From: "H.J. Lu" <hjl.tools@gmail.com>
To: Noah Goldstein <goldstein.w.n@gmail.com>
Cc: GNU C Library <libc-alpha@sourceware.org>,
"Carlos O'Donell" <carlos@systemhalted.org>
Subject: Re: [PATCH v4 1/5] string: Make tests birdirectional test-memcpy.c
Date: Sun, 7 Nov 2021 05:53:26 -0800 [thread overview]
Message-ID: <CAMe9rOpDLnGG5edvT8PPkk33ZoiDK2EQFdPfGS4oge4=vf+haQ@mail.gmail.com> (raw)
In-Reply-To: <CAFUsyf+cYOOFAww9-wL6q_LSn9bbUAjbk6T-Ea1=Bk1jBaCDzw@mail.gmail.com>
On Sat, Nov 6, 2021 at 2:20 PM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
>
> On Sat, Nov 6, 2021 at 2:13 PM H.J. Lu <hjl.tools@gmail.com> wrote:
> >
> > On Sat, Nov 6, 2021 at 11:33 AM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
> > >
> > > This commit updates the memcpy tests to test both dst > src and dst <
> > > src. This is because there is logic in the code based on the
> > > Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
> > > ---
> > > string/test-memcpy.c | 167 +++++++++++++++++++++++++++++++++++-------
> > > string/test-memmove.c | 75 ++++++++++++++++++-
> > > 2 files changed, 214 insertions(+), 28 deletions(-)
> > >
> > > diff --git a/string/test-memcpy.c b/string/test-memcpy.c
> > > index c9e965bed3..3b0f3127b7 100644
> > > --- a/string/test-memcpy.c
> > > +++ b/string/test-memcpy.c
> > > @@ -17,6 +17,7 @@
> > > <https://www.gnu.org/licenses/>. */
> > >
> > > #ifndef MEMCPY_RESULT
> > > +# define DO_EXTRA_TESTS
> > > # define MEMCPY_RESULT(dst, len) dst
> > > # define MIN_PAGE_SIZE 131072
> > > # define TEST_MAIN
> > > @@ -78,7 +79,7 @@ do_one_test (impl_t *impl, char *dst, const char *src,
> > > static void
> > > do_test (size_t align1, size_t align2, size_t len)
> > > {
> > > - size_t i, j;
> > > + size_t i, j, repeats;
> > > char *s1, *s2;
> > >
> > > align1 &= 4095;
> > > @@ -91,12 +92,14 @@ do_test (size_t align1, size_t align2, size_t len)
> > >
> > > s1 = (char *) (buf1 + align1);
> > > s2 = (char *) (buf2 + align2);
> > > + for (repeats = 0; repeats < 2; ++repeats)
> > > + {
> > > + for (i = 0, j = 1; i < len; i++, j += 23)
> > > + s1[i] = j;
> > >
> > > - for (i = 0, j = 1; i < len; i++, j += 23)
> > > - s1[i] = j;
> > > -
> > > - FOR_EACH_IMPL (impl, 0)
> > > - do_one_test (impl, s2, s1, len);
> > > + FOR_EACH_IMPL (impl, 0)
> > > + do_one_test (impl, s2, s1, len);
> > > + }
> > > }
> > >
> > > static void
> > > @@ -212,56 +215,87 @@ do_random_tests (void)
> > > }
> > >
> > > static void
> > > -do_test1 (size_t size)
> > > +do_test1 (size_t align1, size_t align2, size_t size)
> > > {
> > > void *large_buf;
> > > - large_buf = mmap (NULL, size * 2 + page_size, PROT_READ | PROT_WRITE,
> > > - MAP_PRIVATE | MAP_ANON, -1, 0);
> > > + size_t mmap_size, region_size;
> > > +
> > > + align1 &= (page_size - 1);
> > > + if (align1 == 0)
> > > + align1 = page_size;
> > > +
> > > + align2 &= (page_size - 1);
> > > + if (align2 == 0)
> > > + align2 = page_size;
> > > +
> > > + region_size = (size + page_size - 1) & (~(page_size - 1));
> > > +
