@@ -504,7 +504,7 @@
;; Widening instructions have group-overlap constraints. Those are only
;; valid for certain register-group sizes. This attribute marks the
;; alternatives not matching the required register-group size as disabled.
-(define_attr "group_overlap" "none,W21,W42,W84,W43,W86,W87,W0"
+(define_attr "group_overlap" "none,W21,W42,W84,W43,W86,W87,W0,th"
(const_string "none"))
(define_attr "group_overlap_valid" "no,yes"
@@ -543,6 +543,10 @@
(and (eq_attr "group_overlap" "W0")
(match_test "riscv_get_v_regno_alignment (GET_MODE (operands[0])) > 1"))
(const_string "no")
+
+ (and (eq_attr "group_overlap" "th")
+ (match_test "TARGET_XTHEADVECTOR"))
+ (const_string "no")
]
(const_string "yes")))
@@ -3255,7 +3255,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "4")
- (set (attr "avl_type_idx") (const_int 5))])
+ (set (attr "avl_type_idx") (const_int 5))
+ (set_attr "group_overlap" "th,none,none")])
(define_insn "@pred_msbc<mode>"
[(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr")
@@ -3274,7 +3275,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "4")
- (set (attr "avl_type_idx") (const_int 5))])
+ (set (attr "avl_type_idx") (const_int 5))
+ (set_attr "group_overlap" "th,th,none")])
(define_insn "@pred_madc<mode>_scalar"
[(set (match_operand:<VM> 0 "register_operand" "=vr, &vr")
@@ -3294,7 +3296,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "4")
- (set (attr "avl_type_idx") (const_int 5))])
+ (set (attr "avl_type_idx") (const_int 5))
+ (set_attr "group_overlap" "th,none")])
(define_insn "@pred_msbc<mode>_scalar"
[(set (match_operand:<VM> 0 "register_operand" "=vr, &vr")
@@ -3314,7 +3317,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "4")
- (set (attr "avl_type_idx") (const_int 5))])
+ (set (attr "avl_type_idx") (const_int 5))
+ (set_attr "group_overlap" "th,none")])
(define_expand "@pred_madc<mode>_scalar"
[(set (match_operand:<VM> 0 "register_operand")
@@ -3363,7 +3367,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "4")
- (set (attr "avl_type_idx") (const_int 5))])
+ (set (attr "avl_type_idx") (const_int 5))
+ (set_attr "group_overlap" "th,none")])
(define_insn "*pred_madc<mode>_extended_scalar"
[(set (match_operand:<VM> 0 "register_operand" "=vr, &vr")
@@ -3384,7 +3389,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "4")
- (set (attr "avl_type_idx") (const_int 5))])
+ (set (attr "avl_type_idx") (const_int 5))
+ (set_attr "group_overlap" "th,none")])
(define_expand "@pred_msbc<mode>_scalar"
[(set (match_operand:<VM> 0 "register_operand")
@@ -3433,7 +3439,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "4")
- (set (attr "avl_type_idx") (const_int 5))])
+ (set (attr "avl_type_idx") (const_int 5))
+ (set_attr "group_overlap" "th,none")])
(define_insn "*pred_msbc<mode>_extended_scalar"
[(set (match_operand:<VM> 0 "register_operand" "=vr, &vr")
@@ -3454,7 +3461,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "4")
- (set (attr "avl_type_idx") (const_int 5))])
+ (set (attr "avl_type_idx") (const_int 5))
+ (set_attr "group_overlap" "th,none")])
(define_insn "@pred_madc<mode>_overflow"
[(set (match_operand:<VM> 0 "register_operand" "=vr, &vr, &vr")
@@ -3472,7 +3480,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "3")
- (set (attr "avl_type_idx") (const_int 4))])
+ (set (attr "avl_type_idx") (const_int 4))
+ (set_attr "group_overlap" "th,none,none")])
(define_insn "@pred_msbc<mode>_overflow"
[(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr, &vr")
@@ -3490,7 +3499,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "3")
- (set (attr "avl_type_idx") (const_int 4))])
+ (set (attr "avl_type_idx") (const_int 4))
