OV - exec - Function advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D<double>&, clover::Buffer1D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&) [clone .extracted.27]

	Function: advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D<double>&, clover::Buffer1 ...	Module: exec	Source: advec_cell.cpp:65-110 [...]	Coverage (incl. loops): 3.95% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp: 65 - 110

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

65: #pragma omp parallel for simd collapse(2)

66:     for (int j = (y_min + 1); j < (y_max + 2); j++) {

67:       for (int i = (x_min + 1); i < (x_max + 2 + 2); i++)

68:         ({

69:           int upwind, donor, downwind, dif;

70:           double sigmat, sigma3, sigma4, sigmav, sigmam, diffuw, diffdw, limiter, wind;

71:           if (vol_flux_x(i, j) > 0.0) {

72:             upwind = i - 2;

73:             donor = i - 1;

74:             downwind = i;

75:             dif = donor;

76:           } else {

77:             upwind = std::min(i + 1, x_max + 2);

78:             donor = i;

79:             downwind = i - 1;

80:             dif = upwind;

81:           }

82:           sigmat = std::fabs(vol_flux_x(i, j)) / pre_vol(donor, j);

83:           sigma3 = (1.0 + sigmat) * (vertexdx[i] / vertexdx[dif]);

84:           sigma4 = 2.0 - sigmat;

85:           sigmav = sigmat;

86:           diffuw = density1(donor, j) - density1(upwind, j);

87:           diffdw = density1(downwind, j) - density1(donor, j);

88:           wind = 1.0;

89:           if (diffdw <= 0.0) wind = -1.0;

90:           if (diffuw * diffdw > 0.0) {

91:             limiter = (1.0 - sigmav) * wind *

92:                       std::fmin(std::fmin(std::fabs(diffuw), std::fabs(diffdw)),

93:                                 one_by_six * (sigma3 * std::fabs(diffuw) + sigma4 * std::fabs(diffdw)));

94:           } else {

95:             limiter = 0.0;

96:           }

97:           mass_flux_x(i, j) = vol_flux_x(i, j) * (density1(donor, j) + limiter);

98:           sigmam = std::fabs(mass_flux_x(i, j)) / (density1(donor, j) * pre_vol(donor, j));

99:           diffuw = energy1(donor, j) - energy1(upwind, j);

100:           diffdw = energy1(downwind, j) - energy1(donor, j);

101:           wind = 1.0;

102:           if (diffdw <= 0.0) wind = -1.0;

103:           if (diffuw * diffdw > 0.0) {

104:             limiter = (1.0 - sigmam) * wind *

105:                       std::fmin(std::fmin(std::fabs(diffuw), std::fabs(diffdw)),

106:                                 one_by_six * (sigma3 * std::fabs(diffuw) + sigma4 * std::fabs(diffdw)));

107:           } else {

108:             limiter = 0.0;

109:           }

110:           ener_flux(i, j) = mass_flux_x(i, j) * (energy1(donor, j) + limiter);

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h: 46 - 69

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

46:   T &operator[](size_t i) const { return data[i]; }

[...]

69:   T &operator()(size_t i, size_t j) const { return data[i + j * sizeX]; }

0x420340 PUSH	%RBP

0x420341 MOV	%RSP,%RBP

0x420344 PUSH	%R15

0x420346 PUSH	%R14

0x420348 PUSH	%R13

0x42034a PUSH	%R12

0x42034c PUSH	%RBX

0x42034d SUB	$0x1a8,%RSP

0x420354 MOV	%R8,%R12

0x420357 MOV	0x50(%RBP),%RAX

0x42035b MOV	0x40(%RBP),%R10

0x42035f MOV	0x38(%RBP),%RSI

0x420363 MOV	0x30(%RBP),%R8

0x420367 MOV	%R8,-0x80(%RBP)

0x42036b MOV	0x28(%RBP),%RBX

0x42036f MOV	0x20(%RBP),%R13

0x420373 MOV	0x18(%RBP),%R15

0x420377 MOV	0x10(%RBP),%R14

0x42037b MOVL	$0,-0x60(%RBP)

0x420382 TEST	%RAX,%RAX

0x420385 JS	420ce0

0x42038b MOV	%RCX,-0x40(%RBP)

0x42038f MOV	%R9,-0x38(%RBP)

0x420393 MOV	%RSI,-0x50(%RBP)

0x420397 MOV	%R10,-0x30(%RBP)

0x42039b MOV	%RDX,-0x48(%RBP)

0x42039f MOV	(%RDI),%ESI

0x4203a1 MOVQ	$0,-0x98(%RBP)

0x4203ac MOV	%RAX,-0x90(%RBP)

0x4203b3 MOVQ	$0x1,-0xf0(%RBP)

0x4203be SUB	$0x8,%RSP

0x4203c2 LEA	-0xf0(%RBP),%RAX

0x4203c9 LEA	-0x60(%RBP),%RCX

0x4203cd LEA	-0x98(%RBP),%R8

0x4203d4 LEA	-0x90(%RBP),%R9

0x4203db MOV	$0x4b7610,%EDI

0x4203e0 MOV	%ESI,-0x5c(%RBP)

0x4203e3 MOV	$0x22,%EDX

0x4203e8 PUSH	$0x1

0x4203ea PUSH	$0x1

0x4203ec PUSH	%RAX

0x4203ed CALL	4031f0 <__kmpc_for_static_init_8@plt>

0x4203f2 ADD	$0x20,%RSP

0x4203f6 MOV	-0x98(%RBP),%RCX

0x4203fd MOV	-0x90(%RBP),%RAX

0x420404 CMP	%RAX,%RCX

0x420407 JA	420cfb

0x42040d MOV	%RAX,%RDI

0x420410 MOV	-0x30(%RBP),%RDX

0x420414 MOV	-0x50(%RBP),%RSI

0x420418 SUB	%ESI,%EDX

0x42041a MOV	(%R15),%RAX

0x42041d MOV	%RAX,-0x68(%RBP)

0x420421 MOV	0x10(%R15),%R8

0x420425 MOV	(%R13),%R9

0x420429 MOV	0x10(%R13),%RAX

0x42042d MOV	%RAX,-0x58(%RBP)

0x420431 MOV	-0x40(%RBP),%RAX

0x420435 MOV	0x8(%RAX),%RAX

0x420439 MOV	%RAX,-0x88(%RBP)

0x420440 MOV	(%R12),%R13

0x420444 MOV	0x10(%R12),%R12

0x420449 MOV	(%R14),%R10

0x42044c MOV	0x10(%R14),%RAX

0x420450 MOV	%RAX,-0x40(%RBP)

0x420454 MOV	-0x38(%RBP),%RAX

0x420458 MOV	(%RAX),%R11

0x42045b MOV	0x10(%RAX),%R15

0x42045f MOV	(%RBX),%R14

0x420462 MOV	0x10(%RBX),%RAX

0x420466 MOV	%RAX,-0x38(%RBP)

0x42046a MOV	-0x48(%RBP),%RAX

0x42046e ADD	$0x2,%EAX

0x420471 INC	%RDI

0x420474 MOV	%RDI,-0xe8(%RBP)

0x42047b SUB	%RCX,%RDI

0x42047e MOV	$-0x2,%EBX

0x420483 MOV	%RDI,-0xb8(%RBP)

0x42048a AND	%RDI,%RBX

0x42048d MOV	%RAX,-0x48(%RBP)

0x420491 MOV	%R8,-0xe0(%RBP)

0x420498 MOV	%R9,-0x78(%RBP)

0x42049c MOV	%R13,-0x70(%RBP)

0x4204a0 MOV	%R10,-0xd8(%RBP)

0x4204a7 MOV	%RDX,-0x30(%RBP)

0x4204ab MOV	%R14,-0xd0(%RBP)

0x4204b2 JE	420d19

0x4204b8 MOVD	%EDX,%XMM0

0x4204bc PSHUFD	$0x44,%XMM0,%XMM1

0x4204c1 MOVQ	-0x80(%RBP),%XMM0

0x4204c6 PSHUFD	$0x44,%XMM0,%XMM0

0x4204cb MOVDQA	%XMM0,-0x1a0(%RBP)

0x4204d3 MOVD	%ESI,%XMM0

0x4204d7 PSHUFD	$0x50,%XMM0,%XMM0

0x4204dc MOVDQA	%XMM0,-0x190(%RBP)

0x4204e4 MOV	-0x68(%RBP),%RDX

0x4204e8 MOVQ	%RDX,%XMM0

0x4204ed PSHUFD	$0x44,%XMM0,%XMM2

0x4204f2 MOVD	%EAX,%XMM0

0x4204f6 PSHUFD	$0x50,%XMM0,%XMM0

0x4204fb MOVDQA	%XMM0,-0x170(%RBP)

0x420503 MOVQ	%R9,%XMM0

0x420508 PSHUFD	$0x44,%XMM0,%XMM0

0x42050d MOVDQA	%XMM0,-0x160(%RBP)

0x420515 MOVQ	%R13,%XMM0

0x42051a PSHUFD	$0x44,%XMM0,%XMM0

0x42051f MOVDQA	%XMM0,-0x150(%RBP)

0x420527 MOVQ	%R10,%XMM0

0x42052c PSHUFD	$0x44,%XMM0,%XMM0

0x420531 MOVDQA	%XMM0,-0x140(%RBP)

0x420539 MOVQ	%R11,%XMM0

0x42053e PSHUFD	$0x44,%XMM0,%XMM0

0x420543 MOVDQA	%XMM0,-0x130(%RBP)

0x42054b MOVQ	%R14,%XMM0

0x420550 PSHUFD	$0x44,%XMM0,%XMM0

0x420555 MOVDQA	%XMM0,-0x120(%RBP)

0x42055d MOVQ	%RCX,%XMM0

0x420562 PSHUFD	$0x44,%XMM0,%XMM3

0x420567 PADDQ	0x7aec1(%RIP),%XMM3

0x42056f XOR	%R9D,%R9D

0x420572 MOVQ	%XMM1,-0xc8(%RBP)

0x42057a MOVDQA	%XMM1,-0x1b0(%RBP)

0x420582 PSHUFD	$-0x12,%XMM1,%XMM0

0x420587 MOVQ	%XMM0,-0xc0(%RBP)

0x42058f MOVDQA	%XMM2,-0x180(%RBP)

0x420597 PSRLQ	$0x20,%XMM2

0x42059c MOVDQA	%XMM2,-0x110(%RBP)

0x4205a4 MOVQ	%R8,%XMM0

0x4205a9 PSHUFD	$0x44,%XMM0,%XMM0

0x4205ae MOVDQA	%XMM0,-0x100(%RBP)

0x4205b6 MOVAPD	0x7a531(%RIP),%XMM15

0x4205bf MOVAPD	0x7b018(%RIP),%XMM9

0x4205c8 MOV	%RDX,%R13

0x4205cb MOV	%RBX,%R8

0x4205ce JMP	42071a

0x4205d3 NOPW	%CS:(%RAX,%RAX,1)

(156) 0x4205e0 MULPD	%XMM9,%XMM7

(156) 0x4205e5 DIVPD	%XMM7,%XMM8

(156) 0x4205ea MOVAPD	%XMM12,%XMM7

(156) 0x4205ef XORPD	%XMM3,%XMM3

(156) 0x4205f3 CMPPD	$0x6,%XMM3,%XMM7

(156) 0x4205f8 MOVAPD	0x7afdf(%RIP),%XMM9

(156) 0x420601 MOVAPD	%XMM9,%XMM3

(156) 0x420606 SUBPD	%XMM8,%XMM3

(156) 0x42060b SUBPD	%XMM9,%XMM8

(156) 0x420610 ANDPD	%XMM7,%XMM3

(156) 0x420614 ANDNPD	%XMM8,%XMM7

(156) 0x420619 ORPD	%XMM3,%XMM7

(156) 0x42061d ANDPD	%XMM15,%XMM6

(156) 0x420622 ANDPD	%XMM15,%XMM12

(156) 0x420627 MOVAPD	%XMM12,%XMM3

(156) 0x42062c MINPD	%XMM6,%XMM3

(156) 0x420630 MOVAPD	%XMM6,%XMM4

(156) 0x420634 CMPPD	$0x3,%XMM6,%XMM4

(156) 0x420639 MOVAPD	%XMM12,%XMM8

(156) 0x42063e ANDPD	%XMM4,%XMM8

(156) 0x420643 ANDNPD	%XMM3,%XMM4

(156) 0x420647 ORPD	%XMM8,%XMM4

(156) 0x42064c MULPD	%XMM5,%XMM12

(156) 0x420651 MULPD	%XMM13,%XMM6

(156) 0x420656 ADDPD	%XMM12,%XMM6

(156) 0x42065b MOVAPD	0x7af9d(%RIP),%XMM5

(156) 0x420663 MULPD	%XMM5,%XMM6

(156) 0x420667 MOVAPD	%XMM6,%XMM0

(156) 0x42066b MINPD	%XMM4,%XMM0

(156) 0x42066f CMPPD	$0x3,%XMM4,%XMM4

(156) 0x420674 ANDPD	%XMM4,%XMM6

(156) 0x420678 ANDNPD	%XMM0,%XMM4

(156) 0x42067c ORPD	%XMM6,%XMM4

(156) 0x420680 MULPD	%XMM7,%XMM4

(156) 0x420684 ANDPD	%XMM4,%XMM2

(156) 0x420688 ADDPD	%XMM1,%XMM2

(156) 0x42068c MULPD	%XMM10,%XMM2

(156) 0x420691 MOVDQA	-0x120(%RBP),%XMM3

(156) 0x420699 MOVDQA	%XMM3,%XMM0

(156) 0x42069d PSRLQ	$0x20,%XMM0

(156) 0x4206a2 PMULUDQ	%XMM11,%XMM0

(156) 0x4206a7 MOVDQA	%XMM3,%XMM1

(156) 0x4206ab PMULUDQ	%XMM11,%XMM1

(156) 0x4206b0 PSRLQ	$0x20,%XMM11

(156) 0x4206b6 PMULUDQ	%XMM3,%XMM11

(156) 0x4206bb PADDQ	%XMM0,%XMM11

(156) 0x4206c0 PADDQ	-0xb0(%RBP),%XMM1

(156) 0x4206c8 PSLLQ	$0x20,%XMM11

(156) 0x4206ce PADDQ	%XMM11,%XMM1

(156) 0x4206d3 PSLLQ	$0x3,%XMM1

(156) 0x4206d8 MOVQ	-0x38(%RBP),%XMM0

(156) 0x4206dd PSHUFD	$0x44,%XMM0,%XMM0

(156) 0x4206e2 PADDQ	%XMM1,%XMM0

(156) 0x4206e6 MOVQ	%XMM0,%RAX

(156) 0x4206eb PSHUFD	$-0x12,%XMM0,%XMM0

(156) 0x4206f0 MOVQ	%XMM0,%RDX

(156) 0x4206f5 MOVLPD	%XMM2,(%RAX)

