linux/tools/lib/perf
Ian Rogers af9e8d12b1 libperf cpumap: Reduce allocations and sorting in intersect
On hybrid platforms the CPU maps are often disjoint. Rather than copy
CPUs and trim, compute the number of common CPUs, if none early exit,
otherwise copy in an sorted order. This avoids memory allocation in
the disjoint case and avoids a second malloc and useless sort in the
previous trim cases.

Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-11-17 18:43:08 -08:00
..
Documentation perf record: Add 8-byte aligned event type PERF_RECORD_COMPRESSED2 2025-05-16 17:31:40 -03:00
include libperf event: Ensure tracing data is multiple of 8 sized 2025-09-03 12:34:54 -03:00
tests libperf cpumap: Replace usage of perf_cpu_map__new(NULL) with perf_cpu_map__new_online_cpus() 2023-12-12 14:55:13 -03:00
.gitignore libperf: Add gitignore 2024-08-01 12:11:33 -03:00
Build
Makefile perf tools: Fix in-source libperf build 2025-04-29 12:32:31 -07:00
core.c
cpumap.c libperf cpumap: Reduce allocations and sorting in intersect 2025-11-17 18:43:08 -08:00
evlist.c perf parse-events: Support user CPUs mixed with threads/processes 2025-07-24 13:41:35 -07:00
evsel.c libperf evsel: Factor perf_evsel__exit out of perf_evsel__delete 2025-07-24 13:41:35 -07:00
internal.h
lib.c
libperf.map libperf cpumap: Remove perf_cpu_map__read() 2024-12-09 17:52:41 -03:00
libperf.pc.template
mmap.c libperf mmap: In user mmap rdpmc avoid undefined behavior 2025-10-02 15:02:47 -03:00
threadmap.c libperf threadmap: Add perf_thread_map__idx() 2025-05-21 15:07:13 -03:00
xyarray.c