@@ -31,8 +31,8 @@
(match_operand 3 "const_0_operand")]
"TARGET_VECTOR"
{
- riscv_vector::emit_len_op (code_for_pred_mov (<MODE>mode), operands[0],
- operands[1], operands[2], <VM>mode);
+ riscv_vector::emit_nonvlmax_tany_many (code_for_pred_mov (<MODE>mode),
+ RVV_UNOP_NUM, operands);
DONE;
})
@@ -43,8 +43,8 @@
(match_operand 3 "const_0_operand")]
"TARGET_VECTOR"
{
- riscv_vector::emit_len_op (code_for_pred_mov (<MODE>mode), operands[0],
- operands[1], operands[2], <VM>mode);
+ riscv_vector::emit_nonvlmax_tany_many (code_for_pred_mov (<MODE>mode),
+ RVV_UNOP_NUM, operands);
DONE;
})
@@ -118,21 +118,8 @@
(match_operand:VI 2 "<binop_rhs2_predicate>")))]
"TARGET_VECTOR"
{
- if (!register_operand (operands[2], <MODE>mode))
- {
- rtx cst;
- gcc_assert (const_vec_duplicate_p(operands[2], &cst));
- riscv_vector::emit_len_binop (code_for_pred_scalar
- (<CODE>, <MODE>mode),
- operands[0], operands[1], cst,
- NULL, <VM>mode,
- <VEL>mode);
- }
- else
- riscv_vector::emit_len_binop (code_for_pred
- (<CODE>, <MODE>mode),
- operands[0], operands[1], operands[2],
- NULL, <VM>mode);
+ riscv_vector::emit_vlmax_tany_many (code_for_pred (<CODE>, <MODE>mode),
+ RVV_BINOP_NUM, operands);
DONE;
})
@@ -151,12 +138,9 @@
(match_operand:<VEL> 2 "csr_operand")))]
"TARGET_VECTOR"
{
- if (!CONST_SCALAR_INT_P (operands[2]))
- operands[2] = gen_lowpart (Pmode, operands[2]);
- riscv_vector::emit_len_binop (code_for_pred_scalar
- (<CODE>, <MODE>mode),
- operands[0], operands[1], operands[2],
- NULL_RTX, <VM>mode, Pmode);
+ operands[2] = gen_lowpart (Pmode, operands[2]);
+ riscv_vector::emit_vlmax_tany_many (code_for_pred_scalar (<CODE>, <MODE>mode),
+ RVV_BINOP_NUM, operands);
DONE;
})
@@ -174,9 +158,7 @@
(match_operand:VI 2 "vector_shift_operand")))]
"TARGET_VECTOR"
{
- riscv_vector::emit_len_binop (code_for_pred
- (<CODE>, <MODE>mode),
- operands[0], operands[1], operands[2],
- NULL_RTX, <VM>mode);
+ riscv_vector::emit_vlmax_tany_many (code_for_pred (<CODE>, <MODE>mode),
+ RVV_BINOP_NUM, operands);
DONE;
})
@@ -132,6 +132,9 @@ namespace riscv_vector {
#define RVV_VUNDEF(MODE) \
gen_rtx_UNSPEC (MODE, gen_rtvec (1, gen_rtx_REG (SImode, X0_REGNUM)), \
UNSPEC_VUNDEF)
+#define RVV_MISC_OP_NUM 1
+#define RVV_UNOP_NUM 2
+#define RVV_BINOP_NUM 3
enum vlmul_type
{
LMUL_1 = 0,
@@ -163,14 +166,11 @@ rtx expand_builtin (unsigned int, tree, rtx);
bool check_builtin_call (location_t, vec<location_t>, unsigned int,
tree, unsigned int, tree *);
bool const_vec_all_same_in_range_p (rtx, HOST_WIDE_INT, HOST_WIDE_INT);
-bool legitimize_move (rtx, rtx, machine_mode);
+bool legitimize_move (rtx, rtx);
void emit_vlmax_vsetvl (machine_mode, rtx);
void emit_hard_vlmax_vsetvl (machine_mode, rtx);
-void emit_vlmax_op (unsigned, rtx, rtx, machine_mode);
-void emit_vlmax_reg_op (unsigned, rtx, rtx, rtx, machine_mode);
-void emit_len_op (unsigned, rtx, rtx, rtx, machine_mode);
-void emit_len_binop (unsigned, rtx, rtx, rtx, rtx, machine_mode,
- machine_mode = VOIDmode);
+void emit_vlmax_tany_many (unsigned, int, rtx *);
+void emit_nonvlmax_tany_many (unsigned, int, rtx *);
enum vlmul_type get_vlmul (machine_mode);
unsigned int get_ratio (machine_mode);
unsigned int get_nf (machine_mode);
