+2019-11-08 Kewen Lin <linkw@gcc.gnu.org>
+
+ PR target/92132
+ * config/rs6000/predicates.md
+ (signed_or_equality_comparison_operator): New predicate.
+ (unsigned_or_equality_comparison_operator): Likewise.
+ * config/rs6000/rs6000.md (one_cmpl<mode>2): Remove expand.
+ (one_cmpl<mode>3_internal): Rename to one_cmpl<mode>2.
+ * config/rs6000/vector.md
+ (vcond_mask_<mode><mode> for VEC_I and VEC_I): New expand.
+ (vec_cmp<mode><mode> for VEC_I and VEC_I): Likewise.
+ (vec_cmpu<mode><mode> for VEC_I and VEC_I): Likewise.
+ (vcond_mask_<mode><VEC_int> for VEC_F): New expand for float
+ vector modes and same-size integer vector modes.
+ (vec_cmp<mode><VEC_int> for VEC_F): Likewise.
+ (vector_lt<mode> for VEC_F): New expand.
+ (vector_le<mode> for VEC_F): Likewise.
+ (vector_ne<mode> for VEC_F): Likewise.
+ (vector_unge<mode> for VEC_F): Likewise.
+ (vector_ungt<mode> for VEC_F): Likewise.
+ (vector_unle<mode> for VEC_F): Likewise.
+ (vector_unlt<mode> for VEC_F): Likewise.
+ (vector_uneq<mode>): Expose name.
+ (vector_ltgt<mode>): Likewise.
+ (vector_unordered<mode>): Likewise.
+ (vector_ordered<mode>): Likewise.
+
2019-11-08 Hongtao Liu <Hongtao.liu@intel.com>
PR target/92295
(define_predicate "signed_comparison_operator"
(match_code "lt,gt,le,ge"))
+;; Return 1 if OP is a signed comparison or an equality operator.
+(define_predicate "signed_or_equality_comparison_operator"
+ (ior (match_operand 0 "equality_operator")
+ (match_operand 0 "signed_comparison_operator")))
+
+;; Return 1 if OP is an unsigned comparison or an equality operator.
+(define_predicate "unsigned_or_equality_comparison_operator"
+ (ior (match_operand 0 "equality_operator")
+ (match_operand 0 "unsigned_comparison_operator")))
+
;; Return 1 if OP is a comparison operation that is valid for an SCC insn --
;; it must be a positive comparison.
(define_predicate "scc_comparison_operator"
""
"")
-(define_expand "one_cmpl<mode>2"
- [(set (match_operand:BOOL_128 0 "vlogical_operand")
- (not:BOOL_128 (match_operand:BOOL_128 1 "vlogical_operand")))]
- ""
- "")
-
(define_expand "nor<mode>3"
[(set (match_operand:BOOL_128 0 "vlogical_operand")
(and:BOOL_128
(const_string "16")))])
;; 128-bit one's complement
-(define_insn_and_split "*one_cmpl<mode>3_internal"
+(define_insn_and_split "one_cmpl<mode>2"
[(set (match_operand:BOOL_128 0 "vlogical_operand" "=<BOOL_REGS_OUTPUT>")
(not:BOOL_128
(match_operand:BOOL_128 1 "vlogical_operand" "<BOOL_REGS_UNARY>")))]
FAIL;
})
+;; To support vector condition vectorization, define vcond_mask and vec_cmp.
+
+;; Same mode for condition true/false values and predicate operand.
+(define_expand "vcond_mask_<mode><mode>"
+ [(match_operand:VEC_I 0 "vint_operand")
+ (match_operand:VEC_I 1 "vint_operand")
+ (match_operand:VEC_I 2 "vint_operand")
+ (match_operand:VEC_I 3 "vint_operand")]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ emit_insn (gen_vector_select_<mode> (operands[0], operands[2], operands[1],
+ operands[3]));
+ DONE;
+})
+
+;; Condition true/false values are float but predicate operand is of
+;; type integer vector with same element size.
