Rework the (u)maddhisi4 patterns and use VMAC2H(U) instruction instead
of the 64bit MAC(U) instruction.
This fixes the next execute.exp failures:
arith-rand-ll.c -O2 execution test
arith-rand-ll.c -O3 execution test
pr78726.c -O2 execution test
pr78726.c -O3 execution test
Backported to gcc11 too.
gcc/
2021-06-09 Claudiu Zissulescu <claz...@synopsys.com>
* config/arc/arc.md (maddhisi4): Use VMAC2H instruction.
(machi): New pattern.
(umaddhisi4): Use VMAC2HU instruction.
(umachi): New pattern.
Signed-off-by: Claudiu Zissulescu <claz...@synopsys.com>
---
gcc/config/arc/arc.md | 66 +++++++++++++++++++++++++++----------------
1 file changed, 41 insertions(+), 25 deletions(-)
diff --git a/gcc/config/arc/arc.md b/gcc/config/arc/arc.md
index 6f13b3a01d8..aed0b40728b 100644
--- a/gcc/config/arc/arc.md
+++ b/gcc/config/arc/arc.md
@@ -6025,48 +6025,64 @@ (define_insn "stack_irq_dwarf"
;; MAC and DMPY instructions
-; Use MAC instruction to emulate 16bit mac.
+; Use VMAC2H(U) instruction to emulate scalar 16bit mac.
(define_expand "maddhisi4"
[(match_operand:SI 0 "register_operand" "")
(match_operand:HI 1 "register_operand" "")
(match_operand:HI 2 "extend_operand" "")
(match_operand:SI 3 "register_operand" "")]
- "TARGET_PLUS_DMPY"
+ "TARGET_PLUS_MACD"
"{
- rtx acc_reg = gen_rtx_REG (DImode, ACC_REG_FIRST);
- rtx tmp1 = gen_reg_rtx (SImode);
- rtx tmp2 = gen_reg_rtx (SImode);
- rtx accl = gen_lowpart (SImode, acc_reg);
-
- emit_move_insn (accl, operands[3]);
- emit_insn (gen_rtx_SET (tmp1, gen_rtx_SIGN_EXTEND (SImode, operands[1])));
- emit_insn (gen_rtx_SET (tmp2, gen_rtx_SIGN_EXTEND (SImode, operands[2])));
- emit_insn (gen_mac (tmp1, tmp2));
- emit_move_insn (operands[0], accl);
+ rtx acc_reg = gen_rtx_REG (SImode, ACC_REG_FIRST);
+
+ emit_move_insn (acc_reg, operands[3]);
+ emit_insn (gen_machi (operands[1], operands[2]));
+ emit_move_insn (operands[0], acc_reg);
DONE;
}")
-; The same for the unsigned variant, but using MACU instruction.
+(define_insn "machi"
+ [(set (reg:SI ARCV2_ACC)
+ (plus:SI
+ (mult:SI (sign_extend:SI (match_operand:HI 0 "register_operand" "%r"))
+ (sign_extend:SI (match_operand:HI 1 "register_operand" "r")))
+ (reg:SI ARCV2_ACC)))]
+ "TARGET_PLUS_MACD"
+ "vmac2h\\t0,%0,%1"
+ [(set_attr "length" "4")
+ (set_attr "type" "multi")
+ (set_attr "predicable" "no")
+ (set_attr "cond" "nocond")])
+
+; The same for the unsigned variant, but using VMAC2HU instruction.
(define_expand "umaddhisi4"
[(match_operand:SI 0 "register_operand" "")
(match_operand:HI 1 "register_operand" "")
- (match_operand:HI 2 "extend_operand" "")
+ (match_operand:HI 2 "register_operand" "")
(match_operand:SI 3 "register_operand" "")]
- "TARGET_PLUS_DMPY"
+ "TARGET_PLUS_MACD"
"{
- rtx acc_reg = gen_rtx_REG (DImode, ACC_REG_FIRST);
- rtx tmp1 = gen_reg_rtx (SImode);
- rtx tmp2 = gen_reg_rtx (SImode);
- rtx accl = gen_lowpart (SImode, acc_reg);
-
- emit_move_insn (accl, operands[3]);
- emit_insn (gen_rtx_SET (tmp1, gen_rtx_ZERO_EXTEND (SImode, operands[1])));
- emit_insn (gen_rtx_SET (tmp2, gen_rtx_ZERO_EXTEND (SImode, operands[2])));
- emit_insn (gen_macu (tmp1, tmp2));
- emit_move_insn (operands[0], accl);
+ rtx acc_reg = gen_rtx_REG (SImode, ACC_REG_FIRST);
+
+ emit_move_insn (acc_reg, operands[3]);
+ emit_insn (gen_umachi (operands[1], operands[2]));
+ emit_move_insn (operands[0], acc_reg);
DONE;
}")
+(define_insn "umachi"
+ [(set (reg:SI ARCV2_ACC)
+ (plus:SI
+ (mult:SI (zero_extend:SI (match_operand:HI 0 "register_operand" "%r"))
+ (zero_extend:SI (match_operand:HI 1 "register_operand" "r")))
+ (reg:SI ARCV2_ACC)))]
+ "TARGET_PLUS_MACD"
+ "vmac2hu\\t0,%0,%1"
+ [(set_attr "length" "4")
+ (set_attr "type" "multi")
+ (set_attr "predicable" "no")
+ (set_attr "cond" "nocond")])
+
(define_expand "maddsidi4"
[(match_operand:DI 0 "register_operand" "")
(match_operand:SI 1 "register_operand" "")
--
2.31.1
