@@ -1215,6 +1215,39 @@ oacc_parse_default_dims (const char *dims)
targetm.goacc.validate_dims (NULL_TREE, oacc_min_dims, -2, 0);
}
+/* Remove parallelism dimensions below LEVEL which are not set in USED
+ from DIMS and emit a warning pointing to the location of FN. */
+
+static void
+oacc_remove_unused_partitioning (tree fn, int *dims, int level, unsigned used)
+{
+
+ bool host_compiler = true;
+#ifdef ACCEL_COMPILER
+ host_compiler = false;
+#endif
+
+ static char const *const axes[] =
+ /* Must be kept in sync with GOMP_DIM enumeration. */
+ { "gang", "worker", "vector" };
+
+ char removed_partitions[20] = "\0";
+ for (int ix = level >= 0 ? level : 0; ix != GOMP_DIM_MAX; ix++)
+ if (!(used & GOMP_DIM_MASK (ix)) && dims[ix] >= 0)
+ {
+ if (host_compiler)
+ {
+ strcat (removed_partitions, axes[ix]);
+ strcat (removed_partitions, " ");
+ }
+ dims[ix] = -1;
+ }
+ if (removed_partitions[0] != '\0')
+ warning_at (DECL_SOURCE_LOCATION (fn), OPT_Wopenacc_parallelism,
+ "removed %spartitioning from %<kernels%> region",
+ removed_partitions);
+}
+
/* Validate and update the dimensions for offloaded FN. ATTRS is the
raw attribute. DIMS is an array of dimensions, which is filled in.
LEVEL is the partitioning level of a routine, or -1 for an offload
@@ -1235,6 +1268,7 @@ oacc_validate_dims (tree fn, tree attrs, int *dims, int level, unsigned used)
for (ix = 0; ix != GOMP_DIM_MAX; ix++)
{
purpose[ix] = TREE_PURPOSE (pos);
+
tree val = TREE_VALUE (pos);
dims[ix] = val ? TREE_INT_CST_LOW (val) : -1;
pos = TREE_CHAIN (pos);
@@ -1244,14 +1278,15 @@ oacc_validate_dims (tree fn, tree attrs, int *dims, int level, unsigned used)
#ifdef ACCEL_COMPILER
check = false;
#endif
+
+ static char const *const axes[] =
+ /* Must be kept in sync with GOMP_DIM enumeration. */
+ { "gang", "worker", "vector" };
+
if (check
&& warn_openacc_parallelism
- && !lookup_attribute ("oacc kernels", DECL_ATTRIBUTES (fn))
- && !lookup_attribute ("oacc parallel_kernels_graphite", DECL_ATTRIBUTES (fn)))
+ && !lookup_attribute ("oacc kernels", DECL_ATTRIBUTES (fn)))
{
- static char const *const axes[] =
- /* Must be kept in sync with GOMP_DIM enumeration. */
- { "gang", "worker", "vector" };
for (ix = level >= 0 ? level : 0; ix != GOMP_DIM_MAX; ix++)
if (dims[ix] < 0)
; /* Defaulting axis. */
@@ -1262,14 +1297,20 @@ oacc_validate_dims (tree fn, tree attrs, int *dims, int level, unsigned used)
"region contains %s partitioned code but"
" is not %s partitioned", axes[ix], axes[ix]);
else if (!(used & GOMP_DIM_MASK (ix)) && dims[ix] != 1)
+ {
/* The dimension is explicitly partitioned to non-unity, but
no use is made within the region. */
warning_at (DECL_SOURCE_LOCATION (fn), OPT_Wopenacc_parallelism,
"region is %s partitioned but"
" does not contain %s partitioned code",
axes[ix], axes[ix]);
+ }
}
+ if (lookup_attribute ("oacc parallel_kernels_graphite",
+ DECL_ATTRIBUTES (fn)))
+ oacc_remove_unused_partitioning (fn, dims, level, used);
+
bool changed = targetm.goacc.validate_dims (fn, dims, level, used);
/* Default anything left to 1 or a partitioned default. */
@@ -7,6 +7,8 @@
#include <acc_prof.h>
+/* { dg-skip-if "'kernels' not analyzed by Graphite at -O0" { *-*-* } { "-O0" } { "" } } */
+/* { dg-additional-options "-Wopenacc-parallelism" } */
/* Use explicit 'copyin' clauses, to work around "'firstprivate'
optimizations", which will cause the value at the point of call to be used
@@ -41,6 +43,7 @@ static int state = -1;
static acc_device_t acc_device_type;
static int acc_device_num;
static int num_gangs, num_workers, vector_length;
+static int real_num_workers;
static int async;
@@ -96,12 +99,8 @@ static void cb_enqueue_launch_start (acc_prof_info *prof_info, acc_event_info *e
assert (event_info->launch_event.num_workers >= 1);
else
{
-#ifdef __OPTIMIZE__
- assert (event_info->launch_event.num_workers == num_workers);
-#else
- /* See 'num_gangs' above. */
- assert (event_info->launch_event.num_workers == 1);
-#endif
+ /* Unused partitioning levels get removed from "kernels" region. */
+ assert (event_info->launch_event.num_workers == real_num_workers);
}
if (vector_length < 1)
assert (event_info->launch_event.vector_length >= 1);
@@ -186,6 +185,7 @@ int main()
/* Parallelism dimensions: literal. */
num_gangs = 30;
num_workers = 3;
+ real_num_workers = 1;
vector_length = 5;
{
#define N 100
@@ -196,6 +196,8 @@ int main()
/* { dg-prune-output "using vector_length \\(32\\), ignoring 5" } */
{
for (int i = 0; i < N; ++i)
+ /* { dg-warning "region is worker partitioned but does not contain worker partitioned code" "" { target *-*-* } .-1 } */
+ /* { dg-warning "removed worker partitioning from 'kernels' region" "" { target *-*-* } .-2 } */
x[i] = i * i;
}
if (acc_device_type == acc_device_host)
@@ -214,6 +216,9 @@ int main()
/* Parallelism dimensions: variable. */
num_gangs = 22;
num_workers = 5;
+ /* No worker loop and hence, in a kernels region, worker partitioning
+ should be removed. */
+ real_num_workers = 1;
vector_length = 7;
{
#define N 100
@@ -224,6 +229,8 @@ int main()
/* { dg-prune-output "using vector_length \\(32\\), ignoring runtime setting" } */
{
for (int i = 0; i < N; ++i)
+ /* { dg-warning "region is worker partitioned but does not contain worker partitioned code" "" { target *-*-* } .-1 } */
+ /* { dg-warning "removed worker partitioning from 'kernels' region" "" { target *-*-* } .-2 } */
x[i] = i * i;
}
if (acc_device_type == acc_device_host)