On Thu, Jun 7, 2012 at 9:58 PM, Uros Bizjak <ubiz...@gmail.com> wrote:
> Attached patch rewrites x86 soft-FP as an out-of-line function that
> gets conditionally called when exception occurs. This rewrite removes
> 17 instances of the same code from libgcc. In addition, the patch
> unifies a lot of code between 32bit and 64bit x86 target, and also
> introduces SSE instructions for 32bit targets. There is no other
> functional changes, although the change to real SSE FP ops is
> tempting. ;)
>
> 2012-06-07 Uros Bizjak <ubiz...@gmail.com>
>
> * config/i386/32/sfp-machine.h (__gcc_CMPtype, CMPtype,
> _FP_KEEPNANFRACP, _FP_CHOOSENAN, FP_EX_INVALID, FP_EX_DENORM,
> FP_EX_DIVZERO, FP_EX_OVERFLOW, FP_EX_UNDERFLOW, FP_EX_INEXACT,
> FP_HANDLE_EXCEPTIONS, FP_RND_NEAREST, FP_RND_ZERO, FP_RND_PINF,
> FP_RND_MINF, _FP_DEXL_EX, FP_INIT_ROUNDMODE, FP_ROUNDMODE,
> __LITTLE_ENDIAN, __BIG_ENDIAN, strong_alias): Move ...
> * config/i386/64/sfp-machine: ... (delete here) ...
> * config/i386/sfp-machine.h: ... to here.
> (FP_EX_MASK): New.
> (__sfp_handle_exceptions): New function declaration.
> (FP_HANDLE_EXCEPTIONS): Use __sfp_handle_exceptions.
> * config/i386/sfp-exceptions.c: New.
> * config/i386/t-softfp: New.
> * config.host (i[34567]86-*-* and x86_64-*-* soft-fp targets): Add
> i386/t-softfp to tmake_file.
>
> Patch was tested on x86_64-pc-linux-gnu {,-m32}.
I have committed attached, slightly changed patch (asm patterns in
__sfp_handle_exceptions) to the mainline SVN.
Uros.
Index: config/i386/sfp-machine.h
===================================================================
--- config/i386/sfp-machine.h (revision 188333)
+++ config/i386/sfp-machine.h (working copy)
@@ -3,8 +3,83 @@
#define _FP_STRUCT_LAYOUT __attribute__ ((gcc_struct))
#endif
+/* The type of the result of a floating point comparison. This must
+ match `__libgcc_cmp_return__' in GCC for the target. */
+typedef int __gcc_CMPtype __attribute__ ((mode (__libgcc_cmp_return__)));
+#define CMPtype __gcc_CMPtype
+
#ifdef __x86_64__
#include "config/i386/64/sfp-machine.h"
#else
#include "config/i386/32/sfp-machine.h"
#endif
+
+#define _FP_KEEPNANFRACP 1
+
+/* Here is something Intel misdesigned: the specs don't define
+ the case where we have two NaNs with same mantissas, but
+ different sign. Different operations pick up different NaNs. */
+#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP) \
+ do { \
+ if (_FP_FRAC_GT_##wc(X, Y) \
+ || (_FP_FRAC_EQ_##wc(X,Y) && (OP == '+' || OP == '*'))) \
+ { \
+ 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)
+
+#define FP_EX_INVALID 0x01
+#define FP_EX_DENORM 0x02
+#define FP_EX_DIVZERO 0x04
+#define FP_EX_OVERFLOW 0x08
+#define FP_EX_UNDERFLOW 0x10
+#define FP_EX_INEXACT 0x20
+
+#define FP_EX_MASK 0x3f
+
+void __sfp_handle_exceptions (int);
+
+#define FP_HANDLE_EXCEPTIONS \
+ do { \
+ if (_fex & FP_EX_MASK) \
+ __sfp_handle_exceptions (_fex); \
+ } while (0);
+
+#define FP_RND_NEAREST 0
+#define FP_RND_ZERO 0xc00
+#define FP_RND_PINF 0x800
+#define FP_RND_MINF 0x400
+
+#define _FP_DECL_EX \
+ unsigned short _fcw __attribute__ ((unused)) = FP_RND_NEAREST
