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 .omp

	Function: advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D<double>&, clover::Buffer1 ...	Module: exec	Source: advec_cell.cpp:208-216 [...]	Coverage (incl. loops): 3.34% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp: 208 - 216

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

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;

/home/eoseret/qaas_runs_ZEN5/173-937-4090/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]; }

0x233630 PUSH	%RBP

0x233631 MOV	%RSP,%RBP

0x233634 PUSH	%R15

0x233636 PUSH	%R14

0x233638 PUSH	%R13

0x23363a PUSH	%R12

0x23363c PUSH	%RBX

0x23363d SUB	$0xc8,%RSP

0x233644 MOV	(%RDX),%EAX

0x233646 MOV	(%RCX),%EBX

0x233648 INC	%EAX

0x23364a ADD	$0x2,%EBX

0x23364d MOV	%RAX,-0xa8(%RBP)

0x233654 SUB	%EAX,%EBX

0x233656 JLE	233a36

0x23365c MOV	(%R8),%R14D

0x23365f MOV	(%R9),%R15D

0x233662 INC	%R14D

0x233665 ADD	$0x2,%R15D

0x233669 CMP	%R14D,%R15D

0x23366c JLE	233a36

0x233672 SUB	%R14D,%R15D

0x233675 IMUL	%R15,%RBX

0x233679 DEC	%RBX

0x23367c MOVQ	$0,-0xb0(%RBP)

0x233687 MOV	%RBX,-0x48(%RBP)

0x23368b MOVQ	$0x1,-0xe8(%RBP)

0x233696 MOVL	$0,-0x50(%RBP)

0x23369d MOV	(%RDI),%ESI

0x23369f SUB	$0x8,%RSP

0x2336a3 LEA	-0xe8(%RBP),%RAX

0x2336aa LEA	0x2aabf(%RIP),%RDI

0x2336b1 LEA	-0x50(%RBP),%RCX

0x2336b5 LEA	-0xb0(%RBP),%R8

0x2336bc LEA	-0x48(%RBP),%R9

0x2336c0 MOV	%ESI,-0x4c(%RBP)

0x2336c3 MOV	$0x22,%EDX

0x2336c8 PUSH	$0x1

0x2336ca PUSH	$0x1

0x2336cc PUSH	%RAX

0x2336cd CALL	25ccf0 <@plt_start@+0x530>

0x2336d2 ADD	$0x20,%RSP

0x2336d6 MOV	-0x48(%RBP),%RAX

0x2336da CMP	%RBX,%RAX

0x2336dd CMOVL	%RAX,%RBX

0x2336e1 MOV	%RBX,-0x48(%RBP)

0x2336e5 MOV	-0xb0(%RBP),%RSI

0x2336ec CMP	%RBX,%RSI

0x2336ef JG	233a27

0x2336f5 MOV	0x38(%RBP),%RAX

0x2336f9 MOV	0x30(%RBP),%RCX

0x2336fd MOV	0x28(%RBP),%RDX

0x233701 MOV	0x20(%RBP),%RDI

0x233705 MOV	0x18(%RBP),%R8

0x233709 MOV	0x10(%RBP),%R9

0x23370d MOV	(%R9),%R10

0x233710 MOV	0x10(%R9),%R12

0x233714 MOV	(%R8),%R9

0x233717 MOV	0x10(%R8),%R8

0x23371b MOV	%R8,-0xa0(%RBP)

0x233722 MOV	(%RDI),%R8

0x233725 MOV	%R8,-0x98(%RBP)

0x23372c MOV	0x10(%RDI),%RDI

0x233730 MOV	%RDI,-0x90(%RBP)

0x233737 MOV	(%RDX),%RDI

0x23373a MOV	%RDI,-0x88(%RBP)

0x233741 MOV	0x10(%RDX),%RDX

0x233745 MOV	%RDX,-0x80(%RBP)

0x233749 MOV	(%RCX),%RDX

0x23374c MOV	%RDX,-0x78(%RBP)

0x233750 MOV	0x10(%RCX),%RCX

0x233754 MOV	%RCX,-0x70(%RBP)

