Commit Graph

383 Commits

Author SHA1 Message Date
Richard Henderson 42636fb923 softfloat: Add float64r32 arithmetic routines
These variants take a float64 as input, compute the result to
infinite precision (as we do with FloatParts), round the result
to the precision and dynamic range of float32, and then return
the result in the format of float64.

This is the operation PowerPC requires for its float32 operations.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20211119160502.17432-28-richard.henderson@linaro.org>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
2021-12-17 17:57:15 +01:00
Richard Henderson e706d4455b softfloat: Add flag specific to signaling nans
PowerPC has this flag, and it's easier to compute it here
than after the fact.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20211119160502.17432-8-richard.henderson@linaro.org>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
2021-12-17 17:57:14 +01:00
Richard Henderson 81254b02eb softfloat: Add flag specific to convert non-nan to int
PowerPC has this flag, and it's easier to compute it here
than after the fact.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20211119160502.17432-7-richard.henderson@linaro.org>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
2021-12-17 17:57:14 +01:00
Richard Henderson f8718aab89 softfloat: Add flag specific to sqrt(-x)
PowerPC has this flag, and it's easier to compute it here
than after the fact.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20211119160502.17432-6-richard.henderson@linaro.org>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
2021-12-17 17:57:14 +01:00
Richard Henderson 10cc964030 softfloat: Add flags specific to Inf / Inf and 0 / 0
PowerPC has these flags, and it's easier to compute them here
than after the fact.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20211119160502.17432-5-richard.henderson@linaro.org>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
2021-12-17 17:57:14 +01:00
Richard Henderson bead3c9b0f softfloat: Add flag specific to Inf * 0
PowerPC has this flag, and it's easier to compute it here
than after the fact.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20211119160502.17432-4-richard.henderson@linaro.org>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
2021-12-17 17:57:14 +01:00
Richard Henderson ba11446c40 softfloat: Add flag specific to Inf - Inf
PowerPC has this flag, and it's easier to compute it here
than after the fact.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20211119160502.17432-3-richard.henderson@linaro.org>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
2021-12-17 17:57:14 +01:00
Chih-Min Chao 0e9030376e softfloat: add APIs to handle alternative sNaN propagation for fmax/fmin
For "fmax/fmin ft0, ft1, ft2" and if one of the inputs is sNaN,

  The original logic:
    Return NaN and set invalid flag if ft1 == sNaN || ft2 == sNan.

  The alternative path:
    Set invalid flag if ft1 == sNaN || ft2 == sNaN.
    Return NaN only if ft1 == NaN && ft2 == NaN.

The IEEE 754 spec allows both implementation and some architecture such
as riscv choose different defintions in two spec versions.
(riscv-spec-v2.2 use original version, riscv-spec-20191213 changes to
 alternative)

Signed-off-by: Chih-Min Chao <chihmin.chao@sifive.com>
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20211021160847.2748577-2-frank.chang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
2021-10-29 16:55:45 +10:00
Peter Maydell 2c8cb5888e softfloat: Remove assertion preventing silencing of NaN in default-NaN mode
In commit a777d60334 we added an assertion to parts_silence_nan() that
prohibits calling float*_silence_nan() when in default-NaN mode.
This ties together a property of the output ("do we generate a default
NaN when the result is a NaN?") with an operation on an input ("silence
this input NaN").

It's true that most of the time when in default-NaN mode you won't
need to silence an input NaN, because you can just produce the
default NaN as the result instead.  But some functions like
float*_maxnum() are defined to be able to work with quiet NaNs, so
silencing an input SNaN is still reasonable.  In particular, the
upcoming implementation of MVE VMAXNMV would fall over this assertion
if we didn't delete it.

Delete the assertion.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 11:08:17 +01:00
Richard Henderson 6c06aca036 softfloat: Use _Generic instead of QEMU_GENERIC
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20210614233143.1221879-3-richard.henderson@linaro.org>
2021-06-15 18:31:00 -07:00
Richard Henderson f291f45f4e softfloat: Fix tp init in float32_exp2
Typo in the conversion to FloatParts64.

