),%YMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (50.0%)
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %R9,-0x48(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOV -0x38(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
JNE 408995 <sortAtomsInCell+0x2b5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
JMP 408a02 <sortAtomsInCell+0x322>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
MOV $0x38,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV $0x408ed0,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 403280 <qsort@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0.50	N/A
JMP 408eb9 <sortAtomsInCell+0x7d9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
LEA (,%R15,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%R9,%R9,2),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV %RBX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %R12,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %RSI,%R12	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33	N/A
MOV -0x38(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
JMP 408a02 <sortAtomsInCell+0x322>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV -0x38(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
IMUL $0x38,%R9,%R13	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
ADD %RBX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA (%R9,%R15,1),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD %R10,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%R10,%R10,2),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x40(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	scal (12.5%)
MOV $0x38,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV $0x408ed0,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 403280 <qsort@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0.50	N/A
MOV 0x8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x10(%R14),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x18(%R14),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x20(%R14),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
LEA (%RAX,%R15,4),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
CMP %RDI,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETAEB -0x40(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	N/A
LEA -0x1(%R12),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%R12,4),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $-0x4,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
CMP %RBX,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETAEB -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	1	0.50	N/A
SUB %R15,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
IMUL $0x38,%R8,%R8	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	3	0.33	N/A
LEA (%RBX,%R8,1),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $0x34,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%RCX,%R15,4),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
CMP %R8,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%RCX,%R12,4),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $-0x4,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
CMP %RBX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETBB -0x48(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	N/A
CMP %R8,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETBB -0x2a(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	N/A
CMP %RDI,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETBB -0x29(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	N/A
LEA -0x8(,%R12,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%R9,%R9,2),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%RDX,%R10,1),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $0x10,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA (,%R15,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%R9,%R9,2),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%RSI,%R9,1),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
CMP %R14,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %R13B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD %RSI,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD $0x10,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%RDX,%R9,1),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
CMP %R14,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %R10B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOVZX -0x38(%RBP),%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	N/A
TEST %R14B,-0x40(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	N/A
JNE 408def <sortAtomsInCell+0x70f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
OR -0x48(%RBP),%R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	N/A
JE 408def <sortAtomsInCell+0x70f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
MOVZX -0x29(%RBP),%R11D	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (1.6%)
OR %R11B,-0x2a(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	N/A
JE 408def <sortAtomsInCell+0x70f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
OR %R10B,%R13B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
JE 408def <sortAtomsInCell+0x70f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
MOV %R12,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %R15,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R11,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x10,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
JE 408e4b <sortAtomsInCell+0x76b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
LEA -0x1(%R10),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
VPBROADCASTQ 0x1a8ed(%RIP),%ZMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	5	0.50	scal (12.5%)
VMOVDQU64 0x1a6e3(%RIP),%ZMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVDQU64 0x1a719(%RIP),%ZMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a74f(%RIP),%ZMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a785(%RIP),%ZMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a7bb(%RIP),%ZMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a7f1(%RIP),%ZMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a827(%RIP),%ZMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a85d(%RIP),%ZMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %R10,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
JNE 408e4e <sortAtomsInCell+0x76e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
JMP 408eb9 <sortAtomsInCell+0x7d9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
LEA (%R15,%R15,2),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA 0x2(,%RDI,2),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
JMP 408eb9 <sortAtomsInCell+0x7d9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
LEA (%R10,%R10,2),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%R15,%R15,2),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%R8	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33	N/A
LEA (%R8,%RDI,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD %RDI,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD %RDI,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD %R10,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
IMUL $0x38,%R10,%RDI	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	3	0.33	N/A
ADD %RDI,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
LEA -0x28(%RBP),%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.03% of application time for run icx_0

Source file and lines	haloExchange.c:614-645
Module	exec

The function is defined in /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:614-645.

Warnings:
Ignoring paths for analysis

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 24.88 to 5.63 cycles (4.42x speedup).

