Hi!
On Wed, 31 May 2023 12:31:35 +0530
Ajit Agarwal via Gcc-patches <gcc-patches@gcc.gnu.org> wrote:
> Hello All:
>
> This patch improves code sinking pass to sink statements before call to reduce
> register pressure.
> Review comments are incorporated.
>
> For example :
>
> void bar();
> int j;
> void foo(int a, int b, int c, int d, int e, int f)
> {
> int l;
> l = a + b + c + d +e + f;
> if (a != 5)
> {
> bar();
> j = l;
> }
> }
>
> Code Sinking does the following:
>
> void bar();
> int j;
> void foo(int a, int b, int c, int d, int e, int f)
> {
> int l;
>
> if (a != 5)
> {
> l = a + b + c + d +e + f;
> bar();
> j = l;
> }
> }
>
> Bootstrapped regtested on powerpc64-linux-gnu.
>
> Thanks & Regards
> Ajit
>
> tree-ssa-sink: Improve code sinking pass
>
> Code Sinking sinks the blocks after call.This increases register pressure
> for callee-saved registers. Improves code sinking before call in the use
> blocks or immediate dominator of use blocks.
>
> 2023-05-24 Ajit Kumar Agarwal <aagar...@linux.ibm.com>
>
> gcc/ChangeLog:
>
> * tree-ssa-sink.cc (statement_sink_location): Move statements before
> calls.
> (def_use_same_block): New function.
> (select_best_block): Add heuristics to select the best blocks in the
> immediate post dominator.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.dg/tree-ssa/ssa-sink-20.c: New testcase.
> * gcc.dg/tree-ssa/ssa-sink-21.c: New testcase.
> ---
> gcc/testsuite/gcc.dg/tree-ssa/ssa-sink-20.c | 15 +++++
> gcc/testsuite/gcc.dg/tree-ssa/ssa-sink-21.c | 19 ++++++
> gcc/tree-ssa-sink.cc | 74 +++++++++++++++++----
> 3 files changed, 96 insertions(+), 12 deletions(-)
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/ssa-sink-20.c
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/ssa-sink-21.c
>
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-sink-20.c
> b/gcc/testsuite/gcc.dg/tree-ssa/ssa-sink-20.c
> new file mode 100644
> index 00000000000..49d5019ab93
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-sink-20.c
> @@ -0,0 +1,15 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -fdump-tree-optimized -fdump-tree-sink-stats" } */
You don't test the optimized dump, do you?
> +void bar();
> +int j;
> +void foo(int a, int b, int c, int d, int e, int f)
> +{
> + int l;
> + l = a + b + c + d +e + f;
> + if (a != 5)
> + {
> + bar();
> + j = l;
> + }
> +}
> +/* { dg-final { scan-tree-dump
> {l_12\s+=\s+_4\s+\+\s+f_11\(D\);\n\s+bar\s+\(\)} sink1 } } */
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-sink-21.c
> b/gcc/testsuite/gcc.dg/tree-ssa/ssa-sink-21.c
> new file mode 100644
> index 00000000000..84e7938c54f
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-sink-21.c
> @@ -0,0 +1,19 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -fdump-tree-sink-stats" } */
> +void bar();
> +int j, x;
> +void foo(int a, int b, int c, int d, int e, int f)
> +{
> + int l;
> + l = a + b + c + d +e + f;
> + if (a != 5)
> + {
> + bar();
> + if (b != 3)
> + x = 3;
> + else
> + x = 5;
> + j = l;
> + }
> +}
> +/* { dg-final { scan-tree-dump
> {l_13\s+=\s+_4\s+\+\s+f_12\(D\);\n\s+bar\s+\(\)} sink1 } } */
> diff --git a/gcc/tree-ssa-sink.cc b/gcc/tree-ssa-sink.cc
> index b1ba7a2ad6c..ee8988bbb2c 100644
> --- a/gcc/tree-ssa-sink.cc
> +++ b/gcc/tree-ssa-sink.cc
> @@ -171,9 +171,28 @@ nearest_common_dominator_of_uses (def_operand_p def_p,
> bool *debug_stmts)
> return commondom;
> }
>
> +/* Return TRUE if immediate uses of the defs in
> + STMT occur in the same block as STMT, FALSE otherwise. */
> +
> +bool
> +def_use_same_block (gimple *stmt)
Looks like this function should be static.
> +{
> + def_operand_p def;
> + ssa_op_iter iter;
> +
> + FOR_EACH_SSA_DEF_OPERAND (def, stmt, iter, SSA_OP_DEF)
> + {
> + gimple *def_stmt = SSA_NAME_DEF_STMT (DEF_FROM_PTR (def));
> + if ((gimple_bb (def_stmt) == gimple_bb (stmt)))
> + return true;
> + }
> + return false;
> +}
> +
> /* Given EARLY_BB and LATE_BB, two blocks in a path through the dominator
> tree, return the best basic block between them (inclusive) to place
> - statements.
