| Loop Id: 96 | Module: exec | Source: local_halos.cpp:28-30 | Coverage: 0.02% |
|---|
| Loop Id: 96 | Module: exec | Source: local_halos.cpp:28-30 | Coverage: 0.02% |
|---|
0x417520 LDR D0, [X11, W4,SXTW #3] [1] |
0x417524 SUB W4, W4, #1 |
0x417528 SUBS X6, X6, #1 |
0x41752c STR D0, [X11, W5,SXTW #3] [1] |
0x417530 ADD W5, W5, #1 |
0x417534 B.NE 417520 |
/home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/local_halos.cpp: 28 - 30 |
-------------------------------------------------------------------------------- |
28: for (int kk = 0; kk < depth; ++kk) { |
29: int base = jj * x; |
30: buffer[base + (x - halo_depth + kk)] = buffer[base + (x - halo_depth - 1 - kk)]; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►98.23+ | __kmp_invoke_microtask | libomp.so | |
| ○ | __kmp_invoke_task_func | libomp.so | |
| ○ | __kmp_launch_thread | libomp.so | |
| ○ | __kmp_launch_worker(void*) | libomp.so | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►1.12+ | __kmp_invoke_microtask | libomp.so | |
| ○ | __kmp_invoke_task_func | libomp.so | |
| ○ | __kmp_fork_call | libomp.so | |
| ○ | __kmpc_fork_call | libomp.so | |
| ○ | update_face(int, int, int, int[...] | local_halos.cpp:76 | exec |
| ○ | local_halos(int, int, int, int[...] | local_halos.cpp:103 | exec |
| ○ | run_local_halos(Chunk*, Settin[...] | local_halos.cpp:114 | exec |
| ○ | halo_update_driver(Chunk*, Set[...] | halo_update_driver.cpp:12 | exec |
| ○ | cg_driver(Chunk*, Settings&, d[...] | cg_driver.cpp:20 | exec |
| ○ | solve(Chunk*, Settings&, int, [...] | diffuse.cpp:45 | exec |
| ○ | diffuse(Chunk*, Settings&) | diffuse.cpp:12 | exec |
| ○ | main | main.cpp:169 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | 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 | 1.00 |
| CQA speedup if fully vectorized | 4.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.20 |
| Bottlenecks | |
| Function | update_right(int, int, int, int, double*, bool) [clone .omp_outlined] |
| Source | local_halos.cpp:28-30 |
| Source loop unroll info | multi-versionned |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 1.00 |
| CQA cycles if no scalar integer | 1.00 |
| CQA cycles if FP arith vectorized | 1.00 |
| CQA cycles if fully vectorized | 0.25 |
| Front-end cycles | 0.75 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 0.75 |
| P3 cycles | 0.75 |
| P4 cycles | 0.75 |
| P5 cycles | 0.75 |
| P6 cycles | 0.50 |
| P7 cycles | 0.50 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.83 |
| P11 cycles | 0.50 |
| P12 cycles | 0.67 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 6.00 |
| Nb uops | 6.00 |
| Nb loads | NA |
| Nb stores | 1.00 |
| 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 | 0.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 25.00 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | 25.00 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 25.00 |
| 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 | 1.00 |
| CQA speedup if fully vectorized | 4.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.20 |
| Bottlenecks | |
| Function | update_right(int, int, int, int, double*, bool) [clone .omp_outlined] |
| Source | local_halos.cpp:28-30 |
| Source loop unroll info | multi-versionned |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 1.00 |
| CQA cycles if no scalar integer | 1.00 |
| CQA cycles if FP arith vectorized | 1.00 |
| CQA cycles if fully vectorized | 0.25 |
| Front-end cycles | 0.75 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 0.75 |
| P3 cycles | 0.75 |
| P4 cycles | 0.75 |
| P5 cycles | 0.75 |
| P6 cycles | 0.50 |
| P7 cycles | 0.50 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.83 |
| P11 cycles | 0.50 |
| P12 cycles | 0.67 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 6.00 |
| Nb uops | 6.00 |
| Nb loads | NA |
| Nb stores | 1.00 |
| 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 | 0.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 25.00 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | 25.00 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 25.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Path / |
| Function | update_right(int, int, int, int, double*, bool) [clone .omp_outlined] |
| Source file and lines | local_halos.cpp:28-30 |
| Module | exec |
| nb instructions | 6 |
| nb uops | 6 |
| loop length | 24 |
| used w registers | 2 |
| used x registers | 2 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 0 |
| used d registers | 1 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 0.75 cycles |
| front end | 0.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.75 | 0.75 | 0.75 | 0.75 | 0.50 | 0.50 | 0.00 | 0.00 | 0.83 | 0.50 | 0.67 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 0.75 | 0.75 | 0.75 | 0.75 | 0.50 | 0.50 | 0.00 | 0.00 | 0.83 | 0.50 | 0.67 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 0.75 |
| Dispatch | 0.83 |
| Data deps. | 1.00 |
| Overall L1 | 1.00 |
| 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 | NA (no other vectorizable/vectorized instructions) |
| all | 25% |
| load | 25% |
| store | 25% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 25% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDR D0, [X11, W4,SXTW #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| SUB W4, W4, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| SUBS X6, X6, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (25.0%) |
| STR D0, [X11, W5,SXTW #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| ADD W5, W5, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| B.NE 417520 <_Z12update_rightiiiiPdb.omp_outlined+0x1d0> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| Function | update_right(int, int, int, int, double*, bool) [clone .omp_outlined] |
| Source file and lines | local_halos.cpp:28-30 |
| Module | exec |
| nb instructions | 6 |
| nb uops | 6 |
| loop length | 24 |
| used w registers | 2 |
| used x registers | 2 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 0 |
| used d registers | 1 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 0.75 cycles |
| front end | 0.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.75 | 0.75 | 0.75 | 0.75 | 0.50 | 0.50 | 0.00 | 0.00 | 0.83 | 0.50 | 0.67 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 0.75 | 0.75 | 0.75 | 0.75 | 0.50 | 0.50 | 0.00 | 0.00 | 0.83 | 0.50 | 0.67 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 0.75 |
| Dispatch | 0.83 |
| Data deps. | 1.00 |
| Overall L1 | 1.00 |
| 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 | NA (no other vectorizable/vectorized instructions) |
| all | 25% |
| load | 25% |
| store | 25% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 25% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDR D0, [X11, W4,SXTW #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| SUB W4, W4, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| SUBS X6, X6, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (25.0%) |
| STR D0, [X11, W5,SXTW #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| ADD W5, W5, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| B.NE 417520 <_Z12update_rightiiiiPdb.omp_outlined+0x1d0> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
