Re: [PATCH] Allow FSM to thread single block cases too

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

On Tue, Oct 13, 2015 at 2:52 PM, Richard Biener
<richard.guenther@gmail.com> wrote:
> On Tue, Oct 13, 2015 at 2:21 PM, Jeff Law <law@redhat.com> wrote:
>>
>> One of the cases that was missing in the FSM support is threading when the
>> path is a single block.  ie, a control statement's output can be statically
>> determined just by looking at PHIs in the control statement's block for one
>> or incoming edges.
>>
>> This is necessary to fix a regression if I turn off the old jump threader's
>> backedge support.  Just as important, Jan has in the past asked about a
>> trivial jump threader to be run during early optimizations.  Limiting the
>> FSM bits to this case would likely satisfy that need in the future.
>
> I think he asked for trivial forward threads though due to repeated tests.
> I hacked FRE to do this (I think), but maybe some trivial cleanup opportunities
> are still left here.  Honza?

This or other related patches in the range r228731:228774 has caused a quite
big jump in SPEC CPU 2000 binary sizes (notably 176.gcc - so maybe affecting
bootstrap as well, at -O3).  Are you sure this doesn't re-introduce DOM
effectively peeling all loops once?

Richard.

> Richard.
>
>> Bootstrapped and regression tested on x86_64-linux-gnu.  Installed on the
>> trunk.
>>
>> Jeff
>>
>> commit a53bb29a1dffd329aa6235b88b0c2a830aa5a59e
>> Author: Jeff Law <law@redhat.com>
>> Date:   Tue Oct 13 06:19:20 2015 -0600
>>
>>     [PATCH] Allow FSM to thread single block cases too
>>
>>         * tree-ssa-threadbackward.c
>> (fsm_find_control_statement_thread_paths):
>>         Allow single block jump threading paths.
>>
>>         * gcc.dg/tree-ssa/ssa-thread-13.c: New test.
>>
>> diff --git a/gcc/ChangeLog b/gcc/ChangeLog
>> index d71bcd2..caab533 100644
>> --- a/gcc/ChangeLog
>> +++ b/gcc/ChangeLog
>> @@ -1,3 +1,8 @@
>> +2015-10-13  Jeff Law  <law@redhat.com>
>> +
>> +       * tree-ssa-threadbackward.c
>> (fsm_find_control_statement_thread_paths):
>> +       Allow single block jump threading paths.
>> +
>>  2015-10-13  Tom de Vries  <tom@codesourcery.com>
>>
>>         PR tree-optimization/67476
>> diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
>> index 4a08f0f..acf6df5 100644
>> --- a/gcc/testsuite/ChangeLog
>> +++ b/gcc/testsuite/ChangeLog
>> @@ -1,3 +1,7 @@
>> +2015-10-13  Jeff Law  <law@redhat.com>
>> +
>> +       * gcc.dg/tree-ssa/ssa-thread-13.c: New test.
>> +
>>  2015-10-12  Jeff Law  <law@redhat.com>
>>
>>         * gcc.dg/tree-ssa/ssa-thread-12.c: New test.
>> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-13.c
>> b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-13.c
>> new file mode 100644
>> index 0000000..5051d11
>> --- /dev/null
>> +++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-13.c
>> @@ -0,0 +1,70 @@
>> +/* { dg-do compile } */
>> +/* { dg-options "-O2 -fdump-tree-vrp1-details" } */
>> +/* { dg-final { scan-tree-dump "FSM" "vrp1" } } */
>> +
>> +typedef struct rtx_def *rtx;
>> +typedef const struct rtx_def *const_rtx;
>> +enum rtx_code
>> +{
>> +  UNKNOWN, VALUE, DEBUG_EXPR, EXPR_LIST, INSN_LIST, SEQUENCE, ADDRESS,
>> +    DEBUG_INSN, INSN, JUMP_INSN, CALL_INSN, BARRIER, CODE_LABEL, NOTE,