(156) 0x4206f9 MOVHPD	%XMM2,(%RDX)

(156) 0x4206fd MOVDQA	-0x1d0(%RBP),%XMM3

(156) 0x420705 PADDQ	0x7ad43(%RIP),%XMM3

(156) 0x42070d ADD	$0x2,%R9

(156) 0x420711 CMP	%R8,%R9

(156) 0x420714 JAE	420cf2

(156) 0x42071a MOVQ	%XMM3,%RAX

(156) 0x42071f XOR	%EDX,%EDX

(156) 0x420721 DIVQ	-0xc8(%RBP)

(156) 0x420728 MOVQ	%RAX,%XMM0

(156) 0x42072d PSHUFD	$-0x12,%XMM3,%XMM1

(156) 0x420732 MOVQ	%XMM1,%RAX

(156) 0x420737 XOR	%EDX,%EDX

(156) 0x420739 DIVQ	-0xc0(%RBP)

(156) 0x420740 MOVQ	%RAX,%XMM1

(156) 0x420745 PUNPCKLQDQ	%XMM1,%XMM0

(156) 0x420749 MOVDQA	%XMM0,%XMM2

(156) 0x42074d PADDQ	-0x1a0(%RBP),%XMM2

(156) 0x420755 PMULUDQ	-0x1b0(%RBP),%XMM0

(156) 0x42075d MOVDQA	%XMM3,-0x1d0(%RBP)

(156) 0x420765 MOVDQA	%XMM3,%XMM1

(156) 0x420769 PSUBQ	%XMM0,%XMM1

(156) 0x42076d PSHUFD	$-0x18,%XMM1,%XMM14

(156) 0x420773 PADDD	-0x190(%RBP),%XMM14

(156) 0x42077c PXOR	%XMM0,%XMM0

(156) 0x420780 PCMPGTD	%XMM14,%XMM0

(156) 0x420785 MOVDQA	%XMM14,%XMM6

(156) 0x42078a PUNPCKLDQ	%XMM0,%XMM6

(156) 0x42078e PSHUFD	$-0x18,%XMM2,%XMM11

(156) 0x420794 PSLLQ	$0x20,%XMM2

(156) 0x420799 PSRAD	$0x1f,%XMM2

(156) 0x42079e PSHUFD	$-0x13,%XMM2,%XMM0

(156) 0x4207a3 PUNPCKLDQ	%XMM0,%XMM11

(156) 0x4207a8 MOVDQA	-0x180(%RBP),%XMM3

(156) 0x4207b0 MOVDQA	%XMM3,%XMM0

(156) 0x4207b4 PMULUDQ	%XMM11,%XMM0

(156) 0x4207b9 MOVDQA	-0x110(%RBP),%XMM1

(156) 0x4207c1 PMULUDQ	%XMM11,%XMM1

(156) 0x4207c6 PSRLQ	$0x20,%XMM2

(156) 0x4207cb PMULUDQ	%XMM2,%XMM3

(156) 0x4207cf PADDQ	%XMM1,%XMM3

(156) 0x4207d3 PSLLQ	$0x20,%XMM3

(156) 0x4207d8 PADDQ	%XMM6,%XMM0

(156) 0x4207dc PADDQ	%XMM3,%XMM0

(156) 0x4207e0 PSLLQ	$0x3,%XMM0

(156) 0x4207e5 PADDQ	-0x100(%RBP),%XMM0

(156) 0x4207ed MOVQ	%XMM0,%RAX

(156) 0x4207f2 PSHUFD	$-0x12,%XMM0,%XMM0

(156) 0x4207f7 MOVQ	%XMM0,%RDX

(156) 0x4207fc MOVSD	(%RAX),%XMM0

(156) 0x420800 MOVHPD	(%RDX),%XMM0

(156) 0x420804 XORPD	%XMM12,%XMM12

(156) 0x420809 CMPPD	$0x1,%XMM0,%XMM12

(156) 0x42080f MOVAPD	%XMM0,%XMM7

(156) 0x420813 MOVAPD	%XMM0,-0xb0(%RBP)

(156) 0x42081b MOVDQA	%XMM14,%XMM0

(156) 0x420820 PCMPEQD	%XMM3,%XMM3

(156) 0x420824 PADDD	%XMM3,%XMM0

(156) 0x420828 MOVDQA	%XMM14,%XMM1

(156) 0x42082d PSUBD	%XMM3,%XMM1

(156) 0x420831 MOVDQA	%XMM1,%XMM5

(156) 0x420835 MOVDQA	-0x170(%RBP),%XMM3

(156) 0x42083d PCMPGTD	%XMM3,%XMM5

(156) 0x420841 PAND	%XMM5,%XMM3

(156) 0x420845 PANDN	%XMM1,%XMM5

(156) 0x420849 POR	%XMM3,%XMM5

(156) 0x42084d PXOR	%XMM1,%XMM1

(156) 0x420851 PCMPGTD	%XMM0,%XMM1

(156) 0x420855 PUNPCKLDQ	%XMM1,%XMM0

(156) 0x420859 PXOR	%XMM1,%XMM1

(156) 0x42085d PCMPGTD	%XMM5,%XMM1

(156) 0x420861 PUNPCKLDQ	%XMM1,%XMM5

(156) 0x420865 PADDD	0x7ad62(%RIP),%XMM14

(156) 0x42086e PXOR	%XMM1,%XMM1

(156) 0x420872 PCMPGTD	%XMM14,%XMM1

(156) 0x420877 PUNPCKLDQ	%XMM1,%XMM14

(156) 0x42087c MOVAPD	%XMM12,%XMM3

(156) 0x420881 ANDNPD	%XMM5,%XMM3

(156) 0x420885 PAND	%XMM12,%XMM14

(156) 0x42088a POR	%XMM3,%XMM14

(156) 0x42088f MOVDQA	%XMM12,%XMM1

(156) 0x420894 PANDN	%XMM0,%XMM1

(156) 0x420898 PAND	%XMM12,%XMM0

(156) 0x42089d POR	%XMM0,%XMM3

(156) 0x4208a1 MOVDQA	%XMM6,%XMM4

(156) 0x4208a5 PAND	%XMM12,%XMM4

(156) 0x4208aa POR	%XMM1,%XMM4

(156) 0x4208ae MOVDQA	%XMM4,%XMM10

(156) 0x4208b3 MOVDQA	%XMM4,-0x1c0(%RBP)

