Hi,
on 2023/12/11 09:49, HAO CHEN GUI wrote:
> Hi,
> The patch corrects the definition of
> TARGET_EFFICIENT_OVERLAPPING_UNALIGNED and change its name to a
> comprehensible name.
>
> Bootstrapped and tested on x86 and powerpc64-linux BE and LE with no
> regressions. Is this OK for trunk?
>
> Thanks
> Gui Haochen
>
> ChangeLog
> rs6000: Correct definition of macro of fixed point efficient unaligned
>
> Marco TARGET_EFFICIENT_OVERLAPPING_UNALIGNED is used in rs6000-string.cc to
> guard whether a platform is efficient on fixed point unaligned load/store.
> It's originally defined by TARGET_EFFICIENT_UNALIGNED_VSX which is enabled
> from P8 and can be disabled by mno-vsx option. So the definition is wrong.
> This patch corrects the problem and define it by "!STRICT_ALIGNMENT" which
> is true on P7 BE and P8 above.
I agree it's unexpected that the current TARGET_EFFICIENT_OVERLAPPING_UNALIGNED
is mapped as TARGET_EFFICIENT_UNALIGNED_VSX for scalar int access, but there is
one function rs6000_slow_unaligned_access (for hook slow_unaligned_access), I
expect it can well fit into these places, can we just adopt it? IMHO it helps
the long term maintenance.
>
> gcc/
> * config/rs6000/rs6000.h (TARGET_EFFICIENT_OVERLAPPING_UNALIGNED):
> Rename to...
> (TARGET_EFFICIENT_UNALIGNED_FIXEDPOINT): ...this, set it to
> !STRICT_ALIGNMENT.
> * config/rs6000/rs6000-string.cc (select_block_compare_mode):
> Replace TARGET_EFFICIENT_OVERLAPPING_UNALIGNED with
> TARGET_EFFICIENT_UNALIGNED_FIXEDPOINT.
> (select_block_compare_mode): Likewise.
> (expand_block_compare_gpr): Likewise.
> (expand_block_compare): Likewise.
> (expand_strncmp_gpr_sequence): Likewise.
>
> gcc/testsuite/
> * gcc.target/powerpc/target_efficient_unaligned_fixedpoint-1.c: New.
> * gcc.target/powerpc/target_efficient_unaligned_fixedpoint-2.c: New.
>
> patch.diff
> diff --git a/gcc/config/rs6000/rs6000-string.cc
> b/gcc/config/rs6000/rs6000-string.cc
> index 44a946cd453..d4030854b2a 100644
> --- a/gcc/config/rs6000/rs6000-string.cc
> +++ b/gcc/config/rs6000/rs6000-string.cc
> @@ -305,7 +305,7 @@ select_block_compare_mode (unsigned HOST_WIDE_INT offset,
> else if (bytes == GET_MODE_SIZE (QImode))
> return QImode;
> else if (bytes < GET_MODE_SIZE (SImode)
> - && TARGET_EFFICIENT_OVERLAPPING_UNALIGNED
> + && TARGET_EFFICIENT_UNALIGNED_FIXEDPOINT
> && offset >= GET_MODE_SIZE (SImode) - bytes)
> /* This matches the case were we have SImode and 3 bytes
> and offset >= 1 and permits us to move back one and overlap
> @@ -313,7 +313,7 @@ select_block_compare_mode (unsigned HOST_WIDE_INT offset,
> unwanted bytes off of the input. */
> return SImode;
> else if (word_mode_ok && bytes < UNITS_PER_WORD
> - && TARGET_EFFICIENT_OVERLAPPING_UNALIGNED
> + && TARGET_EFFICIENT_UNALIGNED_FIXEDPOINT
> && offset >= UNITS_PER_WORD-bytes)
> /* Similarly, if we can use DImode it will get matched here and
> can do an overlapping read that ends at the end of the block. */
> @@ -1749,7 +1749,7 @@ expand_block_compare_gpr(unsigned HOST_WIDE_INT bytes,
> unsigned int base_align,
> load_mode_size = GET_MODE_SIZE (load_mode);
> if (bytes >= load_mode_size)
> cmp_bytes = load_mode_size;
> - else if (TARGET_EFFICIENT_OVERLAPPING_UNALIGNED)
> + else if (TARGET_EFFICIENT_UNALIGNED_FIXEDPOINT)
> {
> /* Move this load back so it doesn't go past the end.
