代码

// References:
// [0] saffah_codex_6s_agg2, duck.ac submission #103829,
//     https://duck.ac/submission/103829 . Directly copied its accepted
//     packed S/T suffix automata, 80-byte T rows and Euler queries.
// [1] saffah_codex_6s_agg2, duck.ac submission #103353,
//     https://duck.ac/submission/103353 . Packed transitions and
//     query engine inherited through [0].
// [2] saffah_cc_v41_260924, duck.ac submission #99767,
//     https://duck.ac/submission/99767 . Packed S transitions and
//     original query engine inherited through [1].
// [3] saffah_cc_v41_260924, duck.ac submissions #87737 and #99553,
//     https://duck.ac/submission/87737 and
//     https://duck.ac/submission/99553 . Suffix automata, interval query,
//     ancestor painting and block-max ideas inherited through [2].
// No separate license notices appeared on these public submissions;
// authors, URLs and reused parts are credited here.
// Approach:
// Initialize each 80-byte T transition row using five aligned 16-byte
// stores. The old two 32-byte stores sometimes crossed cache-line
// boundaries because successive rows rotate through four offsets.
// Purpose:
// Measure whether avoiding split-line stores lowers official runtime
// below the exact current noi18c leaderboard threshold.
#include <string.h>
#include <stdint.h>
#include <immintrin.h>

#pragma GCC push_options
#pragma GCC target("avx2,popcnt,bmi,bmi2")

typedef unsigned char u8;
typedef unsigned int u32;
typedef unsigned long long u64;
typedef unsigned long ul;

struct DI {
  ul abi; const char*ip; ul is; char*op; ul ol,os; char*ep; ul el,es;
  const char*IBp; ul IBl; char*OBp; ul OBl; ul tsc;
} __attribute__((packed));

#define MAXS 500005
#define MAXST 1000016
#define MAXQ 100005
#define MAXT 1000008
#define MAXTT 2000016

static u32 bhead[MAXS+8], bnext[MAXST], szsub[MAXST], nxt[MAXST];
static u32 tin[MAXST], tout[MAXST], mxo[MAXST];
static u32 ord_[MAXST]; static int nord_;   // len-descending state order (lazy-Euler)
static int eul_ready;
// ancestor painting (see 思路): wl_last[x] = max own+1 among activated prefix-states
// whose suffix-link path passes through x  ==  MX(x, r) exactly.
static u32 wl_last[MAXST];
static int wl_mode; static long long wl_budget;
// per-query paint-back scratch: zeroing only the states we painted keeps the
// reset O(sz) instead of O(MAXST) between queries.
static u32 plist_[MAXST];

// ======================= SAM of S (dense 26-way transitions) ==============
// transitions of state p are at s_nxt[p*26 .. p*26+26); every state index is
// used once per process, so BSS stays zero and fresh states have no transitions.
// Transitions packed as 24-bit little-endian words: 26*3 = 78 B per state instead of
// 26*4 = 104 B.  State ids are <= 2*MAXS+8 < 2^24, so 24 bits are lossless.
// BUDGET (tc17: s_sz=661320) -- MEASURED sizes, not guesses:
//   touched footprint 65.6 MB -> 49.2 MB (-16.4 MB) = -4197 first-touch pages.
//   At the measured 244 ns/page that alone is -1.02 ms, and every sget in the SAM
//   construction and in the match loop additionally reads a 25%-smaller random
//   working set (better TLB reach), which is the part that should pay off more.
// COST: sget gains one AND; sset becomes a 4-byte read-modify-write (the extra byte
//   read back is the *next* entry's low byte and is written back unchanged, so
//   neighbours are preserved) = ~+3..5 uops per access.  Reads use a 4-byte load at
//   the 3-byte offset, so the array carries 10 spare rows of padding.
static u8 s_nxt[(2*MAXS+10)*78];
static u32 s_len[MAXST], s_link[MAXST];
static int s_sz, s_last;
static u32 s_own[MAXS];
static inline int sget(int p, int c){
  u32 x; __builtin_memcpy(&x, s_nxt + (size_t)p*78 + (size_t)c*3, 4);
  return (int)(x & 0xFFFFFFu);
}
static inline void sset(int p, int c, int t){
  size_t off = (size_t)p*78 + (size_t)c*3;
  u32 x; __builtin_memcpy(&x, s_nxt + off, 4);
  x = (x & 0xFF000000u) | ((u32)t & 0xFFFFFFu);   // keep next entry's low byte
  __builtin_memcpy(s_nxt + off, &x, 4);
}
static void build_sam_s(const char* S, int n){
  s_sz = 1; s_last = 1;
  s_len[1] = 0; s_link[1] = 0;
  memset(bhead, 0, (size_t)(n+2)*4);
  for(int i=0;i<n;i++){
    int c = S[i]-'a';
    int cur = ++s_sz;
    s_len[cur] = s_len[s_last]+1;
    { u32 L = s_len[cur]; bnext[cur] = bhead[L]; bhead[L] = (u32)cur; }
    szsub[cur] = 1; mxo[cur] = (u32)(i+1);
    s_own[i] = (u32)cur;
    int p = s_last;
    for(; p && !sget(p,c); p = (int)s_link[p]) sset(p,c,cur);
    if(!p) s_link[cur] = 1;
    else {
      int q = sget(p,c);
      if((int)s_len[p]+1 == (int)s_len[q]) s_link[cur] = (u32)q;
      else {
        int cl = ++s_sz;
        s_len[cl] = s_len[p]+1; s_link[cl] = s_link[q];
        { u32 L = s_len[cl]; bnext[cl] = bhead[L]; bhead[L] = (u32)cl; }
        szsub[cl] = 1; mxo[cl] = 0;
        memcpy(s_nxt + (size_t)cl*78, s_nxt + (size_t)q*78, 78);
        for(; p && sget(p,c)==q; p = (int)s_link[p]) sset(p,c,cl);
        s_link[q] = (u32)cl; s_link[cur] = (u32)cl;
      }
    }
    s_last = cur;
  }
}

