@@ -62,15 +62,15 @@ DEF_BUILTIN (SI_SFI, CODE_FOR_spu_sf, "si_sfi", B_INSN,
DEF_BUILTIN (SI_SFX, CODE_FOR_spu_sfx, "si_sfx", B_INSN, _A4(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
DEF_BUILTIN (SI_BG, CODE_FOR_spu_bg, "si_bg", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
DEF_BUILTIN (SI_BGX, CODE_FOR_spu_bgx, "si_bgx", B_INSN, _A4(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
-DEF_BUILTIN (SI_MPY, CODE_FOR_spu_mpy, "si_mpy", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
-DEF_BUILTIN (SI_MPYU, CODE_FOR_spu_mpyu, "si_mpyu", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
-DEF_BUILTIN (SI_MPYI, CODE_FOR_spu_mpy, "si_mpyi", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_S10))
-DEF_BUILTIN (SI_MPYUI, CODE_FOR_spu_mpyu, "si_mpyui", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_S10))
+DEF_BUILTIN (SI_MPY, CODE_FOR_vec_widen_smult_odd_v8hi, "si_mpy", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
+DEF_BUILTIN (SI_MPYU, CODE_FOR_vec_widen_umult_odd_v8hi, "si_mpyu", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
+DEF_BUILTIN (SI_MPYI, CODE_FOR_vec_widen_smult_odd_v8hi, "si_mpyi", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_S10))
+DEF_BUILTIN (SI_MPYUI, CODE_FOR_vec_widen_umult_odd_v8hi, "si_mpyui", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_S10))
DEF_BUILTIN (SI_MPYA, CODE_FOR_spu_mpya, "si_mpya", B_INSN, _A4(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
DEF_BUILTIN (SI_MPYH, CODE_FOR_spu_mpyh, "si_mpyh", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
DEF_BUILTIN (SI_MPYS, CODE_FOR_spu_mpys, "si_mpys", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
-DEF_BUILTIN (SI_MPYHH, CODE_FOR_spu_mpyhh, "si_mpyhh", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
-DEF_BUILTIN (SI_MPYHHU, CODE_FOR_spu_mpyhhu, "si_mpyhhu", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
+DEF_BUILTIN (SI_MPYHH, CODE_FOR_vec_widen_smult_even_v8hi, "si_mpyhh", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
+DEF_BUILTIN (SI_MPYHHU, CODE_FOR_vec_widen_umult_even_v8hi, "si_mpyhhu", B_INSN, _A3(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
DEF_BUILTIN (SI_MPYHHA, CODE_FOR_spu_mpyhha, "si_mpyhha", B_INSN, _A4(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
DEF_BUILTIN (SI_MPYHHAU, CODE_FOR_spu_mpyhhau, "si_mpyhhau", B_INSN, _A4(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
DEF_BUILTIN (SI_CLZ, CODE_FOR_clzv4si2, "si_clz", B_INSN, _A2(SPU_BTI_QUADWORD, SPU_BTI_QUADWORD))
@@ -295,16 +295,16 @@ DEF_BUILTIN (SPU_MHHADD, CODE_FOR_nothing, "spu_mhhadd",
DEF_BUILTIN (SPU_MHHADD_0, CODE_FOR_spu_mpyhhau, "spu_mhhadd_0", B_INTERNAL, _A4(SPU_BTI_UV4SI, SPU_BTI_UV8HI, SPU_BTI_UV8HI, SPU_BTI_UV4SI))
DEF_BUILTIN (SPU_MHHADD_1, CODE_FOR_spu_mpyhha, "spu_mhhadd_1", B_INTERNAL, _A4(SPU_BTI_V4SI, SPU_BTI_V8HI, SPU_BTI_V8HI, SPU_BTI_V4SI))
DEF_BUILTIN (SPU_MULE, CODE_FOR_nothing, "spu_mule", B_OVERLOAD, _A1(SPU_BTI_VOID))
-DEF_BUILTIN (SPU_MULE_0, CODE_FOR_spu_mpyhhu, "spu_mule_0", B_INTERNAL, _A3(SPU_BTI_UV4SI, SPU_BTI_UV8HI, SPU_BTI_UV8HI))