+(define_expand "vcond_mask_<mode><VEC_int>"
+ [(match_operand:VEC_F 0 "vfloat_operand")
+ (match_operand:VEC_F 1 "vfloat_operand")
+ (match_operand:VEC_F 2 "vfloat_operand")
+ (match_operand:<VEC_INT> 3 "vint_operand")]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ emit_insn (gen_vector_select_<mode> (operands[0], operands[2], operands[1],
+ gen_lowpart (<MODE>mode, operands[3])));
+ DONE;
+})
+
+;; For signed integer vectors comparison.
+(define_expand "vec_cmp<mode><mode>"
+ [(set (match_operand:VEC_I 0 "vint_operand")
+ (match_operator 1 "signed_or_equality_comparison_operator"
+ [(match_operand:VEC_I 2 "vint_operand")
+ (match_operand:VEC_I 3 "vint_operand")]))]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ enum rtx_code code = GET_CODE (operands[1]);
+ rtx tmp = gen_reg_rtx (<MODE>mode);
+ switch (code)
+ {
+ case NE:
+ emit_insn (gen_vector_eq<mode> (operands[0], operands[2], operands[3]));
+ emit_insn (gen_one_cmpl<mode>2 (operands[0], operands[0]));
+ break;
+ case EQ:
+ emit_insn (gen_vector_eq<mode> (operands[0], operands[2], operands[3]));
+ break;
+ case GE:
+ emit_insn (gen_vector_nlt<mode> (operands[0],operands[2], operands[3],
+ tmp));
+ break;
+ case GT:
+ emit_insn (gen_vector_gt<mode> (operands[0], operands[2], operands[3]));
+ break;
+ case LE:
+ emit_insn (gen_vector_ngt<mode> (operands[0], operands[2], operands[3],
+ tmp));
+ break;
+ case LT:
+ emit_insn (gen_vector_gt<mode> (operands[0], operands[3], operands[2]));
+ break;
+ default:
+ gcc_unreachable ();
+ break;
+ }
+ DONE;
+})
+
+;; For unsigned integer vectors comparison.
+(define_expand "vec_cmpu<mode><mode>"
+ [(set (match_operand:VEC_I 0 "vint_operand")
+ (match_operator 1 "unsigned_or_equality_comparison_operator"
+ [(match_operand:VEC_I 2 "vint_operand")
+ (match_operand:VEC_I 3 "vint_operand")]))]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ enum rtx_code code = GET_CODE (operands[1]);
+ rtx tmp = gen_reg_rtx (<MODE>mode);
+ switch (code)
+ {
+ case NE:
+ emit_insn (gen_vector_eq<mode> (operands[0], operands[2], operands[3]));
+ emit_insn (gen_one_cmpl<mode>2 (operands[0], operands[0]));
+ break;
+ case EQ:
+ emit_insn (gen_vector_eq<mode> (operands[0], operands[2], operands[3]));
+ break;
+ case GEU:
+ emit_insn (gen_vector_nltu<mode> (operands[0], operands[2], operands[3],
+ tmp));
+ break;
+ case GTU:
+ emit_insn (gen_vector_gtu<mode> (operands[0], operands[2], operands[3]));
+ break;
+ case LEU:
+ emit_insn (gen_vector_ngtu<mode> (operands[0], operands[2], operands[3],
+ tmp));
+ break;
+ case LTU:
+ emit_insn (gen_vector_gtu<mode> (operands[0], operands[3], operands[2]));
+ break;
+ default:
+ gcc_unreachable ();
+ break;
+ }
+ DONE;
+})
+
+;; For float point vectors comparison.
