mirrors/qemu
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

target/riscv: rvv: Add tail agnostic for vector floating-point instructions

Browse Source 
Compares write mask registers, and so always operate under a tail-
agnostic policy.

Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165449614532.19704.7000832880482980398-12@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
This commit is contained in:
eopXD 2022-06-06 06:16:56 +00:00 committed by Alistair Francis
parent 09106eed30
commit 5eacf7d8a0
2 changed files with 261 additions and 196 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
target/riscv/insn_trans/trans_rvv.c.inc
View File

@ -2338,6 +2338,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
data = FIELD_DP32(data, VDATA, VTA, s->vta); \
data = \
FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
@ -2420,6 +2423,9 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_set_rm(s, RISCV_FRM_DYN); \
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
data = FIELD_DP32(data, VDATA, VTA, s->vta); \
data = FIELD_DP32(data, VDATA, VTA_ALL_1S, \
s->cfg_vta_all_1s); \
return opfvf_trans(a->rd, a->rs1, a->rs2, data, \
fns[s->sew - 1], s); \
} \
@ -2458,6 +2464,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
@ -2497,6 +2504,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_set_rm(s, RISCV_FRM_DYN); \
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
data = FIELD_DP32(data, VDATA, VTA, s->vta); \
return opfvf_trans(a->rd, a->rs1, a->rs2, data, \
fns[s->sew - 1], s); \
} \
@ -2533,6 +2541,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs1), \
vreg_ofs(s, a->rs2), cpu_env, \
@ -2572,6 +2581,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
gen_set_rm(s, RISCV_FRM_DYN); \
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
data = FIELD_DP32(data, VDATA, VTA, s->vta); \
return opfvf_trans(a->rd, a->rs1, a->rs2, data, \
fns[s->sew - 1], s); \
} \
@ -2655,6 +2665,7 @@ static bool do_opfv(DisasContext *s, arg_rmr *a,
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
data = FIELD_DP32(data, VDATA, VTA, s->vta);
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
vreg_ofs(s, a->rs2), cpu_env,
s->cfg_ptr->vlen / 8,
@ -2859,6 +2870,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \
@ -2910,6 +2922,8 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \
@ -2977,6 +2991,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \
@ -3030,6 +3045,8 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
data = FIELD_DP32(data, VDATA, VTA, s->vta); \
tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
vreg_ofs(s, a->rs2), cpu_env, \
s->cfg_ptr->vlen / 8, \

440
target/riscv/vector_helper.c
View File

@ -2994,13 +2994,16 @@ static void do_##NAME(void *vd, void *vs1, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, s1, &env->fp_status); \
}
#define GEN_VEXT_VV_ENV(NAME) \
#define GEN_VEXT_VV_ENV(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint32_t total_elems = \
vext_get_total_elems(env, desc, ESZ); \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@ -3010,14 +3013,17 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
do_##NAME(vd, vs1, vs2, i, env); \
} \
env->vstart = 0; \
/* set tail elements to 1s */ \
vext_set_elems_1s(vd, vta, vl * ESZ, \
total_elems * ESZ); \
}
RVVCALL(OPFVV2, vfadd_vv_h, OP_UUU_H, H2, H2, H2, float16_add)
RVVCALL(OPFVV2, vfadd_vv_w, OP_UUU_W, H4, H4, H4, float32_add)
RVVCALL(OPFVV2, vfadd_vv_d, OP_UUU_D, H8, H8, H8, float64_add)
GEN_VEXT_VV_ENV(vfadd_vv_h)
GEN_VEXT_VV_ENV(vfadd_vv_w)
GEN_VEXT_VV_ENV(vfadd_vv_d)
GEN_VEXT_VV_ENV(vfadd_vv_h, 2)
GEN_VEXT_VV_ENV(vfadd_vv_w, 4)
GEN_VEXT_VV_ENV(vfadd_vv_d, 8)
#define OPFVF2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
@ -3027,13 +3033,16 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1, &env->fp_status);\
}
#define GEN_VEXT_VF(NAME) \
#define GEN_VEXT_VF(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
void *vs2, CPURISCVState *env, \
uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint32_t total_elems = \
vext_get_total_elems(env, desc, ESZ); \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@ -3043,27 +3052,30 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
do_##NAME(vd, s1, vs2, i, env); \
} \
env->vstart = 0; \
/* set tail elements to 1s */ \
vext_set_elems_1s(vd, vta, vl * ESZ, \
total_elems * ESZ); \
}
RVVCALL(OPFVF2, vfadd_vf_h, OP_UUU_H, H2, H2, float16_add)
