mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-27 06:30:56 +07:00
405849610f
The underflow exception cases were wrong.
This is one weird area of ieee1754 handling in that the underflow
behavior changes based upon whether underflow is enabled in the trap
enable mask of the FPU control register. As a specific case the Sparc
V9 manual gives us the following description:
--------------------
If UFM = 0: Underflow occurs if a nonzero result is tiny and a
loss of accuracy occurs. Tininess may be detected
before or after rounding. Loss of accuracy may be
either a denormalization loss or an inexact result.
If UFM = 1: Underflow occurs if a nonzero result is tiny.
Tininess may be detected before or after rounding.
--------------------
What this amounts to in the packing case is if we go subnormal,
we set underflow if any of the following are true:
1) rounding sets inexact
2) we ended up rounding back up to normal (this is the case where
we set the exponent to 1 and set the fraction to zero), this
should set inexact too
3) underflow is set in FPU control register trap-enable mask
The initially discovered example was "DBL_MIN / 16.0" which
incorrectly generated an underflow. It should not, unless underflow
is set in the trap-enable mask of the FPU csr.
Another example, "0x0.0000000000001p-1022 / 16.0", should signal both
inexact and underflow. The cpu implementations and ieee1754
literature is very clear about this. This is case #2 above.
However, if underflow is set in the trap enable mask, only underflow
should be set and reported as a trap. That is handled properly by the
prioritization logic in
arch/sparc{,64}/math-emu/math.c:record_exception().
Based upon a report and test case from Jakub Jelinek.
Signed-off-by: David S. Miller <davem@davemloft.net>
94 lines
3.1 KiB
C
94 lines
3.1 KiB
C
/* Machine-dependent software floating-point definitions.
|
|
Sparc64 kernel version.
|
|
Copyright (C) 1997,1998,1999 Free Software Foundation, Inc.
|
|
This file is part of the GNU C Library.
|
|
Contributed by Richard Henderson (rth@cygnus.com),
|
|
Jakub Jelinek (jj@ultra.linux.cz) and
|
|
David S. Miller (davem@redhat.com).
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
modify it under the terms of the GNU Library General Public License as
|
|
published by the Free Software Foundation; either version 2 of the
|
|
License, or (at your option) any later version.
|
|
|
|
The GNU C Library is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
Library General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Library General Public
|
|
License along with the GNU C Library; see the file COPYING.LIB. If
|
|
not, write to the Free Software Foundation, Inc.,
|
|
59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
|
|
|
|
#ifndef _SFP_MACHINE_H
|
|
#define _SFP_MACHINE_H
|
|
|
|
#define _FP_W_TYPE_SIZE 64
|
|
#define _FP_W_TYPE unsigned long
|
|
#define _FP_WS_TYPE signed long
|
|
#define _FP_I_TYPE long
|
|
|
|
#define _FP_MUL_MEAT_S(R,X,Y) \
|
|
_FP_MUL_MEAT_1_imm(_FP_WFRACBITS_S,R,X,Y)
|
|
#define _FP_MUL_MEAT_D(R,X,Y) \
|
|
_FP_MUL_MEAT_1_wide(_FP_WFRACBITS_D,R,X,Y,umul_ppmm)
|
|
#define _FP_MUL_MEAT_Q(R,X,Y) \
|
|
_FP_MUL_MEAT_2_wide(_FP_WFRACBITS_Q,R,X,Y,umul_ppmm)
|
|
|
|
#define _FP_DIV_MEAT_S(R,X,Y) _FP_DIV_MEAT_1_imm(S,R,X,Y,_FP_DIV_HELP_imm)
|
|
#define _FP_DIV_MEAT_D(R,X,Y) _FP_DIV_MEAT_1_udiv_norm(D,R,X,Y)
|
|
#define _FP_DIV_MEAT_Q(R,X,Y) _FP_DIV_MEAT_2_udiv(Q,R,X,Y)
|
|
|
|
#define _FP_NANFRAC_S ((_FP_QNANBIT_S << 1) - 1)
|
|
#define _FP_NANFRAC_D ((_FP_QNANBIT_D << 1) - 1)
|
|
#define _FP_NANFRAC_Q ((_FP_QNANBIT_Q << 1) - 1), -1
|
|
#define _FP_NANSIGN_S 0
|
|
#define _FP_NANSIGN_D 0
|
|
#define _FP_NANSIGN_Q 0
|
|
|
|
#define _FP_KEEPNANFRACP 1
|
|
|
|
/* If one NaN is signaling and the other is not,
|
|
* we choose that one, otherwise we choose X.
|
|
*/
|
|
/* For _Qp_* and _Q_*, this should prefer X, for
|
|
* CPU instruction emulation this should prefer Y.
|
|
* (see SPAMv9 B.2.2 section).
|
|
*/
|
|
#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP) \
|
|
do { \
|
|
if ((_FP_FRAC_HIGH_RAW_##fs(Y) & _FP_QNANBIT_##fs) \
|
|
&& !(_FP_FRAC_HIGH_RAW_##fs(X) & _FP_QNANBIT_##fs)) \
|
|
{ \
|
|
R##_s = X##_s; \
|
|
_FP_FRAC_COPY_##wc(R,X); \
|
|
} \
|
|
else \
|
|
{ \
|
|
R##_s = Y##_s; \
|
|
_FP_FRAC_COPY_##wc(R,Y); \
|
|
} \
|
|
R##_c = FP_CLS_NAN; \
|
|
} while (0)
|
|
|
|
/* Obtain the current rounding mode. */
|
|
#ifndef FP_ROUNDMODE
|
|
#define FP_ROUNDMODE ((current_thread_info()->xfsr[0] >> 30) & 0x3)
|
|
#endif
|
|
|
|
/* Exception flags. */
|
|
#define FP_EX_INVALID (1 << 4)
|
|
#define FP_EX_OVERFLOW (1 << 3)
|
|
#define FP_EX_UNDERFLOW (1 << 2)
|
|
#define FP_EX_DIVZERO (1 << 1)
|
|
#define FP_EX_INEXACT (1 << 0)
|
|
|
|
#define FP_HANDLE_EXCEPTIONS return _fex
|
|
|
|
#define FP_INHIBIT_RESULTS ((current_thread_info()->xfsr[0] >> 23) & _fex)
|
|
|
|
#define FP_TRAPPING_EXCEPTIONS ((current_thread_info()->xfsr[0] >> 23) & 0x1f)
|
|
|
|
#endif
|