> > > + mmap_size = region_size * 2 + 3 * page_size;
> > > + large_buf = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
> > > + MAP_PRIVATE | MAP_ANON, -1, 0);
> > > if (large_buf == MAP_FAILED)
> > > {
> > > - puts ("Failed to allocat large_buf, skipping do_test1");
> > > + puts ("Failed to allocate large_buf, skipping do_test1");
> > > return;
> > > }
> > > -
> > > - if (mprotect (large_buf + size, page_size, PROT_NONE))
> > > + if (mprotect (large_buf + region_size + page_size, page_size, PROT_NONE))
> > > error (EXIT_FAILURE, errno, "mprotect failed");
> > >
> > > - size_t arrary_size = size / sizeof (uint32_t);
> > > - uint32_t *dest = large_buf;
> > > - uint32_t *src = large_buf + size + page_size;
> > > + size_t array_size = size / sizeof (uint32_t);
> > > + uint32_t *dest = large_buf + align1;
> > > + uint32_t *src = large_buf + region_size + 2 * page_size + align2;
> > > size_t i;
> > > size_t repeats;
> > > for(repeats = 0; repeats < 2; repeats++)
> > > {
> > > - for (i = 0; i < arrary_size; i++)
> > > + for (i = 0; i < array_size; i++)
> > > src[i] = (uint32_t) i;
> > > -
> > > FOR_EACH_IMPL (impl, 0)
> > > {
> > > - printf ("\t\tRunning: %s\n", impl->name);
> > > memset (dest, -1, size);
> > > CALL (impl, (char *) dest, (char *) src, size);
> > > - for (i = 0; i < arrary_size; i++)
> > > + for (i = 0; i < array_size; i++)
> > > if (dest[i] != src[i])
> > > {
> > > error (0, 0,
> > > "Wrong result in function %s dst \"%p\" src \"%p\" offset \"%zd\"",
> > > impl->name, dest, src, i);
> > > ret = 1;
> > > - munmap ((void *) large_buf, size * 2 + page_size);
> > > + munmap ((void *) large_buf, mmap_size);
> > > return;
> > > }
> > > }
> > > - dest = src;
> > > - src = large_buf;
> > > + dest = large_buf + region_size + 2 * page_size + align1;
> > > + src = large_buf + align2;
> > > + }
> > > + munmap ((void *) large_buf, mmap_size);
> > > +}
> > > +
> > > +static void
> > > +do_random_large_tests (void)
> > > +{
> > > + size_t i, align1, align2, size;
> > > + for (i = 0; i < 32; ++i)
> > > + {
> > > + align1 = random ();
> > > + align2 = random ();
> > > + size = (random() % 0x1000000) + 0x200000;
> > > + do_test1 (align1, align2, size);
> > > + }
> > > +
> > > + for (i = 0; i < 128; ++i)
> > > + {
> > > + align1 = random ();
> > > + align2 = random ();
> > > + size = (random() % 32768) + 4096;
> > > + do_test1 (align1, align2, size);
> > > }
> > > - munmap ((void *) large_buf, size * 2 + page_size);
> > > }
> > >
> > > int
> > > test_main (void)
> > > {
> > > - size_t i;
> > > + size_t i, j;
> > >
> > > test_init ();
> > >
> > > @@ -298,6 +332,7 @@ test_main (void)
> > > for (i = 19; i <= 25; ++i)
> > > {
> > > do_test (255, 0, 1 << i);
> > > + do_test (0, 4000, 1 << i);
> > > do_test (0, 255, i);
> > > do_test (0, 4000, i);
> > > }
> > > @@ -306,8 +341,88 @@ test_main (void)
> > >
> > > do_random_tests ();
> > >
> > > - do_test1 (0x100000);
> > > - do_test1 (0x2000000);
> > > + do_test1 (0, 0, 0x100000);
> > > + do_test1 (0, 0, 0x2000000);
