This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Vector comparison
- From: Artem Shinkarov <artyom dot shinkaroff at gmail dot com>
- To: gcc-patches at gcc dot gnu dot org
- Cc: Richard Guenther <richard dot guenther at gmail dot com>
- Date: Sun, 15 Aug 2010 18:09:39 +0100
- Subject: Vector comparison
This patch implements vector comparison according to OpenCL standard.
The patch tries to dispatch vector comparison to hardware-specific
instructions. If case when it is impossible, vector comparison is
expanded piecewise.
Currently the compilation process with this patch applied slows down
dramatically if you compile with -On. Can't find the reason. Any help
would be appreciated.
Changelog:
2010-08-15 Artem Shinkarov <artyom.shinkaroff@gmail.com>
gcc/
* targhooks.c (default_builtin_vec_compare): New hook.
* targhooks.h (default_builtin_vec_compare): New definition.
* target.def (builtin_vec_compare): New hook.
* tree.c (build_vector_from_val): New function.
* tree.h (build_vector_from_val): New definition.
* target.h: New include (gimple.h).
* c-typeck.c (build_binary_op): Allow vector comparison.
(c_obj_common_truthvalue_conversion): Deny vector comparison
inside of if statement.
* tree-vect-generic.c (do_compare): Helper function.
(expand_vector_comparison): Check if hardware comparison
is available, if not expand comparison piecewise.
(expand_vector_operation): Handle vector comparison
expressions separately.
* Makefile.in: New dependencies.
* tree-cfg.c (verify_gimple_comparison): Allow vector
comparison operations in gimple.
* config/i386/i386.c (vector_fp_compare): Build hardware
specific code for floating point vector comparison.
(vector_int_compare): Build hardware specific code for
integer vector comparison.
(ix86_vectorize_builtin_vec_compare): Implementation of
builtin_vec_compare hook.
gcc/testsuite/
* gcc.c-torture/execute/vector-compare-1.c: New test.
gcc/doc
* extend.texi: Adjust.
* tm.texi: Adjust.
* tm.texi.in: Adjust.
bootstrapped and tested on x86_64_unknown-linux.
Thank you,
Artem Shinkarov.
Index: gcc/doc/extend.texi
===================================================================
--- gcc/doc/extend.texi (revision 163244)
+++ gcc/doc/extend.texi (working copy)
@@ -6141,6 +6141,26 @@ minus or complement operators on a vecto
elements are the negative or complemented values of the corresponding
elements in the operand.
+Vector comparison is supported within standard comparison operators:
+@code{==, !=, <, <=, >, >=}. Both integer-type and real-type vectors
+can be compared but only of the same type. The result of the
+comparison is a signed integer-type vector where the size of each
+element must be the same as the size of compared vectors element.
+Comparison is happening element by element. False value is 0, true
+value is -1 (constant of the appropriate type where all bits are set).
+Consider the following example.
+
+@smallexample
+typedef int v4si __attribute__ ((vector_size (16)));
+
+v4si a = @{1,2,3,4@};
+v4si b = @{3,2,1,4@};
+v4si c;
+
+c = a > b; /* The result would be @{0, 0,-1, 0@} */
+c = a == b; /* The result would be @{0,-1, 0,-1@} */
+@end smallexample
+
You can declare variables and use them in function calls and returns, as
well as in assignments and some casts. You can specify a vector type as
a return type for a function. Vector types can also be used as function
Index: gcc/doc/tm.texi
===================================================================
--- gcc/doc/tm.texi (revision 163244)
+++ gcc/doc/tm.texi (working copy)
@@ -5710,6 +5710,10 @@ misalignment value (@var{misalign}).
Return true if vector alignment is reachable (by peeling N iterations) for the given type.
@end deftypefn
+@deftypefn {Target Hook} tree TARGET_VECTORIZE_BUILTIN_VEC_COMPARE (gimple_stmt_iterator *@var{gsi}, tree @var{type}, tree @var{v0}, tree @var{v1}, enum tree_code @var{code})
+This hook should check whether it is possible to express vectorcomparison using the hardware-specific instructions and return resulttree. Hook should return NULL_TREE if expansion is impossible.
+@end deftypefn
+
@deftypefn {Target Hook} tree TARGET_VECTORIZE_BUILTIN_VEC_PERM (tree @var{type}, tree *@var{mask_element_type})
Target builtin that implements vector permute.
@end deftypefn
Index: gcc/doc/tm.texi.in
===================================================================
--- gcc/doc/tm.texi.in (revision 163244)
+++ gcc/doc/tm.texi.in (working copy)
@@ -5710,6 +5710,8 @@ misalignment value (@var{misalign}).