+ (set_attr "group_overlap" "th,th,none,none")])
(define_insn "@pred_madc<mode>_overflow_scalar"
[(set (match_operand:<VM> 0 "register_operand" "=vr, &vr")
@@ -3509,7 +3519,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "3")
- (set (attr "avl_type_idx") (const_int 4))])
+ (set (attr "avl_type_idx") (const_int 4))
+ (set_attr "group_overlap" "th,none")])
(define_insn "@pred_msbc<mode>_overflow_scalar"
[(set (match_operand:<VM> 0 "register_operand" "=vr, &vr")
@@ -3528,7 +3539,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "3")
- (set (attr "avl_type_idx") (const_int 4))])
+ (set (attr "avl_type_idx") (const_int 4))
+ (set_attr "group_overlap" "th,none")])
(define_expand "@pred_madc<mode>_overflow_scalar"
[(set (match_operand:<VM> 0 "register_operand")
@@ -3575,7 +3587,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "3")
- (set (attr "avl_type_idx") (const_int 4))])
+ (set (attr "avl_type_idx") (const_int 4))
+ (set_attr "group_overlap" "th,none")])
(define_insn "*pred_madc<mode>_overflow_extended_scalar"
[(set (match_operand:<VM> 0 "register_operand" "=vr, &vr")
@@ -3595,7 +3608,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "3")
- (set (attr "avl_type_idx") (const_int 4))])
+ (set (attr "avl_type_idx") (const_int 4))
+ (set_attr "group_overlap" "th,none")])
(define_expand "@pred_msbc<mode>_overflow_scalar"
[(set (match_operand:<VM> 0 "register_operand")
@@ -3642,7 +3656,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "3")
- (set (attr "avl_type_idx") (const_int 4))])
+ (set (attr "avl_type_idx") (const_int 4))
+ (set_attr "group_overlap" "th,none")])
(define_insn "*pred_msbc<mode>_overflow_extended_scalar"
[(set (match_operand:<VM> 0 "register_operand" "=vr, &vr")
@@ -3662,7 +3677,8 @@
[(set_attr "type" "vicalu")
(set_attr "mode" "<MODE>")
(set_attr "vl_op_idx" "3")
- (set (attr "avl_type_idx") (const_int 4))])
+ (set (attr "avl_type_idx") (const_int 4))
+ (set_attr "group_overlap" "th,none")])
;; -------------------------------------------------------------------------------
;; ---- Predicated integer unary operations
@@ -3982,7 +3998,8 @@
"TARGET_VECTOR"
"vn<insn>.w%o4\t%0,%3,%v4%p1"
[(set_attr "type" "vnshift")
- (set_attr "mode" "<V_DOUBLE_TRUNC>")])
+ (set_attr "mode" "<V_DOUBLE_TRUNC>")
+ (set_attr "group_overlap" "none,none,th,th,none,th,none,none,none,th,none,none")])
(define_insn "@pred_narrow_<optab><mode>_scalar"
[(set (match_operand:<V_DOUBLE_TRUNC> 0 "register_operand" "=vd, vd, vr, vr, &vr, &vr")
@@ -4003,7 +4020,8 @@
"TARGET_VECTOR"
"vn<insn>.w%o4\t%0,%3,%4%p1"
[(set_attr "type" "vnshift")
- (set_attr "mode" "<V_DOUBLE_TRUNC>")])
+ (set_attr "mode" "<V_DOUBLE_TRUNC>")
+ (set_attr "group_overlap" "none,none,th,th,none,none")])
;; vncvt.x.x.w
(define_insn "@pred_trunc<mode>"
@@ -4027,7 +4045,8 @@
(set_attr "vl_op_idx" "4")
(set (attr "ta") (symbol_ref "riscv_vector::get_ta(operands[5])"))
(set (attr "ma") (symbol_ref "riscv_vector::get_ma(operands[6])"))
- (set (attr "avl_type_idx") (const_int 7))])
+ (set (attr "avl_type_idx") (const_int 7))
+ (set_attr "group_overlap" "none,none,th,th,none,none")])
;; -------------------------------------------------------------------------------
;; ---- Predicated fixed-point operations
@@ -4433,7 +4452,8 @@
"TARGET_VECTOR"
"vnclip<v_su>.w%o4\t%0,%3,%v4%p1"
[(set_attr "type" "vnclip")
- (set_attr "mode" "<V_DOUBLE_TRUNC>")])
+ (set_attr "mode" "<V_DOUBLE_TRUNC>")
+ (set_attr "group_overlap" "th,th,th,th,th,th,none,none,th,th,none,none")])
(define_insn "@pred_narrow_clip<v_su><mode>_scalar"
[(set (match_operand:<V_DOUBLE_TRUNC> 0 "register_operand" "=vd, vd, vr, vr, &vr, &vr")
@@ -4455,7 +4475,8 @@
"TARGET_VECTOR"
"vnclip<v_su>.w%o4\t%0,%3,%4%p1"