+
+#define FP_INIT_ROUNDMODE \
+ do { \
+ __asm__ ("fnstcw %0" : "=m" (_fcw)); \
+ } while (0)
+
+#define FP_ROUNDMODE (_fcw & 0xc00)
+
+#define __LITTLE_ENDIAN 1234
+#define __BIG_ENDIAN 4321
+
+#define __BYTE_ORDER __LITTLE_ENDIAN
+
+/* Define ALIASNAME as a strong alias for NAME. */
+#if defined __MACH__
+/* Mach-O doesn't support aliasing. If these functions ever return
+ anything but CMPtype we need to revisit this... */
+#define strong_alias(name, aliasname) \
+ CMPtype aliasname (TFtype a, TFtype b) { return name(a, b); }
+#else
+# define strong_alias(name, aliasname) _strong_alias(name, aliasname)
+# define _strong_alias(name, aliasname) \
+ extern __typeof (name) aliasname __attribute__ ((alias (#name)));
+#endif
Index: config/i386/64/sfp-machine.h
===================================================================
--- config/i386/64/sfp-machine.h (revision 188333)
+++ config/i386/64/sfp-machine.h (working copy)
@@ -1,5 +1,4 @@
#define _FP_W_TYPE_SIZE 64
-
#define _FP_W_TYPE unsigned long long
#define _FP_WS_TYPE signed long long
#define _FP_I_TYPE long long
@@ -9,11 +8,6 @@
#define TI_BITS (__CHAR_BIT__ * (int)sizeof(TItype))
-/* The type of the result of a floating point comparison. This must
- match `__libgcc_cmp_return__' in GCC for the target. */
-typedef int __gcc_CMPtype __attribute__ ((mode (__libgcc_cmp_return__)));
-#define CMPtype __gcc_CMPtype
-
#define _FP_MUL_MEAT_Q(R,X,Y) \
_FP_MUL_MEAT_2_wide(_FP_WFRACBITS_Q,R,X,Y,umul_ppmm)
@@ -27,126 +21,3 @@
#define _FP_NANSIGN_D 1
#define _FP_NANSIGN_E 1
#define _FP_NANSIGN_Q 1
-
-#define _FP_KEEPNANFRACP 1
-
-/* Here is something Intel misdesigned: the specs don't define
- the case where we have two NaNs with same mantissas, but
- different sign. Different operations pick up different NaNs. */
-#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP) \
- do { \
- if (_FP_FRAC_GT_##wc(X, Y) \
- || (_FP_FRAC_EQ_##wc(X,Y) && (OP == '+' || OP == '*'))) \
- { \
- 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)
-
-#define FP_EX_INVALID 0x01
-#define FP_EX_DENORM 0x02
-#define FP_EX_DIVZERO 0x04
-#define FP_EX_OVERFLOW 0x08
-#define FP_EX_UNDERFLOW 0x10
-#define FP_EX_INEXACT 0x20
-
-struct fenv
-{
- unsigned short int __control_word;
- unsigned short int __unused1;
- unsigned short int __status_word;
- unsigned short int __unused2;
- unsigned short int __tags;
- unsigned short int __unused3;
- unsigned int __eip;
- unsigned short int __cs_selector;
- unsigned int __opcode:11;
- unsigned int __unused4:5;
- unsigned int __data_offset;
- unsigned short int __data_selector;
- unsigned short int __unused5;
-};
-
-#ifdef __AVX__
- #define ASM_INVALID "vdivss %0, %0, %0"
- #define ASM_DIVZERO "vdivss %1, %0, %0"
-#else
- #define ASM_INVALID "divss %0, %0"
- #define ASM_DIVZERO "divss %1, %0"
-#endif
-
-#define FP_HANDLE_EXCEPTIONS \
- do { \
- if (_fex & FP_EX_INVALID) \
- {
\
- float f = 0.0; \
- __asm__ __volatile__ (ASM_INVALID : : "x" (f)); \
- }
\
- if (_fex & FP_EX_DIVZERO) \
- {
\
- float f = 1.0, g = 0.0; \
- __asm__ __volatile__ (ASM_DIVZERO : : "x" (f), "x" (g)); \
- }
\