@@ -202,7 +202,7 @@ bool neg_simm5_p (rtx);
#ifdef RTX_CODE
bool has_vi_variant_p (rtx_code, rtx);
#endif
-bool sew64_scalar_helper (rtx *, rtx *, rtx, machine_mode, machine_mode,
+bool sew64_scalar_helper (rtx *, rtx *, rtx, machine_mode,
bool, void (*)(rtx *, rtx));
rtx gen_scalar_move_mask (machine_mode);
@@ -218,7 +218,7 @@ enum vlen_enum
bool slide1_sew64_helper (int, machine_mode, machine_mode,
machine_mode, rtx *);
rtx gen_avl_for_scalar_move (rtx);
-void expand_tuple_move (machine_mode, rtx *);
+void expand_tuple_move (rtx *);
machine_mode preferred_simd_mode (scalar_mode);
opt_machine_mode get_mask_mode (machine_mode);
void expand_vec_series (rtx, rtx, rtx);
@@ -66,7 +66,29 @@ const_vlmax_p (machine_mode mode)
template <int MAX_OPERANDS> class insn_expander
{
public:
- insn_expander () : m_opno (0), m_has_dest_p(false) {}
+ insn_expander ()
+ : m_opno (0), m_op_num (0), m_has_dest_p (false),
+ m_use_all_trues_mask_p (false), m_use_undef_merge_p (false),
+ m_has_avl_p (false), m_vlmax_p (false), m_has_tail_policy_p (false),
+ m_has_mask_policy_p (false), m_tail_policy (TAIL_ANY),
+ m_mask_policy (MASK_ANY), m_dest_mode (VOIDmode), m_mask_mode (VOIDmode)
+ {}
+
+ /* Initializer for various configurations. */
+ insn_expander (int op_num, bool has_dest_p, bool use_all_trues_mask_p,
+ bool use_undef_merge_p, bool has_avl_p, bool vlmax_p,
+ bool has_tail_policy_p, bool has_mask_policy_p,
+ enum tail_policy tail_policy, enum mask_policy mask_policy,
+ machine_mode dest_mode, machine_mode mask_mode)
+ : m_opno (0), m_op_num (op_num), m_has_dest_p (has_dest_p),
+ m_use_all_trues_mask_p (use_all_trues_mask_p),
+ m_use_undef_merge_p (use_undef_merge_p), m_has_avl_p (has_avl_p),
+ m_vlmax_p (vlmax_p), m_has_tail_policy_p (has_tail_policy_p),
+ m_has_mask_policy_p (has_mask_policy_p), m_tail_policy (tail_policy),
+ m_mask_policy (mask_policy), m_dest_mode (dest_mode),
+ m_mask_mode (mask_mode)
+ {}
+
void add_output_operand (rtx x, machine_mode mode)
{
create_output_operand (&m_ops[m_opno++], x, mode);
@@ -77,67 +99,94 @@ public:
create_input_operand (&m_ops[m_opno++], x, mode);
gcc_assert (m_opno <= MAX_OPERANDS);
}
- void add_all_one_mask_operand (machine_mode mode)
+ void add_all_one_mask_operand ()
{
- add_input_operand (CONSTM1_RTX (mode), mode);
+ add_input_operand (CONSTM1_RTX (m_mask_mode), m_mask_mode);
}
- void add_vundef_operand (machine_mode mode)
+ void add_vundef_operand ()
{
- add_input_operand (RVV_VUNDEF (mode), mode);
+ add_input_operand (RVV_VUNDEF (m_dest_mode), m_dest_mode);
}
- void add_policy_operand (enum tail_policy vta, enum mask_policy vma)
+ void add_policy_operand ()
{
- rtx tail_policy_rtx = gen_int_mode (vta, Pmode);
- rtx mask_policy_rtx = gen_int_mode (vma, Pmode);
- add_input_operand (tail_policy_rtx, Pmode);
- add_input_operand (mask_policy_rtx, Pmode);
+ if (m_has_tail_policy_p)
+ {
+ rtx tail_policy_rtx = gen_int_mode (m_tail_policy, Pmode);
+ add_input_operand (tail_policy_rtx, Pmode);
+ }
+ if (m_has_mask_policy_p)
+ {
+ rtx mask_policy_rtx = gen_int_mode (m_mask_policy, Pmode);
+ add_input_operand (mask_policy_rtx, Pmode);
+ }
}
void add_avl_type_operand (avl_type type)
