#define _POSIX_C_SOURCE 200809L
#include "xtc/xtc_engine.h"
#include <errno.h>
#include <math.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <sys/resource.h>
static double now(void)
{ struct timespec t; if (clock_gettime(CLOCK_MONOTONIC,&t)) abort(); return (double)t.tv_sec+(double)t.tv_nsec/1e9; }
static double cpu_now(void)
{ struct timespec t; if (clock_gettime(CLOCK_PROCESS_CPUTIME_ID,&t)) abort(); return (double)t.tv_sec+(double)t.tv_nsec/1e9; }
static int compare(const void *a,const void *b)
{ double x = *(const double *)a,y = *(const double *)b; return x < y ? -1 : x > y; }
static size_t number(const char *s,size_t maximum)
{
    char *end; unsigned long n;
    errno = 0; n = strtoul(s,&end,10);
    if (errno || !s[0] || *end || n < 1 || n > maximum) return 0;
    return (size_t)n;
}
int main(int argc,char **argv)
{
    size_t nodes,channels,rate,frames,blocks,i,j,id = 0,previous = 0;
    xtc_graph *g = NULL; xtc_plan *p = NULL;
    float *in = NULL,*left = NULL,*right = NULL;
    double *times = NULL,begin,compile,total = 0,cpu_begin,cpu;
    size_t misses = 0;
    struct rusage usage;
    int status = 1;
    if (argc != 6) return 1;
    nodes = number(argv[1],256); channels = number(argv[2],2); rate = number(argv[3],768000);
    frames = number(argv[4],65536); blocks = number(argv[5],100000);
    if (nodes < 2 || !channels || !rate || !frames || !blocks) return 1;
    in = calloc(frames,sizeof(float)); left = calloc(frames,sizeof(float)); right = calloc(frames,sizeof(float));
    times = calloc(blocks,sizeof(double));
    if (!in || !left || !right || !times || xtc_graph_create(nodes,&g) != XTC_OK) goto done;
    for (i = 0; i < nodes; ++i) {
        xtc_result r = i+1 == nodes ? xtc_graph_add_output(g,&id) :
            i+2 == nodes ? xtc_graph_add_meter(g,&id) : xtc_graph_add_gain(g,.999f,&id);
        if (r != XTC_OK || (i && xtc_graph_connect(g,previous,id) != XTC_OK)) goto done;
        previous = id;
    }
    begin = now();
    if (xtc_graph_compile(g,(double)rate,frames,&p) != XTC_OK) goto done;
    compile = now()-begin;
    for (i = 0; i < frames; ++i) in[i] = (float)sin((double)i*.1)*.1f;
    /* Warm caches outside the sample, then measure only the process call. */
    for (i = 0; i < 20; ++i) if (xtc_plan_process_stereo(p,in,NULL,NULL,NULL,NULL,left,channels == 2 ? right : NULL,frames) != XTC_OK) goto done;
    cpu_begin = cpu_now();
    for (i = 0; i < blocks; ++i) {
        begin = now();
        if (xtc_plan_process_stereo(p,in,NULL,NULL,NULL,NULL,left,channels == 2 ? right : NULL,frames) != XTC_OK) goto done;
        times[i] = now()-begin; total += times[i];
        if (times[i] > (double)frames/(double)rate) ++misses;
        for (j = 0; j < frames; ++j) if (!isfinite(left[j]) || (channels == 2 && !isfinite(right[j]))) goto done;
    }
    cpu = cpu_now()-cpu_begin;
    if (getrusage(RUSAGE_SELF,&usage)) goto done;
    qsort(times,blocks,sizeof(double),compare);
    printf("{\"nodes\":%zu,\"channels\":%zu,\"rate\":%zu,\"frames\":%zu,\"blocks\":%zu,"
        "\"compile_ms\":%.6f,\"mean_us\":%.6f,\"p99_us\":%.6f,\"max_us\":%.6f,\"deadline_us\":%.6f,"
        "\"load\":%.6f,\"graph_buffer_bytes\":%zu,\"deadline_misses\":%zu,\"process_cpu_ms\":%.6f,\"peak_rss_kib\":%ld}\n",nodes,channels,rate,frames,blocks,compile*1e3,total/(double)blocks*1e6,
        times[blocks*99/100]*1e6,times[blocks-1]*1e6,(double)frames/(double)rate*1e6,
        total/(double)blocks/((double)frames/(double)rate),nodes*frames*2*sizeof(float),misses,cpu*1e3,usage.ru_maxrss);
    status = 0;
done:
    free(in); free(left); free(right); free(times); xtc_plan_destroy(p); xtc_graph_destroy(g); return status;
}