[(set_attr "type" "vnclip")
- (set_attr "mode" "<V_DOUBLE_TRUNC>")])
+ (set_attr "mode" "<V_DOUBLE_TRUNC>")
+ (set_attr "group_overlap" "th,th,th,th,none,none")])
;; -------------------------------------------------------------------------------
;; ---- Predicated integer comparison operations
@@ -4506,23 +4527,24 @@
;; We don't use early-clobber for LMUL <= 1 to get better codegen.
(define_insn "*pred_cmp<mode>"
- [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, vr, vr")
+ [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, vr, vr, &vr, &vr, &vr, &vr")
(if_then_else:<VM>
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1,vmWc1")
- (match_operand 6 "vector_length_operand" " rK, rK, rK, rK")
- (match_operand 7 "const_int_operand" " i, i, i, i")
- (match_operand 8 "const_int_operand" " i, i, i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1,vmWc1,vmWc1,vmWc1,vmWc1,vmWc1")
+ (match_operand 6 "vector_length_operand" " rK, rK, rK, rK, rK, rK, rK, rK")
+ (match_operand 7 "const_int_operand" " i, i, i, i, i, i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i, i, i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operator:<VM> 3 "comparison_except_ltge_operator"
- [(match_operand:V_VLSI 4 "register_operand" " vr, vr, vr, vr")
- (match_operand:V_VLSI 5 "vector_arith_operand" " vr, vr, vi, vi")])
- (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu, 0")))]
+ [(match_operand:V_VLSI 4 "register_operand" " vr, vr, vr, vr, vr, vr, vr, vr")
+ (match_operand:V_VLSI 5 "vector_arith_operand" " vr, vr, vi, vi, vr, vr, vi, vi")])
+ (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu, 0, vu, 0, vu, 0")))]
"TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode)"
"vms%B3.v%o5\t%0,%4,%v5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "th,th,th,th,none,none,none,none")])
;; We use early-clobber for source LMUL > dest LMUL.
(define_insn "*pred_cmp<mode>_narrow"
@@ -4542,7 +4564,8 @@
"TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode)"
"vms%B3.v%o5\t%0,%4,%v5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "none,th,th,th,th,th,th,none,none")])
(define_expand "@pred_ltge<mode>"
[(set (match_operand:<VM> 0 "register_operand")
@@ -4586,23 +4609,24 @@
;; We don't use early-clobber for LMUL <= 1 to get better codegen.
(define_insn "*pred_ltge<mode>"
- [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, vr, vr")
+ [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, vr, vr, &vr, &vr")
(if_then_else:<VM>
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1,vmWc1")
- (match_operand 6 "vector_length_operand" " rK, rK, rK, rK")
- (match_operand 7 "const_int_operand" " i, i, i, i")
- (match_operand 8 "const_int_operand" " i, i, i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1,vmWc1,vmWc1,vmWc1")
+ (match_operand 6 "vector_length_operand" " rK, rK, rK, rK, rK, rK")
+ (match_operand 7 "const_int_operand" " i, i, i, i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operator:<VM> 3 "ltge_operator"
- [(match_operand:V_VLSI 4 "register_operand" " vr, vr, vr, vr")
- (match_operand:V_VLSI 5 "vector_neg_arith_operand" " vr, vr, vj, vj")])
- (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu, 0")))]
+ [(match_operand:V_VLSI 4 "register_operand" " vr, vr, vr, vr, vr, vr")
+ (match_operand:V_VLSI 5 "vector_neg_arith_operand" " vr, vr, vj, vj, vr, vj")])
+ (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu, 0, vu, vu")))]
"TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode)"
"vms%B3.v%o5\t%0,%4,%v5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "th,th,th,th,none,none")])
;; We use early-clobber for source LMUL > dest LMUL.
