Message ID | ZWsPafxjNGE9t0M1@tucnak |
---|---|
State | New |
Headers | show |
Series | lower-bitint: Fix up lower_addsub_overflow [PR112807] | expand |
> Am 02.12.2023 um 12:05 schrieb Jakub Jelinek <jakub@redhat.com>: > > Hi! > > lower_addsub_overflow uses handle_cast or handle_operand to extract current > limb from the operands. Both of those functions heavily assume that they > return a large or huge BITINT_TYPE. The problem in the testcase is that > this is violated. Normally, lower_addsub_overflow isn't even called if > neither the return's type element type nor any of the operand is large/huge > BITINT_TYPE (on x86_64 129+ bits), for middle BITINT_TYPE (on x86_64 65-128 > bits) some other code casts such operands to {,unsigned }__int128. > In the testcase the result is complex unsigned, so small, but one of the > arguments is _BitInt(256), so lower_addsub_overflow is called. But > range_for_prec asks the ranger for ranges of the operands and in this > case the first argument has [0, 0xffffffff] range and second [-2, 1], so > unsigned 32-bit and signed 2-bit, and in such case the code for > handle_operand/handle_cast purposes would use the _BitInt(256) type for the > first operand (ok), but because prec3 aka maximum of result precision and > the VRP computes ranges of the arguments is 32, use cast to 32-bit > BITINT_TYPE, which is why it didn't work correctly. > The following patch ensures that in such cases we use handle_cast to the > type of the other argument. > > Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk? Ok > Perhaps incrementally, we could try to optimize this in an earlier phase, > see that while the .{ADD,SUB}_OVERFLOW has large/huge _BitInt argument, as > ranger says it fits into a smaller type, add a cast of the larger argument > to the smaller precision type in which it fits. Either in > gimple_lower_bitint, or match.pd. An argument for the latter is that e.g. > complex unsigned .ADD_OVERFLOW (unsigned_long_long_arg, unsigned_arg) > where ranger says unsigned_long_long_arg fits into unsigned 32-bit could > be also more efficient as > .ADD_OVERFLOW ((unsigned) unsigned_long_long_arg, unsigned_arg) Sounds reasonable. Richard > 2023-12-02 Jakub Jelinek <jakub@redhat.com> > > PR middle-end/112807 > * gimple-lower-bitint.cc (bitint_large_huge::lower_addsub_overflow): > When choosing type0 and type1 types, if prec3 has small/middle bitint > kind, use maximum of type0 and type1's precision instead of prec3. > > * gcc.dg/bitint-46.c: New test. > > --- gcc/gimple-lower-bitint.cc.jj 2023-12-01 10:56:45.535228688 +0100 > +++ gcc/gimple-lower-bitint.cc 2023-12-01 18:38:24.633663667 +0100 > @@ -3911,15 +3911,18 @@ bitint_large_huge::lower_addsub_overflow > > tree type0 = TREE_TYPE (arg0); > tree type1 = TREE_TYPE (arg1); > - if (TYPE_PRECISION (type0) < prec3) > + int prec5 = prec3; > + if (bitint_precision_kind (prec5) < bitint_prec_large) > + prec5 = MAX (TYPE_PRECISION (type0), TYPE_PRECISION (type1)); > + if (TYPE_PRECISION (type0) < prec5) > { > - type0 = build_bitint_type (prec3, TYPE_UNSIGNED (type0)); > + type0 = build_bitint_type (prec5, TYPE_UNSIGNED (type0)); > if (TREE_CODE (arg0) == INTEGER_CST) > arg0 = fold_convert (type0, arg0); > } > - if (TYPE_PRECISION (type1) < prec3) > + if (TYPE_PRECISION (type1) < prec5) > { > - type1 = build_bitint_type (prec3, TYPE_UNSIGNED (type1)); > + type1 = build_bitint_type (prec5, TYPE_UNSIGNED (type1)); > if (TREE_CODE (arg1) == INTEGER_CST) > arg1 = fold_convert (type1, arg1); > } > --- gcc/testsuite/gcc.dg/bitint-46.c.jj 2023-12-01 18:47:12.460245617 +0100 > +++ gcc/testsuite/gcc.dg/bitint-46.c 2023-12-01 18:46:41.297683578 +0100 > @@ -0,0 +1,32 @@ > +/* PR middle-end/112807 */ > +/* { dg-do compile { target bitint } } */ > +/* { dg-options "-std=gnu23 -O2" } */ > + > +#if __BITINT_MAXWIDTH__ >= 256 > +__attribute__((noipa)) int > +foo (_BitInt (256) a, _BitInt (2) b) > +{ > + if (a < 0 || a > ~0U) > + return -1; > + return __builtin_sub_overflow_p (a, b, 0); > +} > +#endif > + > +int > +main () > +{ > +#if __BITINT_MAXWIDTH__ >= 256 > + if (foo (-5wb, 1wb) != -1 > + || foo (1 + (_BitInt (256)) ~0U, -2) != -1 > + || foo (0, 0) != 0 > + || foo (0, 1) != 0 > + || foo (0, -1) != 0 > + || foo (~0U, 0) != 1 > + || foo (__INT_MAX__, 0) != 0 > + || foo (__INT_MAX__, -1) != 1 > + || foo (1 + (_BitInt (256)) __INT_MAX__, 0) != 1 > + || foo (1 + (_BitInt (256)) __INT_MAX__, 1) != 0 > + || foo (1 + (_BitInt (256)) __INT_MAX__, -2) != 1) > + __builtin_abort (); > +#endif > +} > > Jakub >
--- gcc/gimple-lower-bitint.cc.jj 2023-12-01 10:56:45.535228688 +0100 +++ gcc/gimple-lower-bitint.cc 2023-12-01 18:38:24.633663667 +0100 @@ -3911,15 +3911,18 @@ bitint_large_huge::lower_addsub_overflow tree type0 = TREE_TYPE (arg0); tree type1 = TREE_TYPE (arg1); - if (TYPE_PRECISION (type0) < prec3) + int prec5 = prec3; + if (bitint_precision_kind (prec5) < bitint_prec_large) + prec5 = MAX (TYPE_PRECISION (type0), TYPE_PRECISION (type1)); + if (TYPE_PRECISION (type0) < prec5) { - type0 = build_bitint_type (prec3, TYPE_UNSIGNED (type0)); + type0 = build_bitint_type (prec5, TYPE_UNSIGNED (type0)); if (TREE_CODE (arg0) == INTEGER_CST) arg0 = fold_convert (type0, arg0); } - if (TYPE_PRECISION (type1) < prec3) + if (TYPE_PRECISION (type1) < prec5) { - type1 = build_bitint_type (prec3, TYPE_UNSIGNED (type1)); + type1 = build_bitint_type (prec5, TYPE_UNSIGNED (type1)); if (TREE_CODE (arg1) == INTEGER_CST) arg1 = fold_convert (type1, arg1); } --- gcc/testsuite/gcc.dg/bitint-46.c.jj 2023-12-01 18:47:12.460245617 +0100 +++ gcc/testsuite/gcc.dg/bitint-46.c 2023-12-01 18:46:41.297683578 +0100 @@ -0,0 +1,32 @@ +/* PR middle-end/112807 */ +/* { dg-do compile { target bitint } } */ +/* { dg-options "-std=gnu23 -O2" } */ + +#if __BITINT_MAXWIDTH__ >= 256 +__attribute__((noipa)) int +foo (_BitInt (256) a, _BitInt (2) b) +{ + if (a < 0 || a > ~0U) + return -1; + return __builtin_sub_overflow_p (a, b, 0); +} +#endif + +int +main () +{ +#if __BITINT_MAXWIDTH__ >= 256 + if (foo (-5wb, 1wb) != -1 + || foo (1 + (_BitInt (256)) ~0U, -2) != -1 + || foo (0, 0) != 0 + || foo (0, 1) != 0 + || foo (0, -1) != 0 + || foo (~0U, 0) != 1 + || foo (__INT_MAX__, 0) != 0 + || foo (__INT_MAX__, -1) != 1 + || foo (1 + (_BitInt (256)) __INT_MAX__, 0) != 1 + || foo (1 + (_BitInt (256)) __INT_MAX__, 1) != 0 + || foo (1 + (_BitInt (256)) __INT_MAX__, -2) != 1) + __builtin_abort (); +#endif +}