+2017-06-20 Carl Love <cel@us.ibm.com>
+
+ * config/rs6000/rs6000-c.c (altivec_overloaded_builtins): Add
+ ALTIVEC_BUILTIN_VMULESW, ALTIVEC_BUILTIN_VMULEUW,
+ ALTIVEC_BUILTIN_VMULOSW, ALTIVEC_BUILTIN_VMULOUW entries.
+ * config/rs6000/rs6000.c (rs6000_gimple_fold_builtin,
+ builtin_function_type): Add ALTIVEC_BUILTIN_* case statements.
+ * config/rs6000/altivec.md (MVULEUW, VMULESW, VMULOUW,
+ VMULOSW): New enum "unspec" values.
+ (vec_widen_umult_even_v4si, vec_widen_smult_even_v4si,
+ vec_widen_umult_odd_v4si, vec_widen_smult_odd_v4si,
+ altivec_vmuleuw, altivec_vmulesw, altivec_vmulouw,
+ altivec_vmulosw): New patterns.
+ * config/rs6000/rs6000-builtin.def (VMLEUW, VMULESW, VMULOUW,
+ VMULOSW): Add definitions.
+
2017-06-20 Julia Koval <julia.koval@intel.com>
* config/i386/i386.c: Fix rounding expand for new pattern.
UNSPEC_VMULESB
UNSPEC_VMULEUH
UNSPEC_VMULESH
+ UNSPEC_VMULEUW
+ UNSPEC_VMULESW
UNSPEC_VMULOUB
UNSPEC_VMULOSB
UNSPEC_VMULOUH
UNSPEC_VMULOSH
+ UNSPEC_VMULOUW
+ UNSPEC_VMULOSW
UNSPEC_VPKPX
UNSPEC_VPACK_SIGN_SIGN_SAT
UNSPEC_VPACK_SIGN_UNS_SAT
DONE;
})
+(define_expand "vec_widen_umult_even_v4si"
+ [(use (match_operand:V2DI 0 "register_operand" ""))
+ (use (match_operand:V4SI 1 "register_operand" ""))
+ (use (match_operand:V4SI 2 "register_operand" ""))]
+ "TARGET_ALTIVEC"
+{
+ if (VECTOR_ELT_ORDER_BIG)
+ emit_insn (gen_altivec_vmuleuw (operands[0], operands[1], operands[2]));
+ else
+ emit_insn (gen_altivec_vmulouw (operands[0], operands[1], operands[2]));
+ DONE;
+})
+
+(define_expand "vec_widen_smult_even_v4si"
+ [(use (match_operand:V2DI 0 "register_operand" ""))
+ (use (match_operand:V4SI 1 "register_operand" ""))
+ (use (match_operand:V4SI 2 "register_operand" ""))]
+ "TARGET_ALTIVEC"
+{
+ if (VECTOR_ELT_ORDER_BIG)
+ emit_insn (gen_altivec_vmulesw (operands[0], operands[1], operands[2]));
+ else
+ emit_insn (gen_altivec_vmulosw (operands[0], operands[1], operands[2]));
+ DONE;
+})
+
(define_expand "vec_widen_umult_odd_v16qi"
[(use (match_operand:V8HI 0 "register_operand" ""))
(use (match_operand:V16QI 1 "register_operand" ""))
DONE;
})
+(define_expand "vec_widen_umult_odd_v4si"
+ [(use (match_operand:V2DI 0 "register_operand" ""))
+ (use (match_operand:V4SI 1 "register_operand" ""))
+ (use (match_operand:V4SI 2 "register_operand" ""))]
+ "TARGET_ALTIVEC"
+{
+ if (VECTOR_ELT_ORDER_BIG)
+ emit_insn (gen_altivec_vmulouw (operands[0], operands[1], operands[2]));
+ else
+ emit_insn (gen_altivec_vmuleuw (operands[0], operands[1], operands[2]));
+ DONE;
+})
+
+(define_expand "vec_widen_smult_odd_v4si"
+ [(use (match_operand:V2DI 0 "register_operand" ""))
+ (use (match_operand:V4SI 1 "register_operand" ""))
+ (use (match_operand:V4SI 2 "register_operand" ""))]
+ "TARGET_ALTIVEC"
+{
