OV - exec - Function void miniqmcreference::MultiBsplineEvalRef::evaluate_v<double>(qmcplusplus::bspline_traits<double, 3u>::SplineType const*, double, double, double, double*, unsigned long)

	Function: void miniqmcreference::MultiBsplineEvalRef::evaluate_v<double>(qmcplusplus::bspline_traits ...	Module: exec	Source: MultiBsplineRef.hpp:41-73 [...]	Coverage (incl. loops): 25.43% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp: 41 - 73

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

41: {

42:   x -= spline_m->x_grid.start;

43:   y -= spline_m->y_grid.start;

44:   z -= spline_m->z_grid.start;

45:   T tx, ty, tz;

46:   int ix, iy, iz;

47:   spline2::getSplineBound(x * spline_m->x_grid.delta_inv, tx, ix, spline_m->x_grid.num - 1);

48:   spline2::getSplineBound(y * spline_m->y_grid.delta_inv, ty, iy, spline_m->y_grid.num - 1);

49:   spline2::getSplineBound(z * spline_m->z_grid.delta_inv, tz, iz, spline_m->z_grid.num - 1);

[...]

57:   const intptr_t ys = spline_m->y_stride;

[...]

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

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

65:     {

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

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

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

69:         vals[n] += pre00 *

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

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

72:     }

73: }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h: 923 - 924

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

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

924: 	*__first = __tmp;

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp: 53 - 63

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

53:   if (x < 0)

[...]

60:     ind = static_cast<int>(x);

61:     dx = x - ind;

62:     // upper bound

63:     if (ind > nmax)

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineData.hpp: 54 - 57

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

54:     a[0] = ((A00 * tx + A01) * tx + A02) * tx + A03;

55:     a[1] = ((A10 * tx + A11) * tx + A12) * tx + A13;

56:     a[2] = ((A20 * tx + A21) * tx + A22) * tx + A23;

57:     a[3] = ((A30 * tx + A31) * tx + A32) * tx + A33;

0x253330 PUSH	%RBP

0x253331 MOV	%RSP,%RBP

0x253334 PUSH	%R15

0x253336 PUSH	%R14

0x253338 PUSH	%R13

0x25333a PUSH	%R12

0x25333c PUSH	%RBX

0x25333d SUB	$0xf8,%RSP

0x253344 VSUBSD	0x28(%RDI),%XMM0,%XMM0

0x253349 VSUBSD	0x50(%RDI),%XMM1,%XMM3

0x25334e MOV	%RDX,-0x30(%RBP)

0x253352 MOV	%RSI,%R14

0x253355 VMULSD	0x48(%RDI),%XMM0,%XMM1

0x25335a VXORPD	%XMM0,%XMM0,%XMM0

0x25335e VUCOMISD	%XMM0,%XMM1

0x253362 JAE	2533ff

0x253368 XOR	%EBX,%EBX

0x25336a VXORPD	%XMM1,%XMM1,%XMM1

0x25336e VMULSD	0x70(%RDI),%XMM3,%XMM3

0x253373 VSUBSD	0x78(%RDI),%XMM2,%XMM2

0x253378 VUCOMISD	%XMM0,%XMM3

0x25337c JB	253444

0x253382 VROUNDSD	$0xb,%XMM3,%XMM3,%XMM0

0x253388 MOV	0x60(%RDI),%EAX

0x25338b VCVTTSD2SI	%XMM3,%EDX

0x25338f VSUBSD	%XMM0,%XMM3,%XMM3

0x253393 VMOVSD	-0x4f293(%RIP),%XMM0

0x25339b CMP	%EDX,%EAX

0x25339d LEA	-0x1(%RAX),%ECX

0x2533a0 SETG	%AL

0x2533a3 CMOVG	%EDX,%ECX

0x2533a6 KMOVD	%EAX,%K1

0x2533aa MOVSXD	%ECX,%R13

0x2533ad VMOVSD	%XMM3,%XMM0,%XMM0{%K1}

0x2533b3 VMULSD	0x98(%RDI),%XMM2,%XMM3

0x2533bb VXORPD	%XMM2,%XMM2,%XMM2

0x2533bf VUCOMISD	%XMM2,%XMM3

0x2533c3 JB	25345d

0x2533c9 VROUNDSD	$0xb,%XMM3,%XMM3,%XMM2

0x2533cf MOV	0x88(%RDI),%EAX

0x2533d5 VCVTTSD2SI	%XMM3,%EDX

0x2533d9 VSUBSD	%XMM2,%XMM3,%XMM3

0x2533dd VMOVSD	-0x4f2dd(%RIP),%XMM2

0x2533e5 CMP	%EDX,%EAX

0x2533e7 LEA	-0x1(%RAX),%ECX

0x2533ea SETG	%AL

0x2533ed CMOVG	%EDX,%ECX

0x2533f0 KMOVD	%EAX,%K1

0x2533f4 MOVSXD	%ECX,%RAX

0x2533f7 VMOVSD	%XMM3,%XMM2,%XMM2{%K1}

0x2533fd JMP	25345f

0x2533ff VROUNDSD	$0xb,%XMM1,%XMM1,%XMM4

0x253405 MOV	0x38(%RDI),%EAX

0x253408 VCVTTSD2SI	%XMM1,%EDX

0x25340c VSUBSD	%XMM4,%XMM1,%XMM4

0x253410 VMOVSD	-0x4f310(%RIP),%XMM1

0x253418 CMP	%EDX,%EAX

0x25341a LEA	-0x1(%RAX),%ECX

0x25341d SETG	%AL

0x253420 CMOVG	%EDX,%ECX

0x253423 KMOVD	%EAX,%K1

0x253427 MOVSXD	%ECX,%RBX

0x25342a VMOVSD	%XMM4,%XMM1,%XMM1{%K1}

0x253430 VMULSD	0x70(%RDI),%XMM3,%XMM3

0x253435 VSUBSD	0x78(%RDI),%XMM2,%XMM2

0x25343a VUCOMISD	%XMM0,%XMM3

0x25343e JAE	253382

0x253444 XOR	%R13D,%R13D

0x253447 VMULSD	0x98(%RDI),%XMM2,%XMM3

0x25344f VXORPD	%XMM2,%XMM2,%XMM2

0x253453 VUCOMISD	%XMM2,%XMM3

0x253457 JAE	2533c9

0x25345d XOR	%EAX,%EAX

0x25345f VMOVSD	-0x4f1f7(%RIP),%XMM3

0x253467 VMOVSD	-0x4f2cf(%RIP),%XMM4

0x25346f VMOVDDUP	%XMM1,%XMM8

0x253473 VMULSD	%XMM1,%XMM1,%XMM7

0x253477 CMPQ	$0,-0x30(%RBP)

