Use a better sorting algorithm

This change changes qsort() to use the same code as NetBSD and MacOS
because it goes 6x faster than Musl's SmoothSort function. Smoothsort
can still be used if you need something that's provenly linearithmic.
This change also improves GNU Make performance on whole by 7 percent!

netbsd nearly   l:    70,196c    22,673ns   m:    68,428c    22,102ns
musl nearly     l:    53,844c    17,391ns   m:    58,726c    18,968ns
unixv6 nearly   l:    65,885c    21,280ns   m:    63,082c    20,375ns

netbsd reverse  l:   120,290c    38,853ns   m:   122,619c    39,605ns
musl reverse    l:   801,826c   258,985ns   m:   794,689c   256,680ns
unixv6 reverse  l:    58,977c    19,049ns   m:    59,764c    19,303ns

netbsd random   l:   146,745c    47,398ns   m:   145,782c    47,087ns
musl random     l:   855,804c   276,420ns   m:   850,912c   274,840ns
unixv6 random   l:   214,325c    69,226ns   m:   213,906c    69,090ns

netbsd 2n       l:    77,299c    24,967ns   m:    76,773c    24,797ns
musl 2n         l:   818,012c   264,213ns   m:   818,282c   264,301ns
unixv6 2n       l: 3,967,009c 1,281,322ns   m: 3,941,792c 1,273,177ns

https://justine.lol/dox/sort.pdf
This commit is contained in:
Justine Tunney 2022-09-06 11:04:29 -07:00
parent 55c6297e13
commit 11ec60d5fc
No known key found for this signature in database
GPG key ID: BE714B4575D6E328
5 changed files with 484 additions and 237 deletions

View file

@ -16,13 +16,14 @@
TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
PERFORMANCE OF THIS SOFTWARE.
*/
#include "libc/mem/alg.h"
#include "libc/intrin/bits.h"
#include "libc/macros.internal.h"
#include "libc/mem/alg.h"
#include "libc/mem/mem.h"
#include "libc/nexgen32e/bsr.h"
#include "libc/stdio/rand.h"
#include "libc/runtime/gc.internal.h"
#include "libc/stdio/rand.h"
#include "libc/stdio/stdio.h"
#include "libc/str/str.h"
#include "libc/testlib/ezbench.h"
#include "libc/testlib/testlib.h"
@ -50,11 +51,39 @@ TEST(qsort, test) {
}
BENCH(qsort, bench) {
size_t i;
size_t n = 1000;
long *p1 = gc(malloc(n * sizeof(long)));
long *p2 = gc(malloc(n * sizeof(long)));
rngset(p1, n * sizeof(long), 0, 0);
EZBENCH2("qsort", memcpy(p2, p1, n * sizeof(long)),
printf("\n");
for (i = 0; i < n; ++i) p1[i] = i + ((lemur64() % 3) - 1);
EZBENCH2("qsort nearly", memcpy(p2, p1, n * sizeof(long)),
qsort(p2, n, sizeof(long), CompareLong));
EZBENCH2("longsort", memcpy(p2, p1, n * sizeof(long)), longsort(p2, n));
EZBENCH2("smoothsort nearly", memcpy(p2, p1, n * sizeof(long)),
smoothsort(p2, n, sizeof(long), CompareLong));
printf("\n");
for (i = 0; i < n; ++i) p1[i] = n - i;
EZBENCH2("qsort reverse", memcpy(p2, p1, n * sizeof(long)),
qsort(p2, n, sizeof(long), CompareLong));
EZBENCH2("smoothsort reverse", memcpy(p2, p1, n * sizeof(long)),
smoothsort(p2, n, sizeof(long), CompareLong));
printf("\n");
rngset(p1, n * sizeof(long), 0, 0);
EZBENCH2("qsort random", memcpy(p2, p1, n * sizeof(long)),
qsort(p2, n, sizeof(long), CompareLong));
EZBENCH2("smoothsort random", memcpy(p2, p1, n * sizeof(long)),
smoothsort(p2, n, sizeof(long), CompareLong));
printf("\n");
for (i = 0; i < n / 2; ++i) {
p1[i] = i;
p1[n - i - 1] = i;
}
EZBENCH2("qsort 2n", memcpy(p2, p1, n * sizeof(long)),
qsort(p2, n, sizeof(long), CompareLong));
EZBENCH2("smoothsort 2n", memcpy(p2, p1, n * sizeof(long)),
smoothsort(p2, n, sizeof(long), CompareLong));
}