Richard Henderson wrote:
While the first set of changes looks good to me, I don't understand those:
> @@ -4728,7 +4733,12 @@ init_alignment_context (struct alignment_context *ac,
> rtx mem,
> ac->aligned = (MEM_ALIGN (mem) >= GET_MODE_BITSIZE (SImode));
>
> if (ac->aligned)
> - ac->memsi = adjust_address (mem, SImode, 0); /* Memory is aligned. */
> + {
> + ac->memsi = adjust_address (mem, SImode, 0); /* Memory is aligned. */
> + ac->shift = const0_rtx;
> + ac->modemask = GEN_INT (GET_MODE_MASK (mode));
> + ac->modemaski = GEN_INT (~GET_MODE_MASK (mode));
> + }
> else
> {
> /* Alignment is unknown. */
> @@ -4755,15 +4765,17 @@ init_alignment_context (struct alignment_context *ac,
> rtx mem,
> ac->shift = expand_simple_binop (SImode, MINUS, ac->shift, byteoffset,
> NULL_RTX, 1, OPTAB_DIRECT);
>
> + /* Shift is the byte count, but we need the bitcount. */
> + ac->shift = expand_simple_binop (SImode, ASHIFT, ac->shift, GEN_INT
> (3),
> + NULL_RTX, 1, OPTAB_DIRECT);
> +
> + /* Calculate masks. */
> + ac->modemask = expand_simple_binop (SImode, ASHIFT,
> + GEN_INT (GET_MODE_MASK (mode)),
> + ac->shift, NULL_RTX, 1, OPTAB_DIRECT);
> + ac->modemaski = expand_simple_unop (SImode, NOT, ac->modemask,
> + NULL_RTX, 1);
> }
> - /* Shift is the byte count, but we need the bitcount. */
> - ac->shift = expand_simple_binop (SImode, MULT, ac->shift, GEN_INT
> (BITS_PER_UNIT),
> - NULL_RTX, 1, OPTAB_DIRECT);
> - /* Calculate masks. */
> - ac->modemask = expand_simple_binop (SImode, ASHIFT,
> - GEN_INT (GET_MODE_MASK (mode)), ac->shift,
> - NULL_RTX, 1, OPTAB_DIRECT);
> - ac->modemaski = expand_simple_unop (SImode, NOT, ac->modemask, NULL_RTX,
> 1);
> }
>
> /* A subroutine of s390_expand_cs_hqi. Insert INS into VAL. If possible,
> @@ -4781,7 +4793,7 @@ s390_two_part_insv (struct alignment_context *ac, rtx
> *seq1, rtx *seq2,
> start_sequence ();
> tmp = copy_to_mode_reg (SImode, val);
> if (s390_expand_insv (tmp, GEN_INT (GET_MODE_BITSIZE (mode)),
> - const0_rtx, ins))
> + GEN_INT (32 - GET_MODE_BITSIZE (mode)), ins))
> {
> *seq1 = NULL;
> *seq2 = get_insns ();
"aligned" accesses do involve the *most significant* part of the word
(on a big-endian machine), which means ac->shift has to be set to
modesize (outer) - modesize (inner), and expand_insv needs to be
called with bitpos 0 (due to bits-big-endian).
When reverting this part of your patch (and together with the EQ/NE fix
pointed out here: http://gcc.gnu.org/ml/gcc-patches/2012-08/msg00170.html),
I can complete a bootstrap/testing cycle without regressions.
(There's still code being generated that looks a bit inefficient, but that's
a different story.)
Bye,
Ulrich
--
Dr. Ulrich Weigand
GNU Toolchain for Linux on System z and Cell BE
[email protected]
