Implementation wise:
1. Remove the VZEROUPPER as memset_{impl}_unaligned_erms does not
use the L(stosb) label that was previously defined.
2. Don't give the hotpath (fallthrough) to zero size.
Code positioning wise:
Move memset_{chk}_erms to its own file. Leaving it in between the
memset_{impl}_unaligned both adds unnecessary complexity to the
file and wastes space in a relatively hot cache section.
Add third argument to X86_ISA_CPU_FEATURES_ARCH_P macro so the runtime
CPU_FEATURES_ARCH_P check can be inverted if the
MINIMUM_X86_ISA_LEVEL is not high enough to constantly evaluate
the check.
Use this new macro to correct the backwards check in ifunc-evex.h
The function was tuned around 64-byte entry alignment and performs
better for all sizes with it.
As well different code boths where explicitly written to touch the
minimum number of cache line i.e sizes <= 32 touch only the entry
cache line.
Most of these don't really matter as there was no dirty upper state
but we should generally avoid stray sse when its not needed.
The one case that really matters is in svml_d_tanh4_core_avx2.S:
blendvps %xmm0, %xmm8, %xmm7
When there was a dirty upper state.
Tested on x86_64-linux
1. Refactor files so that all implementations for in the multiarch
directory.
- Essentially moved sse2 {raw|w}memchr.S implementation to
multiarch/{raw|w}memchr-sse2.S
- The non-multiarch {raw|w}memchr.S file now only includes one of
the implementations in the multiarch directory based on the
compiled ISA level (only used for non-multiarch builds.
Otherwise we go through the ifunc selector).
2. Add ISA level build guards to different implementations.
- I.e memchr-avx2.S which is ISA level 3 will only build if
compiled ISA level <= 3. Otherwise there is no reason to include
it as we will always use one of the ISA level 4
implementations (memchr-evex{-rtm}.S).
3. Add new multiarch/rtld-{raw}memchr.S that just include the
non-multiarch {raw}memchr.S which will in turn select the best
implementation based on the compiled ISA level.
4. Refactor the ifunc selector and ifunc implementation list to use
the ISA level aware wrapper macros that allow functions below the
compiled ISA level (with a guranteed replacement) to be skipped.
- Guranteed replacement essentially means that for any ISA level
build there must be a function that the baseline of the ISA
supports. So for {raw|w}memchr.S since there is not ISA level 2
function, the ISA level 2 build still includes the ISA level
1 (sse2) function. Once we reach the ISA level 3 build, however,
{raw|w}memchr-avx2{-rtm}.S will always be sufficient so the ISA
level 1 implementation ({raw|w}memchr-sse2.S) will not be built.
Tested with and without multiarch on x86_64 for ISA levels:
{generic, x86-64-v2, x86-64-v3, x86-64-v4}
And m32 with and without multiarch.
No functions are changed. It just renames generic implementations from
'{func}_sse2' to '{func}_generic'. This is just because the postfix
"_sse2" was overloaded and was used for files that had hand-optimized
sse2 assembly implementations and files that just redirected back
to the generic implementation.
Full xcheck passed on x86_64.
1. Fix incorrect lower-bound threshold in L(large_memcpy_2x).
Previously was using `__x86_rep_movsb_threshold` and should
have been using `__x86_shared_non_temporal_threshold`.
2. Avoid reloading __x86_shared_non_temporal_threshold before
the L(large_memcpy_4x) bounds check.
3. Document the second bounds check for L(large_memcpy_4x)
more clearly.
This has been missing since the the ifuncs where added.
The performance of SSE4.2 is preferable to to SSE2.
Measured on Tigerlake with N = 20 runs.
Geometric Mean of all benchmarks SSE4.2 / SSE2: 0.906
Add a proper bounds check to __libc_ifunc_impl_list. This makes MAX_IFUNC
redundant and fixes several targets that will write outside the array.
To avoid unnecessary large diffs, pass the maximum in the argument 'i' to
IFUNC_IMPL_ADD - 'max' can be used in new ifunc definitions and existing
ones can be updated if desired.
Passes buildmanyglibc.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
commit 6dcbb7d95d
Author: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Mon Jun 6 21:11:33 2022 -0700
x86: Shrink code size of memchr-avx2.S
Changed how the page cross case aligned string (rdi) in
rawmemchr. This was incompatible with how
`L(cross_page_continue)` expected the pointer to be aligned and
would cause rawmemchr to read data start started before the
beginning of the string. What it would read was in valid memory
but could count CHAR matches resulting in an incorrect return
value.
This commit fixes that issue by essentially reverting the changes to
the L(page_cross) case as they didn't really matter.
Test cases added and all pass with the new code (and where confirmed
to fail with the old code).
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
This is not meant as a performance optimization. The previous code was
far to liberal in aligning targets and wasted code size unnecissarily.
The total code size saving is: 64 bytes
There are no non-negligible changes in the benchmarks.
Geometric Mean of all benchmarks New / Old: 1.000
Full xcheck passes on x86_64.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
This is not meant as a performance optimization. The previous code was
far to liberal in aligning targets and wasted code size unnecissarily.
The total code size saving is: 59 bytes
There are no major changes in the benchmarks.
Geometric Mean of all benchmarks New / Old: 0.967
Full xcheck passes on x86_64.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
The new code:
1. prioritizes smaller user-arg lengths more.
2. optimizes target placement more carefully
3. reuses logic more
4. fixes up various inefficiencies in the logic. The biggest
case here is the `lzcnt` logic for checking returns which
saves either a branch or multiple instructions.
The total code size saving is: 306 bytes
Geometric Mean of all benchmarks New / Old: 0.760
Regressions:
There are some regressions. Particularly where the length (user arg
length) is large but the position of the match char is near the
beginning of the string (in first VEC). This case has roughly a
10-20% regression.
This is because the new logic gives the hot path for immediate matches
to shorter lengths (the more common input). This case has roughly
a 15-45% speedup.
Full xcheck passes on x86_64.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
The new code:
1. prioritizes smaller user-arg lengths more.
2. optimizes target placement more carefully
3. reuses logic more
4. fixes up various inefficiencies in the logic. The biggest
case here is the `lzcnt` logic for checking returns which
saves either a branch or multiple instructions.
The total code size saving is: 263 bytes
Geometric Mean of all benchmarks New / Old: 0.755
Regressions:
There are some regressions. Particularly where the length (user arg
length) is large but the position of the match char is near the
beginning of the string (in first VEC). This case has roughly a
20% regression.
This is because the new logic gives the hot path for immediate matches
to shorter lengths (the more common input). This case has roughly
a 35% speedup.
Full xcheck passes on x86_64.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
The RTM vzeroupper mitigation has no way of replacing inline
vzeroupper not before a return.
This can be useful when hoisting a vzeroupper to save code size
for example:
```
L(foo):
cmpl %eax, %edx
jz L(bar)
tzcntl %eax, %eax
addq %rdi, %rax
VZEROUPPER_RETURN
L(bar):
xorl %eax, %eax
VZEROUPPER_RETURN
```
Can become:
```
L(foo):
COND_VZEROUPPER
cmpl %eax, %edx
jz L(bar)
tzcntl %eax, %eax
addq %rdi, %rax
ret
L(bar):
xorl %eax, %eax
ret
```
This code does not change any existing functionality.
There is no difference in the objdump of libc.so before and after this
patch.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
This patch does not touch any existing code and is only meant to be a
tool for future patches so that simple source files can more easily be
maintained to target multiple VEC classes.
There is no difference in the objdump of libc.so before and after this
patch.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Adding a 512-bit EVEX version of strstr. The algorithm works as follows:
(1) We spend a few cycles at the begining to peek into the needle. We
locate an edge in the needle (first occurance of 2 consequent distinct
characters) and also store the first 64-bytes into a zmm register.
(2) We search for the edge in the haystack by looking into one cache
line of the haystack at a time. This avoids having to read past a page
boundary which can cause a seg fault.
(3) If an edge is found in the haystack we first compare the first
64-bytes of the needle (already stored in a zmm register) before we
proceed with a full string compare performed byte by byte.
Benchmarking results: (old = strstr_sse2_unaligned, new = strstr_avx512)
Geometric mean of all benchmarks: new / old = 0.66
Difficult skiptable(0) : new / old = 0.02
Difficult skiptable(1) : new / old = 0.01
Difficult 2-way : new / old = 0.25
Difficult testing first 2 : new / old = 1.26
Difficult skiptable(0) : new / old = 0.05
Difficult skiptable(1) : new / old = 0.06
Difficult 2-way : new / old = 0.26
Difficult testing first 2 : new / old = 1.05
Difficult skiptable(0) : new / old = 0.42
Difficult skiptable(1) : new / old = 0.24
Difficult 2-way : new / old = 0.21
Difficult testing first 2 : new / old = 1.04
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
This patch implements following evex512 version of string functions.
Perf gain for evex512 version is up to 50% as compared to evex,
depending on length and alignment.
Placeholder function, not used by any processor at the moment.
- String length function using 512 bit vectors.
- String N length using 512 bit vectors.
- Wide string length using 512 bit vectors.
- Wide string N length using 512 bit vectors.
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
Both symbols are marked as legacy in POSIX.1-2001 and removed on
POSIX.1-2008, although the prototypes are defined for _GNU_SOURCE
or _DEFAULT_SOURCE.
GCC also replaces bcopy with a memmove and bzero with memset on default
configuration (to actually get a bzero libc call the code requires
to omit string.h inclusion and built with -fno-builtin), so it is
highly unlikely programs are actually calling libc bzero symbol.
On a recent Linux distro (Ubuntu 22.04), there is no bzero calls
by the installed binaries.
$ cat count_bstring.sh
#!/bin/bash
files=`IFS=':';for i in $PATH; do test -d "$i" && find "$i" -maxdepth 1 -executable -type f; done`
total=0
for file in $files; do
symbols=`objdump -R $file 2>&1`
if [ $? -eq 0 ]; then
ncalls=`echo $symbols | grep -w $1 | wc -l`
((total=total+ncalls))
if [ $ncalls -gt 0 ]; then
echo "$file: $ncalls"
fi
fi
done
echo "TOTAL=$total"
$ ./count_bstring.sh bzero
TOTAL=0
Checked on x86_64-linux-gnu.
The new code unrolls the main loop slightly without adding too much
overhead and minimizes the comparisons for the search CHAR.
Geometric Mean of all benchmarks New / Old: 0.755
See email for all results.
Full xcheck passes on x86_64 with and without multiarch enabled.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
The new code unrolls the main loop slightly without adding too much
overhead and minimizes the comparisons for the search CHAR.
Geometric Mean of all benchmarks New / Old: 0.832
See email for all results.
Full xcheck passes on x86_64 with and without multiarch enabled.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
The new code unrolls the main loop slightly without adding too much
overhead and minimizes the comparisons for the search CHAR.
Geometric Mean of all benchmarks New / Old: 0.741
See email for all results.
Full xcheck passes on x86_64 with and without multiarch enabled.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
commit 8804157ad9
Author: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Fri Apr 15 12:27:59 2022 -0500
x86: Optimize memcmp SSE2 in memcmp.S
Only defined wmemcmp and missed __wmemcmp. This commit fixes that by
defining __wmemcmp and setting wmemcmp as a weak alias to __wmemcmp.
Both multiarch and disable-multiarch builds succeed and full xchecks
pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Code didn't actually use any sse4 instructions since `ptest` was
removed in:
commit 2f9062d717
Author: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Wed Nov 10 16:18:56 2021 -0600
x86: Shrink memcmp-sse4.S code size
The new memcmp-sse2 implementation is also faster.
geometric_mean(N=20) of page cross cases SSE2 / SSE4: 0.905
Note there are two regressions preferring SSE2 for Size = 1 and Size =
65.
Size = 1:
size, align0, align1, ret, New Time/Old Time
1, 1, 1, 0, 1.2
1, 1, 1, 1, 1.197
1, 1, 1, -1, 1.2
This is intentional. Size == 1 is significantly less hot based on
profiles of GCC11 and Python3 than sizes [4, 8] (which is made
hotter).
Python3 Size = 1 -> 13.64%
Python3 Size = [4, 8] -> 60.92%
GCC11 Size = 1 -> 1.29%
GCC11 Size = [4, 8] -> 33.86%
size, align0, align1, ret, New Time/Old Time
4, 4, 4, 0, 0.622
4, 4, 4, 1, 0.797
4, 4, 4, -1, 0.805
5, 5, 5, 0, 0.623
5, 5, 5, 1, 0.777
5, 5, 5, -1, 0.802
6, 6, 6, 0, 0.625
6, 6, 6, 1, 0.813
6, 6, 6, -1, 0.788
7, 7, 7, 0, 0.625
7, 7, 7, 1, 0.799
7, 7, 7, -1, 0.795
8, 8, 8, 0, 0.625
8, 8, 8, 1, 0.848
8, 8, 8, -1, 0.914
9, 9, 9, 0, 0.625
Size = 65:
size, align0, align1, ret, New Time/Old Time
65, 0, 0, 0, 1.103
65, 0, 0, 1, 1.216
65, 0, 0, -1, 1.227
65, 65, 0, 0, 1.091
65, 0, 65, 1, 1.19
65, 65, 65, -1, 1.215
This is because A) the checks in range [65, 96] are now unrolled 2x
and B) because smaller values <= 16 are now given a hotter path. By
contrast the SSE4 version has a branch for Size = 80. The unrolled
version has get better performance for returns which need both
comparisons.
size, align0, align1, ret, New Time/Old Time
128, 4, 8, 0, 0.858
128, 4, 8, 1, 0.879
128, 4, 8, -1, 0.888
As well, out of microbenchmark environments that are not full
predictable the branch will have a real-cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
New code save size (-303 bytes) and has significantly better
performance.
geometric_mean(N=20) of page cross cases New / Original: 0.634
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
The goal is to remove most SSSE3 function as SSE4, AVX2, and EVEX are
generally preferable. memcpy/memmove is one exception where avoiding
unaligned loads with `palignr` is important for some targets.
This commit replaces memmove-ssse3 with a better optimized are lower
code footprint verion. As well it aliases memcpy to memmove.
Aside from this function all other SSSE3 functions should be safe to
remove.
The performance is not changed drastically although shows overall
improvements without any major regressions or gains.
bench-memcpy geometric_mean(N=50) New / Original: 0.957
bench-memcpy-random geometric_mean(N=50) New / Original: 0.912
bench-memcpy-large geometric_mean(N=50) New / Original: 0.892
Benchmarks where run on Zhaoxin KX-6840@2000MHz See attached numbers
for all results.
More important this saves 7246 bytes of code size in memmove an
additional 10741 bytes by reusing memmove code for memcpy (total 17987
bytes saves). As well an additional 896 bytes of rodata for the jump
table entries.
With SSE2, SSE4.1, AVX2, and EVEX versions very few targets prefer
SSSE3. As a result it is no longer worth it to keep the SSSE3
versions given the code size cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
With SSE2, SSE4.1, AVX2, and EVEX versions very few targets prefer
SSSE3. As a result it is no longer worth it to keep the SSSE3
versions given the code size cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
With SSE2, SSE4.1, AVX2, and EVEX versions very few targets prefer
SSSE3. As a result it is no longer worth it to keep the SSSE3
versions given the code size cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
With SSE2, SSE4.1, AVX2, and EVEX versions very few targets prefer
SSSE3. As a result it is no longer worth it to keep the SSSE3
versions given the code size cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
With SSE2, SSE4.1, AVX2, and EVEX versions very few targets prefer
SSSE3. As a result it is no longer worth it to keep the SSSE3
versions given the code size cost.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Just a few small QOL changes.
1. Prefer `add` > `lea` as it has high execution units it can run
on.
2. Don't break macro-fusion between `test` and `jcc`
geometric_mean(N=20) of all benchmarks New / Original: 0.973
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
The rational is:
1. SSE42 has nearly identical logic so any benefit is minimal (3.4%
regression on Tigerlake using SSE42 versus AVX across the
benchtest suite).
2. AVX2 version covers the majority of targets that previously
prefered it.
3. The targets where AVX would still be best (SnB and IVB) are
becoming outdated.
All in all the saving the code size is worth it.
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Slightly faster method of doing TOLOWER that saves an
instruction.
Also replace the hard coded 5-byte no with .p2align 4. On builds with
CET enabled this misaligned entry to strcasecmp.
geometric_mean(N=40) of all benchmarks New / Original: .920
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Overflow case for __wcsncmp_avx2_rtm should be __wcscmp_avx2_rtm not
__wcscmp_avx2.
commit ddf0992cf5
Author: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Sun Jan 9 16:02:21 2022 -0600
x86: Fix __wcsncmp_avx2 in strcmp-avx2.S [BZ# 28755]
Set the wrong fallback function for `__wcsncmp_avx2_rtm`. It was set
to fallback on to `__wcscmp_avx2` instead of `__wcscmp_avx2_rtm` which
can cause spurious aborts.
This change will need to be backported.
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
The generic implementation is faster.
geometric_mean(N=20) of all benchmarks New / Original: .710
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
The generic implementation is faster.
geometric_mean(N=20) of all benchmarks New / Original: .678
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Use _mm_cmpeq_epi8 and _mm_movemask_epi8 to get strlen instead of
_mm_cmpistri. Also change offset to unsigned to avoid unnecessary
sign extensions.
geometric_mean(N=20) of all benchmarks that dont fallback on
sse2; New / Original: .901
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Use _mm_cmpeq_epi8 and _mm_movemask_epi8 to get strlen instead of
_mm_cmpistri. Also change offset to unsigned to avoid unnecessary
sign extensions.
geometric_mean(N=20) of all benchmarks that dont fallback on
sse2/strlen; New / Original: .928
All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Small code cleanup for size: -81 bytes.
Add comment justifying using a branch to do NULL/non-null return.
All string/memory tests pass and no regressions in benchtests.
geometric_mean(N=20) of all benchmarks New / Original: .985
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Small code cleanup for size: -53 bytes.
Add comment justifying using a branch to do NULL/non-null return.
All string/memory tests pass and no regressions in benchtests.
geometric_mean(N=20) of all benchmarks Original / New: 1.00
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
In the overflow fallback strncmp-avx2-rtm and wcsncmp-avx2-rtm would
call strcmp-avx2 and wcscmp-avx2 respectively. This would have
not checks around vzeroupper and would trigger spurious
aborts. This commit fixes that.
test-strcmp, test-strncmp, test-wcscmp, and test-wcsncmp all pass on
AVX2 machines with and without RTM.
Co-authored-by: H.J. Lu <hjl.tools@gmail.com>
Logic can read before the start of `s1` / `s2` if both `s1` and `s2`
are near the start of a page. To avoid having the result contimated by
these comparisons the `strcmp` variants would mask off these
comparisons. This was missing in the `strncmp` variants causing
the bug. This commit adds the masking to `strncmp` so that out of
range comparisons don't affect the result.
test-strcmp, test-strncmp, test-wcscmp, and test-wcsncmp all pass as
well a full xcheck on x86_64 linux.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
commit 3d9f171bfb
Author: H.J. Lu <hjl.tools@gmail.com>
Date: Mon Feb 7 05:55:15 2022 -0800
x86-64: Optimize bzero
added the optimized bzero. Remove bzero weak alias in SS2 memset to
avoid undefined __bzero in memset-sse2-unaligned-erms.
commit 3d9f171bfb
Author: H.J. Lu <hjl.tools@gmail.com>
Date: Mon Feb 7 05:55:15 2022 -0800
x86-64: Optimize bzero
Remove setting the .text section for the code. This commit
adds that back.
memset with zero as the value to set is by far the majority value (99%+
for Python3 and GCC).
bzero can be slightly more optimized for this case by using a zero-idiom
xor for broadcasting the set value to a register (vector or GPR).
Co-developed-by: Noah Goldstein <goldstein.w.n@gmail.com>
No bug.
Split vec generation into multiple steps. This allows the
broadcast in AVX2 to use 'xmm' registers for the L(less_vec)
case. This saves an expensive lane-cross instruction and removes
the need for 'vzeroupper'.
For SSE2 replace 2x 'punpck' instructions with zero-idiom 'pxor' for
byte broadcast.
Results for memset-avx2 small (geomean of N = 20 benchset runs).
size, New Time, Old Time, New / Old
0, 4.100, 3.831, 0.934
1, 5.074, 4.399, 0.867
2, 4.433, 4.411, 0.995
4, 4.487, 4.415, 0.984
8, 4.454, 4.396, 0.987
16, 4.502, 4.443, 0.987
All relevant string/wcsmbs tests are passing.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Optimization are primarily to the loop logic and how the page cross
logic interacts with the loop.
The page cross logic is at times more expensive for short strings near
the end of a page but not crossing the page. This is done to retest
the page cross conditions with a non-faulty check and to improve the
logic for entering the loop afterwards. This is only particular cases,
however, and is general made up for by more than 10x improvements on
the transition from the page cross -> loop case.
The non-page cross cases as well are nearly universally improved.
test-strcmp, test-strncmp, test-wcscmp, and test-wcsncmp all pass.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Optimization are primarily to the loop logic and how the page cross
logic interacts with the loop.
The page cross logic is at times more expensive for short strings near
the end of a page but not crossing the page. This is done to retest
the page cross conditions with a non-faulty check and to improve the
logic for entering the loop afterwards. This is only particular cases,
however, and is general made up for by more than 10x improvements on
the transition from the page cross -> loop case.
The non-page cross cases are improved most for smaller sizes [0, 128]
and go about even for (128, 4096]. The loop page cross logic is
improved so some more significant speedup is seen there as well.
test-strcmp, test-strncmp, test-wcscmp, and test-wcsncmp all pass.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Fixes [BZ# 28755] for wcsncmp by redirecting length >= 2^56 to
__wcscmp_evex. For x86_64 this covers the entire address range so any
length larger could not possibly be used to bound `s1` or `s2`.
test-strcmp, test-strncmp, test-wcscmp, and test-wcsncmp all pass.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Fixes [BZ# 28755] for wcsncmp by redirecting length >= 2^56 to
__wcscmp_avx2. For x86_64 this covers the entire address range so any
length larger could not possibly be used to bound `s1` or `s2`.
test-strcmp, test-strncmp, test-wcscmp, and test-wcsncmp all pass.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
I used these shell commands:
../glibc/scripts/update-copyrights $PWD/../gnulib/build-aux/update-copyright
(cd ../glibc && git commit -am"[this commit message]")
and then ignored the output, which consisted lines saying "FOO: warning:
copyright statement not found" for each of 7061 files FOO.
I then removed trailing white space from math/tgmath.h,
support/tst-support-open-dev-null-range.c, and
sysdeps/x86_64/multiarch/strlen-vec.S, to work around the following
obscure pre-commit check failure diagnostics from Savannah. I don't
know why I run into these diagnostics whereas others evidently do not.
remote: *** 912-#endif
remote: *** 913:
remote: *** 914-
remote: *** error: lines with trailing whitespace found
...
remote: *** error: sysdeps/unix/sysv/linux/statx_cp.c: trailing lines
No bug.
Optimizations are twofold.
1) Replace page cross and 0/1 checks with masked load instructions in
L(less_vec). In applications this reduces branch-misses in the
hot [0, 32] case.
2) Change controlflow so that L(less_vec) case gets the fall through.
Change 2) helps copies in the [0, 32] size range but comes at the cost
of copies in the [33, 64] size range. From profiles of GCC and
Python3, 94%+ and 99%+ of calls are in the [0, 32] range so this
appears to the the right tradeoff.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
No bug.
Optimizations are twofold.
1) Replace page cross and 0/1 checks with masked load instructions in
L(less_vec). In applications this reduces branch-misses in the
hot [0, 32] case.
2) Change controlflow so that L(less_vec) case gets the fall through.
Change 2) helps copies in the [0, 32] size range but comes at the cost
of copies in the [33, 64] size range. From profiles of GCC and
Python3, 94%+ and 99%+ of calls are in the [0, 32] range so this
appears to the the right tradeoff.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Must use notl %edi here as lower bits are for CHAR comparisons
potentially out of range thus can be 0 without indicating mismatch.
This fixes BZ #28646.
Co-Authored-By: H.J. Lu <hjl.tools@gmail.com>
No bug.
This implementation refactors memcmp-sse4.S primarily with minimizing
code size in mind. It does this by removing the lookup table logic and
removing the unrolled check from (256, 512] bytes.
memcmp-sse4 code size reduction : -3487 bytes
wmemcmp-sse4 code size reduction: -1472 bytes
The current memcmp-sse4.S implementation has a large code size
cost. This has serious adverse affects on the ICache / ITLB. While
in micro-benchmarks the implementations appears fast, traces of
real-world code have shown that the speed in micro benchmarks does not
translate when the ICache/ITLB are not primed, and that the cost
of the code size has measurable negative affects on overall
application performance.
See https://research.google/pubs/pub48320/ for more details.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
No bug.
The optimizations are as follows:
1) Always align entry to 64 bytes. This makes behavior more
predictable and makes other frontend optimizations easier.
2) Make the L(more_8x_vec) cases 4k aliasing aware. This can have
significant benefits in the case that:
0 < (dst - src) < [256, 512]
3) Align before `rep movsb`. For ERMS this is roughly a [0, 30%]
improvement and for FSRM [-10%, 25%].
In addition to these primary changes there is general cleanup
throughout to optimize the aligning routines and control flow logic.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Clang cannot assemble movzx in the AT&T dialect mode.
../sysdeps/x86_64/strcmp.S:2232:16: error: invalid operand for instruction
movzx (%rsi), %ecx
^~~~
Change movzx to movzbl, which follows the AT&T dialect and is used
elsewhere in the file.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Remove Prefer_AVX2_STRCMP to enable EVEX strcmp. When comparing 2 32-byte
strings, EVEX strcmp has been improved to require 1 load, 1 VPTESTM, 1
VPCMP, 1 KMOVD and 1 INCL instead of 2 loads, 3 VPCMPs, 2 KORDs, 1 KMOVD
and 1 TESTL while AVX2 strcmp requires 1 load, 2 VPCMPEQs, 1 VPMINU, 1
VPMOVMSKB and 1 TESTL. EVEX strcmp is now faster than AVX2 strcmp by up
to 40% on Tiger Lake and Ice Lake.
In strcmp-evex.S, to compare 2 32-byte strings, replace
VMOVU (%rdi, %rdx), %YMM0
VMOVU (%rsi, %rdx), %YMM1
/* Each bit in K0 represents a mismatch in YMM0 and YMM1. */
VPCMP $4, %YMM0, %YMM1, %k0
VPCMP $0, %YMMZERO, %YMM0, %k1
VPCMP $0, %YMMZERO, %YMM1, %k2
/* Each bit in K1 represents a NULL in YMM0 or YMM1. */
kord %k1, %k2, %k1
/* Each bit in K1 represents a NULL or a mismatch. */
kord %k0, %k1, %k1
kmovd %k1, %ecx
testl %ecx, %ecx
jne L(last_vector)
with
VMOVU (%rdi, %rdx), %YMM0
VPTESTM %YMM0, %YMM0, %k2
/* Each bit cleared in K1 represents a mismatch or a null CHAR
in YMM0 and 32 bytes at (%rsi, %rdx). */
VPCMP $0, (%rsi, %rdx), %YMM0, %k1{%k2}
kmovd %k1, %ecx
incl %ecx
jne L(last_vector)
It makes EVEX strcmp faster than AVX2 strcmp by up to 40% on Tiger Lake
and Ice Lake.
Co-Authored-By: Noah Goldstein <goldstein.w.n@gmail.com>
No bug. This commit adds new optimized __memcmpeq implementation for
evex.
The primary optimizations are:
1) skipping the logic to find the difference of the first mismatched
byte.
2) not updating src/dst addresses as the non-equals logic does not
need to be reused by different areas.
No bug. This commit adds new optimized __memcmpeq implementation for
avx2.
The primary optimizations are:
1) skipping the logic to find the difference of the first mismatched
byte.
2) not updating src/dst addresses as the non-equals logic does not
need to be reused by different areas.
No bug. This commit adds support for __memcmpeq to be implemented
seperately from memcmp. Support is added for versions optimized with
sse2, avx2, and evex.
No bug.
This commit adds support for __memcmpeq() as a new ABI for all
targets. In this commit __memcmpeq() is implemented only as an alias
to the corresponding targets memcmp() implementation. __memcmpeq() is
added as a new symbol starting with GLIBC_2.35 and defined in string.h
with comments explaining its behavior. Basic tests that it is callable
and works where added in string/tester.c
As discussed in the proposal "Add new ABI '__memcmpeq()' to libc"
__memcmpeq() is essentially a reserved namespace for bcmp(). The means
is shares the same specifications as memcmp() except the return value
for non-equal byte sequences is any non-zero value. This is less
strict than memcmp()'s return value specification and can be better
optimized when a boolean return is all that is needed.
__memcmpeq() is meant to only be called by compilers if they can prove
that the return value of a memcmp() call is only used for its boolean
value.
All tests in string/tester.c passed. As well build succeeds on
x86_64-linux-gnu target.
This commit replaces two usages of SSE2 'movups' with AVX 'vmovdqu'.
it could potentially be dangerous to use SSE2 if this function is ever
called without using 'vzeroupper' beforehand. While compilers appear
to use 'vzeroupper' before function calls if AVX2 has been used, using
SSE2 here is more brittle. Since it is not absolutely necessary it
should be avoided.
It costs 2-extra bytes but the extra bytes should only eat into
alignment padding.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
No bug.
Optimization are
1. change control flow for L(more_2x_vec) to fall through to loop and
jump for L(less_4x_vec) and L(less_8x_vec). This uses less code
size and saves jumps for length > 4x VEC_SIZE.
2. For EVEX/AVX512 move L(less_vec) closer to entry.
3. Avoid complex address mode for length > 2x VEC_SIZE
4. Slightly better aligning code for the loop from the perspective of
code size and uops.
5. Align targets so they make full use of their fetch block and if
possible cache line.
6. Try and reduce total number of icache lines that will need to be
pulled in for a given length.
7. Include "local" version of stosb target. For AVX2/EVEX/AVX512
jumping to the stosb target in the sse2 code section will almost
certainly be to a new page. The new version does increase code size
marginally by duplicating the target but should get better iTLB
behavior as a result.
test-memset, test-wmemset, and test-bzero are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
No bug.
The frontend optimizations are to:
1. Reorganize logically connected basic blocks so they are either in
the same cache line or adjacent cache lines.
2. Avoid cases when basic blocks unnecissarily cross cache lines.
3. Try and 32 byte align any basic blocks possible without sacrificing
code size. Smaller / Less hot basic blocks are used for this.
Overall code size shrunk by 168 bytes. This should make up for any
extra costs due to aligning to 64 bytes.
In general performance before deviated a great deal dependending on
whether entry alignment % 64 was 0, 16, 32, or 48. These changes
essentially make it so that the current implementation is at least
equal to the best alignment of the original for any arguments.
The only additional optimization is in the page cross case. Branch on
equals case was removed from the size == [4, 7] case. As well the [4,
7] and [2, 3] case where swapped as [4, 7] is likely a more hot
argument size.
test-memcmp and test-wmemcmp are both passing.
We stopped adding "Contributed by" or similar lines in sources in 2012
in favour of git logs and keeping the Contributors section of the
glibc manual up to date. Removing these lines makes the license
header a bit more consistent across files and also removes the
possibility of error in attribution when license blocks or files are
copied across since the contributed-by lines don't actually reflect
reality in those cases.
Move all "Contributed by" and similar lines (Written by, Test by,
etc.) into a new file CONTRIBUTED-BY to retain record of these
contributions. These contributors are also mentioned in
manual/contrib.texi, so we just maintain this additional record as a
courtesy to the earlier developers.
The following scripts were used to filter a list of files to edit in
place and to clean up the CONTRIBUTED-BY file respectively. These
were not added to the glibc sources because they're not expected to be
of any use in future given that this is a one time task:
https://gist.github.com/siddhesh/b5ecac94eabfd72ed2916d6d8157e7dchttps://gist.github.com/siddhesh/15ea1f5e435ace9774f485030695ee02
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
commit 3ec5d83d2a
Author: H.J. Lu <hjl.tools@gmail.com>
Date: Sat Jan 25 14:19:40 2020 -0800
x86-64: Avoid rep movsb with short distance [BZ #27130]
introduced some regressions on Intel processors without Fast Short REP
MOV (FSRM). Add Avoid_Short_Distance_REP_MOVSB to avoid rep movsb with
short distance only on Intel processors with FSRM. bench-memmove-large
on Skylake server shows that cycles of __memmove_evex_unaligned_erms
improves for the following data size:
before after Improvement
length=4127, align1=3, align2=0: 479.38 349.25 27%
length=4223, align1=9, align2=5: 405.62 333.25 18%
length=8223, align1=3, align2=0: 786.12 496.38 37%
length=8319, align1=9, align2=5: 727.50 501.38 31%
length=16415, align1=3, align2=0: 1436.88 840.00 41%
length=16511, align1=9, align2=5: 1375.50 836.38 39%
length=32799, align1=3, align2=0: 2890.00 1860.12 36%
length=32895, align1=9, align2=5: 2891.38 1931.88 33%
The following commit
commit 6f573a27b6
Author: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Wed Jun 23 01:19:34 2021 -0400
x86-64: Add wcslen optimize for sse4.1
Added wcsnlen-sse4.1 to the wcslen ifunc implementation list and did
not add wcslen-sse4.1 to wcslen ifunc implementation list. This commit
fixes that by removing wcsnlen-sse4.1 from the wcslen ifunc
implementation list and adding wcslen-sse4.1 to the ifunc
implementation list.
Testing:
test-wcslen.c, test-rsi-wcslen.c, and test-rsi-strlen.c are passing as
well as all other tests in wcsmbs and string.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
No bug. The way wcsnlen will check if near the end of maxlen
is the following macro:
mov %r11, %rsi; \
subq %rax, %rsi; \
andq $-64, %rax; \
testq $-64, %rsi; \
je L(strnlen_ret)
Which words independently of s + maxlen overflowing. So the
second overflow check is unnecissary for correctness and
just extra overhead in the common no overflow case.
test-strlen.c, test-wcslen.c, test-strnlen.c and test-wcsnlen.c are
all passing
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
This commit fixes the bug mentioned in the previous commit.
The previous implementations of wmemchr in these files relied
on maxlen * sizeof(wchar_t) which was not guranteed by the standard.
The new overflow tests added in the previous commit now
pass (As well as all the other tests).
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
This commit fixes the bug mentioned in the previous commit.
The previous implementations of wmemchr in these files relied
on n * sizeof(wchar_t) which was not guranteed by the standard.
The new overflow tests added in the previous commit now
pass (As well as all the other tests).
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
No bug. This comment adds the ifunc / build infrastructure
necessary for wcslen to prefer the sse4.1 implementation
in strlen-vec.S. test-wcslen.c is passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Since strlen.S contains SSE2 version of strlen/strnlen and SSE4.1
version of wcslen/wcsnlen, move strlen.S to multiarch/strlen-vec.S
and include multiarch/strlen-vec.S from SSE2 and SSE4.1 variants.
This also removes the unused symbols, __GI___strlen_sse2 and
__GI___wcsnlen_sse4_1.
No bug. This commit makes a few small improvements to
memset-vec-unaligned-erms.S. The changes are 1) only aligning to 64
instead of 128. Either alignment will perform equally well in a loop
and 128 just increases the odds of having to do an extra iteration
which can be significant overhead for small values. 2) Align some
targets and the loop. 3) Remove an ALU from the alignment process. 4)
Reorder the last 4x VEC so that they are stored after the loop. 5)
Move the condition for leq 8x VEC to before the alignment
process. test-memset and test-wmemset are both passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
No bug. This commit optimizes memcmp-evex.S. The optimizations include
adding a new vec compare path for small sizes, reorganizing the entry
control flow, removing some unnecissary ALU instructions from the main
loop, and most importantly replacing the heavy use of vpcmp + kand
logic with vpxor + vptern. test-memcmp and test-wmemcmp are both
passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
No bug. This commit optimizes memcmp-avx2.S. The optimizations include
adding a new vec compare path for small sizes, reorganizing the entry
control flow, and removing some unnecissary ALU instructions from the
main loop. test-memcmp and test-wmemcmp are both passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
No bug.
This commit adds a new implementation for EVEX memchr that is not safe
for RTM because it uses vzeroupper. The benefit is that by using
ymm0-ymm15 it can use vpcmpeq and vpternlogd in the 4x loop which is
faster than the RTM safe version which cannot use vpcmpeq because
there is no EVEX encoding for the instruction. All parts of the
implementation aside from the 4x loop are the same for the two
versions and the optimization is only relevant for large sizes.
Tigerlake:
size , algn , Pos , Cur T , New T , Win , Dif
512 , 6 , 192 , 9.2 , 9.04 , no-RTM , 0.16
512 , 7 , 224 , 9.19 , 8.98 , no-RTM , 0.21
2048 , 0 , 256 , 10.74 , 10.54 , no-RTM , 0.2
2048 , 0 , 512 , 14.81 , 14.87 , RTM , 0.06
2048 , 0 , 1024 , 22.97 , 22.57 , no-RTM , 0.4
2048 , 0 , 2048 , 37.49 , 34.51 , no-RTM , 2.98 <--
Icelake:
size , algn , Pos , Cur T , New T , Win , Dif
512 , 6 , 192 , 7.6 , 7.3 , no-RTM , 0.3
512 , 7 , 224 , 7.63 , 7.27 , no-RTM , 0.36
2048 , 0 , 256 , 8.48 , 8.38 , no-RTM , 0.1
2048 , 0 , 512 , 11.57 , 11.42 , no-RTM , 0.15
2048 , 0 , 1024 , 17.92 , 17.38 , no-RTM , 0.54
2048 , 0 , 2048 , 30.37 , 27.34 , no-RTM , 3.03 <--
test-memchr, test-wmemchr, and test-rawmemchr are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
An unknown vector operation occurred in commit 2a76821c30. Fixed it
by using "ymm{k1}{z}" but not "ymm {k1} {z}".
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
And replace the generic algorithm with the Brian Kernighan's one.
GCC optimize it with popcnt if the architecture supports, so there
is no need to add the extra POPCNT define to enable it.
This is really a micro-optimization that only adds complexity:
recent ABIs already support it (x86-64-v2 or power64le) and it
simplifies the code for internal usage, since i686 does not allow an
internal iFUNC call.
Checked on x86_64-linux-gnu, aarch64-linux-gnu, and
powerpc64le-linux-gnu.
No bug. This commit optimizes memchr-evex.S. The optimizations include
replacing some branches with cmovcc, avoiding some branches entirely
in the less_4x_vec case, making the page cross logic less strict,
saving some ALU in the alignment process, and most importantly
increasing ILP in the 4x loop. test-memchr, test-rawmemchr, and
test-wmemchr are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
No bug. This commit optimizes memchr-avx2.S. The optimizations include
replacing some branches with cmovcc, avoiding some branches entirely
in the less_4x_vec case, making the page cross logic less strict,
asaving a few instructions the in loop return loop. test-memchr,
test-rawmemchr, and test-wmemchr are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
No bug. This commit optimizes strchr-evex.S. The optimizations are
mostly small things such as save an ALU in the alignment process,
saving a few instructions in the loop return. The one significant
change is saving 2 instructions in the 4x loop. test-strchr,
test-strchrnul, test-wcschr, and test-wcschrnul are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
No bug. This commit optimizes strchr-avx2.S. The optimizations are all
small things such as save an ALU in the alignment process, saving a
few instructions in the loop return, saving some bytes in the main
loop, and increasing the ILP in the return cases. test-strchr,
test-strchrnul, test-wcschr, and test-wcschrnul are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
No bug. This commit optimizes strlen-avx2.S. The optimizations are
mostly small things but they add up to roughly 10-30% performance
improvement for strlen. The results for strnlen are bit more
ambiguous. test-strlen, test-strnlen, test-wcslen, and test-wcsnlen
are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
No bug. This commit optimizes strlen-evex.S. The
optimizations are mostly small things but they add up to roughly
10-30% performance improvement for strlen. The results for strnlen are
bit more ambiguous. test-strlen, test-strnlen, test-wcslen, and
test-wcsnlen are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
No bug. This commit adds optimized cased for less_vec memset case that
uses the avx512vl/avx512bw mask store avoiding the excessive
branches. test-memset and test-wmemset are passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Since strchr-avx2.S updated by
commit 1f745ecc21
Author: noah <goldstein.w.n@gmail.com>
Date: Wed Feb 3 00:38:59 2021 -0500
x86-64: Refactor and improve performance of strchr-avx2.S
uses sarx:
c4 e2 72 f7 c0 sarx %ecx,%eax,%eax
for strchr-avx2 family functions, require BMI2 in ifunc-impl-list.c and
ifunc-avx2.h.
Since __strlen_evex and __strnlen_evex added by
commit 1fd8c163a8
Author: H.J. Lu <hjl.tools@gmail.com>
Date: Fri Mar 5 06:24:52 2021 -0800
x86-64: Add ifunc-avx2.h functions with 256-bit EVEX
use sarx:
c4 e2 6a f7 c0 sarx %edx,%eax,%eax
require BMI2 for __strlen_evex and __strnlen_evex in ifunc-impl-list.c.
ifunc-avx2.h already requires BMI2 for EVEX implementation.
No Bug. This commit updates the large memcpy case (no overlap). The
update is to perform memcpy on either 2 or 4 contiguous pages at
once. This 1) helps to alleviate the affects of false memory aliasing
when destination and source have a close 4k alignment and 2) In most
cases and for most DRAM units is a modestly more efficient access
pattern. These changes are a clear performance improvement for
VEC_SIZE =16/32, though more ambiguous for VEC_SIZE=64. test-memcpy,
test-memccpy, test-mempcpy, test-memmove, and tst-memmove-overflow all
pass.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Update ifunc-memmove.h to select the function optimized with AVX512
instructions using ZMM16-ZMM31 registers to avoid RTM abort with usable
AVX512VL since VZEROUPPER isn't needed at function exit.
Update ifunc-memset.h/ifunc-wmemset.h to select the function optimized
with AVX512 instructions using ZMM16-ZMM31 registers to avoid RTM abort
with usable AVX512VL and AVX512BW since VZEROUPPER isn't needed at
function exit.
Since VZEROUPPER triggers RTM abort while VZEROALL won't, select AVX
optimized string/memory functions with
xtest
jz 1f
vzeroall
ret
1:
vzeroupper
ret
at function exit on processors with usable RTM, but without 256-bit EVEX
instructions to avoid VZEROUPPER inside a transactionally executing RTM
region.
Update ifunc-memcmp.h to select the function optimized with 256-bit EVEX
instructions using YMM16-YMM31 registers to avoid RTM abort with usable
AVX512VL, AVX512BW and MOVBE since VZEROUPPER isn't needed at function
exit.
Update ifunc-memset.h/ifunc-wmemset.h to select the function optimized
with 256-bit EVEX instructions using YMM16-YMM31 registers to avoid RTM
abort with usable AVX512VL and AVX512BW since VZEROUPPER isn't needed at
function exit.
Update ifunc-memmove.h to select the function optimized with 256-bit EVEX
instructions using YMM16-YMM31 registers to avoid RTM abort with usable
AVX512VL since VZEROUPPER isn't needed at function exit.
Update ifunc-strcpy.h to select the function optimized with 256-bit EVEX
instructions using YMM16-YMM31 registers to avoid RTM abort with usable
AVX512VL and AVX512BW since VZEROUPPER isn't needed at function exit.
Update ifunc-avx2.h, strchr.c, strcmp.c, strncmp.c and wcsnlen.c to
select the function optimized with 256-bit EVEX instructions using
YMM16-YMM31 registers to avoid RTM abort with usable AVX512VL, AVX512BW
and BMI2 since VZEROUPPER isn't needed at function exit.
For strcmp/strncmp, prefer AVX2 strcmp/strncmp if Prefer_AVX2_STRCMP
is set.
No bug. Just seemed the performance could be improved a bit. Observed
and expected behavior are unchanged. Optimized body of main
loop. Updated page cross logic and optimized accordingly. Made a few
minor instruction selection modifications. No regressions in test
suite. Both test-strchrnul and test-strchr passed.
In the process of optimizing memcpy for AMD machines, we have found the
vector move operations are outperforming enhanced REP MOVSB for data
transfers above the L2 cache size on Zen3 architectures.
To handle this use case, we are adding an upper bound parameter on
enhanced REP MOVSB:'__x86_rep_movsb_stop_threshold'.
As per large-bench results, we are configuring this parameter to the
L2 cache size for AMD machines and applicable from Zen3 architecture
supporting the ERMS feature.
For architectures other than AMD, it is the computed value of
non-temporal threshold parameter.
Reviewed-by: Premachandra Mallappa <premachandra.mallappa@amd.com>
When copying with "rep movsb", if the distance between source and
destination is N*4GB + [1..63] with N >= 0, performance may be very
slow. This patch updates memmove-vec-unaligned-erms.S for AVX and
AVX512 versions with the distance in RCX:
cmpl $63, %ecx
// Don't use "rep movsb" if ECX <= 63
jbe L(Don't use rep movsb")
Use "rep movsb"
Benchtests data with bench-memcpy, bench-memcpy-large, bench-memcpy-random
and bench-memcpy-walk on Skylake, Ice Lake and Tiger Lake show that its
performance impact is within noise range as "rep movsb" is only used for
data size >= 4KB.
I used these shell commands:
../glibc/scripts/update-copyrights $PWD/../gnulib/build-aux/update-copyright
(cd ../glibc && git commit -am"[this commit message]")
and then ignored the output, which consisted lines saying "FOO: warning:
copyright statement not found" for each of 6694 files FOO.
I then removed trailing white space from benchtests/bench-pthread-locks.c
and iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c, to work around this
diagnostic from Savannah:
remote: *** pre-commit check failed ...
remote: *** error: lines with trailing whitespace found
remote: error: hook declined to update refs/heads/master
Install <sys/platform/x86.h> so that programmers can do
#if __has_include(<sys/platform/x86.h>)
#include <sys/platform/x86.h>
#endif
...
if (CPU_FEATURE_USABLE (SSE2))
...
if (CPU_FEATURE_USABLE (AVX2))
...
<sys/platform/x86.h> exports only:
enum
{
COMMON_CPUID_INDEX_1 = 0,
COMMON_CPUID_INDEX_7,
COMMON_CPUID_INDEX_80000001,
COMMON_CPUID_INDEX_D_ECX_1,
COMMON_CPUID_INDEX_80000007,
COMMON_CPUID_INDEX_80000008,
COMMON_CPUID_INDEX_7_ECX_1,
/* Keep the following line at the end. */
COMMON_CPUID_INDEX_MAX
};
struct cpuid_features
{
struct cpuid_registers cpuid;
struct cpuid_registers usable;
};
struct cpu_features
{
struct cpu_features_basic basic;
struct cpuid_features features[COMMON_CPUID_INDEX_MAX];
};
/* Get a pointer to the CPU features structure. */
extern const struct cpu_features *__x86_get_cpu_features
(unsigned int max) __attribute__ ((const));
Since all feature checks are done through macros, programs compiled with
a newer <sys/platform/x86.h> are compatible with the older glibc binaries
as long as the layout of struct cpu_features is identical. The features
array can be expanded with backward binary compatibility for both .o and
.so files. When COMMON_CPUID_INDEX_MAX is increased to support new
processor features, __x86_get_cpu_features in the older glibc binaries
returns NULL and HAS_CPU_FEATURE/CPU_FEATURE_USABLE return false on the
new processor feature. No new symbol version is neeeded.
Both CPU_FEATURE_USABLE and HAS_CPU_FEATURE are provided. HAS_CPU_FEATURE
can be used to identify processor features.
Note: Although GCC has __builtin_cpu_supports, it only supports a subset
of <sys/platform/x86.h> and it is equivalent to CPU_FEATURE_USABLE. It
doesn't support HAS_CPU_FEATURE.
Support usable check for all CPU features with the following changes:
1. Change struct cpu_features to
struct cpuid_features
{
struct cpuid_registers cpuid;
struct cpuid_registers usable;
};
struct cpu_features
{
struct cpu_features_basic basic;
struct cpuid_features features[COMMON_CPUID_INDEX_MAX];
unsigned int preferred[PREFERRED_FEATURE_INDEX_MAX];
...
};
so that there is a usable bit for each cpuid bit.
2. After the cpuid bits have been initialized, copy the known bits to the
usable bits. EAX/EBX from INDEX_1 and EAX from INDEX_7 aren't used for
CPU feature detection.
3. Clear the usable bits which require OS support.
4. If the feature is supported by OS, copy its cpuid bit to its usable
bit.
5. Replace HAS_CPU_FEATURE and CPU_FEATURES_CPU_P with CPU_FEATURE_USABLE
and CPU_FEATURE_USABLE_P to check if a feature is usable.
6. Add DEPR_FPU_CS_DS for INDEX_7_EBX_13.
7. Unset MPX feature since it has been deprecated.
The results are
1. If the feature is known and doesn't requre OS support, its usable bit
is copied from the cpuid bit.
2. Otherwise, its usable bit is copied from the cpuid bit only if the
feature is known to supported by OS.
3. CPU_FEATURE_USABLE/CPU_FEATURE_USABLE_P are used to check if the
feature can be used.
4. HAS_CPU_FEATURE/CPU_FEATURE_CPU_P are used to check if CPU supports
the feature.
Add x86_rep_movsb_threshold and x86_rep_stosb_threshold to tunables
to update thresholds for "rep movsb" and "rep stosb" at run-time.
Note that the user specified threshold for "rep movsb" smaller than
the minimum threshold will be ignored.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
strcmp-avx2.S: In avx2 strncmp function, strings are compared in
chunks of 4 vector size(i.e. 32x4=128 byte for avx2). After first 4
vector size comparison, code must check whether it already passed
the given offset. This patch implement avx2 offset check condition
for strncmp function, if both string compare same for first 4 vector
size.
Since __x86_shared_non_temporal_threshold is defined as
long int __x86_shared_non_temporal_threshold;
and long int is 4 bytes for x32, use RDX_LP to compare against
__x86_shared_non_temporal_threshold in assembly code.
This patch rewrites wcscat using wcslen and wcscpy. This is similar to
the optimization done on strcat by 6e46de42fe.
The strcpy changes are mainly to add the internal alias to avoid PLT
calls.
Checked on x86_64-linux-gnu and a build against the affected
architectures.
* include/wchar.h (__wcscpy): New prototype.
* sysdeps/powerpc/powerpc32/power4/multiarch/wcscpy-ppc32.c
(__wcscpy): Route internal symbol to generic implementation.
* sysdeps/powerpc/powerpc32/power4/multiarch/wcscpy.c (wcscpy):
Add internal __wcscpy alias.
* sysdeps/powerpc/powerpc64/multiarch/wcscpy.c (wcscpy): Likewise.
* sysdeps/s390/wcscpy.c (wcscpy): Likewise.
* sysdeps/x86_64/multiarch/wcscpy.c (wcscpy): Likewise.
* wcsmbs/wcscpy.c (wcscpy): Add
* sysdeps/x86_64/multiarch/wcscpy-c.c (WCSCPY): Adjust macro to
use generic implementation.
* wcsmbs/wcscat.c (wcscat): Rewrite using wcslen and wcscpy.
This fixes the same bug in fnmatch that was fixed by commit 7e2f0d2d77 for
regexp matching. As a side effect it also removes the use of an unbound
VLA.
On x32, the size_t parameter may be passed in the lower 32 bits of a
64-bit register with the non-zero upper 32 bits. The string/memory
functions written in assembly can only use the lower 32 bits of a
64-bit register as length or must clear the upper 32 bits before using
the full 64-bit register for length.
This pach fixes strnlen/wcsnlen for x32. Tested on x86-64 and x32. On
x86-64, libc.so is the same with and withou the fix.
[BZ# 24097]
CVE-2019-6488
* sysdeps/x86_64/multiarch/strlen-avx2.S: Use RSI_LP for length.
Clear the upper 32 bits of RSI register.
* sysdeps/x86_64/strlen.S: Use RSI_LP for length.
* sysdeps/x86_64/x32/Makefile (tests): Add tst-size_t-strnlen
and tst-size_t-wcsnlen.
* sysdeps/x86_64/x32/tst-size_t-strnlen.c: New file.
* sysdeps/x86_64/x32/tst-size_t-wcsnlen.c: Likewise.
On x32, the size_t parameter may be passed in the lower 32 bits of a
64-bit register with the non-zero upper 32 bits. The string/memory
functions written in assembly can only use the lower 32 bits of a
64-bit register as length or must clear the upper 32 bits before using
the full 64-bit register for length.
This pach fixes strncpy for x32. Tested on x86-64 and x32. On x86-64,
libc.so is the same with and withou the fix.
[BZ# 24097]
CVE-2019-6488
* sysdeps/x86_64/multiarch/strcpy-avx2.S: Use RDX_LP for length.
* sysdeps/x86_64/multiarch/strcpy-sse2-unaligned.S: Likewise.
* sysdeps/x86_64/multiarch/strcpy-ssse3.S: Likewise.
* sysdeps/x86_64/x32/Makefile (tests): Add tst-size_t-strncpy.
* sysdeps/x86_64/x32/tst-size_t-strncpy.c: New file.
On x32, the size_t parameter may be passed in the lower 32 bits of a
64-bit register with the non-zero upper 32 bits. The string/memory
functions written in assembly can only use the lower 32 bits of a
64-bit register as length or must clear the upper 32 bits before using
the full 64-bit register for length.
This pach fixes the strncmp family for x32. Tested on x86-64 and x32.
On x86-64, libc.so is the same with and withou the fix.
[BZ# 24097]
CVE-2019-6488
* sysdeps/x86_64/multiarch/strcmp-avx2.S: Use RDX_LP for length.
* sysdeps/x86_64/multiarch/strcmp-sse42.S: Likewise.
* sysdeps/x86_64/strcmp.S: Likewise.
* sysdeps/x86_64/x32/Makefile (tests): Add tst-size_t-strncasecmp,
tst-size_t-strncmp and tst-size_t-wcsncmp.
* sysdeps/x86_64/x32/tst-size_t-strncasecmp.c: New file.
* sysdeps/x86_64/x32/tst-size_t-strncmp.c: Likewise.
* sysdeps/x86_64/x32/tst-size_t-wcsncmp.c: Likewise.
On x32, the size_t parameter may be passed in the lower 32 bits of a
64-bit register with the non-zero upper 32 bits. The string/memory
functions written in assembly can only use the lower 32 bits of a
64-bit register as length or must clear the upper 32 bits before using
the full 64-bit register for length.
This pach fixes memset/wmemset for x32. Tested on x86-64 and x32. On
x86-64, libc.so is the same with and withou the fix.
[BZ# 24097]
CVE-2019-6488
* sysdeps/x86_64/multiarch/memset-avx512-no-vzeroupper.S: Use
RDX_LP for length. Clear the upper 32 bits of RDX register.
* sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S: Likewise.
* sysdeps/x86_64/x32/Makefile (tests): Add tst-size_t-wmemset.
* sysdeps/x86_64/x32/tst-size_t-memset.c: New file.
* sysdeps/x86_64/x32/tst-size_t-wmemset.c: Likewise.
On x32, the size_t parameter may be passed in the lower 32 bits of a
64-bit register with the non-zero upper 32 bits. The string/memory
functions written in assembly can only use the lower 32 bits of a
64-bit register as length or must clear the upper 32 bits before using
the full 64-bit register for length.
This pach fixes memrchr for x32. Tested on x86-64 and x32. On x86-64,
libc.so is the same with and withou the fix.
[BZ# 24097]
CVE-2019-6488
* sysdeps/x86_64/memrchr.S: Use RDX_LP for length.
* sysdeps/x86_64/multiarch/memrchr-avx2.S: Likewise.
* sysdeps/x86_64/x32/Makefile (tests): Add tst-size_t-memrchr.
* sysdeps/x86_64/x32/tst-size_t-memrchr.c: New file.
On x32, the size_t parameter may be passed in the lower 32 bits of a
64-bit register with the non-zero upper 32 bits. The string/memory
functions written in assembly can only use the lower 32 bits of a
64-bit register as length or must clear the upper 32 bits before using
the full 64-bit register for length.
This pach fixes memcpy for x32. Tested on x86-64 and x32. On x86-64,
libc.so is the same with and withou the fix.
[BZ# 24097]
CVE-2019-6488
* sysdeps/x86_64/multiarch/memcpy-ssse3-back.S: Use RDX_LP for
length. Clear the upper 32 bits of RDX register.
* sysdeps/x86_64/multiarch/memcpy-ssse3.S: Likewise.
* sysdeps/x86_64/multiarch/memmove-avx512-no-vzeroupper.S:
Likewise.
* sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:
Likewise.
* sysdeps/x86_64/x32/Makefile (tests): Add tst-size_t-memcpy.
tst-size_t-wmemchr.
* sysdeps/x86_64/x32/tst-size_t-memcpy.c: New file.
On x32, the size_t parameter may be passed in the lower 32 bits of a
64-bit register with the non-zero upper 32 bits. The string/memory
functions written in assembly can only use the lower 32 bits of a
64-bit register as length or must clear the upper 32 bits before using
the full 64-bit register for length.
This pach fixes memcmp/wmemcmp for x32. Tested on x86-64 and x32. On
x86-64, libc.so is the same with and withou the fix.
[BZ# 24097]
CVE-2019-6488
* sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S: Use RDX_LP for
length. Clear the upper 32 bits of RDX register.
* sysdeps/x86_64/multiarch/memcmp-sse4.S: Likewise.
* sysdeps/x86_64/multiarch/memcmp-ssse3.S: Likewise.
* sysdeps/x86_64/x32/Makefile (tests): Add tst-size_t-memcmp and
tst-size_t-wmemcmp.
* sysdeps/x86_64/x32/tst-size_t-memcmp.c: New file.
* sysdeps/x86_64/x32/tst-size_t-wmemcmp.c: Likewise.
On x32, the size_t parameter may be passed in the lower 32 bits of a
64-bit register with the non-zero upper 32 bits. The string/memory
functions written in assembly can only use the lower 32 bits of a
64-bit register as length or must clear the upper 32 bits before using
the full 64-bit register for length.
This pach fixes memchr/wmemchr for x32. Tested on x86-64 and x32. On
x86-64, libc.so is the same with and withou the fix.
[BZ# 24097]
CVE-2019-6488
* sysdeps/x86_64/memchr.S: Use RDX_LP for length. Clear the
upper 32 bits of RDX register.
* sysdeps/x86_64/multiarch/memchr-avx2.S: Likewise.
* sysdeps/x86_64/x32/Makefile (tests): Add tst-size_t-memchr and
tst-size_t-wmemchr.
* sysdeps/x86_64/x32/test-size_t.h: New file.
* sysdeps/x86_64/x32/tst-size_t-memchr.c: Likewise.
* sysdeps/x86_64/x32/tst-size_t-wmemchr.c: Likewise.
Optimize x86-64 strcat/strncat, strcpy/strncpy and stpcpy/stpncpy with AVX2.
It uses vector comparison as much as possible. In general, the larger the
source string, the greater performance gain observed, reaching speedups of
1.6x compared to SSE2 unaligned routines. Select AVX2 strcat/strncat,
strcpy/strncpy and stpcpy/stpncpy on AVX2 machines where vzeroupper is
preferred and AVX unaligned load is fast.
* sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Add
strcat-avx2, strncat-avx2, strcpy-avx2, strncpy-avx2,
stpcpy-avx2 and stpncpy-avx2.
* sysdeps/x86_64/multiarch/ifunc-impl-list.c:
(__libc_ifunc_impl_list): Add tests for __strcat_avx2,
__strncat_avx2, __strcpy_avx2, __strncpy_avx2, __stpcpy_avx2
and __stpncpy_avx2.
* sysdeps/x86_64/multiarch/{ifunc-unaligned-ssse3.h =>
ifunc-strcpy.h}: rename header for a more generic name.
* sysdeps/x86_64/multiarch/ifunc-strcpy.h:
(IFUNC_SELECTOR): Return OPTIMIZE (avx2) on AVX 2 machines if
AVX unaligned load is fast and vzeroupper is preferred.
* sysdeps/x86_64/multiarch/stpcpy-avx2.S: New file
* sysdeps/x86_64/multiarch/stpncpy-avx2.S: Likewise
* sysdeps/x86_64/multiarch/strcat-avx2.S: Likewise
* sysdeps/x86_64/multiarch/strcpy-avx2.S: Likewise
* sysdeps/x86_64/multiarch/strncat-avx2.S: Likewise
* sysdeps/x86_64/multiarch/strncpy-avx2.S: Likewise
Extend CPUID support for all feature bits from CPUID. Add a new macro,
CPU_FEATURE_USABLE, which can be used to check if a feature is usable at
run-time, instead of HAS_CPU_FEATURE and HAS_ARCH_FEATURE.
Add COMMON_CPUID_INDEX_D_ECX_1, COMMON_CPUID_INDEX_80000007 and
COMMON_CPUID_INDEX_80000008 to check CPU feature bits in them.
Tested on i686 and x86-64 as well as using build-many-glibcs.py with
x86 targets.
* sysdeps/x86/cacheinfo.c (intel_check_word): Updated for
cpu_features_basic.
(__cache_sysconf): Likewise.
(init_cacheinfo): Likewise.
* sysdeps/x86/cpu-features.c (get_extended_indeces): Also
populate COMMON_CPUID_INDEX_80000007 and
COMMON_CPUID_INDEX_80000008.
(get_common_indices): Also populate COMMON_CPUID_INDEX_D_ECX_1.
Use CPU_FEATURES_CPU_P (cpu_features, XSAVEC) to check if
XSAVEC is available. Set the bit_arch_XXX_Usable bits.
(init_cpu_features): Use _Static_assert on
index_arch_Fast_Unaligned_Load.
__get_cpuid_registers and __get_arch_feature. Updated for
cpu_features_basic. Set stepping in cpu_features.
* sysdeps/x86/cpu-features.h: (FEATURE_INDEX_1): Changed to enum.
(FEATURE_INDEX_2): New.
(FEATURE_INDEX_MAX): Changed to enum.
(COMMON_CPUID_INDEX_D_ECX_1): New.
(COMMON_CPUID_INDEX_80000007): Likewise.
(COMMON_CPUID_INDEX_80000008): Likewise.
(cpuid_registers): Likewise.
(cpu_features_basic): Likewise.
(CPU_FEATURE_USABLE): Likewise.
(bit_arch_XXX_Usable): Likewise.
(cpu_features): Use cpuid_registers and cpu_features_basic.
(bit_arch_XXX): Reweritten.
(bit_cpu_XXX): Likewise.
(index_cpu_XXX): Likewise.
(reg_XXX): Likewise.
* sysdeps/x86/tst-get-cpu-features.c: Include <stdio.h> and
<support/check.h>.
(CHECK_CPU_FEATURE): New.
(CHECK_CPU_FEATURE_USABLE): Likewise.
(cpu_kinds): Likewise.
(do_test): Print vendor, family, model and stepping. Check
HAS_CPU_FEATURE and CPU_FEATURE_USABLE.
(TEST_FUNCTION): Removed.
Include <support/test-driver.c> instead of
"../../test-skeleton.c".
* sysdeps/x86_64/multiarch/sched_cpucount.c (__sched_cpucount):
Check POPCNT instead of POPCOUNT.
* sysdeps/x86_64/multiarch/test-multiarch.c (do_test): Likewise.
GCC 9 has gained an enhancement to help detect attribute mismatches
between alias declarations and their targets. It consists of a new
warning, -Wattribute-alias, an enhancement to an existing warning,
-Wmissing-attributes, and a new attribute called copy.
The purpose of the warnings is to help identify either possible bugs
(an alias declared with more restrictive attributes than its target
promises) or optimization or diagnostic opportunities (an alias target
missing some attributes that it could be declared with that might
benefit analysis and code generation). The purpose of the new
attribute is to easily apply (almost) the same set of attributes
to one declaration as those already present on another.
As expected (and intended) the enhancement triggers warnings for
many alias declarations in Glibc code. This change, tested on
x86_64-linux, avoids all instances of the new warnings by making
use of the attribute where appropriate. To fully benefit from
the enhancement Glibc will need to be compiled with
-Wattribute-alias=2 and remaining warnings reviewed and dealt with
(there are a couple of thousand but most should be straightforward
to deal with).
ChangeLog:
* include/libc-symbols.h (__attribute_copy__): Define macro unless
it's already defined.
(_strong_alias): Use __attribute_copy__.
(_weak_alias, __hidden_ver1, __hidden_nolink2): Same.
* misc/sys/cdefs.h (__attribute_copy__): New macro.
* sysdeps/x86_64/multiarch/memchr.c (memchr): Use __attribute_copy__.
* sysdeps/x86_64/multiarch/memcmp.c (memcmp): Same.
* sysdeps/x86_64/multiarch/mempcpy.c (mempcpy): Same.
* sysdeps/x86_64/multiarch/memset.c (memset): Same.
* sysdeps/x86_64/multiarch/stpcpy.c (stpcpy): Same.
* sysdeps/x86_64/multiarch/strcat.c (strcat): Same.
* sysdeps/x86_64/multiarch/strchr.c (strchr): Same.
* sysdeps/x86_64/multiarch/strcmp.c (strcmp): Same.
* sysdeps/x86_64/multiarch/strcpy.c (strcpy): Same.
* sysdeps/x86_64/multiarch/strcspn.c (strcspn): Same.
* sysdeps/x86_64/multiarch/strlen.c (strlen): Same.
* sysdeps/x86_64/multiarch/strncmp.c (strncmp): Same.
* sysdeps/x86_64/multiarch/strncpy.c (strncpy): Same.
* sysdeps/x86_64/multiarch/strnlen.c (strnlen): Same.
* sysdeps/x86_64/multiarch/strpbrk.c (strpbrk): Same.
* sysdeps/x86_64/multiarch/strrchr.c (strrchr): Same.
* sysdeps/x86_64/multiarch/strspn.c (strspn): Same.
There is no need to include <init-arch.h> in assembly codes since all
x86 IFUNC selector functions are written in C. Tested on i686 and
x86-64. There is no code change in libc.so, ld.so and libmvec.so.
* sysdeps/i386/i686/multiarch/bzero-ia32.S: Don't include
<init-arch.h>.
* sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core-avx2.S: Likewise.
* sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core-avx2.S: Likewise.
* sysdeps/x86_64/multiarch/memset-sse2-unaligned-erms.S: Likewise.