(define_insn "*pred_ltge<mode>_narrow"
@@ -4622,7 +4646,8 @@
"TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode)"
"vms%B3.v%o5\t%0,%4,%v5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "none,th,th,th,th,th,th,none,none")])
(define_expand "@pred_cmp<mode>_scalar"
[(set (match_operand:<VM> 0 "register_operand")
@@ -4668,24 +4693,25 @@
;; We don't use early-clobber for LMUL <= 1 to get better codegen.
(define_insn "*pred_cmp<mode>_scalar"
- [(set (match_operand:<VM> 0 "register_operand" "=vr, vr")
+ [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr")
(if_then_else:<VM>
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 6 "vector_length_operand" " rK, rK")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1")
+ (match_operand 6 "vector_length_operand" " rK, rK, rK")
+ (match_operand 7 "const_int_operand" " i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operator:<VM> 3 "comparison_except_eqge_operator"
- [(match_operand:V_VLSI_QHS 4 "register_operand" " vr, vr")
+ [(match_operand:V_VLSI_QHS 4 "register_operand" " vr, vr, vr")
(vec_duplicate:V_VLSI_QHS
- (match_operand:<VEL> 5 "register_operand" " r, r"))])
- (match_operand:<VM> 2 "vector_merge_operand" " vu, 0")))]
+ (match_operand:<VEL> 5 "register_operand" " r, r, r"))])
+ (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu")))]
"TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode)"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "th,th,none")])
;; We use early-clobber for source LMUL > dest LMUL.
(define_insn "*pred_cmp<mode>_scalar_narrow"
@@ -4706,7 +4732,8 @@
"TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode)"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "none,th,th,none,none")])
(define_expand "@pred_eqne<mode>_scalar"
[(set (match_operand:<VM> 0 "register_operand")
@@ -4752,24 +4779,25 @@
;; We don't use early-clobber for LMUL <= 1 to get better codegen.
(define_insn "*pred_eqne<mode>_scalar"
- [(set (match_operand:<VM> 0 "register_operand" "=vr, vr")
+ [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr")
(if_then_else:<VM>
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 6 "vector_length_operand" " rK, rK")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1")
+ (match_operand 6 "vector_length_operand" " rK, rK, rK")
+ (match_operand 7 "const_int_operand" " i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operator:<VM> 3 "equality_operator"
[(vec_duplicate:V_VLSI_QHS
- (match_operand:<VEL> 5 "register_operand" " r, r"))
- (match_operand:V_VLSI_QHS 4 "register_operand" " vr, vr")])
- (match_operand:<VM> 2 "vector_merge_operand" " vu, 0")))]
+ (match_operand:<VEL> 5 "register_operand" " r, r, r"))
+ (match_operand:V_VLSI_QHS 4 "register_operand" " vr, vr, vr")])
+ (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu")))]
"TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode)"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "th,th,none")])
;; We use early-clobber for source LMUL > dest LMUL.
(define_insn "*pred_eqne<mode>_scalar_narrow"
@@ -4790,7 +4818,8 @@
"TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode)"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "none,th,th,none,none")])
;; Handle GET_MODE_INNER (mode) = DImode. We need to split them since
;; we need to deal with SEW = 64 in RV32 system.
@@ -4917,24 +4946,25 @@
;; We don't use early-clobber for LMUL <= 1 to get better codegen.