- if (_fex & FP_EX_OVERFLOW) \
- {
\
- struct fenv temp; \
- __asm__ __volatile__ ("fnstenv %0" : "=m" (temp)); \
- temp.__status_word |= FP_EX_OVERFLOW; \
- __asm__ __volatile__ ("fldenv %0" : : "m" (temp)); \
- __asm__ __volatile__ ("fwait"); \
- }
\
- if (_fex & FP_EX_UNDERFLOW)
\
- {
\
- struct fenv temp; \
- __asm__ __volatile__ ("fnstenv %0" : "=m" (temp)); \
- temp.__status_word |= FP_EX_UNDERFLOW; \
- __asm__ __volatile__ ("fldenv %0" : : "m" (temp)); \
- __asm__ __volatile__ ("fwait"); \
- }
\
- if (_fex & FP_EX_INEXACT) \
- {
\
- struct fenv temp; \
- __asm__ __volatile__ ("fnstenv %0" : "=m" (temp)); \
- temp.__status_word |= FP_EX_INEXACT; \
- __asm__ __volatile__ ("fldenv %0" : : "m" (temp)); \
- __asm__ __volatile__ ("fwait"); \
- }
\
- } while (0)
-
-#define FP_RND_NEAREST 0
-#define FP_RND_ZERO 0xc00
-#define FP_RND_PINF 0x800
-#define FP_RND_MINF 0x400
-
-#define _FP_DECL_EX \
- unsigned short _fcw __attribute__ ((unused)) = FP_RND_NEAREST
-
-#define FP_INIT_ROUNDMODE \
- do { \
- __asm__ ("fnstcw %0" : "=m" (_fcw)); \
- } while (0)
-
-#define FP_ROUNDMODE (_fcw & 0xc00)
-
-#define __LITTLE_ENDIAN 1234
-#define __BIG_ENDIAN 4321
-
-#define __BYTE_ORDER __LITTLE_ENDIAN
-
-/* Define ALIASNAME as a strong alias for NAME. */
-#if defined __MACH__
-/* Mach-O doesn't support aliasing. If these functions ever return
- anything but CMPtype we need to revisit this... */
-#define strong_alias(name, aliasname) \
- CMPtype aliasname (TFtype a, TFtype b) { return name(a, b); }
-#else
-# define strong_alias(name, aliasname) _strong_alias(name, aliasname)
-# define _strong_alias(name, aliasname) \
- extern __typeof (name) aliasname __attribute__ ((alias (#name)));
-#endif
Index: config/i386/32/sfp-machine.h
===================================================================
--- config/i386/32/sfp-machine.h (revision 188333)
+++ config/i386/32/sfp-machine.h (working copy)
@@ -3,11 +3,6 @@
#define _FP_WS_TYPE signed int
#define _FP_I_TYPE int
-/* The type of the result of a floating point comparison. This must
- match `__libgcc_cmp_return__' in GCC for the target. */
-typedef int __gcc_CMPtype __attribute__ ((mode (__libgcc_cmp_return__)));
-#define CMPtype __gcc_CMPtype
-
#define __FP_FRAC_ADD_4(r3,r2,r1,r0,x3,x2,x1,x0,y3,y2,y1,y0) \
__asm__ ("add{l} {%11,%3|%3,%11}\n\t" \
"adc{l} {%9,%2|%2,%9}\n\t" \
@@ -85,122 +80,3 @@
#define _FP_NANSIGN_D 1
#define _FP_NANSIGN_E 1
#define _FP_NANSIGN_Q 1
-
-#define _FP_KEEPNANFRACP 1
-
-/* Here is something Intel misdesigned: the specs don't define
- the case where we have two NaNs with same mantissas, but
- different sign. Different operations pick up different NaNs. */
-#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP) \
- do { \
- if (_FP_FRAC_GT_##wc(X, Y) \
- || (_FP_FRAC_EQ_##wc(X,Y) && (OP == '+' || OP == '*'))) \
- { \
- 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)
-
-#define FP_EX_INVALID 0x01
-#define FP_EX_DENORM 0x02
-#define FP_EX_DIVZERO 0x04
-#define FP_EX_OVERFLOW 0x08
-#define FP_EX_UNDERFLOW 0x10
-#define FP_EX_INEXACT 0x20
-
-struct fenv
-{
- unsigned short int __control_word;