-DEF_BUILTIN (SPU_MULE_1, CODE_FOR_spu_mpyhh, "spu_mule_1", B_INTERNAL, _A3(SPU_BTI_V4SI, SPU_BTI_V8HI, SPU_BTI_V8HI))
+DEF_BUILTIN (SPU_MULE_0, CODE_FOR_vec_widen_umult_even_v8hi, "spu_mule_0", B_INTERNAL, _A3(SPU_BTI_UV4SI, SPU_BTI_UV8HI, SPU_BTI_UV8HI))
+DEF_BUILTIN (SPU_MULE_1, CODE_FOR_vec_widen_smult_even_v8hi, "spu_mule_1", B_INTERNAL, _A3(SPU_BTI_V4SI, SPU_BTI_V8HI, SPU_BTI_V8HI))
DEF_BUILTIN (SPU_MUL, CODE_FOR_nothing, "spu_mul", B_OVERLOAD, _A1(SPU_BTI_VOID))
DEF_BUILTIN (SPU_MUL_0, CODE_FOR_mulv4sf3, "spu_mul_0", B_INTERNAL, _A3(SPU_BTI_V4SF, SPU_BTI_V4SF, SPU_BTI_V4SF))
DEF_BUILTIN (SPU_MUL_1, CODE_FOR_mulv2df3, "spu_mul_1", B_INTERNAL, _A3(SPU_BTI_V2DF, SPU_BTI_V2DF, SPU_BTI_V2DF))
DEF_BUILTIN (SPU_MULO, CODE_FOR_nothing, "spu_mulo", B_OVERLOAD, _A1(SPU_BTI_VOID))
-DEF_BUILTIN (SPU_MULO_0, CODE_FOR_spu_mpy, "spu_mulo_0", B_INTERNAL, _A3(SPU_BTI_V4SI, SPU_BTI_V8HI, SPU_BTI_V8HI))
-DEF_BUILTIN (SPU_MULO_1, CODE_FOR_spu_mpyu, "spu_mulo_1", B_INTERNAL, _A3(SPU_BTI_UV4SI, SPU_BTI_UV8HI, SPU_BTI_UV8HI))
-DEF_BUILTIN (SPU_MULO_2, CODE_FOR_spu_mpy, "spu_mulo_2", B_INTERNAL, _A3(SPU_BTI_V4SI, SPU_BTI_V8HI, SPU_BTI_INTHI))
-DEF_BUILTIN (SPU_MULO_3, CODE_FOR_spu_mpyu, "spu_mulo_3", B_INTERNAL, _A3(SPU_BTI_UV4SI, SPU_BTI_UV8HI, SPU_BTI_UINTHI))
+DEF_BUILTIN (SPU_MULO_0, CODE_FOR_vec_widen_smult_odd_v8hi, "spu_mulo_0", B_INTERNAL, _A3(SPU_BTI_V4SI, SPU_BTI_V8HI, SPU_BTI_V8HI))
+DEF_BUILTIN (SPU_MULO_1, CODE_FOR_vec_widen_umult_odd_v8hi, "spu_mulo_1", B_INTERNAL, _A3(SPU_BTI_UV4SI, SPU_BTI_UV8HI, SPU_BTI_UV8HI))
+DEF_BUILTIN (SPU_MULO_2, CODE_FOR_vec_widen_smult_odd_v8hi, "spu_mulo_2", B_INTERNAL, _A3(SPU_BTI_V4SI, SPU_BTI_V8HI, SPU_BTI_INTHI))
+DEF_BUILTIN (SPU_MULO_3, CODE_FOR_vec_widen_umult_odd_v8hi, "spu_mulo_3", B_INTERNAL, _A3(SPU_BTI_UV4SI, SPU_BTI_UV8HI, SPU_BTI_UINTHI))
DEF_BUILTIN (SPU_NMSUB, CODE_FOR_nothing, "spu_nmsub", B_OVERLOAD, _A1(SPU_BTI_VOID))
DEF_BUILTIN (SPU_NMSUB_0, CODE_FOR_fnmav4sf4, "spu_nmsub_0", B_INTERNAL, _A4(SPU_BTI_V4SF, SPU_BTI_V4SF, SPU_BTI_V4SF, SPU_BTI_V4SF))
DEF_BUILTIN (SPU_NMSUB_1, CODE_FOR_nfmsv2df4, "spu_nmsub_1", B_INTERNAL, _A4(SPU_BTI_V2DF, SPU_BTI_V2DF, SPU_BTI_V2DF, SPU_BTI_V2DF))
@@ -197,41 +197,6 @@
""
"")
-;; integer multiply
-(define_insn "spu_mpy"
- [(set (match_operand:V4SI 0 "spu_reg_operand" "=r,r")
- (mult:V4SI
- (sign_extend:V4SI
- (vec_select:V4HI
- (match_operand:V8HI 1 "spu_reg_operand" "r,r")
- (parallel [(const_int 1)(const_int 3)(const_int 5)(const_int 7)])))
- (sign_extend:V4SI
- (vec_select:V4HI
- (match_operand:V8HI 2 "spu_arith_operand" "r,B")
- (parallel [(const_int 1)(const_int 3)(const_int 5)(const_int 7)])))))]
- ""
- "@
- mpy\t%0,%1,%2
- mpyi\t%0,%1,%2"
- [(set_attr "type" "fp7")])
-
-(define_insn "spu_mpyu"
- [(set (match_operand:V4SI 0 "spu_reg_operand" "=r,r")
- (mult:V4SI
- (zero_extend:V4SI
- (vec_select:V4HI
- (match_operand:V8HI 1 "spu_reg_operand" "r,r")
- (parallel [(const_int 1)(const_int 3)(const_int 5)(const_int 7)])))
- (zero_extend:V4SI
- (vec_select:V4HI
- (match_operand:V8HI 2 "spu_arith_operand" "r,B")
- (parallel [(const_int 1)(const_int 3)(const_int 5)(const_int 7)])))))]
