代码

// ===== 引用区（REFERENCES）=====
// [1] duck.ac 账号 saffah_cc_v41_agg1，提交 #130884
//     <https://duck.ac/submission/130884>（题 1013a，361.789 ms，Accepted）。
//     —— 本文件正文（本引用区之后的第一条预处理指令起至文件末尾）= 该提交的**代码正文逐字节副本**；
//     本发相对它的唯一改动见下方【思路区】。 该件正文自带的上游引用链/署名（含 saffah_codex_6a_agg3 等公开提交）在原提交头部注释中，本发未改动其代码正文。
// [2] duck.ac 题目页 <https://duck.ac/problem/1013a>（站点 FAQ 明示：提交的代码将会被公开，所有人可见）。
// LICENSE：上述均为 duck.ac 公开提交，无第三方许可证声明、非来自任何外部仓库；
//     按“账号 + 原提交 URL + 所用内容”具名引用使用，遵守站点公开规则，不附加额外限制。
//     本件未参考任何已发表论文 / 外部开源仓库。
// ===== 思路区（本发目的与改动）=====
// 【本发单变量（唯一改动）】文件级 #pragma GCC target 内的 tune= 由 skylake 改为 broadwell（仅改既有行的一个 token，未新增/重复 pragma）。
// 【依据】本队跨题经验：tune 单轴在判题机上的符号与量级需逐题单发（mmm 家族公开提交注释记录 skylake→broadwell 实测 −3.75%）。
// 【等价性】tune= 只影响指令调度/选择，不改变整数语义 ⇒ 输出逐位不变（本机校验和与基座相同）。
// 【目的】试验性/测量件：把 tune 档位交由判题机冷态单发定价，不改算法。
// ===== 代码正文 =====
#define MF_PFA 1
#define MF_KSPAD 0
#define STRIDE 16
#define MF_PFA 1
#define MF_KSPAD 0
#define STRIDE 16
#define MF_BUILD_E1 1
#define MF_BAND 1
#define MF_QCOEF (43)
#define A13T_PFW(p0) __asm__ __volatile__("prefetchw %0" :: "m"(*(const char *)(p0)))
#define A13V_BINSC(x) ((u32)(((u32)(x) * g_binM) >> g_binS))

#define MF_PFB 32
#define MF_PFB1 64
#define MF_PFB2 64
#define MF_PFB3 8
#define MF_NOSDMP 1
#define MAXQ 256
#pragma GCC optimize("O3,unroll-loops,no-strict-aliasing,live-range-shrinkage,no-tree-ch")
#pragma GCC target("avx2,bmi,bmi2,popcnt,lzcnt,tune=broadwell")
#define MF_NOFILTB 1












#include <immintrin.h>
#include <type_traits>
#include <sys/mman.h>

static inline __m256i LDU(const void *p) {
__m256i v;
__asm__("vmovdqu %1, %0" : "=x"(v) : "m"(*(const __m256i *)p));
return v;
}
static inline __m256i LDA(const void *p) {   
__m256i v;
__asm__("vmovdqa %1, %0" : "=x"(v) : "m"(*(const __m256i *)p));
return v;
}

static inline void STU(void *p, __m256i v) {
__asm__ volatile("vmovdqu %1, %0" : "+m"(*(__m256i *)p) : "x"(v));
}
static inline void STA(void *p, __m256i v) {  
__asm__ volatile("vmovdqa %1, %0" : "+m"(*(__m256i *)p) : "x"(v));
}
static inline __m128i LDQ(const void *p) {
__m128i v;
__asm__("vmovdqu %1, %0" : "=x"(v) : "m"(*(const __m128i *)p));
return v;
}




#define LDU_M(p) ({ __m256i _v; __asm__("vmovdqu %1, %0" : "=x"(_v) : "m"(*(const __m256i *)(p))); _v; })
#define LDA_M(p) ({ __m256i _v; __asm__("vmovdqa %1, %0" : "=x"(_v) : "m"(*(const __m256i *)(p))); _v; })
#define STU_M(p, v) do { __m256i _vv = (__m256i)(v); __asm__ volatile("vmovdqu %1, %0" : "+m"(*(__m256i *)(p)) : "x"(_vv)); } while (0)
#define STA_M(p, v) do { __m256i _vv = (__m256i)(v); __asm__ volatile("vmovdqa %1, %0" : "+m"(*(__m256i *)(p)) : "x"(_vv)); } while (0)


#ifdef LOCAL_TEST
#include <cstdio>
#include <cstdlib>
#include <sys/mman.h>
#include <ctime>
#else
#ifdef __cplusplus
extern "C" void *malloc(unsigned long);
#else
void *malloc(unsigned long);
#endif
#endif

typedef unsigned u32;
typedef unsigned short u16;
#define AMBD_CAP 65536
static u32 s_abi[AMBD_CAP];
static const u32 *s_abp[AMBD_CAP];
static __m256i s_abqT[AMBD_CAP], s_abqTh[AMBD_CAP];
typedef unsigned char u8;
typedef unsigned long long u64;





#define LDU256(p) ({ __m256i _v256; __asm__("vmovdqu %1, %0" : "=x"(_v256) : "m"(*(const __m256i *)(p))); _v256; })


#ifndef MAXN
#define MAXN 1000005
#endif
#define MAXK 8
#define MF_SPL ((size_t)300064)











#ifndef MF_APF
#define MF_APF 0
#endif
#ifndef MF_QCOEF
#endif


#ifndef MF_KSPAD
#endif

#ifndef MF_FILTAUTO
#define MF_FILTAUTO 1
#endif

#ifndef MF_NT
#define MF_NT 1
#endif
#ifndef MF_FR_NOSORT
#define MF_FR_NOSORT 0
#endif
#ifndef MF_FR_NOCAND
#define MF_FR_NOCAND 0
#endif
#ifndef MF_BUILD_NOPOOL
#define MF_BUILD_NOPOOL 0
#endif
#ifndef MF_FR_NOREAD
#define MF_FR_NOREAD 0
#endif
#ifndef MF_NOSDMP
#define MF_NOSDMP 0
#endif




#ifndef MF_FB2
#define MF_FB2 0
#endif
#ifndef MF_FB3
#define MF_FB3 1
#endif

#ifndef MF_PLEN
#define MF_PLEN 1
#endif
#ifndef MF_BUDGETMB
#define MF_BUDGETMB 1900
#endif
#ifndef MF_NOFILTB
#define MF_NOFILTB 0
#endif


#ifndef MF_PFB
#endif



#ifndef MF_ASCR
#define MF_ASCR 1
#endif















#ifndef MF_WTRIM
#define MF_WTRIM 0
#endif
#define AS_WORDS 20480
#ifndef MF_PFA
#endif
#ifndef MF_FR_NOMETA
#define MF_FR_NOMETA 0
#endif

#ifndef MAXQ
#endif

static u32 s_ord[MAXK][MAXN];
static u32 s_gt[MAXK][MAXN];
static u32 s_pm[(size_t)MAXN * STRIDE] __attribute__((aligned(64)));
static u8 s_bd[(size_t)MAXN * MAXK];
static u32 s_g[MAXN];
static u32 s_qord[MAXN], s_tmp[MAXN], s_cntv[MAXN];
static u32 fixed_fringe_keys[7][MAXN];
static u16 s_bkt[MAXN];  
static u32 s_nid[MAXN];
static u32 s_pos[MAXK][MAXN];
static u32 s_posp[(size_t)MAXK * MAXN];   
static u64 s_facc[(size_t)(MAXK - 1) * (((MAXN) + 63) / 64 + 16)];
static u32 s_bnde[(size_t)MAXK * (MAXQ + 2)];   
static u64 *s_fbm = 0;
static u64 s_fbuf[8192] __attribute__((aligned(64)));
static __m256i khi8v, khi8hv;
static u32 g_Qc = 32;
static u32 g_fbm_W = 0;
static int g_use_filt = 0;
static int g_lexsort = 0;
static int g_nofilt = 0;
static u32 s_fpos[(MAXK + 1) * MAXQ];
static u32 s_bval[(MAXK + 1) * MAXQ];
static u64 *s_bs = 0;
static u64 s_acc[MAXN / 64 + 256] __attribute__((aligned(64)));
static u32 *s_sdmp[MAXK];
static u32 *inc_anchor=0; static size_t inc_cap=0; static bool inc_on=false;
static u32 s_bandrec[(size_t)MAXN * 8];
static u32 s_bandacc[MAXN];
static u64 s_bandvec[MAXN];
static u64 s_ascr[AS_WORDS] __attribute__((aligned(64)));
static u32 s_maxr[(size_t)MAXK * MAXK * MAXQ];









static u8 *s_sig = 0;
static u8 a13_sigrow[(size_t)MF_SPL * 8] __attribute__((aligned(64)));
static int g_sig_on = 0;
static int g_sig_merged = 0;
static u32 g_sigsh = 0;



static u32 g_binM = 0, g_binS = 0;
static u32 s_pofs[(size_t)MAXK * MAXQ];
static u32 s_plen[(size_t)MAXK * MAXQ];
static int g_plen_on = 0;

static u32 g_W, g_Q, g_B;
static u64 g_bmag;  
static u32 g_KS;   
static int g_nosort = 0;
static int g_nosdmp = 0;
static int g_skip_and = 0, g_skip_fringe = 0;

#define FPOS(d, b) s_fpos[(size_t)(d) * MAXQ + (b)]
#define BVAL(d, b) s_bval[(size_t)(d) * MAXQ + (b)]

static void *pool_alloc(size_t bytes) {
void *raw = malloc(bytes + (2u << 20));
if (!raw) return 0;
void *p = (void *)(((size_t)raw + (2u << 20) - 1) & ~(size_t)((2u << 20) - 1));
if (bytes >= (16u << 20)) madvise(p, (bytes + (2u << 20) - 1) & ~(size_t)((2u << 20) - 1), MADV_HUGEPAGE);
return p;
}






__attribute__((target("avx2,popcnt")))
static inline u32 hsum256(__m256i v) {


__m128i lo = _mm256_castsi256_si128(v);
__m128i hi = _mm256_extracti128_si256(v, 1);
__m128i s = _mm_add_epi64(lo, hi);
return (u32)((u64)_mm_cvtsi128_si64(s) + (u64)_mm_extract_epi64(s, 1));
}
template<int KK, bool BoundedBand=false>
__attribute__((target("avx2,popcnt")))
static u32 and_popcount_range(const u64 *const *bs, u32 Wr, u32 rem) {
if constexpr(BoundedBand) if(Wr>=16u)__builtin_unreachable();
const __m256i lm = _mm256_set1_epi8(0x0f);
const __m256i lk = _mm256_setr_epi8(0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,
0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4);
const __m256i z = _mm256_setzero_si256();
__m256i tot = z, acc = z;
u32 cnt = 0, total = 0;
const u32 Wr4 = Wr & ~3u;
for (u32 w = 0; w < Wr4; w += 4) {


