* cgraph.h (enum cgraph_simd_clone_arg_type): New.

	(struct cgraph_simd_clone_arg, struct cgraph_simd_clone): New.
	(struct cgraph_node): Add simdclone and simd_clones fields.
	* config/i386/i386.c (ix86_simd_clone_compute_vecsize_and_simdlen,
	ix86_simd_clone_adjust, ix86_simd_clone_usable): New functions.
	(TARGET_SIMD_CLONE_COMPUTE_VECSIZE_AND_SIMDLEN,
	TARGET_SIMD_CLONE_ADJUST, TARGET_SIMD_CLONE_USABLE): Define.
	* doc/tm.texi.in (TARGET_SIMD_CLONE_COMPUTE_VECSIZE_AND_SIMDLEN,
	TARGET_SIMD_CLONE_ADJUST, TARGET_SIMD_CLONE_USABLE): Add.
	* doc/tm.texi: Regenerated.
	* ggc.h (ggc_alloc_cleared_simd_clone_stat): New function.
	* ipa-cp.c (determine_versionability): Fail if "omp declare simd"
	attribute is present.
	* omp-low.c: Include pretty-print.h, ipa-prop.h and tree-eh.h.
	(simd_clone_vector_of_formal_parm_types): New function.
	(simd_clone_struct_alloc, simd_clone_struct_copy,
	simd_clone_vector_of_formal_parm_types, simd_clone_clauses_extract,
	simd_clone_compute_base_data_type, simd_clone_mangle,
	simd_clone_create, simd_clone_adjust_return_type,
	create_tmp_simd_array, simd_clone_adjust_argument_types,
	simd_clone_init_simd_arrays): New functions.
	(struct modify_stmt_info): New type.
	(ipa_simd_modify_stmt_ops, ipa_simd_modify_function_body,
	simd_clone_adjust, expand_simd_clones, ipa_omp_simd_clone): New
	functions.
	(pass_data_omp_simd_clone): New variable.
	(pass_omp_simd_clone): New class.
	(make_pass_omp_simd_clone): New function.
	* passes.def (pass_omp_simd_clone): New.
	* target.def (TARGET_SIMD_CLONE_COMPUTE_VECSIZE_AND_SIMDLEN,
	TARGET_SIMD_CLONE_ADJUST, TARGET_SIMD_CLONE_USABLE): New target
	hooks.
	* target.h (struct cgraph_node, struct cgraph_simd_node): Declare.
	* tree-core.h (OMP_CLAUSE_LINEAR_VARIABLE_STRIDE): Document.
	* tree.h (OMP_CLAUSE_LINEAR_VARIABLE_STRIDE): Define.
	* tree-pass.h (make_pass_omp_simd_clone): New prototype.
	* tree-vect-data-refs.c: Include cgraph.h.
	(vect_analyze_data_refs): Inline by hand find_data_references_in_loop
	and find_data_references_in_bb, if find_data_references_in_stmt
	fails, still allow calls to #pragma omp declare simd functions
	in #pragma omp simd loops unless they contain data references among
	the call arguments or in lhs.
	* tree-vect-loop.c (vect_determine_vectorization_factor): Handle
	calls with no lhs.
	(vect_transform_loop): Allow NULL STMT_VINFO_VECTYPE for calls without
	lhs.
	* tree-vectorizer.h (enum stmt_vec_info_type): Add
	call_simd_clone_vec_info_type.
	(struct _stmt_vec_info): Add simd_clone_fndecl field.
	(STMT_VINFO_SIMD_CLONE_FNDECL): Define.
	* tree-vect-stmts.c: Include tree-ssa-loop.h,
	tree-scalar-evolution.h and cgraph.h.
	(vectorizable_call): Handle calls without lhs.  Assert
	!stmt_can_throw_internal instead of failing for it.  Don't update
	EH stuff.
	(struct simd_call_arg_info): New.
	(vectorizable_simd_clone_call): New function.
	(vect_transform_stmt): Call it.
	(vect_analyze_stmt): Likewise.  Allow NULL STMT_VINFO_VECTYPE for
	calls without lhs.
	* ipa-prop.c (ipa_add_new_function): Only call ipa_analyze_node
	if cgraph_function_with_gimple_body_p is true.
c/
	* c-decl.c (c_builtin_function_ext_scope): Avoid binding if
	external_scope is NULL.
cp/
	* semantics.c (finish_omp_clauses): For #pragma omp declare simd
	linear clause step call maybe_constant_value.
testsuite/
	* g++.dg/gomp/declare-simd-1.C (f38): Make sure
	simdlen is a power of two.
	* gcc.dg/gomp/simd-clones-2.c: Compile on all targets.
	Remove -msse2.  Adjust regexps for name mangling changes.
	* gcc.dg/gomp/simd-clones-3.c: Likewise.
	* gcc.dg/vect/vect-simd-clone-1.c: New test.
	* gcc.dg/vect/vect-simd-clone-2.c: New test.
	* gcc.dg/vect/vect-simd-clone-3.c: New test.
	* gcc.dg/vect/vect-simd-clone-4.c: New test.
	* gcc.dg/vect/vect-simd-clone-5.c: New test.
	* gcc.dg/vect/vect-simd-clone-6.c: New test.
	* gcc.dg/vect/vect-simd-clone-7.c: New test.
	* gcc.dg/vect/vect-simd-clone-8.c: New test.
	* gcc.dg/vect/vect-simd-clone-9.c: New test.
	* gcc.dg/vect/vect-simd-clone-10.c: New test.
	* gcc.dg/vect/vect-simd-clone-10.h: New file.
	* gcc.dg/vect/vect-simd-clone-10a.c: New file.
	* gcc.dg/vect/vect-simd-clone-11.c: New test.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@205442 138bc75d-0d04-0410-961f-82ee72b054a4