Return true if vector alignment is reachable (by peeling N iterations) for the given type.
@end deftypefn
+@hook TARGET_VECTORIZE_BUILTIN_VEC_COMPARE
+
@hook TARGET_VECTORIZE_BUILTIN_VEC_PERM
Target builtin that implements vector permute.
@end deftypefn
Index: gcc/targhooks.c
===================================================================
--- gcc/targhooks.c (revision 163244)
+++ gcc/targhooks.c (working copy)
@@ -969,6 +969,18 @@ default_builtin_vector_alignment_reachab
return true;
}
+/* Replaces vector comparison with the target-specific instructions
+ and returns the resulting variable or NULL_TREE otherwise. */
+tree
+default_builtin_vec_compare (gimple_stmt_iterator *gsi ATTRIBUTE_UNUSED,
+ tree type ATTRIBUTE_UNUSED,
+ tree v0 ATTRIBUTE_UNUSED,
+ tree v1 ATTRIBUTE_UNUSED,
+ enum tree_code code ATTRIBUTE_UNUSED)
+{
+ return NULL_TREE;
+}
+
/* By default, assume that a target supports any factor of misalignment
memory access if it supports movmisalign patten.
is_packed is true if the memory access is defined in a packed struct. */
Index: gcc/targhooks.h
===================================================================
--- gcc/targhooks.h (revision 163244)
+++ gcc/targhooks.h (working copy)
@@ -82,6 +82,11 @@ extern int default_builtin_vectorization
extern tree default_builtin_reciprocal (unsigned int, bool, bool);
extern bool default_builtin_vector_alignment_reachable (const_tree, bool);
+
+extern tree default_builtin_vec_compare (gimple_stmt_iterator *gsi,
+ tree type, tree v0, tree v1,
+ enum tree_code code);
+
extern bool
default_builtin_support_vector_misalignment (enum machine_mode mode,
const_tree,
Index: gcc/target.def
===================================================================
--- gcc/target.def (revision 163244)
+++ gcc/target.def (working copy)
@@ -836,6 +836,15 @@ DEFHOOK
bool, (tree vec_type, tree mask),
hook_bool_tree_tree_true)
+/* Implement hardware vector comparison or return false. */
+DEFHOOK
+(builtin_vec_compare,
+ "This hook should check whether it is possible to express vector\
+comparison using the hardware-specific instructions and return result\
+tree. Hook should return NULL_TREE if expansion is impossible.",
+ tree, (gimple_stmt_iterator *gsi, tree type, tree v0, tree v1, enum tree_code code),
+ default_builtin_vec_compare)
+
/* Return true if the target supports misaligned store/load of a
specific factor denoted in the third parameter. The last parameter
is true if the access is defined in a packed struct. */
Index: gcc/tree.c
===================================================================
--- gcc/tree.c (revision 163244)
+++ gcc/tree.c (working copy)
@@ -1358,6 +1358,28 @@ build_vector_from_ctor (tree type, VEC(c
return build_vector (type, nreverse (list));
}
+/* Build a vector of type VECTYPE where all the elements are SCs. */
+tree
+build_vector_from_val (const tree sc, const tree vectype)
+{
+ tree t = NULL_TREE;
+ int i, nunits = TYPE_VECTOR_SUBPARTS (vectype);
+
+ if (sc == error_mark_node)
+ return sc;
+
+ gcc_assert (TREE_TYPE (sc) == TREE_TYPE (vectype));
+
+ for (i = 0; i < nunits; ++i)
+ t = tree_cons (NULL_TREE, sc, t);
+
+ if (CONSTANT_CLASS_P (sc))
+ return build_vector (vectype, t);
+ else
+ return build_constructor_from_list (vectype, t);
+}
+
+