- unsigned short int __unused1;
- unsigned short int __status_word;
- unsigned short int __unused2;
- unsigned short int __tags;
- unsigned short int __unused3;
- unsigned int __eip;
- unsigned short int __cs_selector;
- unsigned int __opcode:11;
- unsigned int __unused4:5;
- unsigned int __data_offset;
- unsigned short int __data_selector;
- unsigned short int __unused5;
-};
-
-#define FP_HANDLE_EXCEPTIONS \
- do { \
- if (_fex & FP_EX_INVALID) \
- {
\
- float f = 0.0; \
- __asm__ __volatile__ ("fdiv {%y0, %0|%0, %y0}" : "+t" (f)); \
- __asm__ __volatile__ ("fwait"); \
- }
\
- if (_fex & FP_EX_DIVZERO) \
- {
\
- float f = 1.0, g = 0.0; \
- __asm__ __volatile__ ("fdivp {%0, %y1|%y1, %0}" \
- : "+t" (f) : "u" (g) \
- : "st(1)"); \
- __asm__ __volatile__ ("fwait"); \
- }
\
- if (_fex & FP_EX_OVERFLOW) \
- {
\
- struct fenv temp; \
- __asm__ __volatile__ ("fnstenv %0" : "=m" (temp)); \
- temp.__status_word |= FP_EX_OVERFLOW; \
- __asm__ __volatile__ ("fldenv %0" : : "m" (temp)); \
- __asm__ __volatile__ ("fwait"); \
- }
\
- if (_fex & FP_EX_UNDERFLOW)
\
- {
\
- struct fenv temp; \
- __asm__ __volatile__ ("fnstenv %0" : "=m" (temp)); \
- temp.__status_word |= FP_EX_UNDERFLOW; \
- __asm__ __volatile__ ("fldenv %0" : : "m" (temp)); \
- __asm__ __volatile__ ("fwait"); \
- }
\
- if (_fex & FP_EX_INEXACT) \
- {
\
- struct fenv temp; \
- __asm__ __volatile__ ("fnstenv %0" : "=m" (temp)); \
- temp.__status_word |= FP_EX_INEXACT; \
- __asm__ __volatile__ ("fldenv %0" : : "m" (temp)); \
- __asm__ __volatile__ ("fwait"); \
- }
\
- } while (0)
-
-#define FP_RND_NEAREST 0
-#define FP_RND_ZERO 0xc00
-#define FP_RND_PINF 0x800
-#define FP_RND_MINF 0x400
-
-#define _FP_DECL_EX \
- unsigned short _fcw __attribute__ ((unused)) = FP_RND_NEAREST
-
-#define FP_INIT_ROUNDMODE \
- do { \
- __asm__ ("fnstcw %0" : "=m" (_fcw)); \
- } while (0)
-
-#define FP_ROUNDMODE (_fcw & 0xc00)
-
-#define __LITTLE_ENDIAN 1234
-#define __BIG_ENDIAN 4321
-
-#define __BYTE_ORDER __LITTLE_ENDIAN
-
-/* Define ALIASNAME as a strong alias for NAME. */
-#if defined __MACH__
-/* Mach-O doesn't support aliasing. If these functions ever return
- anything but CMPtype we need to revisit this... */
-#define strong_alias(name, aliasname) \
- CMPtype aliasname (TFtype a, TFtype b) { return name(a, b); }
-#else
-# define strong_alias(name, aliasname) _strong_alias(name, aliasname)
-# define _strong_alias(name, aliasname) \
- extern __typeof (name) aliasname __attribute__ ((alias (#name)));
-#endif
Index: config/i386/t-softfp
===================================================================
--- config/i386/t-softfp (revision 0)
+++ config/i386/t-softfp (working copy)
@@ -0,0 +1 @@
+LIB2ADD += $(srcdir)/config/i386/sfp-exceptions.c
Index: config/i386/sfp-exceptions.c
===================================================================
--- config/i386/sfp-exceptions.c (revision 0)
+++ config/i386/sfp-exceptions.c (working copy)
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2012 Free Software Foundation, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 3, or (at your option) any
+ * later version.
