+2013-10-16 Hans-Peter Nilsson <hp@axis.com>
+
+ For CRIS ports, switch to soft-fp. Improve arit.c and longlong.h.
+ * config.host (cpu_type) <Setting default>: Add entry for
+ crisv32-*-*.
+ (tmake_file) <crisv32-*-elf, cris-*-elf, cris-*-linux*>
+ <crisv32-*-linux*>: Adjust.
+ * longlong.h: Wrap the whole CRIS section in a single
+ defined(__CRIS__) conditional. Add comment about add_ssaaaa
+ and sub_ddmmss.
+ (COUNT_LEADING_ZEROS_0): Define when count_leading_zeros is
+ defined.
+ [__CRIS__] (__umulsidi3): Define.
+ [__CRIS__] (umul_ppmm): Define in terms of __umulsidi3.
+ * config/cris/sfp-machine.h: New file.
+ * config/cris/umulsidi3.S: New file.
+ * config/cris/t-elfmulti (LIB2ADD_ST): Add umulsidi3.S.
+ * config/cris/arit.c (SIGNMULT): New macro.
+ (__Div, __Mod): Use SIGNMULT instead of naked multiplication.
+ * config/cris/mulsi3.S: Tweak to avoid redundant register-copying;
+ saving 3 out of originally 33 cycles from the fastest
+ path, 3 out of 54 from the medium path and one from the longest
+ path. Improve comments.
+
2013-10-15 Richard Sandiford <rdsandiford@googlemail.com>
* sync.c: Remove static aliases and define each function directly
;;
cr16-*-*)
;;
+crisv32-*-*)
+ cpu_type=cris
+ ;;
fido-*-*)
cpu_type=m68k
;;
extra_parts="$extra_parts crti.o crtn.o crtlibid.o"
;;
crisv32-*-elf)
- tmake_file="$tmake_file cris/t-cris t-fdpbit"
+ tmake_file="$tmake_file cris/t-cris t-softfp-sfdf t-softfp"
;;
cris-*-elf)
- tmake_file="$tmake_file cris/t-cris t-fdpbit cris/t-elfmulti"
+ tmake_file="$tmake_file cris/t-cris t-softfp-sfdf t-softfp cris/t-elfmulti"
;;
cris-*-linux* | crisv32-*-linux*)
- tmake_file="$tmake_file cris/t-cris t-fdpbit cris/t-linux"
+ tmake_file="$tmake_file cris/t-cris t-softfp-sfdf t-softfp cris/t-linux"
;;
epiphany-*-elf*)
tmake_file="epiphany/t-epiphany t-fdpbit epiphany/t-custom-eqsf"
#define LZ(v) __builtin_clz (v)
#endif
+/* In (at least) the 4.7 series, GCC doesn't automatically choose the
+ most optimal strategy, possibly related to insufficient modelling of
+ delay-slot costs. */
+#if defined (__CRIS_arch_version) && __CRIS_arch_version >= 10
+#define SIGNMULT(s, a) ((s) * (a)) /* Cheap multiplication, better than branch. */
+#else
+#define SIGNMULT(s, a) ((s) < 0 ? -(a) : (a)) /* Branches are still better. */
+#endif
#if defined (L_udivsi3) || defined (L_divsi3) || defined (L_umodsi3) \
|| defined (L_modsi3)
{
long extra = 0;
long sign = (b < 0) ? -1 : 1;
+ long res;
/* We need to handle a == -2147483648 as expected and must while
doing that avoid producing a sequence like "abs (a) < 0" as GCC
if ((a & 0x7fffffff) == 0)
{
/* We're at 0x80000000. Tread carefully. */
- a -= b * sign;
+ a -= SIGNMULT (sign, b);
extra = sign;
}
a = -a;
}
- /* We knowingly penalize pre-v10 models by multiplication with the
- sign. */
- return sign * do_31div (a, __builtin_labs (b)).quot + extra;
+ res = do_31div (a, __builtin_labs (b)).quot;
+ return SIGNMULT (sign, res) + extra;
}
#endif /* L_divsi3 */
__Mod (long a, long b)
{
long sign = 1;
+ long res;
/* We need to handle a == -2147483648 as expected and must while
doing that avoid producing a sequence like "abs (a) < 0" as GCC
a = -a;
}
- return sign * do_31div (a, __builtin_labs (b)).rem;
+ res = do_31div (a, __builtin_labs (b)).rem;
+ return SIGNMULT (sign, res);
}
#endif /* L_modsi3 */
#endif /* L_udivsi3 || L_divsi3 || L_umodsi3 || L_modsi3 */
ret
nop
#else
- move.d $r10,$r12
+;; See if we can avoid multiplying some of the parts, knowing
+;; they're zero.