0x233758 MOV	(%RAX),%RCX

0x23375b MOV	%RCX,-0x68(%RBP)

0x23375f MOV	0x10(%RAX),%RAX

0x233763 MOV	%RAX,-0x60(%RBP)

0x233767 MOV	%RBX,%RAX

0x23376a SUB	%RSI,%RAX

0x23376d INC	%RAX

0x233770 CMP	$0x2,%RAX

0x233774 MOV	%R10,-0x40(%RBP)

0x233778 MOV	%R9,-0x38(%RBP)

0x23377c JAE	233786

0x23377e MOV	%RSI,%RCX

0x233781 JMP	233b5d

0x233786 MOV	%R12,-0x58(%RBP)

0x23378a MOV	%R14D,-0x2c(%RBP)

0x23378e MOV	%RAX,-0xc0(%RBP)

0x233795 AND	$-0x2,%RAX

0x233799 LEA	(%RSI,%RAX,1),%RCX

0x23379d MOV	%RCX,-0xc8(%RBP)

0x2337a4 MOV	%RAX,-0xb8(%RBP)

0x2337ab MOV	%RAX,%RDX

0x2337ae MOV	%RBX,-0xd8(%RBP)

0x2337b5 MOV	%R15,-0xd0(%RBP)

0x2337bc JMP	2339b4

0x2337c1 NOPW	%CS:(%RAX,%RAX,1)

