> On Jun 14, 2024, at 19:09, Martin Storsjö <mar...@martin.st> wrote: > > The default timer register pmccntr_el0 usually requires enabling > access with e.g. a kernel module. > > On macOS, using cntvct_el0 gives measurements with the same > magnitude as mach_absolute_time (which is used currently), but > possibly with a little less overhead/noise. > --- > cntvct_el0 should have less noise than mach_absolute_time or > clock_gettime. > > In one tested case, the cntvct_el0 timer has a frequency of 25 MHz > (readable via the register cntfrq_el0). > --- > libavutil/aarch64/timer.h | 11 ++++++++++- > 1 file changed, 10 insertions(+), 1 deletion(-) > > diff --git a/libavutil/aarch64/timer.h b/libavutil/aarch64/timer.h > index fadc9568f8..922b0c5598 100644 > --- a/libavutil/aarch64/timer.h > +++ b/libavutil/aarch64/timer.h > @@ -24,7 +24,7 @@ > #include <stdint.h> > #include "config.h" > > -#if HAVE_INLINE_ASM && !defined(__APPLE__) > +#if HAVE_INLINE_ASM > > #define AV_READ_TIME read_time > > @@ -33,7 +33,16 @@ static inline uint64_t read_time(void) > uint64_t cycle_counter; > __asm__ volatile( > "isb \t\n" > +#if defined(__ANDROID__) || defined(__APPLE__) > + // cntvct_el0 has lower resolution than pmccntr_el0, but is usually > + // accessible from user space by default. > + "mrs %0, cntvct_el0 " > +#else > + // pmccntr_el0 has higher resolution, but is usually not accessible > + // from user space by default (but access can be enabled with a > custom > + // kernel module). > "mrs %0, pmccntr_el0 " > +#endif > : "=r"(cycle_counter) :: "memory" ); > > return cycle_counter;
LGTM, thanks! _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