RVVCALL(OPFVF2, vfadd_vf_w, OP_UUU_W, H4, H4, float32_add)
RVVCALL(OPFVF2, vfadd_vf_d, OP_UUU_D, H8, H8, float64_add)
GEN_VEXT_VF(vfadd_vf_h)
GEN_VEXT_VF(vfadd_vf_w)
GEN_VEXT_VF(vfadd_vf_d)
GEN_VEXT_VF(vfadd_vf_h, 2)
GEN_VEXT_VF(vfadd_vf_w, 4)
GEN_VEXT_VF(vfadd_vf_d, 8)
RVVCALL(OPFVV2, vfsub_vv_h, OP_UUU_H, H2, H2, H2, float16_sub)
RVVCALL(OPFVV2, vfsub_vv_w, OP_UUU_W, H4, H4, H4, float32_sub)
RVVCALL(OPFVV2, vfsub_vv_d, OP_UUU_D, H8, H8, H8, float64_sub)
GEN_VEXT_VV_ENV(vfsub_vv_h)
GEN_VEXT_VV_ENV(vfsub_vv_w)
GEN_VEXT_VV_ENV(vfsub_vv_d)
GEN_VEXT_VV_ENV(vfsub_vv_h, 2)
GEN_VEXT_VV_ENV(vfsub_vv_w, 4)
GEN_VEXT_VV_ENV(vfsub_vv_d, 8)
RVVCALL(OPFVF2, vfsub_vf_h, OP_UUU_H, H2, H2, float16_sub)
RVVCALL(OPFVF2, vfsub_vf_w, OP_UUU_W, H4, H4, float32_sub)
RVVCALL(OPFVF2, vfsub_vf_d, OP_UUU_D, H8, H8, float64_sub)
GEN_VEXT_VF(vfsub_vf_h)
GEN_VEXT_VF(vfsub_vf_w)
GEN_VEXT_VF(vfsub_vf_d)
GEN_VEXT_VF(vfsub_vf_h, 2)
GEN_VEXT_VF(vfsub_vf_w, 4)
GEN_VEXT_VF(vfsub_vf_d, 8)
static uint16_t float16_rsub(uint16_t a, uint16_t b, float_status *s)
{
@ -3083,9 +3095,9 @@ static uint64_t float64_rsub(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVF2, vfrsub_vf_h, OP_UUU_H, H2, H2, float16_rsub)
RVVCALL(OPFVF2, vfrsub_vf_w, OP_UUU_W, H4, H4, float32_rsub)
RVVCALL(OPFVF2, vfrsub_vf_d, OP_UUU_D, H8, H8, float64_rsub)
GEN_VEXT_VF(vfrsub_vf_h)
GEN_VEXT_VF(vfrsub_vf_w)
GEN_VEXT_VF(vfrsub_vf_d)
GEN_VEXT_VF(vfrsub_vf_h, 2)
GEN_VEXT_VF(vfrsub_vf_w, 4)
GEN_VEXT_VF(vfrsub_vf_d, 8)
/* Vector Widening Floating-Point Add/Subtract Instructions */
static uint32_t vfwadd16(uint16_t a, uint16_t b, float_status *s)
@ -3103,12 +3115,12 @@ static uint64_t vfwadd32(uint32_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwadd_vv_h, WOP_UUU_H, H4, H2, H2, vfwadd16)
RVVCALL(OPFVV2, vfwadd_vv_w, WOP_UUU_W, H8, H4, H4, vfwadd32)
GEN_VEXT_VV_ENV(vfwadd_vv_h)
GEN_VEXT_VV_ENV(vfwadd_vv_w)
GEN_VEXT_VV_ENV(vfwadd_vv_h, 4)
GEN_VEXT_VV_ENV(vfwadd_vv_w, 8)
RVVCALL(OPFVF2, vfwadd_vf_h, WOP_UUU_H, H4, H2, vfwadd16)
RVVCALL(OPFVF2, vfwadd_vf_w, WOP_UUU_W, H8, H4, vfwadd32)
GEN_VEXT_VF(vfwadd_vf_h)
GEN_VEXT_VF(vfwadd_vf_w)
GEN_VEXT_VF(vfwadd_vf_h, 4)
GEN_VEXT_VF(vfwadd_vf_w, 8)
static uint32_t vfwsub16(uint16_t a, uint16_t b, float_status *s)
{
@ -3125,12 +3137,12 @@ static uint64_t vfwsub32(uint32_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwsub_vv_h, WOP_UUU_H, H4, H2, H2, vfwsub16)
RVVCALL(OPFVV2, vfwsub_vv_w, WOP_UUU_W, H8, H4, H4, vfwsub32)
GEN_VEXT_VV_ENV(vfwsub_vv_h)
GEN_VEXT_VV_ENV(vfwsub_vv_w)
GEN_VEXT_VV_ENV(vfwsub_vv_h, 4)
GEN_VEXT_VV_ENV(vfwsub_vv_w, 8)
RVVCALL(OPFVF2, vfwsub_vf_h, WOP_UUU_H, H4, H2, vfwsub16)
RVVCALL(OPFVF2, vfwsub_vf_w, WOP_UUU_W, H8, H4, vfwsub32)
GEN_VEXT_VF(vfwsub_vf_h)
GEN_VEXT_VF(vfwsub_vf_w)
GEN_VEXT_VF(vfwsub_vf_h, 4)
GEN_VEXT_VF(vfwsub_vf_w, 8)
static uint32_t vfwaddw16(uint32_t a, uint16_t b, float_status *s)
{
@ -3144,12 +3156,12 @@ static uint64_t vfwaddw32(uint64_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwadd_wv_h, WOP_WUUU_H, H4, H2, H2, vfwaddw16)
RVVCALL(OPFVV2, vfwadd_wv_w, WOP_WUUU_W, H8, H4, H4, vfwaddw32)
GEN_VEXT_VV_ENV(vfwadd_wv_h)
GEN_VEXT_VV_ENV(vfwadd_wv_w)
GEN_VEXT_VV_ENV(vfwadd_wv_h, 4)
GEN_VEXT_VV_ENV(vfwadd_wv_w, 8)
RVVCALL(OPFVF2, vfwadd_wf_h, WOP_WUUU_H, H4, H2, vfwaddw16)
RVVCALL(OPFVF2, vfwadd_wf_w, WOP_WUUU_W, H8, H4, vfwaddw32)
GEN_VEXT_VF(vfwadd_wf_h)
GEN_VEXT_VF(vfwadd_wf_w)
GEN_VEXT_VF(vfwadd_wf_h, 4)
GEN_VEXT_VF(vfwadd_wf_w, 8)
static uint32_t vfwsubw16(uint32_t a, uint16_t b, float_status *s)
{
@ -3163,39 +3175,39 @@ static uint64_t vfwsubw32(uint64_t a, uint32_t b, float_status *s)
RVVCALL(OPFVV2, vfwsub_wv_h, WOP_WUUU_H, H4, H2, H2, vfwsubw16)
RVVCALL(OPFVV2, vfwsub_wv_w, WOP_WUUU_W, H8, H4, H4, vfwsubw32)
GEN_VEXT_VV_ENV(vfwsub_wv_h)
GEN_VEXT_VV_ENV(vfwsub_wv_w)
GEN_VEXT_VV_ENV(vfwsub_wv_h, 4)
GEN_VEXT_VV_ENV(vfwsub_wv_w, 8)
RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, vfwsubw16)
RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32)
GEN_VEXT_VF(vfwsub_wf_h)
GEN_VEXT_VF(vfwsub_wf_w)
GEN_VEXT_VF(vfwsub_wf_h, 4)
GEN_VEXT_VF(vfwsub_wf_w, 8)
/* Vector Single-Width Floating-Point Multiply/Divide Instructions */
RVVCALL(OPFVV2, vfmul_vv_h, OP_UUU_H, H2, H2, H2, float16_mul)
RVVCALL(OPFVV2, vfmul_vv_w, OP_UUU_W, H4, H4, H4, float32_mul)
RVVCALL(OPFVV2, vfmul_vv_d, OP_UUU_D, H8, H8, H8, float64_mul)
GEN_VEXT_VV_ENV(vfmul_vv_h)
GEN_VEXT_VV_ENV(vfmul_vv_w)
GEN_VEXT_VV_ENV(vfmul_vv_d)
GEN_VEXT_VV_ENV(vfmul_vv_h, 2)
GEN_VEXT_VV_ENV(vfmul_vv_w, 4)