> + statements. The best basic block should be in immediate dominator of
> + best basic block if the use stmt is after the call.
s/in/an/ ?
>
> We want the most control dependent block in the shallowest loop nest.
>
> @@ -190,7 +209,8 @@ nearest_common_dominator_of_uses (def_operand_p def_p,
> bool *debug_stmts)
> static basic_block
> select_best_block (basic_block early_bb,
> basic_block late_bb,
> - gimple *stmt)
> + gimple *stmt,
> + gimple *use)
> {
> basic_block best_bb = late_bb;
> basic_block temp_bb = late_bb;
> @@ -230,14 +250,46 @@ select_best_block (basic_block early_bb,
> if (threshold > 100)
> threshold = 100;
> }
> -
superfluous whitespace change?
> /* If BEST_BB is at the same nesting level, then require it to have
> significantly lower execution frequency to avoid gratuitous movement.
> */
> if (bb_loop_depth (best_bb) == bb_loop_depth (early_bb)
> /* If result of comparsion is unknown, prefer EARLY_BB.
> Thus use !(...>=..) rather than (...<...) */
> && !(best_bb->count * 100 >= early_bb->count * threshold))
> - return best_bb;
> + {
> + basic_block new_best_bb = get_immediate_dominator (CDI_DOMINATORS,
> best_bb);
> + /* Return best_bb if def and use are in same block otherwise
> new_best_bb.
> +
> + Things to consider:
> +
> + new_best_bb is not equal to best_bb and early_bb.
> +
> + stmt is not call.
> +
> + new_best_bb doesnt have any phis.
> +
> + use basic block is not equal to early_bb.
> +
> + use basic block post dominates to new_best_bb.
> +
> + new_best_bb dominates early_bb. */
> + if (new_best_bb && use
> + && (new_best_bb != best_bb)
> + && (new_best_bb != early_bb)
Excess braces in the two lines above and...
> + && !is_gimple_call (stmt)
> + && gsi_end_p (gsi_start_phis (new_best_bb))
> + && (gimple_bb (use) != early_bb)
...here
> + && !is_gimple_call (use)
> + && dominated_by_p (CDI_POST_DOMINATORS, new_best_bb, gimple_bb(use))
Missing space before the open parens: gimple_bb (use)
> + && dominated_by_p (CDI_DOMINATORS, new_best_bb, early_bb))
> + {
> + if (def_use_same_block (use))
> + return best_bb;
> +
> + return new_best_bb;
> + }
> + return best_bb;
> + }
>
Many returns.
I'd have said
&& !def_use_same_block (use)
return new_best_bb;
else
return best_bb;
and rephrase the comment above list of Things to consider accordingly.
> /* No better block found, so return EARLY_BB, which happens to be the
> statement's original block. */
> @@ -382,7 +434,7 @@ statement_sink_location (gimple *stmt, basic_block frombb,
> {
> /* Do not sink loads from hard registers. */
> if (gimple_assign_single_p (stmt)
> - && VAR_P (gimple_assign_rhs1 (stmt))
> + && TREE_CODE (gimple_assign_rhs1 (stmt)) == VAR_DECL
Why? Please don't do this.
thanks,
> && DECL_HARD_REGISTER (gimple_assign_rhs1 (stmt)))
> return false;
>
> @@ -439,7 +491,7 @@ statement_sink_location (gimple *stmt, basic_block frombb,
> if (!dominated_by_p (CDI_DOMINATORS, commondom, frombb))
> return false;
>
> - commondom = select_best_block (frombb, commondom, stmt);
> + commondom = select_best_block (frombb, commondom, stmt, NULL);
>
> if (commondom == frombb)
> return false;
> @@ -456,19 +508,17 @@ statement_sink_location (gimple *stmt, basic_block
> frombb,
> continue;
> break;
> }
> +
> use = USE_STMT (one_use);
>
> if (gimple_code (use) != GIMPLE_PHI)
> {
> - sinkbb = select_best_block (frombb, gimple_bb (use), stmt);
> + sinkbb = select_best_block (frombb, gimple_bb (use), stmt, use);
>
> if (sinkbb == frombb)
> return false;
>
> - if (sinkbb == gimple_bb (use))
> - *togsi = gsi_for_stmt (use);
> - else
> - *togsi = gsi_after_labels (sinkbb);
> + *togsi = gsi_after_labels (sinkbb);
>
> return true;
> }
> @@ -480,7 +530,7 @@ statement_sink_location (gimple *stmt, basic_block frombb,
> if (!sinkbb)
> return false;
>
> - sinkbb = select_best_block (frombb, sinkbb, stmt);
> + sinkbb = select_best_block (frombb, sinkbb, stmt, NULL);
> if (!sinkbb || sinkbb == frombb)
> return false;
>
