diff options
| author | Alex Bennée <alex.bennee@linaro.org> | 2018-03-01 11:05:50 +0000 |
|---|---|---|
| committer | Peter Maydell <peter.maydell@linaro.org> | 2018-03-01 11:13:59 +0000 |
| commit | 026e2d6ef74000afb9049f46add4b94f594c8fb3 (patch) | |
| tree | 903870de4c316d26e09d09622923970c7703c503 /target/arm/helper-a64.c | |
| parent | 2deb992b767d28035fac3b374c7730494ff0b43d (diff) | |
arm/translate-a64: add FP16 FR[ECP/SQRT]S to simd_three_reg_same_fp16
As some of the constants here will also be needed
elsewhere (specifically for the upcoming SVE support) we move them out
to softfloat.h.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20180227143852.11175-13-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Diffstat (limited to 'target/arm/helper-a64.c')
| -rw-r--r-- | target/arm/helper-a64.c | 34 |
1 files changed, 34 insertions, 0 deletions
diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index 1ef13abd76..8fdbe034f3 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -192,6 +192,10 @@ uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp) * versions, these do a fully fused multiply-add or * multiply-add-and-halve. */ +#define float16_two make_float16(0x4000) +#define float16_three make_float16(0x4200) +#define float16_one_point_five make_float16(0x3e00) + #define float32_two make_float32(0x40000000) #define float32_three make_float32(0x40400000) #define float32_one_point_five make_float32(0x3fc00000) @@ -200,6 +204,21 @@ uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp) #define float64_three make_float64(0x4008000000000000ULL) #define float64_one_point_five make_float64(0x3FF8000000000000ULL) +float16 HELPER(recpsf_f16)(float16 a, float16 b, void *fpstp) +{ + float_status *fpst = fpstp; + + a = float16_squash_input_denormal(a, fpst); + b = float16_squash_input_denormal(b, fpst); + + a = float16_chs(a); + if ((float16_is_infinity(a) && float16_is_zero(b)) || + (float16_is_infinity(b) && float16_is_zero(a))) { + return float16_two; + } + return float16_muladd(a, b, float16_two, 0, fpst); +} + float32 HELPER(recpsf_f32)(float32 a, float32 b, void *fpstp) { float_status *fpst = fpstp; @@ -230,6 +249,21 @@ float64 HELPER(recpsf_f64)(float64 a, float64 b, void *fpstp) return float64_muladd(a, b, float64_two, 0, fpst); } +float16 HELPER(rsqrtsf_f16)(float16 a, float16 b, void *fpstp) +{ + float_status *fpst = fpstp; + + a = float16_squash_input_denormal(a, fpst); + b = float16_squash_input_denormal(b, fpst); + + a = float16_chs(a); + if ((float16_is_infinity(a) && float16_is_zero(b)) || + (float16_is_infinity(b) && float16_is_zero(a))) { + return float16_one_point_five; + } + return float16_muladd(a, b, float16_three, float_muladd_halve_result, fpst); +} + float32 HELPER(rsqrtsf_f32)(float32 a, float32 b, void *fpstp) { float_status *fpst = fpstp; |