https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113166
--- Comment #3 from JuzheZhong <juzhe.zhong at rivai dot ai> ---
#include <cstdint>
#include <riscv_vector.h>
template <size_t length>
inline vuint8m1_t tail_load(void const* data);
template<>
inline vuint8m1_t tail_load<sizeof(uint64_t)>(void const* data) {
uint64_t const* ptr64 = reinterpret_cast<uint64_t const*>(data);
#if 1
const vuint64m1_t zero = __riscv_vmv_v_x_u64m1(0,
__riscv_vsetvlmax_e64m1());
vuint64m1_t v64 = __riscv_vslide1up(zero, *ptr64,
__riscv_vsetvlmax_e64m1());
return __riscv_vreinterpret_u8m1(v64);
#elif 1
vuint64m1_t v64 = __riscv_vmv_s_x_u64m1(*ptr64, 1);
const vuint64m1_t zero = __riscv_vmv_v_x_u64m1(0,
__riscv_vsetvlmax_e64m1());
v64 = __riscv_vslideup(v64, zero, 1, __riscv_vsetvlmax_e8m1());
return __riscv_vreinterpret_u8m1(v64);
#elif 1
vuint64m1_t v64 = __riscv_vle64_v_u64m1(ptr64, 1);
const vuint64m1_t zero = __riscv_vmv_v_x_u64m1(0,
__riscv_vsetvlmax_e64m1());
v64 = __riscv_vslideup(v64, zero, 1, __riscv_vsetvlmax_e8m1());
return __riscv_vreinterpret_u8m1(v64);
#else
vuint8m1_t v = __riscv_vreinterpret_u8m1(__riscv_vle64_v_u64m1(ptr64, 1));
const vuint8m1_t zero = __riscv_vmv_v_x_u8m1(0, __riscv_vsetvlmax_e8m1());
return __riscv_vslideup(v, zero, sizeof(uint64_t),
__riscv_vsetvlmax_e8m1());
#endif
}
vuint8m1_t test2(uint64_t data) {
return tail_load<sizeof(data)>(&data);
}
GCC ASM:
test2(unsigned long):
vsetvli a5,zero,e64,m1,ta,ma
vmv.v.i v8,0
vmv1r.v v9,v8
vslide1up.vx v8,v9,a0
ret
LLVM ASM:
test2(unsigned long): # @test2(unsigned long)
vsetvli a1, zero, e64, m1, ta, ma
vmv.v.i v9, 0
vslide1up.vx v8, v9, a0
ret