__m256i a, b2;
if (KK >= 4) {
a  = _mm256_and_si256(LDU256((bs[0] + w)), LDU256((bs[1] + w)));
b2 = _mm256_and_si256(LDU256((bs[2] + w)), LDU256((bs[3] + w)));
for (int d = 4; d + 1 < KK; d += 2) {
a  = _mm256_and_si256(a, LDU256((bs[d] + w)));
b2 = _mm256_and_si256(b2, LDU256((bs[d + 1] + w)));
}
if ((KK & 1) == 0) { int d = KK - 1; a = _mm256_and_si256(a, LDU256((bs[d] + w))); }
a = _mm256_and_si256(a, b2);
} else {
a = LDU256((bs[0] + w));
for (int d = 1; d < KK; d++) a = _mm256_and_si256(a, LDU256((bs[d] + w)));
}
__m256i lo = _mm256_and_si256(a, lm);
__m256i hi = _mm256_and_si256(_mm256_srli_epi16(a, 4), lm);
acc = _mm256_add_epi8(acc, _mm256_add_epi8(_mm256_shuffle_epi8(lk, lo), _mm256_shuffle_epi8(lk, hi)));
if constexpr(!BoundedBand) {
if (++cnt == 31) { tot = _mm256_add_epi64(tot, _mm256_sad_epu8(acc, z)); acc = z; cnt = 0; }
}
}
tot = _mm256_add_epi64(tot, _mm256_sad_epu8(acc, z));
total = hsum256(tot);
for (u32 w = Wr4; w < Wr; w++) {
u64 v = bs[0][w];
for (int d = 1; d < KK; d++) v &= bs[d][w];
total += (u32)__builtin_popcountll(v);
}
if (rem) {
u64 v = bs[0][Wr];
for (int d = 1; d < KK; d++) v &= bs[d][Wr];
total += (u32)__builtin_popcountll(v & ((1ull << rem) - 1));
}
return total;
}

template<int KK>
__attribute__((target("avx2,popcnt")))
__attribute__((flatten))
static void query_group(u32 N, u32 *out, u32 ds, u32 q0, u32 q1, u32 Q, u32 W) {
const int k = KK;
const int K1 = KK - 1;
#if MF_ASCR





const u32 d1 = (ds == 0) ? 1u : 0u;
const u32 e1 = (d1 < ds) ? d1 : d1 - 1;
{
u32 *cntv = s_cntv;
for (u32 v = 0; v <= Q; v++) cntv[v] = 0;
for (u32 qi = q0; qi < q1; qi++) {
#if MF_PFB > 0
if (qi + MF_PFB < q1) _mm_prefetch((const char *)(s_bd + (size_t)s_qord[qi + MF_PFB] * MAXK + d1), _MM_HINT_T0);
#endif
cntv[s_bd[(size_t)s_qord[qi] * MAXK + d1] + 1]++;
}
{ u32 ac = q0; for (u32 v = 0; v <= Q; v++) { u32 c = cntv[v]; cntv[v] = ac; ac += c; } }
for (u32 qi = q0; qi < q1; qi++) { if (qi + 64 < q1) _mm_prefetch((const char *)(s_bd + (size_t)s_qord[qi + 64] * MAXK + d1), _MM_HINT_T0); u32 id = s_qord[qi]; s_tmp[cntv[s_bd[(size_t)id * MAXK + d1] + 1]++] = id; }
for (u32 qi = q0; qi < q1; qi++) s_qord[qi] = s_tmp[qi];
}
#else
const u32 d1 = 0, e1 = 0;
#endif


if (g_lexsort) {
u32 *cntv = s_cntv;
for (int dd = k - 1; dd >= 0; dd--) {
if (dd == ds) continue;
for (u32 v = 0; v <= Q; v++) cntv[v] = 0;
for (u32 qi = q0; qi < q1; qi++) cntv[s_bd[(size_t)s_qord[qi] * MAXK + dd] + 1]++;
{ u32 ac = q0; for (u32 v = 0; v <= Q; v++) { u32 c = cntv[v]; cntv[v] = ac; ac += c; } }
for (u32 qi = q0; qi < q1; qi++) { u32 id = s_qord[qi]; s_tmp[cntv[s_bd[(size_t)id * MAXK + dd] + 1]++] = id; }
for (u32 qi = q0; qi < q1; qi++) s_qord[qi] = s_tmp[qi];
}
}
#ifdef PF_DIST
for (u32 qi = q0; qi < q0 + PF_DIST && qi + PF_DIST < q1; qi++) {
u32 j = s_qord[qi + PF_DIST];
const u8 *bdn = s_bd + (size_t)j * MAXK;
for (int e = 0; e < K1; e++) {
int d = (e < ds) ? e : e + 1;
const char *pp = (const char *)(s_bs + ((size_t)e * (Q + 1) + bdn[d]) * W);
_mm_prefetch(pp, _MM_HINT_T0);
_mm_prefetch(pp + 64, _MM_HINT_T0);
_mm_prefetch(pp + 128, _MM_HINT_T0);
}
}
#endif
#if MF_ASCR
{
u32 inc_used=0;
if(inc_on) for(u32 w=0;w<((N+63u)>>6);w++) s_ascr[w]=0;
u32 qi = q0;
while (qi < q1) {
u32 b1 = s_bd[(size_t)s_qord[qi] * MAXK + d1];
u32 qe = qi + 1;
while (qe < q1 && s_bd[(size_t)s_qord[qe] * MAXK + d1] == b1) qe++;
const u64 *bp1 = g_plen_on ? (s_bs + s_pofs[(size_t)e1 * MAXQ + b1])
: (s_bs + ((size_t)e1 * (Q + 1) + b1) * W);
if(inc_on){
u32 end=(b1<Q)?FPOS(d1,b1):(u32)N;
while(inc_used<end){u32 r=inc_anchor[inc_used++];s_ascr[r>>6]|=1ull<<(r&63);}
bp1=s_ascr;
} else {
u32 mx = 1;
for (u32 t = qi; t < qe; t++) { u32 rr = s_gt[ds][s_qord[t]]; if (rr > mx) mx = rr; }
u32 nwd = (mx >> 6) + 1;
if (nwd <= AS_WORDS) {
const u64 *src = bp1;
for (u32 w = 0; w < nwd; w++) s_ascr[w] = src[w];
bp1 = s_ascr;
}
}
for (u32 qq = qi; qq < qe; qq++) {
u32 i = s_qord[qq];
const u8 *bd = s_bd + (size_t)i * MAXK;
#if MF_PFA > 0
{
u32 qj = qq + MF_PFA;
if (qj < qe) {
u32 j = s_qord[qj];
_mm_prefetch((const char *)(s_bd + (size_t)j * MAXK), _MM_HINT_T0);
_mm_prefetch((const char *)(s_gt[ds] + j), _MM_HINT_T0);
}
}
#endif
const u32 R = s_gt[ds][i];
u32 cnt = 0;
if (R && !g_skip_and) {
const u64 *bp[MAXK];
for (int e = 0; e < K1; e++) {
if (e == (int)e1) bp[e] = bp1;
else { int d = (e < ds) ? e : e + 1;
bp[e] = g_plen_on ? (s_bs + s_pofs[(size_t)e * MAXQ + bd[d]])
: (s_bs + ((size_t)e * (Q + 1) + bd[d]) * W); }
}
cnt = and_popcount_range<KK - 1>(bp, R >> 6, R & 63u);
}
out[i] = cnt;
}
qi = qe;
}
}
#else
for (u32 qi = q0; qi < q1; qi++) {
u32 i = s_qord[qi];
const u8 *bd = s_bd + (size_t)i * MAXK;
#if MF_PFA > 0
{
u32 qj = qi + MF_PFA;
if (qj < q1) {
u32 j = s_qord[qj];
_mm_prefetch((const char *)(s_bd + (size_t)j * MAXK), _MM_HINT_T0);
_mm_prefetch((const char *)(s_gt[ds] + j), _MM_HINT_T0);
}
}
#endif
#ifdef PF_DIST
if (qi + PF_DIST < q1) {
u32 j = s_qord[qi + PF_DIST];
const u8 *bdn = s_bd + (size_t)j * MAXK;
for (int e = 0; e < K1; e++) {
int d = (e < ds) ? e : e + 1;
const char *pp = (const char *)(s_bs + ((size_t)e * (Q + 1) + bdn[d]) * W);
_mm_prefetch(pp, _MM_HINT_T0);
_mm_prefetch(pp + 64, _MM_HINT_T0);
_mm_prefetch(pp + 128, _MM_HINT_T0);
}
}
#endif
const u32 R = s_gt[ds][i];
u32 cnt = 0;
if (R && !g_skip_and) {
const u64 *bp[MAXK];
for (int e = 0; e < K1; e++) {
int d = (e < ds) ? e : e + 1;
bp[e] = g_plen_on ? (s_bs + s_pofs[(size_t)e * MAXQ + bd[d]])
: (s_bs + ((size_t)e * (Q + 1) + bd[d]) * W);
#ifdef DBG_PLEN
if (g_plen_on) {
u32 need = (R >> 6) + ((R & 63) ? 1 : 0);
if (need > s_plen[(size_t)e * MAXQ + bd[d]])
printf("DBG ds=%d e=%d d=%d b=%u R=%u need=%u len=%u\n", ds, e, d, bd[d], R, need, s_plen[(size_t)e * MAXQ + bd[d]]);
}
#endif
}
cnt = and_popcount_range<KK - 1>(bp, R >> 6, R & 63u);
}
out[i] = cnt;
}
#endif
if (g_skip_fringe) return;


for (int d = 0; d < k; d++) {
if (d == ds) continue;





