OV - exec - Function flux_calc_kernel(int, int, int, int, 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]

	Function: flux_calc_kernel(int, int, int, int, double, clover::Buffer2D<double>&, clover::Buffer2D<d ...	Module: exec	Source: flux_calc.cpp:36-41 [...]	Coverage (incl. loops): 3.36% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/flux_calc.cpp: 36 - 41

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

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

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

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

39:       vol_flux_x(i, j) = 0.25 * dt * xarea(i, j) * (xvel0(i, j) + xvel0(i + 0, j + 1) + xvel1(i, j) + xvel1(i + 0, j + 1));

40:       vol_flux_y(i, j) = 0.25 * dt * yarea(i, j) * (yvel0(i, j) + yvel0(i + 1, j + 0) + yvel1(i, j) + yvel1(i + 1, j + 0));

41:     }

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

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

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

0x433b80 PUSH	%RBP

0x433b81 MOV	%RSP,%RBP

0x433b84 PUSH	%R15

0x433b86 PUSH	%R14

0x433b88 PUSH	%R13

0x433b8a PUSH	%R12

0x433b8c PUSH	%RBX

0x433b8d SUB	$0x178,%RSP

0x433b94 MOV	%RCX,%R12

0x433b97 MOV	0x58(%RBP),%RAX

0x433b9b MOV	0x48(%RBP),%R15

0x433b9f MOV	0x40(%RBP),%R10

0x433ba3 MOV	0x30(%RBP),%RCX

0x433ba7 MOV	0x28(%RBP),%R13

0x433bab MOV	0x20(%RBP),%RSI

0x433baf MOV	0x18(%RBP),%R14

0x433bb3 MOV	0x10(%RBP),%RBX

0x433bb7 MOV	0x38(%RBP),%R11D

0x433bbb MOVL	$0,-0x70(%RBP)

0x433bc2 TEST	%RAX,%RAX

0x433bc5 JS	4343c1

0x433bcb MOV	%RDX,-0x48(%RBP)

0x433bcf MOV	%RSI,-0x38(%RBP)

0x433bd3 MOV	%R9,-0x50(%RBP)

0x433bd7 MOV	%RCX,-0x30(%RBP)

0x433bdb MOV	%R8,-0x40(%RBP)

0x433bdf MOV	(%RDI),%ESI

0x433be1 MOVQ	$0,-0x98(%RBP)

0x433bec MOV	%RAX,-0x90(%RBP)

0x433bf3 MOVQ	$0x1,-0xf0(%RBP)

0x433bfe SUB	$0x8,%RSP

0x433c02 LEA	-0xf0(%RBP),%RAX

0x433c09 LEA	-0x70(%RBP),%RCX

0x433c0d LEA	-0x98(%RBP),%R8

0x433c14 LEA	-0x90(%RBP),%R9

0x433c1b MOV	$0x4b80b0,%EDI

0x433c20 MOV	%ESI,-0x6c(%RBP)

0x433c23 MOV	$0x22,%EDX

0x433c28 PUSH	$0x1

0x433c2a PUSH	$0x1

0x433c2c PUSH	%RAX

0x433c2d MOV	%R10,-0x80(%RBP)

0x433c31 MOV	%R11,-0x78(%RBP)

0x433c35 CALL	4031f0 <__kmpc_for_static_init_8@plt>

0x433c3a MOV	-0x78(%RBP),%R11

0x433c3e MOV	-0x80(%RBP),%RAX

0x433c42 ADD	$0x20,%RSP

0x433c46 MOV	-0x98(%RBP),%RCX

0x433c4d MOV	-0x90(%RBP),%R10

0x433c54 CMP	%R10,%RCX

0x433c57 JA	4343a3

0x433c5d MOV	%R15,%R9

0x433c60 MOV	%RAX,%R15

0x433c63 MOVSD	-0x48(%RBP),%XMM2

0x433c68 SUB	%R15D,%R9D

0x433c6b MULSD	0x677ad(%RIP),%XMM2

0x433c73 MOV	(%R12),%RAX

0x433c77 MOV	%RAX,-0x60(%RBP)

0x433c7b MOV	0x10(%R12),%RDX

0x433c80 MOV	%RDX,-0x68(%RBP)

0x433c84 MOV	-0x50(%RBP),%RDX

0x433c88 MOV	(%RDX),%RAX

0x433c8b MOV	%RAX,-0x58(%RBP)

0x433c8f MOV	0x10(%RDX),%RDI

0x433c93 MOV	%RDI,-0x50(%RBP)

0x433c97 MOV	(%R14),%RDI

0x433c9a MOV	0x10(%R14),%R8

0x433c9e MOV	%R8,-0x48(%RBP)

0x433ca2 MOV	(%R13),%R8

0x433ca6 MOV	0x10(%R13),%RAX

0x433caa MOV	-0x40(%RBP),%RDX

0x433cae MOV	(%RDX),%R14

0x433cb1 MOV	0x10(%RDX),%R12

0x433cb5 MOV	%R12,-0x40(%RBP)

0x433cb9 MOV	(%RBX),%R12

0x433cbc MOV	0x10(%RBX),%RBX

0x433cc0 MOV	%RBX,-0x88(%RBP)

0x433cc7 MOV	-0x38(%RBP),%RDX

0x433ccb MOV	(%RDX),%RBX

0x433cce MOV	0x10(%RDX),%R13

0x433cd2 MOV	%R13,-0x38(%RBP)

0x433cd6 MOV	-0x30(%RBP),%RDX

0x433cda MOV	(%RDX),%R13

0x433cdd MOV	0x10(%RDX),%RDX

0x433ce1 MOV	%RDX,-0x30(%RBP)