(define_insn "*pred_cmp<mode>_scalar"
- [(set (match_operand:<VM> 0 "register_operand" "=vr, vr")
+ [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr")
(if_then_else:<VM>
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 6 "vector_length_operand" " rK, rK")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1")
+ (match_operand 6 "vector_length_operand" " rK, rK, rK")
+ (match_operand 7 "const_int_operand" " i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operator:<VM> 3 "comparison_except_eqge_operator"
- [(match_operand:V_VLSI_D 4 "register_operand" " vr, vr")
+ [(match_operand:V_VLSI_D 4 "register_operand" " vr, vr, vr")
(vec_duplicate:V_VLSI_D
- (match_operand:<VEL> 5 "register_operand" " r, r"))])
- (match_operand:<VM> 2 "vector_merge_operand" " vu, 0")))]
+ (match_operand:<VEL> 5 "register_operand" " r, r, r"))])
+ (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu")))]
"TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode)"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "th,th,none")])
;; We use early-clobber for source LMUL > dest LMUL.
(define_insn "*pred_cmp<mode>_scalar_narrow"
@@ -4955,28 +4985,30 @@
"TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode)"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "none,th,th,none,none")])
;; We don't use early-clobber for LMUL <= 1 to get better codegen.
(define_insn "*pred_eqne<mode>_scalar"
- [(set (match_operand:<VM> 0 "register_operand" "=vr, vr")
+ [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr")
(if_then_else:<VM>
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 6 "vector_length_operand" " rK, rK")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1")
+ (match_operand 6 "vector_length_operand" " rK, rK, rK")
+ (match_operand 7 "const_int_operand" " i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operator:<VM> 3 "equality_operator"
[(vec_duplicate:V_VLSI_D
- (match_operand:<VEL> 5 "register_operand" " r, r"))
- (match_operand:V_VLSI_D 4 "register_operand" " vr, vr")])
- (match_operand:<VM> 2 "vector_merge_operand" " vu, 0")))]
+ (match_operand:<VEL> 5 "register_operand" " r, r, r"))
+ (match_operand:V_VLSI_D 4 "register_operand" " vr, vr, vr")])
+ (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu")))]
"TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode)"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "th,th,none")])
;; We use early-clobber for source LMUL > dest LMUL.
(define_insn "*pred_eqne<mode>_scalar_narrow"
@@ -4997,7 +5029,8 @@
"TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode)"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "none,th,th,none,none")])
(define_insn "*pred_cmp<mode>_extended_scalar_merge_tie_mask"
[(set (match_operand:<VM> 0 "register_operand" "=vm")
@@ -5026,25 +5059,26 @@
;; We don't use early-clobber for LMUL <= 1 to get better codegen.
(define_insn "*pred_cmp<mode>_extended_scalar"
- [(set (match_operand:<VM> 0 "register_operand" "=vr, vr")
+ [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr")
(if_then_else:<VM>
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 6 "vector_length_operand" " rK, rK")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1")
+ (match_operand 6 "vector_length_operand" " rK, rK, rK")
+ (match_operand 7 "const_int_operand" " i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operator:<VM> 3 "comparison_except_eqge_operator"
- [(match_operand:V_VLSI_D 4 "register_operand" " vr, vr")
+ [(match_operand:V_VLSI_D 4 "register_operand" " vr, vr, vr")
(vec_duplicate:V_VLSI_D
(sign_extend:<VEL>
- (match_operand:<VSUBEL> 5 "register_operand" " r, r")))])
- (match_operand:<VM> 2 "vector_merge_operand" " vu, 0")))]
+ (match_operand:<VSUBEL> 5 "register_operand" " r, r, r")))])
+ (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu")))]
"TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode) && !TARGET_64BIT"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "th,th,none")])
(define_insn "*pred_cmp<mode>_extended_scalar_narrow"
[(set (match_operand:<VM> 0 "register_operand" "=vm, vr, vr, &vr, &vr")
@@ -5065,7 +5099,8 @@
"TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode) && !TARGET_64BIT"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "none,th,th,none,none")])
(define_insn "*pred_eqne<mode>_extended_scalar_merge_tie_mask"
[(set (match_operand:<VM> 0 "register_operand" "=vm")
@@ -5094,25 +5129,26 @@
;; We don't use early-clobber for LMUL <= 1 to get better codegen.
