Re: [PATCH, vec-tails 01/10] New compiler options

[Richard Biener <richard dot guenther at gmail dot com>]

On Thu, Jun 9, 2016 at 12:36 PM, Ilya Enkovich <enkovich.gnu@gmail.com> wrote:
> Hi Richard,
>
> Do you have some comments on other parts of this series?

It's queued for review ... I'll need a slot of some spare hours to go over it.

Richard.

> Thanks,
> Ilya
>
> 2016-05-20 14:40 GMT+03:00 Ilya Enkovich <enkovich.gnu@gmail.com>:
>> 2016-05-20 14:17 GMT+03:00 Richard Biener <richard.guenther@gmail.com>:
>>> On Fri, May 20, 2016 at 11:50 AM, Ilya Enkovich <enkovich.gnu@gmail.com> wrote:
>>>> 2016-05-20 12:26 GMT+03:00 Richard Biener <richard.guenther@gmail.com>:
>>>>> On Thu, May 19, 2016 at 9:36 PM, Ilya Enkovich <enkovich.gnu@gmail.com> wrote:
>>>>>> Hi,
>>>>>>
>>>>>> This patch introduces new options used for loop epilogues vectorization.
>>>>>
>>>>> Why's that?  This is a bit too much for the casual user and if it is
>>>>> really necessary
>>>>> to control this via options then it is not fine-grained enough.
>>>>>
>>>>> Why doesn't the vectorizer/backend have enough info to decide this itself?
>>>>
>>>> I don't expect casual user to decide which modes to choose.  These controls are
>>>> added for debugging and performance measurement purposes.  I see now I miss
>>>> -ftree-vectorize-epilogues aliased to -ftree-vectorize-epilogues=all.  Surely
>>>> I expect epilogues and short loops vectorization be enabled by default on -O3
>>>> or by -ftree-vectorize-loops.
>>>
>>> Can you make all these --params then?  I think to be useful to users we'd want
>>> them to be loop pragmas rather than options.
>>
>> OK, I'll change it to params.  I didn't think about control via
>> pragmas but will do now.
>>
>> Thanks,
>> Ilya
>>
>>>
>>> Richard.
>>>
>>>> Thanks,
>>>> Ilya
>>>>
>>>>>
>>>>> Richard.
>>>>>
>>>>>> Thanks,
>>>>>> Ilya
>>>>>> --
>>>>>> gcc/
>>>>>>
>>>>>> 2016-05-19  Ilya Enkovich  <ilya.enkovich@intel.com>
>>>>>>
>>>>>>         * common.opt (flag_tree_vectorize_epilogues): New.
>>>>>>         (ftree-vectorize-short-loops): New.
>>>>>>         (ftree-vectorize-epilogues=): New.
>>>>>>         (fno-tree-vectorize-epilogues): New.
>>>>>>         (fvect-epilogue-cost-model=): New.
>>>>>>         * flag-types.h (enum vect_epilogue_mode): New.
>>>>>>         * opts.c (parse_vectorizer_options): New.
>>>>>>         (common_handle_option): Support -ftree-vectorize-epilogues=
>>>>>>         and -fno-tree-vectorize-epilogues options.
>>>>>>
>>>>>>
>>>>>> diff --git a/gcc/common.opt b/gcc/common.opt
>>>>>> index 682cb41..6b83b79 100644
>>>>>> --- a/gcc/common.opt
>>>>>> +++ b/gcc/common.opt
>>>>>> @@ -243,6 +243,10 @@ bool dump_base_name_prefixed = false
>>>>>>  Variable
>>>>>>  bool flag_disable_hsa = false
>>>>>>
>>>>>> +; Flag holding modes for loop epilogue vectorization
>>>>>> +Variable
>>>>>> +unsigned int flag_tree_vectorize_epilogues
>>>>>> +
>>>>>>  ###
>>>>>>  Driver
>>>>>>
>>>>>> @@ -2557,6 +2561,19 @@ ftree-vectorize
>>>>>>  Common Report Var(flag_tree_vectorize) Optimization
>>>>>>  Enable vectorization on trees.
>>>>>>
>>>>>> +ftree-vectorize-short-loops
>>>>>> +Common Report Var(flag_tree_vectorize_short_loops) Optimization
>>>>>> +Enable vectorization of loops with low trip count using masking.
>>>>>> +
>>>>>> +ftree-vectorize-epilogues=
>>>>>> +Common Report Joined Optimization
>>>>>> +Comma separated list of loop epilogue vectorization modes.
>>>>>> +Available modes: combine, mask, nomask.
>>>>>> +
>>>>>> +fno-tree-vectorize-epilogues
>>>>>> +Common RejectNegative Optimization
>>>>>> +Disable epilogues vectorization.
>>>>>> +
>>>>>>  ftree-vectorizer-verbose=
>>>>>>  Common Joined RejectNegative Ignore
>>>>>>  Does nothing.  Preserved for backward compatibility.
>>>>>> @@ -2577,6 +2594,10 @@ fsimd-cost-model=
>>>>>>  Common Joined RejectNegative Enum(vect_cost_model) Var(flag_simd_cost_model) Init(VECT_COST_MODEL_UNLIMITED) Optimization
>>>>>>  Specifies the vectorization cost model for code marked with a simd directive.
>>>>>>
>>>>>> +fvect-epilogue-cost-model=
>>>>>> +Common Joined RejectNegative Enum(vect_cost_model) Var(flag_vect_epilogue_cost_model) Init(VECT_COST_MODEL_DEFAULT) Optimization
