OV - exec - Function hypre_BoomerAMGCoarsenPMIS.extracted

	Function: hypre_BoomerAMGCoarsenPMIS.extracted	Module: exec	Source: par_coarsen.c:2516-2576 [...]	Coverage (incl. loops): 0.11% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c: 2516 - 2576

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

2516: #pragma omp parallel private(ig,i)

[...]

2523:         hypre_GetSimpleThreadPartition(&ig_begin, &ig_end, graph_size);

2524:

2525:         HYPRE_Int ig_offd_begin, ig_offd_end;

2526:         hypre_GetSimpleThreadPartition(&ig_offd_begin, &ig_offd_end, graph_offd_size);

2527:

2528:         for (ig = ig_begin; ig < ig_end; ig++)

2529:         {

2530:            i = graph_array[ig];

2531:

2532:            if (CF_marker[i]!=0) /* C or F point */

2533:            {

2534:               /* the independent set subroutine needs measure 0 for

2535:                  removed nodes */

2536:               measure_array[i] = 0;

2537:            }

2538:            else

2539:            {

2540:               private_graph_size_cnt++;

2541:            }

2542:         }

2543:

2544:         for (ig = ig_offd_begin; ig < ig_offd_end; ig++)

2545:         {

2546:            i = graph_array_offd[ig];

2547:

2548:            if (CF_marker_offd[i]!=0) /* C of F point */

2549:            {

2550:               /* the independent set subroutine needs measure 0 for

2551:                  removed nodes */

2552:               measure_array[i + num_variables] = 0;

2553:            }

2554:            else

2555:            {

2556:               private_graph_offd_size_cnt++;

2557:            }

2558:         }

2559:

2560:         hypre_prefix_sum_pair(&private_graph_size_cnt, &graph_size, &private_graph_offd_size_cnt, &graph_offd_size, prefix_sum_workspace);

2561:

2562:         for (ig = ig_begin; ig < ig_end; ig++)

2563:         {

2564:            i = graph_array[ig];

2565:            if (CF_marker[i]==0)

2566:            {

2567:               graph_array2[private_graph_size_cnt++] = i;

2568:            }

2569:         }

2570:

2571:         for (ig = ig_offd_begin; ig < ig_offd_end; ig++)

2572:         {

2573:            i = graph_array_offd[ig];

2574:            if (CF_marker_offd[i]==0)

2575:            {

2576:               graph_array_offd2[private_graph_offd_size_cnt++] = i;