+
move.d $r11,$r9
- bound.d $r12,$r9
+ bound.d $r10,$r9
cmpu.w 65535,$r9
bls L(L3)
- move.d $r12,$r13
+ move.d $r10,$r12
- movu.w $r11,$r9
+;; Nope, have to do all the parts of a 32-bit multiplication.
+;; See head comment in optabs.c:expand_doubleword_mult.
+
+ move.d $r10,$r13
+ movu.w $r11,$r9 ; ab*cd = (a*d + b*c)<<16 + b*d
lslq 16,$r13
- mstep $r9,$r13
+ mstep $r9,$r13 ; d*b
mstep $r9,$r13
mstep $r9,$r13
mstep $r9,$r13
mstep $r9,$r13
clear.w $r10
test.d $r10
- mstep $r9,$r10
+ mstep $r9,$r10 ; d*a
mstep $r9,$r10
mstep $r9,$r10
mstep $r9,$r10
mstep $r9,$r10
mstep $r9,$r10
movu.w $r12,$r12
- move.d $r11,$r9
- clear.w $r9
- test.d $r9
- mstep $r12,$r9
+ clear.w $r11
+ move.d $r11,$r9 ; Doubles as a "test.d" preparing for the mstep.
+ mstep $r12,$r9 ; b*c
mstep $r12,$r9
mstep $r12,$r9
mstep $r12,$r9
add.d $r13,$r10
L(L3):
- move.d $r9,$r10
+;; Form the maximum in $r10, by knowing the minimum, $r9.
+;; (We don't know which one of $r10 or $r11 it is.)
+;; Check if the largest operand is still just 16 bits.
+
+ xor $r9,$r10
xor $r11,$r10
- xor $r12,$r10
cmpu.w 65535,$r10
bls L(L5)
movu.w $r9,$r13
- movu.w $r13,$r13
+;; We have ab*cd = (a*c)<<32 + (a*d + b*c)<<16 + b*d, but c==0
+;; so we only need (a*d)<<16 + b*d with d = $r13, ab = $r10.
+;; We drop the upper part of (a*d)<<16 as we're only doing a
+;; 32-bit-result multiplication.
+
move.d $r10,$r9
lslq 16,$r9
- mstep $r13,$r9
+ mstep $r13,$r9 ; b*d
mstep $r13,$r9
mstep $r13,$r9
mstep $r13,$r9
mstep $r13,$r9
clear.w $r10
test.d $r10
- mstep $r13,$r10
+ mstep $r13,$r10 ; a*d
mstep $r13,$r10
mstep $r13,$r10
mstep $r13,$r10
add.d $r9,$r10
L(L5):
- movu.w $r9,$r9
+;; We have ab*cd = (a*c)<<32 + (a*d + b*c)<<16 + b*d, but a and c==0
+;; so b*d (with b=$r13, a=$r10) it is.
+
lslq 16,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
- mstep $r9,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
ret
- mstep $r9,$r10
+ mstep $r13,$r10
#endif
L(Lfe1):
.size ___Mul,L(Lfe1)-___Mul
--- /dev/null
+/* Soft-FP definitions for CRIS.
