#define vec_xlx __builtin_vec_vextulx
#define vec_xrx __builtin_vec_vexturx
+
#endif
+/* BCD builtins, map ABI builtin name to existing builtin name. */
+#define __builtin_bcdadd __builtin_vec_bcdadd
+#define __builtin_bcdadd_lt __builtin_vec_bcdadd_lt
+#define __builtin_bcdadd_eq __builtin_vec_bcdadd_eq
+#define __builtin_bcdadd_gt __builtin_vec_bcdadd_gt
+#define __builtin_bcdadd_ofl __builtin_vec_bcdadd_ov
+#define __builtin_bcdadd_ov __builtin_vec_bcdadd_ov
+#define __builtin_bcdsub __builtin_vec_bcdsub
+#define __builtin_bcdsub_lt __builtin_vec_bcdsub_lt
+#define __builtin_bcdsub_eq __builtin_vec_bcdsub_eq
+#define __builtin_bcdsub_gt __builtin_vec_bcdsub_gt
+#define __builtin_bcdsub_ofl __builtin_vec_bcdsub_ov
+#define __builtin_bcdsub_ov __builtin_vec_bcdsub_ov
+#define __builtin_bcdinvalid __builtin_vec_bcdinvalid
+#define __builtin_bcdmul10 __builtin_vec_bcdmul10
+#define __builtin_bcddiv10 __builtin_vec_bcddiv10
+#define __builtin_bcd2dfp __builtin_vec_denb2dfp
+#define __builtin_bcdcmpeq(a,b) __builtin_vec_bcdsub_eq(a,b,0)
+#define __builtin_bcdcmpgt(a,b) __builtin_vec_bcdsub_gt(a,b,0)
+#define __builtin_bcdcmplt(a,b) __builtin_vec_bcdsub_lt(a,b,0)
+#define __builtin_bcdcmpge(a,b) __builtin_vec_bcdsub_ge(a,b,0)
+#define __builtin_bcdcmple(a,b) __builtin_vec_bcdsub_le(a,b,0)
+
+
/* Predicates.
For C++, we use templates in order to allow non-parenthesized arguments.
For C, instead, we use macros since non-parenthesized arguments were
UNSPEC_BCDADD
UNSPEC_BCDSUB
UNSPEC_BCD_OVERFLOW
+ UNSPEC_BCDSHIFT
UNSPEC_VRLMI
UNSPEC_VRLNM
UNSPEC_VCFUGED
(define_int_attr bcd_add_sub [(UNSPEC_BCDADD "add")
(UNSPEC_BCDSUB "sub")])
-(define_code_iterator BCD_TEST [eq lt gt unordered])
+(define_code_iterator BCD_TEST [eq lt le gt ge unordered])
+(define_mode_iterator VBCD [V1TI V16QI])
-(define_insn "bcd<bcd_add_sub>"
- [(set (match_operand:V1TI 0 "gpc_reg_operand" "=v")
- (unspec:V1TI [(match_operand:V1TI 1 "gpc_reg_operand" "v")
- (match_operand:V1TI 2 "gpc_reg_operand" "v")
+(define_insn "bcd<bcd_add_sub>_<mode>"
+ [(set (match_operand:VBCD 0 "register_operand" "=v")
+ (unspec:VBCD [(match_operand:VBCD 1 "register_operand" "v")
+ (match_operand:VBCD 2 "register_operand" "v")
(match_operand:QI 3 "const_0_to_1_operand" "n")]
UNSPEC_BCD_ADD_SUB))
(clobber (reg:CCFP CR6_REGNO))]
;; UNORDERED test on an integer type (like V1TImode) is not defined. The type
;; probably should be one that can go in the VMX (Altivec) registers, so we
;; can't use DDmode or DFmode.
-(define_insn "*bcd<bcd_add_sub>_test"
+(define_insn "*bcd<bcd_add_sub>_test_<mode>"
[(set (reg:CCFP CR6_REGNO)
(compare:CCFP
- (unspec:V2DF [(match_operand:V1TI 1 "register_operand" "v")
- (match_operand:V1TI 2 "register_operand" "v")
+ (unspec:V2DF [(match_operand:VBCD 1 "register_operand" "v")
+ (match_operand:VBCD 2 "register_operand" "v")
(match_operand:QI 3 "const_0_to_1_operand" "i")]
UNSPEC_BCD_ADD_SUB)
(match_operand:V2DF 4 "zero_constant" "j")))
- (clobber (match_scratch:V1TI 0 "=v"))]
+ (clobber (match_scratch:VBCD 0 "=v"))]
"TARGET_P8_VECTOR"
"bcd<bcd_add_sub>. %0,%1,%2,%3"
[(set_attr "type" "vecsimple")])
-(define_insn "*bcd<bcd_add_sub>_test2"
- [(set (match_operand:V1TI 0 "register_operand" "=v")
- (unspec:V1TI [(match_operand:V1TI 1 "register_operand" "v")
- (match_operand:V1TI 2 "register_operand" "v")
+(define_insn "*bcd<bcd_add_sub>_test2_<mode>"
+ [(set (match_operand:VBCD 0 "register_operand" "=v")
+ (unspec:VBCD [(match_operand:VBCD 1 "register_operand" "v")
+ (match_operand:VBCD 2 "register_operand" "v")
(match_operand:QI 3 "const_0_to_1_operand" "i")]
UNSPEC_BCD_ADD_SUB))
(set (reg:CCFP CR6_REGNO)
}
[(set_attr "type" "vecsimple")])
