Hi,
Many thanks for all comments on previous versions.
Comparing with the previous version, I dropped the checks
on costly niter and invalid stmt scanning. As Richard's
suggestion, keep this as simple as possible, refine it
if finding any cases which matter later.
Bootstrapped and regression testing passed on powerpc64le.
Is it OK for trunk?
Thanks,
Kewen
gcc/ChangeLog
2019-06-13 Kewen Lin <li...@gcc.gnu.org>
PR middle-end/80791
* target.def (predict_doloop_p): New hook.
* targhooks.h (default_predict_doloop_p): New declaration.
* targhooks.c (default_predict_doloop_p): New function.
* doc/tm.texi.in (TARGET_PREDICT_DOLOOP_P): New hook.
* doc/tm.texi: Regenerate.
* config/rs6000/rs6000.c (rs6000_predict_doloop_p): New function.
(TARGET_PREDICT_DOLOOP_P): New macro.
* tree-ssa-loop-ivopts.c (generic_predict_doloop_p): New function.
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 91fafc4e766..54bcc1608ae 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -1909,6 +1909,9 @@ static const struct attribute_spec
rs6000_attribute_table[] =
#undef TARGET_CAN_USE_DOLOOP_P
#define TARGET_CAN_USE_DOLOOP_P can_use_doloop_if_innermost
+#undef TARGET_PREDICT_DOLOOP_P
+#define TARGET_PREDICT_DOLOOP_P rs6000_predict_doloop_p
+
#undef TARGET_ATOMIC_ASSIGN_EXPAND_FENV
#define TARGET_ATOMIC_ASSIGN_EXPAND_FENV rs6000_atomic_assign_expand_fenv
@@ -39413,7 +39416,27 @@ rs6000_mangle_decl_assembler_name (tree decl, tree id)
return id;
}
-
+/* Predict whether the given loop in gimple will be transformed in the RTL
+ doloop_optimize pass. This is for rs6000 target specific. */
+
+static bool
+rs6000_predict_doloop_p (struct loop *loop)
+{
+ gcc_assert (loop);
+
+ /* On rs6000, targetm.can_use_doloop_p is actually
+ can_use_doloop_if_innermost. Just ensure it's innermost. */
+ if (loop->inner != NULL)
+ {
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ fprintf (dump_file, "Predict doloop failure due to"
+ " no innermost.\n");
+ return false;
+ }
+
+ return true;
+}
+
struct gcc_target targetm = TARGET_INITIALIZER;
#include "gt-rs6000.h"
diff --git a/gcc/doc/tm.texi b/gcc/doc/tm.texi
index 622e8cf240f..69081ca0700 100644
--- a/gcc/doc/tm.texi
+++ b/gcc/doc/tm.texi
@@ -11610,6 +11610,14 @@ function version at run-time for a given set of
function versions.
body must be generated.
@end deftypefn
+@deftypefn {Target Hook} bool TARGET_PREDICT_DOLOOP_P (struct loop *@var{loop})
+Return true if we can predict it is possible to use a low-overhead loop
+for a particular loop. The parameter @var{loop} is a pointer to the loop.
+This target hook is required only when the target supports low-overhead
+loops, and will help some earlier middle-end passes to make some decisions.
+The default version of this hook returns false.
+@end deftypefn
+
@deftypefn {Target Hook} bool TARGET_CAN_USE_DOLOOP_P (const widest_int
@var{&iterations}, const widest_int @var{&iterations_max}, unsigned int
@var{loop_depth}, bool @var{entered_at_top})
Return true if it is possible to use low-overhead loops (@code{doloop_end}
and @code{doloop_begin}) for a particular loop. @var{iterations} gives the
diff --git a/gcc/doc/tm.texi.in b/gcc/doc/tm.texi.in
index 17560fce6b7..b4d57b86e2f 100644
--- a/gcc/doc/tm.texi.in
+++ b/gcc/doc/tm.texi.in
@@ -7944,6 +7944,8 @@ to by @var{ce_info}.