> > > +
> > > + for (i = 4096; i < 32768; i += 4096)
> > > + {
> > > + for (j = 1; j <= 1024; j <<= 1)
> > > + {
> > > + do_test1 (0, j, i);
> > > + do_test1 (4095, j, i);
> > > + do_test1 (4096 - j, 0, i);
> > > +
> > > + do_test1 (0, j - 1, i);
> > > + do_test1 (4095, j - 1, i);
> > > + do_test1 (4096 - j - 1, 0, i);
> > > +
> > > + do_test1 (0, j + 1, i);
> > > + do_test1 (4095, j + 1, i);
> > > + do_test1 (4096 - j, 1, i);
> > > + }
> > > + }
> > > +
> > > + for (i = 0x300000; i < 0x2000000; i += 0x235689)
> > > + {
> > > + for (j = 64; j <= 1024; j <<= 1)
> > > + {
> > > + do_test1 (0, j, i);
> > > + do_test1 (4095, j, i);
> > > + do_test1 (4096 - j, 0, i);
> > > +
> > > + do_test1 (0, j - 1, i);
> > > + do_test1 (4095, j - 1, i);
> > > + do_test1 (4096 - j - 1, 0, i);
> > > +
> > > + do_test1 (0, j + 1, i);
> > > + do_test1 (4095, j + 1, i);
> > > + do_test1 (4096 - j, 1, i);
> > > + }
> > > + }
> > > +#ifdef DO_EXTRA_TESTS
> > > + for (i = 0x200000; i <= 0x2000000; i += i)
> > > + {
> > > + for (j = 64; j <= 1024; j <<= 1)
> > > + {
> > > + do_test1 (0, j, i);
> > > + do_test1 (4095, j, i);
> > > + do_test1 (4096 - j, 0, i);
> > > +
> > > + do_test1 (0, j - 1, i);
> > > + do_test1 (4095, j - 1, i);
> > > + do_test1 (4096 - j - 1, 0, i);
> > > +
> > > + do_test1 (0, j + 1, i);
> > > + do_test1 (4095, j + 1, i);
> > > + do_test1 (4096 - j, 1, i);
> > > +
> > > + do_test1 (0, j, i + 1);
> > > + do_test1 (4095, j, i + 1);
> > > + do_test1 (4096 - j, 0, i + 1);
> > > +
> > > + do_test1 (0, j - 1, i + 1);
> > > + do_test1 (4095, j - 1, i + 1);
> > > + do_test1 (4096 - j - 1, 0, i + 1);
> > > +
> > > + do_test1 (0, j + 1, i + 1);
> > > + do_test1 (4095, j + 1, i + 1);
> > > + do_test1 (4096 - j, 1, i + 1);
> > > +
> > > + do_test1 (0, j, i - 1);
> > > + do_test1 (4095, j, i - 1);
> > > + do_test1 (4096 - j, 0, i - 1);
> > > +
> > > + do_test1 (0, j - 1, i - 1);
> > > + do_test1 (4095, j - 1, i - 1);
> > > + do_test1 (4096 - j - 1, 0, i - 1);
> > > +
> > > + do_test1 (0, j + 1, i - 1);
> > > + do_test1 (4095, j + 1, i - 1);
> > > + do_test1 (4096 - j, 1, i - 1);
> > > + }
> > > + }
> > > +#endif
> > > + do_random_large_tests ();
> > > return ret;
> > > }
> > >
> > > diff --git a/string/test-memmove.c b/string/test-memmove.c
> > > index a0ce8b0334..5c6d1579e3 100644
> > > --- a/string/test-memmove.c
> > > +++ b/string/test-memmove.c
> > > @@ -100,11 +100,11 @@ do_test (size_t align1, size_t align2, size_t len)
> > > size_t i, j;
> > > char *s1, *s2;
> > >
> > > - align1 &= 63;
> > > + align1 &= (getpagesize() - 1);
> > > if (align1 + len >= page_size)
> > > return;
> > >
> > > - align2 &= 63;
> > > + align2 &= (getpagesize() - 1);
> > > if (align2 + len >= page_size)
> > > return;
> > >
> > > @@ -355,6 +355,51 @@ do_test3 (size_t bytes_move, size_t offset)
> > > munmap ((void *) buf, size);
> > > }
> > >
> > > +static void
> > > +do_test4 (size_t bytes_move, size_t offset1, size_t offset2)
> > > +{
> > > + size_t size, repeats, i;