(define_insn "*pred_eqne<mode>_extended_scalar"
- [(set (match_operand:<VM> 0 "register_operand" "=vr, vr")
+ [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr")
(if_then_else:<VM>
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 6 "vector_length_operand" " rK, rK")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1")
+ (match_operand 6 "vector_length_operand" " rK, rK, rK")
+ (match_operand 7 "const_int_operand" " i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operator:<VM> 3 "equality_operator"
[(vec_duplicate:V_VLSI_D
(sign_extend:<VEL>
- (match_operand:<VSUBEL> 5 "register_operand" " r, r")))
- (match_operand:V_VLSI_D 4 "register_operand" " vr, vr")])
- (match_operand:<VM> 2 "vector_merge_operand" " vu, 0")))]
+ (match_operand:<VSUBEL> 5 "register_operand" " r, r, r")))
+ (match_operand:V_VLSI_D 4 "register_operand" " vr, vr, vr")])
+ (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu")))]
"TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode) && !TARGET_64BIT"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "th,th,none")])
(define_insn "*pred_eqne<mode>_extended_scalar_narrow"
[(set (match_operand:<VM> 0 "register_operand" "=vm, vr, vr, &vr, &vr")
@@ -5133,7 +5169,8 @@
"TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode) && !TARGET_64BIT"
"vms%B3.vx\t%0,%4,%5%p1"
[(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "none,th,th,none,none")])
;; GE, vmsge.vx/vmsgeu.vx
;;
@@ -7322,23 +7359,24 @@
;; We don't use early-clobber for LMUL <= 1 to get better codegen.
(define_insn "*pred_cmp<mode>"
- [(set (match_operand:<VM> 0 "register_operand" "=vr, vr")
+ [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr, &vr")
(if_then_else:<VM>
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 6 "vector_length_operand" " rK, rK")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1,vmWc1")
+ (match_operand 6 "vector_length_operand" " rK, rK, rK, rK")
+ (match_operand 7 "const_int_operand" " i, i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operator:<VM> 3 "signed_order_operator"
- [(match_operand:V_VLSF 4 "register_operand" " vr, vr")
- (match_operand:V_VLSF 5 "register_operand" " vr, vr")])
- (match_operand:<VM> 2 "vector_merge_operand" " vu, 0")))]
+ [(match_operand:V_VLSF 4 "register_operand" " vr, vr, vr, vr")
+ (match_operand:V_VLSF 5 "register_operand" " vr, vr, vr, vr")])
+ (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu, 0")))]
"TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode)"
"vmf%B3.vv\t%0,%4,%5%p1"
[(set_attr "type" "vfcmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "th,th,none,none")])
(define_insn "*pred_cmp<mode>_narrow_merge_tie_mask"
[(set (match_operand:<VM> 0 "register_operand" "=vm")
@@ -7381,7 +7419,8 @@
"TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode)"
"vmf%B3.vv\t%0,%4,%5%p1"
[(set_attr "type" "vfcmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "none,th,th,th,th,th,th,none,none")])
(define_expand "@pred_cmp<mode>_scalar"
[(set (match_operand:<VM> 0 "register_operand")
@@ -7427,24 +7466,25 @@
;; We don't use early-clobber for LMUL <= 1 to get better codegen.
(define_insn "*pred_cmp<mode>_scalar"
- [(set (match_operand:<VM> 0 "register_operand" "=vr, vr")
+ [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr")
(if_then_else:<VM>
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 6 "vector_length_operand" " rK, rK")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1")
+ (match_operand 6 "vector_length_operand" " rK, rK, rK")
+ (match_operand 7 "const_int_operand" " i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operator:<VM> 3 "signed_order_operator"
- [(match_operand:V_VLSF 4 "register_operand" " vr, vr")
+ [(match_operand:V_VLSF 4 "register_operand" " vr, vr, vr")
(vec_duplicate:V_VLSF
- (match_operand:<VEL> 5 "register_operand" " f, f"))])
- (match_operand:<VM> 2 "vector_merge_operand" " vu, 0")))]
+ (match_operand:<VEL> 5 "register_operand" " f, f, f"))])
+ (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu")))]
"TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode)"
"vmf%B3.vf\t%0,%4,%5%p1"
[(set_attr "type" "vfcmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "th,th,none")])
;; We use early-clobber for source LMUL > dest LMUL.