+(define_expand "vec_cmp<mode><VEC_int>"
+ [(set (match_operand:<VEC_INT> 0 "vint_operand")
+ (match_operator 1 "comparison_operator"
+ [(match_operand:VEC_F 2 "vfloat_operand")
+ (match_operand:VEC_F 3 "vfloat_operand")]))]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ enum rtx_code code = GET_CODE (operands[1]);
+ rtx res = gen_reg_rtx (<MODE>mode);
+ switch (code)
+ {
+ case NE:
+ emit_insn (gen_vector_ne<mode> (res, operands[2], operands[3]));
+ break;
+ case EQ:
+ emit_insn (gen_vector_eq<mode> (res, operands[2], operands[3]));
+ break;
+ case GE:
+ emit_insn (gen_vector_ge<mode> (res, operands[2], operands[3]));
+ break;
+ case GT:
+ emit_insn (gen_vector_gt<mode> (res, operands[2], operands[3]));
+ break;
+ case LE:
+ emit_insn (gen_vector_le<mode> (res, operands[2], operands[3]));
+ break;
+ case LT:
+ emit_insn (gen_vector_lt<mode> (res, operands[2], operands[3]));
+ break;
+ case LTGT:
+ emit_insn (gen_vector_ltgt<mode> (res, operands[2], operands[3]));
+ break;
+ case UNORDERED:
+ emit_insn (gen_vector_unordered<mode> (res, operands[2], operands[3]));
+ break;
+ case ORDERED:
+ emit_insn (gen_vector_ordered<mode> (res, operands[2], operands[3]));
+ break;
+ case UNEQ:
+ emit_insn (gen_vector_uneq<mode> (res, operands[2], operands[3]));
+ break;
+ case UNGE:
+ emit_insn (gen_vector_unge<mode> (res, operands[2], operands[3]));
+ break;
+ case UNGT:
+ emit_insn (gen_vector_ungt<mode> (res, operands[2], operands[3]));
+ break;
+ case UNLE:
+ emit_insn (gen_vector_unle<mode> (res, operands[2], operands[3]));
+ break;
+ case UNLT:
+ emit_insn (gen_vector_unlt<mode> (res, operands[2], operands[3]));
+ break;
+
+ default:
+ gcc_unreachable ();
+ }
+
+ emit_insn (gen_move_insn (operands[0], gen_lowpart (<VEC_INT>mode, res)));
+ DONE;
+})
+
+; lt(a,b) = gt(b,a)
+(define_expand "vector_lt<mode>"
+ [(set (match_operand:VEC_F 0 "vfloat_operand")
+ (lt:VEC_F (match_operand:VEC_F 1 "vfloat_operand")
+ (match_operand:VEC_F 2 "vfloat_operand")))]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ emit_insn (gen_vector_gt<mode> (operands[0], operands[2], operands[1]));
+ DONE;
+})
+
+; le(a,b) = ge(b,a)
+(define_expand "vector_le<mode>"
+ [(set (match_operand:VEC_F 0 "vfloat_operand")
+ (le:VEC_F (match_operand:VEC_F 1 "vfloat_operand")
+ (match_operand:VEC_F 2 "vfloat_operand")))]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ emit_insn (gen_vector_ge<mode> (operands[0], operands[2], operands[1]));
+ DONE;
+})
+
+; ne(a,b) = ~eq(a,b)
+(define_expand "vector_ne<mode>"
+ [(set (match_operand:VEC_F 0 "vfloat_operand")
+ (ne:VEC_F (match_operand:VEC_F 1 "vfloat_operand")
+ (match_operand:VEC_F 2 "vfloat_operand")))]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ emit_insn (gen_vector_eq<mode> (operands[0], operands[1], operands[2]));
+ emit_insn (gen_one_cmpl<mode>2 (operands[0], operands[0]));
+ DONE;
+})
+
+; unge(a,b) = ~gt(b,a)
+(define_expand "vector_unge<mode>"
+ [(set (match_operand:VEC_F 0 "vfloat_operand")
