nvptx backend prerequisites for OpenMP offloading

gcc/
	* config/nvptx/mkoffload.c (main): Check that either OpenACC or OpenMP
	is selected.  Pass -mgomp to offload compiler in OpenMP case.
	* config/nvptx/nvptx-protos.h (nvptx_shuffle_kind): Move enum
	declaration from nvptx.c.
	(nvptx_gen_shuffle): Declare.
	(nvptx_output_set_softstack): Declare.
	* config/nvptx/nvptx.c (nvptx_shuffle_kind): Move to nvptx-protos.h.
	(need_softstack_decl): New variable.
	(need_unisimt_decl): New variable.
	(diagnose_openacc_conflict): New.  Use it...
	(nvptx_option_override): ...here.  Handle TARGET_GOMP.
	(nvptx_encode_section_info): Handle "shared" attribute.
	(write_as_kernel): Restrict to OpenACC target regions.
	(init_softstack_frame): New.
	(nvptx_init_unisimt_predicate): New.
	(write_omp_entry): New.  Use it...
	(nvptx_declare_function_name): ...here to emit OpenMP target region
	entrypoints.  Handle TARGET_SOFT_STACK.  Call
	nvptx_init_unisimt_predicate.
	(nvptx_output_set_softstack): New.
	(nvptx_get_drap_rtx): Return %argp as the DRAP if needed.
	(nvptx_gen_shuffle): Export.
	(nvptx_output_call_insn): Handle COND_EXEC patterns.  Emit instruction
	predicate.
	(nvptx_print_operand): Fix handling of instruction predicates.
	(nvptx_get_unisimt_master): New helper function.
	(nvptx_get_unisimt_predicate): Ditto.
	(nvptx_call_insn_is_syscall_p): Ditto.
	(nvptx_unisimt_handle_set): Ditto.
	(nvptx_reorg_uniform_simt): New.  Transform code for -muniform-simt.
	(nvptx_reorg): Call nvptx_reorg_uniform_simt.
	(nvptx_handle_shared_attribute): New.  Use it...
	(nvptx_attribute_table): ... here (new entry).
	(nvptx_record_offload_symbol): Handle NULL attributes.
	(nvptx_file_end): Handle need_softstack_decl and need_unisimt_decl.
	(nvptx_simt_vf): New.
	(TARGET_SIMT_VF): Define.
	* config/nvptx/nvptx.h (TARGET_CPU_CPP_BUILTINS): Define
	__nvptx_softstack or __nvptx_unisimt__ when -msoft-stack, or resp.
	-muniform-simt option is active.
	(STACK_SIZE_MODE): Define.
	(FIXED_REGISTERS): Adjust.
	(SOFTSTACK_SLOT_REGNUM): New.
	(SOFTSTACK_PREV_REGNUM): New.
	(REGISTER_NAMES): Adjust.
	(struct machine_function): New fields.
	* config/nvptx/nvptx.md (UNSPEC_SET_SOFTSTACK): New.
	(UNSPEC_VOTE_BALLOT): Ditto.
	(UNSPEC_LANEID): Ditto.
	(UNSPECV_NOUNROLL): Ditto.
	(atomic): New attribute.
	(predicable): New attribute.  Generate predicated forms via
	define_cond_exec.
	(br_true): Mark as not predicable.
	(br_false): Ditto.
	(br_true_uni): Ditto.
	(br_false_uni): Ditto.
	(return): Ditto.
	(trap_if_true): Ditto.
	(trap_if_false): Ditto.
	(nvptx_fork): Ditto.
	(nvptx_forked): Ditto.
	(nvptx_joining): Ditto.
	(nvptx_join): Ditto.
	(nvptx_barsync): Ditto.
	(epilogue): Emit stack restore if TARGET_SOFT_STACK.
	(allocate_stack): Implement for TARGET_SOFT_STACK.  Remove unused code.
	(allocate_stack_<mode>): Remove unused pattern.
	(set_softstack_insn): New pattern.
	(restore_stack_block): Handle for TARGET_SOFT_STACK.
	(nvptx_vote_ballot): New pattern.
	(omp_simt_lane): Ditto.
	(omp_simt_last_lane): Ditto.
	(omp_simt_ordered): Ditto.
	(omp_simt_vote_any): Ditto.
	(omp_simt_xchg_bfly): Ditto.
	(omp_simt_xchg_idx): Ditto.
	(nvptx_nounroll): Ditto.
	(atomic_compare_and_swap<mode>_1): Mark with atomic attribute.
	(atomic_exchange<mode>): Ditto.
	(atomic_fetch_add<mode>): Ditto.
	(atomic_fetch_addsf): Ditto.
	(atomic_fetch_<logic><mode>): Ditto.
	* config/nvptx/nvptx.opt: (msoft-stack): New option.
	(muniform-simt): Ditto.
	(mgomp): Ditto.
	* config/nvptx/t-nvptx (MULTILIB_OPTIONS): New.
	* doc/extend.texi (Nvidia PTX Variable Attributes): New section.
	* doc/invoke.texi (msoft-stack): Document.
	(muniform-simt): Document
	(mgomp): Document.
	* doc/tm.texi: Regenerate.
	* doc/tm.texi.in: (TARGET_SIMT_VF): New hook.
	* target.def: Define it.
	* target-insns.def (omp_simt_lane): New.
	(omp_simt_last_lane): New.
	(omp_simt_ordered): New.
	(omp_simt_vote_any): New.
	(omp_simt_xchg_bfly): New.
	(omp_simt_xchg_idx): New.