0x433ce5 INC	%R10

0x433ce8 MOV	%R15,%RDX

0x433ceb MOV	%R10,%R15

0x433cee SUB	%RCX,%R15

0x433cf1 MOV	$-0x2,%ESI

0x433cf6 MOV	%R15,-0xb0(%RBP)

0x433cfd AND	%R15,%RSI

0x433d00 MOV	%RDI,-0xe8(%RBP)

0x433d07 MOV	%R8,-0xe0(%RBP)

0x433d0e MOV	%RAX,-0xd8(%RBP)

0x433d15 MOV	%R14,-0xd0(%RBP)

0x433d1c MOV	%R12,-0xc8(%RBP)

0x433d23 MOV	%RBX,-0xc0(%RBP)

0x433d2a MOV	%R13,-0xb8(%RBP)

0x433d31 JE	4343d3

0x433d37 MOV	%R10,-0xa0(%RBP)

0x433d3e MOV	%R9,-0xa8(%RBP)

0x433d45 MOVD	%R9D,%XMM0

0x433d4a PSHUFD	$0x44,%XMM0,%XMM0

0x433d4f MOVDQA	%XMM0,-0x1a0(%RBP)

0x433d57 MOVD	%R11D,%XMM0

0x433d5c PSHUFD	$0x50,%XMM0,%XMM0

0x433d61 MOVDQA	%XMM0,-0x190(%RBP)

0x433d69 MOVD	%EDX,%XMM0

0x433d6d PSHUFD	$0x50,%XMM0,%XMM0

0x433d72 MOVDQA	%XMM0,-0x180(%RBP)

0x433d7a MOVQ	-0x60(%RBP),%XMM0

0x433d7f PSHUFD	$0x44,%XMM0,%XMM0

0x433d84 MOVDQA	%XMM0,-0x170(%RBP)

0x433d8c MOVAPD	%XMM2,-0x100(%RBP)

0x433d94 UNPCKLPD	%XMM2,%XMM2

0x433d98 MOVAPD	%XMM2,-0x160(%RBP)

0x433da0 MOVQ	-0x58(%RBP),%XMM0

0x433da5 PSHUFD	$0x44,%XMM0,%XMM10

0x433dab MOVQ	%RDI,%XMM0

0x433db0 PSHUFD	$0x44,%XMM0,%XMM7

0x433db5 MOVQ	%R8,%XMM0

0x433dba PSHUFD	$0x44,%XMM0,%XMM0

0x433dbf MOVDQA	%XMM0,-0x150(%RBP)

0x433dc7 MOVQ	%R14,%XMM0

0x433dcc PSHUFD	$0x44,%XMM0,%XMM0

0x433dd1 MOVDQA	%XMM0,-0x140(%RBP)

0x433dd9 MOVQ	%R12,%XMM0

0x433dde PSHUFD	$0x44,%XMM0,%XMM0

0x433de3 MOVDQA	%XMM0,-0x130(%RBP)

0x433deb MOVQ	%RBX,%XMM0

0x433df0 PSHUFD	$0x44,%XMM0,%XMM0

0x433df5 MOVDQA	%XMM0,-0x120(%RBP)

0x433dfd MOVQ	%R13,%XMM0

0x433e02 PSHUFD	$0x44,%XMM0,%XMM0

0x433e07 MOVDQA	%XMM0,-0x110(%RBP)

0x433e0f MOVQ	%RCX,%XMM0

0x433e14 PSHUFD	$0x44,%XMM0,%XMM13

0x433e1a PADDQ	0x6760d(%RIP),%XMM13

0x433e23 XOR	%R8D,%R8D

0x433e26 MOV	%RAX,%R12

0x433e29 PXOR	%XMM11,%XMM11

0x433e2e PCMPEQD	%XMM12,%XMM12

0x433e33 NOPW	%CS:(%RAX,%RAX,1)