@hook TARGET_GENERATE_VERSION_DISPATCHER_BODY
+@hook TARGET_PREDICT_DOLOOP_P
+
@hook TARGET_CAN_USE_DOLOOP_P
@hook TARGET_INVALID_WITHIN_DOLOOP
diff --git a/gcc/target.def b/gcc/target.def
index 7d52102c815..5063c3c0b94 100644
--- a/gcc/target.def
+++ b/gcc/target.def
@@ -4236,6 +4236,15 @@ DEFHOOK
rtx, (machine_mode mode, rtx result, rtx val, rtx failval),
default_speculation_safe_value)
+DEFHOOK
+(predict_doloop_p,
+ "Return true if we can predict it is possible to use a low-overhead loop\n\
+for a particular loop. The parameter @var{loop} is a pointer to the loop.\n\
+This target hook is required only when the target supports low-overhead\n\
+loops, and will help some earlier middle-end passes to make some decisions.\n\
+The default version of this hook returns false.",
+ bool, (struct loop *loop),
+ default_predict_doloop_p)
DEFHOOK
(can_use_doloop_p,
diff --git a/gcc/targhooks.c b/gcc/targhooks.c
index b27111639f4..a83166d81ba 100644
--- a/gcc/targhooks.c
+++ b/gcc/targhooks.c
@@ -643,6 +643,19 @@ default_has_ifunc_p (void)
return HAVE_GNU_INDIRECT_FUNCTION;
}
+/* True if we can predict this loop is possible to be transformed to a
+ low-overhead loop, otherwise returns false.
+
+ By default, false is returned, as this hook's applicability should be
+ verified for each target. Target maintainers should re-define the hook
+ if the target can take advantage of it. */
+
+bool
+default_predict_doloop_p (struct loop *loop ATTRIBUTE_UNUSED)
+{
+ return false;
+}
+
/* NULL if INSN insn is valid within a low-overhead loop, otherwise returns
an error message.
diff --git a/gcc/targhooks.h b/gcc/targhooks.h
index 229aacd7b65..50b03ce3aa0 100644
--- a/gcc/targhooks.h
+++ b/gcc/targhooks.h
@@ -85,6 +85,7 @@ extern bool default_fixed_point_supported_p (void);
extern bool default_has_ifunc_p (void);
+extern bool default_predict_doloop_p (struct loop *);
extern const char * default_invalid_within_doloop (const rtx_insn *);
extern tree default_builtin_vectorized_function (unsigned int, tree, tree);
diff --git a/gcc/tree-ssa-loop-ivopts.c b/gcc/tree-ssa-loop-ivopts.c
index 890f9b788b4..530ea4ae343 100644
--- a/gcc/tree-ssa-loop-ivopts.c
+++ b/gcc/tree-ssa-loop-ivopts.c
@@ -3712,6 +3712,63 @@ prepare_decl_rtl (tree *expr_p, int *ws, void *data)
return NULL_TREE;
}
+/* Predict whether the given loop will be transformed in the RTL
+ doloop_optimize pass. Attempt to duplicate some doloop_optimize checks.
+ This is only for target independent checks, see targetm.predict_doloop_p
+ for the target dependent ones.
+
+ Note that according to some initial investigation, some checks like costly
+ niter check and invalid stmt scanning don't have much gains among general
+ cases, so keep this as simple as possible first.
+
+ Some RTL specific checks seems unable to be checked in gimple, if any new
+ checks or easy checks _are_ missing here, please add them. */
+
+static bool ATTRIBUTE_UNUSED
+generic_predict_doloop_p (struct ivopts_data *data)
+{
+ struct loop *loop = data->current_loop;
+
+ /* Call target hook for target dependent checks. */
+ if (!targetm.predict_doloop_p (loop))
+ {
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ fprintf (dump_file, "Predict doloop failure due to"
+ " target specific checks.\n");
+ return false;
+ }
+
+ /* Similar to doloop_optimize, check iteration description to know it's
+ suitable or not. Keep it as simple as possible, feel free to extend it
+ if you find any multiple exits cases matter. */
+ edge exit = single_dom_exit (loop);
+ struct tree_niter_desc *niter_desc;
+ if (!exit || !(niter_desc = niter_for_exit (data, exit)))
+ {
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ fprintf (dump_file, "Predict doloop failure due to"
+ " unexpected niters.\n");
+ return false;
+ }
+
+ /* Similar to doloop_optimize, check whether iteration count too small
+ and not profitable. */
+ HOST_WIDE_INT est_niter = get_estimated_loop_iterations_int (loop);
+ if (est_niter == -1)
+ est_niter = get_likely_max_loop_iterations_int (loop);
+ if (est_niter >= 0 && est_niter < 3)
+ {
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ fprintf (dump_file,
+ "Predict doloop failure due to"
+ " too few iterations (%u).\n",
+ (unsigned int) est_niter);
+ return false;
+ }
+
+ return true;
+}
+
/* Determines cost of the computation of EXPR. */
static unsigned
