https://gcc.gnu.org/bugzilla/show_bug.cgi?id=85052
--- Comment #6 from Devin Hussey <husseydevin at gmail dot com> ---
The patch seems to be working.
typedef unsigned u32x2 __attribute__((vector_size(8)));
typedef unsigned long long u64x2 __attribute__((vector_size(16)));
u64x2 cvt(u32x2 in)
{
return __builtin_convertvector(in, u64x2);
}
It doesn't generate the best code, but it isn't bad.
x86_64, SSE4.1:
cvt:
movq %xmm0, %rax
movd %eax, %xmm0
shrq $32, %rax
pinsrq $1, %rax, %xmm0
ret
x86_64, SSE2:
cvt:
movq %xmm0, %rax
movd %eax, %xmm0
shrq $32, %rax
movq %rax, %xmm1
punpcklqdq %xmm1, %xmm0
ret
ARMv7a NEON:
cvt:
sub sp, sp, #16
mov r3, #0
str r3, [sp, #4]
str r3, [sp, #12]
add r3, sp, #8
vst1.32 {d0[0]}, [sp]
vst1.32 {d0[1]}, [r3]
vld1.64 {d0-d1}, [sp:64]
add sp, sp, #16
bx lr
I haven't built the others yet.
The correct code would be this ([signed|unsigned]):
cvt:
vmovl.[s|u]32 q0, d0
bx lr
I am testing other targets now.
For the reference, this is what clang generates for other targets:
aarch64:
cvt:
[s|u]shll v0.2d, v0.2s, #0
ret
sse4.1/avx:
cvt:
[v]pmov[s|z]xdq xmm0, xmm0
ret
sse2:
signed_cvt:
pxor xmm1, xmm1
pcmpgtd xmm1, xmm0
punpckldq xmm0, xmm1 # xmm0 =
xmm0[0],xmm1[0],xmm0[1],xmm1[1]
ret
unsigned_cvt:
xorps xmm1, xmm1
unpcklps xmm0, xmm1 # xmm0 =
xmm0[0],xmm1[0],xmm0[1],xmm1[1]
ret