{
add_input_operand (gen_int_mode (type, Pmode), Pmode);
}
- void set_dest_and_mask (rtx mask, rtx dest, machine_mode mask_mode)
+ void emit_insn (enum insn_code icode, rtx *ops)
{
- m_dest_mode = GET_MODE (dest);
- m_has_dest_p = true;
-
- add_output_operand (dest, m_dest_mode);
-
- if (mask)
- add_input_operand (mask, GET_MODE (mask));
- else
- add_all_one_mask_operand (mask_mode);
-
- add_vundef_operand (m_dest_mode);
- }
+ int opno = 0;
+ /* It's true if any operand is memory operand. */
+ bool any_mem_p = false;
+ /* It's true if all operands are mask operand. */
+ bool all_mask_p = true;
+ if (m_has_dest_p)
+ {
+ any_mem_p |= MEM_P (ops[opno]);
+ all_mask_p &= GET_MODE_CLASS (GET_MODE (ops[opno])) == MODE_VECTOR_BOOL;
+ add_output_operand (ops[opno++], m_dest_mode);
+ }
- void set_len_and_policy (rtx len, bool force_vlmax = false)
- {
- bool vlmax_p = force_vlmax || !len;
- gcc_assert (m_has_dest_p);
+ if (m_use_all_trues_mask_p)
+ add_all_one_mask_operand ();
- if (vlmax_p && const_vlmax_p (m_dest_mode))
- {
- /* Optimize VLS-VLMAX code gen, we can use vsetivli instead of the
- vsetvli to obtain the value of vlmax. */
- poly_uint64 nunits = GET_MODE_NUNITS (m_dest_mode);
- len = gen_int_mode (nunits, Pmode);
- vlmax_p = false; /* It has became NONVLMAX now. */
- }
- else if (!len)
- {
- len = gen_reg_rtx (Pmode);
- emit_vlmax_vsetvl (m_dest_mode, len);
- }
+ if (m_use_undef_merge_p)
+ add_vundef_operand ();
- add_input_operand (len, Pmode);
+ for (; opno < m_op_num; opno++)
+ {
+ any_mem_p |= MEM_P (ops[opno]);
+ all_mask_p &= GET_MODE_CLASS (GET_MODE (ops[opno])) == MODE_VECTOR_BOOL;
+ machine_mode mode = insn_data[(int) icode].operand[m_opno].mode;
+ /* 'create_input_operand doesn't allow VOIDmode.
+ According to vector.md, we may have some patterns that do not have
+ explicit machine mode specifying the operand. Such operands are
+ always Pmode. */
+ if (mode == VOIDmode)
+ mode = Pmode;
+ add_input_operand (ops[opno], mode);
+ }
- if (GET_MODE_CLASS (m_dest_mode) != MODE_VECTOR_BOOL)
- add_policy_operand (get_prefer_tail_policy (), get_prefer_mask_policy ());
+ if (m_has_avl_p)
+ {
+ rtx len = ops[m_op_num];
+ if (m_vlmax_p)
+ {
+ if (const_vlmax_p (m_dest_mode))
+ {
+ /* Optimize VLS-VLMAX code gen, we can use vsetivli instead of
+ the vsetvli to obtain the value of vlmax. */
+ poly_uint64 nunits = GET_MODE_NUNITS (m_dest_mode);
+ len = gen_int_mode (nunits, Pmode);
+ m_vlmax_p = false; /* It has became NONVLMAX now. */
+ }
+ else if (can_create_pseudo_p ())
+ {
+ len = gen_reg_rtx (Pmode);
+ emit_vlmax_vsetvl (m_dest_mode, len);
+ }
+ }
+ add_input_operand (len, Pmode);
+ }
- add_avl_type_operand (vlmax_p ? avl_type::VLMAX : avl_type::NONVLMAX);
- }
+ if (!all_mask_p)
+ add_policy_operand ();
+ if (m_has_avl_p)
+ add_avl_type_operand (m_vlmax_p ? avl_type::VLMAX : avl_type::NONVLMAX);
+ expand (icode, any_mem_p);
+ }
void expand (enum insn_code icode, bool temporary_volatile_p = false)
{
@@ -152,8 +201,23 @@ public:
private:
int m_opno;
+ int m_op_num;
+ /* It't true when the pattern has a dest operand. Most of the patterns have
+ dest operand wheras some patterns like STOREs does not have dest operand.
