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

	Function: advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D<double>&, clover::Buffer1 ...	Module: exec	Source: advec_cell.cpp:208-217 [...]	Coverage (incl. loops): 2.79% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp: 208 - 217

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

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

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

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

211:         double pre_mass_s = density1(i, j) * pre_vol(i, j);

212:         double post_mass_s = pre_mass_s + mass_flux_y(i, j) - mass_flux_y(i + 0, j + 1);

213:         double post_ener_s = (energy1(i, j) * pre_mass_s + ener_flux(i, j) - ener_flux(i + 0, j + 1)) / post_mass_s;

214:         double advec_vol_s = pre_vol(i, j) + vol_flux_y(i, j) - vol_flux_y(i + 0, j + 1);

215:         density1(i, j) = post_mass_s / advec_vol_s;

216:         energy1(i, j) = post_ener_s;

217:       }

/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]; }

0x41d960 PUSH	%RBP

0x41d961 MOV	%RSP,%RBP

0x41d964 PUSH	%R15

0x41d966 PUSH	%R14

0x41d968 PUSH	%R13

0x41d96a PUSH	%R12

0x41d96c PUSH	%RBX

0x41d96d SUB	$0x188,%RSP

0x41d974 MOV	0x40(%RBP),%RAX

0x41d978 MOV	0x30(%RBP),%R10

0x41d97c MOV	0x28(%RBP),%R11

0x41d980 MOV	0x18(%RBP),%RBX

0x41d984 MOV	0x10(%RBP),%R14

0x41d988 MOV	0x20(%RBP),%R15D

0x41d98c MOVL	$0,-0x50(%RBP)

0x41d993 TEST	%RAX,%RAX

0x41d996 JS	41e070

0x41d99c MOV	%R8,%R12

0x41d99f MOV	%RDX,%R13

0x41d9a2 MOV	%RCX,-0x38(%RBP)

0x41d9a6 MOV	%R9,-0x30(%RBP)

0x41d9aa MOV	(%RDI),%ESI

0x41d9ac MOVQ	$0,-0x80(%RBP)

0x41d9b4 MOV	%RAX,-0x78(%RBP)

0x41d9b8 MOVQ	$0x1,-0xf0(%RBP)

0x41d9c3 SUB	$0x8,%RSP

0x41d9c7 LEA	-0xf0(%RBP),%RAX

0x41d9ce LEA	-0x50(%RBP),%RCX

0x41d9d2 LEA	-0x80(%RBP),%R8

0x41d9d6 LEA	-0x78(%RBP),%R9

0x41d9da MOV	$0x4b7430,%EDI

0x41d9df MOV	%ESI,-0x4c(%RBP)

0x41d9e2 MOV	$0x22,%EDX

0x41d9e7 PUSH	$0x1

0x41d9e9 PUSH	$0x1

0x41d9eb PUSH	%RAX

0x41d9ec MOV	%R15,-0x58(%RBP)

0x41d9f0 MOV	%R10,%R15

0x41d9f3 MOV	%R11,-0x48(%RBP)

0x41d9f7 CALL	4031f0 <__kmpc_for_static_init_8@plt>

0x41d9fc MOV	%R15,%RSI

0x41d9ff MOV	-0x58(%RBP),%R15

0x41da03 ADD	$0x20,%RSP

0x41da07 MOV	-0x80(%RBP),%RCX

0x41da0b MOV	-0x78(%RBP),%RDX

0x41da0f CMP	%RDX,%RCX

0x41da12 JA	41e052

0x41da18 MOV	%RDX,%RAX

0x41da1b MOV	-0x48(%RBP),%R8

0x41da1f SUB	%R8D,%ESI

0x41da22 MOV	(%R13),%RDX

0x41da26 MOV	0x10(%R13),%R13

0x41da2a MOV	(%R14),%RDI

0x41da2d MOV	%RDI,-0x60(%RBP)

0x41da31 MOV	0x10(%R14),%RDI

0x41da35 MOV	%RDI,-0x40(%RBP)

0x41da39 MOV	(%R12),%RDI

0x41da3d MOV	0x10(%R12),%R9

0x41da42 MOV	%R9,-0x70(%RBP)

0x41da46 MOV	-0x38(%RBP),%R9

0x41da4a MOV	(%R9),%R11

0x41da4d MOV	0x10(%R9),%R14

0x41da51 MOV	(%RBX),%R10

0x41da54 MOV	0x10(%RBX),%RBX

0x41da58 MOV	-0x30(%RBP),%R9

0x41da5c MOV	(%R9),%R12

0x41da5f MOV	0x10(%R9),%R9

0x41da63 MOV	%R9,-0x30(%RBP)

0x41da67 INC	%RAX

0x41da6a MOV	%RAX,-0xe0(%RBP)