Workaround

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

Vectorization

Details

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function 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

CALL instructions

Detected function call instructions.

Details

qsort@plt: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:632
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:632

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.

CMOVG: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:621
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:635

Vector unaligned load/store instructions

Detected 6 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 6 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:639

Workaround

Use vector aligned instructions:

align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Conversion instructions

Detected expensive conversion instructions.

Details

MOVZX: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:621
- /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c:621

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

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

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 777 bytes. The binary function is storing 30 bytes.

General properties

nb instructions	201
nb uops	199
loop length	860
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	5
used zmm registers	9
nb stack references	6

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	24.88 cycles
front end	24.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	22.33	22.33	22.33	22.33	22.33	22.33	11.00	11.00	11.00	11.00	0.00	1.00	1.00	0.00	0.00	0.00
cycles	22.33	22.33	22.33	22.33	22.33	22.33	11.00	11.00	11.00	11.00	0.00	1.00	1.00	0.00	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	24.88
Dispatch	22.33
Overall L1	24.88

Vectorization ratios

INT

all	13%
load	37%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	8%

all	100%
load	100%
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	NA (no other vectorizable/vectorized instructions)

INT+FP

all	29%
load	70%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	8%

Vector efficiency ratios

INT

all	18%
load	37%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	13%

all	83%
load	83%
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	NA (no other vectorizable/vectorized instructions)

INT+FP

all	30%
load	61%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 24.88 cycles. At this rate:

12% of peak load performance is reached (31.24 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (1.21 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 4086e0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P11	P12	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x28,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x78(%RSI),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOVSXD %EDX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOVSXD (%RAX,%RCX,4),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	N/A
MOV %EAX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL $0x38,%RSI,%RCX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	3	0.33	N/A
ADD $0xf,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
AND $-0x10,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RSP,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RCX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
JLE 4088fd <sortAtomsInCell+0x21d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x6,%EDX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33	N/A
MOV 0x8(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x10(%R14),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x18(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x20(%R14),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOVSXD %EDX,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.50	scal (12.5%)
MOVSXD %ESI,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%RDX,%R15,1),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
IMUL $0x38,%RDX,%R8	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	3	0.33	N/A
LEA (%RDI,%RSI,4),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $-0x4,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
CMP %RBX,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETAE %R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%R8,%RBX,1),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $-0x4,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%RDI,%R15,4),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
CMP %RDI,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETAE %R13B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%R10,%R15,4),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
MOV %R9,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.50	scal (12.5%)
CMP %R8,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	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	1	0.17	N/A
LEA (%R10,%RSI,4),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $-0x4,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
CMP %RBX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA 0x1(%R15),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
SETB %R10B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
TEST %R13B,%R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
JNE 408917 <sortAtomsInCell+0x237>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
OR %R10B,%R9B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
JE 408917 <sortAtomsInCell+0x237>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
CMP %R12,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %RSI,%R12	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33	N/A
MOV %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %R15,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
JE 40898e <sortAtomsInCell+0x2ae>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RSI,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.50	scal (12.5%)
LEA -0x1(%R9),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (,%R15,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%RSI,%RSI,2),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VPBROADCASTQ 0x1ac2c(%RIP),%YMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	1	0.50	scal (12.5%)
VMOVDQU 0x1ac44(%RIP),%YMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (50.0%)
MOV $0xf,%SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD 0x1ac59(%RIP),%YMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (50.0%)
VMOVUPD 0x1ac71(%RIP),%YMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (50.0%)
VMOVUPD 0x1ac89(%RIP),%YMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (50.0%)
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %R9,-0x48(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOV -0x38(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
JNE 408995 <sortAtomsInCell+0x2b5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
JMP 408a02 <sortAtomsInCell+0x322>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
MOV $0x38,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV $0x408ed0,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 403280 <qsort@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0.50	N/A
JMP 408eb9 <sortAtomsInCell+0x7d9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
LEA (,%R15,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%R9,%R9,2),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV %RBX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %R12,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %RSI,%R12	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33	N/A
MOV -0x38(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
JMP 408a02 <sortAtomsInCell+0x322>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV -0x38(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
IMUL $0x38,%R9,%R13	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
ADD %RBX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA (%R9,%R15,1),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD %R10,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%R10,%R10,2),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x40(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	scal (12.5%)
MOV $0x38,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV $0x408ed0,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 403280 <qsort@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0.50	N/A
MOV 0x8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x10(%R14),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x18(%R14),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV 0x20(%R14),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
LEA (%RAX,%R15,4),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
CMP %RDI,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETAEB -0x40(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	N/A
LEA -0x1(%R12),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%R12,4),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $-0x4,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
CMP %RBX,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETAEB -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	1	0.50	N/A
SUB %R15,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
IMUL $0x38,%R8,%R8	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	3	0.33	N/A
LEA (%RBX,%R8,1),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $0x34,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%RCX,%R15,4),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
CMP %R8,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%RCX,%R12,4),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $-0x4,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
CMP %RBX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETBB -0x48(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	N/A
CMP %R8,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETBB -0x2a(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	N/A
CMP %RDI,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETBB -0x29(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	N/A
LEA -0x8(,%R12,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%R9,%R9,2),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%RDX,%R10,1),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD $0x10,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA (,%R15,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%R9,%R9,2),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%RSI,%R9,1),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
CMP %R14,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %R13B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD %RSI,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD $0x10,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
LEA (%RDX,%R9,1),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
CMP %R14,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETB %R10B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
MOVZX -0x38(%RBP),%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	N/A
TEST %R14B,-0x40(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	N/A
JNE 408def <sortAtomsInCell+0x70f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
OR -0x48(%RBP),%R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	N/A
JE 408def <sortAtomsInCell+0x70f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
MOVZX -0x29(%RBP),%R11D	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (1.6%)
OR %R11B,-0x2a(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	N/A
JE 408def <sortAtomsInCell+0x70f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
OR %R10B,%R13B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
JE 408def <sortAtomsInCell+0x70f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
MOV %R12,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %R15,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R11,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x10,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
JE 408e4b <sortAtomsInCell+0x76b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
LEA -0x1(%R10),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
VPBROADCASTQ 0x1a8ed(%RIP),%ZMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	5	0.50	scal (12.5%)
VMOVDQU64 0x1a6e3(%RIP),%ZMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVDQU64 0x1a719(%RIP),%ZMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a74f(%RIP),%ZMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a785(%RIP),%ZMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a7bb(%RIP),%ZMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a7f1(%RIP),%ZMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a827(%RIP),%ZMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
VMOVUPD 0x1a85d(%RIP),%ZMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.50	vect (100.0%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %R10,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
JNE 408e4e <sortAtomsInCell+0x76e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
JMP 408eb9 <sortAtomsInCell+0x7d9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
LEA (%R15,%R15,2),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA 0x2(,%RDI,2),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
JMP 408eb9 <sortAtomsInCell+0x7d9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
LEA (%R10,%R10,2),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
LEA (%R15,%R15,2),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%R8	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33	N/A
LEA (%R8,%RDI,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
ADD %RDI,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD %RDI,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD %R10,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
IMUL $0x38,%R10,%RDI	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	3	0.33	N/A
ADD %RDI,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
LEA -0x28(%RBP),%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.25	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼sortAtomsInCell–	1.23	0.34
○Loop 65 - haloExchange.c:621-630 - exec	1.10	0.30
○Loop 64 - haloExchange.c:621-629 - exec	0.04	0.01
○Loop 63 - haloExchange.c:633-642 - exec	0.04	0.01
○Loop 62 - haloExchange.c:633-641 - exec	0.01	0.01
○Loop 60 - haloExchange.c:621-629 - exec	0.00	0.00
○Loop 61 - haloExchange.c:633-641 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

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

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code