(220) 0x433e40 MOVQ	%XMM13,%RAX

(220) 0x433e45 MOV	%RSI,%RDI

(220) 0x433e48 MOVDQA	-0x1a0(%RBP),%XMM2

(220) 0x433e50 MOVQ	%XMM2,%RSI

(220) 0x433e55 XOR	%EDX,%EDX

(220) 0x433e57 DIV	%RSI

(220) 0x433e5a PSHUFD	$-0x12,%XMM13,%XMM0

(220) 0x433e60 MOVQ	%XMM0,%RDX

(220) 0x433e65 PSHUFD	$-0x12,%XMM2,%XMM0

(220) 0x433e6a MOVQ	%XMM0,%RSI

(220) 0x433e6f MOVQ	%RAX,%XMM0

(220) 0x433e74 MOV	%RDX,%RAX

(220) 0x433e77 XOR	%EDX,%EDX

(220) 0x433e79 DIV	%RSI

(220) 0x433e7c MOVQ	%RAX,%XMM1

(220) 0x433e81 PUNPCKLQDQ	%XMM1,%XMM0

(220) 0x433e85 PSHUFD	$-0x18,%XMM0,%XMM14

(220) 0x433e8b PADDD	-0x190(%RBP),%XMM14

(220) 0x433e94 PMULUDQ	%XMM2,%XMM0

(220) 0x433e98 MOVDQA	%XMM13,%XMM1

(220) 0x433e9d PSUBQ	%XMM0,%XMM1

(220) 0x433ea1 PSHUFD	$-0x18,%XMM1,%XMM15

(220) 0x433ea7 PXOR	%XMM1,%XMM1

(220) 0x433eab PXOR	%XMM2,%XMM2

(220) 0x433eaf PCMPGTD	%XMM14,%XMM2

(220) 0x433eb4 PADDD	-0x180(%RBP),%XMM15

(220) 0x433ebd MOVDQA	%XMM14,%XMM0

(220) 0x433ec2 PUNPCKLDQ	%XMM2,%XMM0

(220) 0x433ec6 MOVDQA	-0x170(%RBP),%XMM6

(220) 0x433ece MOVDQA	%XMM6,%XMM5

(220) 0x433ed2 PCMPGTD	%XMM15,%XMM1

(220) 0x433ed7 PMULUDQ	%XMM0,%XMM5

(220) 0x433edb MOVDQA	%XMM6,%XMM4

(220) 0x433edf PSRLQ	$0x20,%XMM4

(220) 0x433ee4 MOVDQA	%XMM15,%XMM3

(220) 0x433ee9 PMULUDQ	%XMM0,%XMM4

(220) 0x433eed PUNPCKLDQ	%XMM11,%XMM2

(220) 0x433ef2 PUNPCKLDQ	%XMM1,%XMM3

(220) 0x433ef6 PMULUDQ	%XMM2,%XMM6

(220) 0x433efa PADDQ	%XMM4,%XMM6

(220) 0x433efe PSLLQ	$0x20,%XMM6

(220) 0x433f03 PADDQ	%XMM3,%XMM5

(220) 0x433f07 MOVQ	-0x68(%RBP),%XMM1

(220) 0x433f0c PSHUFD	$0x44,%XMM1,%XMM1

(220) 0x433f11 MOVDQA	%XMM10,%XMM8

(220) 0x433f16 PADDQ	%XMM6,%XMM5

(220) 0x433f1a PSRLQ	$0x20,%XMM8

(220) 0x433f20 MOVDQA	%XMM8,%XMM4

(220) 0x433f25 MOVDQA	%XMM10,%XMM9

(220) 0x433f2a PMULUDQ	%XMM0,%XMM4

(220) 0x433f2e PMULUDQ	%XMM2,%XMM9

(220) 0x433f33 PADDQ	%XMM4,%XMM9

(220) 0x433f38 MOVDQA	%XMM10,%XMM6

(220) 0x433f3d PMULUDQ	%XMM0,%XMM6

(220) 0x433f41 PSLLQ	$0x20,%XMM9

(220) 0x433f47 PADDQ	%XMM3,%XMM6

(220) 0x433f4b PADDQ	%XMM9,%XMM6

(220) 0x433f50 PSLLQ	$0x3,%XMM5

(220) 0x433f55 PSUBD	%XMM12,%XMM14

(220) 0x433f5a PXOR	%XMM4,%XMM4

(220) 0x433f5e PCMPGTD	%XMM14,%XMM4

(220) 0x433f63 PADDQ	%XMM5,%XMM1

(220) 0x433f67 PUNPCKLDQ	%XMM4,%XMM14

(220) 0x433f6c PUNPCKLDQ	%XMM11,%XMM4

(220) 0x433f71 MOVDQA	%XMM10,%XMM9

(220) 0x433f76 PMULUDQ	%XMM14,%XMM8

(220) 0x433f7b PMULUDQ	%XMM4,%XMM9

(220) 0x433f80 PADDQ	%XMM8,%XMM9

(220) 0x433f85 MOVDQA	%XMM10,%XMM5

(220) 0x433f8a PSLLQ	$0x3,%XMM6

(220) 0x433f8f PMULUDQ	%XMM14,%XMM5

(220) 0x433f94 PSLLQ	$0x20,%XMM9

(220) 0x433f9a PADDQ	%XMM3,%XMM5

(220) 0x433f9e MOVQ	%XMM1,%RAX

(220) 0x433fa3 PADDQ	%XMM9,%XMM5

