about summary refs log tree commit diff
path: root/benchtests
Commit message (Collapse)AuthorAgeFilesLines
* Update copyright dates with scripts/update-copyrights.Joseph Myers2017-01-0176-76/+76
|
* Add configure check for python programSiddhesh Poyarekar2016-12-221-2/+8
| | | | | | | | | | | | | | | | | | | Add a configure check that looks for python3 and python in that order since we had agreed in the past to prefer python3 over python in all our code. The patch also adjusts invocations through the various Makefiles to use the set variable. * configure.ac: Check for python3 or python. * configure: Regenerated. * config.make.in (PYTHON): New variable. * benchtests/Makefile: Don't define PYTHON. (bench): Define target only if PYTHON was defined. * Rules: Don't define PYTHON. Define pretty printer targets only if PYTHON was defined. (tests-printers): Add to tests-unsupported if PYTHON is not found. (python-flags, python-invoke): Remove. (tests-printers-out): Use PYTHON instead of python-invoke.
* This patch cleans up the strsep implementation and improves performance.Wilco Dijkstra2016-12-211-21/+58
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently strsep calls strpbrk is is now a veneer to strcspn. Calling strcspn directly is faster. Since it handles a delimiter string of size 1 as a special case, this is not needed in strsep itself. Although this means there is a slightly higher overhead if the delimiter size is 1, all other cases are slightly faster. The overall performance gain is 5-10% on AArch64. The string/bits/string2.h header contains optimizations for constant delimiters of size 1-3. Benchmarking these showed similar performance for size 1 (since in all cases strchr/strchrnul is used), while size 2 and 3 can give up to 2x speedup for small input strings. However if these cases are common it seems much better to add this optimization to strcspn. So move these header optimizations to string-inlines.c. Improve the strsep benchmark so that it actually benchmarks something. The current version contains a delimiter character at every position in the input string, so there is very little work to do, and the extremely inefficent simple_strsep implementation appears fastest in every case. The new version has either no match in the input for the fail case and a match halfway in the input for the success case. The input is then restored so that each iteration does exactly the same amount of work. Reduce the number of testcases since simple_strsep takes a lot of time now. * benchtests/bench-strsep.c (oldstrsep): Add old implementation. (do_one_test) Restore original string so iteration works. * string/string-inlines.c (do_test): Create better input strings. (test_main) Reduce number of testruns. * string/string-inlines.c (__old_strsep_1c): New function. (__old_strsep_2c): Likewise. (__old_strsep_3c): Likewise. * string/strsep.c (__strsep): Remove case of small delim string. Call strcspn directly rather than strpbrk. * string/bits/string2.h (__strsep): Remove define. (__strsep_1c): Remove. (__strsep_2c): Remove. (__strsep_3c): Remove. (strsep): Remove. * sysdeps/unix/sysv/linux/internal_statvfs.c (__statvfs_getflags): Rename to __strsep.
* benchtests: Add fmaxf/fminf benchmarksAdhemerval Zanella2016-12-193-1/+50
| | | | | | | | | | | | | | | | | | | | | | | This patch adds fmaxf and fminf benchtests. It is based on math/s_fmax_template.c implementation which checks for basically four different classes: 1. if x is greater or equal than y. 2. if x is less than y. 3. if x or y is signaling. 4. if y is nan. Cases 1 and 2 are used for default input number (by mixing normal double numbers and infinity), while case 3 and 4 are used each for on for a benchmark class. Checked on x86_64-linux-gnu and powerpc64-linux-gnu. * benchtests/Makefile (bench-math): Add fminf and fmaxf. (CFLAGS-bench-fmaxf.c): New rule. (CFLAGS-bench-fminf.c): Likewise. * benchtests/fmaxf-inputs: New file. * benchtests/fminf-inputs: Likewise.
* benchtests: Add fmax/fmin benchmarksAdhemerval Zanella2016-12-193-1/+49
| | | | | | | | | | | | | | | | | | | | | | This patch adds fmax and fmin benchtests. It is based math/s_fmax_template.c implementation which checks for basically four different classes: 1. if x is greater or equal than y. 2. if x is less than y. 3. if x or y is signaling. 4. if y is nan. Cases 1 and 2 are used for default input number (by mixing normal double numbers and infinity), while case 3 and 4 are used each for on for a benchmark class. Checked on x86_64-linux-gnu and powerpc64-linux-gnu. * benchtests/Makefile (bench-math): Add fmin and fmax. (CFLAGS-bench-fmax.c): New rule. (CFLAGS-bench-fmin.c): New rule. * benchtests/fmax-inputs: New file. * benchtests/fmin-inputs: Likewise.
* Adjust benchtests to new support library.Adhemerval Zanella2016-12-1930-50/+60
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch basically replaces the test-skeleton.c inclusion by support/test-driver.c and also minor adjustments in bench-string.h. Checked on x86_64-linux-gnu and powerpc64le-linux-gnu. * benchtests/bench-string.h (TEST_FUNCTION): Use name without parenthesis. (CMDLINE_PROCESS): Define using function instead of macro. * benchtests/bench-memccpy.c: Include <support/test-driver.c> instead of test-skeleton. * benchtests/bench-memchr.c: Likewise. * benchtests/bench-memcmp.c: Likewise. * benchtests/bench-memcpy-large.c: Likewise. * benchtests/bench-memcpy.c: Likewise. * benchtests/bench-memmem.c: Likewise. * benchtests/bench-memmove-large.c: Likewise. * benchtests/bench-memmove.c: Likewise. * benchtests/bench-memset-large.c: Likewise. * benchtests/bench-memset.c: Likewise. * benchtests/bench-rawmemchr.c: Likewise. * benchtests/bench-strcasecmp.c: Likewise. * benchtests/bench-strcasestr.c: Likewise. * benchtests/bench-strcat.c: Likewise. * benchtests/bench-strchr.c: Likewise. * benchtests/bench-strcmp.c: Likewise. * benchtests/bench-strcpy.c: Likewise. * benchtests/bench-strcpy_chk.c: Likewise. * benchtests/bench-strlen.c: Likewise. * benchtests/bench-strncasecmp.c: Likewise. * benchtests/bench-strncmp.c: Likewise. * benchtests/bench-strncpy.c: Likewise. * benchtests/bench-strnlen.c: Likewise. * benchtests/bench-strpbrk.c: Likewise. * benchtests/bench-strrchr.c: Likewise. * benchtests/bench-strsep.c: Likewise. * benchtests/bench-strspn.c: Likewise. * benchtests/bench-strstr.c: Likewise. * benchtests/bench-strtok.c: Likewise.
* Link benchset tests against libsupportSiddhesh Poyarekar2016-12-181-0/+1
| | | | | | | | Benchsets in benchtests use test-skeleton, so they too need to be linked against the new libsupport DSO. * benchtests/Makefile (binaries-benchset): Depend on libsupport DSO.
* Improve strtok and strtok_r performance. Instead of calling strpbrk whichWilco Dijkstra2016-12-141-3/+31
| | | | | | | | | | | | | | | | | | calls strcspn, call strcspn directly so we get the end of the token without an extra call to rawmemchr. Also avoid an unnecessary call to strcspn after the last token by adding an early exit for an empty string. Change strtok to tailcall strtok_r to avoid unnecessary code duplication. Remove the special header optimization for strtok_r of a 1-character constant string - both strspn and strcspn contain optimizations for this case. Benchmarking this showed similar performance in the worst case, but up to 5.5x better performance in the "found" case for large inputs. * benchtests/bench-strtok.c (oldstrtok): Add old implementation. * string/strtok.c (strtok): Change to tailcall __strtok_r. * string/strtok_r.c (__strtok_r): Optimize for performance. * string/string-inlines.c (__old_strtok_r_1c): New function. * string/bits/string2.h (__strtok_r): Move to string-inlines.c.
* Use -fno-builtin for sqrt benchmark.Joseph Myers2016-10-211-0/+1
| | | | | | | | | | | This patch makes the sqrt benchmark use -fno-builtin, as already done for benchmarks of ffs and ffsll, so that it actually benchmarks the glibc function as (presumably) intended even in the presence of the compiler inlining sqrt. Tested for x86_64 and also used for benchmarking my ARM sqrt patch. * benchtests/Makefile (CFLAGS-bench-sqrt.c): New variable.
* Clear destination buffer updated by the previous runH.J. Lu2016-05-182-0/+5
| | | | | | | | | | | | | Clear the destination buffer updated by the previous run in bench-memcpy.c and test-memcpy.c to catch the error when the following implementations do not copy anything. [BZ #19907] * benchtests/bench-memcpy.c (do_one_test): Clear the destination buffer updated by the previous run. * string/test-memcpy.c (do_one_test): Likewise. * benchtests/bench-memmove.c (do_one_test): Add a comment. * string/test-memmove.c (do_one_test): Likewise.