(158) 0x2337d0 CQTO

(158) 0x2337d2 IDIV	%R15

(158) 0x2337d5 MOV	-0xa8(%RBP),%R14

(158) 0x2337dc LEA	(%R14,%RCX,1),%R15D

(158) 0x2337e0 LEA	(%R14,%RAX,1),%R13D

(158) 0x2337e4 ADD	%R11D,%R8D

(158) 0x2337e7 ADD	%R11D,%EDX

(158) 0x2337ea MOVSXD	%R8D,%R11

(158) 0x2337ed MOVSXD	%EDX,%RBX

(158) 0x2337f0 MOVSXD	%R15D,%R12

(158) 0x2337f3 MOVSXD	%R13D,%R15

(158) 0x2337f6 MOV	-0x40(%RBP),%R8

(158) 0x2337fa MOV	%R8,%RDX

(158) 0x2337fd IMUL	%R12,%RDX

(158) 0x233801 MOV	-0x38(%RBP),%R9

(158) 0x233805 MOV	%R9,%R13

(158) 0x233808 IMUL	%R12,%R13

(158) 0x23380c ADD	%R11,%R13

(158) 0x23380f MOV	-0xa0(%RBP),%RDI

(158) 0x233816 MOVSD	(%RDI,%R13,8),%XMM0

(158) 0x23381c IMUL	%R15,%R9

(158) 0x233820 ADD	%RBX,%R9

(158) 0x233823 MOVHPD	(%RDI,%R9,8),%XMM0

(158) 0x233829 MOV	-0x98(%RBP),%R9

(158) 0x233830 MOV	%R9,%R13

(158) 0x233833 IMUL	%R12,%R13

(158) 0x233837 ADD	%R11,%R13

(158) 0x23383a MOV	-0x90(%RBP),%R10

(158) 0x233841 MOVSD	(%R10,%R13,8),%XMM1

(158) 0x233847 MOV	%R9,%R13

(158) 0x23384a IMUL	%R15,%R13

(158) 0x23384e ADD	%RBX,%R13

(158) 0x233851 MOVHPD	(%R10,%R13,8),%XMM1

(158) 0x233857 IMUL	%R15,%R8

(158) 0x23385b LEA	(%R14,%RCX,1),%EDI

(158) 0x23385f INC	%EDI

(158) 0x233861 LEA	0x1(%R14,%RAX,1),%EAX

(158) 0x233866 MOVSXD	%EDI,%RDI

(158) 0x233869 CLTQ

(158) 0x23386b MOV	%R9,%R13

(158) 0x23386e IMUL	%RDI,%R13

(158) 0x233872 ADD	%R11,%R13

(158) 0x233875 MOVSD	(%R10,%R13,8),%XMM2

(158) 0x23387b MOV	%R9,%R13

(158) 0x23387e IMUL	%RAX,%R13

(158) 0x233882 ADD	%RBX,%R13

(158) 0x233885 MOVHPD	(%R10,%R13,8),%XMM2

(158) 0x23388b MOV	-0x78(%RBP),%R9

(158) 0x23388f MOV	%R9,%R13

(158) 0x233892 IMUL	%R12,%R13

(158) 0x233896 ADD	%R11,%R13

(158) 0x233899 MOV	-0x70(%RBP),%R10

(158) 0x23389d MOVSD	(%R10,%R13,8),%XMM3

(158) 0x2338a3 MOV	%R9,%R13

(158) 0x2338a6 IMUL	%R15,%R13

(158) 0x2338aa ADD	%RBX,%R13

(158) 0x2338ad MOVHPD	(%R10,%R13,8),%XMM3

(158) 0x2338b3 MOV	%R9,%R13

(158) 0x2338b6 IMUL	%RDI,%R13

(158) 0x2338ba ADD	%R11,%R13

(158) 0x2338bd MOVSD	(%R10,%R13,8),%XMM4

(158) 0x2338c3 MOV	%R9,%R13

(158) 0x2338c6 IMUL	%RAX,%R13

(158) 0x2338ca ADD	%RBX,%R13

(158) 0x2338cd MOVHPD	(%R10,%R13,8),%XMM4

(158) 0x2338d3 MOV	-0x88(%RBP),%R9

(158) 0x2338da MOV	%R9,%R13

(158) 0x2338dd IMUL	%R12,%R13

(158) 0x2338e1 MOV	-0x68(%RBP),%R10

(158) 0x2338e5 IMUL	%R10,%R12

(158) 0x2338e9 ADD	%R11,%R12

(158) 0x2338ec MOV	-0x60(%RBP),%R14

(158) 0x2338f0 MOVSD	(%R14,%R12,8),%XMM5

(158) 0x2338f6 MOV	%R9,%R12

(158) 0x2338f9 IMUL	%R15,%R12

(158) 0x2338fd IMUL	%R10,%R15

(158) 0x233901 ADD	%RBX,%R15

(158) 0x233904 MOVHPD	(%R14,%R15,8),%XMM5

(158) 0x23390a ADD	%R11,%RDX

(158) 0x23390d ADD	%R11,%R13

(158) 0x233910 IMUL	%R10,%RDI

(158) 0x233914 ADD	%R11,%RDI

(158) 0x233917 MOVSD	(%R14,%RDI,8),%XMM6

(158) 0x23391d IMUL	%R10,%RAX

(158) 0x233921 ADD	%RBX,%RAX

(158) 0x233924 MOVHPD	(%R14,%RAX,8),%XMM6

(158) 0x23392a ADD	%RBX,%R8

(158) 0x23392d MOV	-0x58(%RBP),%RAX

(158) 0x233931 MOVSD	(%RAX,%RDX,8),%XMM7

(158) 0x233936 MOVHPD	(%RAX,%R8,8),%XMM7

(158) 0x23393c ADD	%RBX,%R12

(158) 0x23393f MULPD	%XMM0,%XMM7

(158) 0x233943 ADDPD	%XMM7,%XMM1

(158) 0x233947 SUBPD	%XMM2,%XMM1

(158) 0x23394b MOV	-0x80(%RBP),%RDI

(158) 0x23394f MOVSD	(%RDI,%R13,8),%XMM2

(158) 0x233955 MOVHPD	(%RDI,%R12,8),%XMM2

(158) 0x23395b MULPD	%XMM7,%XMM2

(158) 0x23395f ADDPD	%XMM3,%XMM2

(158) 0x233963 SUBPD	%XMM4,%XMM2

(158) 0x233967 DIVPD	%XMM1,%XMM2

(158) 0x23396b ADDPD	%XMM0,%XMM5

(158) 0x23396f SUBPD	%XMM6,%XMM5

(158) 0x233973 DIVPD	%XMM5,%XMM1

(158) 0x233977 MOVLPD	%XMM1,(%RAX,%RDX,8)

