mirror of git://gcc.gnu.org/git/gcc.git
25c8a8d431
SVE2 adds [US]ADDW[TB] which we can use when we have to do a single step
widening addition. This is useful for instance when the value to be widened
does not come from a load. For example for
int foo2_int(unsigned short *x, unsigned short * restrict y) {
int sum = 0;
for (int i = 0; i < 8000; i++)
{
x[i] = x[i] + y[i];
sum += x[i];
}
return sum;
}
we used to generate
.L6:
ld1h z1.h, p7/z, [x0, x2, lsl 1]
ld1h z29.h, p7/z, [x1, x2, lsl 1]
add z29.h, z29.h, z1.h
punpklo p6.h, p7.b
uunpklo z0.s, z29.h
add z31.s, p6/m, z31.s, z0.s
punpkhi p6.h, p7.b
uunpkhi z30.s, z29.h
add z31.s, p6/m, z31.s, z30.s
st1h z29.h, p7, [x0, x2, lsl 1]
add x2, x2, x4
whilelo p7.h, w2, w3
b.any .L6
ptrue p7.b, all
uaddv d31, p7, z31.s
but with +sve2
.L12:
ld1h z30.h, p7/z, [x0, x2, lsl 1]
ld1h z29.h, p7/z, [x1, x2, lsl 1]
add z30.h, z30.h, z29.h
uaddwb z31.s, z31.s, z30.h
uaddwt z31.s, z31.s, z30.h
st1h z30.h, p7, [x0, x2, lsl 1]
mov x3, x2
inch x2
cmp w2, w4
bls .L12
inch x3
uaddv d31, p7, z31.s
gcc/ChangeLog:
PR middle-end/122069
* config/aarch64/aarch64-sve2.md: (widen_ssum<mode><Vnarrow>3): New.
(widen_usum<mode><Vnarrow>3): New.
* config/aarch64/iterators.md (Vnarrow): New, to match VNARROW.
gcc/testsuite/ChangeLog:
PR middle-end/122069
* gcc.target/aarch64/sve2/pr122069_1.c: New test.
* gcc.target/aarch64/sve2/pr122069_2.c: New test.
|
||
|---|---|---|
| .forgejo | ||
| .github | ||
| INSTALL | ||
| c++tools | ||
| config | ||
| contrib | ||
| fixincludes | ||
| gcc | ||
| gnattools | ||
| gotools | ||
| include | ||
| libada | ||
| libatomic | ||
| libbacktrace | ||
| libcc1 | ||
| libcody | ||
| libcpp | ||
| libdecnumber | ||
| libffi | ||
| libgcc | ||
| libgcobol | ||
| libgfortran | ||
| libgm2 | ||
| libgo | ||
| libgomp | ||
| libgrust | ||
| libiberty | ||
| libitm | ||
| libobjc | ||
| libphobos | ||
| libquadmath | ||
| libsanitizer | ||
| libssp | ||
| libstdc++-v3 | ||
| libvtv | ||
| lto-plugin | ||
| maintainer-scripts | ||
| zlib | ||
| .b4-config | ||
| .dir-locals.el | ||
| .editorconfig | ||
| .gitattributes | ||
| .gitignore | ||
| ABOUT-NLS | ||
| COPYING | ||
| COPYING.LIB | ||
| COPYING.RUNTIME | ||
| COPYING3 | ||
| COPYING3.LIB | ||
| ChangeLog | ||
| ChangeLog.jit | ||
| ChangeLog.tree-ssa | ||
| MAINTAINERS | ||
| Makefile.def | ||
| Makefile.in | ||
| Makefile.tpl | ||
| README | ||
| SECURITY.txt | ||
| ar-lib | ||
| compile | ||
| config-ml.in | ||
| config.guess | ||
| config.rpath | ||
| config.sub | ||
| configure | ||
| configure.ac | ||
| depcomp | ||
| install-sh | ||
| libtool-ldflags | ||
| libtool.m4 | ||
| ltgcc.m4 | ||
| ltmain.sh | ||
| ltoptions.m4 | ||
| ltsugar.m4 | ||
| ltversion.m4 | ||
| lt~obsolete.m4 | ||
| missing | ||
| mkdep | ||
| mkinstalldirs | ||
| move-if-change | ||
| multilib.am | ||
| symlink-tree | ||
| test-driver | ||
| ylwrap | ||
README
This directory contains the GNU Compiler Collection (GCC). The GNU Compiler Collection is free software. See the files whose names start with COPYING for copying permission. The manuals, and some of the runtime libraries, are under different terms; see the individual source files for details. The directory INSTALL contains copies of the installation information as HTML and plain text. The source of this information is gcc/doc/install.texi. The installation information includes details of what is included in the GCC sources and what files GCC installs. See the file gcc/doc/gcc.texi (together with other files that it includes) for usage and porting information. An online readable version of the manual is in the files gcc/doc/gcc.info*. See http://gcc.gnu.org/bugs/ for how to report bugs usefully. Copyright years on GCC source files may be listed using range notation, e.g., 1987-2012, indicating that every year in the range, inclusive, is a copyrightable year that could otherwise be listed individually.