+ Copyright (C) 2013 Free Software Foundation, Inc.
+
+This file is part of GCC.
+
+GCC 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.
+
+GCC 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/>. */
+
+#define _FP_W_TYPE_SIZE 32
+#define _FP_W_TYPE unsigned long
+#define _FP_WS_TYPE signed long
+#define _FP_I_TYPE long
+
+/* 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
+
+/* FIXME: none of the *MEAT* macros have actually been benchmarked to be
+ better than any other choice for any CRIS variant. */
+
+#define _FP_MUL_MEAT_S(R,X,Y) \
+ _FP_MUL_MEAT_1_wide(_FP_WFRACBITS_S,R,X,Y,umul_ppmm)
+#define _FP_MUL_MEAT_D(R,X,Y) \
+ _FP_MUL_MEAT_2_wide(_FP_WFRACBITS_D,R,X,Y,umul_ppmm)
+
+#define _FP_DIV_MEAT_S(R,X,Y) _FP_DIV_MEAT_1_loop(S,R,X,Y)
+#define _FP_DIV_MEAT_D(R,X,Y) _FP_DIV_MEAT_2_udiv(D,R,X,Y)
+
+#define _FP_NANFRAC_S ((_FP_QNANBIT_S << 1) - 1)
+#define _FP_NANFRAC_D ((_FP_QNANBIT_D << 1) - 1), -1
+#define _FP_NANSIGN_S 0
+#define _FP_NANSIGN_D 0
+#define _FP_QNANNEGATEDP 0
+#define _FP_KEEPNANFRACP 1
+
+/* Someone please check this. */
+#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP) \
+ do { \
+ if ((_FP_FRAC_HIGH_RAW_##fs(X) & _FP_QNANBIT_##fs) \
+ && !(_FP_FRAC_HIGH_RAW_##fs(Y) & _FP_QNANBIT_##fs)) \
+ { \
+ R##_s = Y##_s; \
+ _FP_FRAC_COPY_##wc(R,Y); \
+ } \
+ else \
+ { \
+ R##_s = X##_s; \
+ _FP_FRAC_COPY_##wc(R,X); \
+ } \
+ R##_c = FP_CLS_NAN; \
+ } while (0)
+
+#define __LITTLE_ENDIAN 1234
+#define __BIG_ENDIAN 4321
+
+# define __BYTE_ORDER __LITTLE_ENDIAN
+
+/* Define ALIASNAME as a strong alias for NAME. */
+# define strong_alias(name, aliasname) _strong_alias(name, aliasname)
+# define _strong_alias(name, aliasname) \
+ extern __typeof (name) aliasname __attribute__ ((alias (#name)));
-LIB2ADD_ST = $(srcdir)/config/cris/mulsi3.S
+LIB2ADD_ST = $(srcdir)/config/cris/mulsi3.S $(srcdir)/config/cris/umulsidi3.S
CRTSTUFF_T_CFLAGS = -moverride-best-lib-options
--- /dev/null
+;; Copyright (C) 2001, 2004, 2013 Free Software Foundation, Inc.
+;;
+;; This file is part of GCC.
+;;
+;; GCC 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.
+;;
+;; GCC 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/>.
+;;
+;; This code is derived from mulsi3.S, observing that the mstep*16-based
+;; multiplications there, from which it is formed, are actually
+;; zero-extending; in gcc-speak "umulhisi3". The difference to *this*
+;; function is just a missing top mstep*16 sequence and shifts and 64-bit
+;; additions for the high part. Compared to an implementation based on
+;; calling __Mul four times (see default implementation of umul_ppmm in
+;; longlong.h), this will complete in a time between a fourth and a third
+;; of that, assuming the value-based optimizations don't strike. If they
+;; all strike there (very often) but none here, we still win, though by a
+;; lesser margin, due to lesser total overhead.
