+2011-06-27 Kai Tietz <ktietz@redhat.com>
+
+ * tree-ssa-math-opts.c (do_shift_rotate): Zero bits
+ out of type precision after operation.
+ (find_bswap): Take for limit value the integer auto-
+ promotion into account.
+
2011-06-27 Eric Botcazou <ebotcazou@adacore.com>
* reorg.c (fill_simple_delay_slots): Use stop_search_p to stop the
+2011-06-27 Kai Tietz <ktietz@redhat.com>
+
+ * gcc.dg/optimize-bswapdi-2.c: New test.
+
2011-06-27 Michael Hope <michael.hope@linaro.org>
Richard Sandiford <richard.sandiford@linaro.org>
--- /dev/null
+/* { dg-do compile { target arm*-*-* alpha*-*-* ia64*-*-* x86_64-*-* s390x-*-* powerpc*-*-* rs6000-*-* } } */
+/* { dg-require-effective-target stdint_types } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -fdump-tree-bswap" } */
+
+#include <stdint.h>
+
+/* A variant via unsigned short. */
+
+uint64_t
+swap64_c (uint64_t x)
+{
+ uint16_t a0 = x >> 48;
+ uint16_t a1 = x >> 32;
+ uint16_t a2 = x >> 16;
+ uint16_t a3 = x;
+
+ return ((uint64_t) (((a0 >> 8) & 0xff) | ((a0 << 8) & 0xff00)))
+ | ((uint64_t) (((a1 >> 8) & 0xff) | ((a1 << 8) & 0xff00)) << 16)
+ | ((uint64_t) (((a2 >> 8) & 0xff) | ((a2 << 8) & 0xff00)) << 32)
+ | ((uint64_t) (((a3 >> 8) & 0xff) | ((a3 << 8) & 0xff00)) << 48);
+}
+
+
+/* { dg-final { scan-tree-dump-times "64 bit bswap implementation found at" 1 "bswap" } } */
+/* { dg-final { cleanup-tree-dump "bswap" } } */
default:
return false;
}
+ /* Zero unused bits for size. */
+ if (n->size < (int)sizeof (HOST_WIDEST_INT))
+ n->n &= ((unsigned HOST_WIDEST_INT)1 << (n->size * BITS_PER_UNIT)) - 1;
return true;
}
struct symbolic_number n;
tree source_expr;
+ int limit;
/* The last parameter determines the depth search limit. It usually
correlates directly to the number of bytes to be touched. We
- increase that number by one here in order to also cover signed ->
- unsigned conversions of the src operand as can be seen in
- libgcc. */
- source_expr = find_bswap_1 (stmt, &n,
- TREE_INT_CST_LOW (
- TYPE_SIZE_UNIT (gimple_expr_type (stmt))) + 1);
+ increase that number by three here in order to also
+ cover signed -> unsigned converions of the src operand as can be seen
+ in libgcc, and for initial shift/and operation of the src operand. */
+ limit = TREE_INT_CST_LOW (TYPE_SIZE_UNIT (gimple_expr_type (stmt)));
+ limit += 1 + (int) ceil_log2 ((unsigned HOST_WIDE_INT) limit);
+ source_expr = find_bswap_1 (stmt, &n, limit);
if (!source_expr)
return NULL_TREE;