diff options
Diffstat (limited to 'target-arm/helper-a64.c')
-rw-r--r-- | target-arm/helper-a64.c | 105 |
1 files changed, 105 insertions, 0 deletions
diff --git a/target-arm/helper-a64.c b/target-arm/helper-a64.c index 6ca958afb1..c2ce33ee88 100644 --- a/target-arm/helper-a64.c +++ b/target-arm/helper-a64.c @@ -123,6 +123,32 @@ uint64_t HELPER(vfp_cmped_a64)(float64 x, float64 y, void *fp_status) return float_rel_to_flags(float64_compare(x, y, fp_status)); } +float32 HELPER(vfp_mulxs)(float32 a, float32 b, void *fpstp) +{ + float_status *fpst = fpstp; + + if ((float32_is_zero(a) && float32_is_infinity(b)) || + (float32_is_infinity(a) && float32_is_zero(b))) { + /* 2.0 with the sign bit set to sign(A) XOR sign(B) */ + return make_float32((1U << 30) | + ((float32_val(a) ^ float32_val(b)) & (1U << 31))); + } + return float32_mul(a, b, fpst); +} + +float64 HELPER(vfp_mulxd)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + + if ((float64_is_zero(a) && float64_is_infinity(b)) || + (float64_is_infinity(a) && float64_is_zero(b))) { + /* 2.0 with the sign bit set to sign(A) XOR sign(B) */ + return make_float64((1ULL << 62) | + ((float64_val(a) ^ float64_val(b)) & (1ULL << 63))); + } + return float64_mul(a, b, fpst); +} + uint64_t HELPER(simd_tbl)(CPUARMState *env, uint64_t result, uint64_t indices, uint32_t rn, uint32_t numregs) { @@ -153,3 +179,82 @@ uint64_t HELPER(simd_tbl)(CPUARMState *env, uint64_t result, uint64_t indices, } return result; } + +/* 64bit/double versions of the neon float compare functions */ +uint64_t HELPER(neon_ceq_f64)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + return -float64_eq_quiet(a, b, fpst); +} + +uint64_t HELPER(neon_cge_f64)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + return -float64_le(b, a, fpst); +} + +uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + return -float64_lt(b, a, fpst); +} + +/* Reciprocal step and sqrt step. Note that unlike the A32/T32 + * versions, these do a fully fused multiply-add or + * multiply-add-and-halve. + */ +#define float32_two make_float32(0x40000000) +#define float32_three make_float32(0x40400000) +#define float32_one_point_five make_float32(0x3fc00000) + +#define float64_two make_float64(0x4000000000000000ULL) +#define float64_three make_float64(0x4008000000000000ULL) +#define float64_one_point_five make_float64(0x3FF8000000000000ULL) + +float32 HELPER(recpsf_f32)(float32 a, float32 b, void *fpstp) +{ + float_status *fpst = fpstp; + + a = float32_chs(a); + if ((float32_is_infinity(a) && float32_is_zero(b)) || + (float32_is_infinity(b) && float32_is_zero(a))) { + return float32_two; + } + return float32_muladd(a, b, float32_two, 0, fpst); +} + +float64 HELPER(recpsf_f64)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + + a = float64_chs(a); + if ((float64_is_infinity(a) && float64_is_zero(b)) || + (float64_is_infinity(b) && float64_is_zero(a))) { + return float64_two; + } + return float64_muladd(a, b, float64_two, 0, fpst); +} + +float32 HELPER(rsqrtsf_f32)(float32 a, float32 b, void *fpstp) +{ + float_status *fpst = fpstp; + + a = float32_chs(a); + if ((float32_is_infinity(a) && float32_is_zero(b)) || + (float32_is_infinity(b) && float32_is_zero(a))) { + return float32_one_point_five; + } + return float32_muladd(a, b, float32_three, float_muladd_halve_result, fpst); +} + +float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, void *fpstp) +{ + float_status *fpst = fpstp; + + a = float64_chs(a); + if ((float64_is_infinity(a) && float64_is_zero(b)) || + (float64_is_infinity(b) && float64_is_zero(a))) { + return float64_one_point_five; + } + return float64_muladd(a, b, float64_three, float_muladd_halve_result, fpst); +} |