(220) 0x433fa8 MOVQ	-0x50(%RBP),%XMM8

(220) 0x433fae PSHUFD	$0x44,%XMM8,%XMM8

(220) 0x433fb4 PSHUFD	$-0x12,%XMM1,%XMM1

(220) 0x433fb9 PADDQ	%XMM8,%XMM6

(220) 0x433fbe MOVQ	%XMM6,%RSI

(220) 0x433fc3 PSHUFD	$-0x12,%XMM6,%XMM9

(220) 0x433fc9 MOVQ	%XMM1,%RDX

(220) 0x433fce PSLLQ	$0x3,%XMM5

(220) 0x433fd3 PADDQ	%XMM8,%XMM5

(220) 0x433fd8 MOVDQA	%XMM7,%XMM6

(220) 0x433fdc MOVQ	%XMM9,%R9

(220) 0x433fe1 PSRLQ	$0x20,%XMM6

(220) 0x433fe6 MOVDQA	%XMM6,%XMM1

(220) 0x433fea MOVDQA	%XMM7,%XMM8

(220) 0x433fef PMULUDQ	%XMM0,%XMM1

(220) 0x433ff3 PMULUDQ	%XMM2,%XMM8

(220) 0x433ff8 PADDQ	%XMM1,%XMM8

(220) 0x433ffd MOVDQA	%XMM7,%XMM1

(220) 0x434001 PMULUDQ	%XMM0,%XMM1

(220) 0x434005 PSLLQ	$0x20,%XMM8

(220) 0x43400b PADDQ	%XMM3,%XMM1

(220) 0x43400f PADDQ	%XMM8,%XMM1

(220) 0x434014 MOVQ	%XMM5,%R11

(220) 0x434019 PSLLQ	$0x3,%XMM1

(220) 0x43401e MOVQ	-0x48(%RBP),%XMM8

(220) 0x434024 PSHUFD	$0x44,%XMM8,%XMM8

(220) 0x43402a PSHUFD	$-0x12,%XMM5,%XMM5

(220) 0x43402f PADDQ	%XMM8,%XMM1

(220) 0x434034 MOVQ	%XMM1,%R14

(220) 0x434039 PSHUFD	$-0x12,%XMM1,%XMM1

(220) 0x43403e MOVQ	%XMM5,%RBX

(220) 0x434043 MOVQ	%XMM1,%R13

(220) 0x434048 MOVDQA	%XMM7,%XMM9

(220) 0x43404d PMULUDQ	%XMM14,%XMM9

(220) 0x434052 MOVSD	(%RSI),%XMM1

(220) 0x434056 PMULUDQ	%XMM14,%XMM6

(220) 0x43405b MOVSD	(%R14),%XMM14

(220) 0x434060 MOVHPD	(%R9),%XMM1

(220) 0x434065 PMULUDQ	%XMM7,%XMM4

(220) 0x434069 PADDQ	%XMM6,%XMM4

(220) 0x43406d PSLLQ	$0x20,%XMM4

(220) 0x434072 MOVSD	(%R11),%XMM5

(220) 0x434077 PADDQ	%XMM3,%XMM9

(220) 0x43407c PADDQ	%XMM4,%XMM9

(220) 0x434081 MOVHPD	(%R13),%XMM14

(220) 0x434087 PSLLQ	$0x3,%XMM9

(220) 0x43408d PADDQ	%XMM8,%XMM9

(220) 0x434092 MOVHPD	(%RBX),%XMM5

(220) 0x434096 MOVQ	%XMM9,%R14

(220) 0x43409b PSHUFD	$-0x12,%XMM9,%XMM4

(220) 0x4340a1 MOVQ	%XMM4,%R13

(220) 0x4340a6 MOVDQA	-0x150(%RBP),%XMM8

(220) 0x4340af MOVDQA	%XMM8,%XMM4

(220) 0x4340b4 PMULUDQ	%XMM0,%XMM4

(220) 0x4340b8 MOVDQA	%XMM8,%XMM6

(220) 0x4340bd PSRLQ	$0x20,%XMM6

(220) 0x4340c2 PMULUDQ	%XMM0,%XMM6

(220) 0x4340c6 PMULUDQ	%XMM2,%XMM8

(220) 0x4340cb PADDQ	%XMM6,%XMM8

(220) 0x4340d0 PSLLQ	$0x20,%XMM8

(220) 0x4340d6 PADDQ	%XMM3,%XMM4

(220) 0x4340da MOVDQA	-0x140(%RBP),%XMM9

(220) 0x4340e3 MOVDQA	%XMM9,%XMM6

(220) 0x4340e8 PSRLQ	$0x20,%XMM6

(220) 0x4340ed PADDQ	%XMM8,%XMM4

(220) 0x4340f2 PMULUDQ	%XMM0,%XMM6

(220) 0x4340f6 MOVDQA	%XMM9,%XMM8

(220) 0x4340fb PMULUDQ	%XMM2,%XMM8

(220) 0x434100 PSLLQ	$0x3,%XMM4

(220) 0x434105 PADDQ	%XMM6,%XMM8

(220) 0x43410a MOVQ	%R12,%XMM6

(220) 0x43410f PSHUFD	$0x44,%XMM6,%XMM6

(220) 0x434114 PADDQ	%XMM4,%XMM6

(220) 0x434118 MOVDQA	%XMM9,%XMM4

(220) 0x43411d PMULUDQ	%XMM0,%XMM4

(220) 0x434121 PSLLQ	$0x20,%XMM8

