| Message ID | 20240521135114.40265-1-jdek@itanimul.li |
|---|---|
| State | Accepted |
| Commit | b1adf6d1d02c2be7418ab496486a350724740907 |
| Headers | show |
| Series | [FFmpeg-devel,v3] checkasm: add sample argument to adjust during bench | expand |
| Context | Check | Description |
|---|---|---|
| yinshiyou/make_loongarch64 | success | Make finished |
| yinshiyou/make_fate_loongarch64 | success | Make fate finished |
On 21/05/2024 15:51, J. Dekker wrote: > Some timers on certain device and test combinations can produce noisy > results, affecting the reliability of performance measurements. One > notable example of this is the Canaan K230 RISC-V development board. > > An option to adjust the number of samples by an exponent (--runs) has > been added, allowing developers to increase the sample count for more > reliable results. > > Signed-off-by: J. Dekker <jdek@itanimul.li> > --- > tests/checkasm/checkasm.c | 16 +++++++++++++++- > tests/checkasm/checkasm.h | 7 ++++--- > 2 files changed, 19 insertions(+), 4 deletions(-) > > diff --git a/tests/checkasm/checkasm.c b/tests/checkasm/checkasm.c > index 31ca9f6e2b..669f2be9c1 100644 > --- a/tests/checkasm/checkasm.c > +++ b/tests/checkasm/checkasm.c > @@ -72,6 +72,9 @@ > void (*checkasm_checked_call)(void *func, int dummy, ...) = checkasm_checked_call_novfp; > #endif > > +/* Trade-off between speed and accuracy */ > +uint64_t bench_runs = 1U << 10; > + > /* List of tests to invoke */ > static const struct { > const char *name; > @@ -820,7 +823,7 @@ static void bench_uninit(void) > static int usage(const char *path) > { > fprintf(stderr, > - "Usage: %s [--bench] [--test=<pattern>] [--verbose] [seed]\n", > + "Usage: %s [--bench] [--runs=<ptwo>] [--test=<pattern>] [--verbose] [seed]\n", > path); > return 1; > } > @@ -867,6 +870,17 @@ int main(int argc, char *argv[]) > state.test_name = arg + 7; > } else if (!strcmp(arg, "--verbose") || !strcmp(arg, "-v")) { > state.verbose = 1; > + } else if (!strncmp(arg, "--runs=", 7)) { > + l = strtoul(arg + 7, &end, 10); > + if (*end == '\0') { > + if (l > 30) { > + fprintf(stderr, "checkasm: error: runs exponent must be within the range 0 <= 30\n"); > + usage(argv[0]); > + } > + bench_runs = 1U << l; > + } else { > + return usage(argv[0]); > + } > } else if ((l = strtoul(arg, &end, 10)) <= UINT_MAX && > *end == '\0') { > seed = l; > diff --git a/tests/checkasm/checkasm.h b/tests/checkasm/checkasm.h > index 07fcc751ff..e05053cbf6 100644 > --- a/tests/checkasm/checkasm.h > +++ b/tests/checkasm/checkasm.h > @@ -167,7 +167,7 @@ extern AVLFG checkasm_lfg; > > static av_unused void *func_ref, *func_new; > > -#define BENCH_RUNS 1000 /* Trade-off between accuracy and speed */ > +extern uint64_t bench_runs; > > /* Decide whether or not the specified function needs to be tested */ > #define check_func(func, ...) (checkasm_save_context(), func_ref = checkasm_check_func((func_new = func), __VA_ARGS__)) > @@ -336,10 +336,11 @@ typedef struct CheckasmPerf { > av_unused const int sysfd = perf->sysfd;\ > func_type *tfunc = func_new;\ > uint64_t tsum = 0;\ > - int ti, tcount = 0;\ > + uint64_t ti, tcount = 0;\ > uint64_t t = 0; \ > + const uint64_t truns = bench_runs;\ > checkasm_set_signal_handler_state(1);\ > - for (ti = 0; ti < BENCH_RUNS; ti++) {\ > + for (ti = 0; ti < truns; ti++) {\ > PERF_START(t);\ > tfunc(__VA_ARGS__);\ > tfunc(__VA_ARGS__);\ Tested, works as intended LGTM, thanks
Lynne via ffmpeg-devel <ffmpeg-devel@ffmpeg.org> writes: > [[PGP Signed Part:Undecided]] > On 21/05/2024 15:51, J. Dekker wrote: >> Some timers on certain device and test combinations can produce noisy >> results, affecting the reliability of performance measurements. One >> notable example of this is the Canaan K230 RISC-V development board. >> An option to adjust the number of samples by an exponent (--runs) has >> been added, allowing developers to increase the sample count for more >> reliable results. >> Signed-off-by: J. Dekker <jdek@itanimul.li> >> --- >> tests/checkasm/checkasm.c | 16 +++++++++++++++- >> tests/checkasm/checkasm.h | 7 ++++--- >> 2 files changed, 19 insertions(+), 4 deletions(-)> > Tested, works as intended > LGTM, thanks Thanks pushed with fixed commit message.