(156) 0x4208bb PANDN	%XMM6,%XMM12

(156) 0x4208c0 POR	%XMM0,%XMM12

(156) 0x4208c5 MOVAPD	%XMM7,%XMM1

(156) 0x4208c9 ANDPD	%XMM15,%XMM1

(156) 0x4208ce MOVDQA	-0x160(%RBP),%XMM7

(156) 0x4208d6 MOVDQA	%XMM7,%XMM0

(156) 0x4208da PMULUDQ	%XMM11,%XMM0

(156) 0x4208df MOVDQA	%XMM7,%XMM5

(156) 0x4208e3 PSRLQ	$0x20,%XMM5

(156) 0x4208e8 PMULUDQ	%XMM11,%XMM5

(156) 0x4208ed PMULUDQ	%XMM2,%XMM7

(156) 0x4208f1 PADDQ	%XMM5,%XMM7

(156) 0x4208f5 PSLLQ	$0x20,%XMM7

(156) 0x4208fa PADDQ	%XMM0,%XMM7

(156) 0x4208fe PADDQ	%XMM12,%XMM7

(156) 0x420903 PSLLQ	$0x3,%XMM7

(156) 0x420908 MOVQ	-0x58(%RBP),%XMM0

(156) 0x42090d PSHUFD	$0x44,%XMM0,%XMM0

(156) 0x420912 PADDQ	%XMM7,%XMM0

(156) 0x420916 MOVQ	%XMM0,%RDX

(156) 0x42091b PSHUFD	$-0x12,%XMM0,%XMM0

(156) 0x420920 MOVQ	%XMM0,%RAX

(156) 0x420925 MOVSD	(%RDX),%XMM0

(156) 0x420929 MOVHPD	(%RAX),%XMM0

(156) 0x42092d DIVPD	%XMM0,%XMM1

(156) 0x420931 MOVAPD	%XMM1,%XMM5

(156) 0x420935 ADDPD	%XMM9,%XMM5

(156) 0x42093a MOVDQA	%XMM6,%XMM0

(156) 0x42093e PSLLQ	$0x3,%XMM0

(156) 0x420943 MOVQ	-0x88(%RBP),%XMM7

(156) 0x42094b PSHUFD	$0x44,%XMM7,%XMM7

(156) 0x420950 PADDQ	%XMM7,%XMM0

(156) 0x420954 MOVQ	%XMM0,%RSI

(156) 0x420959 PSHUFD	$-0x12,%XMM0,%XMM0

(156) 0x42095e MOVQ	%XMM0,%RDI

(156) 0x420963 MOVSD	(%RSI),%XMM13

(156) 0x420968 MOVHPD	(%RDI),%XMM13

(156) 0x42096d PSLLQ	$0x3,%XMM3

(156) 0x420972 PADDQ	%XMM7,%XMM3

(156) 0x420976 MOVQ	%XMM3,%RSI

(156) 0x42097b PSHUFD	$-0x12,%XMM3,%XMM3

(156) 0x420980 MOVQ	%XMM3,%RDI

(156) 0x420985 MOVSD	(%RSI),%XMM3

(156) 0x420989 MOVHPD	(%RDI),%XMM3

(156) 0x42098d MULPD	%XMM5,%XMM13

(156) 0x420992 DIVPD	%XMM3,%XMM13

(156) 0x420997 MOVDQA	-0x150(%RBP),%XMM3

(156) 0x42099f MOVDQA	%XMM3,%XMM5

(156) 0x4209a3 PMULUDQ	%XMM11,%XMM5

(156) 0x4209a8 MOVDQA	%XMM3,%XMM7

(156) 0x4209ac PSRLQ	$0x20,%XMM7

(156) 0x4209b1 PMULUDQ	%XMM11,%XMM7

(156) 0x4209b6 PMULUDQ	%XMM2,%XMM3

(156) 0x4209ba PADDQ	%XMM7,%XMM3

(156) 0x4209be PSLLQ	$0x20,%XMM3

(156) 0x4209c3 PADDQ	%XMM5,%XMM3

(156) 0x4209c7 MOVDQA	%XMM3,%XMM5

(156) 0x4209cb PADDQ	%XMM12,%XMM5

(156) 0x4209d0 PSLLQ	$0x3,%XMM5

(156) 0x4209d5 MOVQ	%R12,%XMM7

(156) 0x4209da PSHUFD	$0x44,%XMM7,%XMM7

(156) 0x4209df PADDQ	%XMM7,%XMM5

(156) 0x4209e3 MOVQ	%XMM5,%RSI

(156) 0x4209e8 PSHUFD	$-0x12,%XMM5,%XMM5

(156) 0x4209ed MOVQ	%XMM5,%RBX

(156) 0x4209f2 MOVAPD	%XMM15,%XMM4

(156) 0x4209f7 MOVSD	(%RSI),%XMM15

(156) 0x4209fc MOVHPD	(%RBX),%XMM15

(156) 0x420a01 MOVDQA	%XMM3,%XMM5

(156) 0x420a05 PADDQ	%XMM14,%XMM5

(156) 0x420a0a PSLLQ	$0x3,%XMM5

(156) 0x420a0f PADDQ	%XMM7,%XMM5

(156) 0x420a13 MOVQ	%XMM5,%RDI

(156) 0x420a18 PSHUFD	$-0x12,%XMM5,%XMM5

(156) 0x420a1d MOVQ	%XMM5,%R14

(156) 0x420a22 MOVSD	(%RDI),%XMM5

(156) 0x420a26 MOVHPD	(%R14),%XMM5

(156) 0x420a2b MOVAPD	%XMM15,%XMM8

(156) 0x420a30 PADDQ	%XMM10,%XMM3

(156) 0x420a35 PSLLQ	$0x3,%XMM3

(156) 0x420a3a PADDQ	%XMM7,%XMM3

(156) 0x420a3e MOVQ	%XMM3,%RDI

(156) 0x420a43 PSHUFD	$-0x12,%XMM3,%XMM3

(156) 0x420a48 MOVQ	%XMM3,%R14

(156) 0x420a4d MOVSD	(%RDI),%XMM10

(156) 0x420a52 MOVHPD	(%R14),%XMM10

(156) 0x420a57 SUBPD	%XMM5,%XMM8

(156) 0x420a5c SUBPD	%XMM15,%XMM10

(156) 0x420a61 MOVAPD	%XMM10,%XMM5

(156) 0x420a66 MULPD	%XMM8,%XMM5

(156) 0x420a6b MOVAPD	%XMM9,%XMM0

(156) 0x420a70 XORPD	%XMM9,%XMM9

(156) 0x420a75 CMPPD	$0x1,%XMM5,%XMM9

(156) 0x420a7b ANDPD	%XMM4,%XMM8

(156) 0x420a80 MOVAPD	%XMM10,%XMM3

(156) 0x420a85 ANDPD	%XMM4,%XMM3

(156) 0x420a89 MOVAPD	%XMM3,%XMM5

(156) 0x420a8d MINPD	%XMM8,%XMM5

(156) 0x420a92 MOVAPD	%XMM8,%XMM7

(156) 0x420a97 CMPPD	$0x3,%XMM8,%XMM7

(156) 0x420a9d MOVAPD	%XMM3,%XMM4

(156) 0x420aa1 ANDPD	%XMM7,%XMM4

(156) 0x420aa5 ANDNPD	%XMM5,%XMM7

(156) 0x420aa9 ORPD	%XMM4,%XMM7

(156) 0x420aad MOVAPD	0x7ab3b(%RIP),%XMM5

(156) 0x420ab5 SUBPD	%XMM1,%XMM5

(156) 0x420ab9 MULPD	%XMM5,%XMM3

(156) 0x420abd MULPD	%XMM13,%XMM8

(156) 0x420ac2 ADDPD	%XMM3,%XMM8

(156) 0x420ac7 MULPD	0x7ab30(%RIP),%XMM8

(156) 0x420ad0 MOVAPD	%XMM8,%XMM3

