https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63277
Bug ID: 63277
Summary: ARM - NEON excessive use of vmov for vtbl2 / uint8x8x2
for shuffling data unnecessarily around
Product: gcc
Version: 5.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: janne-gcc at jannau dot net
Created attachment 33500
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=33500&action=edit
small example source code
armv7a-hardfloat-linux-gnueabi-gcc-5.0.0 -v
Using built-in specs.
COLLECT_GCC=/opt/gcc/bin/armv7a-hardfloat-linux-gnueabi-gcc-5.0.0
COLLECT_LTO_WRAPPER=/opt/gcc/libexec/gcc/armv7a-hardfloat-linux-gnueabi/5.0.0/lto-wrapper
Target: armv7a-hardfloat-linux-gnueabi
Configured with: /home/janne/src/gcc-trunk/configure --host=x86_64-pc-linux-gnu
--target=armv7a-hardfloat-linux-gnueabi --build=x86_64-pc-linux-gnu
--prefix=/opt/gcc/ --enable-languages=c,c++,fortran --enable-obsolete
--enable-secureplt --disable-werror --with-system-zlib --enable-nls
--without-included-gettext --enable-checking=release --enable-libstdcxx-time
--enable-poison-system-directories
--with-sysroot=/usr/armv7a-hardfloat-linux-gnueabi --disable-bootstrap
--enable-__cxa_atexit --enable-clocale=gnu --disable-multilib --disable-altivec
--disable-fixed-point --with-float=hard --with-arch=armv7-a --with-float=hard
--with-fpu=neon --disable-libgcj --enable-libgomp --disable-libmudflap
--disable-libssp --enable-lto --without-cloog
Thread model: posix
gcc version 5.0.0 20140916 (experimental) (GCC)
armv7a-hardfloat-linux-gnueabi-gcc-5.0.0 -march=armv7-a -mfpu=neon -O3 -S
arm_neon_excessive_vmov.c -o -
.arch armv7-a
.eabi_attribute 27, 3
.eabi_attribute 28, 1
.fpu neon
.eabi_attribute 20, 1
.eabi_attribute 21, 1
.eabi_attribute 23, 3
.eabi_attribute 24, 1
.eabi_attribute 25, 1
.eabi_attribute 26, 2
.eabi_attribute 30, 2
.eabi_attribute 34, 1
.eabi_attribute 18, 4
.file "arm_neon_excessive_vmov.c"
.text
.align 2
.global gf_w8_split_multiply_region_neon
.type gf_w8_split_multiply_region_neon, %function
gf_w8_split_multiply_region_neon:
@ args = 4, pretend = 0, frame = 0
@ frame_needed = 0, uses_anonymous_args = 0
str lr, [sp, #-4]!
mov r3, r3, asl #4
ldr ip, [sp, #4]
add lr, r0, #4096
add lr, lr, r3
add r0, r0, r3
vmov.i8 q15, #15 @ v16qi
add ip, r2, ip, lsl #4
vld1.8 {d18-d19}, [lr]
cmp r1, ip
vld1.8 {d16-d17}, [r0]
ldrcs pc, [sp], #4
vmov d27, d18 @ v8qi
vmov d26, d19 @ v8qi
vmov d25, d16 @ v8qi
vmov d24, d17 @ v8qi
.L3:
vld1.8 {d18-d19}, [r1]
vmov d20, d25 @ v8qi
vmov d21, d24 @ v8qi
add r1, r1, #16
vshr.u8 q14, q9, #4
cmp r1, ip
vmov d22, d27 @ v8qi
vmov d23, d26 @ v8qi
vtbl.8 d16, {d20, d21}, d28
vand q9, q9, q15
vtbl.8 d28, {d20, d21}, d29
vtbl.8 d17, {d22, d23}, d18
vmov d29, d28 @ v8qi
vmov d28, d16 @ v8qi
vtbl.8 d16, {d22, d23}, d19
vswp d16, d17
veor q8, q8, q14
vst1.8 {d16-d17}, [r2]
add r2, r2, #16
bcc .L3
ldr pc, [sp], #4
.size gf_w8_split_multiply_region_neon,
.-gf_w8_split_multiply_region_neon
.ident "GCC: (GNU) 5.0.0 20140916 (experimental)"
.section .note.GNU-stack,"",%progbits
There is no need for the vmovs/vswp and clang 3.4 generates from the same
source file assembly without them.