-(define_expand "bcd<bcd_add_sub>_<code>"
+(define_expand "bcd<bcd_add_sub>_<code>_<mode>"
[(parallel [(set (reg:CCFP CR6_REGNO)
(compare:CCFP
- (unspec:V2DF [(match_operand:V1TI 1 "register_operand")
- (match_operand:V1TI 2 "register_operand")
+ (unspec:V2DF [(match_operand:VBCD 1 "register_operand")
+ (match_operand:VBCD 2 "register_operand")
(match_operand:QI 3 "const_0_to_1_operand")]
UNSPEC_BCD_ADD_SUB)
(match_dup 4)))
- (clobber (match_scratch:V1TI 5))])
+ (clobber (match_scratch:VBCD 5))])
(set (match_operand:SI 0 "register_operand")
(BCD_TEST:SI (reg:CCFP CR6_REGNO)
(const_int 0)))]
operands[4] = CONST0_RTX (V2DFmode);
})
+(define_insn "*bcdinvalid_<mode>"
+ [(set (reg:CCFP CR6_REGNO)
+ (compare:CCFP
+ (unspec:V2DF [(match_operand:VBCD 1 "register_operand" "v")]
+ UNSPEC_BCDADD)
+ (match_operand:V2DF 2 "zero_constant" "j")))
+ (clobber (match_scratch:VBCD 0 "=v"))]
+ "TARGET_P8_VECTOR"
+ "bcdadd. %0,%1,%1,0"
+ [(set_attr "type" "vecsimple")])
+
+(define_expand "bcdinvalid_<mode>"
+ [(parallel [(set (reg:CCFP CR6_REGNO)
+ (compare:CCFP
+ (unspec:V2DF [(match_operand:VBCD 1 "register_operand")]
+ UNSPEC_BCDADD)
+ (match_dup 2)))
+ (clobber (match_scratch:VBCD 3))])
+ (set (match_operand:SI 0 "register_operand")
+ (unordered:SI (reg:CCFP CR6_REGNO)
+ (const_int 0)))]
+ "TARGET_P8_VECTOR"
+{
+ operands[2] = CONST0_RTX (V2DFmode);
+})
+
+(define_insn "bcdshift_v16qi"
+ [(set (match_operand:V16QI 0 "register_operand" "=v")
+ (unspec:V16QI [(match_operand:V16QI 1 "register_operand" "v")
+ (match_operand:V16QI 2 "register_operand" "v")
+ (match_operand:QI 3 "const_0_to_1_operand" "n")]
+ UNSPEC_BCDSHIFT))
+ (clobber (reg:CCFP CR6_REGNO))]
+ "TARGET_P8_VECTOR"
+ "bcds. %0,%1,%2,%3"
+ [(set_attr "type" "vecsimple")])
+
+(define_expand "bcdmul10_v16qi"
+ [(set (match_operand:V16QI 0 "register_operand")
+ (unspec:V16QI [(match_operand:V16QI 1 "register_operand")]
+ UNSPEC_BCDSHIFT))
+ (clobber (reg:CCFP CR6_REGNO))]
+ "TARGET_P9_VECTOR"
+{
+ rtx one = gen_reg_rtx (V16QImode);
+
+ emit_insn (gen_altivec_vspltisb (one, const1_rtx));
+ emit_insn (gen_bcdshift_v16qi (operands[0], one, operands[1], const0_rtx));
+
+ DONE;
+})
+
+(define_expand "bcddiv10_v16qi"
+ [(set (match_operand:V16QI 0 "register_operand")
+ (unspec:V16QI [(match_operand:V16QI 1 "register_operand")]
+ UNSPEC_BCDSHIFT))
+ (clobber (reg:CCFP CR6_REGNO))]
+ "TARGET_P9_VECTOR"
+{
+ rtx one = gen_reg_rtx (V16QImode);
+
+ emit_insn (gen_altivec_vspltisb (one, constm1_rtx));
+ emit_insn (gen_bcdshift_v16qi (operands[0], one, operands[1], const0_rtx));
+
+ DONE;
+})
+
+
;; Peephole2 pattern to combine a bcdadd/bcdsub that calculates the value and
;; the bcdadd/bcdsub that tests the value. The combiner won't work since
;; CR6 is a hard coded register. Unfortunately, all of the Altivec predicate
"denbcd<q> %1,%0,%2"
[(set_attr "type" "dfp")])
+(define_insn "dfp_denbcd_v16qi_inst"
+ [(set (match_operand:TD 0 "gpc_reg_operand" "=d")
+ (unspec:TD [(match_operand:QI 1 "const_0_to_1_operand" "i")
+ (match_operand:V16QI 2 "register_operand" "d")]
+ UNSPEC_DENBCD))]
+ "TARGET_DFP"
+ "denbcdq %1,%0,%2"
+ [(set_attr "type" "dfp")])
+
+(define_expand "dfp_denbcd_v16qi"
+ [(set (match_operand:TD 0 "gpc_reg_operand" "=d")
+ (unspec:TD [(match_operand:V16QI 1 "register_operand" "v")]
+ UNSPEC_DENBCD))]
+ "TARGET_DFP"
+ {
+ // Move vs128 upper 64-bits and lower 64-bits to fp register pair
+ convert_move (operands[0], operands[1], true);
+ emit_insn (gen_dfp_denbcd_v16qi_inst (operands[0], GEN_INT(1),
+ operands[0]));
+ DONE;
+ })
+
(define_insn "dfp_dxex_<mode>"
[(set (match_operand:DI 0 "gpc_reg_operand" "=d")
(unspec:DI [(match_operand:DDTD 1 "gpc_reg_operand" "d")]