>> +    COND_EXEC, PARALLEL, ASM_INPUT, ASM_OPERANDS, UNSPEC, UNSPEC_VOLATILE,
>> +    ADDR_VEC, ADDR_DIFF_VEC, PREFETCH, SET, USE, CLOBBER, CALL, RETURN,
>> +    EH_RETURN, TRAP_IF, CONST_INT, CONST_FIXED, CONST_DOUBLE, CONST_VECTOR,
>> +    CONST_STRING, CONST, PC, REG, SCRATCH, SUBREG, STRICT_LOW_PART, CONCAT,
>> +    CONCATN, MEM, LABEL_REF, SYMBOL_REF, CC0, IF_THEN_ELSE, COMPARE, PLUS,
>> +    MINUS, NEG, MULT, SS_MULT, US_MULT, DIV, SS_DIV, US_DIV, MOD, UDIV,
>> UMOD,
>> +    AND, IOR, XOR, NOT, ASHIFT, ROTATE, ASHIFTRT, LSHIFTRT, ROTATERT, SMIN,
>> +    SMAX, UMIN, UMAX, PRE_DEC, PRE_INC, POST_DEC, POST_INC, PRE_MODIFY,
>> +    POST_MODIFY, NE, EQ, GE, GT, LE, LT, GEU, GTU, LEU, LTU, UNORDERED,
>> +    ORDERED, UNEQ, UNGE, UNGT, UNLE, UNLT, LTGT, SIGN_EXTEND, ZERO_EXTEND,
>> +    TRUNCATE, FLOAT_EXTEND, FLOAT_TRUNCATE, FLOAT, FIX, UNSIGNED_FLOAT,
>> +    UNSIGNED_FIX, FRACT_CONVERT, UNSIGNED_FRACT_CONVERT, SAT_FRACT,
>> +    UNSIGNED_SAT_FRACT, ABS, SQRT, BSWAP, FFS, CLZ, CTZ, POPCOUNT, PARITY,
>> +    SIGN_EXTRACT, ZERO_EXTRACT, HIGH, LO_SUM, VEC_MERGE, VEC_SELECT,
>> +    VEC_CONCAT, VEC_DUPLICATE, SS_PLUS, US_PLUS, SS_MINUS, SS_NEG, US_NEG,
>> +    SS_ABS, SS_ASHIFT, US_ASHIFT, US_MINUS, SS_TRUNCATE, US_TRUNCATE, FMA,
>> +    VAR_LOCATION, DEBUG_IMPLICIT_PTR, ENTRY_VALUE, LAST_AND_UNUSED_RTX_CODE
>> +};
>> +union rtunion_def
>> +{
>> +  rtx rt_rtx;
>> +};
>> +typedef union rtunion_def rtunion;
>> +struct rtx_def
>> +{
>> +  __extension__ enum rtx_code code:16;
>> +  union u
>> +  {
>> +    rtunion fld[1];
>> +  }
>> +  u;
>> +};
>> +
>> +unsigned int rtx_cost (rtx, enum rtx_code, unsigned char);
>> +rtx single_set_2 (const_rtx, rtx);
>> +
>> +unsigned
>> +seq_cost (const_rtx seq, unsigned char speed)
>> +{
>> +  unsigned cost = 0;
>> +  rtx set;
>> +  for (; seq; seq = (((seq)->u.fld[2]).rt_rtx))
>> +    {
>> +      set =
>> +       (((((enum rtx_code) (seq)->code) == INSN)
>> +         || (((enum rtx_code) (seq)->code) == DEBUG_INSN)
>> +         || (((enum rtx_code) (seq)->code) == JUMP_INSN)
>> +         || (((enum rtx_code) (seq)->code) ==
>> +             CALL_INSN)) ? (((enum rtx_code) ((((seq)->u.fld[4]).rt_rtx))->
>> +                             code) ==
>> +                            SET ? (((seq)->u.fld[4]).
>> +                                   rt_rtx) : single_set_2 (seq,
>> +                                                           (((seq)->u.
>> +                                                             fld[4]).
>> +                                                            rt_rtx))) :
>> (rtx)
>> +        0);
>> +      if (set)
>> +       cost += rtx_cost (set, SET, speed);
>> +    }
>> +}
>> diff --git a/gcc/tree-ssa-threadbackward.c b/gcc/tree-ssa-threadbackward.c
>> index 5be6ee4..9128094 100644
>> --- a/gcc/tree-ssa-threadbackward.c
>> +++ b/gcc/tree-ssa-threadbackward.c
>> @@ -211,10 +211,6 @@ fsm_find_control_statement_thread_paths (tree name,
>>         continue;
>>
>>        int path_length = path->length ();
>> -      /* A path with less than 2 basic blocks should not be jump-threaded.
>> */
>> -      if (path_length < 2)
>> -       continue;
>> -
>>        if (path_length > PARAM_VALUE (PARAM_MAX_FSM_THREAD_LENGTH))
>>         {
>>           if (dump_file && (dump_flags & TDF_DETAILS))
>>