[gcc(refs/users/aoliva/heads/testme)] -finline-stringops: check base blksize for memset [PR112778]
Alexandre Oliva
aoliva@gcc.gnu.org
Mon Dec 11 16:17:09 GMT 2023
https://gcc.gnu.org/g:9d04e48769886a4ecb0aa1d45ca483baa68dfc00
commit 9d04e48769886a4ecb0aa1d45ca483baa68dfc00
Author: Alexandre Oliva <oliva@adacore.com>
Date: Fri Dec 8 21:41:47 2023 -0300
-finline-stringops: check base blksize for memset [PR112778]
The recently-added logic for -finline-stringops=memset introduced an
assumption that doesn't necessarily hold, namely, that
can_store_by_pieces of a larger size implies can_store_by_pieces by
smaller sizes. Checks for all sizes the by-multiple-pieces machinery
might use before committing to an expansion pattern.
for gcc/ChangeLog
PR target/112778
* builtins.cc (can_store_by_multiple_pieces): New.
(try_store_by_multiple_pieces): Call it.
for gcc/testsuite/ChangeLog
PR target/112778
* gcc.dg/inline-mem-cmp-pr112778.c: New.
Diff:
---
gcc/builtins.cc | 57 ++++++++++++++++++++++----
gcc/expr.cc | 14 +++----
gcc/testsuite/gcc.dg/inline-mem-cmp-pr112778.c | 10 +++++
3 files changed, 63 insertions(+), 18 deletions(-)
diff --git a/gcc/builtins.cc b/gcc/builtins.cc
index 12a535d313f..f6c96498f07 100644
--- a/gcc/builtins.cc
+++ b/gcc/builtins.cc
@@ -4284,6 +4284,40 @@ expand_builtin_memset (tree exp, rtx target, machine_mode mode)
return expand_builtin_memset_args (dest, val, len, target, mode, exp);
}
+/* Check that store_by_pieces allows BITS + LEN (so that we don't
+ expand something too unreasonably long), and every power of 2 in
+ BITS. It is assumed that LEN has already been tested by
+ itself. */
+static bool
+can_store_by_multiple_pieces (unsigned HOST_WIDE_INT bits,
+ by_pieces_constfn constfun,
+ void *constfundata, unsigned int align,
+ bool memsetp,
+ unsigned HOST_WIDE_INT len)
+{
+ if (bits
+ && !can_store_by_pieces (bits + len, constfun, constfundata,
+ align, memsetp))
+ return false;
+
+ /* BITS set are expected to be generally in the low range and
+ contiguous. We do NOT want to repeat the test above in case BITS
+ has a single bit set, so we terminate the loop when BITS == BIT.
+ In the unlikely case that BITS has the MSB set, also terminate in
+ case BIT gets shifted out. */
+ for (unsigned HOST_WIDE_INT bit = 1; bit < bits && bit; bit <<= 1)
+ {
+ if ((bits & bit) == 0)
+ continue;
+
+ if (!can_store_by_pieces (bit, constfun, constfundata,
+ align, memsetp))
+ return false;
+ }
+
+ return true;
+}
+
/* Try to store VAL (or, if NULL_RTX, VALC) in LEN bytes starting at TO.