/* Return a new CONSTRUCTOR node whose type is TYPE and whose values
are in the VEC pointed to by VALS. */
tree
Index: gcc/tree.h
===================================================================
--- gcc/tree.h (revision 163244)
+++ gcc/tree.h (working copy)
@@ -4027,6 +4027,7 @@ extern tree build_int_cst_type (tree, HO
extern tree build_int_cst_wide (tree, unsigned HOST_WIDE_INT, HOST_WIDE_INT);
extern tree build_vector (tree, tree);
extern tree build_vector_from_ctor (tree, VEC(constructor_elt,gc) *);
+extern tree build_vector_from_val (const tree, const tree);
extern tree build_constructor (tree, VEC(constructor_elt,gc) *);
extern tree build_constructor_single (tree, tree, tree);
extern tree build_constructor_from_list (tree, tree);
Index: gcc/target.h
===================================================================
--- gcc/target.h (revision 163244)
+++ gcc/target.h (working copy)
@@ -51,7 +51,7 @@
#include "tm.h"
#include "insn-modes.h"
-
+#include "gimple.h"
/* Types used by the record_gcc_switches() target function. */
typedef enum
{
Index: gcc/testsuite/gcc.c-torture/execute/vector-compare-1.c
===================================================================
--- gcc/testsuite/gcc.c-torture/execute/vector-compare-1.c (revision 0)
+++ gcc/testsuite/gcc.c-torture/execute/vector-compare-1.c (revision 0)
@@ -0,0 +1,109 @@
+#define vector(elcount, type) \
+__attribute__((vector_size((elcount)*sizeof(type)))) type
+
+#define vidx(type, vec, idx) (*(((type *) &(vec)) + idx))
+
+#define check_compare(type, count, res, i0, i1, op) \
+do { \
+ int __i; \
+ for (__i = 0; __i < count; __i ++) { \
+ if (vidx (type, res, __i) != \
+ ((vidx (type, i0, __i) op vidx (type, i1, __i)) ? (type)-1 : 0)) { \
+ __builtin_printf ("%i != ((%i " #op " %i) ? -1 : 0) ", vidx (type, res, __i), \
+ vidx (type, i0, __i), vidx (type, i1, __i)); \
+ __builtin_abort (); \
+ } \
+ } \
+} while (0)
+
+#define test(type, count, v0, v1, res); \
+do { \
+ res = (v0 > v1); \
+ check_compare (type, count, res, v0, v1, >); \
+ res = (v0 < v1); \
+ check_compare (type, count, res, v0, v1, <); \
+ res = (v0 >= v1); \
+ check_compare (type, count, res, v0, v1, >=); \
+ res = (v0 <= v1); \
+ check_compare (type, count, res, v0, v1, <=); \
+ res = (v0 == v1); \
+ check_compare (type, count, res, v0, v1, ==); \
+ res = (v0 != v1); \
+ check_compare (type, count, res, v0, v1, !=); \
+} while (0)
+
+
+int main (int argc, char *argv[]) {
+#define INT int
+ vector (4, INT) i0;
+ vector (4, INT) i1;
+ vector (4, int) ires;
+
+ i0 = (vector (4, INT)){argc, 1, 2, 10};
+ i1 = (vector (4, INT)){0, 3, 2, (INT)-23};
+ test (INT, 4, i0, i1, ires);
+#undef INT
+
+
+#define INT unsigned int
+ vector (4, int) ures;
+ vector (4, INT) u0;
+ vector (4, INT) u1;
+
+ u0 = (vector (4, INT)){argc, 1, 2, 10};
+ u1 = (vector (4, INT)){0, 3, 2, (INT)-23};
+ test (INT, 4, u0, u1, ures);
+#undef INT
+
+
+#define SHORT short
+ vector (8, SHORT) s0;
+ vector (8, SHORT) s1;
+ vector (8, short) sres;
+
+ s0 = (vector (8, SHORT)){argc, 1, 2, 10, 6, 87, (SHORT)-5, 2};
+ s1 = (vector (8, SHORT)){0, 3, 2, (SHORT)-23, 12, 10, (SHORT)-2, 0};
+ test (SHORT, 8, s0, s1, sres);
+#undef SHORT
+
+#define SHORT unsigned short
+ vector (8, SHORT) us0;
+ vector (8, SHORT) us1;
+ vector (8, short) usres;
+