0x25347c VMULSD	%XMM3,%XMM1,%XMM5

0x253480 VSUBSD	%XMM5,%XMM4,%XMM6

0x253484 VBLENDPD	$0x2,-0x4ef6e(%RIP),%XMM6,%XMM6

0x25348e VMULPD	%XMM6,%XMM8,%XMM6

0x253492 VADDPD	-0x4ee9a(%RIP),%XMM6,%XMM9

0x25349a VUNPCKLPD	%XMM7,%XMM8,%XMM8

0x25349e VSHUFPD	$0x1,%XMM6,%XMM6,%XMM6

0x2534a3 VFMADD213PD	-0x4efbc(%RIP),%XMM9,%XMM8

0x2534ac VSUBSD	%XMM6,%XMM4,%XMM6

0x2534b0 VFMADD213SD	%XMM4,%XMM1,%XMM6

0x2534b5 VFMADD213SD	%XMM3,%XMM1,%XMM6

0x2534ba VMULSD	%XMM7,%XMM5,%XMM1

0x2534be VMOVAPD	%XMM8,-0x120(%RBP)

0x2534c6 VMOVSD	%XMM6,-0x110(%RBP)

0x2534ce VMOVSD	%XMM1,-0x108(%RBP)

0x2534d6 JE	253b4d

0x2534dc VMULSD	%XMM3,%XMM0,%XMM1

0x2534e0 VMULSD	%XMM0,%XMM0,%XMM6

0x2534e4 MOV	0x20(%RDI),%RCX

0x2534e8 MOV	0x10(%RDI),%R12

0x2534ec MOV	%RDI,-0x48(%RBP)

0x2534f0 XOR	%ESI,%ESI

0x2534f2 MOV	%RAX,-0x40(%RBP)

0x2534f6 VSUBSD	%XMM1,%XMM4,%XMM5

0x2534fa VFMADD213SD	-0x4f393(%RIP),%XMM0,%XMM5

0x253503 MOV	%RCX,-0x50(%RBP)

0x253507 MOV	0x18(%RDI),%RCX

0x25350b MOV	%R14,%RDI

0x25350e MOV	%RCX,-0x38(%RBP)

0x253512 MOV	-0x30(%RBP),%RCX

0x253516 VFMADD213SD	%XMM3,%XMM0,%XMM5

0x25351b LEA	(,%RCX,8),%RDX

0x253523 VMOVSD	%XMM5,-0xb0(%RBP)

0x25352b VMULSD	%XMM4,%XMM0,%XMM5

0x25352f VADDSD	-0x4f457(%RIP),%XMM5,%XMM7

0x253537 VSUBSD	%XMM5,%XMM4,%XMM5

0x25353b VFMADD213SD	-0x4f40c(%RIP),%XMM6,%XMM7

0x253544 VFMADD213SD	%XMM4,%XMM0,%XMM5

0x253549 VFMADD213SD	%XMM3,%XMM0,%XMM5

0x25354e VMULSD	%XMM6,%XMM1,%XMM0

0x253552 VMOVDDUP	-0x4f3ba(%RIP),%XMM6

0x25355a VMOVSD	%XMM0,-0xa0(%RBP)

0x253562 VMULSD	%XMM3,%XMM2,%XMM0

0x253566 VMOVSD	%XMM5,-0xb8(%RBP)

0x25356e VMOVSD	%XMM7,-0xa8(%RBP)

0x253576 VMULSD	%XMM2,%XMM2,%XMM5

0x25357a VSUBSD	%XMM0,%XMM4,%XMM1

0x25357e VMULSD	%XMM5,%XMM0,%XMM0

0x253582 VUNPCKLPD	%XMM1,%XMM6,%XMM1

0x253586 VMOVDDUP	%XMM2,%XMM6

0x25358a VMOVAPD	%XMM0,-0xe0(%RBP)

0x253592 VMULPD	%XMM6,%XMM1,%XMM1

0x253596 VADDPD	-0x4efee(%RIP),%XMM1,%XMM7

0x25359e VBLENDPD	$0x1,%XMM5,%XMM6,%XMM6

0x2535a4 VSUBSD	%XMM1,%XMM4,%XMM1

0x2535a8 VFMADD213PD	-0x4f0e1(%RIP),%XMM7,%XMM6

0x2535b1 VFMADD213SD	%XMM4,%XMM2,%XMM1

0x2535b6 VFMADD213SD	%XMM3,%XMM2,%XMM1

0x2535bb VMOVAPD	%XMM6,-0x100(%RBP)

0x2535c3 VMOVAPD	%XMM1,-0xf0(%RBP)

0x2535cb CALL	2dc3f0 <@plt_start@+0x1b0>

0x2535d0 LEA	0x1(%R13),%R8

0x2535d4 LEA	0x2(%R13),%RSI

0x2535d8 LEA	0x3(%R13),%R15

0x2535dc IMUL	-0x38(%RBP),%R13

0x2535e1 IMUL	%R12,%RBX

0x2535e5 MOV	-0x50(%RBP),%R10

0x2535e9 VMOVAPD	-0x100(%RBP),%XMM11

0x2535f1 VMOVAPD	-0xe0(%RBP),%XMM13

0x2535f9 VMOVAPD	-0xf0(%RBP),%XMM12

0x253601 VMOVSD	-0xa0(%RBP),%XMM10

0x253609 VMOVSD	-0xa8(%RBP),%XMM9

0x253611 VMOVSD	-0xb0(%RBP),%XMM8

0x253619 SAL	$0x3,%R12

0x25361d LEA	(,%R13,8),%RAX

0x253625 VMOVDDUP	%XMM11,%XMM1

0x25362a VMOVDDUP	%XMM12,%XMM2

0x25362f VMOVDDUP	%XMM13,%XMM3

0x253634 VSHUFPD	$0x3,%XMM11,%XMM11,%XMM0

0x25363a LEA	(%RAX,%RBX,8),%R9

0x25363e MOV	-0x48(%RBP),%RAX

0x253642 MOV	0x8(%RAX),%RCX

0x253646 MOV	-0x40(%RBP),%RAX

0x25364a MOV	%RAX,%RDI

0x25364d IMUL	%R10,%RDI

0x253651 LEA	0x8(,%RAX,8),%RDX

0x253659 IMUL	%R10,%RDX

0x25365d LEA	(%R9,%RDI,8),%R11

0x253661 SAL	$0x3,%RDI

0x253665 LEA	(%RDI,%R13,8),%RAX

0x253669 MOV	-0x38(%RBP),%R13

0x25366d ADD	%RCX,%RDX

0x253670 ADD	%RCX,%R11

0x253673 LEA	(%RAX,%RBX,8),%RAX

0x253677 MOV	%RAX,-0x58(%RBP)

0x25367b LEA	(%RDI,%RBX,8),%RAX

0x25367f ADD	%RCX,-0x58(%RBP)