GEN_VEXT_VV_ENV(vfmul_vv_d, 8)
RVVCALL(OPFVF2, vfmul_vf_h, OP_UUU_H, H2, H2, float16_mul)
RVVCALL(OPFVF2, vfmul_vf_w, OP_UUU_W, H4, H4, float32_mul)
RVVCALL(OPFVF2, vfmul_vf_d, OP_UUU_D, H8, H8, float64_mul)
GEN_VEXT_VF(vfmul_vf_h)
GEN_VEXT_VF(vfmul_vf_w)
GEN_VEXT_VF(vfmul_vf_d)
GEN_VEXT_VF(vfmul_vf_h, 2)
GEN_VEXT_VF(vfmul_vf_w, 4)
GEN_VEXT_VF(vfmul_vf_d, 8)
RVVCALL(OPFVV2, vfdiv_vv_h, OP_UUU_H, H2, H2, H2, float16_div)
RVVCALL(OPFVV2, vfdiv_vv_w, OP_UUU_W, H4, H4, H4, float32_div)
RVVCALL(OPFVV2, vfdiv_vv_d, OP_UUU_D, H8, H8, H8, float64_div)
GEN_VEXT_VV_ENV(vfdiv_vv_h)
GEN_VEXT_VV_ENV(vfdiv_vv_w)
GEN_VEXT_VV_ENV(vfdiv_vv_d)
GEN_VEXT_VV_ENV(vfdiv_vv_h, 2)
GEN_VEXT_VV_ENV(vfdiv_vv_w, 4)
GEN_VEXT_VV_ENV(vfdiv_vv_d, 8)
RVVCALL(OPFVF2, vfdiv_vf_h, OP_UUU_H, H2, H2, float16_div)
RVVCALL(OPFVF2, vfdiv_vf_w, OP_UUU_W, H4, H4, float32_div)
RVVCALL(OPFVF2, vfdiv_vf_d, OP_UUU_D, H8, H8, float64_div)
GEN_VEXT_VF(vfdiv_vf_h)
GEN_VEXT_VF(vfdiv_vf_w)
GEN_VEXT_VF(vfdiv_vf_d)
GEN_VEXT_VF(vfdiv_vf_h, 2)
GEN_VEXT_VF(vfdiv_vf_w, 4)
GEN_VEXT_VF(vfdiv_vf_d, 8)
static uint16_t float16_rdiv(uint16_t a, uint16_t b, float_status *s)
{
@ -3215,9 +3227,9 @@ static uint64_t float64_rdiv(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVF2, vfrdiv_vf_h, OP_UUU_H, H2, H2, float16_rdiv)
RVVCALL(OPFVF2, vfrdiv_vf_w, OP_UUU_W, H4, H4, float32_rdiv)
RVVCALL(OPFVF2, vfrdiv_vf_d, OP_UUU_D, H8, H8, float64_rdiv)
GEN_VEXT_VF(vfrdiv_vf_h)
GEN_VEXT_VF(vfrdiv_vf_w)
GEN_VEXT_VF(vfrdiv_vf_d)
GEN_VEXT_VF(vfrdiv_vf_h, 2)
GEN_VEXT_VF(vfrdiv_vf_w, 4)
GEN_VEXT_VF(vfrdiv_vf_d, 8)
/* Vector Widening Floating-Point Multiply */
static uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s)
@ -3234,12 +3246,12 @@ static uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s)
}
RVVCALL(OPFVV2, vfwmul_vv_h, WOP_UUU_H, H4, H2, H2, vfwmul16)
RVVCALL(OPFVV2, vfwmul_vv_w, WOP_UUU_W, H8, H4, H4, vfwmul32)
GEN_VEXT_VV_ENV(vfwmul_vv_h)
GEN_VEXT_VV_ENV(vfwmul_vv_w)
GEN_VEXT_VV_ENV(vfwmul_vv_h, 4)
GEN_VEXT_VV_ENV(vfwmul_vv_w, 8)
RVVCALL(OPFVF2, vfwmul_vf_h, WOP_UUU_H, H4, H2, vfwmul16)
RVVCALL(OPFVF2, vfwmul_vf_w, WOP_UUU_W, H8, H4, vfwmul32)
GEN_VEXT_VF(vfwmul_vf_h)
GEN_VEXT_VF(vfwmul_vf_w)
GEN_VEXT_VF(vfwmul_vf_h, 4)
GEN_VEXT_VF(vfwmul_vf_w, 8)
/* Vector Single-Width Floating-Point Fused Multiply-Add Instructions */
#define OPFVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
@ -3270,9 +3282,9 @@ static uint64_t fmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmacc_vv_h, OP_UUU_H, H2, H2, H2, fmacc16)
RVVCALL(OPFVV3, vfmacc_vv_w, OP_UUU_W, H4, H4, H4, fmacc32)
RVVCALL(OPFVV3, vfmacc_vv_d, OP_UUU_D, H8, H8, H8, fmacc64)
GEN_VEXT_VV_ENV(vfmacc_vv_h)
GEN_VEXT_VV_ENV(vfmacc_vv_w)
GEN_VEXT_VV_ENV(vfmacc_vv_d)
GEN_VEXT_VV_ENV(vfmacc_vv_h, 2)
GEN_VEXT_VV_ENV(vfmacc_vv_w, 4)
GEN_VEXT_VV_ENV(vfmacc_vv_d, 8)
#define OPFVF3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
@ -3286,9 +3298,9 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
RVVCALL(OPFVF3, vfmacc_vf_h, OP_UUU_H, H2, H2, fmacc16)
RVVCALL(OPFVF3, vfmacc_vf_w, OP_UUU_W, H4, H4, fmacc32)
RVVCALL(OPFVF3, vfmacc_vf_d, OP_UUU_D, H8, H8, fmacc64)
GEN_VEXT_VF(vfmacc_vf_h)
GEN_VEXT_VF(vfmacc_vf_w)
GEN_VEXT_VF(vfmacc_vf_d)
GEN_VEXT_VF(vfmacc_vf_h, 2)
GEN_VEXT_VF(vfmacc_vf_w, 4)
GEN_VEXT_VF(vfmacc_vf_d, 8)
static uint16_t fnmacc16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@ -3311,15 +3323,15 @@ static uint64_t fnmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmacc_vv_h, OP_UUU_H, H2, H2, H2, fnmacc16)
RVVCALL(OPFVV3, vfnmacc_vv_w, OP_UUU_W, H4, H4, H4, fnmacc32)
RVVCALL(OPFVV3, vfnmacc_vv_d, OP_UUU_D, H8, H8, H8, fnmacc64)
GEN_VEXT_VV_ENV(vfnmacc_vv_h)
GEN_VEXT_VV_ENV(vfnmacc_vv_w)
GEN_VEXT_VV_ENV(vfnmacc_vv_d)
GEN_VEXT_VV_ENV(vfnmacc_vv_h, 2)
GEN_VEXT_VV_ENV(vfnmacc_vv_w, 4)
GEN_VEXT_VV_ENV(vfnmacc_vv_d, 8)
RVVCALL(OPFVF3, vfnmacc_vf_h, OP_UUU_H, H2, H2, fnmacc16)
RVVCALL(OPFVF3, vfnmacc_vf_w, OP_UUU_W, H4, H4, fnmacc32)
RVVCALL(OPFVF3, vfnmacc_vf_d, OP_UUU_D, H8, H8, fnmacc64)
GEN_VEXT_VF(vfnmacc_vf_h)
GEN_VEXT_VF(vfnmacc_vf_w)
GEN_VEXT_VF(vfnmacc_vf_d)
GEN_VEXT_VF(vfnmacc_vf_h, 2)
GEN_VEXT_VF(vfnmacc_vf_w, 4)
GEN_VEXT_VF(vfnmacc_vf_d, 8)
static uint16_t fmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@ -3339,15 +3351,15 @@ static uint64_t fmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmsac_vv_h, OP_UUU_H, H2, H2, H2, fmsac16)
RVVCALL(OPFVV3, vfmsac_vv_w, OP_UUU_W, H4, H4, H4, fmsac32)
RVVCALL(OPFVV3, vfmsac_vv_d, OP_UUU_D, H8, H8, H8, fmsac64)
