I've committed this patch to
a) fix the breakage I caused this morning, sorry
b) Add a ptx-specific implementation of the fork_join hook. We only need to
keep worker & vector-level forks & joins, and then only when the dimension size
is not unity. This showed an awkwardness in that hook's API, so I tweaked it to
pass the dimension array that oacc-xform has handy.
c) Add smarts to VRP to know the range of the result of the DIM_POS and DIM_SIZE
functions. This allows the new min/max optimizer to remove some MIN_EXPRs that
get inserted.
nathan
2015-08-12 Nathan Sidwell <nat...@codesourcery.com>
* target.def (fork_join): Adjustt prototype.
* targhooks.h (default_foacc_fork_join): Adjust.
* omp-low.c (oacc_xform_dim): Constify DIMS arg.
(execute_oacc_transform): Defer setting defaulted unknown
dimensions to 0. Adjust fork_join hook call.
(default_goacc_fork_join): Adjust.
* config/nvptx/nvptx.c: Include gimple.h
(nvptx_xform_fork_join): New.
(TARGET_GOACC_FORK_JOIN): Override.
* doc/tm.texi: Rebuilt.
Index: config/nvptx/nvptx.c
===================================================================
--- config/nvptx/nvptx.c (revision 226813)
+++ config/nvptx/nvptx.c (working copy)
@@ -61,6 +61,7 @@
#include "cfg.h"
#include "omp-low.h"
#include "gomp-constants.h"
+#include "gimple.h"
/* This file should be included last. */
#include "target-def.h"
@@ -3598,6 +3599,25 @@ nvptx_dim_limit (unsigned axis)
return 0;
}
+/* Determine whether fork & joins are needed. */
+
+static bool
+nvptx_xform_fork_join (gimple_stmt_iterator *ARG_UNUSED (gsi), gimple stmt,
+ const int dims[], bool ARG_UNUSED (is_fork))
+{
+ tree arg = gimple_call_arg (stmt, 0);
+ unsigned axis = TREE_INT_CST_LOW (arg);
+
+ /* We only care about worker and vector partitioning. */
+ if (axis < GOMP_DIM_WORKER)
+ return true;
+
+ /* If the size is 1, there's no partitioning. */
+ if (dims[axis] == 1)
+ return true;
+
+ return false;
+}
#undef TARGET_OPTION_OVERRIDE
#define TARGET_OPTION_OVERRIDE nvptx_option_override
@@ -3699,6 +3719,9 @@ nvptx_dim_limit (unsigned axis)
#undef TARGET_GOACC_DIM_LIMIT
#define TARGET_GOACC_DIM_LIMIT nvptx_dim_limit
+#undef TARGET_GOACC_FORK_JOIN
+#define TARGET_GOACC_FORK_JOIN nvptx_xform_fork_join
+
struct gcc_target targetm = TARGET_INITIALIZER;
#include "gt-nvptx.h"
Index: doc/tm.texi
===================================================================
--- doc/tm.texi (revision 226813)
+++ doc/tm.texi (working copy)
@@ -5753,7 +5753,7 @@ This hook should return the maximum size
or zero if unbounded.
@end deftypefn
-@deftypefn {Target Hook} bool TARGET_GOACC_FORK_JOIN (bool, gimple_stmt_iterator *@var{}, @var{gimple})
+@deftypefn {Target Hook} bool TARGET_GOACC_FORK_JOIN (gimple_stmt_iterator *@var{}, @var{gimple}, const @var{int[]}, @var{bool})
This hook should convert IFN_GOACC_FORK and IFN_GOACC_JOIN function
calls to target-specific gimple. It is executed during the oacc_xform
pass. It should return true, if the functions should be deleted. The
Index: omp-low.c
===================================================================
--- omp-low.c (revision 226813)
+++ omp-low.c (working copy)
@@ -14589,7 +14589,7 @@ oacc_xform_on_device (gimple_stmt_iterat
static void
oacc_xform_dim (gimple_stmt_iterator *gsi, gimple stmt,
- int dims[], bool is_pos)
+ const int dims[], bool is_pos)
{
tree arg = gimple_call_arg (stmt, 0);
unsigned axis = (unsigned)TREE_INT_CST_LOW (arg);
@@ -14636,12 +14636,12 @@ execute_oacc_transform ()
for (ix = 0; ix != GOMP_DIM_MAX; ix++)
{
if (!pos)
- dims[ix] = 0;
+ dims[ix] = -1;
else
{
tree val = TREE_VALUE (pos);
- dims[ix] = val ? TREE_INT_CST_LOW (val) : -1;
+ dims[ix] = val ? TREE_INT_CST_LOW (val) : -2;
pos = TREE_CHAIN (pos);
}
}
@@ -14652,7 +14652,7 @@ execute_oacc_transform ()
for (ix = 0; ix != GOMP_DIM_MAX; ix++)
if (dims[ix] < 0)
{
- dims[ix] = 1;
+ dims[ix] = (int)(dims[ix] < -1);