0x253683 IMUL	%R13,%RSI

0x253687 IMUL	%R13,%R15

0x25368b IMUL	%R13,%R8

0x25368f LEA	(%RAX,%RSI,8),%R13

0x253693 SAL	$0x3,%RSI

0x253697 LEA	(%RAX,%R8,8),%RDI

0x25369b SAL	$0x3,%R8

0x25369f LEA	(%RSI,%RBX,8),%R10

0x2536a3 LEA	(%R8,%RBX,8),%R8

0x2536a7 MOV	%R13,%RSI

0x2536aa LEA	(%RAX,%R15,8),%R13

0x2536ae SAL	$0x3,%R15

0x2536b2 ADD	%RCX,%RDI

0x2536b5 ADD	%RCX,%RSI

0x2536b8 LEA	(%R15,%RBX,8),%RAX

0x2536bc MOV	-0x40(%RBP),%R15

0x2536c0 MOV	%R13,%RBX

0x2536c3 ADD	%RCX,%RBX

0x2536c6 MOV	%RAX,-0x38(%RBP)

0x2536ca MOV	-0x50(%RBP),%RAX

0x2536ce LEA	0x10(,%R15,8),%R13

0x2536d6 LEA	0x18(,%R15,8),%R15

0x2536de IMUL	%RAX,%R13

0x2536e2 IMUL	%RAX,%R15

0x2536e6 ADD	%RCX,%R13

0x2536e9 ADD	%RCX,%R15

0x2536ec MOV	-0x30(%RBP),%RCX

0x2536f0 LEA	(%R13,%R9,1),%RAX

0x2536f5 MOV	%RAX,-0x78(%RBP)

0x2536f9 LEA	(%R15,%R9,1),%RAX

0x2536fd ADD	%RDX,%R9

0x253700 MOV	%RAX,-0x70(%RBP)

0x253704 LEA	(%RDX,%R8,1),%RAX

0x253708 MOV	%RAX,-0x90(%RBP)

0x25370f LEA	(%R13,%R8,1),%RAX

0x253714 ADD	%R15,%R8

0x253717 MOV	%RAX,-0x68(%RBP)

0x25371b LEA	(%RDX,%R10,1),%RAX

0x25371f AND	$-0x2,%RCX

0x253723 MOV	%RAX,-0x88(%RBP)

0x25372a LEA	(%R13,%R10,1),%RAX

0x25372f ADD	%R15,%R10

0x253732 MOV	%RAX,-0x60(%RBP)

0x253736 MOV	-0x38(%RBP),%RAX

0x25373a ADD	%RAX,%RDX

0x25373d ADD	%RAX,%R13

0x253740 ADD	%RAX,%R15

0x253743 XOR	%EAX,%EAX

0x253745 JMP	2537c2

0x253747 NOPW	(%RAX,%RAX,1)

(704) 0x253750 MOV	-0xc8(%RBP),%RAX

(704) 0x253757 MOV	-0xc0(%RBP),%R11

(704) 0x25375e MOV	-0x98(%RBP),%R9

(704) 0x253765 MOV	-0x38(%RBP),%RDI

(704) 0x253769 MOV	-0x80(%RBP),%R8

(704) 0x25376d MOV	-0x40(%RBP),%RSI

(704) 0x253771 MOV	-0x48(%RBP),%RBX

(704) 0x253775 ADD	%R12,-0x78(%RBP)

(704) 0x253779 ADD	%R12,-0x70(%RBP)

(704) 0x25377d ADD	%R12,-0x58(%RBP)

(704) 0x253781 ADD	%R12,-0x90(%RBP)

(704) 0x253788 ADD	%R12,-0x68(%RBP)

(704) 0x25378c ADD	%R12,-0x88(%RBP)

(704) 0x253793 ADD	%R12,-0x60(%RBP)

(704) 0x253797 ADD	%R12,%R10

(704) 0x25379a ADD	%R12,%RDX

(704) 0x25379d ADD	%R12,%R13

(704) 0x2537a0 ADD	%R12,%R15

(704) 0x2537a3 INC	%RAX

(704) 0x2537a6 ADD	%R12,%R11

(704) 0x2537a9 ADD	%R12,%R9

(704) 0x2537ac ADD	%R12,%RDI

(704) 0x2537af ADD	%R12,%R8

(704) 0x2537b2 ADD	%R12,%RSI

(704) 0x2537b5 ADD	%R12,%RBX

(704) 0x2537b8 CMP	$0x4,%RAX

(704) 0x2537bc JE	253b4d

(704) 0x2537c2 VMOVSD	-0x120(%RBP,%RAX,8),%XMM4

(704) 0x2537cb CMPQ	$0x2,-0x30(%RBP)

(704) 0x2537d0 MOV	%RBX,-0x48(%RBP)

(704) 0x2537d4 MOV	%RSI,-0x40(%RBP)

(704) 0x2537d8 MOV	%RDI,-0x38(%RBP)

(704) 0x2537dc MOV	%RAX,-0xc8(%RBP)

(704) 0x2537e3 MOV	%R9,-0x98(%RBP)

(704) 0x2537ea MOV	%R11,-0xc0(%RBP)

(704) 0x2537f1 MOV	%R8,-0x80(%RBP)

(704) 0x2537f5 VMULSD	%XMM4,%XMM8,%XMM5

(704) 0x2537f9 JAE	253800

(704) 0x2537fb XOR	%EAX,%EAX

(704) 0x2537fd JMP	253846

0x2537ff NOP

(704) 0x253800 MOV	-0x78(%RBP),%RSI

(704) 0x253804 MOV	-0x70(%RBP),%RDI

(704) 0x253808 VMOVDDUP	%XMM5,%XMM6

(704) 0x25380c XOR	%EAX,%EAX

(704) 0x25380e XCHG	%AX,%AX

  (700) 0x253810 VMULPD	(%R11,%RAX,8),%XMM0,%XMM7

  (700) 0x253816 VFMADD231PD	(%R9,%RAX,8),%XMM1,%XMM7

  (700) 0x25381c VFMADD231PD	(%RSI,%RAX,8),%XMM2,%XMM7

  (700) 0x253822 VFMADD231PD	(%RDI,%RAX,8),%XMM3,%XMM7

  (700) 0x253828 VFMADD213PD	(%R14,%RAX,8),%XMM6,%XMM7

  (700) 0x25382e VMOVUPD	%XMM7,(%R14,%RAX,8)

  (700) 0x253834 ADD	$0x2,%RAX

  (700) 0x253838 CMP	%RAX,%RCX

  (700) 0x25383b JNE	253810

(704) 0x25383d MOV	%RCX,%RAX

(704) 0x253840 CMP	%RCX,-0x30(%RBP)

(704) 0x253844 JE	2538b8

(704) 0x253846 MOV	-0x78(%RBP),%R8

(704) 0x25384a MOV	-0x70(%RBP),%RDI

(704) 0x25384e MOV	-0x98(%RBP),%R11

(704) 0x253855 MOV	-0x30(%RBP),%RSI

(704) 0x253859 LEA	(%R14,%RAX,8),%RBX

(704) 0x25385d LEA	(%R8,%RAX,8),%R9

(704) 0x253861 MOV	-0x58(%RBP),%R8

(704) 0x253865 LEA	(%RDI,%RAX,8),%RDI

(704) 0x253869 LEA	(%R11,%RAX,8),%R11

(704) 0x25386d SUB	%RAX,%RSI

(704) 0x253870 LEA	(%R8,%RAX,8),%R8

(704) 0x253874 XOR	%EAX,%EAX

(704) 0x253876 NOPW	%CS:(%RAX,%RAX,1)