>>>>>> +Specifies the cost model for epilogue vectorization.
>>>>>> +
>>>>>>  Enum
>>>>>>  Name(vect_cost_model) Type(enum vect_cost_model) UnknownError(unknown vectorizer cost model %qs)
>>>>>>
>>>>>> diff --git a/gcc/flag-types.h b/gcc/flag-types.h
>>>>>> index dd57e16..24081b1 100644
>>>>>> --- a/gcc/flag-types.h
>>>>>> +++ b/gcc/flag-types.h
>>>>>> @@ -200,6 +200,15 @@ enum vect_cost_model {
>>>>>>    VECT_COST_MODEL_DEFAULT = 3
>>>>>>  };
>>>>>>
>>>>>> +/* Epilogue vectorization modes.  */
>>>>>> +enum vect_epilogue_mode {
>>>>>> +  VECT_EPILOGUE_COMBINE = 1 << 0,
>>>>>> +  VECT_EPILOGUE_MASK = 1 << 1,
>>>>>> +  VECT_EPILOGUE_NOMASK = 1 << 2,
>>>>>> +  VECT_EPILOGUE_ALL = VECT_EPILOGUE_COMBINE | VECT_EPILOGUE_MASK
>>>>>> +                     | VECT_EPILOGUE_NOMASK
>>>>>> +};
>>>>>> +
>>>>>>  /* Different instrumentation modes.  */
>>>>>>  enum sanitize_code {
>>>>>>    /* AddressSanitizer.  */
>>>>>> diff --git a/gcc/opts.c b/gcc/opts.c
>>>>>> index 0f9431a..a0c0987 100644
>>>>>> --- a/gcc/opts.c
>>>>>> +++ b/gcc/opts.c
>>>>>> @@ -1531,6 +1531,63 @@ parse_sanitizer_options (const char *p, location_t loc, int scode,
>>>>>>    return flags;
>>>>>>  }
>>>>>>
>>>>>> +/* Parse comma separated vectorizer suboptions from P for option SCODE,
>>>>>> +   adjust previous FLAGS and return new ones.  If COMPLAIN is false,
>>>>>> +   don't issue diagnostics.  */
>>>>>> +
>>>>>> +unsigned int
>>>>>> +parse_vectorizer_options (const char *p, location_t loc, int scode,
>>>>>> +                         unsigned int flags, int value, bool complain)
>>>>>> +{
>>>>>> +  if (scode != OPT_ftree_vectorize_epilogues_)
>>>>>> +    return flags;
>>>>>> +
>>>>>> +  if (!p)
>>>>>> +    return value;
>>>>>> +
>>>>>> +  while (*p != 0)
>>>>>> +    {
>>>>>> +      size_t len;
>>>>>> +      const char *comma = strchr (p, ',');
>>>>>> +      unsigned int flag = 0;
>>>>>> +
>>>>>> +      if (comma == NULL)
>>>>>> +       len = strlen (p);
>>>>>> +      else
>>>>>> +       len = comma - p;
>>>>>> +      if (len == 0)
>>>>>> +       {
>>>>>> +         p = comma + 1;
>>>>>> +         continue;
>>>>>> +       }
>>>>>> +
>>>>>> +      /* Check to see if the string matches an option class name.  */
>>>>>> +      if (len == strlen ("combine")
>>>>>> +         && memcmp (p, "combine", len) == 0)
>>>>>> +       flag = VECT_EPILOGUE_COMBINE;
>>>>>> +      else if (len == strlen ("mask")
>>>>>> +         && memcmp (p, "mask", len) == 0)
>>>>>> +       flag = VECT_EPILOGUE_MASK;
>>>>>> +      else if (len == strlen ("nomask")
>>>>>> +         && memcmp (p, "nomask", len) == 0)
>>>>>> +       flag = VECT_EPILOGUE_NOMASK;
>>>>>> +      else if (complain)
>>>>>> +       error_at (loc, "unrecognized argument to -ftree-vectorize-epilogues= "
>>>>>> +                 "option: %q.*s", (int) len, p);
>>>>>> +
>>>>>> +      if (value)
>>>>>> +       flags |= flag;
>>>>>> +      else
>>>>>> +       flags &= ~flag;
>>>>>> +
>>>>>> +      if (comma == NULL)
>>>>>> +       break;
>>>>>> +      p = comma + 1;
>>>>>> +    }
>>>>>> +
>>>>>> +  return flags;
>>>>>> +}
>>>>>> +
>>>>>>  /* Handle target- and language-independent options.  Return zero to
>>>>>>     generate an "unknown option" message.  Only options that need
>>>>>>     extra handling need to be listed here; if you simply want
>>>>>> @@ -2018,6 +2075,18 @@ common_handle_option (struct gcc_options *opts,
>>>>>>        if (!opts_set->x_flag_tree_slp_vectorize)
>>>>>>          opts->x_flag_tree_slp_vectorize = value;
>>>>>>        break;
>>>>>> +
>>>>>> +    case OPT_ftree_vectorize_epilogues_:
>>>>>> +      opts->x_flag_tree_vectorize_epilogues
>>>>>> +       = parse_vectorizer_options (arg, loc, code,
>>>>>> +                                   opts->x_flag_tree_vectorize_epilogues,
>>>>>> +                                   value, true);
>>>>>> +      break;
>>>>>> +
>>>>>> +    case OPT_fno_tree_vectorize_epilogues:
>>>>>> +      opts->x_flag_tree_vectorize_epilogues = 0;
>>>>>> +      break;
>>>>>> +
>>>>>>      case OPT_fshow_column:
>>>>>>        dc->show_column = value;
>>>>>>        break;