+ */
bool m_has_dest_p;
+ /* It't true if the pattern uses all trues mask operand. */
+ bool m_use_all_trues_mask_p;
+ /* It's true if the pattern uses undefined merge operand. */
+ bool m_use_undef_merge_p;
+ bool m_has_avl_p;
+ bool m_vlmax_p;
+ bool m_has_tail_policy_p;
+ bool m_has_mask_policy_p;
+ enum tail_policy m_tail_policy;
+ enum mask_policy m_mask_policy;
machine_mode m_dest_mode;
+ machine_mode m_mask_mode;
expand_operand m_ops[MAX_OPERANDS];
};
@@ -246,49 +310,6 @@ autovec_use_vlmax_p (void)
|| riscv_autovec_preference == RVV_FIXED_VLMAX);
}
-/* Emit an RVV unmask && vl mov from SRC to DEST. */
-static void
-emit_pred_op (unsigned icode, rtx mask, rtx dest, rtx src, rtx len,
- machine_mode mask_mode, bool force_vlmax = false)
-{
- insn_expander<8> e;
- e.set_dest_and_mask (mask, dest, mask_mode);
-
- e.add_input_operand (src, GET_MODE (src));
-
- e.set_len_and_policy (len, force_vlmax);
-
- e.expand ((enum insn_code) icode, MEM_P (dest) || MEM_P (src));
-}
-
-/* Emit an RVV binop. If one of SRC1 and SRC2 is a scalar operand, its mode is
- specified using SCALAR_MODE. */
-static void
-emit_pred_binop (unsigned icode, rtx mask, rtx dest, rtx src1, rtx src2,
- rtx len, machine_mode mask_mode,
- machine_mode scalar_mode = VOIDmode)
-{
- insn_expander<9> e;
- e.set_dest_and_mask (mask, dest, mask_mode);
-
- gcc_assert (VECTOR_MODE_P (GET_MODE (src1))
- || VECTOR_MODE_P (GET_MODE (src2)));
-
- if (VECTOR_MODE_P (GET_MODE (src1)))
- e.add_input_operand (src1, GET_MODE (src1));
- else
- e.add_input_operand (src1, scalar_mode);
-
- if (VECTOR_MODE_P (GET_MODE (src2)))
- e.add_input_operand (src2, GET_MODE (src2));
- else
- e.add_input_operand (src2, scalar_mode);
-
- e.set_len_and_policy (len);
-
- e.expand ((enum insn_code) icode, MEM_P (dest) || MEM_P (src1) || MEM_P (src2));
-}
-
/* The RISC-V vsetvli pass uses "known vlmax" operations for optimization.
Whether or not an instruction actually is a vlmax operation is not
recognizable from the length operand alone but the avl_type operand
@@ -305,52 +326,42 @@ emit_pred_binop (unsigned icode, rtx mask, rtx dest, rtx src1, rtx src2,
For that case we also allow to set the avl_type to VLMAX.