/* Miscellaneous builtins for instructions added in ISA 2.07. These
instructions do require the ISA 2.07 vector support, but they aren't vector
instructions. */
+#define BU_P8V_MISC_1(ENUM, NAME, ATTR, ICODE) \
+ RS6000_BUILTIN_1 (MISC_BUILTIN_ ## ENUM, /* ENUM */ \
+ "__builtin_" NAME, /* NAME */ \
+ RS6000_BTM_P8_VECTOR, /* MASK */ \
+ (RS6000_BTC_ ## ATTR /* ATTR */ \
+ | RS6000_BTC_UNARY), \
+ CODE_FOR_ ## ICODE) /* ICODE */
+
#define BU_P8V_MISC_3(ENUM, NAME, ATTR, ICODE) \
RS6000_BUILTIN_3 (MISC_BUILTIN_ ## ENUM, /* ENUM */ \
"__builtin_" NAME, /* NAME */ \
BU_P7_MISC_2 (ADDG6S, "addg6s", CONST, addg6s)
/* 3 argument BCD functions added in ISA 2.07. */
-BU_P8V_MISC_3 (BCDADD, "bcdadd", CONST, bcdadd)
-BU_P8V_MISC_3 (BCDADD_LT, "bcdadd_lt", CONST, bcdadd_lt)
-BU_P8V_MISC_3 (BCDADD_EQ, "bcdadd_eq", CONST, bcdadd_eq)
-BU_P8V_MISC_3 (BCDADD_GT, "bcdadd_gt", CONST, bcdadd_gt)
-BU_P8V_MISC_3 (BCDADD_OV, "bcdadd_ov", CONST, bcdadd_unordered)
-BU_P8V_MISC_3 (BCDSUB, "bcdsub", CONST, bcdsub)
-BU_P8V_MISC_3 (BCDSUB_LT, "bcdsub_lt", CONST, bcdsub_lt)
-BU_P8V_MISC_3 (BCDSUB_EQ, "bcdsub_eq", CONST, bcdsub_eq)
-BU_P8V_MISC_3 (BCDSUB_GT, "bcdsub_gt", CONST, bcdsub_gt)
-BU_P8V_MISC_3 (BCDSUB_OV, "bcdsub_ov", CONST, bcdsub_unordered)
+BU_P8V_MISC_3 (BCDADD_V1TI, "bcdadd_v1ti", CONST, bcdadd_v1ti)
+BU_P8V_MISC_3 (BCDADD_V16QI, "bcdadd_v16qi", CONST, bcdadd_v16qi)
+BU_P8V_MISC_3 (BCDADD_LT_V1TI, "bcdadd_lt_v1ti", CONST, bcdadd_lt_v1ti)
+BU_P8V_MISC_3 (BCDADD_LT_V16QI, "bcdadd_lt_v16qi", CONST, bcdadd_lt_v16qi)
+BU_P8V_MISC_3 (BCDADD_EQ_V1TI, "bcdadd_eq_v1ti", CONST, bcdadd_eq_v1ti)
+BU_P8V_MISC_3 (BCDADD_EQ_V16QI, "bcdadd_eq_v16qi", CONST, bcdadd_eq_v16qi)
+BU_P8V_MISC_3 (BCDADD_GT_V1TI, "bcdadd_gt_v1ti", CONST, bcdadd_gt_v1ti)
+BU_P8V_MISC_3 (BCDADD_GT_V16QI, "bcdadd_gt_v16qi", CONST, bcdadd_gt_v16qi)
+BU_P8V_MISC_3 (BCDADD_OV_V1TI, "bcdadd_ov_v1ti", CONST, bcdadd_unordered_v1ti)
+BU_P8V_MISC_3 (BCDADD_OV_V16QI, "bcdadd_ov_v16qi", CONST, bcdadd_unordered_v16qi)
+
+BU_P8V_MISC_3 (BCDSUB_V1TI, "bcdsub_v1ti", CONST, bcdsub_v1ti)
+BU_P8V_MISC_3 (BCDSUB_V16QI, "bcdsub_v16qi", CONST, bcdsub_v16qi)
+BU_P8V_MISC_3 (BCDSUB_LT_V1TI, "bcdsub_lt_v1ti", CONST, bcdsub_lt_v1ti)
+BU_P8V_MISC_3 (BCDSUB_LT_V16QI, "bcdsub_lt_v16qi", CONST, bcdsub_lt_v16qi)
+BU_P8V_MISC_3 (BCDSUB_LE_V1TI, "bcdsub_le_v1ti", CONST, bcdsub_le_v1ti)
+BU_P8V_MISC_3 (BCDSUB_LE_V16QI, "bcdsub_le_v16qi", CONST, bcdsub_le_v16qi)
+BU_P8V_MISC_3 (BCDSUB_EQ_V1TI, "bcdsub_eq_v1ti", CONST, bcdsub_eq_v1ti)
+BU_P8V_MISC_3 (BCDSUB_EQ_V16QI, "bcdsub_eq_v16qi", CONST, bcdsub_eq_v16qi)
+BU_P8V_MISC_3 (BCDSUB_GT_V1TI, "bcdsub_gt_v1ti", CONST, bcdsub_gt_v1ti)
+BU_P8V_MISC_3 (BCDSUB_GT_V16QI, "bcdsub_gt_v16qi", CONST, bcdsub_gt_v16qi)
+BU_P8V_MISC_3 (BCDSUB_GE_V1TI, "bcdsub_ge_v1ti", CONST, bcdsub_ge_v1ti)
+BU_P8V_MISC_3 (BCDSUB_GE_V16QI, "bcdsub_ge_v16qi", CONST, bcdsub_ge_v16qi)
+BU_P8V_MISC_3 (BCDSUB_OV_V1TI, "bcdsub_ov_v1ti", CONST, bcdsub_unordered_v1ti)
+BU_P8V_MISC_3 (BCDSUB_OV_V16QI, "bcdsub_ov_v16qi", CONST, bcdsub_unordered_v16qi)
+
+BU_P8V_MISC_1 (BCDINVALID_V1TI, "bcdinvalid_v1ti", CONST, bcdinvalid_v1ti)
+BU_P8V_MISC_1 (BCDINVALID_V16QI, "bcdinvalid_v16qi", CONST, bcdinvalid_v16qi)
+
+BU_P9V_AV_1 (BCDMUL10_V16QI, "bcdmul10_v16qi", CONST, bcdmul10_v16qi)
+BU_P9V_AV_1 (BCDDIV10_V16QI, "bcddiv10_v16qi", CONST, bcddiv10_v16qi)
+BU_P8V_MISC_1 (DENBCD_V16QI, "denb2dfp_v16qi", CONST, dfp_denbcd_v16qi)
+
+BU_P8V_OVERLOAD_3 (BCDADD, "bcdadd")
+BU_P8V_OVERLOAD_3 (BCDADD_LT, "bcdadd_lt")
+BU_P8V_OVERLOAD_3 (BCDADD_EQ, "bcdadd_eq")
+BU_P8V_OVERLOAD_3 (BCDADD_GT, "bcdadd_gt")
+BU_P8V_OVERLOAD_3 (BCDADD_OV, "bcdadd_ov")
+BU_P8V_OVERLOAD_3 (BCDSUB, "bcdsub")
+BU_P8V_OVERLOAD_3 (BCDSUB_LT, "bcdsub_lt")