Fixes: 572c4d862f
Fixes: Coverity CID 1457457
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20210607223812.110596-1-richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-13 17:42:40 -07:00
Richard Henderson c634754172 meson: Split out fpu/meson.build
Reviewed-by: Luis Pires <luis.pires@eldorado.org.br>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-11 09:26:28 -07:00
Richard Henderson 5d0204b82a softfloat: Use hard-float for {u}int64_to_float{32,64}
For the normal case of no additional scaling, this reduces the
profile contribution of int64_to_float64 to the testcase in the
linked issue from 0.81% to 0.04%.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/134
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:03 -07:00
Richard Henderson feaf2e9c06 softfloat: Convert modrem operations to FloatParts
Rename to parts$N_modrem.  This was the last use of a lot
of the legacy infrastructure, so remove it as required.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson 2fa3546c8f softfloat: Move floatN_log2 to softfloat-parts.c.inc
Rename to parts$N_log2.  Though this is partly a ruse, since I do not
believe the code will succeed for float128 without work.  Which is ok
for now, because we do not need this for more than float32 and float64.

Since berkeley-testfloat-3 doesn't support log2, compare float64_log2
vs the system log2.  Fix the errors for inputs near 1.0:

test: 3ff00000000000b0  +0x1.00000000000b0p+0
  sf: 3d2fa00000000000  +0x1.fa00000000000p-45
libm: 3d2fbd422b1bd36f  +0x1.fbd422b1bd36fp-45
Error in fraction: 32170028290927 ulp

test: 3feec24f6770b100  +0x1.ec24f6770b100p-1
  sf: bfad3740d13c9ec0  -0x1.d3740d13c9ec0p-5
libm: bfad3740d13c9e98  -0x1.d3740d13c9e98p-5
Error in fraction: 40 ulp

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson 572c4d862f softfloat: Convert float32_exp2 to FloatParts
Keep the intermediate results in FloatParts instead of
converting back and forth between float64.  Use muladd
instead of separate mul+add.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson 1b96b006d2 softfloat: Convert floatx80 compare to FloatParts
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson 872e6991f0 softfloat: Convert floatx80_scalbn to FloatParts
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson a1fc527bfb softfloat: Convert floatx80 to integer to FloatParts
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson 8ae5719cd4 softfloat: Convert floatx80 float conversions to FloatParts
This is the last use of commonNaNT and all of the routines
that use it, so remove all of them for Werror.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson 5f9529006e softfloat: Convert integer to floatx80 to FloatParts
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson f9a95a7800 softfloat: Convert floatx80_round_to_int to FloatParts
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson 45a76b71ab softfloat: Convert floatx80_round to FloatParts
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson aa5e19ccbd softfloat: Convert floatx80_sqrt to FloatParts
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson 38db99e282 softfloat: Convert floatx80_div to FloatParts
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson 153f664a74 softfloat: Convert floatx80_mul to FloatParts
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson c1b6299be1 softfloat: Convert floatx80_add/sub to FloatParts
Since this is the first such, this includes all of the
packing and unpacking routines as well.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson 98b3cff753 softfloat: Adjust parts_uncanon_normal for floatx80
With floatx80_precision_x, the rounding happens across
the break between words.  Notice this case with

  frac_lsb = round_mask + 1 -> 0

and check the bits in frac_hi as needed.

In addition, since frac_shift == 0, we won't implicitly clear
round_mask via the right-shift, so explicitly clear those bits.
This fixes rounding for floatx80_precision_[sd].

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:09:02 -07:00
Richard Henderson 8da5f1dbb0 softfloat: Introduce Floatx80RoundPrec
Use an enumeration instead of raw 32/64/80 values.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:04:02 -07:00
Richard Henderson d6e1f0cd59 softfloat: Reduce FloatFmt
Remove frac_lsb, frac_lsbm1, roundeven_mask.  Compute
these from round_mask in parts$N_uncanon_normal.

With floatx80, round_mask will not be tied to frac_shift.
Everything else is easily computable.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:04:02 -07:00
Richard Henderson 25fdedf0d3 softfloat: Split out parts_uncanon_normal
We will need to treat the non-normal cases of floatx80 specially,
so split out the normal case that we can reuse.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 14:04:02 -07:00
Richard Henderson 9261b245f0 softfloat: Move sqrt_float to softfloat-parts.c.inc
Rename to parts$N_sqrt.
Reimplement float128_sqrt with FloatParts128.

Reimplement with the inverse sqrt newton-raphson algorithm from musl.
This is significantly faster than even the berkeley sqrt n-r algorithm,
because it does not use division instructions, only multiplication.

Ordinarily, changing algorithms at the same time as migrating code is
a bad idea, but this is the only way I found that didn't break one of
the routines at the same time.

Tested-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 13:59:34 -07:00
Richard Henderson 39626b0ce8 softfloat: Move scalbn_decomposed to softfloat-parts.c.inc
Rename to parts$N_scalbn.
Reimplement float128_scalbn with FloatParts128.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 13:59:34 -07:00
Richard Henderson 6eb169b89a softfloat: Move compare_floats to softfloat-parts.c.inc
Rename to parts$N_compare.  Rename all of the intermediate
functions to ftype_do_compare.  Rename the hard-float functions
to ftype_hs_compare.  Convert float128 to FloatParts128.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 13:59:34 -07:00
David Hildenbrand ceebc129e5 softfloat: Implement float128_(min|minnum|minnummag|max|maxnum|maxnummag)
The float128 implementation is straight-forward.
Unfortuantely, we don't have any tests we can simply adjust/unlock.

Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210517142739.38597-24-david@redhat.com>
[rth: Update for changed parts_minmax return value]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 13:59:34 -07:00
Richard Henderson e1c4667a9b softfloat: Move minmax_flags to softfloat-parts.c.inc
Rename to parts$N_minmax.  Combine 3 bool arguments to a bitmask.
Introduce ftype_minmax functions as a common optimization point.
Fold bfloat16 expansions into the same macro as the other types.

Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 13:59:34 -07:00
Richard Henderson 37c954a1b9 softfloat: Move uint_to_float to softfloat-parts.c.inc
Rename to parts$N_uint_to_float.
Reimplement uint64_to_float128 with FloatParts128.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 13:59:34 -07:00
Richard Henderson e368951998 softfloat: Move int_to_float to softfloat-parts.c.inc
Rename to parts$N_sint_to_float.
Reimplement int{32,64}_to_float128 with FloatParts128.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 13:59:34 -07:00
Richard Henderson 4ab4aef018 softfloat: Move round_to_uint_and_pack to softfloat-parts.c.inc
Rename to parts$N_float_to_uint.  Reimplement
float128_to_uint{32,64}{_round_to_zero} with FloatParts128.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-06-03 13:59:34 -07:00
Richard Henderson 60c8f7265d softfpu: Add float_round_to_odd_inf
For Arm BFDOT and BFMMLA, we need a version of round-to-odd
that overflows to infinity, instead of the max normal number.

Cc: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-6-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-06-03 16:43:26 +01:00
Richard Henderson 463b3f0d7f softfloat: Move round_to_int_and_pack to softfloat-parts.c.inc
Rename to parts$N_float_to_sint.  Reimplement
float128_to_int{32,64}{_round_to_zero} with FloatParts128.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-05-16 07:13:51 -05:00
Richard Henderson afc34931eb softfloat: Move round_to_int to softfloat-parts.c.inc
At the same time, convert to pointers, split out
parts$N_round_to_int_normal, define a macro for
parts_round_to_int using QEMU_GENERIC.

This necessarily meant some rearrangement to the
rount_to_{,u}int_and_pack routines, so go ahead and
convert to parts_round_to_int_normal, which in turn
allows cleaning up of the raised exception handling.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-05-16 07:13:51 -05:00
Richard Henderson 9882ccaff9 softfloat: Convert float-to-float conversions with float128
Introduce parts_float_to_float_widen and parts_float_to_float_narrow.
Use them for float128_to_float{32,64} and float{32,64}_to_float128.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-05-16 07:13:51 -05:00
Richard Henderson c3f1875ea3 softfloat: Split float_to_float
Split out parts_float_to_ahp and parts_float_to_float.
Convert to pointers.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-05-16 07:13:51 -05:00
Richard Henderson ec961b81b4 softfloat: Move div_floats to softfloat-parts.c.inc
Rename to parts$N_div.
Implement float128_div with FloatParts128.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-05-16 07:13:51 -05:00
Richard Henderson 463e45dcb4 softfloat: Introduce sh[lr]_double primitives
Have x86_64 assembly for them, with a fallback.
This avoids shuffling values through %cl in the x86 case.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-05-16 07:13:51 -05:00
Richard Henderson dedd123c56 softfloat: Move muladd_floats to softfloat-parts.c.inc
Rename to parts$N_muladd.
Implement float128_muladd with FloatParts128.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-05-16 07:13:51 -05:00
Richard Henderson aca845275a softfloat: Move mul_floats to softfloat-parts.c.inc
Rename to parts$N_mul.
Reimplement float128_mul with FloatParts128.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-05-16 07:13:51 -05:00
Richard Henderson 3ff49e56a7 softfloat: Implement float128_add/sub via parts
Replace the existing Berkeley implementation with the
FloatParts implementation.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-05-16 07:13:51 -05:00
Richard Henderson da10a9074a softfloat: Move addsub_floats to softfloat-parts.c.inc
In preparation for implementing multiple sizes.  Rename to parts_addsub,
split out parts_add/sub_normal for future reuse with muladd.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2021-05-16 07:13:51 -05:00