GEN_VEXT_VV_ENV(vfmsac_vv_h)
GEN_VEXT_VV_ENV(vfmsac_vv_w)
GEN_VEXT_VV_ENV(vfmsac_vv_d)
GEN_VEXT_VV_ENV(vfmsac_vv_h, 2)
GEN_VEXT_VV_ENV(vfmsac_vv_w, 4)
GEN_VEXT_VV_ENV(vfmsac_vv_d, 8)
RVVCALL(OPFVF3, vfmsac_vf_h, OP_UUU_H, H2, H2, fmsac16)
RVVCALL(OPFVF3, vfmsac_vf_w, OP_UUU_W, H4, H4, fmsac32)
RVVCALL(OPFVF3, vfmsac_vf_d, OP_UUU_D, H8, H8, fmsac64)
GEN_VEXT_VF(vfmsac_vf_h)
GEN_VEXT_VF(vfmsac_vf_w)
GEN_VEXT_VF(vfmsac_vf_d)
GEN_VEXT_VF(vfmsac_vf_h, 2)
GEN_VEXT_VF(vfmsac_vf_w, 4)
GEN_VEXT_VF(vfmsac_vf_d, 8)
static uint16_t fnmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@ -3367,15 +3379,15 @@ static uint64_t fnmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmsac_vv_h, OP_UUU_H, H2, H2, H2, fnmsac16)
RVVCALL(OPFVV3, vfnmsac_vv_w, OP_UUU_W, H4, H4, H4, fnmsac32)
RVVCALL(OPFVV3, vfnmsac_vv_d, OP_UUU_D, H8, H8, H8, fnmsac64)
GEN_VEXT_VV_ENV(vfnmsac_vv_h)
GEN_VEXT_VV_ENV(vfnmsac_vv_w)
GEN_VEXT_VV_ENV(vfnmsac_vv_d)
GEN_VEXT_VV_ENV(vfnmsac_vv_h, 2)
GEN_VEXT_VV_ENV(vfnmsac_vv_w, 4)
GEN_VEXT_VV_ENV(vfnmsac_vv_d, 8)
RVVCALL(OPFVF3, vfnmsac_vf_h, OP_UUU_H, H2, H2, fnmsac16)
RVVCALL(OPFVF3, vfnmsac_vf_w, OP_UUU_W, H4, H4, fnmsac32)
RVVCALL(OPFVF3, vfnmsac_vf_d, OP_UUU_D, H8, H8, fnmsac64)
GEN_VEXT_VF(vfnmsac_vf_h)
GEN_VEXT_VF(vfnmsac_vf_w)
GEN_VEXT_VF(vfnmsac_vf_d)
GEN_VEXT_VF(vfnmsac_vf_h, 2)
GEN_VEXT_VF(vfnmsac_vf_w, 4)
GEN_VEXT_VF(vfnmsac_vf_d, 8)
static uint16_t fmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@ -3395,15 +3407,15 @@ static uint64_t fmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmadd_vv_h, OP_UUU_H, H2, H2, H2, fmadd16)
RVVCALL(OPFVV3, vfmadd_vv_w, OP_UUU_W, H4, H4, H4, fmadd32)
RVVCALL(OPFVV3, vfmadd_vv_d, OP_UUU_D, H8, H8, H8, fmadd64)
GEN_VEXT_VV_ENV(vfmadd_vv_h)
GEN_VEXT_VV_ENV(vfmadd_vv_w)
GEN_VEXT_VV_ENV(vfmadd_vv_d)
GEN_VEXT_VV_ENV(vfmadd_vv_h, 2)
GEN_VEXT_VV_ENV(vfmadd_vv_w, 4)
GEN_VEXT_VV_ENV(vfmadd_vv_d, 8)
RVVCALL(OPFVF3, vfmadd_vf_h, OP_UUU_H, H2, H2, fmadd16)
RVVCALL(OPFVF3, vfmadd_vf_w, OP_UUU_W, H4, H4, fmadd32)
RVVCALL(OPFVF3, vfmadd_vf_d, OP_UUU_D, H8, H8, fmadd64)
GEN_VEXT_VF(vfmadd_vf_h)
GEN_VEXT_VF(vfmadd_vf_w)
GEN_VEXT_VF(vfmadd_vf_d)
GEN_VEXT_VF(vfmadd_vf_h, 2)
GEN_VEXT_VF(vfmadd_vf_w, 4)
GEN_VEXT_VF(vfmadd_vf_d, 8)
static uint16_t fnmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@ -3426,15 +3438,15 @@ static uint64_t fnmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmadd_vv_h, OP_UUU_H, H2, H2, H2, fnmadd16)
RVVCALL(OPFVV3, vfnmadd_vv_w, OP_UUU_W, H4, H4, H4, fnmadd32)
RVVCALL(OPFVV3, vfnmadd_vv_d, OP_UUU_D, H8, H8, H8, fnmadd64)
GEN_VEXT_VV_ENV(vfnmadd_vv_h)
GEN_VEXT_VV_ENV(vfnmadd_vv_w)
GEN_VEXT_VV_ENV(vfnmadd_vv_d)
GEN_VEXT_VV_ENV(vfnmadd_vv_h, 2)
GEN_VEXT_VV_ENV(vfnmadd_vv_w, 4)
GEN_VEXT_VV_ENV(vfnmadd_vv_d, 8)
RVVCALL(OPFVF3, vfnmadd_vf_h, OP_UUU_H, H2, H2, fnmadd16)
RVVCALL(OPFVF3, vfnmadd_vf_w, OP_UUU_W, H4, H4, fnmadd32)
RVVCALL(OPFVF3, vfnmadd_vf_d, OP_UUU_D, H8, H8, fnmadd64)
GEN_VEXT_VF(vfnmadd_vf_h)
GEN_VEXT_VF(vfnmadd_vf_w)
GEN_VEXT_VF(vfnmadd_vf_d)
GEN_VEXT_VF(vfnmadd_vf_h, 2)
GEN_VEXT_VF(vfnmadd_vf_w, 4)
GEN_VEXT_VF(vfnmadd_vf_d, 8)
static uint16_t fmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@ -3454,15 +3466,15 @@ static uint64_t fmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfmsub_vv_h, OP_UUU_H, H2, H2, H2, fmsub16)
RVVCALL(OPFVV3, vfmsub_vv_w, OP_UUU_W, H4, H4, H4, fmsub32)
RVVCALL(OPFVV3, vfmsub_vv_d, OP_UUU_D, H8, H8, H8, fmsub64)
GEN_VEXT_VV_ENV(vfmsub_vv_h)
GEN_VEXT_VV_ENV(vfmsub_vv_w)
GEN_VEXT_VV_ENV(vfmsub_vv_d)
GEN_VEXT_VV_ENV(vfmsub_vv_h, 2)
GEN_VEXT_VV_ENV(vfmsub_vv_w, 4)
GEN_VEXT_VV_ENV(vfmsub_vv_d, 8)
RVVCALL(OPFVF3, vfmsub_vf_h, OP_UUU_H, H2, H2, fmsub16)
RVVCALL(OPFVF3, vfmsub_vf_w, OP_UUU_W, H4, H4, fmsub32)
RVVCALL(OPFVF3, vfmsub_vf_d, OP_UUU_D, H8, H8, fmsub64)
GEN_VEXT_VF(vfmsub_vf_h)
GEN_VEXT_VF(vfmsub_vf_w)
GEN_VEXT_VF(vfmsub_vf_d)
GEN_VEXT_VF(vfmsub_vf_h, 2)
GEN_VEXT_VF(vfmsub_vf_w, 4)
GEN_VEXT_VF(vfmsub_vf_d, 8)
static uint16_t fnmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
{
@ -3482,15 +3494,15 @@ static uint64_t fnmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfnmsub_vv_h, OP_UUU_H, H2, H2, H2, fnmsub16)
RVVCALL(OPFVV3, vfnmsub_vv_w, OP_UUU_W, H4, H4, H4, fnmsub32)
RVVCALL(OPFVV3, vfnmsub_vv_d, OP_UUU_D, H8, H8, H8, fnmsub64)
GEN_VEXT_VV_ENV(vfnmsub_vv_h)
GEN_VEXT_VV_ENV(vfnmsub_vv_w)
GEN_VEXT_VV_ENV(vfnmsub_vv_d)
GEN_VEXT_VV_ENV(vfnmsub_vv_h, 2)
GEN_VEXT_VV_ENV(vfnmsub_vv_w, 4)
GEN_VEXT_VV_ENV(vfnmsub_vv_d, 8)