0x41da71 MOV	%RAX,%R9

0x41da74 SUB	%RCX,%R9

0x41da77 MOV	$-0x2,%EAX

0x41da7c AND	%R9,%RAX

0x41da7f MOV	%RDI,-0xd0(%RBP)

0x41da86 MOV	%R14,-0x38(%RBP)

0x41da8a MOV	%R10,-0xc0(%RBP)

0x41da91 MOV	%RBX,-0x68(%RBP)

0x41da95 MOV	%R12,-0xb8(%RBP)

0x41da9c MOV	%RDX,-0xd8(%RBP)

0x41daa3 MOV	%R11,-0xc8(%RBP)

0x41daaa JE	41e082

0x41dab0 MOV	%R9,-0x88(%RBP)

0x41dab7 MOV	%RSI,-0x98(%RBP)

0x41dabe MOVD	%ESI,%XMM0

0x41dac2 PSHUFD	$0x44,%XMM0,%XMM2

0x41dac7 MOVD	%R15D,%XMM0

0x41dacc PSHUFD	$0x50,%XMM0,%XMM0

0x41dad1 MOVDQA	%XMM0,-0x1a0(%RBP)

0x41dad9 MOVQ	%R8,%XMM0

0x41dade PSHUFD	$0x44,%XMM0,%XMM0

0x41dae3 MOVDQA	%XMM0,-0x190(%RBP)

0x41daeb MOVQ	%RDX,%XMM0

0x41daf0 PSHUFD	$0x44,%XMM0,%XMM3

0x41daf5 MOVQ	-0x60(%RBP),%XMM0

0x41dafa PSHUFD	$0x44,%XMM0,%XMM4

0x41daff MOVQ	%RDI,%XMM0

0x41db04 PSHUFD	$0x44,%XMM0,%XMM0

0x41db09 MOVDQA	%XMM0,-0x150(%RBP)

0x41db11 MOVQ	%R11,%XMM0

0x41db16 PSHUFD	$0x44,%XMM0,%XMM0

0x41db1b MOVDQA	%XMM0,-0x160(%RBP)

0x41db23 MOVQ	%R10,%XMM0

0x41db28 PSHUFD	$0x44,%XMM0,%XMM0

0x41db2d MOVDQA	%XMM0,-0x140(%RBP)

0x41db35 MOVQ	%R12,%XMM0

0x41db3a MOVQ	%RCX,%XMM1

0x41db3f PSHUFD	$0x44,%XMM1,%XMM8

0x41db45 PADDQ	0x7d8e2(%RIP),%XMM8

0x41db4e PSHUFD	$0x44,%XMM0,%XMM9

0x41db54 XOR	%EDI,%EDI

0x41db56 MOVQ	%XMM2,-0xa8(%RBP)

0x41db5e MOVDQA	%XMM2,-0x1b0(%RBP)

0x41db66 PSHUFD	$-0x12,%XMM2,%XMM0

0x41db6b MOVQ	%XMM0,-0xa0(%RBP)

0x41db73 MOVDQA	%XMM3,-0x180(%RBP)

0x41db7b PSRLQ	$0x20,%XMM3

0x41db80 MOVDQA	%XMM3,-0x130(%RBP)

0x41db88 MOV	%R13,-0x90(%RBP)

0x41db8f MOVQ	%R13,%XMM0

0x41db94 PSHUFD	$0x44,%XMM0,%XMM0

0x41db99 MOVDQA	%XMM0,-0x120(%RBP)

0x41dba1 MOVDQA	%XMM4,-0x170(%RBP)

0x41dba9 PSRLQ	$0x20,%XMM4

0x41dbae MOVDQA	%XMM4,-0x110(%RBP)

0x41dbb6 MOVQ	-0x40(%RBP),%XMM0

0x41dbbb PSHUFD	$0x44,%XMM0,%XMM0

0x41dbc0 MOVDQA	%XMM0,-0x100(%RBP)

0x41dbc8 MOV	%RAX,-0xb0(%RBP)

0x41dbcf NOP

(146) 0x41dbd0 MOVQ	%XMM8,%RAX

(146) 0x41dbd5 XOR	%EDX,%EDX

(146) 0x41dbd7 DIVQ	-0xa8(%RBP)

(146) 0x41dbde MOV	%RAX,%RSI

(146) 0x41dbe1 PSHUFD	$-0x12,%XMM8,%XMM0

(146) 0x41dbe7 MOVQ	%XMM0,%RAX

(146) 0x41dbec XOR	%EDX,%EDX

(146) 0x41dbee DIVQ	-0xa0(%RBP)