0x43d170 PUSH	%RBP

0x43d171 MOV	%RSP,%RBP

0x43d174 PUSH	%R15

0x43d176 PUSH	%R14

0x43d178 PUSH	%R13

0x43d17a PUSH	%R12

0x43d17c PUSH	%RBX

0x43d17d SUB	$0x38,%RSP

0x43d181 MOV	%R9,%R13

0x43d184 MOV	%R8,%RBX

0x43d187 MOV	%RCX,%R14

0x43d18a MOV	%RDX,%R15

0x43d18d MOV	0x28(%RBP),%R12

0x43d191 MOV	0x20(%RBP),%RAX

0x43d195 MOV	(%RAX),%RDX

0x43d198 LEA	-0x40(%RBP),%RDI

0x43d19c LEA	-0x48(%RBP),%RSI

0x43d1a0 CALL	41d3a0 <@plt>

0x43d1a5 MOV	(%R12),%RDX

0x43d1a9 LEA	-0x50(%RBP),%RDI

0x43d1ad LEA	-0x58(%RBP),%RSI

0x43d1b1 CALL	41d3a0 <@plt>

0x43d1b6 MOV	-0x40(%RBP),%RAX

0x43d1ba MOV	-0x48(%RBP),%RCX

0x43d1be MOV	%RCX,%RSI

0x43d1c1 SUB	%RAX,%RSI

0x43d1c4 JLE	43d1d7

0x43d1c6 CMP	$0x4,%RSI

0x43d1ca JAE	43d1de

0x43d1cc XOR	%EDX,%EDX

0x43d1ce MOV	0x10(%RBP),%R10

0x43d1d2 JMP	43d29d

0x43d1d7 XOR	%EDX,%EDX

0x43d1d9 JMP	43d2d7

0x43d1de MOV	%RSI,%RDI

0x43d1e1 SHR	$0x2,%RDI

0x43d1e5 MOV	0x10(%RBP),%R10

0x43d1e9 LEA	(%R10,%RAX,8),%R8

0x43d1ed ADD	$0x18,%R8

0x43d1f1 XOR	%EDX,%EDX

0x43d1f3 JMP	43d216

0x43d1f5 NOPW	%CS:(%RAX,%RAX,1)

(296) 0x43d200 MOVQ	$0,(%R13,%R9,8)

(296) 0x43d209 ADD	$0x20,%R8

(296) 0x43d20d DEC	%RDI

(296) 0x43d210 JE	43d29d

(296) 0x43d216 MOV	-0x18(%R8),%R9

(296) 0x43d21a CMPQ	$0,(%R14,%R9,8)

(296) 0x43d21f JE	43d260

(296) 0x43d221 MOVQ	$0,(%R13,%R9,8)

(296) 0x43d22a MOV	-0x10(%R8),%R9

(296) 0x43d22e CMPQ	$0,(%R14,%R9,8)

(296) 0x43d233 JE	43d26e

(296) 0x43d235 MOVQ	$0,(%R13,%R9,8)

(296) 0x43d23e MOV	-0x8(%R8),%R9

(296) 0x43d242 CMPQ	$0,(%R14,%R9,8)

(296) 0x43d247 JE	43d27c

(296) 0x43d249 MOVQ	$0,(%R13,%R9,8)

(296) 0x43d252 MOV	(%R8),%R9

(296) 0x43d255 CMPQ	$0,(%R14,%R9,8)

(296) 0x43d25a JNE	43d200

(296) 0x43d25c JMP	43d28d

0x43d25e XCHG	%AX,%AX

(296) 0x43d260 INC	%RDX

(296) 0x43d263 MOV	-0x10(%R8),%R9

(296) 0x43d267 CMPQ	$0,(%R14,%R9,8)

(296) 0x43d26c JNE	43d235

(296) 0x43d26e INC	%RDX

(296) 0x43d271 MOV	-0x8(%R8),%R9

(296) 0x43d275 CMPQ	$0,(%R14,%R9,8)

(296) 0x43d27a JNE	43d249

(296) 0x43d27c INC	%RDX

(296) 0x43d27f MOV	(%R8),%R9

(296) 0x43d282 CMPQ	$0,(%R14,%R9,8)

(296) 0x43d287 JNE	43d200

(296) 0x43d28d INC	%RDX

(296) 0x43d290 ADD	$0x20,%R8

(296) 0x43d294 DEC	%RDI

(296) 0x43d297 JNE	43d216

0x43d29d MOV	%RSI,%RDI

0x43d2a0 AND	$-0x4,%RDI

0x43d2a4 CMP	%RSI,%RDI

0x43d2a7 JAE	43d2d7

0x43d2a9 ADD	%RDI,%RAX

0x43d2ac JMP	43d2c1

0x43d2ae XCHG	%AX,%AX

(295) 0x43d2b0 MOVQ	$0,(%R13,%RSI,8)

(295) 0x43d2b9 INC	%RAX

(295) 0x43d2bc CMP	%RAX,%RCX

(295) 0x43d2bf JE	43d2d7

(295) 0x43d2c1 MOV	(%R10,%RAX,8),%RSI

(295) 0x43d2c5 CMPQ	$0,(%R14,%RSI,8)