+ (unge:VEC_F (match_operand:VEC_F 1 "vfloat_operand")
+ (match_operand:VEC_F 2 "vfloat_operand")))]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ emit_insn (gen_vector_gt<mode> (operands[0], operands[2], operands[1]));
+ emit_insn (gen_one_cmpl<mode>2 (operands[0], operands[0]));
+ DONE;
+})
+
+; ungt(a,b) = ~ge(b,a)
+(define_expand "vector_ungt<mode>"
+ [(set (match_operand:VEC_F 0 "vfloat_operand")
+ (ungt:VEC_F (match_operand:VEC_F 1 "vfloat_operand")
+ (match_operand:VEC_F 2 "vfloat_operand")))]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ emit_insn (gen_vector_ge<mode> (operands[0], operands[2], operands[1]));
+ emit_insn (gen_one_cmpl<mode>2 (operands[0], operands[0]));
+ DONE;
+})
+
+; unle(a,b) = ~gt(a,b)
+(define_expand "vector_unle<mode>"
+ [(set (match_operand:VEC_F 0 "vfloat_operand")
+ (unle:VEC_F (match_operand:VEC_F 1 "vfloat_operand")
+ (match_operand:VEC_F 2 "vfloat_operand")))]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ emit_insn (gen_vector_gt<mode> (operands[0], operands[1], operands[2]));
+ emit_insn (gen_one_cmpl<mode>2 (operands[0], operands[0]));
+ DONE;
+})
+
+; unlt(a,b) = ~ge(a,b)
+(define_expand "vector_unlt<mode>"
+ [(set (match_operand:VEC_F 0 "vfloat_operand")
+ (unlt:VEC_F (match_operand:VEC_F 1 "vfloat_operand")
+ (match_operand:VEC_F 2 "vfloat_operand")))]
+ "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+ emit_insn (gen_vector_ge<mode> (operands[0], operands[1], operands[2]));
+ emit_insn (gen_one_cmpl<mode>2 (operands[0], operands[0]));
+ DONE;
+})
+
(define_expand "vector_eq<mode>"
[(set (match_operand:VEC_C 0 "vlogical_operand")
(eq:VEC_C (match_operand:VEC_C 1 "vlogical_operand")
operands[3] = gen_reg_rtx_and_attrs (operands[0]);
})
-(define_insn_and_split "*vector_uneq<mode>"
+(define_insn_and_split "vector_uneq<mode>"
[(set (match_operand:VEC_F 0 "vfloat_operand")
(uneq:VEC_F (match_operand:VEC_F 1 "vfloat_operand")
(match_operand:VEC_F 2 "vfloat_operand")))]
operands[4] = gen_reg_rtx (<MODE>mode);
})
-(define_insn_and_split "*vector_ltgt<mode>"
+(define_insn_and_split "vector_ltgt<mode>"
[(set (match_operand:VEC_F 0 "vfloat_operand")
(ltgt:VEC_F (match_operand:VEC_F 1 "vfloat_operand")
(match_operand:VEC_F 2 "vfloat_operand")))]
operands[4] = gen_reg_rtx (<MODE>mode);
})
-(define_insn_and_split "*vector_ordered<mode>"
+(define_insn_and_split "vector_ordered<mode>"
[(set (match_operand:VEC_F 0 "vfloat_operand")
(ordered:VEC_F (match_operand:VEC_F 1 "vfloat_operand")
(match_operand:VEC_F 2 "vfloat_operand")))]
operands[4] = gen_reg_rtx (<MODE>mode);
})
-(define_insn_and_split "*vector_unordered<mode>"
+(define_insn_and_split "vector_unordered<mode>"
[(set (match_operand:VEC_F 0 "vfloat_operand")
(unordered:VEC_F (match_operand:VEC_F 1 "vfloat_operand")
(match_operand:VEC_F 2 "vfloat_operand")))]
+2019-11-08 Kewen Lin <linkw@gcc.gnu.org>
+
+ PR target/92132
+ * gcc.target/powerpc/pr92132-fp-1.c: New test.
+ * gcc.target/powerpc/pr92132-fp-2.c: New test.
