The following puts in a hard limit on ext-dce because it might end
up requiring memory on the order of the number of basic blocks
times the number of pseudo registers. The limiting follows what
GCSE based passes do and thus I re-use --param max-gcse-memory here.
This doesn't in any way address the implementation issues of the pass,
but it reduces the memory-use when compiling the
module_first_rk_step_part1.F90 TU from 521.wrf_r from 25GB to 1GB.
Bootstrap and regtest running on x86_64-unknown-linux-gnu.
I plan to push this later today unless I hear objection.
PR rtl-optimization/117467
PR rtl-optimization/117934
* ext-dce.cc (ext_dce_execute): Do nothing if a memory
allocation estimate exceeds what is allowed by
--param max-gcse-memory.
---
gcc/ext-dce.cc | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/gcc/ext-dce.cc b/gcc/ext-dce.cc
index 6cf64187349..e257e3bc873 100644
--- a/gcc/ext-dce.cc
+++ b/gcc/ext-dce.cc
@@ -34,6 +34,7 @@ along with GCC; see the file COPYING3. If not see
#include "df.h"
#include "print-rtl.h"
#include "dbgcnt.h"
+#include "diagnostic-core.h"
/* These should probably move into a C++ class. */
static vec<bitmap_head> livein;
@@ -1110,6 +1111,21 @@ static bool ext_dce_rd_confluence_n (edge) { return
true; }
void
ext_dce_execute (void)
{
+ /* Limit the amount of memory we use for livein, with 4 bits per
+ reg per basic-block including overhead that maps to one byte
+ per reg per basic-block. */
+ uint64_t memory_request
+ = (uint64_t)n_basic_blocks_for_fn (cfun) * max_reg_num ();
+ if (memory_request / 1024 > (uint64_t)param_max_gcse_memory)
+ {
+ warning (OPT_Wdisabled_optimization,
+ "ext-dce disabled: %d basic blocks and %d registers; "
+ "increase %<--param max-gcse-memory%> above %wu",
+ n_basic_blocks_for_fn (cfun), max_reg_num (),
+ memory_request / 1024);
+ return;
+ }
+
/* Some settings of SUBREG_PROMOTED_VAR_P are actively harmful
to this pass. Clear it for those cases. */
maybe_clear_subreg_promoted_p ();
--
2.43.0