Return TRUE if successful, FALSE otherwise. TO is assumed to be
aligned at an ALIGN-bits boundary. LEN must be a multiple of
@@ -4341,7 +4375,11 @@ try_store_by_multiple_pieces (rtx to, rtx len, unsigned int ctz_len,
else
/* Huh, max_len < min_len? Punt. See pr100843.c. */
return false;
- if (min_len >= blksize)
+ if (min_len >= blksize
+ /* ??? Maybe try smaller fixed-prefix blksizes before
+ punting? */
+ && can_store_by_pieces (blksize, builtin_memset_read_str,
+ &valc, align, true))
{
min_len -= blksize;
min_bits = floor_log2 (min_len);
@@ -4367,8 +4405,9 @@ try_store_by_multiple_pieces (rtx to, rtx len, unsigned int ctz_len,
happen because of the way max_bits and blksize are related, but
it doesn't hurt to test. */
if (blksize > xlenest
- || !can_store_by_pieces (xlenest, builtin_memset_read_str,
- &valc, align, true))
+ || !can_store_by_multiple_pieces (xlenest - blksize,
+ builtin_memset_read_str,
+ &valc, align, true, blksize))
{
if (!(flag_inline_stringops & ILSOP_MEMSET))
return false;
@@ -4386,17 +4425,17 @@ try_store_by_multiple_pieces (rtx to, rtx len, unsigned int ctz_len,
of overflow. */
if (max_bits < orig_max_bits
&& xlenest + blksize >= xlenest
- && can_store_by_pieces (xlenest + blksize,
- builtin_memset_read_str,
- &valc, align, true))
+ && can_store_by_multiple_pieces (xlenest,
+ builtin_memset_read_str,
+ &valc, align, true, blksize))
{
max_loop = true;
break;
}
if (blksize
- && can_store_by_pieces (xlenest,
- builtin_memset_read_str,
- &valc, align, true))
+ && can_store_by_multiple_pieces (xlenest,
+ builtin_memset_read_str,
+ &valc, align, true, 0))
{
max_len += blksize;
min_len += blksize;
diff --git a/gcc/expr.cc b/gcc/expr.cc
index 178b3ec6d5a..4c9e6aa95bc 100644
--- a/gcc/expr.cc
+++ b/gcc/expr.cc
@@ -2451,15 +2451,13 @@ emit_block_move_via_loop (rtx x, rtx y, rtx size,
opt_scalar_int_mode int_move_mode
= int_mode_for_size (incr * BITS_PER_UNIT, 1);
- if (!int_move_mode.exists ()
- || (GET_MODE_BITSIZE (as_a <scalar_int_mode> (int_move_mode))
+ if (!int_move_mode.exists (&move_mode)
+ || (GET_MODE_BITSIZE (as_a <scalar_int_mode> (move_mode))
!= incr * BITS_PER_UNIT))
{
move_mode = BLKmode;
gcc_checking_assert (can_move_by_pieces (incr, align));
}
- else
- move_mode = as_a <scalar_int_mode> (int_move_mode);
x_addr = force_operand (XEXP (x, 0), NULL_RTX);
y_addr = force_operand (XEXP (y, 0), NULL_RTX);
@@ -2705,16 +2703,14 @@ emit_block_cmp_via_loop (rtx x, rtx y, rtx len, tree len_type, rtx target,
opt_scalar_int_mode int_cmp_mode
= int_mode_for_size (incr * BITS_PER_UNIT, 1);
- if (!int_cmp_mode.exists ()
- || (GET_MODE_BITSIZE (as_a <scalar_int_mode> (int_cmp_mode))
+ if (!int_cmp_mode.exists (&cmp_mode)
+ || (GET_MODE_BITSIZE (as_a <scalar_int_mode> (cmp_mode))
!= incr * BITS_PER_UNIT)
- || !can_compare_p (NE, as_a <scalar_int_mode> (int_cmp_mode), ccp_jump))
+ || !can_compare_p (NE, cmp_mode, ccp_jump))
{
cmp_mode = BLKmode;
gcc_checking_assert (incr != 1);
}
- else
- cmp_mode = as_a <scalar_int_mode> (int_cmp_mode);
/* Save the base addresses. */
x_addr = force_operand (XEXP (x, 0), NULL_RTX);
diff --git a/gcc/testsuite/gcc.dg/inline-mem-cmp-pr112778.c b/gcc/testsuite/gcc.dg/inline-mem-cmp-pr112778.c
new file mode 100644
index 00000000000..fdfc5b6f28c
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/inline-mem-cmp-pr112778.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-finline-stringops" } */
+
+char buf[3];
+
+int
+f ()
+{
+ __builtin_memset (buf, 'v', 3);
+}
More information about the Gcc-cvs
mailing list