+ *
+ * This file 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
+ * General Public License for more details.
+ *
+ * Under Section 7 of GPL version 3, you are granted additional
+ * permissions described in the GCC Runtime Library Exception, version
+ * 3.1, as published by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License and
+ * a copy of the GCC Runtime Library Exception along with this program;
+ * see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ * <http://www.gnu.org/licenses/>.
+ */
+
+#include "sfp-machine.h"
+
+struct fenv
+{
+ unsigned short int __control_word;
+ unsigned short int __unused1;
+ unsigned short int __status_word;
+ unsigned short int __unused2;
+ unsigned short int __tags;
+ unsigned short int __unused3;
+ unsigned int __eip;
+ unsigned short int __cs_selector;
+ unsigned int __opcode:11;
+ unsigned int __unused4:5;
+ unsigned int __data_offset;
+ unsigned short int __data_selector;
+ unsigned short int __unused5;
+};
+
+void
+__sfp_handle_exceptions (int _fex)
+{
+ if (_fex & FP_EX_INVALID)
+ {
+ float f = 0.0f;
+#ifdef __SSE__
+ asm volatile ("%vdivss\t{%0, %d0|%d0, %0}" : "+x" (f));
+#else
+ asm volatile ("fdiv\t{%y0, %0|%0, %y0}" : "+t" (f));
+ asm volatile ("fwait");
+#endif
+ }
+ if (_fex & FP_EX_DIVZERO)
+ {
+ float f = 1.0f, g = 0.0f;
+#ifdef __SSE__
+ asm volatile ("%vdivss\t{%1, %d0|%d0, %1}" : "+x" (f) : "xm" (g));
+#else
+ asm volatile ("fdivs\t%1" : "+t" (f) : "m" (g));
+ asm volatile ("fwait");
+#endif
+ }
+ if (_fex & FP_EX_OVERFLOW)
+ {
+ struct fenv temp;
+ asm volatile ("fnstenv\t%0" : "=m" (temp));
+ temp.__status_word |= FP_EX_OVERFLOW;
+ asm volatile ("fldenv\t%0" : : "m" (temp));
+ asm volatile ("fwait");
+ }
+ if (_fex & FP_EX_UNDERFLOW)
+ {
+ struct fenv temp;
+ asm volatile ("fnstenv\t%0" : "=m" (temp));
+ temp.__status_word |= FP_EX_UNDERFLOW;
+ asm volatile ("fldenv\t%0" : : "m" (temp));
+ asm volatile ("fwait");
+ }
+ if (_fex & FP_EX_INEXACT)
+ {
+ struct fenv temp;
+ asm volatile ("fnstenv\t%0" : "=m" (temp));
+ temp.__status_word |= FP_EX_INEXACT;
+ asm volatile ("fldenv\t%0" : : "m" (temp));
+ asm volatile ("fwait");
+ }
+};
Index: config.host
===================================================================
--- config.host (revision 188333)
+++ config.host (working copy)
@@ -1153,7 +1153,7 @@
if test "${host_address}" = 32; then
tmake_file="${tmake_file} i386/${host_address}/t-softfp"
fi
- tmake_file="${tmake_file} t-softfp"
+ tmake_file="${tmake_file} i386/t-softfp t-softfp"
;;
esac