+ * gcc.target/powerpc/pr92132-int-1.c: New test.
+ * gcc.target/powerpc/pr92132-int-2.c: New test.
+
2019-11-08 Hongtao Liu <hongtao.liu@intel.com>
* gcc.target/i386/pr92295.c: New test.
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target vsx_hw } */
+/* { dg-options "-O2 -ftree-vectorize -mvsx -fno-vect-cost-model -fdump-tree-vect-details" } */
+
+/* To test condition reduction vectorization, where comparison operands are of
+ double type and condition true/false values are integer type. Cover all
+ float point comparison codes. */
+
+#include <math.h>
+
+extern void
+abort (void) __attribute__ ((noreturn));
+
+#define N 27
+#define FP_TYPE double
+
+#define LTGT(a, b) (__builtin_islessgreater ((a), (b)))
+#define UNORD(a, b) (__builtin_isunordered ((a), (b)))
+#define ORD(a, b) (!__builtin_isunordered ((a), (b)))
+#define UNEQ(a, b) (!__builtin_islessgreater ((a), (b)))
+#define UNGT(a, b) (!__builtin_islessequal ((a), (b)))
+#define UNGE(a, b) (!__builtin_isless ((a), (b)))
+#define UNLT(a, b) (!__builtin_isgreaterequal ((a), (b)))
+#define UNLE(a, b) (!__builtin_isgreater ((a), (b)))
+
+__attribute__ ((noinline)) int
+test_eq (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] == min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ne (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] != min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_gt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] > min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ge (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] >= min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_lt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] < min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_le (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] <= min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ltgt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (LTGT (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ord (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (ORD (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_unord (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNORD (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_uneq (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNEQ (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ungt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNGT (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_unge (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNGE (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_unlt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNLT (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_unle (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNLE (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+int
+main (void)
+{
+ int ret = 0;
+
+ FP_TYPE a1[N] = {11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 1, 2, 3, 4,
+ 5, 6, 7, 8, 9, 10, 21, 22, 23, 24, 25, 26, 27};
+
+ FP_TYPE a2[N] = {11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 1, 2, 3, 4,
+ 5, 6, 7, 8, 9, 10, 21, 22, 23, NAN, 25, 26, 27};
+
+ FP_TYPE a3[N] = {21, 22, 23, 24, 25, 26, 27, 28, 29, 10, 11, 12, 13, 14,
+ 15, 16, 17, 18, 19, 20, 1, 2, 3, 4, 5, 6, 7};
+
+ FP_TYPE a4[N] = {21, 22, 23, 24, 25, 26, 27, 28, 29, 10, 11, 12, 13, 14,
+ 15, 16, 17, 18, 19, 20, 1, 2, 3, 4, NAN, 6, 7};
+
+ FP_TYPE a5[N] = {21, 22, 23, 24, 25, 26, 27, 28, 29, 10, 11, 12, 13, 14,
+ 15, 16, 17, 18, 19, 20, 1, 2, 3, 4, NAN, 10, 10};
+
+ ret = test_eq (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ne (a1, 10);
+ if (ret != 26)
+ abort ();
+
+ ret = test_gt (a3, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ge (a3, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_lt (a1, 10);
+ if (ret != 18)
+ abort ();
+
+ ret = test_le (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ltgt (a3, 10);
+ if (ret != 26)
+ abort ();
+
+ ret = test_ltgt (a5, 10);
+ if (ret != 23)
+ abort ();
+
+ ret = test_unord (a5, 10);
+ if (ret != 24)
+ abort ();
+
+ ret = test_ord (a5, 10);
+ if (ret != 26)
+ abort ();
+
+ ret = test_uneq (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_uneq (a4, 10);
+ if (ret != 24)
+ abort ();
+
+ ret = test_ungt (a3, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ungt (a4, 10);
+ if (ret != 24)
+ abort ();
+
+ ret = test_unge (a3, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ungt (a4, 10);