+ us0 = (vector (8, SHORT)){argc, 1, 2, 10, 6, 87, (SHORT)-5, 2};
+ us1 = (vector (8, SHORT)){0, 3, 2, (SHORT)-23, 12, 10, (SHORT)-2, 0};
+ test (SHORT, 8, us0, us1, usres);
+#undef SHORT
+
+
+#define CHAR signed char
+ vector (16, CHAR) c0;
+ vector (16, CHAR) c1;
+ vector (16, signed char) cres;
+
+ c0 = (vector (16, CHAR)){argc, 1, 2, 10, 6, 87, (CHAR)-5, 2, \
+ argc, 1, 2, 10, 6, 87, (CHAR)-5, 2 };
+
+ c1 = (vector (16, CHAR)){0, 3, 2, (CHAR)-23, 12, 10, (CHAR)-2, 0, \
+ 0, 3, 2, (CHAR)-23, 12, 10, (CHAR)-2, 0};
+ test (CHAR, 16, c0, c1, cres);
+#undef CHAR
+
+#define CHAR char
+ vector (16, CHAR) uc0;
+ vector (16, CHAR) uc1;
+ vector (16, signed char) ucres;
+
+ uc0 = (vector (16, CHAR)){argc, 1, 2, 10, 6, 87, (CHAR)-5, 2, \
+ argc, 1, 2, 10, 6, 87, (CHAR)-5, 2 };
+
+ uc1 = (vector (16, CHAR)){0, 3, 2, (CHAR)-23, 12, 10, (CHAR)-2, 0, \
+ 0, 3, 2, (CHAR)-23, 12, 10, (CHAR)-2, 0};
+ test (CHAR, 16, uc0, uc1, ucres);
+#undef CHAR
+
+
+ return 0;
+}
+
Index: gcc/c-typeck.c
===================================================================
--- gcc/c-typeck.c (revision 163244)
+++ gcc/c-typeck.c (working copy)
@@ -9606,6 +9606,29 @@ build_binary_op (location_t location, en
case EQ_EXPR:
case NE_EXPR:
+ if (code0 == VECTOR_TYPE && code1 == VECTOR_TYPE)
+ {
+ tree intt;
+ if (TREE_TYPE (type0) != TREE_TYPE (type1))
+ {
+ error_at (location, "comparing vectors with different "
+ "element types");
+ return error_mark_node;
+ }
+
+ if (TYPE_VECTOR_SUBPARTS (type0) != TYPE_VECTOR_SUBPARTS (type1))
+ {
+ error_at (location, "comparing vectors with different "
+ "number of elements");
+ return error_mark_node;
+ }
+
+ /* Always construct signed integer vector type. */
+ intt = c_common_type_for_size (TYPE_PRECISION (TREE_TYPE (type0)),0);
+ result_type = build_vector_type (intt, TYPE_VECTOR_SUBPARTS (type0));
+ converted = 1;
+ break;
+ }
if (FLOAT_TYPE_P (type0) || FLOAT_TYPE_P (type1))
warning_at (location,
OPT_Wfloat_equal,
@@ -9718,6 +9741,29 @@ build_binary_op (location_t location, en
case GE_EXPR:
case LT_EXPR:
case GT_EXPR:
+ if (code0 == VECTOR_TYPE && code1 == VECTOR_TYPE)
+ {
+ tree intt;
+ if (TREE_TYPE (type0) != TREE_TYPE (type1))
+ {
+ error_at (location, "comparing vectors with different "
+ "element types");
+ return error_mark_node;
+ }
+
+ if (TYPE_VECTOR_SUBPARTS (type0) != TYPE_VECTOR_SUBPARTS (type1))
+ {
+ error_at (location, "comparing vectors with different "
+ "number of elements");
+ return error_mark_node;
+ }
+
+ /* Always construct signed integer vector type. */
+ intt = c_common_type_for_size (TYPE_PRECISION (TREE_TYPE (type0)),0);
+ result_type = build_vector_type (intt, TYPE_VECTOR_SUBPARTS (type0));
+ converted = 1;
+ break;
+ }
build_type = integer_type_node;
if ((code0 == INTEGER_TYPE || code0 == REAL_TYPE
|| code0 == FIXED_POINT_TYPE)
@@ -10113,6 +10159,10 @@ c_objc_common_truthvalue_conversion (loc
case FUNCTION_TYPE:
gcc_unreachable ();
+ case VECTOR_TYPE:
+ error_at (location, "used vector type where scalar is required");
+ return error_mark_node;
+
default:
break;
}
Index: gcc/tree-vect-generic.c
===================================================================
--- gcc/tree-vect-generic.c (revision 163244)
+++ gcc/tree-vect-generic.c (working copy)
@@ -30,6 +30,7 @@ along with GCC; see the file COPYING3.