+BU_P8V_OVERLOAD_3 (BCDSUB_LE, "bcdsub_le")
+BU_P8V_OVERLOAD_3 (BCDSUB_EQ, "bcdsub_eq")
+BU_P8V_OVERLOAD_3 (BCDSUB_GT, "bcdsub_gt")
+BU_P8V_OVERLOAD_3 (BCDSUB_GE, "bcdsub_ge")
+BU_P8V_OVERLOAD_3 (BCDSUB_OV, "bcdsub_ov")
+BU_P8V_OVERLOAD_1 (BCDINVALID, "bcdinvalid")
+BU_P9V_OVERLOAD_1 (BCDMUL10, "bcdmul10")
+BU_P9V_OVERLOAD_1 (BCDDIV10, "bcddiv10")
+BU_P8V_OVERLOAD_1 (DENBCD, "denb2dfp")
/* 2 argument pack/unpack 128-bit floating point types. */
BU_DFP_MISC_2 (PACK_TD, "pack_dec128", CONST, packtd)
RS6000_BTI_unsigned_V4SI, RS6000_BTI_V4SF, RS6000_BTI_INTSI, 0 },
{ ALTIVEC_BUILTIN_VEC_CTU, VSX_BUILTIN_XVCVDPUXDS_SCALE,
RS6000_BTI_unsigned_V2DI, RS6000_BTI_V2DF, RS6000_BTI_INTSI, 0 },
+
+ { P8V_BUILTIN_VEC_BCDADD, MISC_BUILTIN_BCDADD_V1TI,
+ RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDADD, MISC_BUILTIN_BCDADD_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDADD_LT, MISC_BUILTIN_BCDADD_LT_V1TI,
+ RS6000_BTI_INTSI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDADD_LT, MISC_BUILTIN_BCDADD_LT_V16QI,
+ RS6000_BTI_INTSI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDADD_EQ, MISC_BUILTIN_BCDADD_EQ_V1TI,
+ RS6000_BTI_INTSI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDADD_EQ, MISC_BUILTIN_BCDADD_EQ_V16QI,
+ RS6000_BTI_INTSI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDADD_GT, MISC_BUILTIN_BCDADD_GT_V1TI,
+ RS6000_BTI_INTSI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDADD_GT, MISC_BUILTIN_BCDADD_GT_V16QI,
+ RS6000_BTI_INTSI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDADD_OV, MISC_BUILTIN_BCDADD_OV_V1TI,
+ RS6000_BTI_INTSI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDADD_OV, MISC_BUILTIN_BCDADD_OV_V16QI,
+ RS6000_BTI_INTSI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDINVALID, MISC_BUILTIN_BCDINVALID_V1TI,
+ RS6000_BTI_INTSI, RS6000_BTI_V1TI, 0, 0 },
+ { P8V_BUILTIN_VEC_BCDINVALID, MISC_BUILTIN_BCDINVALID_V16QI,
+ RS6000_BTI_INTSI, RS6000_BTI_unsigned_V16QI, 0, 0 },
+
+ { P9V_BUILTIN_VEC_BCDMUL10, P9V_BUILTIN_BCDMUL10_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI, 0, 0 },
+ { P9V_BUILTIN_VEC_BCDDIV10, P9V_BUILTIN_BCDDIV10_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI, 0, 0 },
+
+ { P8V_BUILTIN_VEC_DENBCD, MISC_BUILTIN_DENBCD_V16QI,
+ RS6000_BTI_dfloat128, RS6000_BTI_unsigned_V16QI, 0, 0 },
+
+ { P8V_BUILTIN_VEC_BCDSUB, MISC_BUILTIN_BCDSUB_V1TI,
+ RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB, MISC_BUILTIN_BCDSUB_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_LT, MISC_BUILTIN_BCDSUB_LT_V1TI,
+ RS6000_BTI_INTSI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_LT, MISC_BUILTIN_BCDSUB_LT_V16QI,
+ RS6000_BTI_INTSI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_LE, MISC_BUILTIN_BCDSUB_LE_V1TI,
+ RS6000_BTI_INTSI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_LE, MISC_BUILTIN_BCDSUB_LE_V16QI,
+ RS6000_BTI_INTSI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_EQ, MISC_BUILTIN_BCDSUB_EQ_V1TI,
+ RS6000_BTI_INTSI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_EQ, MISC_BUILTIN_BCDSUB_EQ_V16QI,
+ RS6000_BTI_INTSI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_GT, MISC_BUILTIN_BCDSUB_GT_V1TI,
+ RS6000_BTI_INTSI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_GT, MISC_BUILTIN_BCDSUB_GT_V16QI,
+ RS6000_BTI_INTSI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_GE, MISC_BUILTIN_BCDSUB_GE_V1TI,
+ RS6000_BTI_INTSI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_GE, MISC_BUILTIN_BCDSUB_GE_V16QI,
+ RS6000_BTI_INTSI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_OV, MISC_BUILTIN_BCDSUB_OV_V1TI,
+ RS6000_BTI_INTSI, RS6000_BTI_V1TI, RS6000_BTI_V1TI, RS6000_BTI_INTSI },