*/
-/* This function emits a VLMAX vsetvli followed by the actual operation. */
+/* This function emits a {VLMAX, TAIL_ANY, MASK_ANY} vsetvli followed by the
+ * actual operation. */
void
-emit_vlmax_op (unsigned icode, rtx dest, rtx src, machine_mode mask_mode)
+emit_vlmax_tany_many (unsigned icode, int op_num, rtx *ops)
{
- emit_pred_op (icode, NULL_RTX, dest, src, NULL_RTX, mask_mode);
+ machine_mode data_mode = GET_MODE (ops[0]);
+ machine_mode mask_mode = get_mask_mode (data_mode).require ();
+ /* The number = 11 is because we have maximum 11 operands for
+ RVV instruction patterns according to vector.md. */
+ insn_expander<11> e (/*OP_NUM*/ op_num, /*HAS_DEST_P*/ true,
+ /*USE_ALL_TRUES_MASK_P*/ true,
+ /*USE_UNDEF_MERGE_P*/ true, /*HAS_AVL_P*/ true,
+ /*VLMAX_P*/ true,
+ /*HAS_TAIL_POLICY_P*/ true, /*HAS_MASK_POLICY_P*/ true,
+ /*TAIL_POLICY*/ TAIL_ANY, /*MASK_POLICY*/ MASK_ANY,
+ /*DEST_MODE*/ data_mode, /*MASK_MODE*/ mask_mode);
+ e.emit_insn ((enum insn_code) icode, ops);
}
-/* This function emits an operation with a given LEN that is determined
- by a previously emitted VLMAX vsetvli. */
+/* This function emits a {NONVLMAX, TAIL_ANY, MASK_ANY} vsetvli followed by the
+ * actual operation. */
void
-emit_len_op (unsigned icode, rtx dest, rtx src, rtx len,
- machine_mode mask_mode)
+emit_nonvlmax_tany_many (unsigned icode, int op_num, rtx *ops)
{
- emit_pred_op (icode, NULL_RTX, dest, src, len, mask_mode);
-}
-
-/* This function emits an operation with a given LEN that is known to be
- a preceding VLMAX. It also sets the VLMAX flag which allows further
- optimization in the vsetvli pass. */
-void
-emit_vlmax_reg_op (unsigned icode, rtx dest, rtx src, rtx len,
- machine_mode mask_mode)
-{
- emit_pred_op (icode, NULL_RTX, dest, src, len, mask_mode,
- /* Force VLMAX */ true);
-}
-
-void
-emit_len_binop (unsigned icode, rtx dest, rtx src1, rtx src2, rtx len,
- machine_mode mask_mode, machine_mode scalar_mode)
-{
- emit_pred_binop (icode, NULL_RTX, dest, src1, src2, len,
- mask_mode, scalar_mode);
-}
-
-/* Emit vid.v instruction. */
-
-static void
-emit_index_op (rtx dest, machine_mode mask_mode)
-{
- insn_expander<7> e;
- e.set_dest_and_mask (NULL, dest, mask_mode);
-
- e.set_len_and_policy (NULL, true);
-
- e.expand (code_for_pred_series (GET_MODE (dest)), false);
+ machine_mode data_mode = GET_MODE (ops[0]);
+ machine_mode mask_mode = get_mask_mode (data_mode).require ();
+ /* The number = 11 is because we have maximum 11 operands for
+ RVV instruction patterns according to vector.md. */
+ insn_expander<11> e (/*OP_NUM*/ op_num, /*HAS_DEST_P*/ true,
+ /*USE_ALL_TRUES_MASK_P*/ true,
+ /*USE_UNDEF_MERGE_P*/ true, /*HAS_AVL_P*/ true,
+ /*VLMAX_P*/ false,
+ /*HAS_TAIL_POLICY_P*/ true, /*HAS_MASK_POLICY_P*/ true,
+ /*TAIL_POLICY*/ TAIL_ANY, /*MASK_POLICY*/ MASK_ANY,
+ /*DEST_MODE*/ data_mode, /*MASK_MODE*/ mask_mode);
+ e.emit_insn ((enum insn_code) icode, ops);
}
/* Expand series const vector. */
@@ -359,7 +370,6 @@ void
expand_vec_series (rtx dest, rtx base, rtx step)
{
machine_mode mode = GET_MODE (dest);
- machine_mode inner_mode = GET_MODE_INNER (mode);
machine_mode mask_mode;
gcc_assert (get_mask_mode (mode).exists (&mask_mode));
@@ -367,7 +377,8 @@ expand_vec_series (rtx dest, rtx base, rtx step)
/* Step 1: Generate I = { 0, 1, 2, ... } by vid.v. */
rtx vid = gen_reg_rtx (mode);
- emit_index_op (vid, mask_mode);
+ rtx op[1] = {vid};
+ emit_vlmax_tany_many (code_for_pred_series (mode), RVV_MISC_OP_NUM, op);
/* Step 2: Generate I * STEP.
- STEP is 1, we don't emit any instructions.
