https://gcc.gnu.org/bugzilla/show_bug.cgi?id=87743
--- Comment #2 from H.J. Lu <hjl.tools at gmail dot com> ---
[hjl@gnu-efi-2 pr87317]$ cat y.c
#define MAX 4
long long int dst[MAX];
short src[MAX];
void
foo (void)
{
int i;
for (i = 0; i < MAX; i++)
dst[i] = src[i];
}
[hjl@gnu-efi-2 pr87317]$
/export/ssd/build/tools-build/glibc-many/install/compilers/aarch64-linux-gnu/bin/aarch64-glibc-linux-gnu-gcc
-S -O3 y.c
[hjl@gnu-efi-2 pr87317]$ cat y.s
.arch armv8-a
.file "y.c"
.text
.align 2
.p2align 3,,7
.global foo
.type foo, %function
foo:
.LFB0:
.cfi_startproc
adrp x3, src
add x1, x3, :lo12:src
adrp x2, dst
add x0, x2, :lo12:dst
ldrsh x5, [x3, #:lo12:src]
ldrsh x4, [x1, 2]
ldrsh x3, [x1, 4]
ldrsh x1, [x1, 6]
str x5, [x2, #:lo12:dst]
stp x4, x3, [x0, 8]
str x1, [x0, 24]
ret
.cfi_endproc
.LFE0:
.size foo, .-foo
.comm src,8,8
.comm dst,32,8
.ident "GCC: (GNU) 8.2.1 20180922"
.section .note.GNU-stack,"",@progbits
[hjl@gnu-efi-2 pr87317]$ gcc -march=haswell -S -O3 y.c
[hjl@gnu-efi-2 pr87317]$ cat y.s
.file "y.c"
.text
.p2align 4,,15
.globl foo
.type foo, @function
foo:
.LFB0:
.cfi_startproc
movswq src(%rip), %rax
movswq src+4(%rip), %rcx
movswq src+6(%rip), %rdx
vmovq %rax, %xmm0
movswq src+2(%rip), %rax
vmovq %rcx, %xmm1
vpinsrq $1, %rdx, %xmm1, %xmm1
vpinsrq $1, %rax, %xmm0, %xmm0
vinserti128 $0x1, %xmm1, %ymm0, %ymm0
vmovdqu %ymm0, dst(%rip)
vzeroupper
ret
.cfi_endproc
.LFE0:
.size foo, .-foo
.comm src,8,8
.comm dst,32,32
.ident "GCC: (GNU) 8.2.1 20181011 (Red Hat 8.2.1-4)"
.section .note.GNU-stack,"",@progbits
[hjl@gnu-efi-2 pr87317]$
I don't see much differences between x86-64 and arm64.