* benchtests: Support for cross-building benchmarksSiddhesh Poyarekar2016-04-202-5/+22
| | | | | | | | | | | | | | | | This patch adds full support for cross-building benchmarks. Some benchmarks like those that need locales to be generated cannot be built and are hence skipped for cross builds. Tested by cross building for aarch64 on x86_64 and then running the generated benchmark on aarch64. * benchtests/Makefile (wcsmbs-benchset): Include only for native builds and runs. (LOCALES): Likewise. (bench-build): Build timing-type here instead of the bench target. Generate locale only for native builds. * benchtests/README: Add note for cross-building.
* benchtests: Clean up extra-objsSiddhesh Poyarekar2016-04-201-1/+4
| | | | | The bench-clean target would leave behind json-lib.o. Fix up to clean up all extra-objs registered in benchtests.
* benchtests: Update README to include instructions for bench-build targetSiddhesh Poyarekar2016-04-201-0/+17
|
* New make target to only build benchmark binariesSiddhesh Poyarekar2016-04-201-1/+4
| | | | | | | | | | | | | | | For situations where we are cross-building or where we want to avoid building on the target system, we want a way to only build benchmarks and then copy them over to the target system to run them. I have also added a simple enhancement for the 'bench' target where all benchmark binaries are built and then the benchmarks executed. Tested on arm. Makefile.in (bench-build): New target. Rules (PHONY): Add bench-build target. benchtests/Makefile (bench): Depend on bench-build. (bench-build): New target.
* localedata: iw_IL: delete old/deprecated locale [BZ #16137]Mike Frysinger2016-04-084-4/+3
| | | | | | | | From the bug: Obsolete locale. The ISO-639 code for Hebrew was changed from 'iw' to 'he' in 1989, according to Bruno Haible on libc-alpha 2003-09-01. Reported-by: Chris Leonard <cjlhomeaddress@gmail.com>
* Add memcpy/memmove/memset benchmarks with large dataH.J. Lu2016-04-065-2/+384
| | | | | | | | | | | Add memcpy, memmove and memset benchmarks with large data sizes. * benchtests/Makefile (string-benchset): Add memcpy-large, memmove-large and memset-large. * benchtests/bench-memcpy-large.c: New file. * benchtests/bench-memmove-large.c: Likewise. * benchtests/bench-memmove-large.c: Likewise. * benchtests/bench-string.h (TIMEOUT): Don't redefine.
* Test 64-byte alignment in memset benchtestH.J. Lu2016-04-011-1/+6
| | | | | | | | | Add 64-byte alignment tests in memset benchtest for 64-byte vector registers. * benchtests/bench-memset.c (do_test): Support 64-byte alignment. (test_main): Test 64-byte alignment.
* Test 64-byte alignment in memmove benchtestH.J. Lu2016-04-011-0/+8
| | | | | | | | Add 64-byte alignment tests in memmove benchtest for 64-byte vector registers. * benchtests/bench-memmove.c (test_main): Test 64-byte alignment.
* Test 64-byte alignment in memcpy benchtestH.J. Lu2016-04-011-0/+8
| | | | | | | Add 64-byte alignment tests in memcpy benchtest for 64-byte vector registers. * benchtests/bench-memcpy.c (test_main): Test 64-byte alignment.
* Support --enable-hardcoded-path-in-tests in benchtestsH.J. Lu2016-03-081-2/+2
| | | | | | | | | | benchtests should use $(test-via-rtld-prefix) and $(+link-tests) like other glibc tests. [BZ #19783] * benchtests/Makefile (run-bench): Replace $(rtld-prefix) with $(test-via-rtld-prefix). ($(binaries-bench)): Replace $(+link) with $(+link-tests).
* Use $(PYTHON) to run benchtests python files.Carlos O'Donell2016-01-131-3/+4
|
* Update copyright dates with scripts/update-copyrights.Joseph Myers2016-01-0473-73/+73
|
* benchtests: ffs and ffsll are string functions, not mathSiddhesh Poyarekar2015-12-091-16/+18
| | | | | | | The ffs and ffsll functions were listed as math functions when they are actually defined in strings.h and string.h respectively. Shuffle around the Makefile variables a bit and make a separate space for ffs and ffsll.