(156) 0x420ad5 MINPD	%XMM7,%XMM3

(156) 0x420ad9 CMPPD	$0x3,%XMM7,%XMM7

(156) 0x420ade ANDPD	%XMM7,%XMM8

(156) 0x420ae3 ANDNPD	%XMM3,%XMM7

(156) 0x420ae7 ORPD	%XMM8,%XMM7

(156) 0x420aec CMPPD	$0x6,0x79caa(%RIP),%XMM10

(156) 0x420af6 MOVAPD	%XMM0,%XMM3

(156) 0x420afa SUBPD	%XMM1,%XMM3

(156) 0x420afe SUBPD	%XMM0,%XMM1

(156) 0x420b02 ANDPD	%XMM10,%XMM3

(156) 0x420b07 ANDNPD	%XMM1,%XMM10

(156) 0x420b0c ORPD	%XMM3,%XMM10

(156) 0x420b11 MULPD	%XMM7,%XMM10

(156) 0x420b16 ANDPD	%XMM9,%XMM10

(156) 0x420b1b ADDPD	%XMM15,%XMM10

(156) 0x420b20 MULPD	-0xb0(%RBP),%XMM10

(156) 0x420b29 MOVDQA	-0x140(%RBP),%XMM4

(156) 0x420b31 MOVDQA	%XMM4,%XMM1

(156) 0x420b35 PSRLQ	$0x20,%XMM1

(156) 0x420b3a PMULUDQ	%XMM11,%XMM1

(156) 0x420b3f MOVDQA	%XMM4,%XMM3

(156) 0x420b43 PMULUDQ	%XMM2,%XMM3

(156) 0x420b47 PADDQ	%XMM1,%XMM3

(156) 0x420b4b MOVDQA	%XMM4,%XMM1

(156) 0x420b4f PMULUDQ	%XMM11,%XMM1

(156) 0x420b54 PSLLQ	$0x20,%XMM3

(156) 0x420b59 MOVDQA	%XMM6,-0xb0(%RBP)

(156) 0x420b61 PADDQ	%XMM6,%XMM1

(156) 0x420b65 PADDQ	%XMM3,%XMM1

(156) 0x420b69 PSLLQ	$0x3,%XMM1

(156) 0x420b6e MOVQ	-0x40(%RBP),%XMM3

(156) 0x420b73 PSHUFD	$0x44,%XMM3,%XMM3

(156) 0x420b78 PADDQ	%XMM1,%XMM3

(156) 0x420b7c MOVQ	%XMM3,%RDI

(156) 0x420b81 MOVLPD	%XMM10,(%RDI)

(156) 0x420b86 PSHUFD	$-0x12,%XMM3,%XMM1

(156) 0x420b8b MOVQ	%XMM1,%RDI

(156) 0x420b90 MOVHPD	%XMM10,(%RDI)

(156) 0x420b95 MOVDQA	-0x130(%RBP),%XMM3

(156) 0x420b9d MOVDQA	%XMM3,%XMM1

(156) 0x420ba1 PSRLQ	$0x20,%XMM1

(156) 0x420ba6 PMULUDQ	%XMM11,%XMM1

(156) 0x420bab PMULUDQ	%XMM3,%XMM2

(156) 0x420baf PADDQ	%XMM1,%XMM2

(156) 0x420bb3 MOVDQA	%XMM3,%XMM1

(156) 0x420bb7 PMULUDQ	%XMM11,%XMM1

(156) 0x420bbc PSLLQ	$0x20,%XMM2

(156) 0x420bc1 PADDQ	%XMM1,%XMM2

(156) 0x420bc5 PADDQ	%XMM2,%XMM12

(156) 0x420bca PSLLQ	$0x3,%XMM12

(156) 0x420bd0 MOVQ	%R15,%XMM1

(156) 0x420bd5 PSHUFD	$0x44,%XMM1,%XMM3

(156) 0x420bda PADDQ	%XMM3,%XMM12

(156) 0x420bdf MOVQ	%XMM12,%RDI

(156) 0x420be4 PSHUFD	$-0x12,%XMM12,%XMM1

(156) 0x420bea MOVQ	%XMM1,%R14

(156) 0x420bef MOVSD	(%RDI),%XMM1

(156) 0x420bf3 MOVHPD	(%R14),%XMM1

(156) 0x420bf8 PADDQ	%XMM2,%XMM14

(156) 0x420bfd PSLLQ	$0x3,%XMM14

(156) 0x420c03 PADDQ	%XMM3,%XMM14

(156) 0x420c08 MOVQ	%XMM14,%RDI

(156) 0x420c0d PSHUFD	$-0x12,%XMM14,%XMM4

(156) 0x420c13 MOVQ	%XMM4,%R14

(156) 0x420c18 MOVSD	(%RDI),%XMM4

(156) 0x420c1c MOVHPD	(%R14),%XMM4

(156) 0x420c21 PADDQ	-0x1c0(%RBP),%XMM2

(156) 0x420c29 MOVAPD	%XMM1,%XMM6

(156) 0x420c2d PSLLQ	$0x3,%XMM2

(156) 0x420c32 PADDQ	%XMM3,%XMM2

(156) 0x420c36 MOVQ	%XMM2,%RDI

(156) 0x420c3b PSHUFD	$-0x12,%XMM2,%XMM2

(156) 0x420c40 MOVQ	%XMM2,%R14

(156) 0x420c45 MOVSD	(%RDI),%XMM12

(156) 0x420c4a MOVHPD	(%R14),%XMM12

(156) 0x420c4f SUBPD	%XMM4,%XMM6

(156) 0x420c53 SUBPD	%XMM1,%XMM12

(156) 0x420c58 MOVAPD	%XMM12,%XMM3

(156) 0x420c5d MULPD	%XMM6,%XMM3

(156) 0x420c61 PXOR	%XMM2,%XMM2

(156) 0x420c65 CMPPD	$0x1,%XMM3,%XMM2

(156) 0x420c6a MOVMSKPD	%XMM2,%EDI

(156) 0x420c6e TEST	$0x1,%DIL

(156) 0x420c72 JNE	420ca0

(156) 0x420c74 TEST	$0x2,%DIL

(156) 0x420c78 JNE	420caa

(156) 0x420c7a MOVAPD	0x79e6d(%RIP),%XMM15

(156) 0x420c83 TEST	$0x1,%DIL

(156) 0x420c87 JNE	420cbd

(156) 0x420c89 MOVAPD	%XMM10,%XMM8

(156) 0x420c8e ANDPD	%XMM15,%XMM8

(156) 0x420c93 TEST	$0x2,%DIL

(156) 0x420c97 JE	4205e0

(156) 0x420c9d JMP	420cd6

0x420c9f NOP

(156) 0x420ca0 MOVSD	(%RDX),%XMM7

(156) 0x420ca4 TEST	$0x2,%DIL

(156) 0x420ca8 JE	420c7a

(156) 0x420caa MOVHPD	(%RAX),%XMM7

(156) 0x420cae MOVAPD	0x79e39(%RIP),%XMM15

(156) 0x420cb7 TEST	$0x1,%DIL

(156) 0x420cbb JE	420c89

(156) 0x420cbd MOVSD	(%RSI),%XMM9

(156) 0x420cc2 MOVAPD	%XMM10,%XMM8

(156) 0x420cc7 ANDPD	%XMM15,%XMM8

(156) 0x420ccc TEST	$0x2,%DIL

(156) 0x420cd0 JE	4205e0

(156) 0x420cd6 MOVHPD	(%RBX),%XMM9

(156) 0x420cdb JMP	4205e0

0x420ce0 ADD	$0x1a8,%RSP

0x420ce7 POP	%RBX

0x420ce8 POP	%R12

0x420cea POP	%R13

0x420cec POP	%R14

0x420cee POP	%R15

0x420cf0 POP	%RBP

0x420cf1 RET

0x420cf2 CMP	%R8,-0xb8(%RBP)

