24905a4bd1
Emulated gather/scatter behave similar to strided elementwise
accesses in that they need to decompose the offset vector
and construct or decompose the data vector so handle them
the same way, pessimizing the cases with may elements.
For pr88531-2c.c instead of
.L4:
leaq (%r15,%rcx), %rdx
incl %edi
movl 16(%rdx), %r13d
movl 24(%rdx), %r14d
movl (%rdx), %r10d
movl 4(%rdx), %r9d
movl 8(%rdx), %ebx
movl 12(%rdx), %r11d
movl 20(%rdx), %r12d
vmovss (%rax,%r14,4), %xmm2
movl 28(%rdx), %edx
vmovss (%rax,%r13,4), %xmm1
vmovss (%rax,%r10,4), %xmm0
vinsertps $0x10, (%rax,%rdx,4), %xmm2, %xmm2
vinsertps $0x10, (%rax,%r12,4), %xmm1, %xmm1
vinsertps $0x10, (%rax,%r9,4), %xmm0, %xmm0
vmovlhps %xmm2, %xmm1, %xmm1
vmovss (%rax,%rbx,4), %xmm2
vinsertps $0x10, (%rax,%r11,4), %xmm2, %xmm2
vmovlhps %xmm2, %xmm0, %xmm0
vinsertf128 $0x1, %xmm1, %ymm0, %ymm0
vmulps %ymm3, %ymm0, %ymm0
vmovups %ymm0, (%r8,%rcx)
addq $32, %rcx
cmpl %esi, %edi
jb .L4
we now prefer
.L4:
leaq 0(%rbp,%rdx,8), %rcx
movl (%rcx), %r10d
movl 4(%rcx), %ecx
vmovss (%rsi,%r10,4), %xmm0
vinsertps $0x10, (%rsi,%rcx,4), %xmm0, %xmm0
vmulps %xmm1, %xmm0, %xmm0
vmovlps %xmm0, (%rbx,%rdx,8)
incq %rdx
cmpl %edi, %edx
jb .L4
* config/i386/i386.cc (ix86_vector_costs::add_stmt_cost):
Tame down element extracts and scalar loads for gather/scatter
similar to elementwise strided accesses.
* gcc.target/i386/pr89618-2.c: New testcase.
* gcc.target/i386/pr88531-2b.c: Adjust.
* gcc.target/i386/pr88531-2c.c: Likewise.
|
||
|---|---|---|
| c++tools | ||
| config | ||
| contrib | ||
| fixincludes | ||
| gcc | ||
| gnattools | ||
| gotools | ||
| include | ||
| INSTALL | ||
| intl | ||
| libada | ||
| libatomic | ||
| libbacktrace | ||
| libcc1 | ||
| libcody | ||
| libcpp | ||
| libdecnumber | ||
| libffi | ||
| libgcc | ||
| libgfortran | ||
| libgm2 | ||
| libgo | ||
| libgomp | ||
| libiberty | ||
| libitm | ||
| libobjc | ||
| libphobos | ||
| libquadmath | ||
| libsanitizer | ||
| libssp | ||
| libstdc++-v3 | ||
| libvtv | ||
| lto-plugin | ||
| maintainer-scripts | ||
| zlib | ||
| .dir-locals.el | ||
| .gitattributes | ||
| .gitignore | ||
| ABOUT-NLS | ||
| ar-lib | ||
| ChangeLog | ||
| ChangeLog.jit | ||
| ChangeLog.tree-ssa | ||
| compile | ||
| config-ml.in | ||
| config.guess | ||
| config.rpath | ||
| config.sub | ||
| configure | ||
| configure.ac | ||
| COPYING | ||
| COPYING.LIB | ||
| COPYING.RUNTIME | ||
| COPYING3 | ||
| COPYING3.LIB | ||
| depcomp | ||
| install-sh | ||
| libtool-ldflags | ||
| libtool.m4 | ||
| ltgcc.m4 | ||
| ltmain.sh | ||
| ltoptions.m4 | ||
| ltsugar.m4 | ||
| ltversion.m4 | ||
| lt~obsolete.m4 | ||
| MAINTAINERS | ||
| Makefile.def | ||
| Makefile.in | ||
| Makefile.tpl | ||
| missing | ||
| mkdep | ||
| mkinstalldirs | ||
| move-if-change | ||
| multilib.am | ||
| README | ||
| symlink-tree | ||
| test-driver | ||
| ylwrap | ||
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.