  (708) 0x253880 VMOVSD	(%R11,%RAX,8),%XMM6

  (708) 0x253886 VMOVHPD	(%R8,%RAX,8),%XMM6,%XMM6

  (708) 0x25388c VMULPD	%XMM6,%XMM11,%XMM6

  (708) 0x253890 VSHUFPD	$0x1,%XMM6,%XMM6,%XMM7

  (708) 0x253895 VADDSD	%XMM7,%XMM6,%XMM6

  (708) 0x253899 VFMADD231SD	(%R9,%RAX,8),%XMM12,%XMM6

  (708) 0x25389f VFMADD231SD	(%RDI,%RAX,8),%XMM13,%XMM6

  (708) 0x2538a5 VFMADD213SD	(%RBX,%RAX,8),%XMM5,%XMM6

  (708) 0x2538ab VMOVSD	%XMM6,(%RBX,%RAX,8)

  (708) 0x2538b0 INC	%RAX

  (708) 0x2538b3 CMP	%RAX,%RSI

  (708) 0x2538b6 JNE	253880

(704) 0x2538b8 CMPQ	$0x2,-0x30(%RBP)

(704) 0x2538bd VMULSD	%XMM4,%XMM9,%XMM5

(704) 0x2538c1 JAE	2538d0

(704) 0x2538c3 XOR	%EAX,%EAX

(704) 0x2538c5 JMP	253925

0x2538c7 NOPW	(%RAX,%RAX,1)

(704) 0x2538d0 MOV	-0x38(%RBP),%RSI

(704) 0x2538d4 MOV	-0x80(%RBP),%RDI

(704) 0x2538d8 MOV	-0x90(%RBP),%R8

(704) 0x2538df MOV	-0x68(%RBP),%R9

(704) 0x2538e3 VMOVDDUP	%XMM5,%XMM6

(704) 0x2538e7 XOR	%EAX,%EAX

(704) 0x2538e9 NOPL	(%RAX)

  (701) 0x2538f0 VMULPD	(%RSI,%RAX,8),%XMM0,%XMM7

  (701) 0x2538f5 VFMADD231PD	(%R8,%RAX,8),%XMM1,%XMM7

  (701) 0x2538fb VFMADD231PD	(%R9,%RAX,8),%XMM2,%XMM7

  (701) 0x253901 VFMADD231PD	(%RDI,%RAX,8),%XMM3,%XMM7

  (701) 0x253907 VFMADD213PD	(%R14,%RAX,8),%XMM6,%XMM7

  (701) 0x25390d VMOVUPD	%XMM7,(%R14,%RAX,8)

  (701) 0x253913 ADD	$0x2,%RAX

  (701) 0x253917 CMP	%RAX,%RCX

  (701) 0x25391a JNE	2538f0

(704) 0x25391c MOV	%RCX,%RAX

(704) 0x25391f CMP	%RCX,-0x30(%RBP)

(704) 0x253923 JE	253998

(704) 0x253925 MOV	-0x68(%RBP),%R8

(704) 0x253929 MOV	-0x50(%RBP),%R11

(704) 0x25392d MOV	-0x80(%RBP),%RDI

(704) 0x253931 MOV	-0x30(%RBP),%RSI

(704) 0x253935 LEA	(%R14,%RAX,8),%RBX

(704) 0x253939 LEA	(%R8,%RAX,8),%R9

(704) 0x25393d LEA	(%R11,%RAX,1),%R8

(704) 0x253941 MOV	-0x38(%RBP),%R11

(704) 0x253945 LEA	(%RDI,%RAX,8),%RDI

(704) 0x253949 SUB	%RAX,%RSI

(704) 0x25394c LEA	(%R11,%R8,8),%R11

(704) 0x253950 MOV	-0x38(%RBP),%R8

(704) 0x253954 LEA	(%R8,%RAX,8),%R8

(704) 0x253958 XOR	%EAX,%EAX

(704) 0x25395a NOPW	(%RAX,%RAX,1)

  (707) 0x253960 VMOVSD	(%R11,%RAX,8),%XMM6

  (707) 0x253966 VMOVHPD	(%R8,%RAX,8),%XMM6,%XMM6

  (707) 0x25396c VMULPD	%XMM6,%XMM11,%XMM6

  (707) 0x253970 VSHUFPD	$0x1,%XMM6,%XMM6,%XMM7

  (707) 0x253975 VADDSD	%XMM7,%XMM6,%XMM6

  (707) 0x253979 VFMADD231SD	(%R9,%RAX,8),%XMM12,%XMM6

  (707) 0x25397f VFMADD231SD	(%RDI,%RAX,8),%XMM13,%XMM6

  (707) 0x253985 VFMADD213SD	(%RBX,%RAX,8),%XMM5,%XMM6

  (707) 0x25398b VMOVSD	%XMM6,(%RBX,%RAX,8)

  (707) 0x253990 INC	%RAX

  (707) 0x253993 CMP	%RAX,%RSI

  (707) 0x253996 JNE	253960

(704) 0x253998 VMULSD	-0xb8(%RBP),%XMM4,%XMM5

(704) 0x2539a0 CMPQ	$0x2,-0x30(%RBP)

(704) 0x2539a5 JAE	2539b0

(704) 0x2539a7 XOR	%EAX,%EAX

(704) 0x2539a9 JMP	253a05

0x2539ab NOPL	(%RAX,%RAX,1)

(704) 0x2539b0 MOV	-0x40(%RBP),%RSI

(704) 0x2539b4 MOV	-0x88(%RBP),%RDI

(704) 0x2539bb MOV	-0x60(%RBP),%R8

(704) 0x2539bf VMOVDDUP	%XMM5,%XMM6

(704) 0x2539c3 XOR	%EAX,%EAX

(704) 0x2539c5 NOPW	%CS:(%RAX,%RAX,1)

  (702) 0x2539d0 VMULPD	(%RSI,%RAX,8),%XMM0,%XMM7

  (702) 0x2539d5 VFMADD231PD	(%RDI,%RAX,8),%XMM1,%XMM7

  (702) 0x2539db VFMADD231PD	(%R8,%RAX,8),%XMM2,%XMM7

  (702) 0x2539e1 VFMADD231PD	(%R10,%RAX,8),%XMM3,%XMM7

  (702) 0x2539e7 VFMADD213PD	(%R14,%RAX,8),%XMM6,%XMM7

  (702) 0x2539ed VMOVUPD	%XMM7,(%R14,%RAX,8)

  (702) 0x2539f3 ADD	$0x2,%RAX

  (702) 0x2539f7 CMP	%RAX,%RCX

  (702) 0x2539fa JNE	2539d0

(704) 0x2539fc MOV	%RCX,%RAX

(704) 0x2539ff CMP	%RCX,-0x30(%RBP)