(146) 0x41dbf5 MOVQ	%RSI,%XMM0

(146) 0x41dbfa MOVQ	%RAX,%XMM1

(146) 0x41dbff PUNPCKLQDQ	%XMM1,%XMM0

(146) 0x41dc03 PSHUFD	$-0x18,%XMM0,%XMM10

(146) 0x41dc09 PADDD	-0x1a0(%RBP),%XMM10

(146) 0x41dc12 PMULUDQ	-0x1b0(%RBP),%XMM0

(146) 0x41dc1a MOVDQA	%XMM8,%XMM3

(146) 0x41dc1f PSUBQ	%XMM0,%XMM3

(146) 0x41dc23 PADDQ	-0x190(%RBP),%XMM3

(146) 0x41dc2b PXOR	%XMM2,%XMM2

(146) 0x41dc2f PCMPGTD	%XMM10,%XMM2

(146) 0x41dc34 PSLLQ	$0x20,%XMM3

(146) 0x41dc39 MOVDQA	%XMM10,%XMM1

(146) 0x41dc3e PUNPCKLDQ	%XMM2,%XMM1

(146) 0x41dc42 MOVDQA	-0x180(%RBP),%XMM11

(146) 0x41dc4b MOVDQA	%XMM11,%XMM0

(146) 0x41dc50 PSHUFD	$-0x13,%XMM3,%XMM15

(146) 0x41dc56 PMULUDQ	%XMM1,%XMM0

(146) 0x41dc5a MOVDQA	-0x130(%RBP),%XMM4

(146) 0x41dc62 PMULUDQ	%XMM1,%XMM4

(146) 0x41dc66 MOVDQA	%XMM15,%XMM5

(146) 0x41dc6b PXOR	%XMM6,%XMM6

(146) 0x41dc6f PUNPCKLDQ	%XMM6,%XMM2

(146) 0x41dc73 MOVDQA	%XMM11,%XMM3

(146) 0x41dc78 PMULUDQ	%XMM2,%XMM3

(146) 0x41dc7c PADDQ	%XMM4,%XMM3

(146) 0x41dc80 MOVDQA	-0x170(%RBP),%XMM4

(146) 0x41dc88 MOVDQA	%XMM4,%XMM11

(146) 0x41dc8d PMULUDQ	%XMM1,%XMM11

(146) 0x41dc92 MOVDQA	-0x110(%RBP),%XMM12

(146) 0x41dc9b PSRAD	$0x1f,%XMM5

(146) 0x41dca0 PMULUDQ	%XMM1,%XMM12

(146) 0x41dca5 PMULUDQ	%XMM2,%XMM4

(146) 0x41dca9 PSLLQ	$0x20,%XMM3

(146) 0x41dcae PADDQ	%XMM12,%XMM4

(146) 0x41dcb3 MOVDQA	-0x150(%RBP),%XMM7

(146) 0x41dcbb MOVDQA	%XMM7,%XMM14

(146) 0x41dcc0 PMULUDQ	%XMM1,%XMM14

(146) 0x41dcc5 PUNPCKLDQ	%XMM5,%XMM15

(146) 0x41dcca MOVDQA	%XMM7,%XMM13

(146) 0x41dccf PSRLQ	$0x20,%XMM13

(146) 0x41dcd5 MOVDQA	%XMM13,%XMM5

(146) 0x41dcda PADDQ	%XMM0,%XMM3

(146) 0x41dcde PMULUDQ	%XMM1,%XMM5

(146) 0x41dce2 MOVDQA	%XMM7,%XMM12

(146) 0x41dce7 PMULUDQ	%XMM2,%XMM12

(146) 0x41dcec PSLLQ	$0x20,%XMM4

(146) 0x41dcf1 PADDQ	%XMM5,%XMM12

(146) 0x41dcf6 PSLLQ	$0x20,%XMM12

(146) 0x41dcfc MOVQ	-0x70(%RBP),%XMM0

(146) 0x41dd01 PADDQ	%XMM11,%XMM4

(146) 0x41dd06 PSHUFD	$0x44,%XMM0,%XMM11

(146) 0x41dd0c PSUBD	0x7d8ab(%RIP),%XMM10

(146) 0x41dd15 PXOR	%XMM0,%XMM0

(146) 0x41dd19 PADDQ	%XMM14,%XMM12

(146) 0x41dd1e PCMPGTD	%XMM10,%XMM0

(146) 0x41dd23 PUNPCKLDQ	%XMM0,%XMM10

(146) 0x41dd28 PMULUDQ	%XMM10,%XMM13

(146) 0x41dd2d PADDQ	%XMM15,%XMM12

(146) 0x41dd32 PUNPCKLDQ	%XMM6,%XMM0

(146) 0x41dd36 MOVDQA	%XMM7,%XMM14

(146) 0x41dd3b PMULUDQ	%XMM0,%XMM14

(146) 0x41dd40 PSLLQ	$0x3,%XMM12

(146) 0x41dd46 PADDQ	%XMM13,%XMM14

(146) 0x41dd4b PMULUDQ	%XMM10,%XMM7

(146) 0x41dd50 PADDQ	%XMM11,%XMM12

(146) 0x41dd55 PSLLQ	$0x20,%XMM14

(146) 0x41dd5b PADDQ	%XMM15,%XMM7

(146) 0x41dd60 PADDQ	%XMM14,%XMM7

(146) 0x41dd65 PSLLQ	$0x3,%XMM7

(146) 0x41dd6a MOVDQA	-0x160(%RBP),%XMM14

(146) 0x41dd73 MOVDQA	%XMM14,%XMM13

(146) 0x41dd78 PSRLQ	$0x20,%XMM13

(146) 0x41dd7e PMULUDQ	%XMM1,%XMM13

(146) 0x41dd83 PADDQ	%XMM11,%XMM7

(146) 0x41dd88 MOVDQA	%XMM14,%XMM11

(146) 0x41dd8d PMULUDQ	%XMM2,%XMM11

(146) 0x41dd92 PADDQ	%XMM13,%XMM11

(146) 0x41dd97 MOVDQA	%XMM14,%XMM13

(146) 0x41dd9c PMULUDQ	%XMM1,%XMM13

(146) 0x41dda1 PSLLQ	$0x20,%XMM11

(146) 0x41dda7 PADDQ	%XMM13,%XMM11

(146) 0x41ddac PADDQ	%XMM15,%XMM3

(146) 0x41ddb1 PSLLQ	$0x3,%XMM3

(146) 0x41ddb6 PADDQ	-0x120(%RBP),%XMM3

(146) 0x41ddbe MOVQ	%XMM3,%RSI

(146) 0x41ddc3 PSHUFD	$-0x12,%XMM3,%XMM3

(146) 0x41ddc8 PADDQ	%XMM15,%XMM4

(146) 0x41ddcd PSLLQ	$0x3,%XMM4

(146) 0x41ddd2 PADDQ	-0x100(%RBP),%XMM4

(146) 0x41ddda MOVQ	%XMM4,%RBX

(146) 0x41dddf PSHUFD	$-0x12,%XMM4,%XMM4

(146) 0x41dde4 MOVQ	%XMM12,-0xe8(%RBP)

