It turned out that this patch depended on another one from earlier, so I have backported that to ARM/aarch64-4.7-branch too.
http://gcc.gnu.org/ml/gcc-patches/2012-04/msg00452.html Cheers, Ian > -----Original Message----- > From: Ian Bolton [mailto:ian.bol...@arm.com] > Sent: 23 November 2012 18:09 > To: gcc-patches@gcc.gnu.org > Subject: [PATCH, AArch64 4.7] Backport of __builtin_bswap16 > optimisation > > I had already committed my testcase for this for aarch64, but > it depends on this patch that doesn't yet exist in 4.7, so I > backported to our ARM/aarch64-4.7-branch. > > Cheers, > Ian > > > > From: > http://gcc.gnu.org/git/?p=gcc.git;a=commitdiff;h=f811051bf87b1de7804c19 > c8192d0d099d157145 > > diff --git a/gcc/ChangeLog b/gcc/ChangeLog > index be34843..ce08fce 100644 > --- a/gcc/ChangeLog > +++ b/gcc/ChangeLog > @@ -1,3 +1,8 @@ > +2012-09-26 Christophe Lyon <christophe.l...@linaro.org> > + > + * tree-ssa-math-opts.c (bswap_stats): Add found_16bit field. > + (execute_optimize_bswap): Add support for builtin_bswap16. > + > 2012-09-26 Richard Guenther <rguent...@suse.de> > > * tree.h (DECL_IS_BUILTIN): Compare LOCATION_LOCUS. > diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog > index 3aad841..7c96949 100644 > --- a/gcc/testsuite/ChangeLog > +++ b/gcc/testsuite/ChangeLog > @@ -1,3 +1,7 @@ > +2012-09-26 Christophe Lyon <christophe.l...@linaro.org> > + > + * gcc.target/arm/builtin-bswap16-1.c: New testcase. > + > 2012-09-25 Segher Boessenkool <seg...@kernel.crashing.org> > > PR target/51274 > diff --git a/gcc/testsuite/gcc.target/arm/builtin-bswap16-1.c > b/gcc/testsuite/gcc.target/arm/builtin-bswap16-1.c > new file mode 100644 > index 0000000..6920f00 > --- /dev/null > +++ b/gcc/testsuite/gcc.target/arm/builtin-bswap16-1.c > @@ -0,0 +1,15 @@ > +/* { dg-do compile } */ > +/* { dg-options "-O2" } */ > +/* { dg-require-effective-target arm_arch_v6_ok } */ > +/* { dg-add-options arm_arch_v6 } */ > +/* { dg-final { scan-assembler-not "orr\[ \t\]" } } */ > + > +unsigned short swapu16_1 (unsigned short x) > +{ > + return (x << 8) | (x >> 8); > +} > + > +unsigned short swapu16_2 (unsigned short x) > +{ > + return (x >> 8) | (x << 8); > +} > diff --git a/gcc/tree-ssa-math-opts.c b/gcc/tree-ssa-math-opts.c > index 16ff397..d9f4e9e 100644 > --- a/gcc/tree-ssa-math-opts.c > +++ b/gcc/tree-ssa-math-opts.c > @@ -154,6 +154,9 @@ static struct > > static struct > { > + /* Number of hand-written 16-bit bswaps found. */ > + int found_16bit; > + > /* Number of hand-written 32-bit bswaps found. */ > int found_32bit; > > @@ -1803,9 +1806,9 @@ static unsigned int > execute_optimize_bswap (void) > { > basic_block bb; > - bool bswap32_p, bswap64_p; > + bool bswap16_p, bswap32_p, bswap64_p; > bool changed = false; > - tree bswap32_type = NULL_TREE, bswap64_type = NULL_TREE; > + tree bswap16_type = NULL_TREE, bswap32_type = NULL_TREE, > bswap64_type = NULL_TREE; > > if (BITS_PER_UNIT != 8) > return 0; > @@ -1813,17 +1816,25 @@ execute_optimize_bswap (void) > if (sizeof (HOST_WIDEST_INT) < 8) > return 0; > > + bswap16_p = (builtin_decl_explicit_p (BUILT_IN_BSWAP16) > + && optab_handler (bswap_optab, HImode) != > CODE_FOR_nothing); > bswap32_p = (builtin_decl_explicit_p (BUILT_IN_BSWAP32) > && optab_handler (bswap_optab, SImode) != > CODE_FOR_nothing); > bswap64_p = (builtin_decl_explicit_p (BUILT_IN_BSWAP64) > && (optab_handler (bswap_optab, DImode) != > CODE_FOR_nothing > || (bswap32_p && word_mode == SImode))); > > - if (!bswap32_p && !bswap64_p) > + if (!bswap16_p && !bswap32_p && !bswap64_p) > return 0; > > /* Determine the argument type of the builtins. The code later on > assumes that the return and argument type are the same. */ > + if (bswap16_p) > + { > + tree fndecl = builtin_decl_explicit (BUILT_IN_BSWAP16); > + bswap16_type = TREE_VALUE (TYPE_ARG_TYPES (TREE_TYPE (fndecl))); > + } > + > if (bswap32_p) > { > tree fndecl = builtin_decl_explicit (BUILT_IN_BSWAP32); > @@ -1863,6 +1874,13 @@ execute_optimize_bswap (void) > > switch (type_size) > { > + case 16: > + if (bswap16_p) > + { > + fndecl = builtin_decl_explicit (BUILT_IN_BSWAP16); > + bswap_type = bswap16_type; > + } > + break; > case 32: > if (bswap32_p) > { > @@ -1890,7 +1908,9 @@ execute_optimize_bswap (void) > continue; > > changed = true; > - if (type_size == 32) > + if (type_size == 16) > + bswap_stats.found_16bit++; > + else if (type_size == 32) > bswap_stats.found_32bit++; > else > bswap_stats.found_64bit++; > @@ -1935,6 +1955,8 @@ execute_optimize_bswap (void) > } > } > > + statistics_counter_event (cfun, "16-bit bswap implementations > found", > + bswap_stats.found_16bit); > statistics_counter_event (cfun, "32-bit bswap implementations > found", > bswap_stats.found_32bit); > statistics_counter_event (cfun, "64-bit bswap implementations > found",