(704) 0x253a03 JE	253a78

(704) 0x253a05 MOV	-0x60(%RBP),%R8

(704) 0x253a09 MOV	-0x50(%RBP),%R11

(704) 0x253a0d MOV	-0x30(%RBP),%RSI

(704) 0x253a11 LEA	(%R14,%RAX,8),%RBX

(704) 0x253a15 LEA	(%R10,%RAX,8),%RDI

(704) 0x253a19 LEA	(%R8,%RAX,8),%R9

(704) 0x253a1d LEA	(%R11,%RAX,1),%R8

(704) 0x253a21 MOV	-0x40(%RBP),%R11

(704) 0x253a25 SUB	%RAX,%RSI

(704) 0x253a28 LEA	(%R11,%R8,8),%R11

(704) 0x253a2c MOV	-0x40(%RBP),%R8

(704) 0x253a30 LEA	(%R8,%RAX,8),%R8

(704) 0x253a34 XOR	%EAX,%EAX

(704) 0x253a36 NOPW	%CS:(%RAX,%RAX,1)

  (706) 0x253a40 VMOVSD	(%R11,%RAX,8),%XMM6

  (706) 0x253a46 VMOVHPD	(%R8,%RAX,8),%XMM6,%XMM6

  (706) 0x253a4c VMULPD	%XMM6,%XMM11,%XMM6

  (706) 0x253a50 VSHUFPD	$0x1,%XMM6,%XMM6,%XMM7

  (706) 0x253a55 VADDSD	%XMM7,%XMM6,%XMM6

  (706) 0x253a59 VFMADD231SD	(%R9,%RAX,8),%XMM12,%XMM6

  (706) 0x253a5f VFMADD231SD	(%RDI,%RAX,8),%XMM13,%XMM6

  (706) 0x253a65 VFMADD213SD	(%RBX,%RAX,8),%XMM5,%XMM6

  (706) 0x253a6b VMOVSD	%XMM6,(%RBX,%RAX,8)

  (706) 0x253a70 INC	%RAX

  (706) 0x253a73 CMP	%RAX,%RSI

  (706) 0x253a76 JNE	253a40

(704) 0x253a78 CMPQ	$0x2,-0x30(%RBP)

(704) 0x253a7d VMULSD	%XMM4,%XMM10,%XMM4

(704) 0x253a81 JAE	253a90

(704) 0x253a83 XOR	%EAX,%EAX

(704) 0x253a85 JMP	253ada

0x253a87 NOPW	(%RAX,%RAX,1)

(704) 0x253a90 MOV	-0x48(%RBP),%RSI

(704) 0x253a94 VMOVDDUP	%XMM4,%XMM5

(704) 0x253a98 XOR	%EAX,%EAX

(704) 0x253a9a NOPW	(%RAX,%RAX,1)

  (703) 0x253aa0 VMULPD	(%RSI,%RAX,8),%XMM0,%XMM6

  (703) 0x253aa5 VFMADD231PD	(%RDX,%RAX,8),%XMM1,%XMM6

  (703) 0x253aab VFMADD231PD	(%R13,%RAX,8),%XMM2,%XMM6

  (703) 0x253ab2 VFMADD231PD	(%R15,%RAX,8),%XMM3,%XMM6

  (703) 0x253ab8 VFMADD213PD	(%R14,%RAX,8),%XMM5,%XMM6

  (703) 0x253abe VMOVUPD	%XMM6,(%R14,%RAX,8)

  (703) 0x253ac4 ADD	$0x2,%RAX

  (703) 0x253ac8 CMP	%RAX,%RCX

  (703) 0x253acb JNE	253aa0

(704) 0x253acd MOV	%RCX,%RAX

(704) 0x253ad0 CMP	%RCX,-0x30(%RBP)

(704) 0x253ad4 JE	253750

(704) 0x253ada MOV	-0x50(%RBP),%R8

(704) 0x253ade MOV	-0x48(%RBP),%R11

(704) 0x253ae2 MOV	-0x30(%RBP),%RSI

(704) 0x253ae6 LEA	(%R14,%RAX,8),%RBX

(704) 0x253aea LEA	(%R15,%RAX,8),%RDI

(704) 0x253aee LEA	(%R13,%RAX,8),%R9

(704) 0x253af3 ADD	%RAX,%R8

(704) 0x253af6 SUB	%RAX,%RSI

(704) 0x253af9 LEA	(%R11,%R8,8),%R11

(704) 0x253afd MOV	-0x48(%RBP),%R8

(704) 0x253b01 LEA	(%R8,%RAX,8),%R8

(704) 0x253b05 XOR	%EAX,%EAX

(704) 0x253b07 NOPW	(%RAX,%RAX,1)

  (705) 0x253b10 VMOVSD	(%R11,%RAX,8),%XMM5

  (705) 0x253b16 VMOVHPD	(%R8,%RAX,8),%XMM5,%XMM5

  (705) 0x253b1c VMULPD	%XMM5,%XMM11,%XMM5

  (705) 0x253b20 VSHUFPD	$0x1,%XMM5,%XMM5,%XMM6

  (705) 0x253b25 VADDSD	%XMM6,%XMM5,%XMM5

  (705) 0x253b29 VFMADD231SD	(%R9,%RAX,8),%XMM12,%XMM5

  (705) 0x253b2f VFMADD231SD	(%RDI,%RAX,8),%XMM13,%XMM5

  (705) 0x253b35 VFMADD213SD	(%RBX,%RAX,8),%XMM4,%XMM5

  (705) 0x253b3b VMOVSD	%XMM5,(%RBX,%RAX,8)

  (705) 0x253b40 INC	%RAX

  (705) 0x253b43 CMP	%RAX,%RSI

  (705) 0x253b46 JNE	253b10

(704) 0x253b48 JMP	253750

0x253b4d ADD	$0xf8,%RSP

0x253b54 POP	%RBX

0x253b55 POP	%R12

0x253b57 POP	%R13

0x253b59 POP	%R14

0x253b5b POP	%R15

0x253b5d POP	%RBP

0x253b5e RET

0x253b5f INT	$0x3

Coverage (%)	Name	Source Location	Module
►96.18+	miniqmcreference::einspline_sp[...]	einspline_spo_ref.hpp:175	exec
○	miniqmcreference::einspline_sp[...]	einspline_spo_ref.hpp:183	exec
○	qmcplusplus::SPOSet::evaluateD[...]	OhmmsVector.h:178	exec
○	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:217	exec
○	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:135	exec
○	main.omp_outlined.64	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►3.03+	miniqmcreference::einspline_sp[...]	einspline_spo_ref.hpp:175	exec
○	miniqmcreference::einspline_sp[...]	einspline_spo_ref.hpp:183	exec
○	qmcplusplus::SPOSet::evaluateD[...]	OhmmsVector.h:178	exec
○	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:217	exec
○	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:135	exec
○	main.omp_outlined.64	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_fork_call		libomp.so
○	__kmpc_fork_call		libomp.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		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 0.00% of application time for run aocc_4

Source file and lines	MultiBsplineRef.hpp:41-73
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp:41-49,57,63-73
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:923-924
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53,60-63
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineData.hpp:54-57

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 30.88 to 17.50 cycles (1.76x speedup).