0x420cf9 JNE	420d1f

0x420cfb MOV	$0x4b7630,%EDI

0x420d00 MOV	-0x5c(%RBP),%ESI

0x420d03 ADD	$0x1a8,%RSP

0x420d0a POP	%RBX

0x420d0b POP	%R12

0x420d0d POP	%R13

0x420d0f POP	%R14

0x420d11 POP	%R15

0x420d13 POP	%RBP

0x420d14 JMP	403050

0x420d19 MOV	-0x68(%RBP),%R13

0x420d1d JMP	420d22

0x420d1f ADD	%R8,%RCX

0x420d22 PXOR	%XMM0,%XMM0

0x420d26 MOVSD	0x79d6a(%RIP),%XMM2

0x420d2e MOVSD	0x7a8ea(%RIP),%XMM3

0x420d36 MOVAPD	0x79db2(%RIP),%XMM5

0x420d3e MOVSD	0x7a8e2(%RIP),%XMM6

0x420d46 MOV	%R13,%R10

0x420d49 JMP	420d82

0x420d4b NOPL	(%RAX,%RAX,1)

(155) 0x420d50 ADDSD	%XMM9,%XMM11

(155) 0x420d55 MULSD	%XMM10,%XMM11

(155) 0x420d5a IMUL	-0xd0(%RBP),%RAX

(155) 0x420d62 ADD	%RSI,%RAX

(155) 0x420d65 MOV	-0x38(%RBP),%RDX

(155) 0x420d69 MOVSD	%XMM11,(%RDX,%RAX,8)

(155) 0x420d6f INC	%RCX

(155) 0x420d72 CMP	%RCX,-0xe8(%RBP)

(155) 0x420d79 MOV	%R10,%R13

(155) 0x420d7c JE	420cfb

(155) 0x420d82 MOV	%RCX,%RAX

(155) 0x420d85 SHR	$0x20,%RAX

(155) 0x420d89 JE	420da0

(155) 0x420d8b MOV	%RCX,%RAX

(155) 0x420d8e XOR	%EDX,%EDX

(155) 0x420d90 DIVQ	-0x30(%RBP)

(155) 0x420d94 JMP	420da7

0x420d96 NOPW	%CS:(%RAX,%RAX,1)

(155) 0x420da0 MOV	%ECX,%EAX

(155) 0x420da2 XOR	%EDX,%EDX

(155) 0x420da4 DIVL	-0x30(%RBP)

(155) 0x420da7 MOV	-0x50(%RBP),%R8

(155) 0x420dab ADD	-0x80(%RBP),%EAX

(155) 0x420dae LEA	(%RDX,%R8,1),%R9D

(155) 0x420db2 MOVSXD	%R9D,%RSI

(155) 0x420db5 CLTQ

(155) 0x420db7 MOV	%R13,%RDI

(155) 0x420dba IMUL	%RAX,%RDI

(155) 0x420dbe ADD	%RSI,%RDI

(155) 0x420dc1 MOV	-0xe0(%RBP),%RBX

(155) 0x420dc8 MOVSD	(%RBX,%RDI,8),%XMM9

(155) 0x420dce UCOMISD	%XMM0,%XMM9

(155) 0x420dd3 LEA	-0x1(%RDX,%R8,1),%EDX

(155) 0x420dd8 JBE	420df0

(155) 0x420dda ADD	$-0x2,%R9D

(155) 0x420dde MOVSXD	%EDX,%RDI

(155) 0x420de1 MOVSXD	%R9D,%RDX

(155) 0x420de4 MOV	%RSI,%R8

(155) 0x420de7 MOV	%RDI,%RBX

(155) 0x420dea JMP	420e0a

0x420dec NOPL	(%RAX)

