/* Diagnostic-only exclusive buckets; included only by the copied worker. */
#ifndef LOCAL_PROBE_PROFILE_H
#define LOCAL_PROBE_PROFILE_H
#ifndef _WIN32_WINNT
#define _WIN32_WINNT 0x0600
#endif
#include <windows.h>
#include <stdint.h>
#include <cpuid.h>
#include "local_probe.h"
enum { PF_OTHER, PF_INCREMENT, PF_PERTURB, PF_ZERO, PF_ASSEMBLY,
       PF_BASELINE, PF_INIT, PF_GAS_PREP, PF_RETAINED, PF_FALLBACK,
       PF_CONTEXT, PF_SNAPSHOT, PF_RESTORE, PF_NODE, PF_PORT,
       PF_MECHANICAL, PF_GAS_EQUATIONS, PF_OUTPUTS, PF_PIPE,
       PF_FINITE, PF_DISPATCH, PF_FULL_FALLBACK, PF_CATEGORIES };
/* row 0 = outer callback, row 1 = baseline, row 2+g = probe group g. */
typedef struct { uint64_t ticks,intervals; } PfBucket;
extern PfBucket pf_buckets[LP_NC+2][PF_CATEGORIES],*pf_current;
extern uint64_t pf_previous_tick;
extern unsigned pf_row;
extern int pf_coarse;
extern const unsigned char pf_affected[LP_NC][LP_NO];
extern uint64_t pf_operations[LP_NC][2];
static inline uint64_t pf_clock(void){
    unsigned lo,hi;
    __asm__ __volatile__("lfence\n\trdtsc\n\tlfence" : "=a"(lo),"=d"(hi) :: "memory");
    return ((uint64_t)hi<<32)|lo;
}
static inline void pf_mark(unsigned category) {
    uint64_t t=pf_clock();
    pf_current->ticks+=t-pf_previous_tick;
    pf_current->intervals++;
    pf_previous_tick=t;pf_current=&pf_buckets[pf_row][category];
}
#define PF_MARK(category) pf_mark(category)
#define PF_SCOPE(row,category) do {pf_row=(row);pf_mark(category);} while(0)
#define PF_PROBE(category) do {if(lp_color>=0)pf_mark(category);} while(0)
void pf_initialize(void);void pf_finish(void);
int pf_select(void);void pf_flush(uint64_t,uint64_t);
void pf_eval_count(void);
static inline void pf_operation(int position){
    int retained=pf_affected[lp_color][position];
    pf_operations[lp_color][retained?0:1]++;
    PF_MARK(retained?PF_RETAINED:PF_FALLBACK);
}
void pf_open(void);void pf_close(void);
void pf_snapshot(int,NativePropertyCache*,NativePipeCache*);
void pf_save(double*,double*,double*,double*,double*);
int pf_reuse(int,NativePropertyCache*,NativePipeCache*,double*,double*,double*,double*,double*);
int pf_lp_eval(double,const double*,double*,double*,ModelJacobianWorkspace*);
void lp_jac_time_end(uint64_t,uint64_t);
void pf_validate_matrix(double,const double*,const double*);
#endif