+ if (ret != 24)
+ abort ();
+
+ ret = test_unlt (a1, 10);
+ if (ret != 18)
+ abort ();
+
+ ret = test_unlt (a2, 10);
+ if (ret != 23)
+ abort ();
+
+ ret = test_unle (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_unle (a2, 10);
+ if (ret != 23)
+ abort ();
+
+ return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 14 "vect" } } */
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target vmx_hw } */
+/* { dg-options "-O2 -ftree-vectorize -maltivec -fno-vect-cost-model -fdump-tree-vect-details" } */
+
+/* To test condition reduction vectorization, where comparison operands are of
+ float type and condition true/false values are integer type. Cover all
+ float point comparison codes. */
+
+#include <math.h>
+
+extern void
+abort (void) __attribute__ ((noreturn));
+
+#define N 27
+#define FP_TYPE float
+
+#define LTGT(a, b) (__builtin_islessgreater ((a), (b)))
+#define UNORD(a, b) (__builtin_isunordered ((a), (b)))
+#define ORD(a, b) (!__builtin_isunordered ((a), (b)))
+#define UNEQ(a, b) (!__builtin_islessgreater ((a), (b)))
+#define UNGT(a, b) (!__builtin_islessequal ((a), (b)))
+#define UNGE(a, b) (!__builtin_isless ((a), (b)))
+#define UNLT(a, b) (!__builtin_isgreaterequal ((a), (b)))
+#define UNLE(a, b) (!__builtin_isgreater ((a), (b)))
+
+__attribute__ ((noinline)) int
+test_eq (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] == min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ne (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] != min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_gt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] > min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ge (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] >= min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_lt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] < min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_le (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] <= min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ltgt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (LTGT (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ord (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (ORD (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_unord (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNORD (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_uneq (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNEQ (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ungt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNGT (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_unge (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNGE (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_unlt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNLT (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_unle (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (UNLE (a[i], min_v))
+ last = i;
+
+ return last;
+}
+
+int
+main (void)
+{
+ int ret = 0;
+
+ FP_TYPE a1[N] = {11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 1, 2, 3, 4,
+ 5, 6, 7, 8, 9, 10, 21, 22, 23, 24, 25, 26, 27};
+
+ FP_TYPE a2[N] = {11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 1, 2, 3, 4,
+ 5, 6, 7, 8, 9, 10, 21, 22, 23, NAN, 25, 26, 27};
+
+ FP_TYPE a3[N] = {21, 22, 23, 24, 25, 26, 27, 28, 29, 10, 11, 12, 13, 14,
+ 15, 16, 17, 18, 19, 20, 1, 2, 3, 4, 5, 6, 7};
+
+ FP_TYPE a4[N] = {21, 22, 23, 24, 25, 26, 27, 28, 29, 10, 11, 12, 13, 14,
+ 15, 16, 17, 18, 19, 20, 1, 2, 3, 4, NAN, 6, 7};
+
+ FP_TYPE a5[N] = {21, 22, 23, 24, 25, 26, 27, 28, 29, 10, 11, 12, 13, 14,
+ 15, 16, 17, 18, 19, 20, 1, 2, 3, 4, NAN, 10, 10};
+
+ ret = test_eq (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ne (a1, 10);
+ if (ret != 26)
+ abort ();
+
+ ret = test_gt (a3, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ge (a3, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_lt (a1, 10);
+ if (ret != 18)
+ abort ();
+
+ ret = test_le (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ltgt (a3, 10);
+ if (ret != 26)
+ abort ();
+
+ ret = test_ltgt (a5, 10);
+ if (ret != 23)
+ abort ();
+
+ ret = test_unord (a5, 10);
+ if (ret != 24)
+ abort ();
+
+ ret = test_ord (a5, 10);
+ if (ret != 26)
+ abort ();
+
+ ret = test_uneq (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_uneq (a4, 10);
+ if (ret != 24)
+ abort ();
+
+ ret = test_ungt (a3, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ungt (a4, 10);