const int kk1 = KK - 1; int emap[16]; const u8 *sgb2[16];
for (int e = 0; e < kk1; e++) emap[e] = e + (e >= d);
{ const u8 *sbase = s_sig + (size_t)d * k * MF_SPL;
const size_t spl = MF_SPL;
for (int e2 = 0; e2 < kk1; e2++) sgb2[e2] = sbase + (size_t)emap[e2] * spl; }
#if !MF_FR_NOSORT
{
u32 *cntv = s_cntv;
for (u32 v = 0; v <= Q; v++) cntv[v] = 0;
for (u32 qi = q0; qi < q1; qi++) {
#if MF_PFB > 0
if (qi + MF_PFB < q1) _mm_prefetch((const char *)(s_bd + (size_t)s_qord[qi + MF_PFB] * MAXK + d), _MM_HINT_T0);
#endif
cntv[s_bd[(size_t)s_qord[qi] * MAXK + d] + 1]++;
}
{ u32 ac = q0; for (u32 v = 0; v <= Q; v++) { u32 c = cntv[v]; cntv[v] = ac; ac += c; } }
for (u32 qi = q0; qi < q1; qi++) {
u32 id = s_qord[qi];
#if MF_PFB > 0
if (qi + MF_PFB < q1) _mm_prefetch((const char *)(s_bd + (size_t)s_qord[qi + MF_PFB] * MAXK + d), _MM_HINT_T0);
#endif
s_tmp[cntv[s_bd[(size_t)id * MAXK + d] + 1]++] = id;
}
for (u32 qi = q0; qi < q1; qi++) s_qord[qi] = s_tmp[qi];
}
#endif
u32 exmask = 0;
for (int e = 0; e < d; e++) if (e != ds) exmask |= 1u << e;


u32 hiA[8], hiAh[8];
for (int e = 0; e < 8; e++) hiA[e] = ((exmask >> e) & 1u) ? 0u : 0x7FFFFFFFu;
for (int e = 8; e < 16; e++) hiAh[e - 8] = ((exmask >> e) & 1u) ? 0u : 0x7FFFFFFFu;
const __m256i notexlo = LDU256(hiA);
const __m256i notexloh = LDU256(hiAh);
const __m256i all8 = _mm256_set1_epi32(-1);
const u32 *const odd = s_ord[d];
const u32 *const sdmpd = s_sdmp[d];
for (u32 qi = q0; qi < q1; qi++) {
u32 i = s_qord[qi];
#if MF_PFB > 0
{
u32 qj = qi + MF_PFB;
if (qj < q1) {
u32 j = s_qord[qj];
_mm_prefetch((const char *)(s_pm + (size_t)j * STRIDE), _MM_HINT_T0);
_mm_prefetch((const char *)(s_gt[d] + j), _MM_HINT_T0);
_mm_prefetch((const char *)(s_bd + (size_t)j * MAXK + d), _MM_HINT_T0);
A13T_PFW(out + j);
}
}
#endif
const u8 *bd = s_bd + (size_t)i * MAXK;
const u32 lo = FPOS(d, bd[d]);
const u32 hi = s_gt[d][i];
if (lo >= hi) continue;
const u32 *rec = s_pm + (size_t)i * STRIDE;
u32 Av[STRIDE] __attribute__((aligned(32)));
for (int e = 0; e < k && e < STRIDE; e++) Av[e] = (e == ds) ? 0x7FFFFFFFu : BVAL(e, bd[e]);
for (int e = k; e < STRIDE; e++) Av[e] = 0x7FFFFFFFu;
__m256i qr = _mm256_or_si256(LDA((const __m256i *)rec), khi8v);
__m256i Avm = _mm256_or_si256(LDU256(Av), notexlo);
__m256i qT = _mm256_min_epi32(qr, Avm);
__m256i qTh;
if (k > 8) {
__m256i qrh = _mm256_or_si256(LDU256((rec + 8)), khi8hv);
__m256i Avmh = _mm256_or_si256(LDU256((Av + 8)), notexloh);
qTh = _mm256_min_epi32(qrh, Avmh);
} else {
qTh = all8;
}
u32 add = 0;
const u32 *c0 = sdmpd ? (sdmpd + (size_t)lo * g_KS) : 0;
if (g_use_filt) {
const u32 w0 = lo >> 6;
const u32 nw = ((hi - 1) >> 6) - w0 + 1;
u64 *fb = s_fbuf;
const u64 wcs = (u64)N / g_Qc + 1;
const u32 FW = g_fbm_W;
int first = 1;
#if MF_FR_NOREAD
first = 0;
for (u32 w = 0; w < nw; w++) fb[w] = 0;
#endif
for (int e = 0; e < k; e++) {
if (e == d) continue;
u32 c = (u32)((u64)rec[e] / wcs) + 1;
if (c > g_Qc) c = g_Qc;
const u64 *row = s_fbm + ((size_t)(d * k + e) * (g_Qc + 1) + c) * FW + w0;
if (first) { for (u32 w = 0; w < nw; w++) fb[w] = row[w]; first = 0; }
else { for (u32 w = 0; w < nw; w++) fb[w] &= row[w]; }
}
fb[0] &= ~0ull << (lo & 63);
u32 r2 = hi & 63u;
if (r2) fb[nw - 1] &= (1ull << r2) - 1;
for (u32 w = 0; w < nw; w++) {
u64 vv = fb[w];
#if MF_FR_NOCAND
vv = 0;
#endif
while (vv) {
int t = __builtin_ctzll(vv);
vv &= vv - 1;
u32 j = ((w0 + w) << 6) + (u32)t;
const u32 *cp = c0 ? (c0 + (size_t)(j - lo) * g_KS) : (s_pm + (size_t)s_ord[d][j] * STRIDE);
__m256i pv = LDU256(cp);
u32 ok = (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, pv), all8);
if (k > 8) {
__m256i pvh = LDU256((cp + 8));
ok &= (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qTh, pvh), all8);
}
add += ok;
}
}
out[i] += add;
continue;
}
if (g_sig_on && (hi - lo) >= 32) {


__m256i qsb[16];






{
const __m256i zero8 = _mm256_setzero_si256();
const __m256i shv = _mm256_set1_epi32((int)g_sigsh);
for (int e2 = 0; e2 < kk1; e2++) {
int e = emap[e2];
__m256i src = (e < 8) ? qT : qTh;
__m256i sv = _mm256_srlv_epi32(src, shv);
__m256i bc = _mm256_permutevar8x32_epi32(sv, _mm256_set1_epi32(e & 7));
qsb[e2] = _mm256_shuffle_epi8(bc, zero8);
}
}
u32 aj = lo, aacc = 0, aexact = 0;
for (; aj + 32 <= hi; aj += 32) {
__m256i ac = _mm256_setzero_si256(), eq = _mm256_setzero_si256();
for (int e2 = 0; e2 < kk1; e2++) {
__m256i cv = LDU256((sgb2[e2] + aj));
ac = _mm256_or_si256(ac, _mm256_subs_epu8(cv, qsb[e2]));
eq = _mm256_or_si256(eq, _mm256_cmpeq_epi8(cv, qsb[e2]));
}
__m256i lt = _mm256_cmpeq_epi8(ac, _mm256_setzero_si256());
u32 ltm = (u32)_mm256_movemask_epi8(lt);
u32 amb = ltm & (u32)_mm256_movemask_epi8(eq);
aacc += (u32)__builtin_popcount(ltm & ~amb);
while (amb) {
int t = __builtin_ctz(amb); amb &= amb - 1;
const u32 *cp = c0 + (size_t)(aj + (u32)t - lo) * g_KS;
__m256i pv = LDU256(cp);
u32 okl = (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, pv), all8);
if (k > 8) {
__m256i pvh = LDU256((cp + 8));
okl &= (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qTh, pvh), all8);
}
aacc += okl;
}
}








{
u32 r = hi - aj;
if (r) {
u32 base, lk;
if (hi >= 32u) { base = hi - 32u; lk = 32u - r; }
else           { base = 0u;      lk = lo; }        
u32 kmask = ((r >= 32u) ? 0xFFFFFFFFu : ((1u << r) - 1u)) << lk;
__m256i ac = _mm256_setzero_si256(), eq = _mm256_setzero_si256();
for (int e2 = 0; e2 < kk1; e2++) {
__m256i cv = LDU256((sgb2[e2] + base));
ac = _mm256_or_si256(ac, _mm256_subs_epu8(cv, qsb[e2]));
eq = _mm256_or_si256(eq, _mm256_cmpeq_epi8(cv, qsb[e2]));
}
__m256i lt = _mm256_cmpeq_epi8(ac, _mm256_setzero_si256());
u32 ltm = ((u32)_mm256_movemask_epi8(lt)) & kmask;
u32 amb = ltm & ((u32)_mm256_movemask_epi8(eq));
aacc += (u32)__builtin_popcount(ltm & ~amb);
while (amb) {
int t = __builtin_ctz(amb); amb &= amb - 1;
const u32 *cp = c0 + (size_t)(base + (u32)t - lo) * g_KS;
__m256i pv = LDU256(cp);
u32 okl = (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, pv), all8);
if (k > 8) {
__m256i pvh = LDU256((cp + 8));
okl &= (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qTh, pvh), all8);
}
aacc += okl;
}
}
}
add = aacc;
} else if (c0) {
if (k <= 8) {
const u32 *c = c0;
u32 a0 = 0, a1 = 0, a2 = 0, a3 = 0;
u32 j = lo;
for (; j + 4 <= hi; j += 4) {
__m256i p0 = LDU256((c));
__m256i p1 = LDU256((c + g_KS));
__m256i p2 = LDU256((c + 2 * g_KS));
__m256i p3 = LDU256((c + 3 * g_KS));
a0 += (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, p0), all8);
a1 += (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, p1), all8);
a2 += (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, p2), all8);
a3 += (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, p3), all8);
c += 4 * g_KS;
}
for (; j < hi; j++, c += g_KS) {
__m256i pv = LDU256(c);
a0 += (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, pv), all8);
}
add = a0 + a1 + a2 + a3;
} else {





const u32 *c = c0;
u32 a0 = 0, a1 = 0, a2 = 0, a3 = 0;
u32 j = lo;
for (; j + 4 <= hi; j += 4) {
__m256i p0 = LDU256((c));
__m256i p1 = LDU256((c + g_KS));
__m256i p2 = LDU256((c + 2 * g_KS));
__m256i p3 = LDU256((c + 3 * g_KS));
__m256i h0 = LDU256((c + 8));
__m256i h1 = LDU256((c + g_KS + 8));
__m256i h2 = LDU256((c + 2 * g_KS + 8));
__m256i h3 = LDU256((c + 3 * g_KS + 8));
a0 += (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, p0), all8) & (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qTh, h0), all8);
a1 += (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, p1), all8) & (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qTh, h1), all8);
a2 += (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, p2), all8) & (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qTh, h2), all8);
a3 += (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, p3), all8) & (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qTh, h3), all8);
c += 4 * g_KS;
}
for (; j < hi; j++, c += g_KS) {
__m256i pv = LDU256(c);
__m256i pvh = LDU256((c + 8));
a0 += (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, pv), all8) &
(u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qTh, pvh), all8);
}
add = a0 + a1 + a2 + a3;
}
} else {