(146) 0x41dded PSHUFD	$-0x12,%XMM12,%XMM12

(146) 0x41ddf3 MOVQ	%XMM3,%RDX

(146) 0x41ddf8 PADDQ	%XMM15,%XMM11

(146) 0x41ddfd PSLLQ	$0x3,%XMM11

(146) 0x41de03 MOVQ	-0x38(%RBP),%XMM3

(146) 0x41de08 MOVQ	%XMM4,%R11

(146) 0x41de0d PSHUFD	$0x44,%XMM3,%XMM4

(146) 0x41de12 PADDQ	%XMM11,%XMM4

(146) 0x41de17 MOVDQA	-0x140(%RBP),%XMM6

(146) 0x41de1f MOVDQA	%XMM6,%XMM3

(146) 0x41de23 MOVQ	%XMM12,%R9

(146) 0x41de28 PSRLQ	$0x20,%XMM3

(146) 0x41de2d MOVDQA	%XMM3,%XMM12

(146) 0x41de32 MOVDQA	%XMM6,%XMM11

(146) 0x41de37 PMULUDQ	%XMM1,%XMM12

(146) 0x41de3c PMULUDQ	%XMM2,%XMM11

(146) 0x41de41 PADDQ	%XMM12,%XMM11

(146) 0x41de46 MOVDQA	%XMM6,%XMM12

(146) 0x41de4b PMULUDQ	%XMM1,%XMM12

(146) 0x41de50 PSLLQ	$0x20,%XMM11

(146) 0x41de56 PADDQ	%XMM12,%XMM11

(146) 0x41de5b MOVDQA	%XMM6,%XMM12

(146) 0x41de60 PMULUDQ	%XMM10,%XMM3

(146) 0x41de65 PMULUDQ	%XMM0,%XMM12

(146) 0x41de6a PADDQ	%XMM3,%XMM12

(146) 0x41de6f MOVDQA	%XMM6,%XMM3

(146) 0x41de73 PMULUDQ	%XMM10,%XMM3

(146) 0x41de78 PSLLQ	$0x20,%XMM12

(146) 0x41de7e PADDQ	%XMM15,%XMM3

(146) 0x41de83 PADDQ	%XMM12,%XMM3

(146) 0x41de88 MOVQ	%XMM4,%R13

(146) 0x41de8d PSHUFD	$-0x12,%XMM4,%XMM4

(146) 0x41de92 PADDQ	%XMM15,%XMM11

(146) 0x41de97 PSLLQ	$0x3,%XMM11

(146) 0x41de9d MOVQ	%XMM4,%R8

(146) 0x41dea2 MOVQ	-0x68(%RBP),%XMM4

(146) 0x41dea7 PSHUFD	$0x44,%XMM4,%XMM4

(146) 0x41deac PADDQ	%XMM4,%XMM11

(146) 0x41deb1 MOVQ	%XMM11,%R12

(146) 0x41deb6 PSHUFD	$-0x12,%XMM11,%XMM11

(146) 0x41debc PSLLQ	$0x3,%XMM3

(146) 0x41dec1 PADDQ	%XMM4,%XMM3

(146) 0x41dec5 MOVQ	%XMM11,%R15

(146) 0x41deca MOVDQA	%XMM9,%XMM11

(146) 0x41decf MOVDQA	%XMM9,%XMM4

(146) 0x41ded4 PSRLQ	$0x20,%XMM4

(146) 0x41ded9 PMULUDQ	%XMM1,%XMM11

(146) 0x41dede PMULUDQ	%XMM4,%XMM1

(146) 0x41dee2 PMULUDQ	%XMM9,%XMM2

(146) 0x41dee7 PADDQ	%XMM1,%XMM2

(146) 0x41deeb PSLLQ	$0x20,%XMM2

(146) 0x41def0 PADDQ	%XMM11,%XMM2

(146) 0x41def5 MOVDQA	%XMM9,%XMM1

(146) 0x41defa PMULUDQ	%XMM10,%XMM1

(146) 0x41deff PADDQ	%XMM15,%XMM2

(146) 0x41df04 PMULUDQ	%XMM10,%XMM4

(146) 0x41df09 MOVQ	-0x30(%RBP),%XMM10

(146) 0x41df0f PSHUFD	$0x44,%XMM10,%XMM10

(146) 0x41df15 PSLLQ	$0x3,%XMM2

(146) 0x41df1a PADDQ	%XMM10,%XMM2

(146) 0x41df1f MOVQ	%XMM2,%R14

(146) 0x41df24 PSHUFD	$-0x12,%XMM2,%XMM2

(146) 0x41df29 MOVQ	%XMM2,%RAX

(146) 0x41df2e MOVSD	(%RBX),%XMM11

(146) 0x41df33 MOVQ	%XMM7,%RBX

(146) 0x41df38 PSHUFD	$-0x12,%XMM7,%XMM2

(146) 0x41df3d MOVQ	%XMM2,%R10

(146) 0x41df42 MOVHPD	(%R11),%XMM11

(146) 0x41df47 MOVQ	%XMM3,%R11

(146) 0x41df4c PSHUFD	$-0x12,%XMM3,%XMM3

(146) 0x41df51 PMULUDQ	%XMM9,%XMM0

(146) 0x41df56 PADDQ	%XMM4,%XMM0

(146) 0x41df5a MOVSD	(%R14),%XMM2

(146) 0x41df5f MOVQ	%XMM3,%R14

(146) 0x41df64 MOVHPD	(%RAX),%XMM2

(146) 0x41df68 PADDQ	%XMM15,%XMM1

(146) 0x41df6d MOVSD	(%RSI),%XMM4

(146) 0x41df71 MOVHPD	(%RDX),%XMM4

(146) 0x41df75 MULPD	%XMM11,%XMM4

(146) 0x41df7a ADDPD	%XMM11,%XMM2

(146) 0x41df7f MOV	-0xe8(%RBP),%RAX

(146) 0x41df86 MOVSD	(%RAX),%XMM3

(146) 0x41df8a MOVHPD	(%R9),%XMM3

(146) 0x41df8f PSLLQ	$0x20,%XMM0

(146) 0x41df94 PADDQ	%XMM0,%XMM1

(146) 0x41df98 PSLLQ	$0x3,%XMM1

(146) 0x41df9d PADDQ	%XMM10,%XMM1

(146) 0x41dfa2 ADDPD	%XMM4,%XMM3

(146) 0x41dfa6 MOVSD	(%R13),%XMM0

(146) 0x41dfac MOVHPD	(%R8),%XMM0

(146) 0x41dfb1 MULPD	%XMM4,%XMM0

(146) 0x41dfb5 MOVSD	(%RBX),%XMM4

(146) 0x41dfb9 MOVHPD	(%R10),%XMM4

(146) 0x41dfbe SUBPD	%XMM4,%XMM3

(146) 0x41dfc2 MOVSD	(%R12),%XMM4

(146) 0x41dfc8 MOVHPD	(%R15),%XMM4

(146) 0x41dfcd ADDPD	%XMM0,%XMM4

(146) 0x41dfd1 MOVSD	(%R11),%XMM0

(146) 0x41dfd6 MOVHPD	(%R14),%XMM0

(146) 0x41dfdb SUBPD	%XMM0,%XMM4

(146) 0x41dfdf MOVQ	%XMM1,%RAX

(146) 0x41dfe4 PSHUFD	$-0x12,%XMM1,%XMM0

(146) 0x41dfe9 MOVQ	%XMM0,%R9

(146) 0x41dfee MOVSD	(%RAX),%XMM0

(146) 0x41dff2 MOV	-0xb0(%RBP),%RAX

(146) 0x41dff9 MOVHPD	(%R9),%XMM0

(146) 0x41dffe SUBPD	%XMM0,%XMM2

(146) 0x41e002 DIVPD	%XMM3,%XMM4

(146) 0x41e006 DIVPD	%XMM2,%XMM3

(146) 0x41e00a MOVLPD	%XMM3,(%RSI)