Workaround

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

Vectorization

Your function is not vectorized. Only 14% 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 30.88 to 3.02 cycles (10.21x speedup).

Details

17% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

25% of SSE/AVX loads are used in vector version.
16% of SSE/AVX stores are used in vector version.
11% of SSE/AVX addition or subtraction instructions are used in vector version.
11% of SSE/AVX multiply instructions are used in vector version.
18% of SSE/AVX fused multiply-add instructions are used in vector version.
22% 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.

Masked instructions

Detected masked instructions.

Details

Vector registers are partially exploited, which is expected if your function is irregular or mixes elements of different sizes.

Workaround

If your function is irregular, try to remove or hoist conditional structures out of your function. If it mixes elements of different sizes, try to uniformize them.

FMA

Detected 13 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

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.

unknown: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:924

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: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
KMOVD: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
VCVTTSD2SI: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60
VUCOMISD: 5 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53

Conversion instructions

Detected expensive conversion instructions.

Details

VCVTTSD2SI (FP64 to INT32/64, scalar): 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60

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

46 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 6 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (two at a time).

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

The binary function is composed of 63 FP arithmetical operations:

31: addition or subtraction (13 inside FMA instructions)
32: multiply (13 inside FMA instructions)

The binary function is loading 436 bytes (54 double precision FP elements). The binary function is storing 224 bytes (28 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.10 FP operations per loaded or stored byte.

General properties

nb instructions	238
nb uops	247
loop length	1099
used x86 registers	16
used mmx registers	0
used xmm registers	14
used ymm registers	0
used zmm registers	0
nb stack references	22
ADD-SUB / MUL ratio	0.94

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	30.88 cycles
front end	30.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	14.17	14.17	14.17	14.17	14.17	14.17	18.00	18.00	18.00	18.00	18.25	18.25	18.25	18.25	9.00	9.00
cycles	14.17	14.17	14.17	14.17	14.17	14.17	18.00	18.00	18.00	18.00	18.25	18.25	18.25	18.25	9.00	9.00

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	30.88
Dispatch	18.25
Overall L1	30.88

Vectorization ratios

INT

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

all	22%
load	27%
store	40%
mul	11%
add-sub	12%
fma	18%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	27%

INT+FP

all	17%
load	25%
store	16%
mul	11%
add-sub	11%
fma	18%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	22%

Vector efficiency ratios

INT

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

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

INT+FP

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

Cycles and memory resources usage

Detected masked instructions: assuming all mask elements are active. Assuming all data fit into the L1 cache, each call to the function takes 30.88 cycles. At this rate:

5% of peak load performance is reached (14.12 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.26 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 30.88 to 18.25 cycles (1.69x speedup).

ASM code

In the binary file, the address of the function is: 253330

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	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	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	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	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	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	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0xf8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VSUBSD 0x28(%RDI),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VSUBSD 0x50(%RDI),%XMM1,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV %RDX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RSI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
VMULSD 0x48(%RDI),%XMM0,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUCOMISD %XMM0,%XMM1	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JAE 2533ff <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0xcf>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %EBX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMULSD 0x70(%RDI),%XMM3,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VSUBSD 0x78(%RDI),%XMM2,%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VUCOMISD %XMM0,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JB 253444 <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x114>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VROUNDSD $0xb,%XMM3,%XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
MOV 0x60(%RDI),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VCVTTSD2SI %XMM3,%EDX	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	4	0.50	scal (12.5%)
VSUBSD %XMM0,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD -0x4f293(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
CMP %EDX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
LEA -0x1(%RAX),%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SETG %AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVG %EDX,%ECX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
KMOVD %EAX,%K1	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	N/A
MOVSXD %ECX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM3,%XMM0,%XMM0{%K1}	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMULSD 0x98(%RDI),%XMM2,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUCOMISD %XMM2,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JB 25345d <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x12d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VROUNDSD $0xb,%XMM3,%XMM3,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
MOV 0x88(%RDI),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VCVTTSD2SI %XMM3,%EDX	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	4	0.50	scal (12.5%)
VSUBSD %XMM2,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD -0x4f2dd(%RIP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
CMP %EDX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
LEA -0x1(%RAX),%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SETG %AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVG %EDX,%ECX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
KMOVD %EAX,%K1	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	N/A
MOVSXD %ECX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM3,%XMM2,%XMM2{%K1}	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
JMP 25345f <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x12f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VROUNDSD $0xb,%XMM1,%XMM1,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
MOV 0x38(%RDI),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VCVTTSD2SI %XMM1,%EDX	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	4	0.50	scal (12.5%)
VSUBSD %XMM4,%XMM1,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD -0x4f310(%RIP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
CMP %EDX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
LEA -0x1(%RAX),%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SETG %AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVG %EDX,%ECX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
KMOVD %EAX,%K1	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	N/A
MOVSXD %ECX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM4,%XMM1,%XMM1{%K1}	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMULSD 0x70(%RDI),%XMM3,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VSUBSD 0x78(%RDI),%XMM2,%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VUCOMISD %XMM0,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JAE 253382 <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x52>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VMULSD 0x98(%RDI),%XMM2,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUCOMISD %XMM2,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JAE 2533c9 <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x99>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VMOVSD -0x4f1f7(%RIP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD -0x4f2cf(%RIP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVDDUP %XMM1,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMULSD %XMM1,%XMM1,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPQ $0,-0x30(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
VMULSD %XMM3,%XMM1,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VSUBSD %XMM5,%XMM4,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VBLENDPD $0x2,-0x4ef6e(%RIP),%XMM6,%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	1	0.50	vect (25.0%)
VMULPD %XMM6,%XMM8,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	vect (25.0%)
VADDPD -0x4ee9a(%RIP),%XMM6,%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	vect (25.0%)
VUNPCKLPD %XMM7,%XMM8,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VSHUFPD $0x1,%XMM6,%XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
VFMADD213PD -0x4efbc(%RIP),%XMM9,%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	vect (25.0%)
VSUBSD %XMM6,%XMM4,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VFMADD213SD %XMM4,%XMM1,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM3,%XMM1,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM7,%XMM5,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMOVAPD %XMM8,-0x120(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD %XMM6,-0x110(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM1,-0x108(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
JE 253b4d <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x81d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMULSD %XMM3,%XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMULSD %XMM0,%XMM0,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
MOV 0x20(%RDI),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x10(%RDI),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV %RDI,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV %RAX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
VSUBSD %XMM1,%XMM4,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VFMADD213SD -0x4f393(%RIP),%XMM0,%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
MOV %RCX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x18(%RDI),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV -0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VFMADD213SD %XMM3,%XMM0,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
LEA (,%RCX,8),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVSD %XMM5,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMULSD %XMM4,%XMM0,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VADDSD -0x4f457(%RIP),%XMM5,%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VSUBSD %XMM5,%XMM4,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VFMADD213SD -0x4f40c(%RIP),%XMM6,%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM4,%XMM0,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM3,%XMM0,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM6,%XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMOVDDUP -0x4f3ba(%RIP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM0,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMULSD %XMM3,%XMM2,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMOVSD %XMM5,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM7,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMULSD %XMM2,%XMM2,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VSUBSD %XMM0,%XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMULSD %XMM5,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VUNPCKLPD %XMM1,%XMM6,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM2,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM0,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMULPD %XMM6,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	vect (25.0%)
VADDPD -0x4efee(%RIP),%XMM1,%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	vect (25.0%)
VBLENDPD $0x1,%XMM5,%XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	1	0.50	vect (25.0%)
VSUBSD %XMM1,%XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VFMADD213PD -0x4f0e1(%RIP),%XMM7,%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	vect (25.0%)
VFMADD213SD %XMM4,%XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM3,%XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVAPD %XMM6,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM1,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
CALL 2dc3f0 <@plt_start@+0x1b0>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
LEA 0x1(%R13),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x2(%R13),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x3(%R13),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
IMUL -0x38(%RBP),%R13	1	0.33	0.33	0.33	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.33	N/A
IMUL %R12,%RBX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
MOV -0x50(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VMOVAPD -0x100(%RBP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0xe0(%RBP),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0xf0(%RBP),%XMM12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVSD -0xa0(%RBP),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD -0xa8(%RBP),%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD -0xb0(%RBP),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
SAL $0x3,%R12	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
LEA (,%R13,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVDDUP %XMM11,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM12,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM13,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VSHUFPD $0x3,%XMM11,%XMM11,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
LEA (%RAX,%RBX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x48(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %R10,%RDI	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
LEA 0x8(,%RAX,8),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
IMUL %R10,%RDX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
LEA (%R9,%RDI,8),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%RDI	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA (%RDI,%R13,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x38(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %RCX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RCX,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA (%RAX,%RBX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%RDI,%RBX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD %RCX,-0x58(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
IMUL %R13,%RSI	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
IMUL %R13,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
IMUL %R13,%R8	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
LEA (%RAX,%RSI,8),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%RSI	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA (%RAX,%R8,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	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	0	0	0	0	1	0.33	N/A
LEA (%RSI,%RBX,8),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R8,%RBX,8),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R13,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RAX,%R15,8),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%R15	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
ADD %RCX,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RCX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R15,%RBX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x40(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %R13,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %RCX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA 0x10(,%R15,8),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x18(,%R15,8),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
IMUL %RAX,%R13	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
IMUL %RAX,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
ADD %RCX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RCX,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%R13,%R9,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%R15,%R9,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD %RDX,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%RDX,%R8,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%R13,%R8,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD %R15,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%RDX,%R10,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
AND $-0x2,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%R13,%R10,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD %R15,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV -0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %RAX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RAX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RAX,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 2537c2 <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x492>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0xf8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	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	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	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	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	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	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
INT $0x3																				N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run aocc_4