(158) 0x23397c MOVHPD	%XMM1,(%RAX,%R8,8)

(158) 0x233982 MOVLPD	%XMM2,(%RDI,%R13,8)

(158) 0x233988 MOVHPD	%XMM2,(%RDI,%R12,8)

(158) 0x23398e ADD	$0x2,%RSI

(158) 0x233992 MOV	-0xe0(%RBP),%RDX

(158) 0x233999 ADD	$-0x2,%RDX

(158) 0x23399d MOV	-0xd8(%RBP),%RBX

(158) 0x2339a4 MOV	-0xd0(%RBP),%R15

(158) 0x2339ab MOV	-0xc8(%RBP),%RCX

(158) 0x2339b2 JE	233a0b

(158) 0x2339b4 MOV	%RSI,%RAX

(158) 0x2339b7 SHR	$0x20,%RAX

(158) 0x2339bb MOV	%RDX,-0xe0(%RBP)

(158) 0x2339c2 JE	2339e0

(158) 0x2339c4 MOV	%RSI,%RAX

(158) 0x2339c7 CQTO

(158) 0x2339c9 IDIV	%R15

(158) 0x2339cc MOV	%RDX,%R8

(158) 0x2339cf MOV	%RAX,%RCX

(158) 0x2339d2 JMP	2339ec

0x2339d4 NOPW	%CS:(%RAX,%RAX,1)

(158) 0x2339e0 MOV	%ESI,%EAX

(158) 0x2339e2 XOR	%EDX,%EDX

(158) 0x2339e4 DIV	%R15D

(158) 0x2339e7 MOV	%EDX,%R8D

(158) 0x2339ea MOV	%EAX,%ECX

(158) 0x2339ec MOV	-0x2c(%RBP),%R11D

(158) 0x2339f0 LEA	0x1(%RSI),%RAX

(158) 0x2339f4 MOV	%RAX,%RDX

(158) 0x2339f7 SHR	$0x20,%RDX

(158) 0x2339fb JNE	2337d0

(158) 0x233a01 XOR	%EDX,%EDX

(158) 0x233a03 DIV	%R15D

(158) 0x233a06 JMP	2337d5

0x233a0b MOV	-0xb8(%RBP),%RAX

0x233a12 CMP	%RAX,-0xc0(%RBP)

0x233a19 MOV	-0x2c(%RBP),%R14D

0x233a1d MOV	-0x58(%RBP),%R12

0x233a21 JNE	233b5d

0x233a27 LEA	0x2a75a(%RIP),%RDI

0x233a2e MOV	-0x4c(%RBP),%ESI

0x233a31 CALL	25cd00 <@plt_start@+0x540>

0x233a36 ADD	$0xc8,%RSP

0x233a3d POP	%RBX

0x233a3e POP	%R12

0x233a40 POP	%R13

0x233a42 POP	%R14

0x233a44 POP	%R15

0x233a46 POP	%RBP

0x233a47 RET

0x233a48 NOPL	(%RAX,%RAX,1)