#include "tree-pass.h"
#include "flags.h"
#include "ggc.h"
+#include "target.h"
/* Need to include rtl.h, expr.h, etc. for optabs. */
#include "expr.h"
@@ -125,6 +126,21 @@ do_binop (gimple_stmt_iterator *gsi, tre
return gimplify_build2 (gsi, code, inner_type, a, b);
}
+
+/* Construct expression (A[BITPOS] code B[BITPOS]) ? -1 : 0; */
+static tree
+do_compare (gimple_stmt_iterator *gsi, tree inner_type, tree a, tree b,
+ tree bitpos, tree bitsize, enum tree_code code)
+{
+ tree cond;
+ a = tree_vec_extract (gsi, inner_type, a, bitsize, bitpos);
+ b = tree_vec_extract (gsi, inner_type, b, bitsize, bitpos);
+ cond = gimplify_build2 (gsi, code, inner_type, a, b);
+ return gimplify_build3 (gsi, COND_EXPR, inner_type, cond,
+ build_int_cst (inner_type, -1),
+ build_int_cst (inner_type, 0));
+}
+
/* Expand vector addition to scalars. This does bit twiddling
in order to increase parallelism:
@@ -284,6 +300,21 @@ expand_vector_addition (gimple_stmt_iter
a, b, code);
}
+/* Try a hardware hook for vector comparison or
+ extract comparison piecewise. */
+static tree
+expand_vector_comparison (gimple_stmt_iterator *gsi, tree type, tree op0,
+ tree op1, enum tree_code code)
+{
+ tree t = targetm.vectorize.builtin_vec_compare (gsi, type, op0, op1, code);
+
+ if (t == NULL_TREE)
+ t = expand_vector_piecewise (gsi, do_compare, type,
+ TREE_TYPE (TREE_TYPE (op0)), op0, op1, code);
+ return t;
+
+}
+
static tree
expand_vector_operation (gimple_stmt_iterator *gsi, tree type, tree compute_type,
gimple assign, enum tree_code code)
@@ -326,8 +357,24 @@ expand_vector_operation (gimple_stmt_ite
case BIT_NOT_EXPR:
return expand_vector_parallel (gsi, do_unop, type,
gimple_assign_rhs1 (assign),
- NULL_TREE, code);
-
+ NULL_TREE, code);
+ case EQ_EXPR:
+ case NE_EXPR:
+ case GT_EXPR:
+ case LT_EXPR:
+ case GE_EXPR:
+ case LE_EXPR:
+ case UNEQ_EXPR:
+ case UNGT_EXPR:
+ case UNLT_EXPR:
+ case UNGE_EXPR:
+ case UNLE_EXPR:
+ case LTGT_EXPR:
+ case ORDERED_EXPR:
+ case UNORDERED_EXPR:
+ return expand_vector_comparison (gsi, type,
+ gimple_assign_rhs1 (assign),
+ gimple_assign_rhs2 (assign), code);
default:
break;
}
Index: gcc/Makefile.in
===================================================================
--- gcc/Makefile.in (revision 163244)
+++ gcc/Makefile.in (working copy)
@@ -864,7 +864,7 @@ endif
VEC_H = vec.h statistics.h
EXCEPT_H = except.h $(HASHTAB_H) vecprim.h vecir.h
TOPLEV_H = toplev.h $(INPUT_H) bversion.h $(DIAGNOSTIC_CORE_H)
-TARGET_H = $(TM_H) target.h target.def insn-modes.h
+TGT = $(TM_H) target.h target.def insn-modes.h
MACHMODE_H = machmode.h mode-classes.def insn-modes.h
HOOKS_H = hooks.h $(MACHMODE_H)
HOSTHOOKS_DEF_H = hosthooks-def.h $(HOOKS_H)
@@ -886,8 +886,9 @@ TREE_H = tree.h all-tree.def tree.def c-
REGSET_H = regset.h $(BITMAP_H) hard-reg-set.h
BASIC_BLOCK_H = basic-block.h $(PREDICT_H) $(VEC_H) $(FUNCTION_H) cfghooks.h
GIMPLE_H = gimple.h gimple.def gsstruct.def pointer-set.h $(VEC_H) \
- $(GGC_H) $(BASIC_BLOCK_H) $(TM_H) $(TARGET_H) tree-ssa-operands.h \
+ $(GGC_H) $(BASIC_BLOCK_H) $(TM_H) $(TGT) tree-ssa-operands.h \
tree-ssa-alias.h vecir.h
+TARGET_H = $(TGT) gimple.h
GCOV_IO_H = gcov-io.h gcov-iov.h auto-host.h
COVERAGE_H = coverage.h $(GCOV_IO_H)
DEMANGLE_H = $(srcdir)/../include/demangle.h
@@ -3156,7 +3157,7 @@ tree-vect-generic.o : tree-vect-generic.