* benchtests: Add inputs from sin and cos to sincosSiddhesh Poyarekar2015-12-091-0/+5102
| | | | | | | The sincos benchmark has only about a dozen inputs that don't measure the impact of changes to various passes. Since much of the code properties are inherited from sin and cos, copy those inputs in to get more comprehensive coverage.
* benchtests: Mark output variables as usedSiddhesh Poyarekar2015-11-171-1/+1
| | | | | | | | Prevent function calls that don't return anything from being optimized out by the compiler by marking its input variables as used. This prevents the sincos function call from being optimized out in the benchmark.
* Add a new benchmark for isinf/isnan/isnormal/isfinite/fpclassify. The test ↵Wilco Dijkstra2015-09-185-16/+355
| | | | | | | | | | | | | uses 2 arrays with 1024 doubles, one with 99% finite FP numbers (10% zeroes, 10% negative) and 1% inf/NaN, the other with 50% inf, and 50% Nan. ChangeLog: 2015-09-18 Wilco Dijkstra <wdijkstr@arm.com> * benchtests/Makefile: Add bench-math-inlines, link with libm. * benchtests/bench-math-inlines.c: New benchmark. * benchtests/bench-util.h: New file. * benchtests/bench-util.c: New file. * benchtests/bench-skeleton.c: Add include of bench-util.c/h.
* S390: Optimize wmemcmp.Stefan Liebler2015-08-262-1/+21
| | | | | | | | | | | | | | | | | This patch provides optimized version of wmemcmp with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/wmemcmp-c.c: New File. * sysdeps/s390/multiarch/wmemcmp-vx.S: Likewise. * sysdeps/s390/multiarch/wmemcmp.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add wmemcmp functions. * sysdeps/s390/multiarch/ifunc-impl-list-common.c (__libc_ifunc_impl_list_common): Add ifunc test for wmemcmp. * benchtests/bench-wmemcmp.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wmemcmp.
* S390: Optimize wmemset.Stefan Liebler2015-08-263-22/+63
| | | | | | | | | | | | | | | | | | | | | | This patch provides optimized version of wmemset with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/wmemset-c.c: New File. * sysdeps/s390/multiarch/wmemset-vx.S: Likewise. * sysdeps/s390/multiarch/wmemset.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add wmemset functions. * sysdeps/s390/multiarch/ifunc-impl-list-common.c (__libc_ifunc_impl_list_common): Add ifunc test for wmemset. * wcsmbs/wmemset.c: Use WMEMSET if defined. * string/test-memset.c: Add wmemset support. * wcsmbs/test-wmemset.c: New File. * wcsmbs/Makefile (strop-tests): Add wmemset. * benchtests/bench-memset.c: Add wmemset support. * benchtests/bench-wmemset.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wmemset.
* S390: Optimize memchr, rawmemchr and wmemchr.Stefan Liebler2015-08-263-24/+68
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of memchr, rawmemchr and wmemchr with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/memchr-vx.S: New File. * sysdeps/s390/multiarch/memchr.c: Likewise. * sysdeps/s390/multiarch/rawmemchr-c.c: Likewise. * sysdeps/s390/multiarch/rawmemchr-vx.S: Likewise. * sysdeps/s390/multiarch/rawmemchr.c: Likewise. * sysdeps/s390/multiarch/wmemchr-c.c: Likewise. * sysdeps/s390/multiarch/wmemchr-vx.S: Likewise. * sysdeps/s390/multiarch/wmemchr.c: Likewise. * sysdeps/s390/s390-32/multiarch/memchr.c: Likewise. * sysdeps/s390/s390-64/multiarch/memchr.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add memchr, wmemchr and rawmemchr functions. * sysdeps/s390/multiarch/ifunc-impl-list-common.c (__libc_ifunc_impl_list_common): Add ifunc test for memchr, rawmemchr and wmemchr. * wcsmbs/wmemchr.c: Use WMEMCHR if defined. * string/test-memchr.c: Add wmemchr support. * wcsmbs/test-wmemchr.c: New File. * wcsmbs/Makefile (strop-tests): Add wmemchr. * benchtests/bench-memchr.c: Add wmemchr support. * benchtests/bench-wmemchr.c: New File. * benchtests/Makefile (wcsmbs-bench): wmemchr.
* S390: Optimize strcspn and wcscspn.Stefan Liebler2015-08-263-13/+54
| | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strcspn and wcscspn with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strcspn-c.c: New File. * sysdeps/s390/multiarch/strcspn-vx.S: Likewise. * sysdeps/s390/multiarch/strcspn.c: Likewise. * sysdeps/s390/multiarch/wcscspn-c.c: Likewise. * sysdeps/s390/multiarch/wcscspn-vx.S: Likewise. * sysdeps/s390/multiarch/wcscspn.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strcspn and wcscspn functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strcspn, wcscspn. * wcsmbs/wcscspn.c: Use WCSCSPN if defined. * string/test-strcspn.c: Add wcscspn support. * wcsmbs/test-wcscspn.c: New File. * wcsmbs/Makefile (strop-tests): Add wcscspn. * benchtests/bench-strcspn.c: Add wcscspn support. * benchtests/bench-wcscspn.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcscspn.
* S390: Optimize strpbrk and wcspbrk.Stefan Liebler2015-08-263-36/+86
| | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strpbrk and wcspbrk with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strpbrk-c.c: New File. * sysdeps/s390/multiarch/strpbrk-vx.S: Likewise. * sysdeps/s390/multiarch/strpbrk.c: Likewise. * sysdeps/s390/multiarch/wcspbrk-c.c: Likewise. * sysdeps/s390/multiarch/wcspbrk-vx.S: Likewise. * sysdeps/s390/multiarch/wcspbrk.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strpbrk and wcspbrk functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strpbrk, wcspbrk. * wcsmbs/wcspbrk.c: Use WCSPBRK if defined. * string/test-strpbrk.c: Add wcspbrk support. * wcsmbs/test-wcspbrk.c: New File. * wcsmbs/Makefile (strop-tests): Add wcspbrk. * benchtests/bench-strpbrk.c: Add wcspbrk support. * benchtests/bench-wcspbrk.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcspbrk.
* S390: Optimize strspn and wcsspn.Stefan Liebler2015-08-263-25/+70
| | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strspn and wcsspn with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strspn-c.c: New File. * sysdeps/s390/multiarch/strspn-vx.S: Likewise. * sysdeps/s390/multiarch/strspn.c: Likewise. * sysdeps/s390/multiarch/wcsspn-c.c: Likewise. * sysdeps/s390/multiarch/wcsspn-vx.S: Likewise. * sysdeps/s390/multiarch/wcsspn.c: Likewise. * wcsmbs/wcsspn.c: Use WCSSPN if defined. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strspn and wcsspn functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strspn, wcsspn. * string/test-strspn.c: Add wcsspn support. * wcsmbs/test-wcsspn.c: New File. * wcsmbs/Makefile (strop-tests): Add wcsspn. * benchtests/bench-strspn.c: Add wcsspn support. * benchtests/bench-wcsspn.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcsspn.
* S390: Optimize strrchr and wcsrchr.Stefan Liebler2015-08-262-1/+21
| | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strrchr and wcsrchr with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strrchr-c.c: New File. * sysdeps/s390/multiarch/strrchr-vx.S: Likewise. * sysdeps/s390/multiarch/strrchr.c: Likewise. * sysdeps/s390/multiarch/wcsrchr-c.c: Likewise. * sysdeps/s390/multiarch/wcsrchr-vx.S: Likewise. * sysdeps/s390/multiarch/wcsrchr.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strrchr and wcsrchr functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strrchr, wcsrchr. * benchtests/bench-wcsrchr.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcsrchr.
* S390: Optimize strchrnul and wcschrnul.Stefan Liebler2015-08-263-8/+38
| | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strchrnul and wcschrnul with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strchrnul-c.c: New File. * sysdeps/s390/multiarch/strchrnul-vx.S: Likewise. * sysdeps/s390/multiarch/strchrnul.c: Likewise. * sysdeps/s390/multiarch/wcschrnul-c.c: Likewise. * sysdeps/s390/multiarch/wcschrnul-vx.S: Likewise. * sysdeps/s390/multiarch/wcschrnul.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strchrnul and wcschrnul functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strchrnul, wcschrnul. * wcsmbs/wcschrnul.c: Use WCSCHRNUL if defined. * string/test-strchr.c: Add wcschrnul support. * wcsmbs/test-wcschrnul.c: New File. * wcsmbs/Makefile (strop-tests): Add wcschrnul. * benchtests/bench-strchr.c: Add wcschrnul support. * benchtests/bench-wcschrnul.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcschrnul.
* S390: Optimize strchr and wcschr.Stefan Liebler2015-08-262-1/+21
| | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strchr and wcschr with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strchr-c.c: New File. * sysdeps/s390/multiarch/strchr-vx.S: Likewise. * sysdeps/s390/multiarch/strchr.c: Likewise. * sysdeps/s390/multiarch/wcschr-c.c: Likewise. * sysdeps/s390/multiarch/wcschr-vx.S: Likewise. * sysdeps/s390/multiarch/wcschr.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strchr and wcschr functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strchr, wcschr. * string/strchr.c (STRCHR): Define and use macro. * benchtests/bench-wcschr.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcschr.
* S390: Optimize strncmp and wcsncmp.Stefan Liebler2015-08-263-26/+106
| | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strncmp and wcsncmp with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strncmp-c.c: New File. * sysdeps/s390/multiarch/strncmp-vx.S: Likewise. * sysdeps/s390/multiarch/strncmp.c: Likewise. * sysdeps/s390/multiarch/wcsncmp-c.c: Likewise. * sysdeps/s390/multiarch/wcsncmp-vx.S: Likewise. * sysdeps/s390/multiarch/wcsncmp.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strncmp and wcsncmp functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strncmp, wcsncmp. * wcsmbs/wcsncmp.c (WCSNCMP): Define and use macro. * benchtests/bench-strncmp.c: Add wcsncmp support. * benchtests/bench-wcsncmp.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcsncmp.
* S390: Optimize strcmp and wcscmp.Stefan Liebler2015-08-262-1/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strcmp and wcscmp with the z13 vector instructions. The architecture specific string.h had a typo, which leads to ommiting the inline version in this file if __USE_STRING_INLINES is defined. Tested this inline version by tweaking test-strcmp.c. ChangeLog: * sysdeps/s390/multiarch/strcmp-vx.S: New File. * sysdeps/s390/multiarch/strcmp.c: Likewise. * sysdeps/s390/multiarch/wcscmp-c.c: Likewise. * sysdeps/s390/multiarch/wcscmp-vx.S: Likewise. * sysdeps/s390/multiarch/wcscmp.c: Likewise. * sysdeps/s390/s390-32/multiarch/strcmp.c: Likewise. * sysdeps/s390/s390-64/multiarch/strcmp.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strcmp and wcscmp functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strcmp, wcscmp. * string/strcmp.c (STRCMP): Define and use macro. * benchtests/bench-wcscmp.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcscmp. * sysdeps/s390/bits/string.h: Fix typo: _HAVE_STRING_ARCH_strcmp instead of _HAVE_STRING_ARCH_memchr.
* S390: Optimize strncat wcsncat.Stefan Liebler2015-08-263-37/+82
| | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strncat and wcsncat with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strncat-c.c: New File. * sysdeps/s390/multiarch/strncat-vx.S: Likewise. * sysdeps/s390/multiarch/strncat.c: Likewise. * sysdeps/s390/multiarch/wcsncat-c.c: Likewise. * sysdeps/s390/multiarch/wcsncat-vx.S: Likewise. * sysdeps/s390/multiarch/wcsncat.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strncat and wcsncat functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strncat, wcsncat. * wcsmbs/wcsncat.c (WCSNCAT): Define and use macro. * string/test-strncat.c: Add wcsncat support. * wcsmbs/test-wcsncat.c: New File. * wcsmbs/Makefile (strop-tests): Add wcsncat. * benchtests/bench-strncat.c: Add wcsncat support. * benchtests/bench-wcsncat.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcsncat.
* S390: Optimize strcat and wcscat.Stefan Liebler2015-08-263-32/+78
| | | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strcat and wcscat with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strcat-c.c: New File. * sysdeps/s390/multiarch/strcat-vx.S: Likewise. * sysdeps/s390/multiarch/strcat.c: Likewise. * sysdeps/s390/multiarch/wcscat-c.c: Likewise. * sysdeps/s390/multiarch/wcscat-vx.S: Likewise. * sysdeps/s390/multiarch/wcscat.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strcat and wcscat functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strcat, wcscat. * string/strcat.c (STRCAT): Define and use macro. * wcsmbs/wcscat.c: Use WCSCAT if defined. * string/test-strcat.c: Add wcscat support. * wcsmbs/test-wcscat.c: New File. * wcsmbs/Makefile (strop-tests): Add wcscat. * benchtests/bench-strcat.c: Add wcscat support. * benchtests/bench-wcscat.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcscat.
* S390: Optimize stpncpy and wcpncpy.Stefan Liebler2015-08-263-12/+51
| | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of stpncpy and wcpncpy with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/stpncpy-c.c: New File. * sysdeps/s390/multiarch/stpncpy-vx.S: Likewise. * sysdeps/s390/multiarch/stpncpy.c: Likewise. * sysdeps/s390/multiarch/wcpncpy-c.c: Likewise. * sysdeps/s390/multiarch/wcpncpy-vx.S: Likewise. * sysdeps/s390/multiarch/wcpncpy.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add stpncpy and wcpncpy functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for stpncpy, wcpncpy. * wcsmbs/wcpncpy.c: Use WCPNCPY if defined. * string/test-stpncpy.c: Add wcpncpy support. * wcsmbs/test-wcpncpy.c: New File. * wcsmbs/Makefile (strop-tests): Add wcpncpy. * benchtests/bench-stpncpy.c: Add wcpncpy support. * benchtests/bench-wcpncpy.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcpncpy.
* S390: Optimize strncpy and wcsncpy.Stefan Liebler2015-08-263-38/+94
| | | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strncpy and wcsncpy with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strncpy-vx.S: New File. * sysdeps/s390/multiarch/strncpy.c: Likewise. * sysdeps/s390/multiarch/wcsncpy-c.c: Likewise. * sysdeps/s390/multiarch/wcsncpy-vx.S: Likewise. * sysdeps/s390/multiarch/wcsncpy.c: Likewise. * sysdeps/s390/s390-32/multiarch/strncpy.c: Likewise. * sysdeps/s390/s390-64/multiarch/strncpy.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strncpy and wcsncpy functions. * wcsmbs/wcsncpy.c: Use WCSNCPY if defined. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strncpy, wcsncpy. * string/test-strncpy.c: Add wcsncpy support. * wcsmbs/test-wcsncpy.c: New File. * wcsmbs/Makefile (strop-tests): Add wcsncpy. * benchtests/bench-strncpy.c: Add wcsncpy support. * benchtests/bench-wcsncpy.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcsncpy
* S390: Optimize stpcpy and wcpcpy.Stefan Liebler2015-08-263-10/+45
| | | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of stpcpy and wcpcpy with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/stpcpy-c.c: New File. * sysdeps/s390/multiarch/stpcpy-vx.S: Likewise. * sysdeps/s390/multiarch/stpcpy.c: Likewise. * sysdeps/s390/multiarch/wcpcpy-c.c: Likewise. * sysdeps/s390/multiarch/wcpcpy-vx.S: Likewise. * sysdeps/s390/multiarch/wcpcpy.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add stpcpy and wcpcpy functions. * string/stpcpy.c: Use STPCPY if defined. * wcsmbs/wcpcpy.c: Use WCPCPY if defined. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for stpcpy, wcpcpy. * string/test-stpcpy.c: Add wcpcpy support. * wcsmbs/test-wcpcpy.c: New File. * wcsmbs/Makefile (strop-tests): Add wcpcpy. * benchtests/bench-stpcpy.c: Add wcpcpy support. * benchtests/bench-wcpcpy.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcpcpy.
* S390: Optimize strcpy and wcscpy.Stefan Liebler2015-08-262-1/+21
| | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strcpy and wcscpy with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strcpy-vx.S: New File. * sysdeps/s390/multiarch/strcpy.c: Likewise. * sysdeps/s390/multiarch/wcscpy-c.c: Likewise. * sysdeps/s390/multiarch/wcscpy-vx.S: Likewise. * sysdeps/s390/multiarch/wcscpy.c: Likewise. * sysdeps/s390/s390-32/multiarch/strcpy.c: Likewise. * sysdeps/s390/s390-64/multiarch/strcpy.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strcpy and wcscpy functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strcpy, wcscpy. * benchtests/bench-wcscpy.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcscpy.
* S390: Optimize strnlen and wcsnlen.Stefan Liebler2015-08-263-26/+67
| | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strnlen and wcsnlen with the z13 vector instructions. ChangeLog: * sysdeps/s390/multiarch/strnlen-c.c: New File. * sysdeps/s390/multiarch/strnlen-vx.S: Likewise. * sysdeps/s390/multiarch/strnlen.c: Likewise. * sysdeps/s390/multiarch/wcsnlen-c.c: Likewise. * sysdeps/s390/multiarch/wcsnlen-vx.S: Likewise. * sysdeps/s390/multiarch/wcsnlen.c: Likewise. * sysdeps/s390/multiarch/Makefile (sysdep_routines): Add strnlen and wcsnlen functions. * sysdeps/s390/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add ifunc test for strnlen, wcsnlen. * wcsmbs/wcsnlen.c: Use WCSNLEN if defined. * string/test-strnlen.c: Add wcsnlen support. * wcsmbs/test-wcsnlen.c: New File. * wcsmbs/Makefile (strop-tests): Add wcsnlen. * benchtests/bench-strnlen.c: Add wcsnlen support. * benchtests/bench-wcsnlen.c: New File. * benchtests/Makefile (wcsmbs-bench): Add wcsnlen.
* S390: Optimize strlen and wcslen.Stefan Liebler2015-08-262-1/+22
| | | | | | | | | | | | | | | | | | | | | | | | | This patch provides optimized versions of strlen and wcslen with the z13 vector instructions. The helper macro IFUNC_VX_IMPL is introduced and is used to register all __<func>_c() and __<func>_vx() functions within __libc_ifunc_impl_list() to the ifunc test framework. ChangeLog: * sysdeps/s390/multiarch/Makefile: New File. * sysdeps/s390/multiarch/strlen-c.c: Likewise. * sysdeps/s390/multiarch/strlen-vx.S: Likewise. * sysdeps/s390/multiarch/strlen.c: Likewise. * sysdeps/s390/multiarch/wcslen-c.c: Likewise. * sysdeps/s390/multiarch/wcslen-vx.S: Likewise. * sysdeps/s390/multiarch/wcslen.c: Likewise. * string/strlen.c (STRLEN): Define and use macro. * sysdeps/s390/multiarch/ifunc-impl-list.c (IFUNC_VX_IMPL): New macro function. (__libc_ifunc_impl_list): Add ifunc test for strlen, wcslen. * benchtests/Makefile (wcsmbs-bench): New variable. (string-bench-all): Added wcsmbs-bench. * benchtests/bench-wcslen.c: New File.
* Reflect renaming of bh_IN and tu_IN in SUPPORTED file [BZ #17475]Khem Raj2015-07-201-2/+2
|
* Fix benchtests build failure after 'add benchmark for strcoll'Stefan Liebler2015-06-191-3/+1
| | | | | | | | | | | This patch fixes implicit declaration of function strdup, strtok, strcoll, strchr and removes unused variable res. ChangeLog: * benchtests/bench-strcoll.c: Include string.h. (main): Remove unused variable res.
* benchtest: script to compare two benchmarksSiddhesh Poyarekar2015-06-012-0/+280
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This script is a sample implementation that uses import_bench to construct two benchmark objects and compare them. If detailed timing information is available (when one does `make DETAILED=1 bench`), it writes out graphs for all functions it benchmarks and prints significant differences in timings of the two benchmark runs. If detailed timing information is not available, it points out significant differences in aggregate times. Call this script as follows: compare_bench.py schema_file.json bench1.out bench2.out Alternatively, if one wants to set a different threshold for warnings (default is a 10% difference): compare_bench.py schema_file.json bench1.out bench2.out 25 The threshold in the example above is 25%. schema_file.json is the JSON schema (which is $srcdir/benchtests/scripts/benchout.schema.json for the benchmark output file) and bench1.out and bench2.out are the two benchmark output files to compare. The key functionality here is the compress_timings function which groups together points that are close together into a single point that is the mean of all its representative points. Any point in such a group is at most 1.5x the smallest point in that group. The detailed derivation is a comment in the function. * benchtests/scripts/compare_bench.py: New file. * benchtests/scripts/import_bench.py (mean): New function. (split_list): Likewise. (do_for_all_timings): Likewise. (compress_timings): Likewise.
* New module to import and process benchmark outputSiddhesh Poyarekar2015-06-012-25/+71
| | | | | | | | | | | | | | | This is the beginning of a module to import and process benchmark outputs. The module currently supports importing of a bench.out and validating it against a schema file. In future this could grow a set of routines that benchmark consumers may find useful to build their own analysis tools. I have altered validate_bench to use this module too. * benchtests/scripts/import_bench.py: New file. * benchtests/scripts/validate_benchout.py: Import import_bench instead of jsonschema. (validate_bench): Remove function. (main): Use import_bench.
* Add sprintf benchmark.Carlos O'Donell2015-05-213-1/+19
| | | | | Tests position and non-positional arguments with two test string.
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-12-02 05:06:37 +0000