+ { P8V_BUILTIN_VEC_BCDSUB_OV, MISC_BUILTIN_BCDSUB_OV_V16QI,
+ RS6000_BTI_INTSI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_INTSI },
+
+
{ VSX_BUILTIN_VEC_DIV, VSX_BUILTIN_XVDIVSP,
RS6000_BTI_V4SF, RS6000_BTI_V4SF, RS6000_BTI_V4SF, 0 },
{ VSX_BUILTIN_VEC_DIV, VSX_BUILTIN_XVDIVDP,
}
else if (icode == CODE_FOR_vsx_set_v2df
|| icode == CODE_FOR_vsx_set_v2di
- || icode == CODE_FOR_bcdadd
- || icode == CODE_FOR_bcdadd_lt
- || icode == CODE_FOR_bcdadd_eq
- || icode == CODE_FOR_bcdadd_gt
- || icode == CODE_FOR_bcdsub
- || icode == CODE_FOR_bcdsub_lt
- || icode == CODE_FOR_bcdsub_eq
- || icode == CODE_FOR_bcdsub_gt)
+ || icode == CODE_FOR_bcdadd_v16qi
+ || icode == CODE_FOR_bcdadd_v1ti
+ || icode == CODE_FOR_bcdadd_lt_v16qi
+ || icode == CODE_FOR_bcdadd_lt_v1ti
+ || icode == CODE_FOR_bcdadd_eq_v16qi
+ || icode == CODE_FOR_bcdadd_eq_v1ti
+ || icode == CODE_FOR_bcdadd_gt_v16qi
+ || icode == CODE_FOR_bcdadd_gt_v1ti
+ || icode == CODE_FOR_bcdsub_v16qi
+ || icode == CODE_FOR_bcdsub_v1ti
+ || icode == CODE_FOR_bcdsub_lt_v16qi
+ || icode == CODE_FOR_bcdsub_lt_v1ti
+ || icode == CODE_FOR_bcdsub_eq_v16qi
+ || icode == CODE_FOR_bcdsub_eq_v1ti
+ || icode == CODE_FOR_bcdsub_gt_v16qi
+ || icode == CODE_FOR_bcdsub_gt_v1ti)
{
/* Only allow 1-bit unsigned literals. */
STRIP_NOPS (arg2);
}
}
else if (icode == CODE_FOR_dfp_denbcd_dd
- || icode == CODE_FOR_dfp_denbcd_td)
+ || icode == CODE_FOR_dfp_denbcd_td
+ || icode == CODE_FOR_dfp_denbcd_v16qi)
{
/* Only allow 1-bit unsigned literals. */
STRIP_NOPS (arg0);
__uint128 vec_vsubuqm (__uint128, __uint128);
vector __int128 __builtin_bcdadd (vector __int128, vector __int128, const int);
+vector unsigned char __builtin_bcdadd (vector unsigned char, vector unsigned char,
+ const int);
int __builtin_bcdadd_lt (vector __int128, vector __int128, const int);
+int __builtin_bcdadd_lt (vector unsigned char, vector unsigned char, const int);
int __builtin_bcdadd_eq (vector __int128, vector __int128, const int);
+int __builtin_bcdadd_eq (vector unsigned char, vector unsigned char, const int);
int __builtin_bcdadd_gt (vector __int128, vector __int128, const int);
+int __builtin_bcdadd_gt (vector unsigned char, vector unsigned char, const int);
int __builtin_bcdadd_ov (vector __int128, vector __int128, const int);
+int __builtin_bcdadd_ov (vector unsigned char, vector unsigned char, const int);
+
vector __int128 __builtin_bcdsub (vector __int128, vector __int128, const int);
+vector unsigned char __builtin_bcdsub (vector unsigned char, vector unsigned char,
+ const int);
int __builtin_bcdsub_lt (vector __int128, vector __int128, const int);
+int __builtin_bcdsub_lt (vector unsigned char, vector unsigned char, const int);
int __builtin_bcdsub_eq (vector __int128, vector __int128, const int);
+int __builtin_bcdsub_eq (vector unsigned char, vector unsigned char, const int);
int __builtin_bcdsub_gt (vector __int128, vector __int128, const int);
+int __builtin_bcdsub_gt (vector unsigned char, vector unsigned char, const int);
int __builtin_bcdsub_ov (vector __int128, vector __int128, const int);
+int __builtin_bcdsub_ov (vector unsigned char, vector unsigned char, const int);
@end smallexample
@node PowerPC AltiVec Built-in Functions Available on ISA 3.0
/* { dg-final { scan-assembler-not "stxvw4x" } } */
/* { dg-final { scan-assembler-not "stxvd2x" } } */
+#include <altivec.h>
+
typedef __int128_t __attribute__((__vector_size__(16))) vector_128_t;
typedef __int128_t scalar_128_t;
typedef unsigned long long scalar_64_t;
typedef __int128_t scalar_128_t;
typedef unsigned long long scalar_64_t;
+#include <altivec.h>
+
/* Test whether the peephole works to allow folding a bcdadd, with a