RVVCALL(OPFVF3, vfnmsub_vf_h, OP_UUU_H, H2, H2, fnmsub16)
RVVCALL(OPFVF3, vfnmsub_vf_w, OP_UUU_W, H4, H4, fnmsub32)
RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64)
GEN_VEXT_VF(vfnmsub_vf_h)
GEN_VEXT_VF(vfnmsub_vf_w)
GEN_VEXT_VF(vfnmsub_vf_d)
GEN_VEXT_VF(vfnmsub_vf_h, 2)
GEN_VEXT_VF(vfnmsub_vf_w, 4)
GEN_VEXT_VF(vfnmsub_vf_d, 8)
/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
@ -3507,12 +3519,12 @@ static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16)
RVVCALL(OPFVV3, vfwmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwmacc32)
GEN_VEXT_VV_ENV(vfwmacc_vv_h)
GEN_VEXT_VV_ENV(vfwmacc_vv_w)
GEN_VEXT_VV_ENV(vfwmacc_vv_h, 4)
GEN_VEXT_VV_ENV(vfwmacc_vv_w, 8)
RVVCALL(OPFVF3, vfwmacc_vf_h, WOP_UUU_H, H4, H2, fwmacc16)
RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32)
GEN_VEXT_VF(vfwmacc_vf_h)
GEN_VEXT_VF(vfwmacc_vf_w)
GEN_VEXT_VF(vfwmacc_vf_h, 4)
GEN_VEXT_VF(vfwmacc_vf_w, 8)
static uint32_t fwnmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@ -3530,12 +3542,12 @@ static uint64_t fwnmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwnmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwnmacc16)
RVVCALL(OPFVV3, vfwnmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwnmacc32)
GEN_VEXT_VV_ENV(vfwnmacc_vv_h)
GEN_VEXT_VV_ENV(vfwnmacc_vv_w)
GEN_VEXT_VV_ENV(vfwnmacc_vv_h, 4)
GEN_VEXT_VV_ENV(vfwnmacc_vv_w, 8)
RVVCALL(OPFVF3, vfwnmacc_vf_h, WOP_UUU_H, H4, H2, fwnmacc16)
RVVCALL(OPFVF3, vfwnmacc_vf_w, WOP_UUU_W, H8, H4, fwnmacc32)
GEN_VEXT_VF(vfwnmacc_vf_h)
GEN_VEXT_VF(vfwnmacc_vf_w)
GEN_VEXT_VF(vfwnmacc_vf_h, 4)
GEN_VEXT_VF(vfwnmacc_vf_w, 8)
static uint32_t fwmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@ -3553,12 +3565,12 @@ static uint64_t fwmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwmsac16)
RVVCALL(OPFVV3, vfwmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwmsac32)
GEN_VEXT_VV_ENV(vfwmsac_vv_h)
GEN_VEXT_VV_ENV(vfwmsac_vv_w)
GEN_VEXT_VV_ENV(vfwmsac_vv_h, 4)
GEN_VEXT_VV_ENV(vfwmsac_vv_w, 8)
RVVCALL(OPFVF3, vfwmsac_vf_h, WOP_UUU_H, H4, H2, fwmsac16)
RVVCALL(OPFVF3, vfwmsac_vf_w, WOP_UUU_W, H8, H4, fwmsac32)
GEN_VEXT_VF(vfwmsac_vf_h)
GEN_VEXT_VF(vfwmsac_vf_w)
GEN_VEXT_VF(vfwmsac_vf_h, 4)
GEN_VEXT_VF(vfwmsac_vf_w, 8)
static uint32_t fwnmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
{
@ -3576,12 +3588,12 @@ static uint64_t fwnmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
RVVCALL(OPFVV3, vfwnmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwnmsac16)
RVVCALL(OPFVV3, vfwnmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwnmsac32)
GEN_VEXT_VV_ENV(vfwnmsac_vv_h)
GEN_VEXT_VV_ENV(vfwnmsac_vv_w)
GEN_VEXT_VV_ENV(vfwnmsac_vv_h, 4)
GEN_VEXT_VV_ENV(vfwnmsac_vv_w, 8)
RVVCALL(OPFVF3, vfwnmsac_vf_h, WOP_UUU_H, H4, H2, fwnmsac16)
RVVCALL(OPFVF3, vfwnmsac_vf_w, WOP_UUU_W, H8, H4, fwnmsac32)
GEN_VEXT_VF(vfwnmsac_vf_h)
GEN_VEXT_VF(vfwnmsac_vf_w)
GEN_VEXT_VF(vfwnmsac_vf_h, 4)
GEN_VEXT_VF(vfwnmsac_vf_w, 8)
/* Vector Floating-Point Square-Root Instruction */
/* (TD, T2, TX2) */
@ -3597,12 +3609,15 @@ static void do_##NAME(void *vd, void *vs2, int i, \
*((TD *)vd + HD(i)) = OP(s2, &env->fp_status); \
}
#define GEN_VEXT_V_ENV(NAME) \
#define GEN_VEXT_V_ENV(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint32_t total_elems = \
vext_get_total_elems(env, desc, ESZ); \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
if (vl == 0) { \
@ -3615,14 +3630,16 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
do_##NAME(vd, vs2, i, env); \
} \
env->vstart = 0; \
vext_set_elems_1s(vd, vta, vl * ESZ, \
total_elems * ESZ); \
}
RVVCALL(OPFVV1, vfsqrt_v_h, OP_UU_H, H2, H2, float16_sqrt)
RVVCALL(OPFVV1, vfsqrt_v_w, OP_UU_W, H4, H4, float32_sqrt)
RVVCALL(OPFVV1, vfsqrt_v_d, OP_UU_D, H8, H8, float64_sqrt)
GEN_VEXT_V_ENV(vfsqrt_v_h)
GEN_VEXT_V_ENV(vfsqrt_v_w)
GEN_VEXT_V_ENV(vfsqrt_v_d)
GEN_VEXT_V_ENV(vfsqrt_v_h, 2)
GEN_VEXT_V_ENV(vfsqrt_v_w, 4)
GEN_VEXT_V_ENV(vfsqrt_v_d, 8)
/*
* Vector Floating-Point Reciprocal Square-Root Estimate Instruction
@ -3802,9 +3819,9 @@ static float64 frsqrt7_d(float64 f, float_status *s)
RVVCALL(OPFVV1, vfrsqrt7_v_h, OP_UU_H, H2, H2, frsqrt7_h)
RVVCALL(OPFVV1, vfrsqrt7_v_w, OP_UU_W, H4, H4, frsqrt7_s)
RVVCALL(OPFVV1, vfrsqrt7_v_d, OP_UU_D, H8, H8, frsqrt7_d)
GEN_VEXT_V_ENV(vfrsqrt7_v_h)
GEN_VEXT_V_ENV(vfrsqrt7_v_w)
GEN_VEXT_V_ENV(vfrsqrt7_v_d)
GEN_VEXT_V_ENV(vfrsqrt7_v_h, 2)
GEN_VEXT_V_ENV(vfrsqrt7_v_w, 4)
GEN_VEXT_V_ENV(vfrsqrt7_v_d, 8)
/*
* Vector Floating-Point Reciprocal Estimate Instruction
