ext/numo/narray/gen/tmpl/qsort.c in numo-narray-0.9.1.2 vs ext/numo/narray/gen/tmpl/qsort.c in numo-narray-0.9.1.3
- old
+ new
@@ -51,16 +51,56 @@
#ifndef QSORT_INCL
#define QSORT_INCL
#define Min(x, y) ((x) < (y) ? (x) : (y))
-#define swap(type,a,b) \
- do {type tmp=*(type*)(a); *(type*)(a)=*(type*)(b); *(type*)(b)=tmp;} while(0)
+/*
+ * Qsort routine based on J. L. Bentley and M. D. McIlroy,
+ * "Engineering a sort function",
+ * Software--Practice and Experience 23 (1993) 1249-1265.
+ * We have modified their original by adding a check for already-sorted input,
+ * which seems to be a win per discussions on pgsql-hackers around 2006-03-21.
+ */
+#define swapcode(TYPE, parmi, parmj, n) \
+ do { \
+ size_t i = (n) / sizeof (TYPE); \
+ TYPE *pi = (TYPE *)(void *)(parmi); \
+ TYPE *pj = (TYPE *)(void *)(parmj); \
+ do { \
+ TYPE t = *pi; \
+ *pi++ = *pj; \
+ *pj++ = t; \
+ } while (--i > 0); \
+ } while (0)
-#define vecswap(type, a, b, n) if ((n)>0) swap(type,(a),(b))
+#define SWAPINIT(a, es) swaptype = ((char *)(a) - (char *)0) % sizeof(long) || \
+ (es) % sizeof(long) ? 2 : (es) == sizeof(long)? 0 : 1;
-#define MED3(a,b,c) \
+static inline void
+swapfunc(a, b, n, swaptype)
+ char *a,
+ *b;
+ size_t n;
+ int swaptype;
+{
+ if (swaptype <= 1)
+ swapcode(long, a, b, n);
+ else
+ swapcode(char, a, b, n);
+}
+
+#define swap(a, b) \
+ if (swaptype == 0) { \
+ long t = *(long *)(void *)(a); \
+ *(long *)(void *)(a) = *(long *)(void *)(b); \
+ *(long *)(void *)(b) = t; \
+ } else \
+ swapfunc(a, b, es, swaptype)
+
+#define vecswap(a, b, n) if ((n) > 0) swapfunc((a), (b), (size_t)(n), swaptype)
+
+#define med3(a,b,c,_cmp) \
(cmpgt(b,a) ? \
(cmpgt(c,b) ? b : (cmpgt(c,a) ? c : a)) \
: (cmpgt(b,c) ? b : (cmpgt(c,a) ? a : c)))
#endif
@@ -74,77 +114,99 @@
#define cmp(a,b) cmp<%=suffix%>(a,b)
#define cmpgt(a,b) cmpgt<%=suffix%>(a,b)
<% end %>
<% c_func(:nodef)%>
-void
+static void
<%=type_name%>_qsort<%=suffix%>(void *a, size_t n, ssize_t es)
{
- char *pa, *pb, *pc, *pd, *pl, *pm, *pn;
- int d, r, presorted;
+ char *pa,
+ *pb,
+ *pc,
+ *pd,
+ *pl,
+ *pm,
+ *pn;
+ int d,
+ r,
+ swaptype,
+ presorted;
- loop:
- if (n < 7) {
- for (pm = (char *) a + es; pm < (char *) a + n * es; pm += es)
- for (pl = pm; pl > (char *) a && cmpgt(pl - es, pl);
- pl -= es)
- swap(qsort_dtype, pl, pl - es);
- return;
- }
+ loop:SWAPINIT(a, es);
+ if (n < 7)
+ {
+ for (pm = (char *) a + es; pm < (char *) a + n * es; pm += es)
+ for (pl = pm; pl > (char *) a && cmpgt(pl - es, pl);
+ pl -= es)
+ swap(pl, pl - es);
+ return;
+ }
presorted = 1;
- for (pm = (char *) a + es; pm < (char *) a + n * es; pm += es) {
- if (cmpgt(pm - es, pm)) {
- presorted = 0;
- break;
+ for (pm = (char *) a + es; pm < (char *) a + n * es; pm += es)
+ {
+ if (cmpgt(pm - es, pm))
+ {
+ presorted = 0;
+ break;
+ }
}
- }
if (presorted)
return;
pm = (char *) a + (n / 2) * es;
- if (n > 7) {
- pl = (char *) a;
- pn = (char *) a + (n - 1) * es;
- if (n > 40) {
- d = (n / 8) * es;
- pl = MED3(pl, pl + d, pl + 2 * d);
- pm = MED3(pm - d, pm, pm + d);
- pn = MED3(pn - 2 * d, pn - d, pn);
+ if (n > 7)
+ {
+ pl = (char *) a;
+ pn = (char *) a + (n - 1) * es;
+ if (n > 40)
+ {
+ d = (n / 8) * es;
+ pl = med3(pl, pl + d, pl + 2 * d, cmp);
+ pm = med3(pm - d, pm, pm + d, cmp);
+ pn = med3(pn - 2 * d, pn - d, pn, cmp);
+ }
+ pm = med3(pl, pm, pn, cmp);
}
- pm = MED3(pl, pm, pn);
- }
- swap(qsort_dtype, a, pm);
+ swap(a, pm);
pa = pb = (char *) a + es;
pc = pd = (char *) a + (n - 1) * es;
- for (;;) {
- while (pb <= pc && (r = cmp(pb, a)) <= 0) {
- if (r == 0) {
- swap(qsort_dtype, pa, pb);
- pa += es;
- }
+ for (;;)
+ {
+ while (pb <= pc && (r = cmp(pb, a)) <= 0)
+ {
+ if (r == 0)
+ {
+ swap(pa, pb);
+ pa += es;
+ }
+ pb += es;
+ }
+ while (pb <= pc && (r = cmp(pc, a)) >= 0)
+ {
+ if (r == 0)
+ {
+ swap(pc, pd);
+ pd -= es;
+ }
+ pc -= es;
+ }
+ if (pb > pc)
+ break;
+ swap(pb, pc);
pb += es;
- }
- while (pb <= pc && (r = cmp(pc, a)) >= 0) {
- if (r == 0) {
- swap(qsort_dtype, pc, pd);
- pd -= es;
- }
pc -= es;
}
- if (pb > pc)
- break;
- swap(qsort_dtype, pb, pc);
- pb += es;
- pc -= es;
- }
pn = (char *) a + n * es;
r = Min(pa - (char *) a, pb - pa);
- vecswap(qsort_dtype, a, pb - r, r);
+ vecswap(a, pb - r, r);
r = Min(pd - pc, pn - pd - es);
- vecswap(qsort_dtype, pb, pn - r, r);
+ vecswap(pb, pn - r, r);
if ((r = pb - pa) > es)
<%=type_name%>_qsort<%=suffix%>(a, r / es, es);
- if ((r = pd - pc) > es) {
- a = pn - r;
- n = r / es;
- goto loop;
- }
+ if ((r = pd - pc) > es)
+ {
+ /* Iterate rather than recurse to save stack space */
+ a = pn - r;
+ n = r / es;
+ goto loop;
+ }
+ /* qsort(pn - r, r / es, es, cmp);*/
}