Improve the random memcpy benchmark. Double the number of copies and
increase the memory sizes tested to 512KB. Add a more detailed
distribution of memcpy alignment and sizes up to 4096 based on SPEC2017
traces.
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
Add a script for visualizing the JSON output generated by existing
glibc string microbenchmarks.
Overview:
plot_strings.py is capable of plotting benchmark results in the
following formats, which are controlled with the -p or --plot argument:
1. absolute timings (-p time): plot the timings as they are in the
input benchmark results file.
2. relative timings (-p rel): plot relative timing difference with
respect to a chosen ifunc (controlled with -b argument).
3. performance relative to max (-p max): for each varied parameter
value, plot 1/timing as the percentage of the maximum value out of
the plotted ifuncs.
4. throughput (-p thru): plot varied parameter value over timing
For all types of graphs, there is an option to explicitly specify
the subset of ifuncs to plot using the --ifuncs parameter.
For plot types 1. and 4. one can hide/expose exact benchmark figures
using the --values flag.
When plotting relative timing differences between ifuncs, the first
ifunc listed in the input JSON file is the baseline, unless the
baseline implementation is explicitly chosen with the --baseline
parameter. For the ease of reading, the script marks the statistically
insignificant range on the graphs. The default is +-5% but this
value can be controlled with the --threshold parameter.
To accommodate for the heterogeneity in benchmark results files,
one can control i.e the x-axis scale, the resolution (dpi) of the
generated figures or the key to access the varied parameter value
in the JSON file. The corresponding options are --logarithmic,
--resolution or --key. The --key parameter ensures that plot_strings.py
works with all files which pass JSON schema validation. The schema
can be chosen with the --schema parameter.
If a window manager is available, one can enable interactive
figure display using the --display flag.
Finally, one can use the --grid flag to enable grid lines in the
generated figures.
Implementation:
plot_strings.py traverses the JSON tree until a 'results' array
is found and generates a separate figure for each such array.
The figure is then saved to a file in one of the available formats
(controlled with the --extension parameter).
As the tree is traversed, the recursive function tracks the metadata
about the test being run, so that each figure has a unique and
meaningful title and filename.
While plot_strings.py works with existing benchmarks, provisions
have been made to allow adding more structure and metadata to these
benchmarks. Currently, many benchmarks produce multiple timing values
for the same value of the varied parameter (typically 'length').
Mutiple data points for the same parameter usually mean that some other
parameter was varied as well, for example, if memmove's src and dst
buffers overlap or not (see bench-memmove-walk.c and
bench-memmove-walk.out).
Unfortunately, this information is not exposed in the benchmark output
file, so plot_strings.py has to resort to computing the geometric mean
of these multiple values. In the process, useful information about the
benchmark configuration is lost. Also, averaging the timings for
different alignments can hide useful characterstics of the benchmarked
ifuncs.
Testing:
plot_strings.py has been tested on all existing string microbenchmarks
which produce results in JSON format. The script was tested on both
Windows 10 and Ubuntu 16.04.2 LTS. It runs on both python 2 and 3
(2.7.12 and 3.5.12 tested).
Useful commands:
1. Plot timings for all ifuncs in bench-strlen.out:
$ ./plot_strings.py bench-strlen.out
2. Display help:
$ ./plot_strings.py -h
3. Plot throughput for __memset_avx512_unaligned_erms and
__memset_avx512_unaligned. Save the generated figure in pdf format to
'results/'. Use logarithmic x-axis scale, show grid lines and expose
the performance numbers:
$ ./plot_strings.py bench.out -o results/ -lgv -e pdf -p thru \
-i __memset_avx512_unaligned_erms __memset_avx512_unaligned
4. Plot relative timings for all ifuncs in bench.out with __generic_memset
as baseline. Display percentage difference threshold of +-10%:
$ ./plot_strings.py bench.out -p rel -b __generic_memset -t 10
Discussion:
1. I would like to propose relaxing the benchout_strings.schema.json
to allow specifying either a 'results' array with 'timings' (as before)
or a 'variants' array. See below example:
{
"timing_type": "hp_timing",
"functions": {
"memcpy": {
"bench-variant": "default",
"ifuncs": ["generic_memcpy", "__memcpy_thunderx"],
"variants": [
{
"name": "powers of 2",
"variants": [
{
"name": "both aligned",
"results": [
{
"length": 1,
"align1": 0,
"align2": 0,
"timings": [x, y]
},
{
"length": 2,
"align1": 0,
"align2": 0,
"timings": [x, y]
},
...
{
"length": 65536,
"align1": 0,
"align2": 0,
"timings": [x, y]
}]
},
{
"name": "dst misaligned",
"results": [
{
"length": 1,
"align1": 0,
"align2": 0,
"timings": [x, y]
},
{
"length": 2,
"align1": 0,
"align2": 1,
"timings": [x, y]
},
...
'variants' array consists of objects such that each object has a 'name'
attribute to describe the configuration of a particular test in the
benchmark. This can be a description, for example, of how the parameter
was varied or what was the buffer alignment tested. The 'name' attribute
is then followed by another 'variants' array or a 'results' array.
The nesting of variants allows arbitrary grouping of benchmark timings,
while allowing description of these groups. Using recusion, it is
possible to proceduraly create titles and filenames for the figures being
generated.
Use the generic C memset/memcpy/memmove in benchtests since comparing
against a slow byte-oriented implementation makes no sense.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
2019-08-29 Wilco Dijkstra <wdijkstr@arm.com>
* benchtests/bench-memcpy.c (simple_memcpy): Remove.
(generic_memcpy): Include generic C memcpy.
* benchtests/bench-memmove.c (simple_memmove): Remove.
(generic_memmove): Include generic C memmove.
* benchtests/bench-memset.c (simple_memset): Remove.
(generic_memset): Include generic C memset.
* benchtests/bench-memset-large.c (simple_memset): Remove.
(generic_memset): Include generic C memset.
* benchtests/bench-memset-walk.c (simple_memset): Remove.
(generic_memset): Include generic C memset.
* string/memcpy.c (MEMCPY): Add defines to enable redirection.
* string/memset.c (MEMSET): Likewise.
* sysdeps/x86_64/memcopy.h: Remove empty file.
* benchtests/Makefile (bench-math): Add logb.
* benchtests/logb-inputs: New file.
* benchtests/logbf-inputs: New file.
Reviewed-by: Gabriel F. T. Gomes <gabrielftg@linux.ibm.com>
Inputs are based on argument reductions from generic and powerpc
implementation.
* benchtests/Makefile (bench-math): Add hypot.
* benchtests/hypot-inputs: New file.
Reviewed-by: Gabriel F. T. Gomes <gabrielftg@linux.ibm.com>
Some benchmarks with a very short runtime show significantly
different results across runs on Aarch64 - up to tens of percents.
Increasing the runtime to 100ms+ makes the deviation under 5%.
Tested on Aarch64 and x86-64.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
* benchtests/bench-memccpy.c: Replace INNER_LOOP_ITERS
with INNER_LOOP_ITERS_LARGE.
* benchtests/bench-memchr.c: Likewise.
* benchtests/bench-rawmemchr.c: Likewise.
* benchtests/bench-strcat.c: Likewise.
* benchtests/bench-strchr.c: Likewise.
* benchtests/bench-string.h: Likewise.
* benchtests/bench-strlen.c: Likewise.
* benchtests/bench-strncpy.c: Likewise.
* benchtests/bench-strnlen.c: Likewise.
This patch fixes the following gcc 9 warnings for "make xcheck" / "make bench":
-string/tst-strcasestr.c:
../include/bits/../../misc/bits/error.h:42:5: error: ‘%s’ directive argument is null [-Werror=format-overflow=]
-argp/argp-test.c:
argp-test.c:130:20: error: ‘%d’ directive writing between 1 and 11 bytes into a region of size 10 [-Werror=format-overflow=]
argp-test.c:130:19: note: directive argument in the range [-2147483648, 122]
argp-test.c:130:5: note: ‘sprintf’ output between 2 and 12 bytes into a destination of size 10
-nss/tst-field.c:
tst-field.c:52:7: error: ‘%s’ directive argument is null [-Werror=format-overflow=]
-benchtests/bench-strstr.c:
../include/bits/../../misc/bits/error.h:42:5: error: ‘%s’ directive argument is null [-Werror=format-overflow=]
-benchtests/bench-malloc-simple.c:
bench-malloc-simple.c:93:16: error: iteration 3 invokes undefined behavior [-Werror=aggressive-loop-optimizations]
ChangeLog:
[BZ #24556]
* string/test-strcasestr.c (check_result): Add NULL check.