+ if (VECTOR_ELT_ORDER_BIG)
+ emit_insn (gen_altivec_vmulosw (operands[0], operands[1],
+ operands[2]));
+ else
+ emit_insn (gen_altivec_vmulesw (operands[0], operands[1],
+ operands[2]));
+ DONE;
+})
+
(define_insn "altivec_vmuleub"
[(set (match_operand:V8HI 0 "register_operand" "=v")
(unspec:V8HI [(match_operand:V16QI 1 "register_operand" "v")
"vmulosh %0,%1,%2"
[(set_attr "type" "veccomplex")])
+(define_insn "altivec_vmuleuw"
+ [(set (match_operand:V2DI 0 "register_operand" "=v")
+ (unspec:V2DI [(match_operand:V4SI 1 "register_operand" "v")
+ (match_operand:V4SI 2 "register_operand" "v")]
+ UNSPEC_VMULEUW))]
+ "TARGET_ALTIVEC"
+ "vmuleuw %0,%1,%2"
+ [(set_attr "type" "veccomplex")])
+
+(define_insn "altivec_vmulouw"
+ [(set (match_operand:V2DI 0 "register_operand" "=v")
+ (unspec:V2DI [(match_operand:V4SI 1 "register_operand" "v")
+ (match_operand:V4SI 2 "register_operand" "v")]
+ UNSPEC_VMULOUW))]
+ "TARGET_ALTIVEC"
+ "vmulouw %0,%1,%2"
+ [(set_attr "type" "veccomplex")])
+
+(define_insn "altivec_vmulesw"
+ [(set (match_operand:V2DI 0 "register_operand" "=v")
+ (unspec:V2DI [(match_operand:V4SI 1 "register_operand" "v")
+ (match_operand:V4SI 2 "register_operand" "v")]
+ UNSPEC_VMULESW))]
+ "TARGET_ALTIVEC"
+ "vmulesw %0,%1,%2"
+ [(set_attr "type" "veccomplex")])
+
+(define_insn "altivec_vmulosw"
+ [(set (match_operand:V2DI 0 "register_operand" "=v")
+ (unspec:V2DI [(match_operand:V4SI 1 "register_operand" "v")
+ (match_operand:V4SI 2 "register_operand" "v")]
+ UNSPEC_VMULOSW))]
+ "TARGET_ALTIVEC"
+ "vmulosw %0,%1,%2"
+ [(set_attr "type" "veccomplex")])
;; Vector pack/unpack
(define_insn "altivec_vpkpx"
BU_ALTIVEC_2 (VMULESB, "vmulesb", CONST, vec_widen_smult_even_v16qi)
BU_ALTIVEC_2 (VMULEUH, "vmuleuh", CONST, vec_widen_umult_even_v8hi)
BU_ALTIVEC_2 (VMULESH, "vmulesh", CONST, vec_widen_smult_even_v8hi)
+BU_ALTIVEC_2 (VMULEUW, "vmuleuw", CONST, vec_widen_umult_even_v4si)
+BU_ALTIVEC_2 (VMULESW, "vmulesw", CONST, vec_widen_smult_even_v4si)
BU_ALTIVEC_2 (VMULOUB, "vmuloub", CONST, vec_widen_umult_odd_v16qi)
BU_ALTIVEC_2 (VMULOSB, "vmulosb", CONST, vec_widen_smult_odd_v16qi)
BU_ALTIVEC_2 (VMULOUH, "vmulouh", CONST, vec_widen_umult_odd_v8hi)
BU_ALTIVEC_2 (VMULOSH, "vmulosh", CONST, vec_widen_smult_odd_v8hi)
+BU_ALTIVEC_2 (VMULOUW, "vmulouw", CONST, vec_widen_umult_odd_v4si)
+BU_ALTIVEC_2 (VMULOSW, "vmulosw", CONST, vec_widen_smult_odd_v4si)
BU_ALTIVEC_2 (VNOR, "vnor", CONST, norv4si3)
BU_ALTIVEC_2 (VOR, "vor", CONST, iorv4si3)
BU_ALTIVEC_2 (VPKUHUM, "vpkuhum", CONST, altivec_vpkuhum)
BU_ALTIVEC_OVERLOAD_2 (VMRGLW, "vmrglw")
BU_ALTIVEC_OVERLOAD_2 (VMULESB, "vmulesb")
BU_ALTIVEC_OVERLOAD_2 (VMULESH, "vmulesh")
+BU_ALTIVEC_OVERLOAD_2 (VMULESW, "vmulesw")
BU_ALTIVEC_OVERLOAD_2 (VMULEUB, "vmuleub")