(157) 0x233a50 MOV	%RCX,%RAX

(157) 0x233a53 CQTO

(157) 0x233a55 IDIV	%R15

(157) 0x233a58 MOV	-0x40(%RBP),%R8

(157) 0x233a5c MOV	-0x38(%RBP),%R9

(157) 0x233a60 MOV	-0xa8(%RBP),%R10

(157) 0x233a67 LEA	(%R10,%RAX,1),%EDI

(157) 0x233a6b ADD	%R14D,%EDX

(157) 0x233a6e MOVSXD	%EDX,%RSI

(157) 0x233a71 MOVSXD	%EDI,%RDI

(157) 0x233a74 MOV	%R8,%RDX

(157) 0x233a77 IMUL	%RDI,%RDX

(157) 0x233a7b ADD	%RSI,%RDX

(157) 0x233a7e MOV	%R9,%R8

(157) 0x233a81 IMUL	%RDI,%R8

(157) 0x233a85 ADD	%RSI,%R8

(157) 0x233a88 MOV	-0xa0(%RBP),%R9

(157) 0x233a8f MOVSD	(%R9,%R8,8),%XMM1

(157) 0x233a95 MOVSD	(%R12,%RDX,8),%XMM0

(157) 0x233a9b MULSD	%XMM1,%XMM0

(157) 0x233a9f MOV	-0x98(%RBP),%R9

(157) 0x233aa6 MOV	%R9,%R8

(157) 0x233aa9 IMUL	%RDI,%R8

(157) 0x233aad ADD	%RSI,%R8

(157) 0x233ab0 MOV	-0x90(%RBP),%R11

(157) 0x233ab7 MOVSD	(%R11,%R8,8),%XMM2

(157) 0x233abd ADDSD	%XMM0,%XMM2

(157) 0x233ac1 ADD	%R10D,%EAX

(157) 0x233ac4 INC	%EAX

(157) 0x233ac6 CLTQ

(157) 0x233ac8 MOV	%R9,%R8

(157) 0x233acb IMUL	%RAX,%R8

(157) 0x233acf ADD	%RSI,%R8

(157) 0x233ad2 SUBSD	(%R11,%R8,8),%XMM2

(157) 0x233ad8 MOV	-0x88(%RBP),%R8

(157) 0x233adf IMUL	%RDI,%R8

(157) 0x233ae3 ADD	%RSI,%R8

(157) 0x233ae6 MOV	-0x78(%RBP),%R11

(157) 0x233aea MOV	%R11,%R10

(157) 0x233aed IMUL	%RDI,%R10

(157) 0x233af1 MOV	-0x80(%RBP),%R9

(157) 0x233af5 MULSD	(%R9,%R8,8),%XMM0

(157) 0x233afb ADD	%RSI,%R10

(157) 0x233afe MOV	-0x70(%RBP),%R13

(157) 0x233b02 ADDSD	(%R13,%R10,8),%XMM0

(157) 0x233b09 MOV	%R11,%R10

(157) 0x233b0c IMUL	%RAX,%R10

(157) 0x233b10 ADD	%RSI,%R10

(157) 0x233b13 SUBSD	(%R13,%R10,8),%XMM0

(157) 0x233b1a MOV	-0x68(%RBP),%R10

(157) 0x233b1e IMUL	%R10,%RDI

(157) 0x233b22 ADD	%RSI,%RDI

(157) 0x233b25 MOV	-0x60(%RBP),%R11

(157) 0x233b29 ADDSD	(%R11,%RDI,8),%XMM1

(157) 0x233b2f IMUL	%R10,%RAX

(157) 0x233b33 ADD	%RSI,%RAX

(157) 0x233b36 SUBSD	(%R11,%RAX,8),%XMM1

(157) 0x233b3c DIVSD	%XMM2,%XMM0

(157) 0x233b40 DIVSD	%XMM1,%XMM2

(157) 0x233b44 MOVSD	%XMM2,(%R12,%RDX,8)

(157) 0x233b4a MOVSD	%XMM0,(%R9,%R8,8)

(157) 0x233b50 CMP	%RBX,%RCX

(157) 0x233b53 LEA	0x1(%RCX),%RCX

(157) 0x233b57 JGE	233a27

(157) 0x233b5d MOV	%RCX,%RAX

(157) 0x233b60 SHR	$0x20,%RAX

(157) 0x233b64 JNE	233a50

(157) 0x233b6a MOV	%ECX,%EAX

(157) 0x233b6c XOR	%EDX,%EDX

(157) 0x233b6e DIV	%R15D

(157) 0x233b71 JMP	233a58

0x233b76 NOPW	%CS:(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

Path /

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

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

Source file and lines	advec_cell.cpp:208-216
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:208-216
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 10% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 14.38 to 1.27 cycles (11.36x speedup).

Details

All SSE/AVX instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized function can use their full power.

Workaround

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

Execution units bottlenecks

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

No data for this section

CALL instructions

Detected function call instructions.

Details

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

unknown: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:208
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:208

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:209

Type of elements and instruction set

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

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 212 bytes. The binary function is storing 188 bytes.