changed = true;
}
@@ -14699,7 +14699,7 @@ execute_oacc_transform ()
case IFN_GOACC_FORK:
case IFN_GOACC_JOIN:
if (targetm.goacc.fork_join
- (ifn_code == IFN_GOACC_FORK, &gsi, stmt))
+ (&gsi, stmt, dims, ifn_code == IFN_GOACC_FORK))
{
replace_uses_by (gimple_vdef (stmt),
gimple_vuse (stmt));
@@ -14754,24 +14754,25 @@ default_goacc_dim_limit (unsigned ARG_UN
there is no RTL expander. */
bool
-default_goacc_fork_join (bool is_fork, gimple_stmt_iterator *ARG_UNUSED (gsi),
- gimple ARG_UNUSED (stmt))
+default_goacc_fork_join (gimple_stmt_iterator *ARG_UNUSED (gsi),
+ gimple ARG_UNUSED (stmt),
+ const int *ARG_UNUSED (dims), bool is_fork)
{
+ /* If there is no expander, we can delete the functions. */
if (is_fork)
{
-#ifdef HAVE_oacc_fork
- return false;
+#ifndef HAVE_oacc_fork
+ return true;
#endif
}
else
{
-#ifdef HAVE_oacc_join
- return false;
+#ifndef HAVE_oacc_join
+ return true;
#endif
}
- /* We have no expander, so delete the functions now. */
- return true;
+ return false;
}
namespace {
Index: target.def
===================================================================
--- target.def (revision 226813)
+++ target.def (working copy)
@@ -1667,7 +1667,7 @@ DEFHOOK
calls to target-specific gimple. It is executed during the oacc_xform\n\
pass. It should return true, if the functions should be deleted. The\n\
default hook returns true, if there is no RTL expanders for them.",
-bool, (bool, gimple_stmt_iterator *, gimple),
+bool, (gimple_stmt_iterator *, gimple, const int[], bool),
default_goacc_fork_join)
HOOK_VECTOR_END (goacc)
Index: targhooks.h
===================================================================
--- targhooks.h (revision 226813)
+++ targhooks.h (working copy)
@@ -109,7 +109,8 @@ extern void default_destroy_cost_data (v
extern bool default_goacc_validate_dims (tree, int []);
extern unsigned default_goacc_dim_limit (unsigned);
-extern bool default_goacc_fork_join (bool, gimple_stmt_iterator *, gimple);
+extern bool default_goacc_fork_join (gimple_stmt_iterator *, gimple,
+ const int [], bool);
/* These are here, and not in hooks.[ch], because not all users of
hooks.h include tm.h, and thus we don't have CUMULATIVE_ARGS. */
Index: tree-vrp.c
===================================================================
--- tree-vrp.c (revision 226813)
+++ tree-vrp.c (working copy)
@@ -66,8 +66,8 @@ along with GCC; see the file COPYING3.
#include "optabs.h"
#include "tree-ssa-scopedtables.h"
#include "tree-ssa-threadedge.h"
-
-
+#include "omp-low.h"
+#include "target.h"
/* Range of values that can be associated with an SSA_NAME after VRP
has executed. */
@@ -4126,7 +4126,9 @@ extract_range_basic (value_range_t *vr,
else if (is_gimple_call (stmt) && gimple_call_internal_p (stmt))
{
enum tree_code subcode = ERROR_MARK;
- switch (gimple_call_internal_fn (stmt))
+ unsigned ifn_code = gimple_call_internal_fn (stmt);
+
+ switch (ifn_code)
{
case IFN_UBSAN_CHECK_ADD:
subcode = PLUS_EXPR;
@@ -4137,6 +4139,33 @@ extract_range_basic (value_range_t *vr,
case IFN_UBSAN_CHECK_MUL:
subcode = MULT_EXPR;
break;
+ case IFN_GOACC_DIM_SIZE:
+ case IFN_GOACC_DIM_POS:
+ /* Optimizing these two internal functions helps the loop
+ optimizer elimitate outer comparisons. Size is [1,N]
+ and pos is [0,N-1]. */
+ {
+ bool is_pos = ifn_code == IFN_GOACC_DIM_POS;
+ tree attr = get_oacc_fn_attrib (current_function_decl);
+ tree arg = gimple_call_arg (stmt, 0);
+ unsigned axis = (unsigned)TREE_INT_CST_LOW (arg);
+ tree dims = TREE_VALUE (attr);
+
+ for (unsigned ix = axis; ix--;)
+ dims = TREE_CHAIN (dims);
+ int size = TREE_INT_CST_LOW (TREE_VALUE (dims));
+
+ if (!size)
+ size = targetm.goacc.dim_limit (axis);
+ if (size)
+ set_value_range (vr, VR_RANGE,
+ build_int_cst (integer_type_node, !is_pos),
+ build_int_cst (integer_type_node,
+ size - is_pos), NULL);
+ return;
+ }
+ break;
+
default:
break;
}
