Searched refs:branches (Results 1 – 25 of 28) sorted by relevance
12
| /tools/perf/Documentation/ |
| D | itrace.txt | 2 b synthesize branches events (branch misses for Arm SPE)
3 c synthesize branches events (calls only)
4 r synthesize branches events (returns only)
47 It is also possible to skip events generated (instructions, branches, transactions,
|
| D | intel-hybrid.txt | 196 cpu_core/branches/,
197 cpu_atom/branches/,
|
| D | perf-top.txt | 240 taken branches. The number of branches captured with each sample depends on the
241 underlying hardware, the type of branches of interest, and the executed code.
242 It is possible to select the types of branches captured by enabling filters.
|
| D | tips.txt | 19 Treat branches as callchains: perf report --branch-history
|
| D | perf-intel-pt.txt | 35 or "branches" events had been recorded. Presently 3 tools support this:
98 To represent software control flow, "branches" samples are produced. By default
158 the average IPC since the last IPC for that event type. Note IPC for "branches"
167 Another note, in the case of "branches" events, non-taken branches are not
179 branches, and supports 2 additional modes selected by option:
889 b synthesize "branches" events
893 c synthesize branches events (calls only)
894 r synthesize branches events (returns only)
910 "Branches" events look like they were recorded by "perf record -e branches". "c"
917 Note that "instructions", "branches" and "transactions" events depend on code
[all …]
|
| D | security.txt | 203 19,628,798 branches # 0.539 M/sec
204 1,259,201 branch-misses # 6.42% of all branches
|
| D | perf-record.txt | 370 taken branches. The number of branches captured with each sample depends on the
371 underlying hardware, the type of branches of interest, and the executed code.
372 It is possible to select the types of branches captured by enabling filters. The
375 - any: any type of branches
386 - cond: conditional branches
|
| D | perf-dlfilter.txt | 210 Filter out everything except branches from "foo" to "bar":
|
| D | perf-config.txt | 353 If use this, the number of branches jumping to that address can be printed as below.
707 branches.
711 branches decoded without consuming any trace packets. If
|
| D | perf-diff.txt | 297 two perf.data. The program basic block is the code between two branches.
|
| D | perf-stat.txt | 509 69,704,684,856 branches:u # 832.559 M/sec
510 2,078,861,393 branch-misses:u # 2.98% of all branches
|
| D | perf-report.txt | 367 Use the addresses of sampled taken branches instead of the instruction
376 Add the addresses of sampled taken branches to the callstack.
|
| D | perf.data-file-format.txt | 390 cpu pmu capabilities: branches=32, max_precise=3, pmu_name=icelake
|
| /tools/perf/scripts/python/ |
| D | export-to-sqlite.py | 121 branches = (columns == "branches") variable
205 if branches:
586 if branches:
703 if branches:
|
| D | export-to-postgresql.py | 300 branches = (columns == "branches") variable
381 if branches:
1029 if branches:
|
| /tools/perf/util/ |
| D | parse-events.l | 334 branch-instructions|branches { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INS…
371 branch|branches|bpu|btb|bpc |
|
| D | auxtrace.h | 115 bool branches; member
|
| D | auxtrace.c | 1334 synth_opts->branches = true; in itrace_synth_opts__set_default()
1471 synth_opts->branches = true; in itrace_do_parse_synth_opts()
1498 synth_opts->branches = true; in itrace_do_parse_synth_opts()
1502 synth_opts->branches = true; in itrace_do_parse_synth_opts()
|
| D | s390-cpumsf.c | 1077 ison = itops->inject || itops->instructions || itops->branches || in check_auxtrace_itrace()
|
| D | intel-bts.c | 811 if (bts->synth_opts.branches) { in intel_bts_synth_events()
|
| D | arm-spe.c | 1007 if (spe->synth_opts.branches) { in arm_spe_synth_events()
|
| /tools/memory-model/Documentation/ |
| D | control-dependencies.txt | 60 identical stores on both branches of the "if" statement as follows:
|
| D | litmus-tests.txt | 311 conditional branches. In LKMM, conditional branches can affect ordering,
313 to optimize away conditional branches). The following example shows
|
| D | ordering.txt | 419 control-flow instructions such as comparisons and conditional branches.
|
| /tools/perf/ |
| D | design.txt | 7 as instructions executed, cachemisses suffered, or branches mis-predicted -
|
12