* nss/tst-field.c (check_rewrite): Likewise.
* benchtests/bench-strstr.c (do_one_test): Likewise.
* string/test-strstr.c (check_result): Likewise.
* argp/argp-test.c (popt): Increase size of buf to 12.
* benchtests/bench-malloc-simple.c (bench):
Do not initialize tests array out of bounds.
* benchtests/Makefile (bench-math): Add isnan, isinf, and isfinite.
(CFLAGS-bench-isnan.c, CFLAGS-bench-isinf.c,
CFLAGS-bench-isfinite.c): New rule.
* benchtests/isnan-input: New file.
* benchtests/isinf-input: New file.
* benchtests/isfinite-input: New file.
Reviewed-by: Gabriel F. T. Gomes <gabrielftg@linux.ibm.com>
Benchmark needles which exhibit worst-case performance. This shows that
basic_strstr is quadratic and thus unsuitable for large needles.
On the other hand the Two-way and new strstr implementations are linear with
increasing needle sizes. The slowest cases of the two implementations are
within a factor of 2 on several different microarchitectures. Two-way is
slowest on inputs which cause a branch mispredict on almost every character.
The new strstr is slowest on inputs which almost match and result in many
calls to memcmp. Thanks to Szabolcs for providing various hard needles.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
* benchtests/bench-strstr.c (test_hard_needle): New function.
Improve string benchtest timing. Many tests run for 0.01s which is way too
short to give accurate results. Other tests take over 40 seconds which is
way too long. Significantly increase the iterations of the short running
tests. Reduce number of alignment variations in the long running memcpy walk
tests so they take less than 5 seconds.
As a result most tests take at least 0.1s and all finish within 5 seconds.
* benchtests/bench-memcpy-random.c (do_one_test): Use medium iterations.
* benchtests/bench-memcpy-walk.c (test_main): Reduce alignment tests.
* benchtests/bench-memmem.c (do_one_test): Use small iterations.
* benchtests/bench-memmove-walk.c (test_main): Reduce alignment tests.
* benchtests/bench-memset-walk.c (test_main): Reduce alignment tests.
* benchtests/bench-strcasestr.c (do_one_test): Use small iterations.
* benchtests/bench-string.h (INNER_LOOP_ITERS): Increase iterations.
(INNER_LOOP_ITERS_MEDIUM): New define.
(INNER_LOOP_ITERS_SMALL): New define.
* benchtests/bench-strpbrk.c (do_one_test): Use medium iterations.
* benchtests/bench-strsep.c (do_one_test): Use small iterations.
* benchtests/bench-strspn.c (do_one_test): Use medium iterations.
* benchtests/bench-strstr.c (do_one_test): Use small iterations.
* benchtests/bench-strtok.c (do_one_test): Use small iterations.
Benchmarks should reflect distribution build policies, so it makes
sense to honor the BIND_NOW configuration for them.
This commit keeps using $(+link-tests), so that the benchmarks are
linked according to the --enable-hardcoded-path-in-tests configure
option.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Reduce the total time taken by benchtests. The malloc thread test takes 4
minutes to run which is significantly more than most other tests. Reduce
this to a more reasonable 40 seconds. The math tests take 10 seconds each,
eventhough all they do is loop on the same input. Anything more than 1
second runtime is way overkill, so set the limit to 1 second.
* benchtests/Makefile (BENCH_DURATION): Set to 1 second.
* benchtests/bench-malloc-thread.c (BENCH_DURATION): Set to 10 seconds.
Replace slow byte-oriented tests in several string benchmarks with the
generic implementations from the string/ directory so the comparisons
are more realistic and useful.
* benchtests/bench-stpcpy.c (SIMPLE_STPCPY): Remove function.
(generic_stpcpy): New function.
* benchtests/bench-stpncpy.c (SIMPLE_STPNCPY): Remove function.
(generic_stpncpy): New function.
* benchtests/bench-strcat.c (SIMPLE_STRCAT): Remove function.
(generic_strcat): New function.
* benchtests/bench-strcpy.c (SIMPLE_STRCPY): Remove function.
(generic_strcpy): New function.
* benchtests/bench-strncat.c (SIMPLE_STRNCAT): Remove function.
(STUPID_STRNCAT): Remove function.
(generic_strncat): New function.
* benchtests/bench-strncpy.c (SIMPLE_STRNCPY): Remove function.
(STUPID_STRNCPY): Remove function.
(generic_strncpy): New function.
* benchtests/bench-strnlen.c (SIMPLE_STRNLEN): Remove function.
(generic_strnlen): New function.
(memchr_strnlen): New function.
* benchtests/bench-strlen.c (generic_strlen): Define for WIDE.
(memchr_strlen): Likewise.
Improve bench-strstr by using an extract from the manual as the input
to make the test more realistic. Use the same input for both found and
fail cases rather than using a memset of '0' for most of the string,
which measures performance of strchr rather than strstr. Add result
checking to catch potential errors. Remove the repeated tests at slightly
different alignments and add more large needle and haystack testcases.
Replace stupid_strstr with an efficient basic implementation. Add the
Two-way implementation to simplify comparisons with much faster generic
implementations.
* benchtests/bench-strstr.c (input): Add realistic input text.
(stupid_strstr): Remove function.
(basic_strstr): Add function.
(twoway_strstr): Add function.
(do_one_test): Add result checking.
(do_test): Use new input text. Remove accidental early matches.
(test_main): Improve range of tests, reduce unaligned cases.
Improve bench-memmem by replacing simple_memmem with a more efficient
implementation. Add the Two-way implementation to enable direct comparison
with the optimized memmem.
* benchtests/bench-memmem.c (simple_memmem): Remove function.
(basic_memmem): Add function.
(twoway_memmem): Add function.
Add missing generic hp_timing support. It uses clock_gettime (CLOCK_MONOTONIC)
which has unspecified starting time, nano-second accuracy, and should faster on
architectures that implementes the symbol as vDSO.
Checked on aarch64-linux-gnu, x86_64-linux-gnu, and i686-linux-gnu. I also
checked the builds for all afected ABIs.
* benchtests/Makefile (USE_CLOCK_GETTIME) Remove.
* benchtests/README: Update description.
* benchtests/bench-timing.h: Default to hp-timing.
* sysdeps/generic/hp-timing.h (HP_TIMING_DIFF, HP_TIMING_ACCUM_NT,
HP_TIMING_PRINT): Remove.
(HP_TIMING_NOW): Add generic implementation.
(hp_timing_t): Change to uint64_t.
This patch refactor how hp-timing is used on loader code for statistics
report. The HP_TIMING_AVAIL and HP_SMALL_TIMING_AVAIL are removed and
HP_TIMING_INLINE is used instead to check for hp-timing avaliability.
For alpha, which only defines HP_SMALL_TIMING_AVAIL, the HP_TIMING_INLINE
is set iff for IS_IN(rtld).
Checked on aarch64-linux-gnu, x86_64-linux-gnu, and i686-linux-gnu. I also
checked the builds for all afected ABIs.
* benchtests/bench-timing.h: Replace HP_TIMING_AVAIL with
HP_TIMING_INLINE.
* nptl/descr.h: Likewise.
* elf/rtld.c (RLTD_TIMING_DECLARE, RTLD_TIMING_NOW, RTLD_TIMING_DIFF,
RTLD_TIMING_ACCUM_NT, RTLD_TIMING_SET): Define.
(dl_start_final_info, _dl_start_final, dl_main, print_statistics):
Abstract hp-timing usage with RTLD_* macros.
* sysdeps/alpha/hp-timing.h (HP_TIMING_INLINE): Define iff IS_IN(rtld).
(HP_TIMING_AVAIL, HP_SMALL_TIMING_AVAIL): Remove.
* sysdeps/generic/hp-timing.h (HP_TIMING_AVAIL, HP_SMALL_TIMING_AVAIL,
HP_TIMING_NONAVAIL): Likewise.
* sysdeps/ia64/hp-timing.h (HP_TIMING_AVAIL, HP_SMALL_TIMING_AVAIL):
Likewise.
* sysdeps/powerpc/powerpc32/power4/hp-timing.h (HP_TIMING_AVAIL,
HP_SMALL_TIMING_AVAIL): Likewise.
* sysdeps/powerpc/powerpc64/hp-timing.h (HP_TIMING_AVAIL,
HP_SMALL_TIMING_AVAIL): Likewise.
* sysdeps/sparc/sparc32/sparcv9/hp-timing.h (HP_TIMING_AVAIL,
HP_SMALL_TIMING_AVAIL): Likewise.
* sysdeps/sparc/sparc64/hp-timing.h (HP_TIMING_AVAIL,
HP_SMALL_TIMING_AVAIL): Likewise.
* sysdeps/x86/hp-timing.h (HP_TIMING_AVAIL, HP_SMALL_TIMING_AVAIL):
Likewise.
* sysdeps/generic/hp-timing-common.h: Update comment with
HP_TIMING_AVAIL removal.
Add a malloc micro benchmark to enable accurate testing of the
various paths in malloc and free. The benchmark does a varying
number of allocations of a given block size, then frees them again.
It tests 3 different scenarios: single-threaded using main arena,
multi-threaded using thread-arena, main arena with SINGLE_THREAD_P
false.
* benchtests/Makefile: Add malloc-simple benchmark.
* benchtests/bench-malloc-simple.c: New benchmark.
The ORIG_SRC argument is likely a useless relic from the original
correctness tests that are not needed in the benchmarks. Remove the
argument and use S1 to point to the source to avoid confusion.
* benchtests/bench-memmove.c (do_one_test): Remove unused
ORIG_SRC.
(do_test): Adjust.
* benchtests/bench-memmove-large.c (do_one_test): Remove unused
ORIG_SRC.
(do_test): Adjust.
The current bench-strlen compares against a slow byte-oriented strlen which
is not useful given it's too easy to beat. Remove it and compare against the
generic C strlen version and memchr.
* benchtests/bench-strlen.c (generic_strlen): New function.
(memchr_strlen): New function.
Non-consumable data, alias data not related to benchmarks, should be sent to
the standard error, thus pipelines can work as expected.
* benchtests/scripts/compare_bench.py (do_compare): write to stderr in case
stat is not present.
* benchtests/scripts/compare_bench.py (plot_graphs): write to stderr in case
timings field is not present. Also string showing the output filename goes
into the stderr.
Allows user to pick a statistic, defaulting to min and mean, from command
line. At the same time, if stat does not exit, catch the run-time exception
and keep comparing the rest of benchmarked functions. Finally, take care of
division-by-zero exceptions and as the latter, keep comparing the rest of the
functions, turning the script a bit more fault tolerant thus useful.
* benchtests/scripts/compare_bench.py (do_compare): Catch KeyError and
ZeroDivisorError exceptions.
* benchtests/scripts/compare_bench.py (compare_runs): Use stats argument to
loop through user provided statistics.
* benchtests/scripts/compare_bench.py (main): Include the --stats argument.
Allows other functions to be processed, making the script a bit more fault
tolerant thus useful.
* benchtests/scripts/compare_bench.py (compare_runs): Continue instead of return.
This patch makes Python 3.4 or later a required tool for building
glibc, so allowing changes of awk, perl etc. code used in the build
and test to Python code without any such changes needing makefile
conditionals or to handle older Python versions.
This patch makes the configure test for Python check the version and
give an error if Python is missing or too old, and removes makefile
conditionals that are no longer needed. It does not itself convert
any code from another language to Python, and does not remove any
compatibility with older Python versions from existing scripts.
Tested for x86_64.
* configure.ac (PYTHON_PROG): Use AC_CHECK_PROG_VER. Set
critic_missing for versions before 3.4.
* configure: Regenerated.
* manual/install.texi (Tools for Compilation): Document
requirement for Python to build glibc.
* INSTALL: Regenerated.
* Rules [PYTHON]: Make code unconditional.
* benchtests/Makefile [PYTHON]: Likewise.
* conform/Makefile [PYTHON]: Likewise.
* manual/Makefile [PYTHON]: Likewise.
* math/Makefile [PYTHON]: Likewise.
RDTSCP waits until all previous instructions have executed and all
previous loads are globally visible before reading the counter. RDTSC
doesn't wait until all previous instructions have been executed before
reading the counter. All x86 processors since 2010 support RDTSCP
instruction. This patch adds RDTSCP support to benchtests.
* benchtests/Makefile (CPPFLAGS-nonlib): Add -DUSE_RDTSCP if
USE_RDTSCP is defined.
* sysdeps/x86/hp-timing.h (HP_TIMING_NOW): Use RDTSCP if
USE_RDTSCP is defined.
Otherwise, we see the following runtime error when using the parameter:
File "./glibc/benchtests/scripts/compare_bench.py", line 46, in do_compare
if d > threshold:
TypeError: '>' not supported between instances of 'float' and 'str'
* benchtests/scripts/compare_bench.py (main): set float type on
threshold argument.
Add the workload test properties (max-throughput, latency, etc.) to
the schema to prevent benchmark output validation from failing.
* benchtests/scripts/benchout.schema.json (properties): Add
new properties.
Add the duration and iterations attributes to the workloads tests to
make the json schema parser happy
* benchtests/bench-skeleton.c (main): Add duration and
iterations attributes.
Drop realloc_bufs in favour of making alloc_bufs transparently
reallocate the buffers if it had allocated before. Also consolidate
computation of buffer lengths so that they don't get repeated on every
reallocation.
* benchtests/bench-string.h (buf1_size, buf2_size): New
variables.
(init_sizes): New function.
(test_init): Use it.
(alloc_buf, exit_error): New functions.
(alloc_bufs): Use ALLOC_BUF.
(realloc_bufs): Remove.
* benchtests/bench-memcmp.c (do_test): Adjust.
* benchtests/bench-memset-large.c (do_test): Likewise.
* benchtests/bench-memset-walk.c (do_test): Likewise.
* benchtests/bench-memset.c (do_test): Likewise.
* benchtests/bench-strncmp.c (do_test): Likewise.
Python 2 does not have a FileNotFoundError so drop it in favour of
simply printing out the last (and most informative) line of the
exception.
* benchtests/scripts/compare_strings.py: Import traceback.
(parse_file): Pretty-print error.
The argparse library is used on compare_bench script to improve command line
argument parsing. The 'schema validation file' is now optional, reducing by
one the number of required parameters.
* benchtests/scripts/compare_bench.py (__main__): use the argparse
library to improve command line parsing.
(__main__): make schema file as optional parameter (--schema),
defaulting to benchtests/scripts/benchout.schema.json.
(main): move out of the parsing stuff to __main_ and leave it
only as caller of main comparison functions.
Improve strstr performance. Strstr tends to be slow because it uses
many calls to memchr and a slow byte loop to scan for the next match.
Performance is significantly improved by using strnlen on larger blocks
and using strchr to search for the next matching character. strcasestr
can also use strnlen to scan ahead, and memmem can use memchr to check
for the next match.
On the GLIBC bench tests the performance gains on Cortex-A72 are:
strstr: +25%
strcasestr: +4.3%
memmem: +18%
On a 256KB dataset strstr performance improves by 67%, strcasestr by 47%.
Reviewd-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
On x86-64, there may be multiple IFUNC implementations for a given
function. But we may be only interested in a subset of them. This
patch adds -f/--functions argument to compare a subset of IFUNC
implementations.
* benchtests/scripts/compare_strings.py (process_results): Add
funcs argument. Compare only functions which are selected.
(main): Check if base function is among selected functions.
Pass selected functions to process_results.
(__main__): Add -f/--functions argument.
Catch runtime exceptions in case the user provided: wrong base
function, attribute(s) or input file. In any of the latter, quit
immediately with non-zero return code.
* benchtests/scripts/compare_string.py: (process_results) Catch
exception in non-existent base_func and catch exception in
non-existent attribute.
(parse_file) Catch exception in non-existent input file.
Having a string comparison report with neither diff numbers nor header
yields a more useful output to be consumed by other tools.
* benchtests/scripts/compare_string.py: Add --no-diff and --no-header
options to avoid diff calculation and omit header, respectively.
(main): process --no-diff and --no-header
This is a minor style change to move the definition of I to its usage
scope instead of at the top of the function. This is consistent with
glibc style guidelines and more importantly it was getting in the way
of my testing.
* benchtests/bench-memcpy-walk.c (do_test): Move declaration
of I into loop header.
* benchtests/bench-memmove-walk.c (do_test): Likewise.