@ -3993,36 +4010,36 @@ static float64 frec7_d(float64 f, float_status *s)
RVVCALL(OPFVV1, vfrec7_v_h, OP_UU_H, H2, H2, frec7_h)
RVVCALL(OPFVV1, vfrec7_v_w, OP_UU_W, H4, H4, frec7_s)
RVVCALL(OPFVV1, vfrec7_v_d, OP_UU_D, H8, H8, frec7_d)
GEN_VEXT_V_ENV(vfrec7_v_h)
GEN_VEXT_V_ENV(vfrec7_v_w)
GEN_VEXT_V_ENV(vfrec7_v_d)
GEN_VEXT_V_ENV(vfrec7_v_h, 2)
GEN_VEXT_V_ENV(vfrec7_v_w, 4)
GEN_VEXT_V_ENV(vfrec7_v_d, 8)
/* Vector Floating-Point MIN/MAX Instructions */
RVVCALL(OPFVV2, vfmin_vv_h, OP_UUU_H, H2, H2, H2, float16_minimum_number)
RVVCALL(OPFVV2, vfmin_vv_w, OP_UUU_W, H4, H4, H4, float32_minimum_number)
RVVCALL(OPFVV2, vfmin_vv_d, OP_UUU_D, H8, H8, H8, float64_minimum_number)
GEN_VEXT_VV_ENV(vfmin_vv_h)
GEN_VEXT_VV_ENV(vfmin_vv_w)
GEN_VEXT_VV_ENV(vfmin_vv_d)
GEN_VEXT_VV_ENV(vfmin_vv_h, 2)
GEN_VEXT_VV_ENV(vfmin_vv_w, 4)
GEN_VEXT_VV_ENV(vfmin_vv_d, 8)
RVVCALL(OPFVF2, vfmin_vf_h, OP_UUU_H, H2, H2, float16_minimum_number)
RVVCALL(OPFVF2, vfmin_vf_w, OP_UUU_W, H4, H4, float32_minimum_number)
RVVCALL(OPFVF2, vfmin_vf_d, OP_UUU_D, H8, H8, float64_minimum_number)
GEN_VEXT_VF(vfmin_vf_h)
GEN_VEXT_VF(vfmin_vf_w)
GEN_VEXT_VF(vfmin_vf_d)
GEN_VEXT_VF(vfmin_vf_h, 2)
GEN_VEXT_VF(vfmin_vf_w, 4)
GEN_VEXT_VF(vfmin_vf_d, 8)
RVVCALL(OPFVV2, vfmax_vv_h, OP_UUU_H, H2, H2, H2, float16_maximum_number)
RVVCALL(OPFVV2, vfmax_vv_w, OP_UUU_W, H4, H4, H4, float32_maximum_number)
RVVCALL(OPFVV2, vfmax_vv_d, OP_UUU_D, H8, H8, H8, float64_maximum_number)
GEN_VEXT_VV_ENV(vfmax_vv_h)
GEN_VEXT_VV_ENV(vfmax_vv_w)
GEN_VEXT_VV_ENV(vfmax_vv_d)
GEN_VEXT_VV_ENV(vfmax_vv_h, 2)
GEN_VEXT_VV_ENV(vfmax_vv_w, 4)
GEN_VEXT_VV_ENV(vfmax_vv_d, 8)
RVVCALL(OPFVF2, vfmax_vf_h, OP_UUU_H, H2, H2, float16_maximum_number)
RVVCALL(OPFVF2, vfmax_vf_w, OP_UUU_W, H4, H4, float32_maximum_number)
RVVCALL(OPFVF2, vfmax_vf_d, OP_UUU_D, H8, H8, float64_maximum_number)
GEN_VEXT_VF(vfmax_vf_h)
GEN_VEXT_VF(vfmax_vf_w)
GEN_VEXT_VF(vfmax_vf_d)
GEN_VEXT_VF(vfmax_vf_h, 2)
GEN_VEXT_VF(vfmax_vf_w, 4)
GEN_VEXT_VF(vfmax_vf_d, 8)
/* Vector Floating-Point Sign-Injection Instructions */
static uint16_t fsgnj16(uint16_t a, uint16_t b, float_status *s)
@ -4043,15 +4060,15 @@ static uint64_t fsgnj64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnj_vv_h, OP_UUU_H, H2, H2, H2, fsgnj16)
RVVCALL(OPFVV2, vfsgnj_vv_w, OP_UUU_W, H4, H4, H4, fsgnj32)
RVVCALL(OPFVV2, vfsgnj_vv_d, OP_UUU_D, H8, H8, H8, fsgnj64)
GEN_VEXT_VV_ENV(vfsgnj_vv_h)
GEN_VEXT_VV_ENV(vfsgnj_vv_w)
GEN_VEXT_VV_ENV(vfsgnj_vv_d)
GEN_VEXT_VV_ENV(vfsgnj_vv_h, 2)
GEN_VEXT_VV_ENV(vfsgnj_vv_w, 4)
GEN_VEXT_VV_ENV(vfsgnj_vv_d, 8)
RVVCALL(OPFVF2, vfsgnj_vf_h, OP_UUU_H, H2, H2, fsgnj16)
RVVCALL(OPFVF2, vfsgnj_vf_w, OP_UUU_W, H4, H4, fsgnj32)
RVVCALL(OPFVF2, vfsgnj_vf_d, OP_UUU_D, H8, H8, fsgnj64)
GEN_VEXT_VF(vfsgnj_vf_h)
GEN_VEXT_VF(vfsgnj_vf_w)
GEN_VEXT_VF(vfsgnj_vf_d)
GEN_VEXT_VF(vfsgnj_vf_h, 2)
GEN_VEXT_VF(vfsgnj_vf_w, 4)
GEN_VEXT_VF(vfsgnj_vf_d, 8)
static uint16_t fsgnjn16(uint16_t a, uint16_t b, float_status *s)
{
@ -4071,15 +4088,15 @@ static uint64_t fsgnjn64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnjn_vv_h, OP_UUU_H, H2, H2, H2, fsgnjn16)
RVVCALL(OPFVV2, vfsgnjn_vv_w, OP_UUU_W, H4, H4, H4, fsgnjn32)
RVVCALL(OPFVV2, vfsgnjn_vv_d, OP_UUU_D, H8, H8, H8, fsgnjn64)
GEN_VEXT_VV_ENV(vfsgnjn_vv_h)
GEN_VEXT_VV_ENV(vfsgnjn_vv_w)
GEN_VEXT_VV_ENV(vfsgnjn_vv_d)
GEN_VEXT_VV_ENV(vfsgnjn_vv_h, 2)
GEN_VEXT_VV_ENV(vfsgnjn_vv_w, 4)
GEN_VEXT_VV_ENV(vfsgnjn_vv_d, 8)
RVVCALL(OPFVF2, vfsgnjn_vf_h, OP_UUU_H, H2, H2, fsgnjn16)
RVVCALL(OPFVF2, vfsgnjn_vf_w, OP_UUU_W, H4, H4, fsgnjn32)
RVVCALL(OPFVF2, vfsgnjn_vf_d, OP_UUU_D, H8, H8, fsgnjn64)
GEN_VEXT_VF(vfsgnjn_vf_h)
GEN_VEXT_VF(vfsgnjn_vf_w)
GEN_VEXT_VF(vfsgnjn_vf_d)
GEN_VEXT_VF(vfsgnjn_vf_h, 2)
GEN_VEXT_VF(vfsgnjn_vf_w, 4)
GEN_VEXT_VF(vfsgnjn_vf_d, 8)
static uint16_t fsgnjx16(uint16_t a, uint16_t b, float_status *s)
{
@ -4099,15 +4116,15 @@ static uint64_t fsgnjx64(uint64_t a, uint64_t b, float_status *s)
RVVCALL(OPFVV2, vfsgnjx_vv_h, OP_UUU_H, H2, H2, H2, fsgnjx16)
RVVCALL(OPFVV2, vfsgnjx_vv_w, OP_UUU_W, H4, H4, H4, fsgnjx32)
RVVCALL(OPFVV2, vfsgnjx_vv_d, OP_UUU_D, H8, H8, H8, fsgnjx64)
GEN_VEXT_VV_ENV(vfsgnjx_vv_h)
GEN_VEXT_VV_ENV(vfsgnjx_vv_w)
GEN_VEXT_VV_ENV(vfsgnjx_vv_d)
GEN_VEXT_VV_ENV(vfsgnjx_vv_h, 2)
GEN_VEXT_VV_ENV(vfsgnjx_vv_w, 4)
GEN_VEXT_VV_ENV(vfsgnjx_vv_d, 8)
RVVCALL(OPFVF2, vfsgnjx_vf_h, OP_UUU_H, H2, H2, fsgnjx16)
RVVCALL(OPFVF2, vfsgnjx_vf_w, OP_UUU_W, H4, H4, fsgnjx32)
RVVCALL(OPFVF2, vfsgnjx_vf_d, OP_UUU_D, H8, H8, fsgnjx64)
