diff options
Diffstat (limited to 'target/riscv/vector_helper.c')
| -rw-r--r-- | target/riscv/vector_helper.c | 76 |
1 files changed, 50 insertions, 26 deletions
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 81ac85b7d5..f4d0438988 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -382,8 +382,8 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, } /* - * masked unit-stride load and store operation will be a special case of stride, - * stride = NF * sizeof (MTYPE) + * masked unit-stride load and store operation will be a special case of + * stride, stride = NF * sizeof (MTYPE) */ #define GEN_VEXT_LD_US(NAME, ETYPE, LOAD_FN) \ @@ -678,7 +678,8 @@ vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, /* load/store rest of elements of current segment pointed by vstart */ for (pos = off; pos < max_elems; pos++, env->vstart++) { target_ulong addr = base + ((pos + k * max_elems) << log2_esz); - ldst_elem(env, adjust_addr(env, addr), pos + k * max_elems, vd, ra); + ldst_elem(env, adjust_addr(env, addr), pos + k * max_elems, vd, + ra); } k++; } @@ -1306,7 +1307,9 @@ GEN_VEXT_SHIFT_VV(vsra_vv_h, uint16_t, int16_t, H2, H2, DO_SRL, 0xf) GEN_VEXT_SHIFT_VV(vsra_vv_w, uint32_t, int32_t, H4, H4, DO_SRL, 0x1f) GEN_VEXT_SHIFT_VV(vsra_vv_d, uint64_t, int64_t, H8, H8, DO_SRL, 0x3f) -/* generate the helpers for shift instructions with one vector and one scalar */ +/* + * generate the helpers for shift instructions with one vector and one scalar + */ #define GEN_VEXT_SHIFT_VX(NAME, TD, TS2, HD, HS2, OP, MASK) \ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ void *vs2, CPURISCVState *env, \ @@ -2165,7 +2168,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ do_##NAME, ESZ); \ } -static inline uint8_t saddu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b) +static inline uint8_t saddu8(CPURISCVState *env, int vxrm, uint8_t a, + uint8_t b) { uint8_t res = a + b; if (res < a) { @@ -2309,7 +2313,8 @@ static inline int8_t sadd8(CPURISCVState *env, int vxrm, int8_t a, int8_t b) return res; } -static inline int16_t sadd16(CPURISCVState *env, int vxrm, int16_t a, int16_t b) +static inline int16_t sadd16(CPURISCVState *env, int vxrm, int16_t a, + int16_t b) { int16_t res = a + b; if ((res ^ a) & (res ^ b) & INT16_MIN) { @@ -2319,7 +2324,8 @@ static inline int16_t sadd16(CPURISCVState *env, int vxrm, int16_t a, int16_t b) return res; } -static inline int32_t sadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) +static inline int32_t sadd32(CPURISCVState *env, int vxrm, int32_t a, + int32_t b) { int32_t res = a + b; if ((res ^ a) & (res ^ b) & INT32_MIN) { @@ -2329,7 +2335,8 @@ static inline int32_t sadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) return res; } -static inline int64_t sadd64(CPURISCVState *env, int vxrm, int64_t a, int64_t b) +static inline int64_t sadd64(CPURISCVState *env, int vxrm, int64_t a, + int64_t b) { int64_t res = a + b; if ((res ^ a) & (res ^ b) & INT64_MIN) { @@ -2357,7 +2364,8 @@ GEN_VEXT_VX_RM(vsadd_vx_h, 2) GEN_VEXT_VX_RM(vsadd_vx_w, 4) GEN_VEXT_VX_RM(vsadd_vx_d, 8) -static inline uint8_t ssubu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b) +static inline uint8_t ssubu8(CPURISCVState *env, int vxrm, uint8_t a, + uint8_t b) { uint8_t res = a - b; if (res > a) { @@ -2428,7 +2436,8 @@ static inline int8_t ssub8(CPURISCVState *env, int vxrm, int8_t a, int8_t b) return res; } -static inline int16_t ssub16(CPURISCVState *env, int vxrm, int16_t a, int16_t b) +static inline int16_t ssub16(CPURISCVState *env, int vxrm, int16_t a, + int16_t b) { int16_t res = a - b; if ((res ^ a) & (a ^ b) & INT16_MIN) { @@ -2438,7 +2447,8 @@ static inline int16_t ssub16(CPURISCVState *env, int vxrm, int16_t a, int16_t b) return res; } -static inline int32_t ssub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) +static inline int32_t ssub32(CPURISCVState *env, int vxrm, int32_t a, + int32_t b) { int32_t res = a - b; if ((res ^ a) & (a ^ b) & INT32_MIN) { @@ -2448,7 +2458,8 @@ static inline int32_t ssub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) return res; } -static inline int64_t ssub64(CPURISCVState *env, int vxrm, int64_t a, int64_t b) +static inline int64_t ssub64(CPURISCVState *env, int vxrm, int64_t a, + int64_t b) { int64_t res = a - b; if ((res ^ a) & (a ^ b) & INT64_MIN) { @@ -2504,7 +2515,8 @@ static inline uint8_t get_round(int vxrm, uint64_t v, uint8_t shift) return 0; /* round-down (truncate) */ } -static inline int32_t aadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) +static inline int32_t aadd32(CPURISCVState *env, int vxrm, int32_t a, + int32_t b) { int64_t res = (int64_t)a + b; uint8_t round = get_round(vxrm, res, 1); @@ -2512,7 +2524,8 @@ static inline int32_t aadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) return (res >> 1) + round; } -static inline int64_t aadd64(CPURISCVState *env, int vxrm, int64_t a, int64_t b) +static inline int64_t aadd64(CPURISCVState *env, int vxrm, int64_t a, + int64_t b) { int64_t res = a + b; uint8_t round = get_round(vxrm, res, 1); @@ -2577,7 +2590,8 @@ GEN_VEXT_VX_RM(vaaddu_vx_h, 2) GEN_VEXT_VX_RM(vaaddu_vx_w, 4) GEN_VEXT_VX_RM(vaaddu_vx_d, 8) -static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) +static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, + int32_t b) { int64_t res = (int64_t)a - b; uint8_t round = get_round(vxrm, res, 1); @@ -2585,7 +2599,8 @@ static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b) return (res >> 1) + round; } -static inline int64_t asub64(CPURISCVState *env, int vxrm, int64_t a, int64_t b) +static inline int64_t asub64(CPURISCVState *env, int vxrm, int64_t a, + int64_t b) { int64_t res = (int64_t)a - b; uint8_t round = get_round(vxrm, res, 1); @@ -4498,7 +4513,9 @@ RVVCALL(OPFVV1, vfwcvt_x_f_v_w, WOP_UU_W, H8, H4, float32_to_int64) GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 4) GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 8) -/* vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float */ +/* + * vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float. + */ RVVCALL(OPFVV1, vfwcvt_f_xu_v_b, WOP_UU_B, H2, H1, uint8_to_float16) RVVCALL(OPFVV1, vfwcvt_f_xu_v_h, WOP_UU_H, H4, H2, uint16_to_float32) RVVCALL(OPFVV1, vfwcvt_f_xu_v_w, WOP_UU_W, H8, H4, uint32_to_float64) @@ -4515,8 +4532,7 @@ GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 4) GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 8) /* - * vfwcvt.f.f.v vd, vs2, vm - * Convert single-width float to double-width float. + * vfwcvt.f.f.v vd, vs2, vm # Convert single-width float to double-width float. */ static uint32_t vfwcvtffv16(uint16_t a, float_status *s) { @@ -4549,7 +4565,9 @@ GEN_VEXT_V_ENV(vfncvt_x_f_w_b, 1) GEN_VEXT_V_ENV(vfncvt_x_f_w_h, 2) GEN_VEXT_V_ENV(vfncvt_x_f_w_w, 4) -/* vfncvt.f.xu.v vd, vs2, vm # Convert double-width unsigned integer to float */ +/* + * vfncvt.f.xu.v vd, vs2, vm # Convert double-width unsigned integer to float. + */ RVVCALL(OPFVV1, vfncvt_f_xu_w_h, NOP_UU_H, H2, H4, uint32_to_float16) RVVCALL(OPFVV1, vfncvt_f_xu_w_w, NOP_UU_W, H4, H8, uint64_to_float32) GEN_VEXT_V_ENV(vfncvt_f_xu_w_h, 2) @@ -4699,14 +4717,20 @@ GEN_VEXT_FRED(vfredosum_vs_w, uint32_t, uint32_t, H4, H4, float32_add) GEN_VEXT_FRED(vfredosum_vs_d, uint64_t, uint64_t, H8, H8, float64_add) /* Maximum value */ -GEN_VEXT_FRED(vfredmax_vs_h, uint16_t, uint16_t, H2, H2, float16_maximum_number) -GEN_VEXT_FRED(vfredmax_vs_w, uint32_t, uint32_t, H4, H4, float32_maximum_number) -GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8, float64_maximum_number) +GEN_VEXT_FRED(vfredmax_vs_h, uint16_t, uint16_t, H2, H2, + float16_maximum_number) +GEN_VEXT_FRED(vfredmax_vs_w, uint32_t, uint32_t, H4, H4, + float32_maximum_number) +GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8, + float64_maximum_number) /* Minimum value */ -GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, float16_minimum_number) -GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, float32_minimum_number) -GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minimum_number) +GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, + float16_minimum_number) +GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, + float32_minimum_number) +GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, + float64_minimum_number) /* Vector Widening Floating-Point Add Instructions */ static uint32_t fwadd16(uint32_t a, uint16_t b, float_status *s) |