General properties

nb instructions	116
nb uops	115
loop length	507
used x86 registers	15
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	30

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.38 cycles
front end	14.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.67	6.67	6.67	6.67	6.67	6.67	14.25	14.25	14.25	14.25	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.67	6.67	6.67	6.67	6.67	6.67	14.25	14.25	14.25	14.25	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	14.38
Dispatch	14.25
Overall L1	14.38

Vectorization ratios

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

Vector efficiency ratios

all	10%
load	9%
store	11%
mul	12%
add-sub	7%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 14.38 cycles. At this rate:

5% of peak load performance is reached (14.75 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (13.08 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).

ASM code

In the binary file, the address of the function is: 233630

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0xc8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV (%RDX),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RCX),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
INC %EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD $0x2,%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
SUB %EAX,%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 233a36 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x406>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%R14D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV (%R9),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
INC %R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
ADD $0x2,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMP %R14D,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 233a36 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x406>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
SUB %R14D,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
IMUL %R15,%RBX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOVQ $0,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RBX,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0xe8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0xe8(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA 0x2aabf(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x50(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0xb0(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x48(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x4c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV -0x48(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RBX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVL %RAX,%RBX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
MOV %RBX,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xb0(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RBX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 233a27 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x3f7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x28(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R9),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%R9),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%R8),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R8,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R8,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RCX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RCX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RBX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R10,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R9,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JAE 233786 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x156>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 233b5d <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x52d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R12,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R14D,-0x2c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RAX,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
AND $-0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%RAX,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RCX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RBX,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 2339b4 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x384>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xb8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0xc0(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
MOV -0x2c(%RBP),%R14D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 233b5d <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x52d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x2a75a(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV -0x4c(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CALL 25cd00 <@plt_start@+0x540>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0xc8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

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

Source file and lines	advec_cell.cpp:208-216
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:208-216
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Details

Workaround

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

Execution units bottlenecks

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

No data for this section

CALL instructions

Detected function call instructions.

Details

unknown: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:208
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:208

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:209

Type of elements and instruction set

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

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 212 bytes. The binary function is storing 188 bytes.

General properties

nb instructions	116
nb uops	115
loop length	507
used x86 registers	15
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	30

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.38 cycles
front end	14.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.67	6.67	6.67	6.67	6.67	6.67	14.25	14.25	14.25	14.25	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.67	6.67	6.67	6.67	6.67	6.67	14.25	14.25	14.25	14.25	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	14.38
Dispatch	14.25
Overall L1	14.38

Vectorization ratios

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

Vector efficiency ratios

all	10%
load	9%
store	11%
mul	12%
add-sub	7%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 14.38 cycles. At this rate:

5% of peak load performance is reached (14.75 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (13.08 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).

ASM code

In the binary file, the address of the function is: 233630

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0xc8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV (%RDX),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RCX),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
INC %EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD $0x2,%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
SUB %EAX,%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 233a36 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x406>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%R14D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV (%R9),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
INC %R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
ADD $0x2,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMP %R14D,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 233a36 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x406>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
SUB %R14D,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
IMUL %R15,%RBX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOVQ $0,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RBX,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0xe8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0xe8(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA 0x2aabf(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x50(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0xb0(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x48(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x4c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV -0x48(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RBX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVL %RAX,%RBX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
MOV %RBX,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xb0(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RBX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 233a27 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x3f7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x28(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R9),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%R9),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%R8),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R8,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R8,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RCX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RCX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RBX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R10,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R9,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JAE 233786 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x156>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 233b5d <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x52d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R12,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R14D,-0x2c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RAX,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
AND $-0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%RAX,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RCX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RBX,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 2339b4 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x384>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xb8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0xc0(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
MOV -0x2c(%RBP),%R14D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 233b5d <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.14+0x52d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x2a75a(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV -0x4c(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CALL 25cd00 <@plt_start@+0x540>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0xc8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D&, clover::Buffer1D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D–	3.34	1.30
○Loop 158 - advec_cell.cpp:209-216 - exec	3.34	1.30
○Loop 157 - advec_cell.cpp:209-216 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex 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

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex 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