GEN_VEXT_VF(vfsgnjx_vf_h)
GEN_VEXT_VF(vfsgnjx_vf_w)
GEN_VEXT_VF(vfsgnjx_vf_d)
GEN_VEXT_VF(vfsgnjx_vf_h, 2)
GEN_VEXT_VF(vfsgnjx_vf_w, 4)
GEN_VEXT_VF(vfsgnjx_vf_d, 8)
/* Vector Floating-Point Compare Instructions */
#define GEN_VEXT_CMP_VV_ENV(NAME, ETYPE, H, DO_OP) \
@ -4116,6 +4133,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@ -4128,6 +4147,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
DO_OP(s2, s1, &env->fp_status)); \
} \
env->vstart = 0; \
/* mask destination register are always tail-agnostic */ \
/* set tail elements to 1s */ \
if (vta_all_1s) { \
for (; i < total_elems; i++) { \
vext_set_elem_mask(vd, i, 1); \
} \
} \
}
GEN_VEXT_CMP_VV_ENV(vmfeq_vv_h, uint16_t, H2, float16_eq_quiet)
@ -4140,6 +4166,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint32_t total_elems = env_archcpu(env)->cfg.vlen; \
uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@ -4151,6 +4179,13 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
DO_OP(s2, (ETYPE)s1, &env->fp_status)); \
} \
env->vstart = 0; \
/* mask destination register are always tail-agnostic */ \
/* set tail elements to 1s */ \
if (vta_all_1s) { \
for (; i < total_elems; i++) { \
vext_set_elem_mask(vd, i, 1); \
} \
} \
}
GEN_VEXT_CMP_VF(vmfeq_vf_h, uint16_t, H2, float16_eq_quiet)
@ -4251,12 +4286,15 @@ static void do_##NAME(void *vd, void *vs2, int i) \
*((TD *)vd + HD(i)) = OP(s2); \
}
#define GEN_VEXT_V(NAME) \
#define GEN_VEXT_V(NAME, ESZ) \
void HELPER(NAME)(void *vd, void *v0, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint32_t total_elems = \
vext_get_total_elems(env, desc, ESZ); \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@ -4266,6 +4304,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
do_##NAME(vd, vs2, i); \
} \
env->vstart = 0; \
/* set tail elements to 1s */ \
vext_set_elems_1s(vd, vta, vl * ESZ, \
total_elems * ESZ); \
}
target_ulong fclass_h(uint64_t frs1)
@ -4328,17 +4369,22 @@ target_ulong fclass_d(uint64_t frs1)
RVVCALL(OPIVV1, vfclass_v_h, OP_UU_H, H2, H2, fclass_h)
RVVCALL(OPIVV1, vfclass_v_w, OP_UU_W, H4, H4, fclass_s)
RVVCALL(OPIVV1, vfclass_v_d, OP_UU_D, H8, H8, fclass_d)
GEN_VEXT_V(vfclass_v_h)
GEN_VEXT_V(vfclass_v_w)
GEN_VEXT_V(vfclass_v_d)
GEN_VEXT_V(vfclass_v_h, 2)
GEN_VEXT_V(vfclass_v_w, 4)
GEN_VEXT_V(vfclass_v_d, 8)
/* Vector Floating-Point Merge Instruction */
#define GEN_VFMERGE_VF(NAME, ETYPE, H) \
void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint32_t esz = sizeof(ETYPE); \
uint32_t total_elems = \
vext_get_total_elems(env, desc, esz); \
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
for (i = env->vstart; i < vl; i++) { \
@ -4347,6 +4393,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
= (!vm && !vext_elem_mask(v0, i) ? s2 : s1); \
} \
env->vstart = 0; \
/* set tail elements to 1s */ \
vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
GEN_VFMERGE_VF(vfmerge_vfm_h, int16_t, H2)
@ -4358,33 +4406,33 @@ GEN_VFMERGE_VF(vfmerge_vfm_d, int64_t, H8)
RVVCALL(OPFVV1, vfcvt_xu_f_v_h, OP_UU_H, H2, H2, float16_to_uint16)
RVVCALL(OPFVV1, vfcvt_xu_f_v_w, OP_UU_W, H4, H4, float32_to_uint32)
RVVCALL(OPFVV1, vfcvt_xu_f_v_d, OP_UU_D, H8, H8, float64_to_uint64)
GEN_VEXT_V_ENV(vfcvt_xu_f_v_h)
GEN_VEXT_V_ENV(vfcvt_xu_f_v_w)
GEN_VEXT_V_ENV(vfcvt_xu_f_v_d)
GEN_VEXT_V_ENV(vfcvt_xu_f_v_h, 2)
GEN_VEXT_V_ENV(vfcvt_xu_f_v_w, 4)
GEN_VEXT_V_ENV(vfcvt_xu_f_v_d, 8)
/* vfcvt.x.f.v vd, vs2, vm # Convert float to signed integer. */
RVVCALL(OPFVV1, vfcvt_x_f_v_h, OP_UU_H, H2, H2, float16_to_int16)
RVVCALL(OPFVV1, vfcvt_x_f_v_w, OP_UU_W, H4, H4, float32_to_int32)
RVVCALL(OPFVV1, vfcvt_x_f_v_d, OP_UU_D, H8, H8, float64_to_int64)
GEN_VEXT_V_ENV(vfcvt_x_f_v_h)
GEN_VEXT_V_ENV(vfcvt_x_f_v_w)
GEN_VEXT_V_ENV(vfcvt_x_f_v_d)
GEN_VEXT_V_ENV(vfcvt_x_f_v_h, 2)
GEN_VEXT_V_ENV(vfcvt_x_f_v_w, 4)
GEN_VEXT_V_ENV(vfcvt_x_f_v_d, 8)
/* vfcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to float. */
RVVCALL(OPFVV1, vfcvt_f_xu_v_h, OP_UU_H, H2, H2, uint16_to_float16)
RVVCALL(OPFVV1, vfcvt_f_xu_v_w, OP_UU_W, H4, H4, uint32_to_float32)
RVVCALL(OPFVV1, vfcvt_f_xu_v_d, OP_UU_D, H8, H8, uint64_to_float64)
GEN_VEXT_V_ENV(vfcvt_f_xu_v_h)
GEN_VEXT_V_ENV(vfcvt_f_xu_v_w)
GEN_VEXT_V_ENV(vfcvt_f_xu_v_d)
GEN_VEXT_V_ENV(vfcvt_f_xu_v_h, 2)
GEN_VEXT_V_ENV(vfcvt_f_xu_v_w, 4)
GEN_VEXT_V_ENV(vfcvt_f_xu_v_d, 8)
/* vfcvt.f.x.v vd, vs2, vm # Convert integer to float. */
RVVCALL(OPFVV1, vfcvt_f_x_v_h, OP_UU_H, H2, H2, int16_to_float16)