$(TM_H) $(TREE_FLOW_H) $(GIMPLE_H) tree-iterator.h $(TREE_PASS_H) \
$(FLAGS_H) $(OPTABS_H) $(MACHMODE_H) $(EXPR_H) \
langhooks.h $(FLAGS_H) $(DIAGNOSTIC_H) gt-tree-vect-generic.h $(GGC_H) \
- coretypes.h insn-codes.h
+ coretypes.h insn-codes.h target.h
df-core.o : df-core.c $(CONFIG_H) $(SYSTEM_H) coretypes.h $(TM_H) $(RTL_H) \
insn-config.h $(RECOG_H) $(FUNCTION_H) $(REGS_H) alloc-pool.h \
hard-reg-set.h $(BASIC_BLOCK_H) $(DF_H) $(BITMAP_H) sbitmap.h $(TIMEVAR_H) \
Index: gcc/tree-cfg.c
===================================================================
--- gcc/tree-cfg.c (revision 163244)
+++ gcc/tree-cfg.c (working copy)
@@ -3144,6 +3144,38 @@ verify_gimple_comparison (tree type, tre
return true;
}
+ if (TREE_CODE (op0_type) == VECTOR_TYPE
+ && TREE_CODE (op1_type) == VECTOR_TYPE
+ && TREE_CODE (type) == VECTOR_TYPE)
+ {
+ if (TYPE_VECTOR_SUBPARTS (op0_type) != TYPE_VECTOR_SUBPARTS (op1_type))
+ {
+ error ("invalid vector comparison, number of elements do not match");
+ debug_generic_expr (op0_type);
+ debug_generic_expr (op1_type);
+ return true;
+ }
+
+ if (TREE_TYPE (op0_type) != TREE_TYPE (op1_type))
+ {
+ error ("invalid vector comparison, vector element type mismatch");
+ debug_generic_expr (op0_type);
+ debug_generic_expr (op1_type);
+ return true;
+ }
+
+ if (TYPE_VECTOR_SUBPARTS (type) != TYPE_VECTOR_SUBPARTS (op0_type)
+ && TYPE_PRECISION (TREE_TYPE (op0_type))
+ != TYPE_PRECISION (TREE_TYPE (type)))
+ {
+ error ("invalid vector comparison resulting type");
+ debug_generic_expr (type);
+ return true;
+ }
+
+ return false;
+ }
+
/* For comparisons we do not have the operations type as the
effective type the comparison is carried out in. Instead
we require that either the first operand is trivially
Index: gcc/config/i386/i386.c
===================================================================
--- gcc/config/i386/i386.c (revision 163244)
+++ gcc/config/i386/i386.c (working copy)
@@ -25,6 +25,7 @@ along with GCC; see the file COPYING3.
#include "tm.h"
#include "rtl.h"
#include "tree.h"
+#include "tree-flow.h"
#include "tm_p.h"
#include "regs.h"
#include "hard-reg-set.h"
@@ -30222,6 +30223,276 @@ ix86_vectorize_builtin_vec_perm (tree ve
return ix86_builtins[(int) fcode];
}
+/* Find target specific sequence for vector comparison of
+ real-type vectors V0 and V1. Returns variable containing
+ result of the comparison or NULL_TREE in other case. */
+static tree
+vector_fp_compare (gimple_stmt_iterator *gsi, tree rettype,
+ enum machine_mode mode, tree v0, tree v1,
+ enum tree_code code)
+{
+ enum ix86_builtins fcode;
+ int arg = -1;
+ tree fdef, frtype, tmp, var, t;
+ gimple new_stmt;
+ bool reverse = false;
+
+#define SWITCH_MODE(mode, fcode, code, value) \
+switch (mode) \
+ { \
+ case V2DFmode: \
+ if (!TARGET_SSE2) return NULL_TREE; \
+ fcode = IX86_BUILTIN_CMP ## code ## PD; \
+ break; \
+ case V4DFmode: \
+ if (!TARGET_AVX) return NULL_TREE; \
+ fcode = IX86_BUILTIN_CMPPD256; \
+ arg = value; \
+ break; \
+ case V4SFmode: \
+ if (!TARGET_SSE) return NULL_TREE; \
+ fcode = IX86_BUILTIN_CMP ## code ## SS; \
+ break; \
+ case V8SFmode: \
+ if (!TARGET_AVX) return NULL_TREE; \
+ fcode = IX86_BUILTIN_CMPPS256; \
+ arg = value; \
+ break; \
+ default: \
