GCC provides intrinsics to access the SIMD instructions provided by the
ST Microelectronics Loongson-2E and -2F processors. These intrinsics,
available after inclusion of the loongson.h header file,
operate on the following 64-bit vector types:
uint8x8_t, a vector of eight unsigned 8-bit integers;
uint16x4_t, a vector of four unsigned 16-bit integers;
uint32x2_t, a vector of two unsigned 32-bit integers;
int8x8_t, a vector of eight signed 8-bit integers;
int16x4_t, a vector of four signed 16-bit integers;
int32x2_t, a vector of two signed 32-bit integers.
The intrinsics provided are listed below; each is named after the machine instruction to which it corresponds, with suffixes added as appropriate to distinguish intrinsics that expand to the same machine instruction yet have different argument types. Refer to the architecture documentation for a description of the functionality of each instruction.
int16x4_t packsswh (int32x2_t s, int32x2_t t);
int8x8_t packsshb (int16x4_t s, int16x4_t t);
uint8x8_t packushb (uint16x4_t s, uint16x4_t t);
uint32x2_t paddw_u (uint32x2_t s, uint32x2_t t);
uint16x4_t paddh_u (uint16x4_t s, uint16x4_t t);
uint8x8_t paddb_u (uint8x8_t s, uint8x8_t t);
int32x2_t paddw_s (int32x2_t s, int32x2_t t);
int16x4_t paddh_s (int16x4_t s, int16x4_t t);
int8x8_t paddb_s (int8x8_t s, int8x8_t t);
uint64_t paddd_u (uint64_t s, uint64_t t);
int64_t paddd_s (int64_t s, int64_t t);
int16x4_t paddsh (int16x4_t s, int16x4_t t);
int8x8_t paddsb (int8x8_t s, int8x8_t t);
uint16x4_t paddush (uint16x4_t s, uint16x4_t t);
uint8x8_t paddusb (uint8x8_t s, uint8x8_t t);
uint64_t pandn_ud (uint64_t s, uint64_t t);
uint32x2_t pandn_uw (uint32x2_t s, uint32x2_t t);
uint16x4_t pandn_uh (uint16x4_t s, uint16x4_t t);
uint8x8_t pandn_ub (uint8x8_t s, uint8x8_t t);
int64_t pandn_sd (int64_t s, int64_t t);
int32x2_t pandn_sw (int32x2_t s, int32x2_t t);
int16x4_t pandn_sh (int16x4_t s, int16x4_t t);
int8x8_t pandn_sb (int8x8_t s, int8x8_t t);
uint16x4_t pavgh (uint16x4_t s, uint16x4_t t);
uint8x8_t pavgb (uint8x8_t s, uint8x8_t t);
uint32x2_t pcmpeqw_u (uint32x2_t s, uint32x2_t t);
uint16x4_t pcmpeqh_u (uint16x4_t s, uint16x4_t t);
uint8x8_t pcmpeqb_u (uint8x8_t s, uint8x8_t t);
int32x2_t pcmpeqw_s (int32x2_t s, int32x2_t t);
int16x4_t pcmpeqh_s (int16x4_t s, int16x4_t t);
int8x8_t pcmpeqb_s (int8x8_t s, int8x8_t t);
uint32x2_t pcmpgtw_u (uint32x2_t s, uint32x2_t t);
uint16x4_t pcmpgth_u (uint16x4_t s, uint16x4_t t);
uint8x8_t pcmpgtb_u (uint8x8_t s, uint8x8_t t);
int32x2_t pcmpgtw_s (int32x2_t s, int32x2_t t);
int16x4_t pcmpgth_s (int16x4_t s, int16x4_t t);
int8x8_t pcmpgtb_s (int8x8_t s, int8x8_t t);
uint16x4_t pextrh_u (uint16x4_t s, int field);
int16x4_t pextrh_s (int16x4_t s, int field);
uint16x4_t pinsrh_0_u (uint16x4_t s, uint16x4_t t);
uint16x4_t pinsrh_1_u (uint16x4_t s, uint16x4_t t);
uint16x4_t pinsrh_2_u (uint16x4_t s, uint16x4_t t);
uint16x4_t pinsrh_3_u (uint16x4_t s, uint16x4_t t);
int16x4_t pinsrh_0_s (int16x4_t s, int16x4_t t);
int16x4_t pinsrh_1_s (int16x4_t s, int16x4_t t);
int16x4_t pinsrh_2_s (int16x4_t s, int16x4_t t);
int16x4_t pinsrh_3_s (int16x4_t s, int16x4_t t);
int32x2_t pmaddhw (int16x4_t s, int16x4_t t);
int16x4_t pmaxsh (int16x4_t s, int16x4_t t);
uint8x8_t pmaxub (uint8x8_t s, uint8x8_t t);
int16x4_t pminsh (int16x4_t s, int16x4_t t);
uint8x8_t pminub (uint8x8_t s, uint8x8_t t);
uint8x8_t pmovmskb_u (uint8x8_t s);
int8x8_t pmovmskb_s (int8x8_t s);
uint16x4_t pmulhuh (uint16x4_t s, uint16x4_t t);
int16x4_t pmulhh (int16x4_t s, int16x4_t t);
int16x4_t pmullh (int16x4_t s, int16x4_t t);
int64_t pmuluw (uint32x2_t s, uint32x2_t t);
uint8x8_t pasubub (uint8x8_t s, uint8x8_t t);
uint16x4_t biadd (uint8x8_t s);
uint16x4_t psadbh (uint8x8_t s, uint8x8_t t);
uint16x4_t pshufh_u (uint16x4_t dest, uint16x4_t s, uint8_t order);
int16x4_t pshufh_s (int16x4_t dest, int16x4_t s, uint8_t order);
uint16x4_t psllh_u (uint16x4_t s, uint8_t amount);
int16x4_t psllh_s (int16x4_t s, uint8_t amount);
uint32x2_t psllw_u (uint32x2_t s, uint8_t amount);
int32x2_t psllw_s (int32x2_t s, uint8_t amount);
uint16x4_t psrlh_u (uint16x4_t s, uint8_t amount);
int16x4_t psrlh_s (int16x4_t s, uint8_t amount);
uint32x2_t psrlw_u (uint32x2_t s, uint8_t amount);
int32x2_t psrlw_s (int32x2_t s, uint8_t amount);
uint16x4_t psrah_u (uint16x4_t s, uint8_t amount);
int16x4_t psrah_s (int16x4_t s, uint8_t amount);
uint32x2_t psraw_u (uint32x2_t s, uint8_t amount);
int32x2_t psraw_s (int32x2_t s, uint8_t amount);
uint32x2_t psubw_u (uint32x2_t s, uint32x2_t t);
uint16x4_t psubh_u (uint16x4_t s, uint16x4_t t);
uint8x8_t psubb_u (uint8x8_t s, uint8x8_t t);
int32x2_t psubw_s (int32x2_t s, int32x2_t t);
int16x4_t psubh_s (int16x4_t s, int16x4_t t);
int8x8_t psubb_s (int8x8_t s, int8x8_t t);
uint64_t psubd_u (uint64_t s, uint64_t t);
int64_t psubd_s (int64_t s, int64_t t);
int16x4_t psubsh (int16x4_t s, int16x4_t t);
int8x8_t psubsb (int8x8_t s, int8x8_t t);
uint16x4_t psubush (uint16x4_t s, uint16x4_t t);
uint8x8_t psubusb (uint8x8_t s, uint8x8_t t);
uint32x2_t punpckhwd_u (uint32x2_t s, uint32x2_t t);
uint16x4_t punpckhhw_u (uint16x4_t s, uint16x4_t t);
uint8x8_t punpckhbh_u (uint8x8_t s, uint8x8_t t);
int32x2_t punpckhwd_s (int32x2_t s, int32x2_t t);
int16x4_t punpckhhw_s (int16x4_t s, int16x4_t t);
int8x8_t punpckhbh_s (int8x8_t s, int8x8_t t);
uint32x2_t punpcklwd_u (uint32x2_t s, uint32x2_t t);
uint16x4_t punpcklhw_u (uint16x4_t s, uint16x4_t t);
uint8x8_t punpcklbh_u (uint8x8_t s, uint8x8_t t);
int32x2_t punpcklwd_s (int32x2_t s, int32x2_t t);
int16x4_t punpcklhw_s (int16x4_t s, int16x4_t t);
int8x8_t punpcklbh_s (int8x8_t s, int8x8_t t);