Hi,
This patch introduces an option fopt-info-oacc.
When using the option like this with a kernels region in kernels-loop.c
that parloops does not manage to parallelize:
...
$ gcc kernels-loop.c -S -O2 -fopenacc -fopt-info-oacc-all
...
we get a message:
...
kernels-loop.c:23:9: note: kernels region executed sequentially.
Consider mapping it to host execution, to avoid data copy penalty.
...
Any comments?
Thanks,
- Tom
Add fopt-info-oacc
---
gcc/dumpfile.c | 1 +
gcc/dumpfile.h | 5 +++--
gcc/omp-low.c | 30 +++++++++++++++++++++++++++++-
3 files changed, 33 insertions(+), 3 deletions(-)
diff --git a/gcc/dumpfile.c b/gcc/dumpfile.c
index 144e371..e8aa0e1 100644
--- a/gcc/dumpfile.c
+++ b/gcc/dumpfile.c
@@ -137,6 +137,7 @@ static const struct dump_option_value_info optgroup_options[] =
{"loop", OPTGROUP_LOOP},
{"inline", OPTGROUP_INLINE},
{"vec", OPTGROUP_VEC},
+ {"oacc", OPTGROUP_OACC},
{"optall", OPTGROUP_ALL},
{NULL, 0}
};
diff --git a/gcc/dumpfile.h b/gcc/dumpfile.h
index c168cbf..6e1c657 100644
--- a/gcc/dumpfile.h
+++ b/gcc/dumpfile.h
@@ -97,9 +97,10 @@ enum tree_dump_index
#define OPTGROUP_LOOP (1 << 2) /* Loop optimization passes */
#define OPTGROUP_INLINE (1 << 3) /* Inlining passes */
#define OPTGROUP_VEC (1 << 4) /* Vectorization passes */
-#define OPTGROUP_OTHER (1 << 5) /* All other passes */
+#define OPTGROUP_OACC (1 << 5) /* Openacc passes */
+#define OPTGROUP_OTHER (1 << 6) /* All other passes */
#define OPTGROUP_ALL (OPTGROUP_IPA | OPTGROUP_LOOP | OPTGROUP_INLINE \
- | OPTGROUP_VEC | OPTGROUP_OTHER)
+ | OPTGROUP_VEC | OPTGROUP_OACC | OPTGROUP_OTHER)
/* Define a tree dump switch. */
struct dump_file_info
diff --git a/gcc/omp-low.c b/gcc/omp-low.c
index a6e3fe3..d5c3484 100644
--- a/gcc/omp-low.c
+++ b/gcc/omp-low.c
@@ -20139,6 +20139,34 @@ execute_oacc_device_lower ()
: fn_level < 0 ? "Function is parallel offload\n"
: "Function is routine level %d\n", fn_level);
+#if defined ACCEL_COMPILER
+ bool is_kernels = oacc_fn_attrib_kernels_p (attrs);
+ if (is_kernels)
+ {
+ bool all_one = true;
+ tree pos = TREE_VALUE (attrs);
+ for (unsigned ix = 0; ix != GOMP_DIM_MAX; ix++)
+ {
+ tree tree_val = TREE_VALUE (pos);
+ unsigned HOST_WIDE_INT val = (tree_val
+ ? TREE_INT_CST_LOW (tree_val)
+ : 1);
+ if (val != 1)
+ {
+ all_one = false;
+ break;
+ }
+ pos = TREE_CHAIN (pos);
+ }
+
+ if (all_one)
+ dump_printf_loc (MSG_MISSED_OPTIMIZATION, cfun->function_start_locus,
+ "Kernels region executed sequentially. Consider"
+ " mapping it to host execution, to avoid data copy"
+ " penalty.\n");
+ }
+#endif
+
unsigned outer_mask = fn_level >= 0 ? GOMP_DIM_MASK (fn_level) - 1 : 0;
unsigned used_mask = oacc_loop_partition (loops, outer_mask);
int dims[GOMP_DIM_MAX];
@@ -20312,7 +20340,7 @@ const pass_data pass_data_oacc_device_lower =
{
GIMPLE_PASS, /* type */
"oaccdevlow", /* name */
- OPTGROUP_NONE, /* optinfo_flags */
+ OPTGROUP_OACC, /* optinfo_flags */
TV_NONE, /* tv_id */
PROP_cfg, /* properties_required */
0 /* Possibly PROP_gimple_eomp. */, /* properties_provided */
