aulevel_performance.c

#include <re.h>
#include <rem.h>
#include <stdint.h>

enum {
	SILENCE_Q = 1024 * 1024, /* Quadratic sample value for silence */
};


static bool auframe_silence(struct auframe *af)
{
	const int16_t *v;
	int32_t sum = 0;
	size_t i;

	v = af->sampv;
	for (i = 0; i < af->sampc; i++) {
		sum += v[i] * v[i];

		if (sum > (int32_t)(i + 1) * SILENCE_Q)
			return false;
	}

	return true;
}


static bool auframe_silence2(struct auframe *af)
{
	return auframe_level(af) < -30.;
}


int main(void)
{
	uint64_t start, end;
	int16_t testv[1920] = {0, 0};
	struct auframe af;
	bool ret;
	int cnt = 0;

	auframe_init(&af, AUFMT_S16LE, testv, ARRAY_SIZE(testv), 48000, 2);

	for (int j = 0; j < 2; j++) {
		cnt   = 0;
		start = tmr_jiffies_usec();
		for (int i = 0; i < 2000; i++) {
			ret = auframe_silence(&af);
			if (ret)
				cnt++;
			af.level = AULEVEL_UNDEF;
		}
		end = tmr_jiffies_usec();

		re_printf("auframe_silence %d usecs (%d)\n", end - start, cnt);

		cnt   = 0;
		start = tmr_jiffies_usec();
		for (int i = 0; i < 2000; i++) {
			ret = auframe_silence2(&af);
			if (ret)
				cnt++;
			af.level = AULEVEL_UNDEF;
		}
		end = tmr_jiffies_usec();

		re_printf("auframe_silence2 %d usecs (%d)\n", end - start,
			  cnt);
	}
	return 0;
}

Didn't realized that yours is faster. Okay, then I replace the auframe_silence() in my PR.

The compare is so slow?

if (sum > (int32_t)(i + 1) * SILENCE_Q)

Or why?

Yes I think so. For silence its done 1920 times (20ms audio stereo). For non silence your code is much faster (if early max values) but I think we can assume ~50% of a normal conversation could be silence (since only one person is talking).

We found that the example code has to be compiled also with same optimization level like rem. But anyway your silence detection is slightly faster:

auframe_silence2 1713 usecs (2000)
auframe_silence 2318 usecs (2000)
auframe_silence2 683 usecs (2000)
auframe_silence 2341 usecs (2000)

Also I tried with this code:

bool auframe_silence(struct auframe *af)
{
	const int16_t *v;
	int32_t sum = 0;
	int64_t b = SILENCE_Q;
	size_t i;
	size_t len = af->sampc;

	v = af->sampv;
	for (i = 0; i < len; i++) {
		sum += v[i] * v[i];
		b += SILENCE_Q;

		if (sum > b)
			return false;
	}

	return true;
}

Here b += SILENCE_Q; and if (sum > b) leads to the performance loss.