Source file and lines	MultiBsplineRef.hpp:41-73
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp:41-49,57,63-73
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:923-924
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53,60-63
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineData.hpp:54-57

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

17% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

25% of SSE/AVX loads are used in vector version.
16% of SSE/AVX stores are used in vector version.
11% of SSE/AVX addition or subtraction instructions are used in vector version.
11% of SSE/AVX multiply instructions are used in vector version.
18% of SSE/AVX fused multiply-add instructions are used in vector version.
22% 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.

Masked instructions

Detected masked instructions.

Details

Vector registers are partially exploited, which is expected if your function is irregular or mixes elements of different sizes.

Workaround

If your function is irregular, try to remove or hoist conditional structures out of your function. If it mixes elements of different sizes, try to uniformize them.

FMA

Detected 13 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

CALL instructions

Detected function call instructions.

Details

unknown: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h:924

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: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
KMOVD: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:63
VCVTTSD2SI: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60
VUCOMISD: 5 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:53

Conversion instructions

Detected expensive conversion instructions.

Details

VCVTTSD2SI (FP64 to INT32/64, scalar): 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp:60

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

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

The binary function is composed of 63 FP arithmetical operations:

31: addition or subtraction (13 inside FMA instructions)
32: multiply (13 inside FMA instructions)

The binary function is loading 436 bytes (54 double precision FP elements). The binary function is storing 224 bytes (28 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.10 FP operations per loaded or stored byte.

General properties

nb instructions	238
nb uops	247
loop length	1099
used x86 registers	16
used mmx registers	0
used xmm registers	14
used ymm registers	0
used zmm registers	0
nb stack references	22
ADD-SUB / MUL ratio	0.94

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	30.88 cycles
front end	30.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	14.17	14.17	14.17	14.17	14.17	14.17	18.00	18.00	18.00	18.00	18.25	18.25	18.25	18.25	9.00	9.00
cycles	14.17	14.17	14.17	14.17	14.17	14.17	18.00	18.00	18.00	18.00	18.25	18.25	18.25	18.25	9.00	9.00

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	30.88
Dispatch	18.25
Overall L1	30.88

Vectorization ratios

INT

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

all	22%
load	27%
store	40%
mul	11%
add-sub	12%
fma	18%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	27%

INT+FP

all	17%
load	25%
store	16%
mul	11%
add-sub	11%
fma	18%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	22%

Vector efficiency ratios

INT

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

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

INT+FP

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

Cycles and memory resources usage

Detected masked instructions: assuming all mask elements are active. Assuming all data fit into the L1 cache, each call to the function takes 30.88 cycles. At this rate:

5% of peak load performance is reached (14.12 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.26 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: 253330