(155) 0x420df0 INC	%R9D

(155) 0x420df3 MOV	-0x48(%RBP),%RDI

(155) 0x420df7 CMP	%R9D,%EDI

(155) 0x420dfa CMOVL	%EDI,%R9D

(155) 0x420dfe MOVSXD	%EDX,%R8

(155) 0x420e01 MOVSXD	%R9D,%RDX

(155) 0x420e04 MOV	%RDX,%RDI

(155) 0x420e07 MOV	%RSI,%RBX

(155) 0x420e0a MOV	-0x78(%RBP),%R9

(155) 0x420e0e MOV	-0x70(%RBP),%R13

(155) 0x420e12 MOVAPD	%XMM9,%XMM1

(155) 0x420e17 ANDPD	0x79cd1(%RIP),%XMM1

(155) 0x420e1f IMUL	%RAX,%R9

(155) 0x420e23 ADD	%RBX,%R9

(155) 0x420e26 MOV	-0x58(%RBP),%R14

(155) 0x420e2a DIVSD	(%R14,%R9,8),%XMM1

(155) 0x420e30 MOVAPD	%XMM1,%XMM7

(155) 0x420e34 ADDSD	%XMM2,%XMM7

(155) 0x420e38 MOV	-0x88(%RBP),%R14

(155) 0x420e3f MULSD	(%R14,%RSI,8),%XMM7

(155) 0x420e45 DIVSD	(%R14,%RDI,8),%XMM7

(155) 0x420e4b MOV	%R13,%R14

(155) 0x420e4e IMUL	%RAX,%R14

(155) 0x420e52 LEA	(%R14,%RBX,1),%RDI

(155) 0x420e56 MOVSD	(%R12,%RDI,8),%XMM12

(155) 0x420e5c LEA	(%R14,%RDX,1),%R13

(155) 0x420e60 MOVAPD	%XMM12,%XMM14

(155) 0x420e65 SUBSD	(%R12,%R13,8),%XMM14

(155) 0x420e6b ADD	%R8,%R14

(155) 0x420e6e MOVSD	(%R12,%R14,8),%XMM15

(155) 0x420e74 MOVAPD	%XMM3,%XMM8

(155) 0x420e79 SUBSD	%XMM1,%XMM8

(155) 0x420e7e SUBSD	%XMM12,%XMM15

(155) 0x420e83 MOVAPD	%XMM15,%XMM10

(155) 0x420e88 MULSD	%XMM14,%XMM10

(155) 0x420e8d PXOR	%XMM11,%XMM11

(155) 0x420e92 UCOMISD	%XMM11,%XMM10

(155) 0x420e97 XORPD	%XMM10,%XMM10

(155) 0x420e9c JBE	420f43

(155) 0x420ea2 MOVAPD	%XMM2,%XMM10

(155) 0x420ea7 SUBSD	%XMM1,%XMM10

(155) 0x420eac MOVAPD	%XMM15,%XMM1

(155) 0x420eb1 CMPSD	$0x6,%XMM0,%XMM1

(155) 0x420eb6 MOVAPD	%XMM1,%XMM13

(155) 0x420ebb ANDPD	%XMM10,%XMM13

(155) 0x420ec0 XORPD	0x7a747(%RIP),%XMM10

(155) 0x420ec9 ANDNPD	%XMM10,%XMM1

(155) 0x420ece ORPD	%XMM13,%XMM1

(155) 0x420ed3 ANDPD	%XMM5,%XMM14

(155) 0x420ed8 ANDPD	%XMM5,%XMM15

(155) 0x420edd MOVAPD	%XMM14,%XMM10

(155) 0x420ee2 CMPSD	$0x3,%XMM14,%XMM10

(155) 0x420ee8 MOVAPD	%XMM10,%XMM4

(155) 0x420eed ANDPD	%XMM15,%XMM4

(155) 0x420ef2 MOVAPD	%XMM15,%XMM13

(155) 0x420ef7 MINSD	%XMM14,%XMM13

(155) 0x420efc ANDNPD	%XMM13,%XMM10

(155) 0x420f01 ORPD	%XMM4,%XMM10

(155) 0x420f06 MULSD	%XMM7,%XMM14

(155) 0x420f0b MULSD	%XMM8,%XMM15

(155) 0x420f10 ADDSD	%XMM14,%XMM15

(155) 0x420f15 MULSD	%XMM6,%XMM15

(155) 0x420f1a MOVAPD	%XMM15,%XMM4

(155) 0x420f1f MINSD	%XMM10,%XMM4

(155) 0x420f24 CMPSD	$0x3,%XMM10,%XMM10

(155) 0x420f2a MOVAPD	%XMM10,%XMM13

(155) 0x420f2f ANDNPD	%XMM4,%XMM13

(155) 0x420f34 ANDPD	%XMM15,%XMM10

(155) 0x420f39 ORPD	%XMM13,%XMM10

(155) 0x420f3e MULSD	%XMM1,%XMM10

(155) 0x420f43 ADDSD	%XMM12,%XMM10

(155) 0x420f48 MULSD	%XMM9,%XMM10

(155) 0x420f4d MOV	-0xd8(%RBP),%R14

(155) 0x420f54 IMUL	%RAX,%R14

(155) 0x420f58 ADD	%RSI,%R14

(155) 0x420f5b MOV	-0x40(%RBP),%R13

(155) 0x420f5f MOVSD	%XMM10,(%R13,%R14,8)

(155) 0x420f66 MOV	%R11,%R14

(155) 0x420f69 IMUL	%RAX,%R14

(155) 0x420f6d ADD	%R14,%RBX

(155) 0x420f70 MOVSD	(%R15,%RBX,8),%XMM9

(155) 0x420f76 ADD	%R14,%RDX

(155) 0x420f79 MOVAPD	%XMM9,%XMM13

(155) 0x420f7e SUBSD	(%R15,%RDX,8),%XMM13

(155) 0x420f84 ADD	%R8,%R14

(155) 0x420f87 MOVSD	(%R15,%R14,8),%XMM12

(155) 0x420f8d SUBSD	%XMM9,%XMM12

(155) 0x420f92 MOVAPD	%XMM12,%XMM1

(155) 0x420f97 MULSD	%XMM13,%XMM1

(155) 0x420f9c UCOMISD	%XMM11,%XMM1

(155) 0x420fa1 JBE	420d50

(155) 0x420fa7 MOVAPD	%XMM10,%XMM1

(155) 0x420fac ANDPD	%XMM5,%XMM1

(155) 0x420fb0 MOV	-0x58(%RBP),%RDX

(155) 0x420fb4 MOVSD	(%RDX,%R9,8),%XMM4

(155) 0x420fba MULSD	(%R12,%RDI,8),%XMM4

(155) 0x420fc0 DIVSD	%XMM4,%XMM1

(155) 0x420fc4 MOVAPD	%XMM2,%XMM4

(155) 0x420fc8 SUBSD	%XMM1,%XMM4

(155) 0x420fcc MOVAPD	%XMM12,%XMM14

(155) 0x420fd1 CMPSD	$0x6,%XMM0,%XMM14

(155) 0x420fd7 MOVAPD	%XMM14,%XMM1

(155) 0x420fdc ANDPD	%XMM4,%XMM1

(155) 0x420fe0 XORPD	0x7a628(%RIP),%XMM4

(155) 0x420fe8 ANDNPD	%XMM4,%XMM14

(155) 0x420fed ORPD	%XMM1,%XMM14

(155) 0x420ff2 ANDPD	%XMM5,%XMM13

(155) 0x420ff7 ANDPD	%XMM5,%XMM12

(155) 0x420ffc MOVAPD	%XMM13,%XMM11

(155) 0x421001 CMPSD	$0x3,%XMM13,%XMM11

(155) 0x421007 MOVAPD	%XMM11,%XMM1

(155) 0x42100c ANDPD	%XMM12,%XMM1

(155) 0x421011 MOVAPD	%XMM12,%XMM4

(155) 0x421016 MINSD	%XMM13,%XMM4

(155) 0x42101b ANDNPD	%XMM4,%XMM11

(155) 0x421020 ORPD	%XMM1,%XMM11

(155) 0x421025 MULSD	%XMM7,%XMM13

(155) 0x42102a MULSD	%XMM8,%XMM12

(155) 0x42102f ADDSD	%XMM13,%XMM12

(155) 0x421034 MULSD	%XMM6,%XMM12

(155) 0x421039 MOVAPD	%XMM12,%XMM1

(155) 0x42103e MINSD	%XMM11,%XMM1

(155) 0x421043 CMPSD	$0x3,%XMM11,%XMM11

(155) 0x421049 MOVAPD	%XMM11,%XMM4

(155) 0x42104e ANDNPD	%XMM1,%XMM4

(155) 0x421052 ANDPD	%XMM12,%XMM11

(155) 0x421057 ORPD	%XMM4,%XMM11

(155) 0x42105c MULSD	%XMM14,%XMM11

(155) 0x421061 JMP	420d50

0x421066 NOPW	%CS:(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
►99.99+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so

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 0.00% of application time for run orig_0

Source file and lines	advec_cell.cpp:65-110
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:65-110
/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:46,69

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 28.67 to 12.00 cycles (2.39x speedup).

Workaround

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

Vectorization

Your function is poorly vectorized. Only 15% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your function, you can lower the cost of an iteration from 28.67 to 3.37 cycles (8.49x speedup).

Details

32% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

21% of SSE/AVX loads are used in vector version.
30% of SSE/AVX stores are used in vector version.
14% of SSE/AVX addition or subtraction instructions are used in vector version.
46% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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.

__kmpc_for_static_init_8@plt: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:65

Type of elements and instruction set

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 352 bytes. The binary function is storing 400 bytes.