(295) 0x43d2ca JNE	43d2b0

(295) 0x43d2cc INC	%RDX

(295) 0x43d2cf INC	%RAX

(295) 0x43d2d2 CMP	%RAX,%RCX

(295) 0x43d2d5 JNE	43d2c1

0x43d2d7 MOV	0x30(%RBP),%R8

0x43d2db MOV	0x18(%RBP),%R12

0x43d2df MOV	%RDX,-0x30(%RBP)

0x43d2e3 MOV	-0x50(%RBP),%RAX

0x43d2e7 MOV	-0x58(%RBP),%RCX

0x43d2eb MOV	%RCX,%RSI

0x43d2ee SUB	%RAX,%RSI

0x43d2f1 JLE	43d300

0x43d2f3 CMP	$0x4,%RSI

0x43d2f7 JAE	43d307

0x43d2f9 XOR	%EDX,%EDX

0x43d2fb JMP	43d3cd

0x43d300 XOR	%EDX,%EDX

0x43d302 JMP	43d40a

0x43d307 MOV	%RSI,%RDI

0x43d30a SHR	$0x2,%RDI

0x43d30e LEA	(%R12,%RAX,8),%R9

0x43d312 ADD	$0x18,%R9

0x43d316 XOR	%EDX,%EDX

0x43d318 JMP	43d339

0x43d31a NOPW	(%RAX,%RAX,1)

(294) 0x43d320 ADD	%R15,%R10

(294) 0x43d323 MOVQ	$0,(%R13,%R10,8)

(294) 0x43d32c ADD	$0x20,%R9

(294) 0x43d330 DEC	%RDI

(294) 0x43d333 JE	43d3cd

(294) 0x43d339 MOV	-0x18(%R9),%R10

(294) 0x43d33d CMPQ	$0,(%RBX,%R10,8)

(294) 0x43d342 JE	43d390

(294) 0x43d344 ADD	%R15,%R10

(294) 0x43d347 MOVQ	$0,(%R13,%R10,8)

(294) 0x43d350 MOV	-0x10(%R9),%R10

(294) 0x43d354 CMPQ	$0,(%RBX,%R10,8)

(294) 0x43d359 JE	43d39e

(294) 0x43d35b ADD	%R15,%R10

(294) 0x43d35e MOVQ	$0,(%R13,%R10,8)

(294) 0x43d367 MOV	-0x8(%R9),%R10

(294) 0x43d36b CMPQ	$0,(%RBX,%R10,8)

(294) 0x43d370 JE	43d3ac

(294) 0x43d372 ADD	%R15,%R10

(294) 0x43d375 MOVQ	$0,(%R13,%R10,8)

(294) 0x43d37e MOV	(%R9),%R10

(294) 0x43d381 CMPQ	$0,(%RBX,%R10,8)

(294) 0x43d386 JNE	43d320

(294) 0x43d388 JMP	43d3bd

0x43d38a NOPW	(%RAX,%RAX,1)

(294) 0x43d390 INC	%RDX

(294) 0x43d393 MOV	-0x10(%R9),%R10

(294) 0x43d397 CMPQ	$0,(%RBX,%R10,8)

(294) 0x43d39c JNE	43d35b

(294) 0x43d39e INC	%RDX

(294) 0x43d3a1 MOV	-0x8(%R9),%R10

(294) 0x43d3a5 CMPQ	$0,(%RBX,%R10,8)

(294) 0x43d3aa JNE	43d372

(294) 0x43d3ac INC	%RDX

(294) 0x43d3af MOV	(%R9),%R10

(294) 0x43d3b2 CMPQ	$0,(%RBX,%R10,8)