(220) 0x434127 PADDQ	%XMM3,%XMM4

(220) 0x43412b PADDQ	%XMM8,%XMM4

(220) 0x434130 MOVQ	-0x40(%RBP),%XMM8

(220) 0x434136 PSHUFD	$0x44,%XMM8,%XMM8

(220) 0x43413c PSLLQ	$0x3,%XMM4

(220) 0x434141 PADDQ	%XMM4,%XMM8

(220) 0x434146 MOVQ	%XMM6,%RSI

(220) 0x43414b PSHUFD	$-0x12,%XMM6,%XMM4

(220) 0x434150 MOVQ	%XMM4,%RBX

(220) 0x434155 MOVSD	(%R14),%XMM4

(220) 0x43415a MOVHPD	(%R13),%XMM4

(220) 0x434160 MOVQ	%XMM8,%R13

(220) 0x434165 PSHUFD	$-0x12,%XMM8,%XMM6

(220) 0x43416b MOVQ	%XMM6,%R14

(220) 0x434170 MOVDQA	-0x130(%RBP),%XMM9

(220) 0x434179 MOVDQA	%XMM9,%XMM8

(220) 0x43417e ADDPD	%XMM1,%XMM14

(220) 0x434183 PSRLQ	$0x20,%XMM8

(220) 0x434189 PMULUDQ	%XMM0,%XMM8

(220) 0x43418e MOVDQA	%XMM9,%XMM6

(220) 0x434193 PMULUDQ	%XMM2,%XMM6

(220) 0x434197 PADDQ	%XMM8,%XMM6

(220) 0x43419c MOVDQA	%XMM9,%XMM1

(220) 0x4341a1 PMULUDQ	%XMM0,%XMM1

(220) 0x4341a5 PSLLQ	$0x20,%XMM6

(220) 0x4341aa PADDQ	%XMM1,%XMM6

(220) 0x4341ae MOVDQA	%XMM6,%XMM1

(220) 0x4341b2 PADDQ	%XMM3,%XMM1

(220) 0x4341b6 ADDPD	%XMM5,%XMM4

(220) 0x4341ba PSUBD	%XMM12,%XMM15

(220) 0x4341bf XORPD	%XMM5,%XMM5

(220) 0x4341c3 PCMPGTD	%XMM15,%XMM5

(220) 0x4341c8 PSLLQ	$0x3,%XMM1

(220) 0x4341cd PUNPCKLDQ	%XMM5,%XMM15

(220) 0x4341d2 MOVQ	-0x88(%RBP),%XMM5

(220) 0x4341da PSHUFD	$0x44,%XMM5,%XMM5

(220) 0x4341df PADDQ	%XMM5,%XMM1

(220) 0x4341e3 PADDQ	%XMM15,%XMM6

(220) 0x4341e8 PSLLQ	$0x3,%XMM6

(220) 0x4341ed PADDQ	%XMM5,%XMM6

(220) 0x4341f1 MOVQ	%XMM6,%R9

(220) 0x4341f6 PSHUFD	$-0x12,%XMM6,%XMM5

(220) 0x4341fb MOVQ	%XMM5,%R11

(220) 0x434200 MOVDQA	-0x120(%RBP),%XMM8

(220) 0x434209 MOVDQA	%XMM8,%XMM6

(220) 0x43420e ADDPD	%XMM14,%XMM4

(220) 0x434213 PSRLQ	$0x20,%XMM6

(220) 0x434218 PMULUDQ	%XMM0,%XMM6

(220) 0x43421c MOVDQA	%XMM8,%XMM5

(220) 0x434221 PMULUDQ	%XMM2,%XMM5

(220) 0x434225 PADDQ	%XMM6,%XMM5

(220) 0x434229 MOVDQA	%XMM8,%XMM6

(220) 0x43422e PMULUDQ	%XMM0,%XMM6

(220) 0x434232 PSLLQ	$0x20,%XMM5

(220) 0x434237 PADDQ	%XMM6,%XMM5

(220) 0x43423b MOVSD	(%RAX),%XMM6

(220) 0x43423f MOVHPD	(%RDX),%XMM6

(220) 0x434243 MOVAPD	-0x160(%RBP),%XMM8

(220) 0x43424c MULPD	%XMM8,%XMM6

(220) 0x434251 MOVQ	%XMM1,%RAX

(220) 0x434256 PSHUFD	$-0x12,%XMM1,%XMM1

(220) 0x43425b MULPD	%XMM6,%XMM4

(220) 0x43425f MOVDQA	%XMM5,%XMM6

(220) 0x434263 PADDQ	%XMM3,%XMM6

(220) 0x434267 PSLLQ	$0x3,%XMM6

(220) 0x43426c MOVQ	%XMM1,%RDX

(220) 0x434271 MOVQ	-0x38(%RBP),%XMM1

(220) 0x434276 PSHUFD	$0x44,%XMM1,%XMM1

(220) 0x43427b PADDQ	%XMM1,%XMM6

(220) 0x43427f MOVQ	%XMM6,%R10

(220) 0x434284 PSHUFD	$-0x12,%XMM6,%XMM6

(220) 0x434289 MOVQ	%XMM6,%R15

(220) 0x43428e MOVLPD	%XMM4,(%RSI)

(220) 0x434292 MOV	%RDI,%RSI

(220) 0x434295 MOVHPD	%XMM4,(%RBX)