(146) 0x41e00e MOVHPD	%XMM3,(%RDX)

(146) 0x41e012 MOVLPD	%XMM4,(%R13)

(146) 0x41e018 MOVHPD	%XMM4,(%R8)

(146) 0x41e01d PADDQ	0x7d42a(%RIP),%XMM8

(146) 0x41e026 ADD	$0x2,%RDI

(146) 0x41e02a CMP	%RAX,%RDI

(146) 0x41e02d JB	41dbd0

0x41e033 CMP	%RAX,-0x88(%RBP)

0x41e03a MOV	-0x98(%RBP),%RSI

0x41e041 MOV	-0x58(%RBP),%R15

0x41e045 MOV	-0x90(%RBP),%R13

0x41e04c MOV	-0x40(%RBP),%R12

0x41e050 JNE	41e08b

0x41e052 MOV	$0x4b7450,%EDI

0x41e057 MOV	-0x4c(%RBP),%ESI

0x41e05a ADD	$0x188,%RSP

0x41e061 POP	%RBX

0x41e062 POP	%R12

0x41e064 POP	%R13

0x41e066 POP	%R14

0x41e068 POP	%R15

0x41e06a POP	%RBP

0x41e06b JMP	403050

0x41e070 ADD	$0x188,%RSP

0x41e077 POP	%RBX

0x41e078 POP	%R12

0x41e07a POP	%R13

0x41e07c POP	%R14

0x41e07e POP	%R15

0x41e080 POP	%RBP

0x41e081 RET

0x41e082 MOV	-0x40(%RBP),%R12

0x41e086 JMP	41e1a8

0x41e08b ADD	%RAX,%RCX

0x41e08e JMP	41e1a8

0x41e093 NOPW	%CS:(%RAX,%RAX,1)