> P8/P9 can do this efficiently. */
> @@ -2026,7 +2026,7 @@ expand_block_compare (rtx operands[])
> /* The code generated for p7 and older is not faster than glibc
> memcmp if alignment is small and length is not short, so bail
> out to avoid those conditions. */
> - if (!TARGET_EFFICIENT_OVERLAPPING_UNALIGNED
> + if (!TARGET_EFFICIENT_UNALIGNED_FIXEDPOINT
> && ((base_align == 1 && bytes > 16)
> || (base_align == 2 && bytes > 32)))
> return false;
> @@ -2168,7 +2168,7 @@ expand_strncmp_gpr_sequence (unsigned HOST_WIDE_INT
> bytes_to_compare,
> load_mode_size = GET_MODE_SIZE (load_mode);
> if (bytes_to_compare >= load_mode_size)
> cmp_bytes = load_mode_size;
> - else if (TARGET_EFFICIENT_OVERLAPPING_UNALIGNED)
> + else if (TARGET_EFFICIENT_UNALIGNED_FIXEDPOINT)
> {
> /* Move this load back so it doesn't go past the end.
> P8/P9 can do this efficiently. */
> diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
> index 326c45221e9..2f3a82942c1 100644
> --- a/gcc/config/rs6000/rs6000.h
> +++ b/gcc/config/rs6000/rs6000.h
> @@ -483,9 +483,9 @@ extern int rs6000_vector_align[];
> #define TARGET_NO_SF_SUBREG TARGET_DIRECT_MOVE_64BIT
> #define TARGET_ALLOW_SF_SUBREG (!TARGET_DIRECT_MOVE_64BIT)
>
> -/* This wants to be set for p8 and newer. On p7, overlapping unaligned
> - loads are slow. */
> -#define TARGET_EFFICIENT_OVERLAPPING_UNALIGNED TARGET_EFFICIENT_UNALIGNED_VSX
> +/* Like TARGET_EFFICIENT_UNALIGNED_VSX, indicates if unaligned fixed point
> + loads/stores are efficient. */
> +#define TARGET_EFFICIENT_UNALIGNED_FIXEDPOINT (!STRICT_ALIGNMENT)
>
> /* Byte/char syncs were added as phased in for ISA 2.06B, but are not present
> in power7, so conditionalize them on p8 features. TImode syncs need quad
> diff --git
> a/gcc/testsuite/gcc.target/powerpc/target_efficient_unaligned_fixedpoint-1.c
> b/gcc/testsuite/gcc.target/powerpc/target_efficient_unaligned_fixedpoint-1.c
> new file mode 100644
> index 00000000000..e090755e23f
> --- /dev/null
> +++
> b/gcc/testsuite/gcc.target/powerpc/target_efficient_unaligned_fixedpoint-1.c
Nit: I found we have block-move-{1,2}, can we make these cases as
block-cmp-{1,2}.c,
put some details as comments in these test cases themselves. The potential
future
test cases for this block comparison enhancement can have the same naming style
then.
> @@ -0,0 +1,8 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mdejagnu-cpu=power8 -mno-vsx" } */
> +/* { dg-final { scan-assembler-not {\mbl memcmp\M} } } */
> +
> +int foo (const char* s1, const char* s2)
> +{
> + return __builtin_memcmp (s1, s2, 20);
> +}
> diff --git
> a/gcc/testsuite/gcc.target/powerpc/target_efficient_unaligned_fixedpoint-2.c
> b/gcc/testsuite/gcc.target/powerpc/target_efficient_unaligned_fixedpoint-2.c
> new file mode 100644
> index 00000000000..c7ebcd90a0b
> --- /dev/null
> +++
> b/gcc/testsuite/gcc.target/powerpc/target_efficient_unaligned_fixedpoint-2.c
> @@ -0,0 +1,8 @@
> +/* { dg-do compile { target le } } */
Since STRICT_ALIGNMENT is defined as 0 on non-sysv4, I'm not sure if it's
possible to
have such combination (in future) and make it fail, maybe we can instead add
with one
explicit -mstrict-align and check.
BR,
Kewen
> +/* { dg-options "-O2 -mdejagnu-cpu=power7 -mno-vsx" } */
> +/* { dg-final { scan-assembler-times {\mbl memcmp\M} 1 } } */
> +
> +int foo (const char* s1, const char* s2)
> +{
> + return __builtin_memcmp (s1, s2, 20);
> +}
>