BU_ALTIVEC_OVERLOAD_2 (VMULEUH, "vmuleuh")
+BU_ALTIVEC_OVERLOAD_2 (VMULEUW, "vmuleuw")
BU_ALTIVEC_OVERLOAD_2 (VMULOSB, "vmulosb")
BU_ALTIVEC_OVERLOAD_2 (VMULOSH, "vmulosh")
+BU_ALTIVEC_OVERLOAD_2 (VMULOSW, "vmulosw")
BU_ALTIVEC_OVERLOAD_2 (VMULOUB, "vmuloub")
BU_ALTIVEC_OVERLOAD_2 (VMULOUH, "vmulouh")
+BU_ALTIVEC_OVERLOAD_2 (VMULOUW, "vmulouw")
BU_ALTIVEC_OVERLOAD_2 (VPKSHSS, "vpkshss")
BU_ALTIVEC_OVERLOAD_2 (VPKSHUS, "vpkshus")
BU_ALTIVEC_OVERLOAD_2 (VPKSWSS, "vpkswss")
RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V8HI, RS6000_BTI_unsigned_V8HI, 0 },
{ ALTIVEC_BUILTIN_VEC_MULE, ALTIVEC_BUILTIN_VMULESH,
RS6000_BTI_V4SI, RS6000_BTI_V8HI, RS6000_BTI_V8HI, 0 },
- { ALTIVEC_BUILTIN_VEC_MULE, ALTIVEC_BUILTIN_VMULESH,
+ { ALTIVEC_BUILTIN_VEC_MULE, ALTIVEC_BUILTIN_VMULESW,
RS6000_BTI_V2DI, RS6000_BTI_V4SI, RS6000_BTI_V4SI, 0 },
- { ALTIVEC_BUILTIN_VEC_MULE, ALTIVEC_BUILTIN_VMULEUH,
+ { ALTIVEC_BUILTIN_VEC_MULE, ALTIVEC_BUILTIN_VMULEUW,
RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V4SI,
RS6000_BTI_unsigned_V4SI, 0 },
{ ALTIVEC_BUILTIN_VEC_VMULEUB, ALTIVEC_BUILTIN_VMULEUB,
RS6000_BTI_V8HI, RS6000_BTI_V16QI, RS6000_BTI_V16QI, 0 },
{ ALTIVEC_BUILTIN_VEC_MULO, ALTIVEC_BUILTIN_VMULOUH,
RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V8HI, RS6000_BTI_unsigned_V8HI, 0 },
- { ALTIVEC_BUILTIN_VEC_MULO, ALTIVEC_BUILTIN_VMULOSH,
+ { ALTIVEC_BUILTIN_VEC_MULO, ALTIVEC_BUILTIN_VMULOSW,
RS6000_BTI_V2DI, RS6000_BTI_V4SI, RS6000_BTI_V4SI, 0 },
- { ALTIVEC_BUILTIN_VEC_MULO, ALTIVEC_BUILTIN_VMULOUH,
+ { ALTIVEC_BUILTIN_VEC_MULO, ALTIVEC_BUILTIN_VMULOUW,
RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V4SI,
RS6000_BTI_unsigned_V4SI, 0 },
{ ALTIVEC_BUILTIN_VEC_MULO, ALTIVEC_BUILTIN_VMULOSH,
/* Even element flavors of vec_mul (signed). */
case ALTIVEC_BUILTIN_VMULESB:
case ALTIVEC_BUILTIN_VMULESH:
+ case ALTIVEC_BUILTIN_VMULESW:
/* Even element flavors of vec_mul (unsigned). */
case ALTIVEC_BUILTIN_VMULEUB:
case ALTIVEC_BUILTIN_VMULEUH:
+ case ALTIVEC_BUILTIN_VMULEUW:
{
arg0 = gimple_call_arg (stmt, 0);
arg1 = gimple_call_arg (stmt, 1);
/* Odd element flavors of vec_mul (signed). */
case ALTIVEC_BUILTIN_VMULOSB:
case ALTIVEC_BUILTIN_VMULOSH:
+ case ALTIVEC_BUILTIN_VMULOSW:
/* Odd element flavors of vec_mul (unsigned). */
case ALTIVEC_BUILTIN_VMULOUB:
case ALTIVEC_BUILTIN_VMULOUH:
+ case ALTIVEC_BUILTIN_VMULOUW:
{
arg0 = gimple_call_arg (stmt, 0);
arg1 = gimple_call_arg (stmt, 1);
/* unsigned 2 argument functions. */
case ALTIVEC_BUILTIN_VMULEUB:
case ALTIVEC_BUILTIN_VMULEUH:
+ case ALTIVEC_BUILTIN_VMULEUW:
case ALTIVEC_BUILTIN_VMULOUB:
case ALTIVEC_BUILTIN_VMULOUH:
+ case ALTIVEC_BUILTIN_VMULOUW:
case CRYPTO_BUILTIN_VCIPHER:
case CRYPTO_BUILTIN_VCIPHERLAST:
case CRYPTO_BUILTIN_VNCIPHER: