mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-27 11:29:36 +03:00
62a65a654e
This re-use the framework established for SSE2, SSSE3 and AVX2. However, GCC is using FP registers on Aarch64, so unlike SSE/AVX2 we can't rely on the registers being left alone between ASM statements. So instead, the NEON code uses C variables and GCC extended ASM syntax. Note that since the kernel explicitly disable vector registers, they have to be locally re-enabled explicitly. As we use the variable's number to define the symbolic name, and GCC won't allow duplicate symbolic names, numbers have to be unique. Even when the code is not going to be used (e.g. the case for 4 registers when using the macro with only 2). Only the actually used variables should be declared, otherwise the build will fails in debug mode. This requires the replacement of the XOR(X,X) syntax by a new ZERO(X) macro, which does the same thing but without repeating the argument. And perhaps someday there will be a machine where there is a more efficient way to zero a register than XOR with itself. This affects scalar, SSE2, SSSE3 and AVX2 as they need the new macro. It's possible to write faster implementations (different scheduling, different unrolling, interleaving NEON and scalar, ...) for various cores, but this one has the advantage of fitting in the current state of the code, and thus is likely easier to review/check/merge. The only difference between aarch64-neon and aarch64-neonx2 is that aarch64-neonx2 unroll some functions some more. Reviewed-by: Gvozden Neskovic <neskovic@gmail.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Romain Dolbeau <romain.dolbeau@atos.net> Closes #4801
139 lines
2.2 KiB
Makefile
139 lines
2.2 KiB
Makefile
include $(top_srcdir)/config/Rules.am
|
|
|
|
VPATH = \
|
|
$(top_srcdir)/module/zfs \
|
|
$(top_srcdir)/module/zcommon \
|
|
$(top_srcdir)/lib/libzpool
|
|
|
|
AM_CFLAGS += $(DEBUG_STACKFLAGS) $(FRAME_LARGER_THAN)
|
|
|
|
DEFAULT_INCLUDES += \
|
|
-I$(top_srcdir)/include \
|
|
-I$(top_srcdir)/lib/libspl/include
|
|
|
|
lib_LTLIBRARIES = libzpool.la
|
|
|
|
USER_C = \
|
|
kernel.c \
|
|
taskq.c \
|
|
util.c
|
|
|
|
KERNEL_C = \
|
|
zfs_comutil.c \
|
|
zfs_deleg.c \
|
|
zfs_fletcher.c \
|
|
zfs_fletcher_intel.c \
|
|
zfs_fletcher_sse.c \
|
|
zfs_fletcher_avx512.c \
|
|
zfs_namecheck.c \
|
|
zfs_prop.c \
|
|
zfs_uio.c \
|
|
zpool_prop.c \
|
|
zprop_common.c \
|
|
arc.c \
|
|
blkptr.c \
|
|
bplist.c \
|
|
bpobj.c \
|
|
bptree.c \
|
|
bqueue.c \
|
|
dbuf.c \
|
|
dbuf_stats.c \
|
|
ddt.c \
|
|
ddt_zap.c \
|
|
dmu.c \
|
|
dmu_diff.c \
|
|
dmu_object.c \
|
|
dmu_objset.c \
|
|
dmu_send.c \
|
|
dmu_traverse.c \
|
|
dmu_tx.c \
|
|
dmu_zfetch.c \
|
|
dnode.c \
|
|
dnode_sync.c \
|
|
dsl_bookmark.c \
|
|
dsl_dataset.c \
|
|
dsl_deadlist.c \
|
|
dsl_deleg.c \
|
|
dsl_dir.c \
|
|
dsl_pool.c \
|
|
dsl_prop.c \
|
|
dsl_scan.c \
|
|
dsl_synctask.c \
|
|
dsl_destroy.c \
|
|
dsl_userhold.c \
|
|
fm.c \
|
|
gzip.c \
|
|
lzjb.c \
|
|
lz4.c \
|
|
metaslab.c \
|
|
multilist.c \
|
|
pathname.c \
|
|
range_tree.c \
|
|
refcount.c \
|
|
rrwlock.c \
|
|
sa.c \
|
|
sha256.c \
|
|
spa.c \
|
|
spa_boot.c \
|
|
spa_config.c \
|
|
spa_errlog.c \
|
|
spa_history.c \
|
|
spa_misc.c \
|
|
spa_stats.c \
|
|
space_map.c \
|
|
space_reftree.c \
|
|
txg.c \
|
|
trace.c \
|
|
uberblock.c \
|
|
unique.c \
|
|
vdev.c \
|
|
vdev_cache.c \
|
|
vdev_file.c \
|
|
vdev_label.c \
|
|
vdev_mirror.c \
|
|
vdev_missing.c \
|
|
vdev_queue.c \
|
|
vdev_raidz.c \
|
|
vdev_raidz_math.c \
|
|
vdev_raidz_math_scalar.c \
|
|
vdev_raidz_math_sse2.c \
|
|
vdev_raidz_math_ssse3.c \
|
|
vdev_raidz_math_avx2.c \
|
|
vdev_raidz_math_aarch64_neon.c \
|
|
vdev_raidz_math_aarch64_neonx2.c \
|
|
vdev_root.c \
|
|
zap.c \
|
|
zap_leaf.c \
|
|
zap_micro.c \
|
|
zfeature.c \
|
|
zfeature_common.c \
|
|
zfs_byteswap.c \
|
|
zfs_debug.c \
|
|
zfs_fm.c \
|
|
zfs_fuid.c \
|
|
zfs_sa.c \
|
|
zfs_znode.c \
|
|
zfs_rlock.c \
|
|
zil.c \
|
|
zio.c \
|
|
zio_checksum.c \
|
|
zio_compress.c \
|
|
zio_inject.c \
|
|
zle.c \
|
|
zrlock.c
|
|
|
|
nodist_libzpool_la_SOURCES = \
|
|
$(USER_C) \
|
|
$(KERNEL_C)
|
|
|
|
libzpool_la_LIBADD = \
|
|
$(top_builddir)/lib/libunicode/libunicode.la \
|
|
$(top_builddir)/lib/libuutil/libuutil.la \
|
|
$(top_builddir)/lib/libnvpair/libnvpair.la \
|
|
$(top_builddir)/lib/libicp/libicp.la
|
|
|
|
libzpool_la_LIBADD += $(ZLIB)
|
|
libzpool_la_LDFLAGS = -version-info 2:0:0
|
|
|
|
EXTRA_DIST = $(USER_C)
|