On Tue, Jan 8, 2019 at 3:39 PM H.J. Lu <hjl.to...@gmail.com> wrote:
>
> On Mon, Jan 7, 2019 at 11:12 PM Uros Bizjak <ubiz...@gmail.com> wrote:
> >
> > On Mon, Jan 7, 2019 at 6:40 PM H.J. Lu <hongjiu...@intel.com> wrote:
> > >
> > > There is no need to generate vzeroupper if caller uses upper bits of
> > > AVX/AVX512 registers, We track caller's avx_u128_state and avoid
> > > vzeroupper when caller's avx_u128_state is AVX_U128_DIRTY.
> > >
> > > Tested on i686 and x86-64 with and without --with-arch=native.
> > >
> > > OK for trunk?
> >
> > In principle OK, but I think we don't have to cache the result of
> > ix86_avx_u128_mode_entry. Simply call the function from
> > ix86_avx_u128_mode_exit; it is a simple function, so I guess we can
> > afford to re-call it one more time per function.
>
> Do we really need ix86_avx_u128_mode_entry? We can just
> set entry state to AVX_U128_CLEAN and set exit state to
> AVX_U128_DIRTY if caller returns AVX/AVX512 register or passes
> AVX/AVX512 registers to callee.
>
> Does this patch look OK?
No, the compiler is then free to move optimal insertion point at the
beginning of the function.
Uros.
> Thanks.
>
> H.J.
> --
> diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
> index d01278d866f..1ac89fd2eb5 100644
> --- a/gcc/config/i386/i386.c
> +++ b/gcc/config/i386/i386.c
> @@ -19087,25 +19087,6 @@ ix86_dirflag_mode_entry (void)
> return X86_DIRFLAG_RESET;
> }
>
> -static int
> -ix86_avx_u128_mode_entry (void)
> -{
> - tree arg;
> -
> - /* Entry mode is set to AVX_U128_DIRTY if there are
> - 256bit or 512bit modes used in function arguments. */
> - for (arg = DECL_ARGUMENTS (current_function_decl); arg;
> - arg = TREE_CHAIN (arg))
> - {
> - rtx incoming = DECL_INCOMING_RTL (arg);
> -
> - if (incoming && ix86_check_avx_upper_register (incoming))
> - return AVX_U128_DIRTY;
> - }
> -
> - return AVX_U128_CLEAN;
> -}
> -
> /* Return a mode that ENTITY is assumed to be
> switched to at function entry. */
>
> @@ -19117,7 +19098,7 @@ ix86_mode_entry (int entity)
> case X86_DIRFLAG:
> return ix86_dirflag_mode_entry ();
> case AVX_U128:
> - return ix86_avx_u128_mode_entry ();
> + return AVX_U128_CLEAN;
> case I387_TRUNC:
> case I387_FLOOR:
> case I387_CEIL:
> @@ -19130,13 +19111,24 @@ ix86_mode_entry (int entity)
> static int
> ix86_avx_u128_mode_exit (void)
> {
> + /* Exit mode is set to AVX_U128_DIRTY if there are 256bit or 512bit
> + modes used in function arguments or function return.. */
> rtx reg = crtl->return_rtx;
>
> - /* Exit mode is set to AVX_U128_DIRTY if there are 256bit
> - or 512 bit modes used in the function return register. */
> if (reg && ix86_check_avx_upper_register (reg))
> return AVX_U128_DIRTY;
>
> + tree arg;
> +
> + for (arg = DECL_ARGUMENTS (current_function_decl); arg;
> + arg = TREE_CHAIN (arg))
> + {
> + rtx incoming = DECL_INCOMING_RTL (arg);
> +
> + if (incoming && ix86_check_avx_upper_register (incoming))
> + return AVX_U128_DIRTY;
> + }
> +
> return AVX_U128_CLEAN;
> }