(294) 0x43d3b7 JNE	43d320

(294) 0x43d3bd INC	%RDX

(294) 0x43d3c0 ADD	$0x20,%R9

(294) 0x43d3c4 DEC	%RDI

(294) 0x43d3c7 JNE	43d339

0x43d3cd MOV	%RSI,%RDI

0x43d3d0 AND	$-0x4,%RDI

0x43d3d4 CMP	%RSI,%RDI

0x43d3d7 JAE	43d40a

0x43d3d9 ADD	%RDI,%RAX

0x43d3dc JMP	43d3f4

0x43d3de XCHG	%AX,%AX

(293) 0x43d3e0 ADD	%R15,%RSI

(293) 0x43d3e3 MOVQ	$0,(%R13,%RSI,8)

(293) 0x43d3ec INC	%RAX

(293) 0x43d3ef CMP	%RAX,%RCX

(293) 0x43d3f2 JE	43d40a

(293) 0x43d3f4 MOV	(%R12,%RAX,8),%RSI

(293) 0x43d3f8 CMPQ	$0,(%RBX,%RSI,8)

(293) 0x43d3fd JNE	43d3e0

(293) 0x43d3ff INC	%RDX

(293) 0x43d402 INC	%RAX

(293) 0x43d405 CMP	%RAX,%RCX

(293) 0x43d408 JNE	43d3f4

0x43d40a MOV	%RDX,-0x38(%RBP)

0x43d40e LEA	-0x30(%RBP),%RDI

0x43d412 LEA	-0x38(%RBP),%RDX

0x43d416 MOV	0x20(%RBP),%RSI

0x43d41a MOV	0x28(%RBP),%RCX

0x43d41e CALL	41e240 <@plt>

0x43d423 MOV	-0x40(%RBP),%RAX

0x43d427 MOV	-0x48(%RBP),%RCX

0x43d42b MOV	%RCX,%RDI

0x43d42e SUB	%RAX,%RDI

0x43d431 MOV	0x10(%RBP),%R11

0x43d435 JLE	43d47c

0x43d437 MOV	0x38(%RBP),%RDX

0x43d43b MOV	-0x30(%RBP),%RSI

0x43d43f CMP	$0x4,%RDI

0x43d443 JAE	43d4db

0x43d449 MOV	%RDI,%R8

0x43d44c AND	$-0x4,%R8

0x43d450 CMP	%RDI,%R8

0x43d453 JAE	43d47c

0x43d455 ADD	%R8,%RAX

0x43d458 JMP	43d468

0x43d45a NOPW	(%RAX,%RAX,1)

(291) 0x43d460 INC	%RAX

(291) 0x43d463 CMP	%RAX,%RCX

(291) 0x43d466 JE	43d47c

(291) 0x43d468 MOV	(%R11,%RAX,8),%RDI

(291) 0x43d46c CMPQ	$0,(%R14,%RDI,8)

(291) 0x43d471 JNE	43d460

(291) 0x43d473 MOV	%RDI,(%RDX,%RSI,8)

(291) 0x43d477 INC	%RSI

(291) 0x43d47a JMP	43d460

0x43d47c MOV	-0x50(%RBP),%RAX

0x43d480 MOV	-0x58(%RBP),%RCX

0x43d484 MOV	%RCX,%RDI

0x43d487 SUB	%RAX,%RDI

0x43d48a JLE	43d4cc

0x43d48c MOV	0x40(%RBP),%RDX

0x43d490 MOV	-0x38(%RBP),%RSI

0x43d494 CMP	$0x4,%RDI

0x43d498 JAE	43d56e

0x43d49e MOV	%RDI,%R8

0x43d4a1 AND	$-0x4,%R8

0x43d4a5 CMP	%RDI,%R8

0x43d4a8 JAE	43d4cc

0x43d4aa ADD	%R8,%RAX

0x43d4ad JMP	43d4b8

0x43d4af NOP

(289) 0x43d4b0 INC	%RAX

(289) 0x43d4b3 CMP	%RAX,%RCX

(289) 0x43d4b6 JE	43d4cc

(289) 0x43d4b8 MOV	(%R12,%RAX,8),%RDI

(289) 0x43d4bc CMPQ	$0,(%RBX,%RDI,8)