// ======================= SAM of T, rebuilt per query (dense) ==============
static u8 t_nxt[(2*MAXT+10)*80] __attribute__((aligned(16)));
static u32 t_len[MAXTT], t_link[MAXTT];
static int t_sz, t_last;
static inline int tget(int p, int c){
  u32 x; __builtin_memcpy(&x, t_nxt + (size_t)p*80 + (size_t)c*3, 4);
  return (int)(x & 0xFFFFFFu);
}
static inline void tset(int p, int c, int t){
  size_t off = (size_t)p*80 + (size_t)c*3;
  u32 x; __builtin_memcpy(&x, t_nxt + off, 4);
  x = (x & 0xFF000000u) | ((u32)t & 0xFFFFFFu);
  __builtin_memcpy(t_nxt + off, &x, 4);
}
static inline void tzero(int p){
  u8* row = t_nxt + (size_t)p*80;
  __m128i z = _mm_setzero_si128();
  _mm_store_si128((__m128i*)(row+0), z);
  _mm_store_si128((__m128i*)(row+16), z);
  _mm_store_si128((__m128i*)(row+32), z);
  _mm_store_si128((__m128i*)(row+48), z);
  _mm_store_si128((__m128i*)(row+64), z);
}

// ============ suffix-link tree: len-bucket lists + two linear passes ======

static int s_sn;
// Pass 1 (ALWAYS needed): mxo[v] = max own+1 over the subtree of v, by a
// len-descending sweep (children strictly before parents).  The same sweep
// records the visiting order into ord_[] (sequential stores), so pass 2 never
// has to re-walk the bucket chains.
static void build_meta(void){
  int cnt = 0;
  for(int L = s_sn; L >= 0; L--){
    for(u32 v = bhead[L]; v; v = bnext[v]){
      ord_[cnt++] = v;
      u32 p = s_link[v];
      if(p && mxo[v] > mxo[p]) mxo[p] = mxo[v];
    }
  }
  nord_ = cnt;
}
// Pass 2 (LAZY): subtree sizes + preorder numbers.  Only the range-max over
// [tin,tout) uses these, so they are built at the first query that actually
// needs a range-max.  ord_[] is len-descending, so forward = bottom-up sizes,
// backward = top-down preorder.
static void build_intervals(void){
  for(int i=0;i<nord_;i++){
    u32 v = ord_[i]; u32 p = s_link[v];
    if(p) szsub[p] += szsub[v];
  }
  tin[1] = 1; nxt[1] = 2;
  for(int i=nord_-1;i>=0;i--){
    u32 v = ord_[i];
    if(v == 1) continue;
    u32 p = s_link[v];
    u32 t = nxt[p];
    tin[v] = t; tout[v] = t + szsub[v];
    nxt[p] = t + szsub[v];
    nxt[v] = t + 1;
  }
}