diff --git a/tests/checkasm/checkasm.c b/tests/checkasm/checkasm.c index 31ca9f6e2b..669f2be9c1 100644 --- a/tests/checkasm/checkasm.c +++ b/tests/checkasm/checkasm.c @@ -72,6 +72,9 @@ void (*checkasm_checked_call)(void *func, int dummy, ...) = checkasm_checked_call_novfp; #endif +/* Trade-off between speed and accuracy */ +uint64_t bench_runs = 1U << 10; + /* List of tests to invoke */ static const struct { const char *name; @@ -820,7 +823,7 @@ static void bench_uninit(void) static int usage(const char *path) { fprintf(stderr, - "Usage: %s [--bench] [--test=<pattern>] [--verbose] [seed]\n", + "Usage: %s [--bench] [--runs=<ptwo>] [--test=<pattern>] [--verbose] [seed]\n", path); return 1; } @@ -867,6 +870,17 @@ int main(int argc, char *argv[]) state.test_name = arg + 7; } else if (!strcmp(arg, "--verbose") || !strcmp(arg, "-v")) { state.verbose = 1; + } else if (!strncmp(arg, "--runs=", 7)) { + l = strtoul(arg + 7, &end, 10); + if (*end == '\0') { + if (l > 30) { + fprintf(stderr, "checkasm: error: runs exponent must be within the range 0 <= 30\n"); + usage(argv[0]); + } + bench_runs = 1U << l; + } else { + return usage(argv[0]); + } } else if ((l = strtoul(arg, &end, 10)) <= UINT_MAX && *end == '\0') { seed = l; diff --git a/tests/checkasm/checkasm.h b/tests/checkasm/checkasm.h index 07fcc751ff..e05053cbf6 100644 --- a/tests/checkasm/checkasm.h +++ b/tests/checkasm/checkasm.h @@ -167,7 +167,7 @@ extern AVLFG checkasm_lfg; static av_unused void *func_ref, *func_new; -#define BENCH_RUNS 1000 /* Trade-off between accuracy and speed */ +extern uint64_t bench_runs; /* Decide whether or not the specified function needs to be tested */ #define check_func(func, ...) (checkasm_save_context(), func_ref = checkasm_check_func((func_new = func), __VA_ARGS__)) @@ -336,10 +336,11 @@ typedef struct CheckasmPerf { av_unused const int sysfd = perf->sysfd;\ func_type *tfunc = func_new;\ uint64_t tsum = 0;\ - int ti, tcount = 0;\ + uint64_t ti, tcount = 0;\ uint64_t t = 0; \ + const uint64_t truns = bench_runs;\ checkasm_set_signal_handler_state(1);\ - for (ti = 0; ti < BENCH_RUNS; ti++) {\ + for (ti = 0; ti < truns; ti++) {\ PERF_START(t);\ tfunc(__VA_ARGS__);\ tfunc(__VA_ARGS__);\
Some timers on certain device and test combinations can produce noisy results, affecting the reliability of performance measurements. One notable example of this is the Canaan K230 RISC-V development board. An option to adjust the number of samples by an exponent (--runs) has been added, allowing developers to increase the sample count for more reliable results. Signed-off-by: J. Dekker <jdek@itanimul.li> --- tests/checkasm/checkasm.c | 16 +++++++++++++++- tests/checkasm/checkasm.h | 7 ++++--- 2 files changed, 19 insertions(+), 4 deletions(-)