(145) 0x41e0a0 MOV	%RCX,%RAX

(145) 0x41e0a3 XOR	%EDX,%EDX

(145) 0x41e0a5 MOV	%RSI,%R14

(145) 0x41e0a8 DIV	%RSI

(145) 0x41e0ab MOV	-0x48(%RBP),%RSI

(145) 0x41e0af LEA	(%RAX,%R15,1),%EDI

(145) 0x41e0b3 ADD	%ESI,%EDX

(145) 0x41e0b5 MOVSXD	%EDX,%RSI

(145) 0x41e0b8 MOVSXD	%EDI,%RDI

(145) 0x41e0bb MOV	-0xd8(%RBP),%RDX

(145) 0x41e0c2 IMUL	%RDI,%RDX

(145) 0x41e0c6 ADD	%RSI,%RDX

(145) 0x41e0c9 MOV	-0x60(%RBP),%R8

(145) 0x41e0cd IMUL	%RDI,%R8

(145) 0x41e0d1 ADD	%RSI,%R8

(145) 0x41e0d4 MOVSD	(%R12,%R8,8),%XMM1

(145) 0x41e0da MOVSD	(%R13,%RDX,8),%XMM0

(145) 0x41e0e1 MULSD	%XMM1,%XMM0

(145) 0x41e0e5 MOV	-0xd0(%RBP),%R9

(145) 0x41e0ec MOV	%R9,%R8

(145) 0x41e0ef IMUL	%RDI,%R8

(145) 0x41e0f3 ADD	%RSI,%R8

(145) 0x41e0f6 MOV	-0x70(%RBP),%R11

(145) 0x41e0fa MOVSD	(%R11,%R8,8),%XMM2

(145) 0x41e100 ADDSD	%XMM0,%XMM2

(145) 0x41e104 ADD	%R15D,%EAX

(145) 0x41e107 INC	%EAX

(145) 0x41e109 CLTQ

(145) 0x41e10b MOV	%R9,%R8

(145) 0x41e10e IMUL	%RAX,%R8

(145) 0x41e112 ADD	%RSI,%R8

(145) 0x41e115 SUBSD	(%R11,%R8,8),%XMM2

(145) 0x41e11b MOV	-0xc8(%RBP),%R8

(145) 0x41e122 IMUL	%RDI,%R8

(145) 0x41e126 ADD	%RSI,%R8

(145) 0x41e129 MOV	-0x38(%RBP),%R11

(145) 0x41e12d MULSD	(%R11,%R8,8),%XMM0

(145) 0x41e133 MOV	-0xc0(%RBP),%R10

(145) 0x41e13a MOV	%R10,%R9

(145) 0x41e13d IMUL	%RDI,%R9

(145) 0x41e141 ADD	%RSI,%R9

(145) 0x41e144 MOV	-0x68(%RBP),%RBX

(145) 0x41e148 ADDSD	(%RBX,%R9,8),%XMM0

(145) 0x41e14e IMUL	%RAX,%R10

(145) 0x41e152 ADD	%RSI,%R10

(145) 0x41e155 SUBSD	(%RBX,%R10,8),%XMM0

(145) 0x41e15b MOV	-0xb8(%RBP),%R9

(145) 0x41e162 IMUL	%R9,%RDI

(145) 0x41e166 ADD	%RSI,%RDI

(145) 0x41e169 MOV	-0x30(%RBP),%R10

(145) 0x41e16d ADDSD	(%R10,%RDI,8),%XMM1

(145) 0x41e173 IMUL	%R9,%RAX

(145) 0x41e177 ADD	%RSI,%RAX

(145) 0x41e17a SUBSD	(%R10,%RAX,8),%XMM1

(145) 0x41e180 DIVSD	%XMM2,%XMM0

(145) 0x41e184 DIVSD	%XMM1,%XMM2

(145) 0x41e188 MOVSD	%XMM2,(%R13,%RDX,8)

(145) 0x41e18f MOVSD	%XMM0,(%R11,%R8,8)

(145) 0x41e195 INC	%RCX

(145) 0x41e198 CMP	%RCX,-0xe0(%RBP)

(145) 0x41e19f MOV	%R14,%RSI

(145) 0x41e1a2 JE	41e052

(145) 0x41e1a8 MOV	%RCX,%RAX

(145) 0x41e1ab SHR	$0x20,%RAX

(145) 0x41e1af JNE	41e0a0

(145) 0x41e1b5 MOV	%ECX,%EAX

(145) 0x41e1b7 XOR	%EDX,%EDX

(145) 0x41e1b9 MOV	%RSI,%R14

(145) 0x41e1bc DIV	%ESI

(145) 0x41e1be JMP	41e0ab

0x41e1c3 NOPW	%CS:(%RAX,%RAX,1)

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	advec_cell.cpp:208-217
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:208-217
/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 26.83 to 11.50 cycles (2.33x 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 26.83 to 3.37 cycles (7.95x speedup).

Details

30% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

5% of SSE/AVX loads are used in vector version.
30% of SSE/AVX stores are used in vector version.
14% of SSE/AVX addition or subtraction instructions are used in vector version.
48% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

CALL instructions

Detected function call instructions.

Details

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

__kmpc_for_static_init_8@plt: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:208

Type of elements and instruction set

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 276 bytes. The binary function is storing 400 bytes.

General properties

nb instructions	160
nb uops	161
loop length	746
used x86 registers	16
used mmx registers	0
used xmm registers	7
used ymm registers	0
used zmm registers	0
nb stack references	43

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	26.83 cycles
front end	26.83 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	7.30	11.50	16.00	16.00	24.50	11.50	7.30	24.50	24.50	24.50	7.40	16.00
cycles	7.30	11.50	16.00	16.00	24.50	11.50	7.30	24.50	24.50	24.50	7.40	16.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	26.83
Dispatch	24.50
Overall L1	26.83

Vectorization ratios

all	30%
load	5%
store	30%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	14%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	48%

Vector efficiency ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 26.83 cycles. At this rate:

5% of peak load performance is reached (10.29 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.91 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 26.83 to 24.50 cycles (1.10x speedup).

ASM code

In the binary file, the address of the function is: 41d960

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 $0x188,%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 0x40(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%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 0x28(%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 0x18(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x20(%RBP),%R15D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOVL $0,-0x50(%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 41e070 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x710>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R8,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,-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,-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 (%RDI),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOVQ $0,-0x80(%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,-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%)
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 -0x50(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x80(%RBP),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x78(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x4b7430,%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,-0x4c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %R15,-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 %R10,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R11,-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%)