(220) 0x434299 MOVSD	(%RAX),%XMM6

(220) 0x43429d PADDQ	%XMM15,%XMM5

(220) 0x4342a2 MOVHPD	(%RDX),%XMM6

(220) 0x4342a6 MOVSD	(%R9),%XMM4

(220) 0x4342ab MOVHPD	(%R11),%XMM4

(220) 0x4342b0 ADDPD	%XMM6,%XMM4

(220) 0x4342b4 MOVSD	(%R10),%XMM6

(220) 0x4342b9 PSLLQ	$0x3,%XMM5

(220) 0x4342be MOVHPD	(%R15),%XMM6

(220) 0x4342c3 PADDQ	%XMM1,%XMM5

(220) 0x4342c7 MOVQ	%XMM5,%RAX

(220) 0x4342cc PSHUFD	$-0x12,%XMM5,%XMM5

(220) 0x4342d1 MOVSD	(%RAX),%XMM1

(220) 0x4342d5 MOVQ	%XMM5,%RAX

(220) 0x4342da MOVHPD	(%RAX),%XMM1

(220) 0x4342de ADDPD	%XMM6,%XMM1

(220) 0x4342e2 MOVDQA	-0x110(%RBP),%XMM9

(220) 0x4342eb MOVDQA	%XMM9,%XMM5

(220) 0x4342f0 MOVDQA	%XMM9,%XMM6

(220) 0x4342f5 PSRLQ	$0x20,%XMM6

(220) 0x4342fa PMULUDQ	%XMM0,%XMM5

(220) 0x4342fe PMULUDQ	%XMM0,%XMM6

(220) 0x434302 PMULUDQ	%XMM9,%XMM2

(220) 0x434307 PADDQ	%XMM6,%XMM2

(220) 0x43430b ADDPD	%XMM4,%XMM1

(220) 0x43430f PADDQ	%XMM3,%XMM5

(220) 0x434313 PSLLQ	$0x20,%XMM2

(220) 0x434318 PADDQ	%XMM2,%XMM5

(220) 0x43431c MOVSD	(%R13),%XMM0

(220) 0x434322 MOVHPD	(%R14),%XMM0

(220) 0x434327 MULPD	%XMM8,%XMM0

(220) 0x43432c MULPD	%XMM0,%XMM1

(220) 0x434330 PSLLQ	$0x3,%XMM5

(220) 0x434335 MOVQ	-0x30(%RBP),%XMM0

(220) 0x43433a PSHUFD	$0x44,%XMM0,%XMM0

(220) 0x43433f PADDQ	%XMM5,%XMM0

(220) 0x434343 MOVQ	%XMM0,%RAX

(220) 0x434348 PSHUFD	$-0x12,%XMM0,%XMM0

(220) 0x43434d MOVQ	%XMM0,%RDX

(220) 0x434352 MOVLPD	%XMM1,(%RAX)

(220) 0x434356 MOVHPD	%XMM1,(%RDX)

(220) 0x43435a PADDQ	0x670ed(%RIP),%XMM13

(220) 0x434363 ADD	$0x2,%R8

(220) 0x434367 CMP	%RDI,%R8

(220) 0x43436a JB	433e40

0x434370 CMP	%RSI,-0xb0(%RBP)

0x434377 MOV	-0xa8(%RBP),%R9

0x43437e MOV	-0x80(%RBP),%R15

0x434382 MOV	-0x78(%RBP),%R11

0x434386 MOV	-0xa0(%RBP),%R10

0x43438d MOVAPD	-0x100(%RBP),%XMM2

0x434395 MOV	-0x60(%RBP),%RBX

0x434399 MOV	-0x68(%RBP),%R14

0x43439d MOV	-0x58(%RBP),%R13

0x4343a1 JNE	4343e7

0x4343a3 MOV	$0x4b80d0,%EDI

0x4343a8 MOV	-0x6c(%RBP),%ESI

0x4343ab ADD	$0x178,%RSP

0x4343b2 POP	%RBX

0x4343b3 POP	%R12

0x4343b5 POP	%R13

0x4343b7 POP	%R14

0x4343b9 POP	%R15

0x4343bb POP	%RBP

0x4343bc JMP	403050

0x4343c1 ADD	$0x178,%RSP

0x4343c8 POP	%RBX

0x4343c9 POP	%R12

0x4343cb POP	%R13

0x4343cd POP	%R14

0x4343cf POP	%R15

0x4343d1 POP	%RBP

0x4343d2 RET

0x4343d3 MOV	-0x60(%RBP),%RBX

0x4343d7 MOV	-0x68(%RBP),%R14

0x4343db MOV	-0x58(%RBP),%R13

0x4343df MOV	%RDX,%R15

0x4343e2 JMP	434514

0x4343e7 ADD	%RSI,%RCX

0x4343ea JMP	434514

0x4343ef NOP

(219) 0x4343f0 MOV	%RCX,%RAX

(219) 0x4343f3 XOR	%EDX,%EDX

(219) 0x4343f5 DIV	%R9

(219) 0x4343f8 LEA	(%RAX,%R11,1),%R8D

(219) 0x4343fc ADD	%R15D,%EDX

(219) 0x4343ff MOVSXD	%EDX,%RSI

(219) 0x434402 MOVSXD	%R8D,%RDX

(219) 0x434405 MOV	%RBX,%R8

(219) 0x434408 IMUL	%RDX,%R8

(219) 0x43440c ADD	%RSI,%R8

(219) 0x43440f MOVSD	(%R14,%R8,8),%XMM0

(219) 0x434415 MULSD	%XMM2,%XMM0

(219) 0x434419 ADD	%R11D,%EAX

(219) 0x43441c INC	%EAX

(219) 0x43441e CLTQ

(219) 0x434420 MOV	%R13,%R8

(219) 0x434423 IMUL	%RAX,%R8

(219) 0x434427 ADD	%RSI,%R8

(219) 0x43442a MOV	-0x50(%RBP),%RDI

(219) 0x43442e MOVSD	(%RDI,%R8,8),%XMM1

(219) 0x434434 MOV	%R13,%R8

(219) 0x434437 IMUL	%RDX,%R8

(219) 0x43443b ADD	%RSI,%R8

(219) 0x43443e ADDSD	(%RDI,%R8,8),%XMM1

(219) 0x434444 MOV	-0xe8(%RBP),%RDI

(219) 0x43444b MOV	%RDI,%R8

(219) 0x43444e IMUL	%RDX,%R8

(219) 0x434452 ADD	%RSI,%R8

(219) 0x434455 MOV	-0x48(%RBP),%R12

(219) 0x434459 ADDSD	(%R12,%R8,8),%XMM1

(219) 0x43445f IMUL	%RDI,%RAX

(219) 0x434463 ADD	%RSI,%RAX

(219) 0x434466 ADDSD	(%R12,%RAX,8),%XMM1

(219) 0x43446c MULSD	%XMM0,%XMM1

(219) 0x434470 MOV	-0xe0(%RBP),%RAX

(219) 0x434477 IMUL	%RDX,%RAX

(219) 0x43447b ADD	%RSI,%RAX

(219) 0x43447e MOV	-0xd8(%RBP),%RDI

(219) 0x434485 MOVSD	%XMM1,(%RDI,%RAX,8)

