On Wed, Nov 20, 2019 at 12:53 AM Jakub Jelinek <ja...@redhat.com> wrote:
>
> Hi!
>
> The arch= handling in target attribute right now clears almost all isa_flags
> and all isa_flags2, so that later call to ix86_option_override_internal
> can set just the isa options for the specific arch and nothing else.
> Unfortunately, it doesn't work, because next to the ix86_isa_flags{,2}
> we have also ix86_isa_flags{,2}_explicit bitmask and in
> ix86_option_override_internal and say for arch=x86_64 will not try to
> set sse2 isa when we cleared it in ix86_isa_flags but kept it set in
> ix86_isa_flags_explicit.
> So, the testcase works fine with -O2, but doesn't work with -O2 -msse2,
> in the former case ix86_isa_flags_explicit doesn't have MASK_SSE2 bit set,
> but in the latter case it does, so in the former case we end up with
> MASK_SSE2 in ix86_isa_flags, in the latter not in the function with target
> attribute.
>
> The following patch thus clears both ix86_isa_flags{,2} and corresponding
> ix86_isa_flags{,2}_explicit. Also, so that say
> target ("arch=x86_64", "avx") works, the clearing is done when actually
> seeing the arch=, not at the end. target ("avx", "arch=x86_64") will still
> not enable avx, like before, though.
>
> Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
>
> 2019-11-19 Jakub Jelinek <ja...@redhat.com>
>
> PR target/90867
> * config/i386/i386-options.c (ix86_valid_target_attribute_tree): Don't
> clear opts->x_ix86_isa_flags{,2} here...
> (ix86_valid_target_attribute_inner_p): ... but here when seeing
> arch=. Also clear opts->x_ix86_isa_flags{,2}_explicit.
>
> * gcc.target/i386/pr90867.c: New test.
OK, also for backports.
Thanks,
Uros.
> --- gcc/config/i386/i386-options.c.jj 2019-11-18 12:07:54.672405129 +0100
> +++ gcc/config/i386/i386-options.c 2019-11-19 18:43:36.426606458 +0100
> @@ -1147,7 +1147,25 @@ ix86_valid_target_attribute_inner_p (tre
> ret = false;
> }
> else
> - p_strings[opt] = xstrdup (p + opt_len);
> + {
> + p_strings[opt] = xstrdup (p + opt_len);
> + if (opt == IX86_FUNCTION_SPECIFIC_ARCH)
> + {
> + /* If arch= is set, clear all bits in x_ix86_isa_flags,
> + except for ISA_64BIT, ABI_64, ABI_X32, and CODE16
> + and all bits in x_ix86_isa_flags2. */
> + opts->x_ix86_isa_flags &= (OPTION_MASK_ISA_64BIT
> + | OPTION_MASK_ABI_64
> + | OPTION_MASK_ABI_X32
> + | OPTION_MASK_CODE16);
> + opts->x_ix86_isa_flags_explicit &= (OPTION_MASK_ISA_64BIT
> + | OPTION_MASK_ABI_64
> + | OPTION_MASK_ABI_X32
> + | OPTION_MASK_CODE16);
> + opts->x_ix86_isa_flags2 = 0;
> + opts->x_ix86_isa_flags2_explicit = 0;
> + }
> + }
> }
>
> else if (type == ix86_opt_enum)
> @@ -1225,18 +1243,8 @@ ix86_valid_target_attribute_tree (tree f
> /* If we are using the default tune= or arch=, undo the string
> assigned,
> and use the default. */
> if (option_strings[IX86_FUNCTION_SPECIFIC_ARCH])
> - {
> - opts->x_ix86_arch_string
> - = ggc_strdup (option_strings[IX86_FUNCTION_SPECIFIC_ARCH]);
> -
> - /* If arch= is set, clear all bits in x_ix86_isa_flags,
> - except for ISA_64BIT, ABI_64, ABI_X32, and CODE16. */
> - opts->x_ix86_isa_flags &= (OPTION_MASK_ISA_64BIT
> - | OPTION_MASK_ABI_64
> - | OPTION_MASK_ABI_X32
> - | OPTION_MASK_CODE16);
> - opts->x_ix86_isa_flags2 = 0;
> - }
> + opts->x_ix86_arch_string
> + = ggc_strdup (option_strings[IX86_FUNCTION_SPECIFIC_ARCH]);
> else if (!orig_arch_specified)
> opts->x_ix86_arch_string = NULL;
>
> --- gcc/testsuite/gcc.target/i386/pr90867.c.jj 2019-11-19 18:49:11.746592189
> +0100
> +++ gcc/testsuite/gcc.target/i386/pr90867.c 2019-11-19 18:48:17.271406789
> +0100
> @@ -0,0 +1,30 @@
> +/* PR target/90867 */
> +/* { dg-do run { target lp64 } } */
> +/* { dg-options "-O2 -msse2" } */
> +
> +unsigned long long freq = 3600000000UL; /* 3.6 GHz = 3600.0 MHz */
> +
> +__attribute__((noipa)) void
> +bar (double x)
> +{
> + static double d = 3600000000.0;
> + if (x != d)
> + __builtin_abort ();
> + d /= 1000.0;
> +}
> +
> +__attribute__ ((target ("arch=x86-64"))) int
> +foo ()
> +{
> + bar ((double) freq);
> + bar (1e-3 * freq);
> + bar (1e-6 * freq);
> + bar (1e-9 * freq);
> + return 0;
> +}
> +
> +int
> +main ()
> +{
> + return foo ();
> +}
>
> Jakub
>