(define_insn "*pred_cmp<mode>_scalar_narrow"
@@ -7465,7 +7505,8 @@
"TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode)"
"vmf%B3.vf\t%0,%4,%5%p1"
[(set_attr "type" "vfcmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "none,th,th,none,none")])
(define_expand "@pred_eqne<mode>_scalar"
[(set (match_operand:<VM> 0 "register_operand")
@@ -7511,24 +7552,25 @@
;; We don't use early-clobber for LMUL <= 1 to get better codegen.
(define_insn "*pred_eqne<mode>_scalar"
- [(set (match_operand:<VM> 0 "register_operand" "=vr, vr")
+ [(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr")
(if_then_else:<VM>
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 6 "vector_length_operand" " rK, rK")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1")
+ (match_operand 6 "vector_length_operand" " rK, rK, rK")
+ (match_operand 7 "const_int_operand" " i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operator:<VM> 3 "equality_operator"
[(vec_duplicate:V_VLSF
- (match_operand:<VEL> 5 "register_operand" " f, f"))
- (match_operand:V_VLSF 4 "register_operand" " vr, vr")])
- (match_operand:<VM> 2 "vector_merge_operand" " vu, 0")))]
+ (match_operand:<VEL> 5 "register_operand" " f, f, f"))
+ (match_operand:V_VLSF 4 "register_operand" " vr, vr, vr")])
+ (match_operand:<VM> 2 "vector_merge_operand" " vu, 0, vu")))]
"TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode)"
"vmf%B3.vf\t%0,%4,%5%p1"
[(set_attr "type" "vfcmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "th,th,none")])
;; We use early-clobber for source LMUL > dest LMUL.
(define_insn "*pred_eqne<mode>_scalar_narrow"
@@ -7549,7 +7591,8 @@
"TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode)"
"vmf%B3.vf\t%0,%4,%5%p1"
[(set_attr "type" "vfcmp")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "none,th,th,none,none")])
;; -------------------------------------------------------------------------------
;; ---- Predicated floating-point merge
@@ -7769,7 +7812,8 @@
[(set_attr "type" "vfncvtftoi")
(set_attr "mode" "<VNCONVERT>")
(set (attr "frm_mode")
- (symbol_ref "riscv_vector::get_frm_mode (operands[8])"))])
+ (symbol_ref "riscv_vector::get_frm_mode (operands[8])"))
+ (set_attr "group_overlap" "none,none,th,th,none,none")])
(define_insn "@pred_narrow_<fix_cvt><mode>"
[(set (match_operand:<VNCONVERT> 0 "register_operand" "=vd, vd, vr, vr, &vr, &vr")
@@ -7811,7 +7855,8 @@
[(set_attr "type" "vfncvtitof")
(set_attr "mode" "<VNCONVERT>")
(set (attr "frm_mode")
- (symbol_ref "riscv_vector::get_frm_mode (operands[8])"))])
+ (symbol_ref "riscv_vector::get_frm_mode (operands[8])"))
+ (set_attr "group_overlap" "none,none,th,th,none,none")])
(define_insn "@pred_trunc<mode>"
[(set (match_operand:<V_DOUBLE_TRUNC> 0 "register_operand" "=vd, vd, vr, vr, &vr, &vr")
@@ -7834,7 +7879,8 @@
[(set_attr "type" "vfncvtftof")
(set_attr "mode" "<V_DOUBLE_TRUNC>")
(set (attr "frm_mode")
- (symbol_ref "riscv_vector::get_frm_mode (operands[8])"))])
+ (symbol_ref "riscv_vector::get_frm_mode (operands[8])"))
+ (set_attr "group_overlap" "none,none,th,th,none,none")])
(define_insn "@pred_rod_trunc<mode>"
[(set (match_operand:<V_DOUBLE_TRUNC> 0 "register_operand" "=vd, vd, vr, vr, &vr, &vr")