libgcc/
	* config/nvptx/crt0.c (__main): Setup __nvptx_stacks and __nvptx_uni.
	* config/nvptx/mgomp.c: New file.
	* config/nvptx/t-nvptx: Add mgomp.c

gcc/testsuite/
	* lib/target-supports.exp (check_effective_target_alloca): Use a
	compile test.
	* gcc.target/nvptx/softstack.c: New test.
	* gcc.target/nvptx/decl-shared.c: New test.
	* gcc.target/nvptx/decl-shared-init.c: New test.



git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@242503 138bc75d-0d04-0410-961f-82ee72b054a4

4 files changed, 52 insertions, 1 deletions

diff --git a/libgcc/ChangeLog b/libgcc/ChangeLog
index cfa61115f6a..4daa0aa3409 100644
--- a/libgcc/ChangeLog
+++ b/libgcc/ChangeLog
@@ -1,3 +1,9 @@
+2016-11-16  Alexander Monakov  <amonakov@ispras.ru>
+
+	* config/nvptx/crt0.c (__main): Setup __nvptx_stacks and __nvptx_uni.
+	* config/nvptx/mgomp.c: New file.
+	* config/nvptx/t-nvptx: Add mgomp.c
+
 2016-11-16  Waldemar Brodkorb  <wbx@openadk.org>
 
 	PR libgcc/68468
diff --git a/libgcc/config/nvptx/crt0.c b/libgcc/config/nvptx/crt0.c
index 3b7382d43af..5a7dbf6f22f 100644
--- a/libgcc/config/nvptx/crt0.c
+++ b/libgcc/config/nvptx/crt0.c
@@ -24,6 +24,14 @@ int *__exitval_ptr;
 extern void __attribute__((noreturn)) exit (int status);
 extern int main (int, void **);
 
+/* Always setup soft stacks to allow testing with -msoft-stack but without
+   -mgomp.  32 is the maximum number of warps in a CTA: the definition here
+   must match the external declaration emitted by the compiler.  */
+void *__nvptx_stacks[32] __attribute__((shared,nocommon));
+
+/* Likewise for -muniform-simt.  */
+unsigned __nvptx_uni[32] __attribute__((shared,nocommon));
+
 void __attribute__((kernel))
 __main (int *rval_ptr, int argc, void **argv)
 {
@@ -33,5 +41,9 @@ __main (int *rval_ptr, int argc, void **argv)
   if (rval_ptr)
     *rval_ptr = 255;
 
+  static char stack[131072] __attribute__((aligned(8)));
+  __nvptx_stacks[0] = stack + sizeof stack;
+  __nvptx_uni[0] = 0;
+
   exit (main (argc, argv));
 }
diff --git a/libgcc/config/nvptx/mgomp.c b/libgcc/config/nvptx/mgomp.c
new file mode 100644
index 00000000000..d8ca5818314
--- /dev/null
+++ b/libgcc/config/nvptx/mgomp.c
@@ -0,0 +1,32 @@
+/* Define shared memory arrays for -msoft-stack and -muniform-simt.
+
+   Copyright (C) 2015-2016 Free Software Foundation, Inc.
+
+   This file is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published by the
+   Free Software Foundation; either version 3, or (at your option) any
+   later version.
+
+   This file is distributed in the hope that it will be useful, but
+   WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   General Public License for more details.
+
+   Under Section 7 of GPL version 3, you are granted additional
+   permissions described in the GCC Runtime Library Exception, version
+   3.1, as published by the Free Software Foundation.
+
+   You should have received a copy of the GNU General Public License and
+   a copy of the GCC Runtime Library Exception along with this program;
+   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+   <http://www.gnu.org/licenses/>.  */
+
+/* OpenACC offloading does not use these symbols; thus, they are exposed
+   only for the -mgomp multilib.  The same definitions are also provided
+   in crt0.c for the case of non-offloading compilation.  32 is the maximum
+   number of warps in a CTA.  */
+
+#if defined(__nvptx_softstack__) && defined(__nvptx_unisimt__)
+void *__nvptx_stacks[32] __attribute__((shared,nocommon));
+unsigned __nvptx_uni[32] __attribute__((shared,nocommon));
+#endif
diff --git a/libgcc/config/nvptx/t-nvptx b/libgcc/config/nvptx/t-nvptx
index daf252f2472..c4d20c94cbb 100644
--- a/libgcc/config/nvptx/t-nvptx
+++ b/libgcc/config/nvptx/t-nvptx
@@ -1,4 +1,5 @@
-LIB2ADD=$(srcdir)/config/nvptx/reduction.c
+LIB2ADD=$(srcdir)/config/nvptx/reduction.c \
+	$(srcdir)/config/nvptx/mgomp.c
 
 LIB2ADDEH=
 LIB2FUNCS_EXCLUDE=__main