> > > + uint8_t *buf, *dst, *src;
> > > +
> > > + size = bytes_move + MAX(offset1, offset2);
> > > + buf = mmap(NULL, size, PROT_READ | PROT_WRITE,
> > > + MAP_PRIVATE | MAP_ANON, -1, 0);
> > > +
> > > + if (buf == MAP_FAILED)
> > > + error (EXIT_UNSUPPORTED, errno, "mmap failed");
> > > +
> > > + dst = &buf[offset1];
> > > + src = &buf[offset2];
> > > + for (repeats = 0; repeats < 2; ++repeats)
> > > + {
> > > + FOR_EACH_IMPL (impl, 0)
> > > + {
> > > + for (i = 0; i < bytes_move; i++)
> > > + src[i] = (uint8_t) i;
> > > +#ifdef TEST_BCOPY
> > > + CALL (impl, (char *) src, (char *) dst, bytes_move);
> > > +#else
> > > + CALL (impl, (char *) dst, (char *) src, bytes_move);
> > > +#endif
> > > + for (i = 0; i < bytes_move; i++)
> > > + {
> > > + if (dst[i] != (uint8_t) i)
> > > + {
> > > + error (0, 0,
> > > + "Wrong result in function %s dst \"%p\" src \"%p\" offset \"%zd\"",
> > > + impl->name, dst, buf, i);
> > > + ret = 1;
> > > + break;
> > > + }
> > > + }
> > > + }
> > > + dst = &buf[offset2];
> > > + src = &buf[offset1];
> > > + }
> > > + munmap ((void *) buf, size);
> > > +}
> > > +
> > > +
> > > int
> > > test_main (void)
> > > {
> > > @@ -395,13 +440,39 @@ test_main (void)
> > >
> > > do_random_tests ();
> > >
> > > + do_test2 (0);
> > > do_test2 (33);
> > > + do_test2 (0x200000 - 1);
> > > do_test2 (0x200000);
> > > + do_test2 (0x200000 + 1);
> > > + do_test2 (0x1000000 - 1);
> > > + do_test2 (0x1000000);
> > > + do_test2 (0x1000000 + 1);
> > > do_test2 (0x4000000 - 1);
> > > do_test2 (0x4000000);
> > > + do_test2 (0x4000000 + 1);
> > >
> > > /* Copy 16KB data. */
> > > do_test3 (16384, 3);
> > > + for (i = 4096; i <= 16384; i <<= 1)
> > > + {
> > > + do_test4 (i, 0, i);
> > > + do_test4 (i, 0, i - 1);
> > > + do_test4 (i, 0, i + 1);
> > > + do_test4 (i, 63, i + 63);
> > > + do_test4 (i, 63, i + 64);
> > > + do_test4 (i, 63, i);
> > > +
> > > + do_test4 (i, 0, 1);
> > > + do_test4 (i, 0, 15);
> > > + do_test4 (i, 0, 31);
> > > + do_test4 (i, 0, 63);
> > > + do_test4 (i, 0, 64);
> > > + do_test4 (i, 0, 65);
> > > + do_test4 (i, 0, 127);
> > > + do_test4 (i, 0, 129);
> > > + }
> > > +
> > >
> > > return ret;
> > > }
> > > --
> > > 2.25.1
> > >
> >
> > LGTM.
> >
> > Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
> >
> > Thanks.
>
> Thanks. Pushed the patchset.
>
We need to increase its timeout. On a loaded machine, I got
[hjl@gnu-skx-1 build-x86_64-linux]$ cat string/test-memcpy.out
builtin_memcpy simple_memcpy
__memcpy_avx_unaligned __memcpy_avx_unaligned_erms
__memcpy_avx_unaligned_rtm __memcpy_avx_unaligned_erms_rtm
__memcpy_evex_unaligned __memcpy_evex_unaligned_erms
__memcpy_ssse3_back __memcpy_ssse3 __memcpy_avx512_no_vzeroupper
__memcpy_avx512_unaligned __memcpy_avx512_unaligned_erms
__memcpy_sse2_unaligned __memcpy_sse2_unaligned_erms __memcpy_erms
Timed out: killed the child process
Termination time: 2021-11-07T13:37:49.398927171
Last write to standard output: 2021-11-07T13:33:49.398122020
[hjl@gnu-skx-1 build-x86_64-linux]$
--
H.J.