+ if (ret != 24)
+ abort ();
+
+ ret = test_unge (a3, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ungt (a4, 10);
+ if (ret != 24)
+ abort ();
+
+ ret = test_unlt (a1, 10);
+ if (ret != 18)
+ abort ();
+
+ ret = test_unlt (a2, 10);
+ if (ret != 23)
+ abort ();
+
+ ret = test_unle (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_unle (a2, 10);
+ if (ret != 23)
+ abort ();
+
+ return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 14 "vect" } } */
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target p8vector_hw } */
+/* { dg-options "-O2 -ftree-vectorize -mdejagnu-cpu=power8 -fno-vect-cost-model -fdump-tree-vect-details" } */
+
+/* To test condition reduction vectorization, where comparison operands are of
+ signed long long type and condition true/false values are integer type. */
+
+#include <math.h>
+
+extern void
+abort (void) __attribute__ ((noreturn));
+
+#define N 27
+#define FP_TYPE signed long long
+
+__attribute__ ((noinline)) int
+test_eq (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] == min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ne (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] != min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_gt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] > min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ge (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] >= min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_lt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] < min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_le (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] <= min_v)
+ last = i;
+
+ return last;
+}
+
+int
+main (void)
+{
+ int ret = 0;
+
+ FP_TYPE a1[N] = {11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 1, 2, 3, 4,
+ 5, 6, 7, 8, 9, 10, 21, 22, 23, 24, 25, 26, 27};
+
+ FP_TYPE a2[N] = {21, 22, 23, 24, 25, 26, 27, 28, 29, 10, 11, 12, 13, 14,
+ 15, 16, 17, 18, 19, 20, 1, 2, 3, 4, 5, 6, 7};
+
+ ret = test_eq (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ne (a1, 10);
+ if (ret != 26)
+ abort ();
+
+ ret = test_gt (a2, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ge (a2, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_lt (a1, 10);
+ if (ret != 18)
+ abort ();
+
+ ret = test_le (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 6 "vect" } } */
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target p8vector_hw } */
+/* { dg-options "-O2 -ftree-vectorize -mdejagnu-cpu=power8 -fno-vect-cost-model -fdump-tree-vect-details" } */
+
+/* To test condition reduction vectorization, where comparison operands are of
+ unsigned long long type and condition true/false values are integer type. */
+
+#include <math.h>
+
+extern void
+abort (void) __attribute__ ((noreturn));
+
+#define N 27
+#define FP_TYPE unsigned long long
+
+__attribute__ ((noinline)) int
+test_eq (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] == min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ne (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] != min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_gt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] > min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_ge (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] >= min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_lt (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] < min_v)
+ last = i;
+
+ return last;
+}
+
+__attribute__ ((noinline)) int
+test_le (FP_TYPE *a, FP_TYPE min_v)
+{
+ int last = 0;
+
+ for (int i = 0; i < N; i++)
+ if (a[i] <= min_v)
+ last = i;
+
+ return last;
+}
+
+int
+main (void)
+{
+ int ret = 0;
+
+ FP_TYPE a1[N] = {11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 1, 2, 3, 4,
+ 5, 6, 7, 8, 9, 10, 21, 22, 23, 24, 25, 26, 27};
+
+ FP_TYPE a2[N] = {21, 22, 23, 24, 25, 26, 27, 28, 29, 10, 11, 12, 13, 14,
+ 15, 16, 17, 18, 19, 20, 1, 2, 3, 4, 5, 6, 7};
+
+ ret = test_eq (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ne (a1, 10);
+ if (ret != 26)
+ abort ();
+
+ ret = test_gt (a2, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_ge (a2, 10);
+ if (ret != 19)
+ abort ();
+
+ ret = test_lt (a1, 10);
+ if (ret != 18)
+ abort ();
+
+ ret = test_le (a1, 10);
+ if (ret != 19)
+ abort ();
+
+ return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 6 "vect" } } */
projects / gcc.git / commitdiff