bcdadd_<test> into a single instruction. */
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target int128 } */
+/* { dg-require-effective-target power10_hw } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2 -save-temps" } */
+/* { dg-final { scan-assembler-times {\mbcdadd\M} 7 } } */
+/* { dg-final { scan-assembler-times {\mbcdsub\M} 18 } } */
+/* { dg-final { scan-assembler-times {\mbcds\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mdenbcdq\M} 1 } } */
+
+#include <altivec.h>
+
+#define DEBUG 0
+
+#if DEBUG
+#include <stdio.h>
+#endif
+
+
+#define BCD_POS0 12 // 0xC
+#define BCD_POS1 15 // 0xF
+#define BCD_NEG 13 // 0xD
+
+void abort (void);
+
+ union conv_t
+ {
+ _Decimal128 d128;
+ vector unsigned char ch;
+ vector long long unsigned int vllui;
+ } conv;
+
+_Decimal128 convert_vec_char (vector unsigned char a)
+{
+ union conv_t conv;
+ _Decimal128 result;
+
+ conv.ch = a;
+ result = conv.d128;
+ return result;
+}
+
+vector unsigned char maxbcd(unsigned int sign)
+{
+ vector unsigned char result;
+ int i;
+
+ for (i = 15; i > 0; i--)
+ result[i] = 0x99;
+
+ result[0] = sign << 4 | 0x9;
+}
+
+vector unsigned char num2bcd(long int a, int encoding)
+{
+ int i;
+ unsigned int hi, low, sign;
+
+ vector unsigned char result;
+
+ if (a > 0) {
+ if (encoding == 0)
+ sign = BCD_POS0;
+ else
+ sign = BCD_POS1;
+
+ } else {
+ sign = BCD_NEG;
+ a = -a;
+ }
+
+ hi = a % 10; // 1st digit
+ a = a / 10;
+ result[0] = hi << 4| sign;
+
+ for (i = 1; i < 16; i++)
+ {
+ low = a % 10;
+ a = a / 10;
+ hi = a % 10;
+ a = a / 10;
+ result[i] = hi << 4 | low;
+ }
+
+
+ return result;
+}
+
+int main ()
+{
+ int i;
+ long int value_a, value_b, value_result;
+ vector unsigned char a, b, result, exp_result;
+ _Decimal128 result_d128, exp_result_d128;
+
+ /* Make a and b positive BCD numbers */
+ value_a = 1020304;
+ a = num2bcd(value_a, 0);
+
+ value_b = 101010;
+ b = num2bcd(value_b, 0);
+
+ value_result = value_a + value_b;
+ exp_result = num2bcd(value_result, 0);
+
+ result = __builtin_bcdadd (a, b, 0);
+
+ for (i = 0; i < 16; i++)
+ if (exp_result[i] != result[i]) {
+
+#if DEBUG
+ printf("ERROR: __builtin_bcdadd result[%d] = %d does not match "
+ "expected_result[%d] = %d\n",
+ i, result[i], i, exp_result[i]);
+#else
+ abort();
+#endif
+ }
+
+ /* result should be positive */
+ if ((result[0] & 0xF) != BCD_POS0)
+#if DEBUG
+ printf("ERROR: __builtin_bcdadd sign of result is %d. Does not match "
+ "expected_result = %d\n",
+ result[0] & 0xF, BCD_POS0);
+#else
+ abort();
+#endif
+
+ /* Make a and b positive BCD numbers using alternate positive encoding. */
+ value_a = 1030507;
+ a = num2bcd(value_a, 1);
+
+ value_b = 204060;
+ b = num2bcd(value_b, 1);
+
+ value_result = value_a + value_b;
+ exp_result = num2bcd(value_result, 1);
+
+ result = __builtin_bcdadd (a, b, 1);
+
+ for (i = 0; i < 16; i++)
+ if (exp_result[i] != result[i]) {
+#if DEBUG
+ printf("ERROR: __builtin_bcdadd result[%d] = %d does not match "
+ "expected_result[%d] = %d\n",
+ i, result[i], i, exp_result[i]);
+#else
+ abort();
+#endif
+ }
+
+ /* Result should be positive, alternate encoding. */
+ if ((result[0] & 0xF) != BCD_POS1)
+#if DEBUG
+ printf("ERROR: __builtin_bcdadd sign of result is %d. Does not "
+ "match expected_result = %d\n",
+ result[0] & 0xF, BCD_POS1);
+#else
+ abort();
+#endif
+
+ /* Make a and b negative BCD numbers */
+ value_a = -1030507;
+ a = num2bcd(value_a, 0);
+
+ value_b = -1010101;
+ b = num2bcd(value_b, 0);
+
+ value_result = value_a + value_b;
+ exp_result = num2bcd(value_result, 0);
+
+ result = __builtin_bcdadd (a, b, 0);
+
+ for (i = 0; i < 16; i++)
+ if (exp_result[i] != result[i]) {
+#if DEBUG
