@@ -43,7 +43,6 @@ extern bool ia64_expand_vecint_minmax (enum rtx_code, enum machine_mode, rtx[]);
extern void ia64_unpack_assemble (rtx, rtx, rtx, bool);
extern void ia64_expand_unpack (rtx [], bool, bool);
extern void ia64_expand_widen_sum (rtx[], bool);
-extern void ia64_expand_dot_prod_v8qi (rtx[], bool);
extern void ia64_expand_call (rtx, rtx, rtx, int);
extern void ia64_split_call (rtx, rtx, rtx, rtx, rtx, int, int);
extern void ia64_reload_gp (void);
@@ -2096,46 +2096,6 @@ ia64_expand_widen_sum (rtx operands[3], bool unsignedp)
emit_move_insn (operands[0], t);
}
-/* Emit a signed or unsigned V8QI dot product operation. */
-
-void
-ia64_expand_dot_prod_v8qi (rtx operands[4], bool unsignedp)
-{
- rtx op1, op2, sn1, sn2, l1, l2, h1, h2;
- rtx p1, p2, p3, p4, s1, s2, s3;
-
- op1 = operands[1];
- op2 = operands[2];
- sn1 = ia64_unpack_sign (op1, unsignedp);
- sn2 = ia64_unpack_sign (op2, unsignedp);
-
- l1 = gen_reg_rtx (V4HImode);
- l2 = gen_reg_rtx (V4HImode);
- h1 = gen_reg_rtx (V4HImode);
- h2 = gen_reg_rtx (V4HImode);
- ia64_unpack_assemble (l1, op1, sn1, false);
- ia64_unpack_assemble (l2, op2, sn2, false);
- ia64_unpack_assemble (h1, op1, sn1, true);
- ia64_unpack_assemble (h2, op2, sn2, true);
-
- p1 = gen_reg_rtx (V2SImode);
- p2 = gen_reg_rtx (V2SImode);
- p3 = gen_reg_rtx (V2SImode);
- p4 = gen_reg_rtx (V2SImode);
- emit_insn (gen_pmpy2_even (p1, l1, l2));
- emit_insn (gen_pmpy2_even (p2, h1, h2));
- emit_insn (gen_pmpy2_odd (p3, l1, l2));
- emit_insn (gen_pmpy2_odd (p4, h1, h2));
-
- s1 = gen_reg_rtx (V2SImode);
- s2 = gen_reg_rtx (V2SImode);
- s3 = gen_reg_rtx (V2SImode);
- emit_insn (gen_addv2si3 (s1, p1, p2));
- emit_insn (gen_addv2si3 (s2, p3, p4));
- emit_insn (gen_addv2si3 (s3, s1, operands[3]));
- emit_insn (gen_addv2si3 (operands[0], s2, s3));
-}
-
/* Emit the appropriate sequence for a call. */
void
@@ -278,7 +278,29 @@
"pmpyshr2.u %0 = %1, %2, %3"
[(set_attr "itanium_class" "mmmul")])
-(define_insn "pmpy2_even"
+(define_expand "smulv4hi3_highpart"
+ [(match_operand:V4HI 0 "gr_register_operand")
+ (match_operand:V4HI 1 "gr_register_operand")
+ (match_operand:V4HI 2 "gr_register_operand")]
+ ""
+{
+ emit_insn (gen_pmpyshr2 (operands[0], operands[1],
+ operands[2], GEN_INT (16)));
+ DONE;
+})
+
+(define_expand "umulv4hi3_highpart"
+ [(match_operand:V4HI 0 "gr_register_operand")
+ (match_operand:V4HI 1 "gr_register_operand")
+ (match_operand:V4HI 2 "gr_register_operand")]
+ ""
+{
+ emit_insn (gen_pmpyshr2_u (operands[0], operands[1],
+ operands[2], GEN_INT (16)));
+ DONE;
+})
+
+(define_insn "vec_widen_smult_even_v4hi"
[(set (match_operand:V2SI 0 "gr_register_operand" "=r")
(mult:V2SI
(vec_select:V2SI
@@ -299,7 +321,7 @@
}
[(set_attr "itanium_class" "mmshf")])
-(define_insn "pmpy2_odd"
+(define_insn "vec_widen_smult_odd_v4hi"
[(set (match_operand:V2SI 0 "gr_register_operand" "=r")
(mult:V2SI
(vec_select:V2SI
@@ -602,68 +624,6 @@
DONE;
})
-(define_expand "udot_prodv8qi"
- [(match_operand:V2SI 0 "gr_register_operand" "")
- (match_operand:V8QI 1 "gr_register_operand" "")
- (match_operand:V8QI 2 "gr_register_operand" "")
- (match_operand:V2SI 3 "gr_register_operand" "")]
- ""
-{
- ia64_expand_dot_prod_v8qi (operands, true);
- DONE;
-})
-
-(define_expand "sdot_prodv8qi"
- [(match_operand:V2SI 0 "gr_register_operand" "")
- (match_operand:V8QI 1 "gr_register_operand" "")
- (match_operand:V8QI 2 "gr_register_operand" "")
- (match_operand:V2SI 3 "gr_register_operand" "")]
- ""
-{
- ia64_expand_dot_prod_v8qi (operands, false);
- DONE;
-})
-
-(define_expand "sdot_prodv4hi"
- [(match_operand:V2SI 0 "gr_register_operand" "")
- (match_operand:V4HI 1 "gr_register_operand" "")
- (match_operand:V4HI 2 "gr_register_operand" "")
- (match_operand:V2SI 3 "gr_register_operand" "")]
- ""
-{
- rtx e, o, t;
-
- e = gen_reg_rtx (V2SImode);
- o = gen_reg_rtx (V2SImode);
- t = gen_reg_rtx (V2SImode);
-
- emit_insn (gen_pmpy2_even (e, operands[1], operands[2]));
- emit_insn (gen_pmpy2_odd (o, operands[1], operands[2]));
- emit_insn (gen_addv2si3 (t, e, operands[3]));
- emit_insn (gen_addv2si3 (operands[0], t, o));
- DONE;
-})
-
-(define_expand "udot_prodv4hi"
- [(match_operand:V2SI 0 "gr_register_operand" "")
- (match_operand:V4HI 1 "gr_register_operand" "")
- (match_operand:V4HI 2 "gr_register_operand" "")
- (match_operand:V2SI 3 "gr_register_operand" "")]
- ""
-{
- rtx l, h, t;
-
- l = gen_reg_rtx (V2SImode);
- h = gen_reg_rtx (V2SImode);
- t = gen_reg_rtx (V2SImode);
-
- emit_insn (gen_vec_widen_umult_lo_v4hi (l, operands[1], operands[2]));
- emit_insn (gen_vec_widen_umult_hi_v4hi (h, operands[1], operands[2]));
- emit_insn (gen_addv2si3 (t, l, operands[3]));
- emit_insn (gen_addv2si3 (operands[0], t, h));
- DONE;
-})
-
(define_expand "vcond<mode><mode>"
[(set (match_operand:VECINT 0 "gr_register_operand" "")
(if_then_else:VECINT
With the even/odd v4hi multiply pattern names, we'll automatically generate the same code for dot_prodv4hi. The dot_prodv8qi pattern was actively incorrect wrt output mode. r~ * config/ia64/vect.md (smulv4hi3_highpart): New. (umulv4hi3_highpart): New. (vec_widen_smult_even_v4hi): Rename from pmpy2_even. (vec_widen_smult_odd_v4hi): Rename from pmpy2_odd. (udot_prodv8qi, sdot_prodv8qi): Remove. (sdot_prodv4hi, udot_prodv4hi): Remove. * config/ia64/ia64.c (ia64_expand_dot_prod_v8qi): Remove. * config/ia64/ia64-protos.h: Update. --- gcc/ChangeLog | 9 ++++ gcc/config/ia64/ia64-protos.h | 1 - gcc/config/ia64/ia64.c | 40 ------------------ gcc/config/ia64/vect.md | 88 +++++++++++----------------------------- 4 files changed, 33 insertions(+), 105 deletions(-)