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 %R15,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x58(%RBP),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x80(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CMP %RDX,%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 41e052 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x6f2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RDX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x48(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
SUB %R8D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV (%R13),%RDX	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),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
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 %RDI,-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(%R14),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,-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 (%R12),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%R12),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x38(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R9),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%R9),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RBX),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%RBX),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x30(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R9),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%R9),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,-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 %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-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,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %RCX,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $-0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
AND %R9,%RAX	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,-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 %R14,-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 %R10,-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 %RBX,-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 %R12,-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%)
MOV %RDX,-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 %R11,-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%)
JE 41e082 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x722>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R9,-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 %RSI,-0x98(%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 %ESI,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
PSHUFD $0x44,%XMM0,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVD %R15D,%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,-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%)
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,-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%)
MOVQ %RDX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
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,%XMM4	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,%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 %R11,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-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 %R10,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x140(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R12,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
MOVQ %RCX,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM1,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ 0x7d8e2(%RIP),%XMM8	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%)
PSHUFD $0x44,%XMM0,%XMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVQ %XMM2,-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%)
MOVDQA %XMM2,-0x1b0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PSHUFD $-0x12,%XMM2,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,-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%)
MOVDQA %XMM3,-0x180(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PSRLQ $0x20,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVDQA %XMM3,-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%)
MOV %R13,-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 %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,-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%)
MOVDQA %XMM4,-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%)
PSRLQ $0x20,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVDQA %XMM4,-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 -0x40(%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,-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%)
MOV %RAX,-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%)
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,-0x88(%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 -0x98(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x58(%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 -0x90(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x40(%RBP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JNE 41e08b <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x72b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x4b7450,%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 -0x4c(%RBP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
ADD $0x188,%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 $0x188,%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 -0x40(%RBP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JMP 41e1a8 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x848>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
ADD %RAX,%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 41e1a8 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x848>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