(219) 0x43448a MOV	-0xc8(%RBP),%RAX

(219) 0x434491 IMUL	%RDX,%RAX

(219) 0x434495 LEA	(%RAX,%RSI,1),%R8

(219) 0x434499 INC	%R8

(219) 0x43449c ADD	%RSI,%RAX

(219) 0x43449f MOV	-0x88(%RBP),%RDI

(219) 0x4344a6 MOVSD	(%RDI,%R8,8),%XMM0

(219) 0x4344ac ADDSD	(%RDI,%RAX,8),%XMM0

(219) 0x4344b1 MOV	-0xc0(%RBP),%RAX

(219) 0x4344b8 IMUL	%RDX,%RAX

(219) 0x4344bc LEA	(%RAX,%RSI,1),%R8

(219) 0x4344c0 MOV	-0x38(%RBP),%RDI

(219) 0x4344c4 ADDSD	(%RDI,%R8,8),%XMM0

(219) 0x4344ca ADD	%RSI,%RAX

(219) 0x4344cd INC	%RAX

(219) 0x4344d0 ADDSD	(%RDI,%RAX,8),%XMM0

(219) 0x4344d5 MOV	-0xd0(%RBP),%RAX

(219) 0x4344dc IMUL	%RDX,%RAX

(219) 0x4344e0 ADD	%RSI,%RAX

(219) 0x4344e3 MOV	-0x40(%RBP),%RDI

(219) 0x4344e7 MOVSD	(%RDI,%RAX,8),%XMM1

(219) 0x4344ec IMUL	-0xb8(%RBP),%RDX

(219) 0x4344f4 ADD	%RSI,%RDX

(219) 0x4344f7 MULSD	%XMM2,%XMM1

(219) 0x4344fb MULSD	%XMM1,%XMM0

(219) 0x4344ff MOV	-0x30(%RBP),%RAX

(219) 0x434503 MOVSD	%XMM0,(%RAX,%RDX,8)

(219) 0x434508 INC	%RCX

(219) 0x43450b CMP	%RCX,%R10

(219) 0x43450e JE	4343a3

(219) 0x434514 MOV	%RCX,%RAX

(219) 0x434517 SHR	$0x20,%RAX

(219) 0x43451b JNE	4343f0

(219) 0x434521 MOV	%ECX,%EAX

(219) 0x434523 XOR	%EDX,%EDX

(219) 0x434525 DIV	%R9D

(219) 0x434528 JMP	4343f8

0x43452d NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►100.00+	__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	flux_calc.cpp:36-41
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/flux_calc.cpp:36-41
/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h: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 30.33 to 12.00 cycles (2.53x 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 30.33 to 3.50 cycles (8.67x speedup).

Details

27% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

11% of SSE/AVX loads are used in vector version.
26% of SSE/AVX stores are used in vector version.
11% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX multiply instructions are used in vector version.
42% 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/flux_calc.cpp:36

Type of elements and instruction set

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

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

The binary function is composed of 1 FP arithmetical operations:

1: multiply

The binary function is loading 420 bytes (52 double precision FP elements). The binary function is storing 416 bytes (52 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	181
nb uops	182
loop length	835
used x86 registers	16
used mmx registers	0
used xmm registers	7
used ymm registers	0
used zmm registers	0
nb stack references	46

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	30.33 cycles
front end	30.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	7.00	12.00	21.67	21.67	26.00	12.00	7.00	26.00	26.00	26.00	7.00	21.67
cycles	7.00	12.00	21.67	21.67	26.00	12.00	7.00	26.00	26.00	26.00	7.00	21.67

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	30.33
Dispatch	26.00
Overall L1	30.33

Vectorization ratios

INT

all	25%
load	6%
store	22%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	11%
fma	NA (no fma vectorizable/vectorized instructions)
other	43%

all	50%
load	33%
store	100%
mul	0%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	27%
load	11%
store	26%
mul	0%
add-sub	11%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	42%

Vector efficiency ratios

INT

all	15%
load	12%
store	14%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	13%
fma	NA (no fma vectorizable/vectorized instructions)
other	17%

all	18%
load	16%
store	25%
mul	12%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

INT+FP

all	15%
load	13%
store	15%
mul	12%
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 30.33 cycles. At this rate:

7% of peak load performance is reached (13.85 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (13.71 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 30.33 to 26.00 cycles (1.17x speedup).

ASM code

In the binary file, the address of the function is: 433b80

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 $0x178,%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 %RCX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x58(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x48(%RBP),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
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 0x30(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x28(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x20(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x38(%RBP),%R11D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOVL $0,-0x70(%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 4343c1 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x841>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
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 %RSI,-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 %R9,-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 %RCX,-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 %R8,-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 (%RDI),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
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 -0x70(%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 $0x4b80b0,%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,-0x6c(%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	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 $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
MOV %R10,-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 %R11,-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%)
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
MOV -0x78(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x80(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CMP %R10,%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 4343a3 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x823>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R15,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RAX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOVSD -0x48(%RBP),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
SUB %R15D,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MULSD 0x677ad(%RIP),%XMM2	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
MOV (%R12),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x60(%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(%R12),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDX,-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 -0x50(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDX),%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 0x10(%RDX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,-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 (%R14),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%R14),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R8,-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 (%R13),%R8	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 -0x40(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDX),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDX),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12,-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 (%RBX),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RBX),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RBX,-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 -0x38(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDX),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDX),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R13,-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 -0x30(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDX),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
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%)
INC %R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R15,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R10,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SUB %RCX,%R15	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 $-0x2,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R15,-0xb0(%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 %R15,%RSI	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 %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%)
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 %RAX,-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 %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%)
MOV %R12,-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%)
MOV %RBX,-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%)
MOV %R13,-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%)
JE 4343d3 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x853>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R10,-0xa0(%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,-0xa8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVD %R9D,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
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 %R11D,%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%)
MOVD %EDX,%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,-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%)
MOVQ -0x60(%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,-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%)
MOVAPD %XMM2,-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%)
UNPCKLPD %XMM2,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
MOVAPD %XMM2,-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 -0x58(%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,%XMM10	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %RDI,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM7	1	0	0.50	0	0	0	0.50	0	0	0	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,-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 %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,-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 %R12,%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 %RBX,%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 %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,-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 %RCX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM13	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ 0x6760d(%RIP),%XMM13	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 %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
MOV %RAX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PXOR %XMM11,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
PCMPEQD %XMM12,%XMM12	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RSI,-0xb0(%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%)
MOV -0xa8(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x80(%RBP),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x78(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0xa0(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVAPD -0x100(%RBP),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOV -0x60(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JNE 4343e7 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x867>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x4b80d0,%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 -0x6c(%RBP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x178,%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
ADD $0x178,%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
MOV -0x60(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JMP 434514 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x994>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
ADD %RSI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JMP 434514 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x994>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOP	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