+ printf("ERROR: __builtin_bcdadd, neg result[%d] = %d does not match "
+ "expected_result[%d] = %d\n",
+ i, result[i], i, exp_result[i]);
+#else
+ abort();
+#endif
+ }
+
+ /* result should be negative */
+ if ((result[0] & 0xF) != BCD_NEG)
+#if DEBUG
+ printf("ERROR: __builtin_bcdadd sign, neg of result is %d. Does not "
+ "match expected_result = %d\n",
+ result[0] & 0xF, BCD_NEG);
+#else
+ abort();
+#endif
+
+
+ /* Make a negative, b positive BCD numbers */
+ value_a = -1030507;
+ a = num2bcd(value_a, 0);
+
+ value_b = 1010101;
+ b = num2bcd(value_b, 0);
+
+ value_result = value_a - value_b;
+ exp_result = num2bcd(value_result, 0);
+
+ result = __builtin_bcdsub (a, b, 0);
+
+ for (i = 0; i < 16; i++)
+ if (exp_result[i] != result[i]) {
+#if DEBUG
+ printf("ERROR: __builtin_bcdsub, neg result[%d] = %d does not match "
+ "expected_result[%d] = %d\n",
+ i, result[i], i, exp_result[i]);
+#else
+ abort();
+#endif
+ }
+
+ /* result should be positive, alt encoding */
+ if ((result[0] & 0xF) != BCD_NEG)
+#if DEBUG
+ printf("ERROR: __builtin_bcdadd sign, of result is %d. Does not match "
+ "expected_result = %d\n",
+ result[0] & 0xF, BCD_NEG);
+#else
+ abort();
+#endif
+
+ /* Make a and b positive BCD numbers */
+ value_a = 1030507;
+ a = num2bcd(value_a, 1);
+
+ value_b = 1010101;
+ b = num2bcd(value_b, 1);
+
+ value_result = value_a - value_b;
+ exp_result = num2bcd(value_result, 1);
+
+ result = __builtin_bcdsub (a, b, 1);
+
+ for (i = 0; i < 16; i++)
+ if (exp_result[i] != result[i]) {
+#if DEBUG
+ printf("ERROR:carll __builtin_bcdsub, pos result[%d] = %d does not "
+ "match expected_result[%d] = %d\n",
+ i, result[i], i, exp_result[i]);
+#else
+ abort();
+#endif
+ }
+
+ /* result should be positive */
+ if ((result[0] & 0xF) != BCD_POS1)
+#if DEBUG
+ printf("ERROR: __builtin_bcdsub sign, result is %d. Does not match "
+ "expected_result = %d\n",
+ result[0] & 0xF, BCD_POS1);
+#else
+ abort();
+#endif
+
+ /* Test overflow add and subtract. */
+ a = maxbcd(BCD_POS0);
+ b = maxbcd(BCD_POS0);
+
+ if(__builtin_bcdadd_ofl (a, b, 0) == 0)
+#if DEBUG
+ printf("ERROR: __builtin_bcdadd did not overflow as expected\n");
+#else
+ abort();
+#endif
+
+ value_a = 99999999;
+ a = num2bcd(value_a, 0);
+
+ value_b = 999999999;
+ b = num2bcd(value_b, 0);
+
+ if(__builtin_bcdadd_ofl (a, b, 0))
+#if DEBUG
+ printf("ERROR: __builtin_bcdadd unexpectedly overflowed\n");
+#else
+ abort();
+#endif
+
+ a = maxbcd(BCD_NEG);
+ b = maxbcd(BCD_NEG);
+
+ if (__builtin_bcdsub_ofl (a, b, 0) == 0)
+#if DEBUG
+ printf("ERROR: __builtin_bcdsub did not overflow as expected\n");
+#else
+ abort();
+#endif
+
+ value_a = -99999999;
+ a = num2bcd(value_a, 0);
+
+ value_b = -999999999;
+ b = num2bcd(value_b, 0);
+
+ if (__builtin_bcdsub_ofl (a, b, 0))
+#if DEBUG
+ printf("ERROR: __builtin_bcdsub unexpectedly overflowed\n");
+#else
+ abort();
+#endif
+
+ /* Test arguments for valid/invalid */
+ if (__builtin_bcdinvalid (a))
+#if DEBUG
+ printf("ERROR: __builtin_invalid input is unexpectedly invalid.\n");
+#else
+ abort();
+#endif
+
+ a[3] = 0xBB; /* an invalid BCD digit */
+ if (!__builtin_bcdinvalid (a))
+#if DEBUG
+ printf("ERROR: __builtin_invalid input is unexpectedly valid.\n");
+#else
+ abort();
+#endif
+
+ value_a = 1020304;
+ a = num2bcd(value_a, 0);
+
+ value_b = 101010;
+ b = num2bcd(value_b, 0);
+
+ /* Test equality */
+ if (__builtin_bcdcmpeq (a, b))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmpeq result is unexpectedly 1.\n");
+#else
+ abort();
+#endif
+
+ if (!__builtin_bcdcmpeq (a, a))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmpeq result is unexpectedly 0.\n");
+#else
+ abort();
+#endif
+
+
+ /* Test a greater then b, inputs already setup this way. */