next prev parent reply other threads:[~2021-11-07 13:54 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-01 5:49 [PATCH v1 " Noah Goldstein
2021-11-01 5:49 ` [PATCH v1 2/5] benchtests: Add additional cases to bench-memcpy.c and bench-memmove.c Noah Goldstein
2021-11-06 2:27 ` H.J. Lu
2021-11-01 5:49 ` [PATCH v1 3/5] benchtests: Add partial overlap case in bench-memmove-walk.c Noah Goldstein
2021-11-06 2:28 ` H.J. Lu
2021-11-01 5:49 ` [PATCH v1 4/5] x86: Optimize memmove-vec-unaligned-erms.S Noah Goldstein
2021-11-01 5:52 ` Noah Goldstein
2021-11-06 2:29 ` H.J. Lu
2021-11-01 5:49 ` [PATCH v1 5/5] x86: Double size of ERMS rep_movsb_threshold in dl-cacheinfo.h Noah Goldstein
2021-11-06 2:31 ` H.J. Lu
2021-11-06 4:39 ` Noah Goldstein
2021-11-06 12:04 ` H.J. Lu
2021-11-06 17:38 ` Noah Goldstein
2021-11-06 2:27 ` [PATCH v1 1/5] string: Make tests birdirectional test-memcpy.c H.J. Lu
2021-11-06 4:39 ` [PATCH v2 " Noah Goldstein
2021-11-06 4:39 ` [PATCH v2 2/5] benchtests: Add additional cases to bench-memcpy.c and bench-memmove.c Noah Goldstein
2021-11-06 4:39 ` [PATCH v2 3/5] benchtests: Add partial overlap case in bench-memmove-walk.c Noah Goldstein
2021-11-06 4:39 ` [PATCH v2 4/5] x86: Optimize memmove-vec-unaligned-erms.S Noah Goldstein
2021-11-06 4:39 ` [PATCH v2 5/5] x86: Double size of ERMS rep_movsb_threshold in dl-cacheinfo.h Noah Goldstein
2021-11-06 17:37 ` [PATCH v3 1/5] string: Make tests birdirectional test-memcpy.c Noah Goldstein
2021-11-06 17:37 ` [PATCH v3 2/5] benchtests: Add additional cases to bench-memcpy.c and bench-memmove.c Noah Goldstein
2021-11-06 17:37 ` [PATCH v3 3/5] benchtests: Add partial overlap case in bench-memmove-walk.c Noah Goldstein
2021-11-06 17:37 ` [PATCH v3 4/5] x86: Optimize memmove-vec-unaligned-erms.S Noah Goldstein
2021-11-06 17:37 ` [PATCH v3 5/5] x86: Double size of ERMS rep_movsb_threshold in dl-cacheinfo.h Noah Goldstein
2021-11-06 17:56 ` H.J. Lu
2021-11-06 18:11 ` Noah Goldstein
2021-11-06 18:21 ` H.J. Lu
2021-11-06 18:34 ` Noah Goldstein
2021-11-06 18:33 ` [PATCH v4 1/5] string: Make tests birdirectional test-memcpy.c Noah Goldstein
2021-11-06 18:33 ` [PATCH v4 2/5] benchtests: Add additional cases to bench-memcpy.c and bench-memmove.c Noah Goldstein
2021-11-06 19:12 ` H.J. Lu
2021-11-06 18:33 ` [PATCH v4 3/5] benchtests: Add partial overlap case in bench-memmove-walk.c Noah Goldstein
2021-11-06 19:11 ` H.J. Lu
2021-11-06 18:33 ` [PATCH v4 4/5] x86: Optimize memmove-vec-unaligned-erms.S Noah Goldstein
2021-11-06 19:11 ` H.J. Lu
2022-04-23 1:41 ` Sunil Pandey
2021-11-06 18:33 ` [PATCH v4 5/5] x86: Double size of ERMS rep_movsb_threshold in dl-cacheinfo.h Noah Goldstein
2021-11-06 19:10 ` H.J. Lu
2022-04-23 1:42 ` Sunil Pandey
2021-11-06 19:12 ` [PATCH v4 1/5] string: Make tests birdirectional test-memcpy.c H.J. Lu
2021-11-06 21:20 ` Noah Goldstein
2021-11-07 13:53 ` H.J. Lu [this message]
2021-12-07 21:10 ` Stafford Horne
2021-12-07 21:36 ` Noah Goldstein
2021-12-07 22:07 ` Stafford Horne
2021-12-07 22:13 ` Noah Goldstein
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAMe9rOpDLnGG5edvT8PPkk33ZoiDK2EQFdPfGS4oge4=vf+haQ@mail.gmail.com' \
--to=hjl.tools@gmail.com \
--cc=carlos@systemhalted.org \
--cc=goldstein.w.n@gmail.com \
--cc=libc-alpha@sourceware.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).