(289) 0x43d4c1 JNE	43d4b0

(289) 0x43d4c3 MOV	%RDI,(%RDX,%RSI,8)

(289) 0x43d4c7 INC	%RSI

(289) 0x43d4ca JMP	43d4b0

0x43d4cc ADD	$0x38,%RSP

0x43d4d0 POP	%RBX

0x43d4d1 POP	%R12

0x43d4d3 POP	%R13

0x43d4d5 POP	%R14

0x43d4d7 POP	%R15

0x43d4d9 POP	%RBP

0x43d4da RET

0x43d4db MOV	%RDI,%R8

0x43d4de SHR	$0x2,%R8

0x43d4e2 LEA	(%R11,%RAX,8),%R9

0x43d4e6 ADD	$0x18,%R9

0x43d4ea JMP	43d4fd

0x43d4ec NOPL	(%RAX)

(292) 0x43d4f0 ADD	$0x20,%R9

(292) 0x43d4f4 DEC	%R8

(292) 0x43d4f7 JE	43d449

(292) 0x43d4fd MOV	-0x18(%R9),%R10

(292) 0x43d501 CMPQ	$0,(%R14,%R10,8)

(292) 0x43d506 JE	43d530

(292) 0x43d508 MOV	-0x10(%R9),%R10

(292) 0x43d50c CMPQ	$0,(%R14,%R10,8)

(292) 0x43d511 JE	43d542

(292) 0x43d513 MOV	-0x8(%R9),%R10

(292) 0x43d517 CMPQ	$0,(%R14,%R10,8)

(292) 0x43d51c JE	43d554

(292) 0x43d51e MOV	(%R9),%R10

(292) 0x43d521 CMPQ	$0,(%R14,%R10,8)

(292) 0x43d526 JNE	43d4f0

(292) 0x43d528 JMP	43d565

0x43d52a NOPW	(%RAX,%RAX,1)

(292) 0x43d530 MOV	%R10,(%RDX,%RSI,8)

(292) 0x43d534 INC	%RSI

(292) 0x43d537 MOV	-0x10(%R9),%R10

(292) 0x43d53b CMPQ	$0,(%R14,%R10,8)

(292) 0x43d540 JNE	43d513

(292) 0x43d542 MOV	%R10,(%RDX,%RSI,8)

(292) 0x43d546 INC	%RSI

(292) 0x43d549 MOV	-0x8(%R9),%R10

(292) 0x43d54d CMPQ	$0,(%R14,%R10,8)

(292) 0x43d552 JNE	43d51e

(292) 0x43d554 MOV	%R10,(%RDX,%RSI,8)

(292) 0x43d558 INC	%RSI

(292) 0x43d55b MOV	(%R9),%R10

(292) 0x43d55e CMPQ	$0,(%R14,%R10,8)

(292) 0x43d563 JNE	43d4f0

(292) 0x43d565 MOV	%R10,(%RDX,%RSI,8)

(292) 0x43d569 INC	%RSI

(292) 0x43d56c JMP	43d4f0

0x43d56e MOV	%RDI,%R8

0x43d571 SHR	$0x2,%R8

0x43d575 LEA	(%R12,%RAX,8),%R9

0x43d579 ADD	$0x18,%R9

0x43d57d JMP	43d58d

0x43d57f NOP

(290) 0x43d580 ADD	$0x20,%R9

(290) 0x43d584 DEC	%R8

(290) 0x43d587 JE	43d49e

(290) 0x43d58d MOV	-0x18(%R9),%R10

(290) 0x43d591 CMPQ	$0,(%RBX,%R10,8)

(290) 0x43d596 JE	43d5c0

(290) 0x43d598 MOV	-0x10(%R9),%R10

(290) 0x43d59c CMPQ	$0,(%RBX,%R10,8)

(290) 0x43d5a1 JE	43d5d2

(290) 0x43d5a3 MOV	-0x8(%R9),%R10

(290) 0x43d5a7 CMPQ	$0,(%RBX,%R10,8)