// ============ range max over the Euler array (fused block scans) ============
// Replaces the earlier "block prefix/suffix arrays + segment tree over blocks".
// MEASURED on the real judge (tools/probe.py, n=5e5 random 26-letter S, cycles):
//   old eactivate  70.15M   old build_meta 15.58M  old build_intervals 22.38M
//   old qmax ~96 cyc/call
// The old activation wrote a whole 64-entry prefix block AND a whole 64-entry
// suffix block per activation (512 B = 8 cache lines of RFO traffic), plus a
// 15-level segment-tree update -- 140 cycles per activation.  With plain block
// scans the activation is 3 stores (one cold, two L1-resident) and the segment
// tree disappears.
#define EBS 8
#define EBSH 3
#define GBS 128
#define GBSH 7
#define ENB ((MAXST>>EBSH)+8)
#define ESB ((ENB>>GBSH)+8)
static u32 ev[MAXST+8];
static u32 ebmax[ENB+8];
static u32 eb2[ESB+8];

static inline void eactivate(int leaf, u32 val){
  ev[leaf] = val;
  int b = leaf >> EBSH;
  ebmax[b] = val;
  eb2[b >> GBSH] = val;
}
#define AVX2T __attribute__((target("avx2")))
AVX2T static inline __m256i ldu256(const void *p){
  __m256i r; __asm__("vmovdqu %1, %0" : "=x"(r) : "m"(*(const __m256i *)p)); return r; }
// accumulate max over p[0..n) into acc for ANY n>=0 (n<8 must not use the
// overlapping tail load -- it would read BEFORE p and pick up foreign values)
AVX2T static inline __m256i accblk(__m256i acc, const u32* p, int n){
  if(n <= 0) return acc;
  if(n < 8){
    for(int i=0;i<n;i++) acc = _mm256_max_epu32(acc, _mm256_set1_epi32((int)p[i]));
    return acc;
  }
  int i = 0;
  for(; i+8 <= n; i += 8) acc = _mm256_max_epu32(acc, ldu256(p+i));
  if(i < n) acc = _mm256_max_epu32(acc, ldu256(p+n-8));   // overlapping tail load
  return acc;
}
AVX2T static inline u32 red256(__m256i acc){
  __m128i lo = _mm256_castsi256_si128(acc), hi = _mm256_extracti128_si256(acc,1);
  __m128i m = _mm_max_epu32(lo,hi);
  m = _mm_max_epu32(m, _mm_shuffle_epi32(m,_MM_SHUFFLE(1,0,3,2)));
  m = _mm_max_epu32(m, _mm_shuffle_epi32(m,_MM_SHUFFLE(2,3,0,1)));
  return (u32)_mm_cvtsi128_si32(m);
}
AVX2T static inline u32 scanmax(const u32* p, int n){
  if(n <= 0) return 0;
  return red256(accblk(_mm256_setzero_si256(), p, n));
}
static inline u32 qmax(int l, int r){          // max over [l,r)
  if(l>=r) return 0;
  int b1=l>>EBSH, b2=(r-1)>>EBSH;
  if(b1==b2) return scanmax(ev+l, r-l);
  __m256i acc = _mm256_setzero_si256();
  acc = accblk(acc, ev+l, ((b1+1)<<EBSH) - l);
  int j = r & (EBS-1);
  if(j) acc = accblk(acc, ev+(b2<<EBSH), j);
  else  acc = accblk(acc, ebmax+b2, 1);
  int lo=b1+1, hi=b2, cnt=hi-lo;             // whole blocks [lo,hi)
  if(cnt > 0){
    if(cnt <= GBS){
      acc = accblk(acc, ebmax+lo, cnt);
    } else {
      int s1=(lo+GBS-1)&~(GBS-1), s2=hi&~(GBS-1);
      if(s1>lo) acc = accblk(acc, ebmax+lo, s1-lo);
      if(s2>s1) acc = accblk(acc, eb2+(s1>>GBSH), (s2-s1)>>GBSH);
      if(hi>s2) acc = accblk(acc, ebmax+s2, hi-s2);
    }
  }
  return red256(acc);
}

// ============================== query handling ============================
struct QE { const char* t; int tl, l, r, idx; };
static QE qs[MAXQ];
static QE qs2[MAXQ];
static long long answers[MAXQ];
static int f_[MAXS];
static int cnt_[MAXS+2];

static char* OUTP;
static inline void emit(long long v){
  char b[24]; int c=0;
  if(v==0){ *OUTP++='0'; *OUTP++='\n'; return; }
  while(v){ b[c++] = (char)('0' + (int)(v%10)); v/=10; }
  while(c) *OUTP++ = b[--c];
  *OUTP++='\n';
}

static void run(const u8* in, ul insz, char* out){
  const char* p = (const char*)in;
  const char* e = p + insz;
  OUTP = out;

  while(p<e && (*p<'a'||*p>'z')) p++;
  const char* sstart = p;
  while(p<e && *p>='a'&&*p<='z') p++;
  int sn = (int)(p - sstart);
  build_sam_s(sstart, sn);

  while(p<e && (*p<'0'||*p>'9')) p++;
  int Q=0;
  while(p<e && *p>='0'&&*p<='9'){ Q = Q*10 + (*p-'0'); p++; }
  if(Q>MAXQ) Q=MAXQ;

  for(int i=0;i<Q;i++){
    while(p<e && (*p<'a'||*p>'z')) p++;
    const char* ts = p;
    while(p<e && *p>='a'&&*p<='z') p++;
    int tl = (int)(p-ts);
    if(tl>MAXT) tl=MAXT;
    while(p<e && (*p<'0'||*p>'9')) p++;
    int l=0; while(p<e && *p>='0'&&*p<='9'){ l=l*10+(*p-'0'); p++; }
    while(p<e && (*p<'0'||*p>'9')) p++;
    int r=0; while(p<e && *p>='0'&&*p<='9'){ r=r*10+(*p-'0'); p++; }
    qs[i].t = ts; qs[i].tl = tl; qs[i].l = l; qs[i].r = r; qs[i].idx = i;
  }

  s_sn = sn;
  int sz = s_sz;
  // ---- strategy choice ---------------------------------------------------
  // The ancestor-painting routes are KEPT in the file but no longer selected:
  // real-judge measurement showed their cost is sum_i depth(s_own[i]) steps, which
  // the 256-sample estimate can under-predict (a deep tree blows it up ~4x), while
  // the Euler route is now bounded and cheap: with the block-scan activation its
  // fixed cost is 34 cyc/state (intervals) + 20 cyc/activation + 113 cyc/qmax.
  // Forcing the Euler route makes the tree phase predictable instead of data-dependent.
  wl_mode = 0; wl_budget = 0;
  if(!wl_mode) build_meta();
  eul_ready = 0;
  // ev / ebmax / etree are zero initialized (BSS): no clearing needed

  { // counting sort of the queries by r
    int mx = sn+1;
    memset(cnt_, 0, (size_t)(mx+2)*4);
    for(int i=0;i<Q;i++){ int rr = qs[i].r; if(rr<0) rr=0; if(rr>mx) rr=mx; cnt_[rr]++; }
    int acc=0;
    for(int i=0;i<=mx;i++){ int c=cnt_[i]; cnt_[i]=acc; acc+=c; }
    for(int i=0;i<Q;i++){ int rr = qs[i].r; if(rr<0) rr=0; if(rr>mx) rr=mx; qs2[cnt_[rr]++] = qs[i]; }
  }