+ if (!__builtin_bcdcmpgt (a, b))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmpgt result is unexpectedly 0.\n");
+#else
+ abort();
+#endif
+
+ if (__builtin_bcdcmpgt (b, a))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmpgt result is unexpectedly 1.\n");
+#else
+ abort();
+#endif
+
+ if (__builtin_bcdcmpgt (a, a))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmpgt input equal, result is unexpectedly "
+ "1.\n");
+#else
+ abort();
+#endif
+
+
+ if (!__builtin_bcdcmpge (a, b))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmpge result is unexpectedly 0.\n");
+#else
+ abort();
+#endif
+
+ if (__builtin_bcdcmpge (b, a))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmpge result is unexpectedly 1.\n");
+#else
+ abort();
+#endif
+
+ if (!__builtin_bcdcmpge (b, b))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmpge inputs equal result is unexpectedly "
+ "0.\n");
+#else
+ abort();
+#endif
+
+ /* Test a less then b. */
+ value_a = 101010;
+ a = num2bcd(value_a, 0);
+ value_b = 1020304;
+ b = num2bcd(value_b, 0);
+
+ if (!__builtin_bcdcmplt (a, b))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmplt result is unexpectedly 0.\n");
+#else
+ abort();
+#endif
+
+ if (__builtin_bcdcmplt (b, a))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmplt result is unexpectedly 1.\n");
+#else
+ abort();
+#endif
+
+ if (__builtin_bcdcmplt (b, b))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmplt inputs equal result is unexpectedly "
+ "1.\n");
+#else
+ abort();
+#endif
+
+
+ if (!__builtin_bcdcmple (a, b))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmple result is unexpectedly 0.\n");
+#else
+ abort();
+#endif
+
+ if (__builtin_bcdcmple (b, a))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmple result is unexpectedly 1.\n");
+#else
+ abort();
+#endif
+
+ if (!__builtin_bcdcmple (a, a))
+#if DEBUG
+ printf("ERROR: __builtin__bcdcmple inputs equal result is unexpectedly "
+ "0.\n");
+#else
+ abort();
+#endif
+
+ /* Test multipy 10 */
+ value_a = 1020304;
+ a = num2bcd(value_a, 0);
+
+ value_result = value_a * 10;
+ exp_result = num2bcd(value_result, 0);
+
+ result = __builtin_bcdmul10 (a);
+
+ for (i = 0; i < 16; i++)
+ if (exp_result[i] != result[i]) {
+#if DEBUG
+ printf("ERROR:carll __builtin_bcdmul10, pos result[%d] = %d does not "
+ "match expected_result[%d] = %d\n",
+ i, result[i], i, exp_result[i]);
+#else
+ abort();
+#endif
+ }
+
+ /* result should be positive */
+ if ((result[0] & 0xF) != BCD_POS0)
+#if 0
+ printf("ERROR: __builtin_bcdmul10 sign, result is %d. Does not match "
+ "expected_result = %d\n",
+ result[0] & 0xF, BCD_POS1);
+#else
+ abort();
+#endif
+
+ /* Test divide 10 */
+ value_a = 1020304;
+ a = num2bcd(value_a, 0);
+
+ value_result = value_a / 10;
+ exp_result = num2bcd(value_result, 0);
+
+ result = __builtin_bcddiv10 (a);
+
+ for (i = 0; i < 16; i++)
+ if (exp_result[i] != result[i]) {
+#if DEBUG
+ printf("ERROR:carll __builtin_bcddiv10, pos result[%d] = %d does not "
+ "match expected_result[%d] = %d\n",
+ i, result[i], i, exp_result[i]);
+#else
+ abort();
+#endif
+ }
+
+ /* result should be positive */
+ if ((result[0] & 0xF) != BCD_POS0)
+#if DEBUG
+ printf("ERROR: __builtin_bcddiv10 sign, result is %d. Does not match "
+ "expected_result = %d\n",
+ result[0] & 0xF, BCD_POS1);
+#else
+ abort();
+#endif
+
+ value_a = 1020304;
+ exp_result_d128 = 1020304;
+ a = num2bcd(value_a, 0);
+
+ conv.ch = a;
+ conv.d128 = __builtin_bcd2dfp (a);
+ result_d128 = conv.d128;
+
+ if (result_d128 != exp_result_d128)
+#if DEBUG
+ printf("ERROR: __builtin_bcd2dfp, result does not match expected_result."
+ "\n");
+#else
+ abort();
+#endif
+ return 0;
+}
+