(290) 0x43d5ac JE	43d5e4

(290) 0x43d5ae MOV	(%R9),%R10

(290) 0x43d5b1 CMPQ	$0,(%RBX,%R10,8)

(290) 0x43d5b6 JNE	43d580

(290) 0x43d5b8 JMP	43d5f5

0x43d5ba NOPW	(%RAX,%RAX,1)

(290) 0x43d5c0 MOV	%R10,(%RDX,%RSI,8)

(290) 0x43d5c4 INC	%RSI

(290) 0x43d5c7 MOV	-0x10(%R9),%R10

(290) 0x43d5cb CMPQ	$0,(%RBX,%R10,8)

(290) 0x43d5d0 JNE	43d5a3

(290) 0x43d5d2 MOV	%R10,(%RDX,%RSI,8)

(290) 0x43d5d6 INC	%RSI

(290) 0x43d5d9 MOV	-0x8(%R9),%R10

(290) 0x43d5dd CMPQ	$0,(%RBX,%R10,8)

(290) 0x43d5e2 JNE	43d5ae

(290) 0x43d5e4 MOV	%R10,(%RDX,%RSI,8)

(290) 0x43d5e8 INC	%RSI

(290) 0x43d5eb MOV	(%R9),%R10

(290) 0x43d5ee CMPQ	$0,(%RBX,%R10,8)

(290) 0x43d5f3 JNE	43d580

(290) 0x43d5f5 MOV	%R10,(%RDX,%RSI,8)

(290) 0x43d5f9 INC	%RSI

(290) 0x43d5fc JMP	43d580

0x43d5fe XCHG	%AX,%AX

Coverage (%)	Name	Source Location	Module
►95.30+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►2.75+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	hypre_BoomerAMGCoarsenPMIS	par_coarsen.c:2516	exec
○	hypre_BoomerAMGSetup	par_amg_setup.c:612	exec
○	hypre_PCGSetup	pcg.c:234	exec
○	main	amg.c:398	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start		exec
►1.67+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so

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 icx_5

Source file and lines	par_coarsen.c:2516-2576
Module	exec

The function is defined in /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2516,2523-2576.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 11% 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 16.38 to 1.30 cycles (12.60x 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: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2523
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2526
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2560

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 184 bytes. The binary function is storing 16 bytes.

General properties

nb instructions	141
nb uops	131
loop length	469
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	13

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	16.38 cycles
front end	16.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	11.33	11.33	11.33	11.33	11.33	11.33	7.00	7.00	7.00	7.00	0.00	0.00	0.00	0.00	0.00	0.00
cycles	11.33	11.33	11.33	11.33	11.33	11.33	7.00	7.00	7.00	7.00	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	16.38
Dispatch	11.33
Overall L1	16.38

Vectorization ratios

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
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	11%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
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 16.38 cycles. At this rate:

4% of peak load performance is reached (11.24 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (0.98 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 16.38 to 11.33 cycles (1.44x speedup).