+
+#define L(x) .x
+#define CONCAT1(a, b) CONCAT2(a, b)
+#define CONCAT2(a, b) a ## b
+
+#ifdef __USER_LABEL_PREFIX__
+# define SYM(x) CONCAT1 (__USER_LABEL_PREFIX__, x)
+#else
+# define SYM(x) x
+#endif
+
+ .global SYM(__umulsidi3)
+ .type SYM(__umulsidi3),@function
+SYM(__umulsidi3):
+#if defined (__CRIS_arch_version) && __CRIS_arch_version >= 10
+;; Can't have the mulu.d last on a cache-line, due to a hardware bug. See
+;; the documentation for -mmul-bug-workaround.
+;; Not worthwhile to conditionalize here.
+ .p2alignw 2,0x050f
+ mulu.d $r11,$r10
+ ret
+ move $mof,$r11
+#else
+ move.d $r11,$r9
+ bound.d $r10,$r9
+ cmpu.w 65535,$r9
+ bls L(L3)
+ move.d $r10,$r12
+
+ move.d $r10,$r13
+ movu.w $r11,$r9 ; ab*cd = (a*c)<<32 (a*d + b*c)<<16 + b*d
+
+;; We're called for floating point numbers very often with the "low" 16
+;; bits zero, so it's worthwhile to optimize for that.
+
+ beq L(L6) ; d == 0?
+ lslq 16,$r13
+
+ beq L(L7) ; b == 0?
+ clear.w $r10
+
+ mstep $r9,$r13 ; d*b
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+ mstep $r9,$r13
+
+L(L7):
+ test.d $r10
+ mstep $r9,$r10 ; d*a
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+ mstep $r9,$r10
+
+;; d*a in $r10, d*b in $r13, ab in $r12 and cd in $r11
+;; $r9 = d, need to do b*c and a*c; we can drop d.
+;; so $r9 is up for use and we can shift down $r11 as the mstep
+;; source for the next mstep-part.
+
+L(L8):
+ lsrq 16,$r11
+ move.d $r12,$r9
+ lslq 16,$r9
+ beq L(L9) ; b == 0?
+ mstep $r11,$r9
+
+ mstep $r11,$r9 ; b*c
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+ mstep $r11,$r9
+L(L9):
+
+;; d*a in $r10, d*b in $r13, c*b in $r9, ab in $r12 and c in $r11,
+;; need to do a*c. We want that to end up in $r11, so we shift up $r11 to
+;; now use as the destination operand. We'd need a test insn to update N
+;; to do it the other way round.
+
+ lsrq 16,$r12
+ lslq 16,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+ mstep $r12,$r11
+
+;; d*a in $r10, d*b in $r13, c*b in $r9, a*c in $r11 ($r12 free).
+;; Need (a*d + b*c)<<16 + b*d into $r10 and
+;; a*c + (a*d + b*c)>>16 plus carry from the additions into $r11.
+
+ add.d $r9,$r10 ; (a*d + b*c) - may produce a carry.
+ scs $r12 ; The carry corresponds to bit 16 of $r11.
+ lslq 16,$r12
+ add.d $r12,$r11 ; $r11 = a*c + carry from (a*d + b*c).
+
+#if defined (__CRIS_arch_version) && __CRIS_arch_version >= 8
+ swapw $r10
+ addu.w $r10,$r11 ; $r11 = a*c + (a*d + b*c) >> 16 including carry.
+ clear.w $r10 ; $r10 = (a*d + b*c) << 16
+#else
+ move.d $r10,$r9
+ lsrq 16,$r9
+ add.d $r9,$r11 ; $r11 = a*c + (a*d + b*c) >> 16 including carry.
+ lslq 16,$r10 ; $r10 = (a*d + b*c) << 16
+#endif
+ add.d $r13,$r10 ; $r10 = (a*d + b*c) << 16 + b*d - may produce a carry.
