This patch provides AMD GCN-specific parts supporting middle-end
worker partitioning. The adjust_propagation_record hook is now called
create_propagation_record. Several builtins are redefined to take an
argument in a special address space (corresponding to GPU shared memory).
Tested alongside other patches in this series. OK?
Thanks,
Julian
ChangeLog
gcc/
* config/gcn/gcn-protos.h (gcn_goacc_adjust_propagation_record): Rename
prototype to...
(gcn_goacc_create_propagation_record): This.
* config/gcn/gcn-tree.c (gcn_goacc_adjust_propagation_record): Rename
function to...
(gcn_goacc_create_propagation_record): This. Adjust comment.
* config/gcn/gcn.c (gcn_init_builtins): Override decls for
BUILT_IN_GOACC_SINGLE_START, BUILT_IN_GOACC_SINGLE_COPY_START,
BUILT_IN_GOACC_SINGLE_COPY_END and BUILT_IN_GOACC_BARRIER.
(gcn_fork_join): Remove inaccurate comment.
(TARGET_GOACC_ADJUST_PROPAGATION_RECORD): Rename to...
(TARGET_GOACC_CREATE_PROPAGATION_RECORD): This.
---
gcc/config/gcn/gcn-protos.h | 2 +-
gcc/config/gcn/gcn-tree.c | 6 +++---
gcc/config/gcn/gcn.c | 11 +++--------
3 files changed, 7 insertions(+), 12 deletions(-)
diff --git a/gcc/config/gcn/gcn-protos.h b/gcc/config/gcn/gcn-protos.h
index 714d51189d9..e33c0598fee 100644
--- a/gcc/config/gcn/gcn-protos.h
+++ b/gcc/config/gcn/gcn-protos.h
@@ -37,7 +37,7 @@ extern rtx gcn_full_exec ();
extern rtx gcn_full_exec_reg ();
extern rtx gcn_gen_undef (machine_mode);
extern bool gcn_global_address_p (rtx);
-extern tree gcn_goacc_adjust_propagation_record (tree record_type, bool sender,
+extern tree gcn_goacc_create_propagation_record (tree record_type, bool sender,
const char *name);
extern void gcn_goacc_adjust_private_decl (tree var, int level);
extern void gcn_goacc_reduction (gcall *call);
diff --git a/gcc/config/gcn/gcn-tree.c b/gcc/config/gcn/gcn-tree.c
index aa56e236134..538034f7372 100644
--- a/gcc/config/gcn/gcn-tree.c
+++ b/gcc/config/gcn/gcn-tree.c
@@ -667,12 +667,12 @@ gcn_goacc_reduction (gcall *call)
}
}
-/* Implement TARGET_GOACC_ADJUST_PROPAGATION_RECORD.
+/* Implement TARGET_GOACC_CREATE_PROPAGATION_RECORD.
- Tweak (worker) propagation record, e.g. to put it in shared memory. */
+ Create (worker) propagation record in shared memory. */
tree
-gcn_goacc_adjust_propagation_record (tree record_type, bool sender,
+gcn_goacc_create_propagation_record (tree record_type, bool sender,
const char *name)
{
tree type = record_type;
diff --git a/gcc/config/gcn/gcn.c b/gcc/config/gcn/gcn.c
index cf2f30413ae..2f758ef3ddc 100644
--- a/gcc/config/gcn/gcn.c
+++ b/gcc/config/gcn/gcn.c
@@ -3494,8 +3494,6 @@ gcn_init_builtins (void)
TREE_NOTHROW (gcn_builtin_decls[i]) = 1;
}
-/* FIXME: remove the ifdef once OpenACC support is merged upstream. */
-#ifdef BUILT_IN_GOACC_SINGLE_START
/* These builtins need to take/return an LDS pointer: override the generic
versions here. */
@@ -3512,7 +3510,6 @@ gcn_init_builtins (void)
set_builtin_decl (BUILT_IN_GOACC_BARRIER,
gcn_builtin_decls[GCN_BUILTIN_ACC_BARRIER], false);
-#endif
}
/* Expand the CMP_SWAP GCN builtins. We have our own versions that do
@@ -4798,8 +4795,6 @@ static bool
gcn_fork_join (gcall *ARG_UNUSED (call), const int *ARG_UNUSED (dims),
bool ARG_UNUSED (is_fork))
{
- /* GCN does not use the fork/join concept invented for NVPTX.
- Instead we use standard autovectorization. */
return false;
}
@@ -6064,9 +6059,9 @@ print_operand (FILE *file, rtx x, int code)
#define TARGET_GIMPLIFY_VA_ARG_EXPR gcn_gimplify_va_arg_expr
#undef TARGET_OMP_DEVICE_KIND_ARCH_ISA
#define TARGET_OMP_DEVICE_KIND_ARCH_ISA gcn_omp_device_kind_arch_isa
-#undef TARGET_GOACC_ADJUST_PROPAGATION_RECORD
-#define TARGET_GOACC_ADJUST_PROPAGATION_RECORD \
- gcn_goacc_adjust_propagation_record
+#undef TARGET_GOACC_CREATE_PROPAGATION_RECORD
+#define TARGET_GOACC_CREATE_PROPAGATION_RECORD \
+ gcn_goacc_create_propagation_record
#undef TARGET_GOACC_ADJUST_PRIVATE_DECL
#define TARGET_GOACC_ADJUST_PRIVATE_DECL gcn_goacc_adjust_private_decl
#undef TARGET_GOACC_FORK_JOIN
--
2.23.0
