Message ID | 20241208224844.570491-12-richard.henderson@linaro.org |
---|---|
State | Superseded |
Headers | show |
Series | softfloat, hexagon: Cleanup fmaf | expand |
On 12/8/2024 4:48 PM, Richard Henderson wrote: > There are multiple special cases for this instruction. > (1) The saturate to normal maximum instead of overflow to infinity is > handled by the new float_round_nearest_even_max rounding mode. > (2) The 0 * n + c special case is handled by the new > float_muladd_suppress_add_product_zero flag. > (3) The Inf - Inf -> 0 special case can be detected after the fact > by examining float_flag_invalid_isi. > > Signed-off-by: Richard Henderson <richard.henderson@linaro.org> > --- > target/hexagon/op_helper.c | 105 +++++++++---------------------------- > 1 file changed, 26 insertions(+), 79 deletions(-) > > diff --git a/target/hexagon/op_helper.c b/target/hexagon/op_helper.c > index eb010422bf..26e329f7b9 100644 > --- a/target/hexagon/op_helper.c > +++ b/target/hexagon/op_helper.c > @@ -1171,24 +1171,6 @@ float32 HELPER(sffma)(CPUHexagonState *env, float32 RxV, > return RxV; > } > > -static bool is_zero_prod(float32 a, float32 b) > -{ > - return ((float32_is_zero(a) && is_finite(b)) || > - (float32_is_zero(b) && is_finite(a))); > -} > - > -static float32 check_nan(float32 dst, float32 x, float_status *fp_status) > -{ > - float32 ret = dst; > - if (float32_is_any_nan(x)) { > - if (extract32(x, 22, 1) == 0) { > - float_raise(float_flag_invalid, fp_status); > - } > - ret = make_float32(0xffffffff); /* nan */ > - } > - return ret; > -} > - > float32 HELPER(sffma_sc)(CPUHexagonState *env, float32 RxV, > float32 RsV, float32 RtV, float32 PuV) > { > @@ -1210,78 +1192,43 @@ float32 HELPER(sffms)(CPUHexagonState *env, float32 RxV, > return RxV; > } > > -static bool is_inf_prod(int32_t a, int32_t b) > +static float32 do_sffma_lib(CPUHexagonState *env, float32 RxV, > + float32 RsV, float32 RtV, int negate) > { > - return (float32_is_infinity(a) && float32_is_infinity(b)) || > - (float32_is_infinity(a) && is_finite(b) && !float32_is_zero(b)) || > - (float32_is_infinity(b) && is_finite(a) && !float32_is_zero(a)); > + int flags; > + > + arch_fpop_start(env); > + > + set_float_rounding_mode(float_round_nearest_even_max, &env->fp_status); > + RxV = float32_muladd(RsV, RtV, RxV, > + negate | float_muladd_suppress_add_product_zero, > + &env->fp_status); > + > + flags = get_float_exception_flags(&env->fp_status); > + if (flags) { > + /* Flags are suppressed by this instruction. */ > + set_float_exception_flags(0, &env->fp_status); > + > + /* Return 0 for Inf - Inf. */ > + if (flags & float_flag_invalid_isi) { > + RxV = 0; > + } > + } > + > + arch_fpop_end(env); > + return RxV; > } > > float32 HELPER(sffma_lib)(CPUHexagonState *env, float32 RxV, > float32 RsV, float32 RtV) > { > - bool infinp; > - bool infminusinf; > - float32 tmp; > - > - arch_fpop_start(env); > - set_float_rounding_mode(float_round_nearest_even, &env->fp_status); > - infminusinf = float32_is_infinity(RxV) && > - is_inf_prod(RsV, RtV) && > - (fGETBIT(31, RsV ^ RxV ^ RtV) != 0); > - infinp = float32_is_infinity(RxV) || > - float32_is_infinity(RtV) || > - float32_is_infinity(RsV); > - RxV = check_nan(RxV, RxV, &env->fp_status); > - RxV = check_nan(RxV, RsV, &env->fp_status); > - RxV = check_nan(RxV, RtV, &env->fp_status); > - tmp = internal_fmafx(RsV, RtV, RxV, 0, &env->fp_status); > - if (!(float32_is_zero(RxV) && is_zero_prod(RsV, RtV))) { > - RxV = tmp; > - } > - set_float_exception_flags(0, &env->fp_status); > - if (float32_is_infinity(RxV) && !infinp) { > - RxV = RxV - 1; > - } > - if (infminusinf) { > - RxV = 0; > - } > - arch_fpop_end(env); > - return RxV; > + return do_sffma_lib(env, RxV, RsV, RtV, 0); > } > > float32 HELPER(sffms_lib)(CPUHexagonState *env, float32 RxV, > float32 RsV, float32 RtV) > { > - bool infinp; > - bool infminusinf; > - float32 tmp; > - > - arch_fpop_start(env); > - set_float_rounding_mode(float_round_nearest_even, &env->fp_status); > - infminusinf = float32_is_infinity(RxV) && > - is_inf_prod(RsV, RtV) && > - (fGETBIT(31, RsV ^ RxV ^ RtV) == 0); > - infinp = float32_is_infinity(RxV) || > - float32_is_infinity(RtV) || > - float32_is_infinity(RsV); > - RxV = check_nan(RxV, RxV, &env->fp_status); > - RxV = check_nan(RxV, RsV, &env->fp_status); > - RxV = check_nan(RxV, RtV, &env->fp_status); > - float32 minus_RsV = float32_sub(float32_zero, RsV, &env->fp_status); > - tmp = internal_fmafx(minus_RsV, RtV, RxV, 0, &env->fp_status); > - if (!(float32_is_zero(RxV) && is_zero_prod(RsV, RtV))) { > - RxV = tmp; > - } > - set_float_exception_flags(0, &env->fp_status); > - if (float32_is_infinity(RxV) && !infinp) { > - RxV = RxV - 1; > - } > - if (infminusinf) { > - RxV = 0; > - } > - arch_fpop_end(env); > - return RxV; > + return do_sffma_lib(env, RxV, RsV, RtV, float_muladd_negate_product); > } > Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> > float64 HELPER(dfmpyfix)(CPUHexagonState *env, float64 RssV, float64 RttV)
diff --git a/target/hexagon/op_helper.c b/target/hexagon/op_helper.c index eb010422bf..26e329f7b9 100644 --- a/target/hexagon/op_helper.c +++ b/target/hexagon/op_helper.c @@ -1171,24 +1171,6 @@ float32 HELPER(sffma)(CPUHexagonState *env, float32 RxV, return RxV; } -static bool is_zero_prod(float32 a, float32 b) -{ - return ((float32_is_zero(a) && is_finite(b)) || - (float32_is_zero(b) && is_finite(a))); -} - -static float32 check_nan(float32 dst, float32 x, float_status *fp_status) -{ - float32 ret = dst; - if (float32_is_any_nan(x)) { - if (extract32(x, 22, 1) == 0) { - float_raise(float_flag_invalid, fp_status); - } - ret = make_float32(0xffffffff); /* nan */ - } - return ret; -} - float32 HELPER(sffma_sc)(CPUHexagonState *env, float32 RxV, float32 RsV, float32 RtV, float32 PuV) { @@ -1210,78 +1192,43 @@ float32 HELPER(sffms)(CPUHexagonState *env, float32 RxV, return RxV; } -static bool is_inf_prod(int32_t a, int32_t b) +static float32 do_sffma_lib(CPUHexagonState *env, float32 RxV, + float32 RsV, float32 RtV, int negate) { - return (float32_is_infinity(a) && float32_is_infinity(b)) || - (float32_is_infinity(a) && is_finite(b) && !float32_is_zero(b)) || - (float32_is_infinity(b) && is_finite(a) && !float32_is_zero(a)); + int flags; + + arch_fpop_start(env); + + set_float_rounding_mode(float_round_nearest_even_max, &env->fp_status); + RxV = float32_muladd(RsV, RtV, RxV, + negate | float_muladd_suppress_add_product_zero, + &env->fp_status); + + flags = get_float_exception_flags(&env->fp_status); + if (flags) { + /* Flags are suppressed by this instruction. */ + set_float_exception_flags(0, &env->fp_status); + + /* Return 0 for Inf - Inf. */ + if (flags & float_flag_invalid_isi) { + RxV = 0; + } + } + + arch_fpop_end(env); + return RxV; } float32 HELPER(sffma_lib)(CPUHexagonState *env, float32 RxV, float32 RsV, float32 RtV) { - bool infinp; - bool infminusinf; - float32 tmp; - - arch_fpop_start(env); - set_float_rounding_mode(float_round_nearest_even, &env->fp_status); - infminusinf = float32_is_infinity(RxV) && - is_inf_prod(RsV, RtV) && - (fGETBIT(31, RsV ^ RxV ^ RtV) != 0); - infinp = float32_is_infinity(RxV) || - float32_is_infinity(RtV) || - float32_is_infinity(RsV); - RxV = check_nan(RxV, RxV, &env->fp_status); - RxV = check_nan(RxV, RsV, &env->fp_status); - RxV = check_nan(RxV, RtV, &env->fp_status); - tmp = internal_fmafx(RsV, RtV, RxV, 0, &env->fp_status); - if (!(float32_is_zero(RxV) && is_zero_prod(RsV, RtV))) { - RxV = tmp; - } - set_float_exception_flags(0, &env->fp_status); - if (float32_is_infinity(RxV) && !infinp) { - RxV = RxV - 1; - } - if (infminusinf) { - RxV = 0; - } - arch_fpop_end(env); - return RxV; + return do_sffma_lib(env, RxV, RsV, RtV, 0); } float32 HELPER(sffms_lib)(CPUHexagonState *env, float32 RxV, float32 RsV, float32 RtV) { - bool infinp; - bool infminusinf; - float32 tmp; - - arch_fpop_start(env); - set_float_rounding_mode(float_round_nearest_even, &env->fp_status); - infminusinf = float32_is_infinity(RxV) && - is_inf_prod(RsV, RtV) && - (fGETBIT(31, RsV ^ RxV ^ RtV) == 0); - infinp = float32_is_infinity(RxV) || - float32_is_infinity(RtV) || - float32_is_infinity(RsV); - RxV = check_nan(RxV, RxV, &env->fp_status); - RxV = check_nan(RxV, RsV, &env->fp_status); - RxV = check_nan(RxV, RtV, &env->fp_status); - float32 minus_RsV = float32_sub(float32_zero, RsV, &env->fp_status); - tmp = internal_fmafx(minus_RsV, RtV, RxV, 0, &env->fp_status); - if (!(float32_is_zero(RxV) && is_zero_prod(RsV, RtV))) { - RxV = tmp; - } - set_float_exception_flags(0, &env->fp_status); - if (float32_is_infinity(RxV) && !infinp) { - RxV = RxV - 1; - } - if (infminusinf) { - RxV = 0; - } - arch_fpop_end(env); - return RxV; + return do_sffma_lib(env, RxV, RsV, RtV, float_muladd_negate_product); } float64 HELPER(dfmpyfix)(CPUHexagonState *env, float64 RssV, float64 RttV)
There are multiple special cases for this instruction. (1) The saturate to normal maximum instead of overflow to infinity is handled by the new float_round_nearest_even_max rounding mode. (2) The 0 * n + c special case is handled by the new float_muladd_suppress_add_product_zero flag. (3) The Inf - Inf -> 0 special case can be detected after the fact by examining float_flag_invalid_isi. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/hexagon/op_helper.c | 105 +++++++++---------------------------- 1 file changed, 26 insertions(+), 79 deletions(-)