for (u32 j = lo; j < hi; j++) {
const u32 *c = s_pm + (size_t)odd[j] * STRIDE;
__m256i pv = LDA((const __m256i *)c);
u32 ok = (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, pv), all8);
if (k > 8) {
__m256i pvh = LDA((const __m256i *)(c + 8));
ok &= (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qTh, pvh), all8);
}
add += ok;
}
}
out[i] += add;
}
}
}









static const unsigned char a13_mskb[4 * 32] __attribute__((aligned(32))) = {
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4, 4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,
8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8, 8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,
12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,
};
template<int KK, int DD, int DS>
__attribute__((target("avx2,popcnt")))
__attribute__((flatten))
static void fringe_d(u32 N, u32 *out, u32 ds, u32 q0, u32 q1, u32 Q, u32 W, u32 d1, int d_rt) {
const int k = KK;
const int K1 = KK - 1;
const int d = (DD >= 0) ? DD : d_rt;





const int kk1 = k - 1;
const u8 *const splane = s_sig + (size_t)d * k * MF_SPL;
const u32 *fo = fixed_fringe_keys[d];
u32 exmask = 0;
for (int e = 0; e < d; e++) if (e != DS) exmask |= 1u << e;


u32 hiA[8], hiAh[8];
for (int e = 0; e < 8; e++) hiA[e] = ((exmask >> e) & 1u) ? 0u : 0x7FFFFFFFu;
for (int e = 8; e < 16; e++) hiAh[e - 8] = ((exmask >> e) & 1u) ? 0u : 0x7FFFFFFFu;
const __m256i notexlo = LDU256(hiA);
const __m256i gmask = _mm256_cmpeq_epi32(notexlo, _mm256_setzero_si256());
const __m256i koff = _mm256_setr_epi32(0, MAXQ, 2 * MAXQ, 3 * MAXQ,
4 * MAXQ, 5 * MAXQ, 6 * MAXQ, 7 * MAXQ);
const __m256i notexloh = LDU256(hiAh);
const __m256i all8 = _mm256_set1_epi32(-1);
int amb_n = 0;
const u32 *const odd = s_ord[d];
const u32 *const sdmpd = s_sdmp[d];
for (u32 qi = q0; qi < q1; qi++) {
u32 i = fo[qi]&0xfffffu;
#if MF_PFB > 0
{
u32 qj = qi + MF_PFB3;
if (qj < q1) {
u32 j = fo[qj]&0xfffffu;
_mm_prefetch((const char *)(s_pm + (size_t)j * STRIDE), _MM_HINT_T0);
_mm_prefetch((const char *)(s_gt[d] + j), _MM_HINT_T0);
A13T_PFW(out + j);
}
}
#endif
const u32 lo = FPOS(d, fo[qi]>>20);
const u32 hi = s_gt[d][i];
if (lo >= hi) continue;
const u32 *rec = s_pm + (size_t)i * STRIDE;
__m256i qr = _mm256_or_si256(LDA((const __m256i *)rec), khi8v);
__m256i Avm = _mm256_or_si256(_mm256_load_si256((const __m256i*)(rec+8)),notexlo);
__m256i qT = _mm256_min_epi32(qr, Avm);
__m256i qTh;
if (k > 8) {
__m256i qrh = _mm256_or_si256(LDU256((rec + 8)), khi8hv);
__m256i Avmh = _mm256_or_si256(_mm256_set1_epi32(0x7FFFFFFF), notexloh);
qTh = _mm256_min_epi32(qrh, Avmh);
} else {
qTh = all8;
}
u32 add = 0;
const u32 *c0 = sdmpd ? (sdmpd + (size_t)lo * g_KS) : 0;
if (g_sig_on && hi > lo) {


__m256i qsb[16];






{
__m256i sv0;
if (k == 7) {

sv0 = _mm256_srlv_epi32(_mm256_mullo_epi32(qT, _mm256_set1_epi32((int)g_binM)),
_mm256_set1_epi32((int)g_binS));
} else {
const __m256i shv = _mm256_set1_epi32((int)g_sigsh);
sv0 = _mm256_srlv_epi32(qT, shv);
}
const __m256i sv0x = _mm256_xor_si256(sv0, _mm256_set1_epi8((char)0x80));
const __m256i ylo = _mm256_broadcastsi128_si256(_mm256_castsi256_si128(sv0x));
const __m256i yhi = _mm256_broadcastsi128_si256(_mm256_extracti128_si256(sv0x, 1));
for (int e = 0; e < k; e++) {
if (e == (int)d) { qsb[e] = _mm256_set1_epi8((char)0x7F); continue; }
__m256i src = (e < 4) ? ylo : yhi;
qsb[e] = _mm256_shuffle_epi8(src,
_mm256_load_si256((const __m256i *)(a13_mskb + (e & 3) * 32)));
}
}
u32 aj = lo, aacc = 0, aexact = 0;
for (; aj + 32 <= hi; aj += 32) {






/* [r82z1_ TREE3] k=7 专用：3 对成对归约 + 1 层 max，**全展开无运行期循环**
S 链 12 -> 4 拍；活跃 YMM = 6 qsb + 3 对 + 1 瞬态 = 10（<16） */
__m256i m0R, m1R, m2R;
if (k == 7) {
int ixR = 0;
for (int e = 0; e < k; e++) {
if (e == (int)d) continue;
__m256i cv = LDU256((splane + (size_t)e * MF_SPL + aj));
__m256i sv = _mm256_subs_epi8(cv, qsb[e]);
switch (ixR++) {
case 0: m0R = sv; break;
case 1: m0R = _mm256_max_epi8(m0R, sv); break;
case 2: m1R = sv; break;
case 3: m1R = _mm256_max_epi8(m1R, sv); break;
case 4: m2R = sv; break;
default: m2R = _mm256_max_epi8(m2R, sv); break;
}
}
m0R = _mm256_max_epi8(m0R, m1R);
m0R = _mm256_max_epi8(m0R, m2R);
} else {
m0R = _mm256_set1_epi8((char)0x80);
for (int e = 0; e < k; e++) {
if (e == (int)d) continue;
__m256i cv = LDU256((splane + (size_t)e * MF_SPL + aj));
m0R = _mm256_max_epi8(m0R, _mm256_subs_epi8(cv, qsb[e]));
}
}
__m256i S = m0R;
u32 ltm = (u32)_mm256_movemask_epi8(S);
u32 amb = (u32)_mm256_movemask_epi8(_mm256_cmpeq_epi8(S, _mm256_setzero_si256()));
aacc += (u32)__builtin_popcount(ltm);
while (amb) {
int t = __builtin_ctz(amb); amb &= amb - 1;
const u32 *cp = s_pm + (size_t)odd[aj + (u32)t] * STRIDE;
if (amb_n < AMBD_CAP) {
s_abi[amb_n] = i;
s_abp[amb_n] = cp;
_mm256_store_si256(&s_abqT[amb_n], qT);
if (k > 8) _mm256_store_si256(&s_abqTh[amb_n], qTh);
amb_n++;
} else {
__m256i pv = LDU256(cp);
u32 okl = (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, pv), all8);
if (k > 8) {
__m256i pvh = LDU256((cp + 8));
okl &= (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qTh, pvh), all8);
}
aacc += okl;
}
}
}








{
u32 r = hi - aj;
if (r) {
u32 base = aj;
u32 kmask = (1u << r) - 1u;
/* [r82z1_ TREE3] k=7 专用：3 对成对归约 + 1 层 max，**全展开无运行期循环**
S 链 12 -> 4 拍；活跃 YMM = 6 qsb + 3 对 + 1 瞬态 = 10（<16） */
__m256i m0R, m1R, m2R;
if (k == 7) {
int ixR = 0;
for (int e = 0; e < k; e++) {
if (e == (int)d) continue;
__m256i cv = LDU256((splane + (size_t)e * MF_SPL + base));
__m256i sv = _mm256_subs_epi8(cv, qsb[e]);
switch (ixR++) {
case 0: m0R = sv; break;
case 1: m0R = _mm256_max_epi8(m0R, sv); break;
case 2: m1R = sv; break;
case 3: m1R = _mm256_max_epi8(m1R, sv); break;
case 4: m2R = sv; break;
default: m2R = _mm256_max_epi8(m2R, sv); break;
}
}
m0R = _mm256_max_epi8(m0R, m1R);
m0R = _mm256_max_epi8(m0R, m2R);
} else {
m0R = _mm256_set1_epi8((char)0x80);
for (int e = 0; e < k; e++) {
if (e == (int)d) continue;
__m256i cv = LDU256((splane + (size_t)e * MF_SPL + base));
m0R = _mm256_max_epi8(m0R, _mm256_subs_epi8(cv, qsb[e]));
}
}
__m256i S = m0R;
u32 ltm = ((u32)_mm256_movemask_epi8(S)) & kmask;
u32 amb = ((u32)_mm256_movemask_epi8(_mm256_cmpeq_epi8(S, _mm256_setzero_si256()))) & kmask;
aacc += (u32)__builtin_popcount(ltm);
while (amb) {
int t = __builtin_ctz(amb); amb &= amb - 1;
const u32 *cp = s_pm + (size_t)odd[base + (u32)t] * STRIDE;
if (amb_n < AMBD_CAP) {
s_abi[amb_n] = i;
s_abp[amb_n] = cp;
_mm256_store_si256(&s_abqT[amb_n], qT);
if (k > 8) _mm256_store_si256(&s_abqTh[amb_n], qTh);
amb_n++;
} else {
__m256i pv = LDU256(cp);
u32 okl = (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qT, pv), all8);
if (k > 8) {
__m256i pvh = LDU256((cp + 8));
okl &= (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qTh, pvh), all8);
}
aacc += okl;
}
}
}
}
add = aacc;
}
out[i] += add;
}
for (int z = 0; z < amb_n; z++) {
if (z + 48 < amb_n) __builtin_prefetch(s_abp[z + 48], 0, 0);
const u32 *cp = s_abp[z];
__m256i pv = LDU256(cp);
__m256i qv = _mm256_load_si256(&s_abqT[z]);
u32 ok = (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qv, pv), all8);
if (k > 8) {
__m256i pvh = LDU256(cp + 8);
__m256i qvh = _mm256_load_si256(&s_abqTh[z]);
ok &= (u32)_mm256_testc_si256(_mm256_cmpgt_epi32(qvh, pvh), all8);
}
out[s_abi[z]] += ok;
}
}