  int act = 0;   // positions < act already activated
  long long wl_work = 0;
  for(int qi=0; qi<Q; qi++){
    const QE& q = qs2[qi];
    int need = q.r;                 // activate positions 0..r-1
    if(need > sn) need = sn;
    if(need < 0) need = 0;
    int npaint = 0;
    if(wl_mode == 2){
      // downward sweep, stop at the first state already painted this query:
      // the first state painted gets the largest own+1, which is exactly MX(x, need)
      for(int i=need-1;i>=0;i--){
        int a = (int)s_own[i]; u32 val = (u32)(i+1);
        while(a != 1 && !wl_last[a]){ wl_last[a] = val; plist_[npaint++] = (u32)a; a = (int)s_link[a]; }
      }
    } else if(wl_mode){
      for(; act<need; act++){
        int a = (int)s_own[act]; u32 val = (u32)(act+1);
        wl_last[a] = val; wl_work++;
        while(a != 1){ a = (int)s_link[a]; wl_last[a] = val; wl_work++; }
        if(wl_work > wl_budget){ wl_mode = 0; break; }   // blew the budget
      }
      if(!wl_mode){                 // fell back mid-activation: replay into the Euler struct
        build_meta(); build_intervals(); eul_ready = 1;
        for(int i=0;i<act;i++){ int v = (int)s_own[i]; eactivate((int)tin[v], (u32)(i+1)); }
        for(; act<need; act++){ int v = (int)s_own[act]; eactivate((int)tin[v], (u32)(act+1)); }
      }
    } else if(eul_ready){
      for(; act<need; act++){
        int v = (int)s_own[act];
        eactivate((int)tin[v], (u32)(act+1));
      }
    } else if(need > act) act = need;
    const char* T = q.t;
    int tl = q.tl;
    int l0 = q.l - 1;
    int r1 = q.r - 1;
    int maxlen = q.r - q.l + 1;
    if(maxlen < 0) maxlen = 0;
    int v = 1, len = 0, e = -1;   // e = witness end position of the current match
    for(int i=0;i<tl;i++){
      int c = T[i]-'a';
      // fast path: the match extends in place at the witness (f[i] <= f[i-1]+1, so len+1 is optimal)
      if(len > 0 && e < r1 && sstart[e+1]-'a' == c){
        v = sget(v,c); len++; e++;
        f_[i] = len;
        continue;
      }
      while(v!=1 && !sget(v,c)){ v = (int)s_link[v]; len = (int)s_len[v]; }
      int nx = sget(v,c);
      if(nx){ v = nx; len++; } else { v = 1; len = 0; }
      e = -1;
      // clip the match to S[l..r]: longest suffix whose endpos hits [l+len-1, r-1]
      while(len>0){
        if(len > maxlen){
          len = maxlen;
          while(v != 1 && len <= (int)s_len[s_link[v]]) v = (int)s_link[v];
          if(len == 0) break;
        }
        u32 m;
        if(mxo[v] <= (u32)q.r) m = mxo[v];
        else {
          if(!eul_ready){
            build_intervals();
            for(int i2=0;i2<act;i2++){ int vv=(int)s_own[i2]; eactivate((int)tin[vv], (u32)(i2+1)); }
            eul_ready = 1;
          }
          m = qmax((int)tin[v],(int)tout[v]);
        }
        // lengths in this state's class that can still satisfy the test
        int lim = (int)m - l0;
        if(lim >= len){ e = (int)m - 1; break; }
        int pl = (int)s_len[s_link[v]];
        if(lim > pl){ len = lim; e = (int)m - 1; break; }
        len = pl;
        if(len == 0) break;
        v = (int)s_link[v];
      }
      f_[i] = len;
    }
    if(wl_mode == 2){ for(int k=0;k<npaint;k++) wl_last[plist_[k]] = 0; }
    // SAM(T) -> g[], accumulate
    t_sz=1; t_last=1;
    t_len[1]=0; t_link[1]=0;
    tzero(1);
    long long ans=0;
    for(int i=0;i<tl;i++){
      int c = T[i]-'a';
      int cur = ++t_sz;
      t_len[cur] = t_len[t_last]+1; t_link[cur]=0;
      tzero(cur);
      int pp = t_last;
      for(; pp && !tget(pp,c); pp = (int)t_link[pp]) tset(pp,c,cur);
      int lk;
      if(!pp) lk = 1;
      else {
        int qq = tget(pp,c);
        if((int)t_len[pp]+1 == (int)t_len[qq]) lk = qq;
        else {
          int cl = ++t_sz;
          t_len[cl] = t_len[pp]+1; t_link[cl] = t_link[qq];
          memcpy(t_nxt + (size_t)cl*80, t_nxt + (size_t)qq*80, 80);
          for(; pp && tget(pp,c)==qq; pp = (int)t_link[pp]) tset(pp,c,cl);
          t_link[qq] = (u32)cl; lk = cl;
        }
      }
      t_link[cur] = (u32)lk;
      t_last = cur;
      int g = (int)t_len[lk];
      int m = g > f_[i] ? g : f_[i];
      ans += (long long)(i+1) - m;
    }
    answers[q.idx] = ans;
  }
  for(int i=0;i<Q;i++) emit(answers[i]);
}

#pragma GCC pop_options

#ifndef LOCAL
int main(){ return 0; }
extern "C" void __libc_start_main(void*mm,int argc,char**argv){
  ul *p=(ul*)(argv+argc+1);
  while(*p) p++; p++;
  DI *d=0; for(; p[0]; p+=2) if(p[0]==0x6b637564UL){ d=(DI*)p[1]; break; }
  if(d){
    const u8* in=(const u8*)d->IBp; ul insz=d->IBl;
    if(!insz && d->is){ in=(const u8*)d->ip; insz=d->is; }
    run(in,insz,d->op);
    d->os=(ul)(OUTP-d->op);
  }
  __asm__ volatile("syscall"::"a"(60),"D"(0):"rcx","r11","memory");
  for(;;);
}
#endif

评测结果