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	flux_calc.cpp:36-41
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/flux_calc.cpp:36-41
/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h: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

27% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

11% of SSE/AVX loads are used in vector version.
26% of SSE/AVX stores are used in vector version.
11% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX multiply instructions are used in vector version.
42% 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/flux_calc.cpp:36

Type of elements and instruction set

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

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

The binary function is composed of 1 FP arithmetical operations:

1: multiply

The binary function is loading 420 bytes (52 double precision FP elements). The binary function is storing 416 bytes (52 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	181
nb uops	182
loop length	835
used x86 registers	16
used mmx registers	0
used xmm registers	7
used ymm registers	0
used zmm registers	0
nb stack references	46

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	30.33 cycles
front end	30.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	7.00	12.00	21.67	21.67	26.00	12.00	7.00	26.00	26.00	26.00	7.00	21.67
cycles	7.00	12.00	21.67	21.67	26.00	12.00	7.00	26.00	26.00	26.00	7.00	21.67

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	30.33
Dispatch	26.00
Overall L1	30.33

Vectorization ratios

INT

all	25%
load	6%
store	22%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	11%
fma	NA (no fma vectorizable/vectorized instructions)
other	43%

all	50%
load	33%
store	100%
mul	0%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	27%
load	11%
store	26%
mul	0%
add-sub	11%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	42%

Vector efficiency ratios

INT

all	15%
load	12%
store	14%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	13%
fma	NA (no fma vectorizable/vectorized instructions)
other	17%

all	18%
load	16%
store	25%
mul	12%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

INT+FP

all	15%
load	13%
store	15%
mul	12%
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 30.33 cycles. At this rate:

7% of peak load performance is reached (13.85 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (13.71 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: 433b80

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 $0x178,%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 %RCX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x58(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x48(%RBP),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
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 0x30(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x28(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x20(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x38(%RBP),%R11D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOVL $0,-0x70(%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 4343c1 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x841>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
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 %RSI,-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 %R9,-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 %RCX,-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 %R8,-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 (%RDI),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
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 -0x70(%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 $0x4b80b0,%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,-0x6c(%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	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 $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
MOV %R10,-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 %R11,-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%)
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
MOV -0x78(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x80(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CMP %R10,%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 4343a3 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x823>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R15,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RAX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOVSD -0x48(%RBP),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
SUB %R15D,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MULSD 0x677ad(%RIP),%XMM2	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
MOV (%R12),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x60(%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(%R12),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDX,-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 -0x50(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDX),%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 0x10(%RDX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,-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 (%R14),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%R14),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R8,-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 (%R13),%R8	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 -0x40(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDX),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDX),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12,-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 (%RBX),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RBX),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RBX,-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 -0x38(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDX),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDX),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R13,-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 -0x30(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDX),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
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%)
INC %R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R15,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R10,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SUB %RCX,%R15	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 $-0x2,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R15,-0xb0(%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 %R15,%RSI	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 %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%)
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 %RAX,-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 %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%)
MOV %R12,-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%)
MOV %RBX,-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%)
MOV %R13,-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%)
JE 4343d3 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x853>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R10,-0xa0(%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,-0xa8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVD %R9D,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
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 %R11D,%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%)
MOVD %EDX,%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,-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%)
MOVQ -0x60(%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,-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%)
MOVAPD %XMM2,-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%)
UNPCKLPD %XMM2,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
MOVAPD %XMM2,-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 -0x58(%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,%XMM10	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %RDI,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM7	1	0	0.50	0	0	0	0.50	0	0	0	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,-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 %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,-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 %R12,%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 %RBX,%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 %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,-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 %RCX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM13	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ 0x6760d(%RIP),%XMM13	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 %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
MOV %RAX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PXOR %XMM11,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
PCMPEQD %XMM12,%XMM12	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RSI,-0xb0(%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%)
MOV -0xa8(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x80(%RBP),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x78(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0xa0(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVAPD -0x100(%RBP),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOV -0x60(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JNE 4343e7 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x867>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x4b80d0,%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 -0x6c(%RBP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x178,%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
ADD $0x178,%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
MOV -0x60(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JMP 434514 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x994>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
ADD %RSI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JMP 434514 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.extracted+0x994>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOP	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

Name	Coverage (%)	Time (s)
▼flux_calc_kernel(int, int, int, int, double, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D–	3.36	1.33
○Loop 220 - flux_calc.cpp:37-41 - exec	3.36	1.32
○Loop 219 - flux_calc.cpp:37-41 - 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

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

CALL instructions

Details

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