| Loop Id: 2413 | Module: exec | Source: par_strength.c:1756-1765 | Coverage: 0.01% |
|---|
| Loop Id: 2413 | Module: exec | Source: par_strength.c:1756-1765 | Coverage: 0.01% |
|---|
0x4c9700 CMP X14, X16 |
0x4c9704 B.GE 4c974c |
(2414) 0x4c9708 LDR X27, [X25, X14,LSL #3] |
(2414) 0x4c970c ADD X14, X14, #1 |
(2414) 0x4c9710 UBFM X5, X27, #61, #60 |
(2414) 0x4c9714 LDR X6, [X24, X5] |
(2414) 0x4c9718 CMP X6, #0 |
(2414) 0x4c971c B.LE 4c9700 |
(2414) 0x4c9720 LDR X27, [X18, X5] |
(2414) 0x4c9724 UBFM X5, X27, #61, #60 |
(2414) 0x4c9728 LDR X6, [X19, X5] |
(2414) 0x4c972c CMP X7, X6 |
(2414) 0x4c9730 B.LE 4c9700 |
(2414) 0x4c9734 STR X2, [X19, X5] |
(2414) 0x4c9738 MOVZ W17, #1 |
(2414) 0x4c973c ADD X2, X2, #1 |
(2414) 0x4c9740 LDR X16, [X28] |
(2414) 0x4c9744 CMP X14, X16 |
(2414) 0x4c9748 B.LT 4c9708 |
/home/hbollore/qaas/qaas-runs/174-161-6712/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c: 1756 - 1765 |
-------------------------------------------------------------------------------- |
1756: for (jj2 = S_offd_i[i2]; jj2 < S_offd_i[i2+1]; jj2++) |
1757: { |
1758: i3 = S_offd_j[jj2]; |
1759: if (CF_marker_offd[i3] > 0) |
1760: { |
1761: index = map_S_to_C[i3]; |
1762: if (S_marker_offd[index] < jj_row_begin_offd) |
1763: { |
1764: S_marker_offd[index] = num_nonzeros_offd; |
1765: num_nonzeros_offd++; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►96.15+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►3.85+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | hypre_BoomerAMGCreate2ndS | par_strength.c:2236 | exec |
| ○ | hypre_BoomerAMGSetup | par_amg_setup.c:622 | 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 | amg.c:253 | exec |
| 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 / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | NA |
| CQA speedup if fully vectorized | NA |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 2.00 |
| Bottlenecks | P0, P1, |
| Function | hypre_BoomerAMGCreate2ndS._omp_fn.7 |
| Source | par_strength.c:1756-1756 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 0.50 |
| CQA cycles if no scalar integer | 0.50 |
| CQA cycles if FP arith vectorized | NA |
| CQA cycles if fully vectorized | NA |
| Front-end cycles | 0.25 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 0.25 |
| P3 cycles | 0.25 |
| P4 cycles | 0.00 |
| P5 cycles | 0.00 |
| P6 cycles | 0.25 |
| P7 cycles | 0.25 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.00 |
| P11 cycles | 0.00 |
| P12 cycles | 0.00 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| P15 cycles | 0.00 |
| P16 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 0 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 2.00 |
| Nb uops | 2.00 |
| Nb loads | NA |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | NA |
| Vectorization ratio load | NA |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | NA |
| Vector-efficiency ratio load | NA |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | NA |
| CQA speedup if fully vectorized | NA |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 2.00 |
| Bottlenecks | P0, P1, |
| Function | hypre_BoomerAMGCreate2ndS._omp_fn.7 |
| Source | par_strength.c:1756-1756 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 0.50 |
| CQA cycles if no scalar integer | 0.50 |
| CQA cycles if FP arith vectorized | NA |
| CQA cycles if fully vectorized | NA |
| Front-end cycles | 0.25 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 0.25 |
| P3 cycles | 0.25 |
| P4 cycles | 0.00 |
| P5 cycles | 0.00 |
| P6 cycles | 0.25 |
| P7 cycles | 0.25 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.00 |
| P11 cycles | 0.00 |
| P12 cycles | 0.00 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| P15 cycles | 0.00 |
| P16 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 0 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 2.00 |
| Nb uops | 2.00 |
| Nb loads | NA |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | NA |
| Vectorization ratio load | NA |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | NA |
| Vector-efficiency ratio load | NA |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Path / |
| Function | hypre_BoomerAMGCreate2ndS._omp_fn.7 |
| Source file and lines | par_strength.c:1756-1765 |
| Module | exec |
| nb instructions | 2 |
| loop length | 8 |
| nb stack references | 0 |
| front end | 0.25 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.25 | 0.25 | 0.00 | 0.00 | 0.25 | 0.25 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 0.25 | 0.25 | 0.00 | 0.00 | 0.25 | 0.25 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 0.00 |
| Front-end | 0.25 |
| Data deps. | 0.00 |
| Overall L1 | 0.50 |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CMP X14, X16 | 1 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
| B.GE 4c974c <hypre_BoomerAMGCreate2ndS._omp_fn.7+0x172c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| Function | hypre_BoomerAMGCreate2ndS._omp_fn.7 |
| Source file and lines | par_strength.c:1756-1765 |
| Module | exec |
| nb instructions | 2 |
| loop length | 8 |
| nb stack references | 0 |
| front end | 0.25 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.25 | 0.25 | 0.00 | 0.00 | 0.25 | 0.25 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 0.25 | 0.25 | 0.00 | 0.00 | 0.25 | 0.25 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 0.00 |
| Front-end | 0.25 |
| Data deps. | 0.00 |
| Overall L1 | 0.50 |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CMP X14, X16 | 1 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
| B.GE 4c974c <hypre_BoomerAMGCreate2ndS._omp_fn.7+0x172c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |