diff options
| -rw-r--r-- | target-ppc/helper.h | 2 | ||||
| -rw-r--r-- | target-ppc/op_helper.c | 37 | ||||
| -rw-r--r-- | target-ppc/translate.c | 1 |
3 files changed, 40 insertions, 0 deletions
diff --git a/target-ppc/helper.h b/target-ppc/helper.h index 43d1867d2a..af6c8396c0 100644 --- a/target-ppc/helper.h +++ b/target-ppc/helper.h @@ -236,6 +236,8 @@ DEF_HELPER_3(vaddfp, void, avr, avr, avr) DEF_HELPER_3(vsubfp, void, avr, avr, avr) DEF_HELPER_3(vmaxfp, void, avr, avr, avr) DEF_HELPER_3(vminfp, void, avr, avr, avr) +DEF_HELPER_4(vmaddfp, void, avr, avr, avr, avr) +DEF_HELPER_4(vnmsubfp, void, avr, avr, avr, avr) DEF_HELPER_2(vlogefp, void, avr, avr) DEF_HELPER_2(vrfim, void, avr, avr) DEF_HELPER_2(vrfin, void, avr, avr) diff --git a/target-ppc/op_helper.c b/target-ppc/op_helper.c index 6cf47a3576..f59cd15cf6 100644 --- a/target-ppc/op_helper.c +++ b/target-ppc/op_helper.c @@ -2220,6 +2220,24 @@ VCMP(gtsw, >, s32) #undef VCMP_DO #undef VCMP +void helper_vmaddfp (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) +{ + int i; + for (i = 0; i < ARRAY_SIZE(r->f); i++) { + HANDLE_NAN3(r->f[i], a->f[i], b->f[i], c->f[i]) { + /* Need to do the computation in higher precision and round + * once at the end. */ + float64 af, bf, cf, t; + af = float32_to_float64(a->f[i], &env->vec_status); + bf = float32_to_float64(b->f[i], &env->vec_status); + cf = float32_to_float64(c->f[i], &env->vec_status); + t = float64_mul(af, cf, &env->vec_status); + t = float64_add(t, bf, &env->vec_status); + r->f[i] = float64_to_float32(t, &env->vec_status); + } + } +} + void helper_vmhaddshs (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) { int sat = 0; @@ -2456,6 +2474,25 @@ VMUL(uh, u16, u32) #undef VMUL_DO #undef VMUL +void helper_vnmsubfp (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) +{ + int i; + for (i = 0; i < ARRAY_SIZE(r->f); i++) { + HANDLE_NAN3(r->f[i], a->f[i], b->f[i], c->f[i]) { + /* Need to do the computation is higher precision and round + * once at the end. */ + float64 af, bf, cf, t; + af = float32_to_float64(a->f[i], &env->vec_status); + bf = float32_to_float64(b->f[i], &env->vec_status); + cf = float32_to_float64(c->f[i], &env->vec_status); + t = float64_mul(af, cf, &env->vec_status); + t = float64_sub(t, bf, &env->vec_status); + t = float64_chs(t); + r->f[i] = float64_to_float32(t, &env->vec_status); + } + } +} + void helper_vperm (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) { ppc_avr_t result; diff --git a/target-ppc/translate.c b/target-ppc/translate.c index af83b198ef..88426af946 100644 --- a/target-ppc/translate.c +++ b/target-ppc/translate.c @@ -6584,6 +6584,7 @@ GEN_VAFORM_PAIRED(vmsumubm, vmsummbm, 18) GEN_VAFORM_PAIRED(vmsumuhm, vmsumuhs, 19) GEN_VAFORM_PAIRED(vmsumshm, vmsumshs, 20) GEN_VAFORM_PAIRED(vsel, vperm, 21) +GEN_VAFORM_PAIRED(vmaddfp, vnmsubfp, 23) /*** SPE extension ***/ /* Register moves */ |