ASM code

In the binary file, the address of the function is: 43d170

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 $0x38,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R9,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %R8,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV 0x28(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RAX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
LEA -0x40(%RBP),%RDI	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),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
CALL 41d3a0 <@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV (%R12),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
LEA -0x50(%RBP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x58(%RBP),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
CALL 41d3a0 <@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x48(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %RAX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 43d1d7 <hypre_BoomerAMGCoarsenPMIS.extracted+0x67>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
CMP $0x4,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d1de <hypre_BoomerAMGCoarsenPMIS.extracted+0x6e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOV 0x10(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 43d29d <hypre_BoomerAMGCoarsenPMIS.extracted+0x12d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 43d2d7 <hypre_BoomerAMGCoarsenPMIS.extracted+0x167>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SHR $0x2,%RDI	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
MOV 0x10(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (%R10,%RAX,8),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD $0x18,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 43d216 <hypre_BoomerAMGCoarsenPMIS.extracted+0xa6>	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
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x4,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMP %RSI,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d2d7 <hypre_BoomerAMGCoarsenPMIS.extracted+0x167>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADD %RDI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d2c1 <hypre_BoomerAMGCoarsenPMIS.extracted+0x151>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV 0x30(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x18(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x58(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %RAX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 43d300 <hypre_BoomerAMGCoarsenPMIS.extracted+0x190>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
CMP $0x4,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d307 <hypre_BoomerAMGCoarsenPMIS.extracted+0x197>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 43d3cd <hypre_BoomerAMGCoarsenPMIS.extracted+0x25d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 43d40a <hypre_BoomerAMGCoarsenPMIS.extracted+0x29a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SHR $0x2,%RDI	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
LEA (%R12,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD $0x18,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 43d339 <hypre_BoomerAMGCoarsenPMIS.extracted+0x1c9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x4,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMP %RSI,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d40a <hypre_BoomerAMGCoarsenPMIS.extracted+0x29a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADD %RDI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d3f4 <hypre_BoomerAMGCoarsenPMIS.extracted+0x284>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV %RDX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA -0x30(%RBP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x38(%RBP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x20(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x28(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
CALL 41e240 <@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x48(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %RAX,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x10(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JLE 43d47c <hypre_BoomerAMGCoarsenPMIS.extracted+0x30c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x38(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x30(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
CMP $0x4,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d4db <hypre_BoomerAMGCoarsenPMIS.extracted+0x36b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x4,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMP %RDI,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d47c <hypre_BoomerAMGCoarsenPMIS.extracted+0x30c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADD %R8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d468 <hypre_BoomerAMGCoarsenPMIS.extracted+0x2f8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x58(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %RAX,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 43d4cc <hypre_BoomerAMGCoarsenPMIS.extracted+0x35c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x40(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x38(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
CMP $0x4,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d56e <hypre_BoomerAMGCoarsenPMIS.extracted+0x3fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x4,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMP %RDI,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d4cc <hypre_BoomerAMGCoarsenPMIS.extracted+0x35c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADD %R8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d4b8 <hypre_BoomerAMGCoarsenPMIS.extracted+0x348>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x38,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
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
MOV %RDI,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SHR $0x2,%R8	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
LEA (%R11,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD $0x18,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d4fd <hypre_BoomerAMGCoarsenPMIS.extracted+0x38d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV %RDI,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SHR $0x2,%R8	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
LEA (%R12,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD $0x18,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d58d <hypre_BoomerAMGCoarsenPMIS.extracted+0x41d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
XCHG %AX,%AX	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 icx_5

Source file and lines	par_coarsen.c:2516-2576
Module	exec

The function is defined in /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2516,2523-2576.

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: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2523
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2526
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2560

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 184 bytes. The binary function is storing 16 bytes.

General properties

nb instructions	141
nb uops	131
loop length	469
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	13

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	16.38 cycles
front end	16.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	11.33	11.33	11.33	11.33	11.33	11.33	7.00	7.00	7.00	7.00	0.00	0.00	0.00	0.00	0.00	0.00
cycles	11.33	11.33	11.33	11.33	11.33	11.33	7.00	7.00	7.00	7.00	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	16.38
Dispatch	11.33
Overall L1	16.38

Vectorization ratios

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
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	11%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
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 16.38 cycles. At this rate:

4% of peak load performance is reached (11.24 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (0.98 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: 43d170