+ return NULL_TREE; \
+ /* FIXME: Similar instructions for MMX. */ \
+ }
+
+ switch (code)
+ {
+ case EQ_EXPR:
+ SWITCH_MODE (mode, fcode, EQ, 0);
+ break;
+
+ case NE_EXPR:
+ SWITCH_MODE (mode, fcode, NEQ, 4);
+ break;
+
+ case GT_EXPR:
+ SWITCH_MODE (mode, fcode, LT, 1);
+ reverse = true;
+ break;
+
+ case LT_EXPR:
+ SWITCH_MODE (mode, fcode, LT, 1);
+ break;
+
+ case LE_EXPR:
+ SWITCH_MODE (mode, fcode, LE, 2);
+ break;
+
+ case GE_EXPR:
+ SWITCH_MODE (mode, fcode, LE, 2);
+ reverse = true;
+ break;
+
+ default:
+ return NULL_TREE;
+ }
+#undef SWITCH_MODE
+
+ fdef = ix86_builtins[(int)fcode];
+ frtype = TREE_TYPE (TREE_TYPE (fdef));
+
+ tmp = create_tmp_var (frtype, "tmp");
+ var = create_tmp_var (rettype, "tmp");
+
+ if (arg == -1)
+ if (reverse)
+ new_stmt = gimple_build_call (fdef, 2, v1, v0);
+ else
+ new_stmt = gimple_build_call (fdef, 2, v0, v1);
+ else
+ if (reverse)
+ new_stmt = gimple_build_call (fdef, 3, v0, v1,
+ build_int_cst (char_type_node, arg));
+ else
+ new_stmt = gimple_build_call (fdef, 3, v1, v0,
+ build_int_cst (char_type_node, arg));
+
+ gimple_call_set_lhs (new_stmt, tmp);
+ gsi_insert_before (gsi, new_stmt, GSI_SAME_STMT);
+ t = gimplify_build1 (gsi, VIEW_CONVERT_EXPR, rettype, tmp);
+ new_stmt = gimple_build_assign (var, t);
+ gsi_insert_before (gsi, new_stmt, GSI_SAME_STMT);
+
+ return var;
+}
+
+/* Find target specific sequence for vector comparison of
+ integer-type vectors V0 and V1. Returns variable containing
+ result of the comparison or NULL_TREE in other case. */
+static tree
+vector_int_compare (gimple_stmt_iterator *gsi, tree rettype,
+ enum machine_mode mode, tree v0, tree v1,
+ enum tree_code code)
+{
+ enum ix86_builtins feq, fgt;
+ tree var, t, tmp, tmp1, tmp2, defeq, defgt, gtrtype, eqrtype;
+ gimple new_stmt;
+
+ switch (mode)
+ {
+ /* SSE integer-type vectors. */
+ case V2DImode:
+ if (!TARGET_SSE4_2) return NULL_TREE;
+ feq = IX86_BUILTIN_PCMPEQQ;
+ fgt = IX86_BUILTIN_PCMPGTQ;
+ break;
+
+ case V4SImode:
+ if (!TARGET_SSE2) return NULL_TREE;
+ feq = IX86_BUILTIN_PCMPEQD128;
+ fgt = IX86_BUILTIN_PCMPGTD128;
+ break;
+
+ case V8HImode:
+ if (!TARGET_SSE2) return NULL_TREE;
+ feq = IX86_BUILTIN_PCMPEQW128;
+ fgt = IX86_BUILTIN_PCMPGTW128;
+ break;
+
+ case V16QImode:
+ if (!TARGET_SSE2) return NULL_TREE;
+ feq = IX86_BUILTIN_PCMPEQB128;
+ fgt = IX86_BUILTIN_PCMPGTB128;
+ break;
+
+ /* MMX integer-type vectors. */
+ case V2SImode:
+ if (!TARGET_MMX) return NULL_TREE;
+ feq = IX86_BUILTIN_PCMPEQD;
+ fgt = IX86_BUILTIN_PCMPGTD;
+ break;
+
+ case V4HImode:
+ if (!TARGET_MMX) return NULL_TREE;
+ feq = IX86_BUILTIN_PCMPEQW;
+ fgt = IX86_BUILTIN_PCMPGTW;
+ break;
+
+ case V8QImode:
+ if (!TARGET_MMX) return NULL_TREE;
+ feq = IX86_BUILTIN_PCMPEQB;
+ fgt = IX86_BUILTIN_PCMPGTB;
+ break;
+
+ /* FIXME: Similar instructions for AVX. */
+ default:
+ return NULL_TREE;
+ }
+
+
+ var = create_tmp_var (rettype, "ret");
+ defeq = ix86_builtins[(int)feq];
+ defgt = ix86_builtins[(int)fgt];
+ eqrtype = TREE_TYPE (TREE_TYPE (defeq));
+ gtrtype = TREE_TYPE (TREE_TYPE (defgt));
+
+#define EQGT_CALL(gsi, stmt, var, op0, op1, gteq) \
+do { \
+ var = create_tmp_var (gteq ## rtype, "tmp"); \
+ stmt = gimple_build_call (def ## gteq, 2, op0, op1); \