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	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	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	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	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	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	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0xf8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VSUBSD 0x28(%RDI),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VSUBSD 0x50(%RDI),%XMM1,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV %RDX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RSI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
VMULSD 0x48(%RDI),%XMM0,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUCOMISD %XMM0,%XMM1	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JAE 2533ff <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0xcf>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %EBX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMULSD 0x70(%RDI),%XMM3,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VSUBSD 0x78(%RDI),%XMM2,%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VUCOMISD %XMM0,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JB 253444 <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x114>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VROUNDSD $0xb,%XMM3,%XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
MOV 0x60(%RDI),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VCVTTSD2SI %XMM3,%EDX	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	4	0.50	scal (12.5%)
VSUBSD %XMM0,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD -0x4f293(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
CMP %EDX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
LEA -0x1(%RAX),%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SETG %AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVG %EDX,%ECX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
KMOVD %EAX,%K1	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	N/A
MOVSXD %ECX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM3,%XMM0,%XMM0{%K1}	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMULSD 0x98(%RDI),%XMM2,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUCOMISD %XMM2,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JB 25345d <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x12d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VROUNDSD $0xb,%XMM3,%XMM3,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
MOV 0x88(%RDI),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VCVTTSD2SI %XMM3,%EDX	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	4	0.50	scal (12.5%)
VSUBSD %XMM2,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD -0x4f2dd(%RIP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
CMP %EDX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
LEA -0x1(%RAX),%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SETG %AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVG %EDX,%ECX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
KMOVD %EAX,%K1	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	N/A
MOVSXD %ECX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM3,%XMM2,%XMM2{%K1}	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
JMP 25345f <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x12f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VROUNDSD $0xb,%XMM1,%XMM1,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
MOV 0x38(%RDI),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VCVTTSD2SI %XMM1,%EDX	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	4	0.50	scal (12.5%)
VSUBSD %XMM4,%XMM1,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD -0x4f310(%RIP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
CMP %EDX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
LEA -0x1(%RAX),%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SETG %AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVG %EDX,%ECX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
KMOVD %EAX,%K1	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	N/A
MOVSXD %ECX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM4,%XMM1,%XMM1{%K1}	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMULSD 0x70(%RDI),%XMM3,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VSUBSD 0x78(%RDI),%XMM2,%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VUCOMISD %XMM0,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JAE 253382 <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x52>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VMULSD 0x98(%RDI),%XMM2,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUCOMISD %XMM2,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	0.50	scal (12.5%)
JAE 2533c9 <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x99>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VMOVSD -0x4f1f7(%RIP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD -0x4f2cf(%RIP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVDDUP %XMM1,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMULSD %XMM1,%XMM1,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPQ $0,-0x30(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
VMULSD %XMM3,%XMM1,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VSUBSD %XMM5,%XMM4,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VBLENDPD $0x2,-0x4ef6e(%RIP),%XMM6,%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	1	0.50	vect (25.0%)
VMULPD %XMM6,%XMM8,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	vect (25.0%)
VADDPD -0x4ee9a(%RIP),%XMM6,%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	vect (25.0%)
VUNPCKLPD %XMM7,%XMM8,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VSHUFPD $0x1,%XMM6,%XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
VFMADD213PD -0x4efbc(%RIP),%XMM9,%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	vect (25.0%)
VSUBSD %XMM6,%XMM4,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VFMADD213SD %XMM4,%XMM1,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM3,%XMM1,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM7,%XMM5,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMOVAPD %XMM8,-0x120(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD %XMM6,-0x110(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM1,-0x108(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
JE 253b4d <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x81d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMULSD %XMM3,%XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMULSD %XMM0,%XMM0,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
MOV 0x20(%RDI),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x10(%RDI),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV %RDI,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV %RAX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
VSUBSD %XMM1,%XMM4,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VFMADD213SD -0x4f393(%RIP),%XMM0,%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
MOV %RCX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x18(%RDI),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV -0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VFMADD213SD %XMM3,%XMM0,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
LEA (,%RCX,8),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVSD %XMM5,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMULSD %XMM4,%XMM0,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VADDSD -0x4f457(%RIP),%XMM5,%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VSUBSD %XMM5,%XMM4,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VFMADD213SD -0x4f40c(%RIP),%XMM6,%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM4,%XMM0,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM3,%XMM0,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMULSD %XMM6,%XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMOVDDUP -0x4f3ba(%RIP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM0,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMULSD %XMM3,%XMM2,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMOVSD %XMM5,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM7,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMULSD %XMM2,%XMM2,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VSUBSD %XMM0,%XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMULSD %XMM5,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VUNPCKLPD %XMM1,%XMM6,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM2,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM0,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMULPD %XMM6,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	vect (25.0%)
VADDPD -0x4efee(%RIP),%XMM1,%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	vect (25.0%)
VBLENDPD $0x1,%XMM5,%XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	1	0.50	vect (25.0%)
VSUBSD %XMM1,%XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VFMADD213PD -0x4f0e1(%RIP),%XMM7,%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	vect (25.0%)
VFMADD213SD %XMM4,%XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM3,%XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVAPD %XMM6,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM1,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
CALL 2dc3f0 <@plt_start@+0x1b0>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
LEA 0x1(%R13),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x2(%R13),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x3(%R13),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
IMUL -0x38(%RBP),%R13	1	0.33	0.33	0.33	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.33	N/A
IMUL %R12,%RBX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
MOV -0x50(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VMOVAPD -0x100(%RBP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0xe0(%RBP),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0xf0(%RBP),%XMM12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVSD -0xa0(%RBP),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD -0xa8(%RBP),%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD -0xb0(%RBP),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
SAL $0x3,%R12	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
LEA (,%R13,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVDDUP %XMM11,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM12,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM13,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VSHUFPD $0x3,%XMM11,%XMM11,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
LEA (%RAX,%RBX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x48(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %R10,%RDI	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
LEA 0x8(,%RAX,8),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
IMUL %R10,%RDX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
LEA (%R9,%RDI,8),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%RDI	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA (%RDI,%R13,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x38(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %RCX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RCX,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA (%RAX,%RBX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%RDI,%RBX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD %RCX,-0x58(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
IMUL %R13,%RSI	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
IMUL %R13,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
IMUL %R13,%R8	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
LEA (%RAX,%RSI,8),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%RSI	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA (%RAX,%R8,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	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	0	0	0	0	1	0.33	N/A
LEA (%RSI,%RBX,8),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R8,%RBX,8),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R13,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RAX,%R15,8),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%R15	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
ADD %RCX,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RCX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R15,%RBX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x40(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %R13,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %RCX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA 0x10(,%R15,8),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x18(,%R15,8),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
IMUL %RAX,%R13	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
IMUL %RAX,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
ADD %RCX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RCX,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%R13,%R9,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%R15,%R9,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD %RDX,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%RDX,%R8,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%R13,%R8,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD %R15,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%RDX,%R10,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
AND $-0x2,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%R13,%R10,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD %R15,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV -0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %RAX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RAX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RAX,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 2537c2 <_ZN16miniqmcreference19MultiBsplineEvalRef10evaluate_vIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_m+0x492>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0xf8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	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	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	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	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	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	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
INT $0x3																				N/A

Name	Coverage (%)	Time (s)
▼void miniqmcreference::MultiBsplineEvalRef::evaluate_v(qmcplusplus::bspline_traits::SplineType const, double, double, double, double, unsigned long)–	25.43	42.23
▼Loop 704 - MultiBsplineRef.hpp:63-70 - exec–	0.00	0.01
○Loop 700 - MultiBsplineRef.hpp:68-70 - exec	6.40	10.57
○Loop 703 - MultiBsplineRef.hpp:68-70 - exec	6.39	10.55
○Loop 701 - MultiBsplineRef.hpp:68-70 - exec	6.32	10.44
○Loop 702 - MultiBsplineRef.hpp:68-70 - exec	6.31	10.42
○Loop 707 - MultiBsplineRef.hpp:68-70 - exec	0.00	0.00
○Loop 708 - MultiBsplineRef.hpp:68-70 - exec	0.00	0.00
○Loop 705 - MultiBsplineRef.hpp:68-70 - exec	0.00	0.00
○Loop 706 - MultiBsplineRef.hpp:68-70 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Masked instructions

Details

Workaround

FMA

Workaround

CALL instructions

Details

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Masked instructions

Details

Workaround

FMA

Workaround

CALL instructions

Details

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code