+ scs $r9
+ ret
+ add.d $r9,$r11 ; Last carry added to the high-order 32 bits.
+
+L(L6):
+ clear.d $r13
+ ba L(L8)
+ clear.d $r10
+
+L(L11):
+ clear.d $r10
+ ret
+ clear.d $r11
+
+L(L3):
+;; Form the maximum in $r10, by knowing the minimum, $r9.
+;; (We don't know which one of $r10 or $r11 it is.)
+;; Check if the largest operand is still just 16 bits.
+
+ xor $r9,$r10
+ xor $r11,$r10
+ cmpu.w 65535,$r10
+ bls L(L5)
+ movu.w $r9,$r13
+
+;; We have ab*cd = (a*c)<<32 + (a*d + b*c)<<16 + b*d, but c==0
+;; so we only need (a*d)<<16 + b*d with d = $r13, ab = $r10.
+;; Remember that the upper part of (a*d)<<16 goes into the lower part
+;; of $r11 and there may be a carry from adding the low 32 parts.
+ beq L(L11) ; d == 0?
+ move.d $r10,$r9
+
+ lslq 16,$r9
+ beq L(L10) ; b == 0?
+ clear.w $r10
+
+ mstep $r13,$r9 ; b*d
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+ mstep $r13,$r9
+L(L10):
+ test.d $r10
+ mstep $r13,$r10 ; a*d
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ move.d $r10,$r11
+ lsrq 16,$r11
+ lslq 16,$r10
+ add.d $r9,$r10
+ scs $r12
+ ret
+ add.d $r12,$r11
+
+L(L5):
+;; We have ab*cd = (a*c)<<32 + (a*d + b*c)<<16 + b*d, but a and c==0
+;; so b*d (with min=b=$r13, max=d=$r10) it is. As it won't overflow the
+;; 32-bit part, just set $r11 to 0.
+
+ lslq 16,$r10
+ clear.d $r11
+
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ mstep $r13,$r10
+ ret
+ mstep $r13,$r10
+#endif
+L(Lfe1):
+ .size SYM(__umulsidi3),L(Lfe1)-SYM(__umulsidi3)
#endif /* defined (__AVR__) */
-#if defined (__CRIS__) && __CRIS_arch_version >= 3
+#if defined (__CRIS__)
+
+#if __CRIS_arch_version >= 3
#define count_leading_zeros(COUNT, X) ((COUNT) = __builtin_clz (X))
+#define COUNT_LEADING_ZEROS_0 32
+#endif /* __CRIS_arch_version >= 3 */
+
#if __CRIS_arch_version >= 8
#define count_trailing_zeros(COUNT, X) ((COUNT) = __builtin_ctz (X))
-#endif
-#endif /* __CRIS__ */
+#endif /* __CRIS_arch_version >= 8 */
+
+#if __CRIS_arch_version >= 10
+#define __umulsidi3(u,v) ((UDItype)(USItype) (u) * (UDItype)(USItype) (v))
+#else
+#define __umulsidi3 __umulsidi3
+extern UDItype __umulsidi3 (USItype, USItype);
+#endif /* __CRIS_arch_version >= 10 */
+
+#define umul_ppmm(w1, w0, u, v) \
+ do { \
+ UDItype __x = __umulsidi3 (u, v); \
+ (w0) = (USItype) (__x); \
+ (w1) = (USItype) (__x >> 32); \
+ } while (0)
+
+/* FIXME: defining add_ssaaaa and sub_ddmmss should be advantageous for
+ DFmode ("double" intrinsics, avoiding two of the three insns handling
+ carry), but defining them as open-code C composing and doing the
+ operation in DImode (UDImode) shows that the DImode needs work:
+ register pressure from requiring neighboring registers and the
+ traffic to and from them come to dominate, in the 4.7 series. */
+
+#endif /* defined (__CRIS__) */
#if defined (__hppa) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
projects / platform / upstream / gcc.git / commitdiff