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

Source file and lines	advec_cell.cpp:208-217
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:208-217
/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

30% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

5% of SSE/AVX loads are used in vector version.
30% of SSE/AVX stores are used in vector version.
14% of SSE/AVX addition or subtraction instructions are used in vector version.
48% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

CALL instructions

Detected function call instructions.

Details

__kmpc_for_static_init_8@plt: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:208

Type of elements and instruction set

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 276 bytes. The binary function is storing 400 bytes.

General properties

nb instructions	160
nb uops	161
loop length	746
used x86 registers	16
used mmx registers	0
used xmm registers	7
used ymm registers	0
used zmm registers	0
nb stack references	43

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	26.83 cycles
front end	26.83 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	7.30	11.50	16.00	16.00	24.50	11.50	7.30	24.50	24.50	24.50	7.40	16.00
cycles	7.30	11.50	16.00	16.00	24.50	11.50	7.30	24.50	24.50	24.50	7.40	16.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	26.83
Dispatch	24.50
Overall L1	26.83

Vectorization ratios

all	30%
load	5%
store	30%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	14%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	48%

Vector efficiency ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 26.83 cycles. At this rate:

5% of peak load performance is reached (10.29 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.91 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: 41d960

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 $0x188,%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 0x40(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%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 0x28(%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 0x18(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x20(%RBP),%R15D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOVL $0,-0x50(%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 41e070 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x710>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R8,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,-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,-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 (%RDI),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOVQ $0,-0x80(%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,-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%)
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 -0x50(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x80(%RBP),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x78(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x4b7430,%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,-0x4c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %R15,-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 %R10,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R11,-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%)
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 %R15,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x58(%RBP),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x80(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CMP %RDX,%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 41e052 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x6f2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RDX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x48(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
SUB %R8D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV (%R13),%RDX	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),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
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 %RDI,-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(%R14),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,-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 (%R12),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%R12),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x38(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R9),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%R9),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RBX),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x10(%RBX),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x30(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R9),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%R9),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,-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 %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-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,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %RCX,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $-0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
AND %R9,%RAX	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,-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 %R14,-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 %R10,-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 %RBX,-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 %R12,-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%)
MOV %RDX,-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 %R11,-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%)
JE 41e082 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x722>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R9,-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 %RSI,-0x98(%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 %ESI,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
PSHUFD $0x44,%XMM0,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVD %R15D,%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,-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%)
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,-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%)
MOVQ %RDX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
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,%XMM4	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,%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 %R11,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-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 %R10,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVDQA %XMM0,-0x140(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ %R12,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
MOVQ %RCX,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM1,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ 0x7d8e2(%RIP),%XMM8	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%)
PSHUFD $0x44,%XMM0,%XMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVQ %XMM2,-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%)
MOVDQA %XMM2,-0x1b0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PSHUFD $-0x12,%XMM2,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,-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%)
MOVDQA %XMM3,-0x180(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PSRLQ $0x20,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVDQA %XMM3,-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%)
MOV %R13,-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 %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,-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%)
MOVDQA %XMM4,-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%)
PSRLQ $0x20,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVDQA %XMM4,-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 -0x40(%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,-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%)
MOV %RAX,-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%)
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,-0x88(%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 -0x98(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x58(%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 -0x90(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x40(%RBP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JNE 41e08b <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x72b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x4b7450,%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 -0x4c(%RBP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
ADD $0x188,%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 $0x188,%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 -0x40(%RBP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JMP 41e1a8 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x848>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
ADD %RAX,%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 41e1a8 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted+0x848>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D&, clover::Buffer1D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D–	2.79	1.10
○Loop 146 - advec_cell.cpp:209-217 - exec	2.79	1.10
○Loop 145 - advec_cell.cpp:209-217 - exec	0.00	0.01

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code