- ""
- "@
- mpyu\t%0,%1,%2
- mpyui\t%0,%1,%2"
- [(set_attr "type" "fp7")])
-
(define_insn "spu_mpya"
[(set (match_operand:V4SI 0 "spu_reg_operand" "=r")
(plus:V4SI
@@ -283,36 +248,6 @@
"mpys\t%0,%1,%2"
[(set_attr "type" "fp7")])
-(define_insn "spu_mpyhhu"
- [(set (match_operand:V4SI 0 "spu_reg_operand" "=r")
- (mult:V4SI
- (zero_extend:V4SI
- (vec_select:V4HI
- (match_operand:V8HI 1 "spu_reg_operand" "r")
- (parallel [(const_int 0)(const_int 2)(const_int 4)(const_int 6)])))
- (zero_extend:V4SI
- (vec_select:V4HI
- (match_operand:V8HI 2 "spu_reg_operand" "r")
- (parallel [(const_int 0)(const_int 2)(const_int 4)(const_int 6)])))))]
- ""
- "mpyhhu\t%0,%1,%2"
- [(set_attr "type" "fp7")])
-
-(define_insn "spu_mpyhh"
- [(set (match_operand:V4SI 0 "spu_reg_operand" "=r")
- (mult:V4SI
- (sign_extend:V4SI
- (vec_select:V4HI
- (match_operand:V8HI 1 "spu_reg_operand" "r")
- (parallel [(const_int 0)(const_int 2)(const_int 4)(const_int 6)])))
- (sign_extend:V4SI
- (vec_select:V4HI
- (match_operand:V8HI 2 "spu_reg_operand" "r")
- (parallel [(const_int 0)(const_int 2)(const_int 4)(const_int 6)])))))]
- ""
- "mpyhh\t%0,%1,%2"
- [(set_attr "type" "fp7")])
-
(define_insn "spu_mpyhhau"
[(set (match_operand:V4SI 0 "spu_reg_operand" "=r")
(plus:V4SI
@@ -1387,8 +1387,8 @@
rtx mask = gen_reg_rtx (V4SImode);
emit_move_insn (mask, spu_const (V4SImode, 0x0000ffff));
- emit_insn (gen_spu_mpyhh (high, operands[1], operands[2]));
- emit_insn (gen_spu_mpy (low, operands[1], operands[2]));
+ emit_insn (gen_vec_widen_smult_even_v8hi (high, operands[1], operands[2]));
+ emit_insn (gen_vec_widen_smult_odd_v8hi (low, operands[1], operands[2]));
emit_insn (gen_vashlv4si3 (shift, high, spu_const(V4SImode, 16)));
emit_insn (gen_selb (result, shift, low, mask));
DONE;
@@ -1482,7 +1482,7 @@
rtx op2 = simplify_gen_subreg (V8HImode, operands[2], V4SImode, 0);
emit_insn (gen_spu_mpyh(a, op1, op2));
emit_insn (gen_spu_mpyh(b, op2, op1));
- emit_insn (gen_spu_mpyu(c, op1, op2));
+ emit_insn (gen_vec_widen_umult_odd_v8hi (c, op1, op2));
emit_insn (gen_addv4si3(d, a, b));
emit_insn (gen_addv4si3(operands[0], d, c));
DONE;
@@ -4612,6 +4612,70 @@ selb\t%0,%4,%0,%3"
DONE;
}")
+(define_insn "vec_widen_smult_odd_v8hi"
+ [(set (match_operand:V4SI 0 "spu_reg_operand" "=r,r")
+ (mult:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 1 "spu_reg_operand" "r,r")
+ (parallel [(const_int 1)(const_int 3)(const_int 5)(const_int 7)])))
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 2 "spu_arith_operand" "r,B")
+ (parallel [(const_int 1)(const_int 3)(const_int 5)(const_int 7)])))))]
+ ""
+ "@
+ mpy\t%0,%1,%2
+ mpyi\t%0,%1,%2"
+ [(set_attr "type" "fp7")])
+
+(define_insn "vec_widen_umult_odd_v8hi"
+ [(set (match_operand:V4SI 0 "spu_reg_operand" "=r,r")
+ (mult:V4SI
+ (zero_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 1 "spu_reg_operand" "r,r")
+ (parallel [(const_int 1)(const_int 3)(const_int 5)(const_int 7)])))
+ (zero_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 2 "spu_arith_operand" "r,B")
+ (parallel [(const_int 1)(const_int 3)(const_int 5)(const_int 7)])))))]