__attribute__((target("avx2")))
static inline __m256i band_pair_intersection(const u64 *p,const u64 *q) {
__m256i v;
__asm__("vmovdqu %1,%0\n\tvpand %2,%0,%0"
: "=&x"(v) : "m"(*(const __m256i*)p), "m"(*(const __m256i*)q));
return v;
}

template<int KK, int DS>
__attribute__((target("avx2,popcnt")))
__attribute__((flatten))
static void qg_t(u32 N, u32 *out, u32 ds, u32 q0, u32 q1, u32 Q, u32 W) {
const int k = KK;
const int K1 = KK - 1;
static_assert(8ull*(MAXK-1)*MAXQ*(((MAXN+63ull)/64ull+7ull)&~7ull)<(1ull<<32),"band byte offsets fit u32");
#if MF_BAND
/* [n13b_ BANDAND] band-major 池位图 AND —— 见文件头说明 */
const u32 d1 = (DS == 0) ? 1u : 0u;
if (g_lexsort) {
u32 *cntv = s_cntv;
for (int dd = k - 1; dd >= 0; dd--) {
if (dd == DS) continue;
for (u32 v = 0; v <= Q; v++) cntv[v] = 0;
for (u32 qi = q0; qi < q1; qi++) cntv[s_bd[(size_t)s_qord[qi] * MAXK + dd] + 1]++;
{ u32 ac = q0; for (u32 v = 0; v <= Q; v++) { u32 c = cntv[v]; cntv[v] = ac; ac += c; } }
for (u32 qi = q0; qi < q1; qi++) { u32 id = s_qord[qi]; s_tmp[cntv[s_bd[(size_t)id * MAXK + dd] + 1]++] = id; }
for (u32 qi = q0; qi < q1; qi++) s_qord[qi] = s_tmp[qi];
}
}
if (!g_skip_and) {
const u32 nq = q1 - q0;
u32 *rec = s_bandrec;
{
u32 *cv = s_cntv;
for (u32 v = 0; v <= (u32)N; v++) cv[v] = 0;
for (u32 t = 0; t < nq; t++) cv[s_gt[DS][s_qord[q0 + t]] + 1]++;
{ u32 ac = 0; for (u32 v = 0; v <= (u32)N; v++) { u32 c = cv[v]; cv[v] = ac; ac += c; } }
for (u32 t = 0; t < nq; t++) {
u32 i = s_qord[q0 + t];
const u8 *bd = s_bd + (size_t)i * MAXK;
u32 R = s_gt[DS][i];
u32 *rp = rec + (size_t)(cv[R + 1]++) * 8;
rp[0] = R;
for (int e = 0; e < K1; e++) {
int d = (e < DS) ? e : e + 1;
rp[1 + e] = 8u * (g_plen_on ? s_pofs[(size_t)e * MAXQ + bd[d]]
: (u32)(((size_t)e * (Q + 1) + bd[d]) * W));
}
rp[7] = i;
}
}
{
u32 *acc = s_bandacc;
for (u32 t = 0; t < nq; t++){ acc[t] = 0; s_bandvec[t]=0; }
if (nq) {
const u32 maxR = rec[(size_t)(nq - 1) * 8];
const u32 maxband = (maxR + 1023u) / 1024u;
const __m256i lm = _mm256_set1_epi8(0x0f);
const __m256i lk = _mm256_setr_epi8(0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,
0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4);
const __m256i zz = _mm256_setzero_si256();
u32 ps = 0;
for (u32 bk = 0; bk <= maxband; bk++) {
const u32 lim = bk * 1024u;
while (ps < nq && rec[(size_t)ps * 8] <= lim) ps++;
if (ps >= nq) break;
u32 psp = ps;
while (psp < nq && rec[(size_t)psp * 8] < lim + 1024u) psp++;
const size_t off8 = (size_t)bk * 16u;
const char *band_base=(const char*)s_bs+(size_t)bk*128u;
u32 t=psp;
const u32 prefetch_end=nq>=2u?nq-2u:0u;
for (;t<prefetch_end;t++) {
const u32* next=rec+(size_t)(t+2)*8;
for(int e=0;e<K1;e++){
const u64* pp=(const u64*)(band_base+(size_t)next[1+e]);
_mm_prefetch((const char*)pp,_MM_HINT_T0);
_mm_prefetch((const char*)(pp+8),_MM_HINT_T0);
}
const u32 *rp = rec + (size_t)t * 8;
__m256i bytes=zz;
for (u32 lane=0;lane<16u;lane+=4) {
const u64 *p0=(const u64*)(band_base+(size_t)rp[1]+(size_t)lane*8u);
__m256i a0;
if constexpr(K1==6) {
__m256i v01=band_pair_intersection(p0,(const u64*)(band_base+(size_t)rp[2]+(size_t)lane*8u));
__m256i v23=band_pair_intersection((const u64*)(band_base+(size_t)rp[3]+(size_t)lane*8u),(const u64*)(band_base+(size_t)rp[4]+(size_t)lane*8u));
__m256i v45=band_pair_intersection((const u64*)(band_base+(size_t)rp[5]+(size_t)lane*8u),(const u64*)(band_base+(size_t)rp[6]+(size_t)lane*8u));
a0=_mm256_and_si256(_mm256_and_si256(v01,v23),v45);
} else {
a0=LDU256(p0);
for(int e=1;e<K1;e++)a0=_mm256_and_si256(a0,LDU256((const u64*)(band_base+(size_t)rp[1+e]+(size_t)lane*8u)));
}
__m256i low=_mm256_and_si256(a0,lm),high=_mm256_and_si256(_mm256_srli_epi16(a0,4),lm);
bytes=_mm256_add_epi8(bytes,_mm256_add_epi8(_mm256_shuffle_epi8(lk,low),_mm256_shuffle_epi8(lk,high)));
}
__m256i sum64=_mm256_sad_epu8(bytes,zz);
__m128i lanes=_mm_add_epi32(_mm256_castsi256_si128(sum64),_mm256_extracti128_si256(sum64,1));
lanes=_mm_shuffle_epi32(lanes,0x88);
// Both packed 32-bit totals are bounded by N, so a 64-bit add cannot carry between lanes.
s_bandvec[t] += (u64)_mm_cvtsi128_si64(lanes);
}
for (;t<nq;t++) {
const u32 *rp = rec + (size_t)t * 8;
__m256i bytes=zz;
for (u32 lane=0;lane<16u;lane+=4) {
const u64 *p0=(const u64*)(band_base+(size_t)rp[1]+(size_t)lane*8u);
__m256i a0;
if constexpr(K1==6) {
__m256i v01=band_pair_intersection(p0,(const u64*)(band_base+(size_t)rp[2]+(size_t)lane*8u));
__m256i v23=band_pair_intersection((const u64*)(band_base+(size_t)rp[3]+(size_t)lane*8u),(const u64*)(band_base+(size_t)rp[4]+(size_t)lane*8u));
__m256i v45=band_pair_intersection((const u64*)(band_base+(size_t)rp[5]+(size_t)lane*8u),(const u64*)(band_base+(size_t)rp[6]+(size_t)lane*8u));
a0=_mm256_and_si256(_mm256_and_si256(v01,v23),v45);
} else {
a0=LDU256(p0);
for(int e=1;e<K1;e++)a0=_mm256_and_si256(a0,LDU256((const u64*)(band_base+(size_t)rp[1+e]+(size_t)lane*8u)));
}
__m256i low=_mm256_and_si256(a0,lm),high=_mm256_and_si256(_mm256_srli_epi16(a0,4),lm);
bytes=_mm256_add_epi8(bytes,_mm256_add_epi8(_mm256_shuffle_epi8(lk,low),_mm256_shuffle_epi8(lk,high)));
}
__m256i sum64=_mm256_sad_epu8(bytes,zz);
__m128i lanes=_mm_add_epi32(_mm256_castsi256_si128(sum64),_mm256_extracti128_si256(sum64,1));
lanes=_mm_shuffle_epi32(lanes,0x88);
// Both packed 32-bit totals are bounded by N, so a 64-bit add cannot carry between lanes.
s_bandvec[t] += (u64)_mm_cvtsi128_si64(lanes);
}
for (u32 t = ps; t < psp; t++) {
const u32 *rp = rec + (size_t)t * 8;
const u32 R = rp[0];
const u64 *bp[MAXK];
for (int e = 0; e < K1; e++) bp[e] = (const u64*)(band_base + (size_t)rp[1 + e]);
acc[t] += and_popcount_range<KK - 1, true>(bp, (R >> 6) - (u32)off8, R & 63u);
}
}
for (u32 t = 0; t < nq; t++){__m128i lanes=_mm_loadl_epi64((const __m128i*)(s_bandvec+t));out[rec[(size_t)t * 8 + 7]] = acc[t]+(u32)_mm_cvtsi128_si32(lanes)+(u32)_mm_extract_epi32(lanes,1);}
}
}
}
#else
const u32 d1 = (DS == 0) ? 1u : 0u;
for (u32 qi = q0; qi < q1; qi++) {
u32 i = s_qord[qi];
const u8 *bd = s_bd + (size_t)i * MAXK;
const u32 R = s_gt[DS][i];
u32 cnt = 0;
if (R && !g_skip_and) {
const u64 *bp[MAXK];
for (int e = 0; e < K1; e++) {
int d = (e < DS) ? e : e + 1;
bp[e] = g_plen_on ? (s_bs + s_pofs[(size_t)e * MAXQ + bd[d]])
: (s_bs + ((size_t)e * (Q + 1) + bd[d]) * W);
}
cnt = and_popcount_range<KK - 1>(bp, R >> 6, R & 63u);
}
out[i] = cnt;
}
#endif
if (g_skip_fringe) return;


for (int d_ = 0; d_ < k; d_++) {
if (d_ == (int)DS) continue;
switch (d_) {
case 0: fringe_d<KK,0,DS>(N, out, ds, q0, q1, Q, W, d1, 0); break;
case 1: fringe_d<KK,1,DS>(N, out, ds, q0, q1, Q, W, d1, 0); break;
case 2: fringe_d<KK,2,DS>(N, out, ds, q0, q1, Q, W, d1, 0); break;
case 3: fringe_d<KK,3,DS>(N, out, ds, q0, q1, Q, W, d1, 0); break;
case 4: fringe_d<KK,4,DS>(N, out, ds, q0, q1, Q, W, d1, 0); break;
case 5: fringe_d<KK,5,DS>(N, out, ds, q0, q1, Q, W, d1, 0); break;
case 6: fringe_d<KK,6,DS>(N, out, ds, q0, q1, Q, W, d1, 0); break;
default: fringe_d<KK,-1,DS>(N, out, ds, q0, q1, Q, W, d1, d_); break;
}
}
}

