https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65375
Bug ID: 65375
Summary: poor codegen for ld[234]/st[234]
Product: gcc
Version: 5.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: kugan at gcc dot gnu.org
#include <arm_neon.h>
void hello_vst2(float* fout, float *fin)
{
float32x4x2_t a;
a = vld2q_f32 (fin);
vst2q_f32 (fout, a);
}
with aarch64-none-linux-gnu-gcc -O2 -ffast-math -unsafe-math-optimisations
produces:
.cpu generic+fp+simd
.file "neon.c"
.text
.align 2
.p2align 3,,7
.global hello_vst2
.type hello_vst2, %function
hello_vst2:
ld2 {v0.4s - v1.4s}, [x1]
sub sp, sp, #32
umov x1, v0.d[0]
umov x2, v0.d[1]
str q1, [sp, 16]
mov x5, x1
stp x5, x2, [sp]
ld1 {v0.16b - v1.16b}, [sp]
st2 {v0.4s - v1.4s}, [x0]
add sp, sp, 32
ret
.size hello_vst2, .-hello_vst2
.ident "GCC: (GNU) 5.0.0 20150305 (experimental)"
.section .note.GNU-stack,"",%progbits
