diff options
Diffstat (limited to 'target/arm/vec_helper.c')
| -rw-r--r-- | target/arm/vec_helper.c | 30 |
1 files changed, 30 insertions, 0 deletions
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index 0111a23..e5bb5e3 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -825,6 +825,33 @@ static float32 float32_recps_nf(float32 op1, float32 op2, float_status *stat) return float32_sub(float32_two, float32_mul(op1, op2, stat), stat); } +/* Reciprocal square-root step. AArch32 non-fused semantics. */ +static float16 float16_rsqrts_nf(float16 op1, float16 op2, float_status *stat) +{ + op1 = float16_squash_input_denormal(op1, stat); + op2 = float16_squash_input_denormal(op2, stat); + + if ((float16_is_infinity(op1) && float16_is_zero(op2)) || + (float16_is_infinity(op2) && float16_is_zero(op1))) { + return float16_one_point_five; + } + op1 = float16_sub(float16_three, float16_mul(op1, op2, stat), stat); + return float16_div(op1, float16_two, stat); +} + +static float32 float32_rsqrts_nf(float32 op1, float32 op2, float_status *stat) +{ + op1 = float32_squash_input_denormal(op1, stat); + op2 = float32_squash_input_denormal(op2, stat); + + if ((float32_is_infinity(op1) && float32_is_zero(op2)) || + (float32_is_infinity(op2) && float32_is_zero(op1))) { + return float32_one_point_five; + } + op1 = float32_sub(float32_three, float32_mul(op1, op2, stat), stat); + return float32_div(op1, float32_two, stat); +} + #define DO_3OP(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ @@ -885,6 +912,9 @@ DO_3OP(gvec_fminnum_s, float32_minnum, float32) DO_3OP(gvec_recps_nf_h, float16_recps_nf, float16) DO_3OP(gvec_recps_nf_s, float32_recps_nf, float32) +DO_3OP(gvec_rsqrts_nf_h, float16_rsqrts_nf, float16) +DO_3OP(gvec_rsqrts_nf_s, float32_rsqrts_nf, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) |