__attribute__((target("avx2")))
static void solve_mf(u32 N, const unsigned **x, u32 *out, int k) {


const u32 W = ((N + 63) / 64 + 7u) & ~7u;
g_W = W;
#ifdef MF_SKIP_AND
g_skip_and = 1;
#endif
#ifdef MF_FILT
g_use_filt = 1;
#endif
#ifdef MF_NOFILT
g_use_filt = 0;
#endif
#ifdef MF_Q
g_Q = MF_Q; g_B = (u32)((N + (MF_Q) - 1) / (MF_Q));
#endif
#ifdef MF_FILT
g_use_filt = 1;
#endif
#ifdef MF_NOFILT
g_use_filt = 0;
#endif
#ifdef MF_SKIP_FRINGE
g_skip_fringe = 1;
#endif
if (!g_Q) {


u64 r = (u64)N, s2 = 0;
while (s2 * s2 < r) s2++;                       


u64 overhead = (u64)(5 * k + 21) * N * 4;
overhead += (u64)k * k * 4 * N;






overhead += (u64)k * k * MF_SPL;
overhead += (u64)N * ((k <= 8) ? 8u : (u32)k) * 4 * k;
u64 budget = ((u64)MF_BUDGETMB << 20);
if (budget > overhead + ((u64)64 << 20)) budget -= overhead; else budget = (u64)64 << 20;


#if MF_PLEN
static const u32 kfill[7] = {72, 67, 62, 58, 54, 50, 46};   
u64 perfill = ((u64)(k - 1) * W * 8) * kfill[k - 4] / 100;
#else
u64 perfill = (u64)(k - 1) * W * 8;
#endif
u64 Qmem = budget / (perfill ? perfill : 1);
if (Qmem < 8) Qmem = 8;
static const u32 kscale[7] = {82, 91, 100, 108, 115, 122, 129};  
u32 q = (u32)((s2 * MF_QCOEF + 99) / 100);
q = (u32)(((u64)q * kscale[k - 4] + 99) / 100);
if ((u64)q > Qmem) q = (u32)Qmem;
if (q > N) q = N;
if (q >= MAXQ) q = MAXQ - 1;
g_Q = q;
g_B = (N + q - 1) / q;
}
const u32 Q = g_Q, B = g_B;
g_bmag = ((1ull << 40) + B - 1) / B;
#if MF_PLEN
g_plen_on = 1;   
#endif
#if MF_WTRIM
u32 Wpool = W;   
#else
const u32 Wpool = W;
#endif
#if MF_FILTAUTO
if (!g_use_filt && B >= 400) g_use_filt = 1;   
#endif
if (g_use_filt && (u64)k * k * (g_Qc + 1) * W * 8 > ((u64)700 << 20)) g_use_filt = 0;
#if !MF_FILTAUTO
g_use_filt = 0;
#endif
#if MF_NOFILTB


g_use_filt = 0;
#endif
{
int lo8[8], hi8[8];
for (int e = 0; e < 8; e++) lo8[e] = (e < k) ? 0 : 0x7FFFFFFF;
for (int e = 0; e < 8; e++) hi8[e] = (8 + e < k) ? 0 : 0x7FFFFFFF;
khi8v = LDU256(lo8);
khi8hv = LDU256(hi8);
}
const int K1 = k - 1;

for (int d = 0; d < k; d++) {
const unsigned *xd = x[d];
u32 *od = s_ord[d];




static u8 hist8[MAXN+1] __attribute__((aligned(64)));
for(u32 i=0;i<=N;i++)hist8[i]=0;
for(u32 i=0;i<N;i++){u32 v=xd[i];hist8[v<N?v:0]++;}
u32 sum=0;
for(u32 i=0;i<=N;i++){u32 c=hist8[i];s_tmp[i]=sum;sum+=c;}
bool compact=(sum==N);
if(!compact){
for(u32 i=0;i<=N;i++)s_cntv[i]=0;
for(u32 i=0;i<N;i++){u32 v=xd[i];s_cntv[v<N?v:0]++;}
sum=0;for(u32 i=0;i<=N;i++){u32 c=s_cntv[i];s_cntv[i]=sum;s_tmp[i]=sum;sum+=c;}
}
u32 *gt=s_gt[d],*pp=s_pos[d];
auto scatter=[&](auto tag){
for(u32 i=0;i<N;i++){
if(i+16<N){u32 vn=xd[i+16];if(vn>=N)vn=0;
_mm_prefetch((const char*)(s_tmp+vn),_MM_HINT_T0);
u32 qn;if constexpr(decltype(tag)::value){u32 w=s_tmp[vn];qn=(w&0xfffffu)+(w>>20);}else qn=s_tmp[vn];
_mm_prefetch((const char*)(od+qn),_MM_HINT_T0);
}
u32 v=xd[i];if(v>=N)v=0;
u32 st,q,num;
if constexpr(decltype(tag)::value){
u32 w=s_tmp[v];st=w&0xfffffu;q=st+(w>>20);s_tmp[v]=w+(1u<<20);
num=(s_tmp[v+1]&0xfffffu)-1u;
}else{st=s_cntv[v];q=s_tmp[v]++;num=s_cntv[v+1]-1u;}
od[q]=i;pp[i]=q;gt[i]=st;
#if MF_FB2
s_posp[(size_t)i*MAXK+d]=q;
#endif
if(num>N)num=N;
u32 bb=(u32)(((u64)num*g_bmag)>>40);
s_bd[(size_t)i*MAXK+d]=bb>Q-1?Q-1:bb;
}
};
if(compact)scatter(std::true_type{});else scatter(std::false_type{});
BVAL(d, 0) = 0; FPOS(d, 0) = 0;
for (u32 b = 1; b < Q; b++) {
u32 pos = b * B < N ? b * B : N - 1;
u32 v = xd[od[pos]];
BVAL(d, b) = v;
u32 gs = pos;
while (gs > 0 && xd[od[gs - 1]] == v) gs--;
FPOS(d, b) = gs;
}
BVAL(d, Q) = 0xFFFFFFFFu; FPOS(d, Q) = 0;
}
for (u32 i = 0; i < N; i++) {
u32 *p = s_pm + (size_t)i * STRIDE;
for (int d = 0; d < k; d++) p[d] = x[d][i];
for (int d = k; d < STRIDE; d++) p[d] = 0;
const u8*bd=s_bd+(size_t)i*MAXK;
__m256i idx=_mm256_add_epi32(_mm256_cvtepu8_epi32(_mm_loadl_epi64((const __m128i*)bd)),_mm256_setr_epi32(0,MAXQ,2*MAXQ,3*MAXQ,4*MAXQ,5*MAXQ,6*MAXQ,7*MAXQ));
_mm256_store_si256((__m256i*)(p+8),_mm256_i32gather_epi32((const int*)s_bval,idx,4));
for(int d=k;d<8;d++)p[8+d]=0x7fffffffu;
}


{
u32 nn = N - 1; u32 sh = 0;



while (nn > ((k == 7) ? 255u : 127u)) { nn >>= 1; sh++; }        
g_sigsh = sh;


g_binS = 18;
g_binM = (N > 1) ? (u32)(((u64)256 << 18) / (u64)(N - 1)) : 1u;
if (g_binM < 1) g_binM = 1;
size_t need = (size_t)k * k * MF_SPL;
static u8 *sigpool = 0; static size_t sigcap = 0;


if (need > ((size_t)220 << 20) || (size_t)N + 32 > MF_SPL) { sigpool = 0; sigcap = 0; }
else if (need > sigcap) { sigpool = (u8 *)pool_alloc(need); sigcap = sigpool ? need : 0; }
if (sigpool) {
s_sig = sigpool;















g_sig_on = 1;
g_sig_merged = 0;
}
}

#if MF_NOFILTB
g_use_filt = 0;
#endif
#if MF_FB3
if (g_use_filt) {
u32 Qc = g_Qc;
u64 wc = (u64)N / Qc + 1;
for (int e = 0; e < k; e++) {
const unsigned *xe = x[e];
const u32 *pe = s_ord[e];
u32 ptr = 0;
u32 *bn = s_bnde + (size_t)e * (MAXQ + 2);
for (u32 c = 0; c <= Qc; c++) {
u64 v = (u64)c * wc;
if (v > 0xFFFFFFFFull) v = 0xFFFFFFFFull;
while (v && ptr < N && (u64)xe[pe[ptr]] < v) ptr++;
bn[c] = ptr;
}
}
}
#endif
if (g_use_filt) {
u32 Qc = g_Qc;
u64 wc = (u64)N / Qc + 1;
size_t need2 = (size_t)k * k * (Qc + 1) * W * sizeof(u64);
static u64 *fpool = 0; static size_t fcap = 0;
if (need2 > fcap) { fpool = (u64 *)pool_alloc(need2 + 4096); fcap = need2; }
if (fpool) {
s_fbm = fpool; g_fbm_W = W;
#if MF_FB2






for (int d = 0; d < k; d++)
for (int e = 0; e < k; e++) {
if (e == d) continue;
u64 *b0 = s_fbm + (size_t)(d * k + e) * (Qc + 1) * W;
for (u32 w = 0; w < W; w++) b0[w] = 0;
}
for (int e = 0; e < k; e++) {
const unsigned *xe = x[e];
const u32 *pe = s_ord[e];
int dmap[MAXK], km1 = 0;
for (int d = 0; d < k; d++) if (d != e) dmap[km1++] = d;
for (int i = 0; i < km1; i++) { u64 *a = s_facc + (size_t)i * W; for (u32 w = 0; w < W; w++) a[w] = 0; }
u32 ptr = 0;
for (u32 c = 1; c <= Qc; c++) {
u64 v = (u64)c * wc;
if (v > 0xFFFFFFFFull) v = 0xFFFFFFFFull;
while (ptr < N && (u64)xe[pe[ptr]] < v) {
const u32 *pv = s_posp + (size_t)pe[ptr] * MAXK;
for (int i = 0; i < km1; i++) {
u32 q = pv[dmap[i]];
s_facc[(size_t)i * W + (q >> 6)] |= 1ull << (q & 63);
}
ptr++;
}
for (int i = 0; i < km1; i++) {
int d = dmap[i];
u64 *dst = s_fbm + ((size_t)(d * k + e) * (Qc + 1) + c) * W;
const u64 *src = s_facc + (size_t)i * W;
#if MF_NT
{ u32 w = 0;
for (; w + 4 <= W; w += 4) _mm256_stream_si256((__m256i *)(dst + w), LDA((const __m256i *)(src + w)));
for (; w < W; w++) dst[w] = src[w]; }
#else
for (u32 w = 0; w < W; w++) dst[w] = src[w];
#endif
}
}
}
#else
for (int d = 0; d < k; d++) {
for (int e = 0; e < k; e++) {
if (e == d) continue;
const unsigned *xe = x[e];
const u32 *pe = s_ord[e];
const u32 *pd = s_pos[d];
u64 *base = s_fbm + (size_t)(d * k + e) * (Qc + 1) * W;
for (u32 w = 0; w < W; w++) base[w] = 0;
u64 *cur = s_acc;
for (u32 w = 0; w < W; w++) cur[w] = 0;
u32 ptr = 0;
for (u32 c = 1; c <= Qc; c++) {
#if MF_FB3
u32 pend = s_bnde[(size_t)e * (MAXQ + 2) + c];
#else
u64 v = (u64)c * wc;
if (v > 0xFFFFFFFFull) v = 0xFFFFFFFFull;
u32 pend = ptr;
{ const unsigned *xe_ = xe; const u32 *pe_ = pe;
while (pend < N && (u64)xe_[pe_[pend]] < v) pend++; }
#endif
while (ptr < pend) { u32 q = pd[pe[ptr]]; cur[q >> 6] |= 1ull << (q & 63); ptr++; }
u64 *dst = base + (size_t)c * W;
#if MF_NT
{ u32 w = 0;
for (; w + 4 <= W; w += 4) _mm256_stream_si256((__m256i *)(dst + w), LDA((const __m256i *)(cur + w)));
for (; w < W; w++) dst[w] = cur[w]; }
#else
for (u32 w = 0; w < W; w++) dst[w] = cur[w];
#endif
}
}
}
#endif
} else { g_use_filt = 0; }
_mm_sfence();
}


{
size_t mrn = (size_t)MAXK * MAXK * MAXQ;
for (size_t z = 0; z < mrn; z++) s_maxr[z] = 0;
}
if(k==7){
u32 i=0;
for(;i+8<=N;i+=8){
__m256i v=_mm256_slli_epi32(_mm256_loadu_si256((const __m256i*)(s_gt[0]+i)),4);
for(unsigned d=1;d<7;++d){
__m256i q=_mm256_or_si256(_mm256_slli_epi32(_mm256_loadu_si256((const __m256i*)(s_gt[d]+i)),4),_mm256_set1_epi32(d));
v=_mm256_min_epu32(v,q);
}
_mm256_storeu_si256((__m256i*)(s_tmp+i),v);
}
for(;i<N;++i){u32 v=s_gt[0][i]<<4;for(unsigned d=1;d<7;++d){u32 q=(s_gt[d][i]<<4)|d;if(q<v)v=q;}s_tmp[i]=v;}
}
u32 gstart[MAXK+2] = {};
for (u32 i = 0; i < N; i++) {
u32 best;int ds;
if(k==7){best=s_tmp[i]>>4;ds=s_tmp[i]&15u;}else{
best = 0xFFFFFFFFu; ds = 0;
for (int d = 0; d < k; d++) {
u32 g = s_gt[d][i];
if (g < best) { best = g; ds = d; }
}
}
s_g[i] = (u32)ds;
++gstart[ds+1];



if (g_plen_on) {
const u8 *bdv = s_bd + (size_t)i * MAXK;
u32 *mr = s_maxr + ((size_t)ds * MAXK) * MAXQ;
u32 bb = best;
for (int d = 0; d < k; d++) {
u32 b = bdv[d];
if (bb > mr[(size_t)d * MAXQ + b]) mr[(size_t)d * MAXQ + b] = bb;
}
}
}
for(unsigned d=1;d<=unsigned(k+1);++d)gstart[d]+=gstart[d-1];
u32 fold_write[MAXK];
for(int d=0;d<k;++d)fold_write[d]=gstart[d];
for(u32 i=0;i<N;++i)s_qord[fold_write[s_g[i]]++]=i;
if(k==7){
for(int d=0;d<7;d++){
u32 cursor[7];for(int ds=0;ds<7;ds++)cursor[ds]=gstart[ds];
for(u32 r=0;r<N;r++){
u32 id=s_ord[d][r];
fixed_fringe_keys[d][cursor[s_g[id]]++]=id|((u32)s_bd[(size_t)id*MAXK+d]<<20);
}
}
}



if (s_sig && k == 7 && (size_t)N <= MF_SPL) {
for (u32 i = 0; i < N; i++) {
u8 *dst = a13_sigrow + (size_t)i * 8;
for (int e = 0; e < 7; e++) dst[e] = (u8)(A13V_BINSC(x[e][i]) ^ 0x80u);
}
}

#if MF_NOSDMP
g_nosdmp = 1;
#endif
if (!g_nosdmp) {
u32 KS = k;
#if MF_KSPAD
if (k <= 8) KS = 8;          
#endif
size_t per = (size_t)N * KS * 4;
size_t lim = (size_t)150 << 20;
if (k >= 9) lim = (size_t)470 << 20;   
if (per * k <= lim) {
static u32 *pool = 0; static size_t cap = 0;
if (per * k > cap) { pool = (u32 *)pool_alloc(per * k + 256); cap = per * k; }
if (pool) {
g_KS = KS;
for (int d = 0; d < k; d++) {
s_sdmp[d] = pool + (size_t)d * N * g_KS;
const u32 *od = s_ord[d];
u32 *dst = s_sdmp[d];
const u32 KSx = g_KS;
for (u32 j = 0; j < N; j++) {
#if MF_PFB > 0
if (j + MF_PFB < N) _mm_prefetch((const char *)(s_pm + (size_t)od[j + MF_PFB] * STRIDE), _MM_HINT_T0);
#endif
const u32 *row = s_pm + (size_t)od[j] * STRIDE;
/* [a13y_ NSDMP] s_sdmp is BUILT BUT NEVER READ (its only readers are the
fringe's `else if (c0)` / `g_use_filt` branches, both unreachable in
production; instrumented counter c0hit = 0 over 1,797,724 query*dim
iterations, sig branch = 100%).  The sig-plane build below is untouched. */
if (0) { u32 *dp = dst + (size_t)j * KSx;
for (u32 e = 0; e < KSx; e++) dp[e] = (e < (u32)k) ? row[e] : 0u; }
if (s_sig) {
u8 *sb = s_sig + (size_t)d * k * MF_SPL;
for (int e = 0; e < k; e++) sb[(size_t)e * MF_SPL + j] = (u8)(((u8)((k == 7) ? A13V_BINSC(row[e]) : (row[e] >> g_sigsh)) ^ ((k == 7) ? 0x80u : 0u)));
}
}
if (s_sig) g_sig_merged = 1;
}
}
}
}

if (s_sig && !g_sig_merged && k==7) {
for(int d=0;d<k;d++) {
const u32 *od=s_ord[d];u8 *base=s_sig+(size_t)d*k*MF_SPL;
u32 j=0;
for(;j+8<=N;j+=8) {
if(j+64<N)_mm_prefetch((const char *)(a13_sigrow+(size_t)od[j+64]*8),_MM_HINT_T0);
__m128i r0=_mm_loadl_epi64((const __m128i *)(a13_sigrow+(size_t)od[j+0]*8));
__m128i r1=_mm_loadl_epi64((const __m128i *)(a13_sigrow+(size_t)od[j+1]*8));
__m128i r2=_mm_loadl_epi64((const __m128i *)(a13_sigrow+(size_t)od[j+2]*8));
__m128i r3=_mm_loadl_epi64((const __m128i *)(a13_sigrow+(size_t)od[j+3]*8));
__m128i r4=_mm_loadl_epi64((const __m128i *)(a13_sigrow+(size_t)od[j+4]*8));
__m128i r5=_mm_loadl_epi64((const __m128i *)(a13_sigrow+(size_t)od[j+5]*8));
__m128i r6=_mm_loadl_epi64((const __m128i *)(a13_sigrow+(size_t)od[j+6]*8));
__m128i r7=_mm_loadl_epi64((const __m128i *)(a13_sigrow+(size_t)od[j+7]*8));
__m128i t0=_mm_unpacklo_epi8(r0,r1);
__m128i t1=_mm_unpacklo_epi8(r2,r3);
__m128i t2=_mm_unpacklo_epi8(r4,r5);
__m128i t3=_mm_unpacklo_epi8(r6,r7);
__m128i u0=_mm_unpacklo_epi16(t0,t1);
__m128i u1=_mm_unpackhi_epi16(t0,t1);
__m128i u2=_mm_unpacklo_epi16(t2,t3);
__m128i u3=_mm_unpackhi_epi16(t2,t3);
__m128i v0=_mm_unpacklo_epi32(u0,u2);
__m128i v1=_mm_unpackhi_epi32(u0,u2);
__m128i v2=_mm_unpacklo_epi32(u1,u3);
__m128i v3=_mm_unpackhi_epi32(u1,u3);
if(d!=0)_mm_storel_epi64((__m128i *)(base+(size_t)0*MF_SPL+j),v0);
if(d!=1)_mm_storel_epi64((__m128i *)(base+(size_t)1*MF_SPL+j),_mm_srli_si128(v0,8));
if(d!=2)_mm_storel_epi64((__m128i *)(base+(size_t)2*MF_SPL+j),v1);
if(d!=3)_mm_storel_epi64((__m128i *)(base+(size_t)3*MF_SPL+j),_mm_srli_si128(v1,8));
if(d!=4)_mm_storel_epi64((__m128i *)(base+(size_t)4*MF_SPL+j),v2);
if(d!=5)_mm_storel_epi64((__m128i *)(base+(size_t)5*MF_SPL+j),_mm_srli_si128(v2,8));
if(d!=6)_mm_storel_epi64((__m128i *)(base+(size_t)6*MF_SPL+j),v3);
}
for(;j<N;j++){const u8 *row=a13_sigrow+(size_t)od[j]*8;for(int e=0;e<7;e++)if(e!=d)base[(size_t)e*MF_SPL+j]=row[e];}
}
g_sig_merged=1;
}
if (s_sig && !g_sig_merged) {
for (int d = 0; d < k; d++) {
const u32 *od = s_ord[d];
u8 *base = s_sig + (size_t)d * k * MF_SPL;
for (u32 j = 0; j < N; j++) {
#if MF_PFB > 0
if (j + MF_PFB < N) {
if (k == 7) _mm_prefetch((const char *)(a13_sigrow + (size_t)od[j + MF_PFB] * 8), _MM_HINT_T0);
else _mm_prefetch((const char *)(s_pm + (size_t)od[j + MF_PFB] * STRIDE), _MM_HINT_T0);
}
#endif
if (k == 7) {
const u8 *row = a13_sigrow + (size_t)od[j] * 8;
for (int e = 0; e < 7; e++) if (e != d) base[(size_t)e * MF_SPL + j] = row[e];
} else {
const u32 *row = s_pm + (size_t)od[j] * STRIDE;
for (int e = 0; e < k; e++) {
if (e == d) continue;
base[(size_t)e * MF_SPL + j] = (u8)(row[e] >> g_sigsh);
}
}
}
}
}