1 files changed, 99 insertions, 0 deletions

diff --git a/gcc/cgraph.h b/gcc/cgraph.h
index c6b35f9cfc4..547950498d0 100644
--- a/gcc/cgraph.h
+++ b/gcc/cgraph.h
@@ -256,6 +256,99 @@ struct GTY(()) cgraph_clone_info
   bitmap combined_args_to_skip;
 };
 
+enum cgraph_simd_clone_arg_type
+{
+  SIMD_CLONE_ARG_TYPE_VECTOR,
+  SIMD_CLONE_ARG_TYPE_UNIFORM,
+  SIMD_CLONE_ARG_TYPE_LINEAR_CONSTANT_STEP,
+  SIMD_CLONE_ARG_TYPE_LINEAR_VARIABLE_STEP,
+  SIMD_CLONE_ARG_TYPE_MASK
+};
+
+/* Function arguments in the original function of a SIMD clone.
+   Supplementary data for `struct simd_clone'.  */
+
+struct GTY(()) cgraph_simd_clone_arg {
+  /* Original function argument as it originally existed in
+     DECL_ARGUMENTS.  */
+  tree orig_arg;
+
+  /* orig_arg's function (or for extern functions type from
+     TYPE_ARG_TYPES).  */
+  tree orig_type;
+
+  /* If argument is a vector, this holds the vector version of
+     orig_arg that after adjusting the argument types will live in
+     DECL_ARGUMENTS.  Otherwise, this is NULL.
+
+     This basically holds:
+       vector(simdlen) __typeof__(orig_arg) new_arg.  */
+  tree vector_arg;
+
+  /* vector_arg's type (or for extern functions new vector type.  */
+  tree vector_type;
+
+  /* If argument is a vector, this holds the array where the simd
+     argument is held while executing the simd clone function.  This
+     is a local variable in the cloned function.  Its content is
+     copied from vector_arg upon entry to the clone.
+
+     This basically holds:
+       __typeof__(orig_arg) simd_array[simdlen].  */
+  tree simd_array;
+
+  /* A SIMD clone's argument can be either linear (constant or
+     variable), uniform, or vector.  */
+  enum cgraph_simd_clone_arg_type arg_type;
+
+  /* For arg_type SIMD_CLONE_ARG_TYPE_LINEAR_CONSTANT_STEP this is
+     the constant linear step, if arg_type is
+     SIMD_CLONE_ARG_TYPE_LINEAR_VARIABLE_STEP, this is index of
+     the uniform argument holding the step, otherwise 0.  */
+  HOST_WIDE_INT linear_step;
+
+  /* Variable alignment if available, otherwise 0.  */
+  unsigned int alignment;
+};
+
+/* Specific data for a SIMD function clone.  */
+
+struct GTY(()) cgraph_simd_clone {
+  /* Number of words in the SIMD lane associated with this clone.  */
+  unsigned int simdlen;
+
+  /* Number of annotated function arguments in `args'.  This is
+     usually the number of named arguments in FNDECL.  */
+  unsigned int nargs;
+
+  /* Max hardware vector size in bits for integral vectors.  */
+  unsigned int vecsize_int;
+
+  /* Max hardware vector size in bits for floating point vectors.  */
+  unsigned int vecsize_float;
+
+  /* The mangling character for a given vector size.  This is is used
+     to determine the ISA mangling bit as specified in the Intel
+     Vector ABI.  */
+  unsigned char vecsize_mangle;
+
+  /* True if this is the masked, in-branch version of the clone,
+     otherwise false.  */
+  unsigned int inbranch : 1;
+
+  /* True if this is a Cilk Plus variant.  */
+  unsigned int cilk_elemental : 1;
+
+  /* Doubly linked list of SIMD clones.  */
+  struct cgraph_node *prev_clone, *next_clone;
+
+  /* Original cgraph node the SIMD clones were created for.  */
+  struct cgraph_node *origin;
+
+  /* Annotated function arguments for the original function.  */
+  struct cgraph_simd_clone_arg GTY((length ("%h.nargs"))) args[1];
+};
+
 
 /* The cgraph data structure.
    Each function decl has assigned cgraph_node listing callees and callers.  */
@@ -284,6 +377,12 @@ public:
   /* Declaration node used to be clone of. */
   tree former_clone_of;
 
+  /* If this is a SIMD clone, this points to the SIMD specific
+     information for it.  */
+  struct cgraph_simd_clone *simdclone;
+  /* If this function has SIMD clones, this points to the first clone.  */
+  struct cgraph_node *simd_clones;
+
   /* Interprocedural passes scheduled to have their transform functions
      applied next time we execute local pass on them.  We maintain it
      per-function in order to allow IPA passes to introduce new functions.  */