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 $0x38,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R9,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %R8,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV 0x28(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RAX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
LEA -0x40(%RBP),%RDI	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),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
CALL 41d3a0 <@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV (%R12),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
LEA -0x50(%RBP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x58(%RBP),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
CALL 41d3a0 <@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x48(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %RAX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 43d1d7 <hypre_BoomerAMGCoarsenPMIS.extracted+0x67>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
CMP $0x4,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d1de <hypre_BoomerAMGCoarsenPMIS.extracted+0x6e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOV 0x10(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 43d29d <hypre_BoomerAMGCoarsenPMIS.extracted+0x12d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 43d2d7 <hypre_BoomerAMGCoarsenPMIS.extracted+0x167>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SHR $0x2,%RDI	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
MOV 0x10(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (%R10,%RAX,8),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD $0x18,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 43d216 <hypre_BoomerAMGCoarsenPMIS.extracted+0xa6>	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
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x4,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMP %RSI,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d2d7 <hypre_BoomerAMGCoarsenPMIS.extracted+0x167>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADD %RDI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d2c1 <hypre_BoomerAMGCoarsenPMIS.extracted+0x151>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV 0x30(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x18(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x58(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %RAX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 43d300 <hypre_BoomerAMGCoarsenPMIS.extracted+0x190>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
CMP $0x4,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d307 <hypre_BoomerAMGCoarsenPMIS.extracted+0x197>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 43d3cd <hypre_BoomerAMGCoarsenPMIS.extracted+0x25d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 43d40a <hypre_BoomerAMGCoarsenPMIS.extracted+0x29a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SHR $0x2,%RDI	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
LEA (%R12,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD $0x18,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 43d339 <hypre_BoomerAMGCoarsenPMIS.extracted+0x1c9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x4,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMP %RSI,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d40a <hypre_BoomerAMGCoarsenPMIS.extracted+0x29a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADD %RDI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d3f4 <hypre_BoomerAMGCoarsenPMIS.extracted+0x284>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV %RDX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA -0x30(%RBP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x38(%RBP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x20(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x28(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
CALL 41e240 <@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x48(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %RAX,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x10(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JLE 43d47c <hypre_BoomerAMGCoarsenPMIS.extracted+0x30c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x38(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x30(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
CMP $0x4,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d4db <hypre_BoomerAMGCoarsenPMIS.extracted+0x36b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x4,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMP %RDI,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d47c <hypre_BoomerAMGCoarsenPMIS.extracted+0x30c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADD %R8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d468 <hypre_BoomerAMGCoarsenPMIS.extracted+0x2f8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x58(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %RAX,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 43d4cc <hypre_BoomerAMGCoarsenPMIS.extracted+0x35c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x40(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x38(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
CMP $0x4,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d56e <hypre_BoomerAMGCoarsenPMIS.extracted+0x3fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $-0x4,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMP %RDI,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 43d4cc <hypre_BoomerAMGCoarsenPMIS.extracted+0x35c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADD %R8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d4b8 <hypre_BoomerAMGCoarsenPMIS.extracted+0x348>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x38,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
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
MOV %RDI,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SHR $0x2,%R8	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
LEA (%R11,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD $0x18,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d4fd <hypre_BoomerAMGCoarsenPMIS.extracted+0x38d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV %RDI,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SHR $0x2,%R8	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
LEA (%R12,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD $0x18,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 43d58d <hypre_BoomerAMGCoarsenPMIS.extracted+0x41d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼hypre_BoomerAMGCoarsenPMIS.extracted–	0.11	0.06
○Loop 296 - par_coarsen.c:2528-2540 - exec	0.07	0.04
○Loop 292 - par_coarsen.c:2562-2567 - exec	0.04	0.02
○Loop 290 - par_coarsen.c:2571-2576 - exec	0.00	0.00
○Loop 294 - par_coarsen.c:2544-2556 - exec	0.00	0.00
○Loop 289 - par_coarsen.c:2571-2576 - exec	0.00	0.00
○Loop 295 - par_coarsen.c:2528-2540 - exec	0.00	0.00
○Loop 293 - par_coarsen.c:2544-2556 - exec	0.00	0.00
○Loop 291 - par_coarsen.c:2562-2567 - exec	0.00	0.00

Report Configuration

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

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