u64 poolwords = (u64)K1 * (Q + 1) * W;
#if MF_PLEN
if (g_plen_on) {
u64 best = 0;
for (int dsx = 0; dsx < k; dsx++) {
u64 tot = 0;
for (int e = 0; e < K1; e++) {
int d = (e < dsx) ? e : e + 1;
const u32 *mr = s_maxr + ((size_t)dsx * MAXK + d) * MAXQ;
for (u32 b = 0; b <= Q; b++) {
u32 RR = mr[b];
u32 len = ((RR >> 6) + 8u) & ~7u;
if (len > W) len = W;
tot += len;
}
}
if (tot > best) best = tot;
}
if (best && best < poolwords) poolwords = best;
}
#endif
size_t need = (size_t)poolwords * sizeof(u64);
static u64 *pool = 0; static size_t cap2 = 0;
if (need > cap2) { pool = (u64 *)pool_alloc(need + 4096); cap2 = need; }
s_bs = pool;
{ size_t bytes=(size_t)N*sizeof(u32)+4096;
if(bytes>inc_cap){ inc_anchor=(u32*)pool_alloc(bytes); inc_cap=inc_anchor?bytes:0; }
inc_on=inc_anchor && (u64)N<=(u64)AS_WORDS*64;
}

for (int ds = 0; ds < k; ds++) {
u32 q0 = gstart[ds], q1 = gstart[ds + 1];
if (q0 >= q1) continue;
#if MF_WTRIM
{
u32 mx = 1;
for (u32 qi = q0; qi < q1; qi++) { u32 rr = s_gt[ds][s_qord[qi]]; if (rr > mx) mx = rr; }
u32 wp = ((mx >> 6) + 8u) & ~7u;
Wpool = (wp < W) ? wp : W;
}
#endif
#if MF_PLEN

if (g_plen_on) {
u64 tot = 0;
for (int e = 0; e < K1; e++) {
int d = (e < ds) ? e : e + 1;
const u32 *mr = s_maxr + ((size_t)ds * MAXK + d) * MAXQ;
u32 *po = s_pofs + (size_t)e * MAXQ;
u32 *pl = s_plen + (size_t)e * MAXQ;
for (u32 b = 0; b <= Q; b++) {




u32 RR = mr[b];
u32 len = ((RR >> 6) + 8u) & ~7u;
if (len > Wpool) len = Wpool;
po[b] = (u32)tot; pl[b] = len; tot += len;
}
}
if (tot > (u64)K1 * (Q + 1) * W) { g_plen_on = 0; }   
}
#endif

const u32 *spp=s_pos[ds];
for (int e = 0; e < K1; e++) {
int d = (e < ds) ? e : e + 1;
const unsigned *xd = x[d];
const u32 *od = s_ord[d];
if(inc_on && d==((ds==0)?1:0)){
for(u32 j=0;j<N;j++) inc_anchor[j]=spp[od[j]];
#if !MF_BUILD_E1
continue;
#endif
}
u64 *base = g_plen_on ? s_bs : (s_bs + (size_t)e * (Q + 1) * Wpool);
u64 *cur = s_acc;
for (u32 w = 0; w < Wpool; w++) cur[w] = 0;
if (g_plen_on) {

u64 *d0 = s_bs + s_pofs[(size_t)e * MAXQ];
u32 l0 = s_plen[(size_t)e * MAXQ];
for (u32 w = 0; w < l0; w++) d0[w] = 0;
}
u32 ptr = 0;
#if MF_BUILD_NOPOOL
while (ptr < N) ptr++;
#else
for (u32 b = 1; b <= Q; b++) {





u32 pend = (b < Q) ? FPOS(d, b) : (u32)N;
while (ptr < pend) { u32 q = spp[od[ptr]]; cur[q >> 6] |= 1ull << (q & 63); ptr++; }
u64 *dst = g_plen_on ? (base + s_pofs[(size_t)e * MAXQ + b])
: (base + (size_t)b * Wpool);
u32 wlen = g_plen_on ? s_plen[(size_t)e * MAXQ + b] : Wpool;
#if MF_NT




{
u32 w = 0;
for (; w + 4 <= wlen; w += 4)
_mm256_stream_si256((__m256i *)(dst + w), LDA((const __m256i *)(cur + w)));
for (; w < wlen; w++) dst[w] = cur[w];
}
#else
for (u32 w = 0; w < wlen; w++) dst[w] = cur[w];
#endif
}
_mm_sfence();
#endif
}
switch (k) {
case 4: query_group<4>(N, out, ds, q0, q1, Q, Wpool); break;
case 5: query_group<5>(N, out, ds, q0, q1, Q, Wpool); break;
case 6: query_group<6>(N, out, ds, q0, q1, Q, Wpool); break;
case 7: switch (ds) {
case 0: qg_t<7,0>(N, out, ds, q0, q1, Q, Wpool); break;
case 1: qg_t<7,1>(N, out, ds, q0, q1, Q, Wpool); break;
case 2: qg_t<7,2>(N, out, ds, q0, q1, Q, Wpool); break;
case 3: qg_t<7,3>(N, out, ds, q0, q1, Q, Wpool); break;
case 4: qg_t<7,4>(N, out, ds, q0, q1, Q, Wpool); break;
case 5: qg_t<7,5>(N, out, ds, q0, q1, Q, Wpool); break;
case 6: qg_t<7,6>(N, out, ds, q0, q1, Q, Wpool); break;
default: query_group<7>(N, out, ds, q0, q1, Q, Wpool); break;
} break;
case 8: query_group<8>(N, out, ds, q0, q1, Q, Wpool); break;
case 9: query_group<9>(N, out, ds, q0, q1, Q, Wpool); break;
default: query_group<10>(N, out, ds, q0, q1, Q, Wpool); break;
}
}
}

void count_4d(int n, const unsigned *x[4], unsigned *out) { solve_mf((u32)n, (const unsigned **)x, out, 4); }
void count_5d(int n, const unsigned *x[5], unsigned *out) { solve_mf((u32)n, (const unsigned **)x, out, 5); }
void count_6d(int n, const unsigned *x[6], unsigned *out) { solve_mf((u32)n, (const unsigned **)x, out, 6); }
void count_7d(int n, const unsigned *x[7], unsigned *out) { solve_mf((u32)n, (const unsigned **)x, out, 7); }
void count_8d(int n, const unsigned *x[8], unsigned *out) { solve_mf((u32)n, (const unsigned **)x, out, 8); }
void count_9d(int n, const unsigned *x[9], unsigned *out) { solve_mf((u32)n, (const unsigned **)x, out, 9); }
void count_10d(int n, const unsigned *x[10], unsigned *out) { solve_mf((u32)n, (const unsigned **)x, out, 10); }

#ifdef LOCAL_TEST
static void brute_nd(int n, const u32 **x, u32 *out, int k) {
for (int i = 0; i < n; i++) {
u32 c = 0;
for (int j = 0; j < n; j++) {
int ok = 1;
for (int d = 0; d < k; d++) if (!(x[d][j] < x[d][i])) { ok = 0; break; }
c += ok;
}
out[i] = c;
}
}
int main(int argc, char **argv) {
int k = (argc > 1) ? atoi(argv[1]) : 6;
int n = (argc > 2) ? atoi(argv[2]) : 200;
int seed = (argc > 3) ? atoi(argv[3]) : 1;
int mode = (argc > 4) ? atoi(argv[4]) : 0;
int qq = (argc > 5 && atoi(argv[5]) > 0) ? atoi(argv[5]) : 0;
g_Q = qq ? (u32)qq : (u32)(n / 250 + 1);
g_B = (u32)((n + g_Q - 1) / g_Q);
if (argc > 6) g_nosort = atoi(argv[6]);
if (argc > 7) g_nosdmp = atoi(argv[7]);
if (argc > 8) g_skip_and = atoi(argv[8]);
if (argc > 9) g_skip_fringe = atoi(argv[9]);
if (argc > 10) g_use_filt = atoi(argv[10]);
if (argc > 11) g_lexsort = atoi(argv[11]);
const int dm = (mode >= 10) ? mode - 10 : mode;
srand(seed);
static u32 *xs[10];
u32 *out = (u32 *)malloc(sizeof(u32) * n);
u32 *ref = (u32 *)malloc(sizeof(u32) * n);
for (int d = 0; d < k; d++) {
xs[d] = (u32 *)malloc(sizeof(u32) * n);
for (int i = 0; i < n; i++) {
if (dm == 0) xs[d][i] = (u32)(rand() % n);
else if (dm == 1) xs[d][i] = (u32)(rand() % 3);
else if (dm == 2) xs[d][i] = 0;
else if (dm == 3) xs[d][i] = (u32)(n - 1 - (rand() % n));
else if (dm == 4) xs[d][i] = (u32)(i);
else xs[d][i] = (u32)(rand() % n);
}
}
if (mode >= 10) {
struct timespec t0, t1;
clock_gettime(CLOCK_MONOTONIC, &t0);
switch (k) {
case 4: count_4d(n, (const unsigned **)xs, out); break;
case 5: count_5d(n, (const unsigned **)xs, out); break;
case 6: count_6d(n, (const unsigned **)xs, out); break;
case 7: count_7d(n, (const unsigned **)xs, out); break;
case 8: count_8d(n, (const unsigned **)xs, out); break;
case 9: count_9d(n, (const unsigned **)xs, out); break;
default: count_10d(n, (const unsigned **)xs, out); break;
}
clock_gettime(CLOCK_MONOTONIC, &t1);
double ms = (t1.tv_sec - t0.tv_sec) * 1e3 + (t1.tv_nsec - t0.tv_nsec) / 1e6;
u64 s = 0; for (int i = 0; i < n; i++) s += out[i];
printf("k=%d n=%d Q=%u TIME %.1f ms  checksum %llu\n", k, n, g_Q, ms, s);
return 0;
}
switch (k) {
case 4: count_4d(n, (const unsigned **)xs, out); break;
case 5: count_5d(n, (const unsigned **)xs, out); break;
case 6: count_6d(n, (const unsigned **)xs, out); break;
case 7: count_7d(n, (const unsigned **)xs, out); break;
case 8: count_8d(n, (const unsigned **)xs, out); break;
case 9: count_9d(n, (const unsigned **)xs, out); break;
default: count_10d(n, (const unsigned **)xs, out); break;
}
brute_nd(n, (const u32 **)xs, ref, k);
int bad = 0;
for (int i = 0; i < n; i++) if (out[i] != ref[i]) { if (bad < 5) printf("MISMATCH i=%d got=%u ref=%u\n", i, out[i], ref[i]); bad++; }
printf("k=%d n=%d mode=%d Q=%u %s (%d mismatches)\n", k, n, mode, g_Q, bad ? "FAIL" : "OK", bad);
return bad != 0;
}
#endif

评测结果