+ ""
+ "@
+ mpyu\t%0,%1,%2
+ mpyui\t%0,%1,%2"
+ [(set_attr "type" "fp7")])
+
+(define_insn "vec_widen_smult_even_v8hi"
+ [(set (match_operand:V4SI 0 "spu_reg_operand" "=r")
+ (mult:V4SI
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 1 "spu_reg_operand" "r")
+ (parallel [(const_int 0)(const_int 2)(const_int 4)(const_int 6)])))
+ (sign_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 2 "spu_reg_operand" "r")
+ (parallel [(const_int 0)(const_int 2)(const_int 4)(const_int 6)])))))]
+ ""
+ "mpyhh\t%0,%1,%2"
+ [(set_attr "type" "fp7")])
+
+(define_insn "vec_widen_umult_even_v8hi"
+ [(set (match_operand:V4SI 0 "spu_reg_operand" "=r")
+ (mult:V4SI
+ (zero_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 1 "spu_reg_operand" "r")
+ (parallel [(const_int 0)(const_int 2)(const_int 4)(const_int 6)])))
+ (zero_extend:V4SI
+ (vec_select:V4HI
+ (match_operand:V8HI 2 "spu_reg_operand" "r")
+ (parallel [(const_int 0)(const_int 2)(const_int 4)(const_int 6)])))))]
+ ""
+ "mpyhhu\t%0,%1,%2"
+ [(set_attr "type" "fp7")])
+
(define_expand "vec_widen_umult_hi_v8hi"
[(set (match_operand:V4SI 0 "register_operand" "=r")
(mult:V4SI
@@ -4634,8 +4698,8 @@ selb\t%0,%4,%0,%3"
0x04, 0x05, 0x06, 0x07, 0x14, 0x15, 0x16, 0x17};
emit_move_insn (mask, array_to_constant (TImode, arr));
- emit_insn (gen_spu_mpyhhu (ve, operands[1], operands[2]));
- emit_insn (gen_spu_mpyu (vo, operands[1], operands[2]));
+ emit_insn (gen_vec_widen_umult_even_v8hi (ve, operands[1], operands[2]));
+ emit_insn (gen_vec_widen_umult_odd_v8hi (vo, operands[1], operands[2]));
emit_insn (gen_shufb (operands[0], ve, vo, mask));
DONE;
}")
@@ -4662,8 +4726,8 @@ selb\t%0,%4,%0,%3"
0x0C, 0x0D, 0x0E, 0x0F, 0x1C, 0x1D, 0x1E, 0x1F};
emit_move_insn (mask, array_to_constant (TImode, arr));
- emit_insn (gen_spu_mpyhhu (ve, operands[1], operands[2]));
- emit_insn (gen_spu_mpyu (vo, operands[1], operands[2]));
+ emit_insn (gen_vec_widen_umult_even_v8hi (ve, operands[1], operands[2]));
+ emit_insn (gen_vec_widen_umult_odd_v8hi (vo, operands[1], operands[2]));
emit_insn (gen_shufb (operands[0], ve, vo, mask));
DONE;
}")
@@ -4690,8 +4754,8 @@ selb\t%0,%4,%0,%3"
0x04, 0x05, 0x06, 0x07, 0x14, 0x15, 0x16, 0x17};
emit_move_insn (mask, array_to_constant (TImode, arr));
- emit_insn (gen_spu_mpyhh (ve, operands[1], operands[2]));
- emit_insn (gen_spu_mpy (vo, operands[1], operands[2]));
+ emit_insn (gen_vec_widen_smult_even_v8hi (ve, operands[1], operands[2]));
+ emit_insn (gen_vec_widen_smult_odd_v8hi (vo, operands[1], operands[2]));
emit_insn (gen_shufb (operands[0], ve, vo, mask));
DONE;
}")
@@ -4718,8 +4782,8 @@ selb\t%0,%4,%0,%3"
0x0C, 0x0D, 0x0E, 0x0F, 0x1C, 0x1D, 0x1E, 0x1F};
emit_move_insn (mask, array_to_constant (TImode, arr));
- emit_insn (gen_spu_mpyhh (ve, operands[1], operands[2]));
- emit_insn (gen_spu_mpy (vo, operands[1], operands[2]));
+ emit_insn (gen_vec_widen_smult_even_v8hi (ve, operands[1], operands[2]));
+ emit_insn (gen_vec_widen_smult_odd_v8hi (vo, operands[1], operands[2]));
emit_insn (gen_shufb (operands[0], ve, vo, mask));
DONE;
}")