RVVCALL(OPFVV1, vfcvt_f_x_v_w, OP_UU_W, H4, H4, int32_to_float32)
RVVCALL(OPFVV1, vfcvt_f_x_v_d, OP_UU_D, H8, H8, int64_to_float64)
GEN_VEXT_V_ENV(vfcvt_f_x_v_h)
GEN_VEXT_V_ENV(vfcvt_f_x_v_w)
GEN_VEXT_V_ENV(vfcvt_f_x_v_d)
GEN_VEXT_V_ENV(vfcvt_f_x_v_h, 2)
GEN_VEXT_V_ENV(vfcvt_f_x_v_w, 4)
GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8)
/* Widening Floating-Point/Integer Type-Convert Instructions */
/* (TD, T2, TX2) */
@ -4394,30 +4442,30 @@ GEN_VEXT_V_ENV(vfcvt_f_x_v_d)
/* vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned integer.*/
RVVCALL(OPFVV1, vfwcvt_xu_f_v_h, WOP_UU_H, H4, H2, float16_to_uint32)
RVVCALL(OPFVV1, vfwcvt_xu_f_v_w, WOP_UU_W, H8, H4, float32_to_uint64)
GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h)
GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w)
GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h, 4)
GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w, 8)
/* vfwcvt.x.f.v vd, vs2, vm # Convert float to double-width signed integer. */
RVVCALL(OPFVV1, vfwcvt_x_f_v_h, WOP_UU_H, H4, H2, float16_to_int32)
RVVCALL(OPFVV1, vfwcvt_x_f_v_w, WOP_UU_W, H8, H4, float32_to_int64)
GEN_VEXT_V_ENV(vfwcvt_x_f_v_h)
GEN_VEXT_V_ENV(vfwcvt_x_f_v_w)
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 */
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)
GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b)
GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h)
GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w)
GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b, 2)
GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h, 4)
GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w, 8)
/* vfwcvt.f.x.v vd, vs2, vm # Convert integer to double-width float. */
RVVCALL(OPFVV1, vfwcvt_f_x_v_b, WOP_UU_B, H2, H1, int8_to_float16)
RVVCALL(OPFVV1, vfwcvt_f_x_v_h, WOP_UU_H, H4, H2, int16_to_float32)
RVVCALL(OPFVV1, vfwcvt_f_x_v_w, WOP_UU_W, H8, H4, int32_to_float64)
GEN_VEXT_V_ENV(vfwcvt_f_x_v_b)
GEN_VEXT_V_ENV(vfwcvt_f_x_v_h)
GEN_VEXT_V_ENV(vfwcvt_f_x_v_w)
GEN_VEXT_V_ENV(vfwcvt_f_x_v_b, 2)
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
@ -4430,8 +4478,8 @@ static uint32_t vfwcvtffv16(uint16_t a, float_status *s)
RVVCALL(OPFVV1, vfwcvt_f_f_v_h, WOP_UU_H, H4, H2, vfwcvtffv16)
RVVCALL(OPFVV1, vfwcvt_f_f_v_w, WOP_UU_W, H8, H4, float32_to_float64)
GEN_VEXT_V_ENV(vfwcvt_f_f_v_h)
GEN_VEXT_V_ENV(vfwcvt_f_f_v_w)
GEN_VEXT_V_ENV(vfwcvt_f_f_v_h, 4)
GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 8)
/* Narrowing Floating-Point/Integer Type-Convert Instructions */
/* (TD, T2, TX2) */
@ -4442,29 +4490,29 @@ GEN_VEXT_V_ENV(vfwcvt_f_f_v_w)
RVVCALL(OPFVV1, vfncvt_xu_f_w_b, NOP_UU_B, H1, H2, float16_to_uint8)
RVVCALL(OPFVV1, vfncvt_xu_f_w_h, NOP_UU_H, H2, H4, float32_to_uint16)
RVVCALL(OPFVV1, vfncvt_xu_f_w_w, NOP_UU_W, H4, H8, float64_to_uint32)
GEN_VEXT_V_ENV(vfncvt_xu_f_w_b)
GEN_VEXT_V_ENV(vfncvt_xu_f_w_h)
GEN_VEXT_V_ENV(vfncvt_xu_f_w_w)
GEN_VEXT_V_ENV(vfncvt_xu_f_w_b, 1)
GEN_VEXT_V_ENV(vfncvt_xu_f_w_h, 2)
GEN_VEXT_V_ENV(vfncvt_xu_f_w_w, 4)
/* vfncvt.x.f.v vd, vs2, vm # Convert double-width float to signed integer. */
RVVCALL(OPFVV1, vfncvt_x_f_w_b, NOP_UU_B, H1, H2, float16_to_int8)
RVVCALL(OPFVV1, vfncvt_x_f_w_h, NOP_UU_H, H2, H4, float32_to_int16)
RVVCALL(OPFVV1, vfncvt_x_f_w_w, NOP_UU_W, H4, H8, float64_to_int32)
GEN_VEXT_V_ENV(vfncvt_x_f_w_b)
GEN_VEXT_V_ENV(vfncvt_x_f_w_h)
GEN_VEXT_V_ENV(vfncvt_x_f_w_w)
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 */
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)
GEN_VEXT_V_ENV(vfncvt_f_xu_w_w)
GEN_VEXT_V_ENV(vfncvt_f_xu_w_h, 2)
GEN_VEXT_V_ENV(vfncvt_f_xu_w_w, 4)
/* vfncvt.f.x.v vd, vs2, vm # Convert double-width integer to float. */
RVVCALL(OPFVV1, vfncvt_f_x_w_h, NOP_UU_H, H2, H4, int32_to_float16)
RVVCALL(OPFVV1, vfncvt_f_x_w_w, NOP_UU_W, H4, H8, int64_to_float32)
GEN_VEXT_V_ENV(vfncvt_f_x_w_h)
GEN_VEXT_V_ENV(vfncvt_f_x_w_w)
GEN_VEXT_V_ENV(vfncvt_f_x_w_h, 2)
GEN_VEXT_V_ENV(vfncvt_f_x_w_w, 4)
/* vfncvt.f.f.v vd, vs2, vm # Convert double float to single-width float. */
static uint16_t vfncvtffv16(uint32_t a, float_status *s)
@ -4474,8 +4522,8 @@ static uint16_t vfncvtffv16(uint32_t a, float_status *s)
RVVCALL(OPFVV1, vfncvt_f_f_w_h, NOP_UU_H, H2, H4, vfncvtffv16)
RVVCALL(OPFVV1, vfncvt_f_f_w_w, NOP_UU_W, H4, H8, float64_to_float32)
GEN_VEXT_V_ENV(vfncvt_f_f_w_h)
GEN_VEXT_V_ENV(vfncvt_f_f_w_w)
GEN_VEXT_V_ENV(vfncvt_f_f_w_h, 2)
GEN_VEXT_V_ENV(vfncvt_f_f_w_w, 4)
/*
*** Vector Reduction Operations