+ gimple_call_set_lhs (stmt, var); \
+ gsi_insert_before (gsi, stmt, GSI_SAME_STMT); \
+} while (0)
+
+ switch (code)
+ {
+ case EQ_EXPR:
+ EQGT_CALL (gsi, new_stmt, tmp, v0, v1, eq);
+ break;
+
+ case NE_EXPR:
+ tmp = create_tmp_var (eqrtype, "tmp");
+
+ EQGT_CALL (gsi, new_stmt, tmp1, v0, v1, eq);
+ EQGT_CALL (gsi, new_stmt, tmp2, v0, v0, eq);
+
+ /* t = tmp1 ^ {-1, -1,...} */
+ t = gimplify_build2 (gsi, BIT_XOR_EXPR, eqrtype, tmp1, tmp2);
+ new_stmt = gimple_build_assign (tmp, t);
+ gsi_insert_before (gsi, new_stmt, GSI_SAME_STMT);
+ break;
+
+ case GT_EXPR:
+ EQGT_CALL (gsi, new_stmt, tmp, v0, v1, gt);
+ break;
+
+ case LT_EXPR:
+ EQGT_CALL (gsi, new_stmt, tmp, v1, v0, gt);
+ break;
+
+ case GE_EXPR:
+ if (eqrtype != gtrtype)
+ return NULL_TREE;
+ tmp = create_tmp_var (eqrtype, "tmp");
+ EQGT_CALL (gsi, new_stmt, tmp1, v0, v1, gt);
+ EQGT_CALL (gsi, new_stmt, tmp2, v0, v1, eq);
+ t = gimplify_build2 (gsi, BIT_IOR_EXPR, eqrtype, tmp1, tmp2);
+ new_stmt = gimple_build_assign (tmp, t);
+ gsi_insert_before (gsi, new_stmt, GSI_SAME_STMT);
+ break;
+
+ case LE_EXPR:
+ if (eqrtype != gtrtype)
+ return NULL_TREE;
+ tmp = create_tmp_var (eqrtype, "tmp");
+ EQGT_CALL (gsi, new_stmt, tmp1, v1, v0, gt);
+ EQGT_CALL (gsi, new_stmt, tmp2, v0, v1, eq);
+ t = gimplify_build2 (gsi, BIT_IOR_EXPR, eqrtype, tmp1, tmp2);
+ new_stmt = gimple_build_assign (tmp, t);
+ gsi_insert_before (gsi, new_stmt, GSI_SAME_STMT);
+ break;
+
+ default:
+ return NULL_TREE;
+ }
+#undef EQGT_CALL
+
+ t = gimplify_build1 (gsi, VIEW_CONVERT_EXPR, rettype, tmp);
+ new_stmt = gimple_build_assign (var, t);
+ gsi_insert_before (gsi, new_stmt, GSI_SAME_STMT);
+ return var;
+}
+
+/* Lower a comparison of two vectors V0 and V1, returning a
+ variable with the result of comparison. Returns NULL_TREE
+ when it is impossible to find a target specific sequence. */
+static tree
+ix86_vectorize_builtin_vec_compare (gimple_stmt_iterator *gsi, tree rettype,
+ tree v0, tree v1, enum tree_code code)
+{
+ tree type;
+
+ /* Make sure we are comparing the same types. */
+ if (TREE_TYPE (v0) != TREE_TYPE (v1)
+ || TREE_TYPE (TREE_TYPE (v0)) != TREE_TYPE (TREE_TYPE (v1)))
+ return NULL_TREE;
+
+ type = TREE_TYPE (v0);
+
+ /* Cannot compare packed unsigned integers
+ unless it is EQ or NEQ operations. */
+ if (TREE_CODE (TREE_TYPE (type)) == INTEGER_TYPE
+ && TYPE_UNSIGNED (TREE_TYPE (type)))
+ if (code != EQ_EXPR && code != NE_EXPR)
+ return NULL_TREE;
+
+
+ if (TREE_CODE (TREE_TYPE (type)) == REAL_TYPE)
+ return vector_fp_compare (gsi, rettype, TYPE_MODE (type), v0, v1, code);
+ else if (TREE_CODE (TREE_TYPE (type)) == INTEGER_TYPE)
+ return vector_int_compare (gsi, rettype, TYPE_MODE (type), v0, v1, code);
+ else
+ return NULL_TREE;
+}
+
/* Return a vector mode with twice as many elements as VMODE. */
/* ??? Consider moving this to a table generated by genmodes.c. */
@@ -31715,6 +31986,11 @@ ix86_enum_va_list (int idx, const char *
#define TARGET_VECTORIZE_BUILTIN_VEC_PERM_OK \
ix86_vectorize_builtin_vec_perm_ok
+#undef TARGET_VECTORIZE_BUILTIN_VEC_COMPARE
+#define TARGET_VECTORIZE_BUILTIN_VEC_COMPARE \
+ ix86_vectorize_builtin_vec_compare
+
+
#undef TARGET_SET_CURRENT_FUNCTION
#define TARGET_SET_CURRENT_FUNCTION ix86_set_current_function