General properties

nb instructions	171
nb uops	172
loop length	809
used x86 registers	16
used mmx registers	0
used xmm registers	8
used ymm registers	0
used zmm registers	0
nb stack references	43

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	28.67 cycles
front end	28.67 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	7.40	12.00	18.00	18.00	24.50	12.00	7.40	24.50	24.50	24.50	7.20	18.00
cycles	7.40	12.00	18.00	18.00	24.50	12.00	7.40	24.50	24.50	24.50	7.20	18.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	28.67
Dispatch	24.50
Overall L1	28.67

Vectorization ratios

INT

all	31%
load	7%
store	30%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	14%
fma	NA (no fma vectorizable/vectorized instructions)
other	46%

all	50%
load	50%
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	32%
load	21%
store	30%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	14%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	46%

Vector efficiency ratios

INT

all	15%
load	12%
store	15%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	13%
fma	NA (no fma vectorizable/vectorized instructions)
other	17%

all	18%
load	18%
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	15%
load	14%
store	15%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	13%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	17%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 28.67 cycles. At this rate:

6% of peak load performance is reached (12.28 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (13.95 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 28.67 to 24.50 cycles (1.17x speedup).

ASM code

In the binary file, the address of the function is: 420340

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
SUB $0x1a8,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV %R8,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x50(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x40(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x38(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x30(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R8,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x28(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x20(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RBP),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVL $0,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
TEST %RAX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JS 420ce0 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9a0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RCX,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R9,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R10,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOVQ $0,-0x98(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVQ $0x1,-0xf0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA -0xf0(%RBP),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x60(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x98(%RBP),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x90(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x4b7610,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %ESI,-0x5c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL 4031f0 <__kmpc_for_static_init_8@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x98(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x90(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RAX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JA 420cfb <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9bb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x30(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x50(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
SUB %ESI,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV (%R15),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x10(%R15),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R13),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%R13),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x40(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%R12),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%R12),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R14),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%R14),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x38(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RAX),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%RAX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RBX),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RBX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
INC %RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDI,-0xe8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SUB %RCX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $-0x2,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RDI,-0xb8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
AND %RDI,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R8,-0xe0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R9,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R13,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R10,-0xd8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R14,-0xd0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JE 420d19 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9d9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVD %EDX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
PSHUFD $0x44,%XMM0,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ -0x80(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x1a0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVD %ESI,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
PSHUFD $0x50,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x190(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOV -0x68(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVQ %RDX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVD %EAX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
PSHUFD $0x50,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x170(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R9,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x160(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R13,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x150(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R10,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x140(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R11,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x130(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R14,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x120(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %RCX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ 0x7aec1(%RIP),%XMM3	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
MOVQ %XMM1,-0xc8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVDQA %XMM1,-0x1b0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PSHUFD $-0x12,%XMM1,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,-0xc0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVDQA %XMM2,-0x180(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PSRLQ $0x20,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVDQA %XMM2,-0x110(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R8,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x100(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVAPD 0x7a531(%RIP),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVAPD 0x7b018(%RIP),%XMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOV %RDX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 42071a <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x3da>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD $0x1a8,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
CMP %R8,-0xb8(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JNE 420d1f <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9df>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x4b7630,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x5c(%RBP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
ADD $0x1a8,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
JMP 403050 <__kmpc_for_static_fini@plt>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV -0x68(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JMP 420d22 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9e2>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
ADD %R8,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
PXOR %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVSD 0x79d6a(%RIP),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVSD 0x7a8ea(%RIP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVAPD 0x79db2(%RIP),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVSD 0x7a8e2(%RIP),%XMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R13,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JMP 420d82 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0xa42>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run orig_0

Source file and lines	advec_cell.cpp:65-110
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:65-110
/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:46,69

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Workaround

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

Vectorization

Details

32% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

21% of SSE/AVX loads are used in vector version.
30% of SSE/AVX stores are used in vector version.
14% of SSE/AVX addition or subtraction instructions are used in vector version.
46% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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

__kmpc_for_static_init_8@plt: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:65

Type of elements and instruction set

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 352 bytes. The binary function is storing 400 bytes.

General properties

nb instructions	171
nb uops	172
loop length	809
used x86 registers	16
used mmx registers	0
used xmm registers	8
used ymm registers	0
used zmm registers	0
nb stack references	43

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	28.67 cycles
front end	28.67 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	7.40	12.00	18.00	18.00	24.50	12.00	7.40	24.50	24.50	24.50	7.20	18.00
cycles	7.40	12.00	18.00	18.00	24.50	12.00	7.40	24.50	24.50	24.50	7.20	18.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	28.67
Dispatch	24.50
Overall L1	28.67

Vectorization ratios

INT

all	31%
load	7%
store	30%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	14%
fma	NA (no fma vectorizable/vectorized instructions)
other	46%

all	50%
load	50%
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	32%
load	21%
store	30%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	14%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	46%

Vector efficiency ratios

INT

all	15%
load	12%
store	15%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	13%
fma	NA (no fma vectorizable/vectorized instructions)
other	17%

all	18%
load	18%
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	15%
load	14%
store	15%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	13%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	17%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 28.67 cycles. At this rate:

6% of peak load performance is reached (12.28 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (13.95 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: 420340

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
SUB $0x1a8,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV %R8,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x50(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x40(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x38(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x30(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R8,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x28(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x20(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RBP),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVL $0,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
TEST %RAX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JS 420ce0 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9a0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RCX,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R9,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R10,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOVQ $0,-0x98(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVQ $0x1,-0xf0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA -0xf0(%RBP),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x60(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x98(%RBP),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x90(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x4b7610,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %ESI,-0x5c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL 4031f0 <__kmpc_for_static_init_8@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x98(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x90(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RAX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JA 420cfb <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9bb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x30(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x50(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
SUB %ESI,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV (%R15),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x10(%R15),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R13),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%R13),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x40(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%R12),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%R12),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R14),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%R14),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x38(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RAX),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%RAX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RBX),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RBX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
INC %RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDI,-0xe8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SUB %RCX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $-0x2,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RDI,-0xb8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
AND %RDI,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R8,-0xe0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R9,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R13,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R10,-0xd8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R14,-0xd0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JE 420d19 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9d9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVD %EDX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
PSHUFD $0x44,%XMM0,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ -0x80(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x1a0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVD %ESI,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
PSHUFD $0x50,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x190(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOV -0x68(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVQ %RDX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVD %EAX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
PSHUFD $0x50,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x170(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R9,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x160(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R13,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x150(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R10,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x140(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R11,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x130(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R14,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x120(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %RCX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ 0x7aec1(%RIP),%XMM3	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
MOVQ %XMM1,-0xc8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVDQA %XMM1,-0x1b0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PSHUFD $-0x12,%XMM1,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,-0xc0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVDQA %XMM2,-0x180(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PSRLQ $0x20,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVDQA %XMM2,-0x110(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R8,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x100(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVAPD 0x7a531(%RIP),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVAPD 0x7b018(%RIP),%XMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOV %RDX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 42071a <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x3da>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD $0x1a8,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
CMP %R8,-0xb8(%RBP)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JNE 420d1f <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9df>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x4b7630,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x5c(%RBP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
ADD $0x1a8,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
JMP 403050 <__kmpc_for_static_fini@plt>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV -0x68(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JMP 420d22 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9e2>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
ADD %R8,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
PXOR %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVSD 0x79d6a(%RIP),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVSD 0x7a8ea(%RIP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVAPD 0x79db2(%RIP),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVSD 0x7a8e2(%RIP),%XMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R13,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JMP 420d82 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0xa42>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D&, clover::Buffer1D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D–	3.95	1.56
○Loop 156 - advec_cell.cpp:66-110 - exec	3.95	1.56
○Loop 155 - advec_cell.cpp:66-110 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

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

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