@@ -385,14 +396,14 @@ expand_vec_series (rtx dest, rtx base, rtx step)
int shift = exact_log2 (INTVAL (step));
rtx shift_amount = gen_int_mode (shift, Pmode);
insn_code icode = code_for_pred_scalar (ASHIFT, mode);
- emit_len_binop (icode, step_adj, vid, shift_amount,
- NULL, mask_mode, Pmode);
+ rtx ops[3] = {step_adj, vid, shift_amount};
+ emit_vlmax_tany_many (icode, RVV_BINOP_NUM, ops);
}
else
{
insn_code icode = code_for_pred_scalar (MULT, mode);
- emit_len_binop (icode, step_adj, vid, step,
- NULL, mask_mode, inner_mode);
+ rtx ops[3] = {step_adj, vid, step};
+ emit_vlmax_tany_many (icode, RVV_BINOP_NUM, ops);
}
}
@@ -407,14 +418,14 @@ expand_vec_series (rtx dest, rtx base, rtx step)
{
rtx result = gen_reg_rtx (mode);
insn_code icode = code_for_pred_scalar (PLUS, mode);
- emit_len_binop (icode, result, step_adj, base,
- NULL, mask_mode, inner_mode);
+ rtx ops[3] = {result, step_adj, base};
+ emit_vlmax_tany_many (icode, RVV_BINOP_NUM, ops);
emit_move_insn (dest, result);
}
}
static void
-expand_const_vector (rtx target, rtx src, machine_mode mask_mode)
+expand_const_vector (rtx target, rtx src)
{
machine_mode mode = GET_MODE (target);
scalar_mode elt_mode = GET_MODE_INNER (mode);
@@ -424,7 +435,8 @@ expand_const_vector (rtx target, rtx src, machine_mode mask_mode)
gcc_assert (
const_vec_duplicate_p (src, &elt)
&& (rtx_equal_p (elt, const0_rtx) || rtx_equal_p (elt, const1_rtx)));
- emit_vlmax_op (code_for_pred_mov (mode), target, src, mask_mode);
+ rtx ops[2] = {target, src};
+ emit_vlmax_tany_many (code_for_pred_mov (mode), RVV_UNOP_NUM, ops);
return;
}
@@ -435,10 +447,16 @@ expand_const_vector (rtx target, rtx src, machine_mode mask_mode)
/* Element in range -16 ~ 15 integer or 0.0 floating-point,
we use vmv.v.i instruction. */
if (satisfies_constraint_vi (src) || satisfies_constraint_Wc0 (src))
- emit_vlmax_op (code_for_pred_mov (mode), tmp, src, mask_mode);
+ {
+ rtx ops[2] = {tmp, src};
+ emit_vlmax_tany_many (code_for_pred_mov (mode), RVV_UNOP_NUM, ops);
+ }
else
- emit_vlmax_op (code_for_pred_broadcast (mode), tmp,
- force_reg (elt_mode, elt), mask_mode);
+ {
+ elt = force_reg (elt_mode, elt);
+ rtx ops[2] = {tmp, elt};
+ emit_vlmax_tany_many (code_for_pred_broadcast (mode), RVV_UNOP_NUM, ops);
+ }
if (tmp != target)
emit_move_insn (target, tmp);
@@ -463,12 +481,12 @@ expand_const_vector (rtx target, rtx src, machine_mode mask_mode)
/* Expand a pre-RA RVV data move from SRC to DEST.
It expands move for RVV fractional vector modes. */
bool
-legitimize_move (rtx dest, rtx src, machine_mode mask_mode)
+legitimize_move (rtx dest, rtx src)
{
machine_mode mode = GET_MODE (dest);
if (CONST_VECTOR_P (src))
{
- expand_const_vector (dest, src, mask_mode);
+ expand_const_vector (dest, src);
return true;
}
@@ -505,7 +523,10 @@ legitimize_move (rtx dest, rtx src, machine_mode mask_mode)
{
rtx tmp = gen_reg_rtx (mode);
if (MEM_P (src))
- emit_vlmax_op (code_for_pred_mov (mode), tmp, src, mask_mode);
+ {
+ rtx ops[2] = {tmp, src};
+ emit_vlmax_tany_many (code_for_pred_mov (mode), RVV_UNOP_NUM, ops);
+ }
else
emit_move_insn (tmp, src);
src = tmp;
@@ -514,7 +535,8 @@ legitimize_move (rtx dest, rtx src, machine_mode mask_mode)
if (satisfies_constraint_vu (src))
return false;
- emit_vlmax_op (code_for_pred_mov (mode), dest, src, mask_mode);
+ rtx ops[2] = {dest, src};
+ emit_vlmax_tany_many (code_for_pred_mov (mode), RVV_UNOP_NUM, ops);
return true;
}
@@ -748,8 +770,7 @@ has_vi_variant_p (rtx_code code, rtx x)
bool
sew64_scalar_helper (rtx *operands, rtx *scalar_op, rtx vl,
- machine_mode vector_mode, machine_mode mask_mode,
- bool has_vi_variant_p,
+ machine_mode vector_mode, bool has_vi_variant_p,
void (*emit_vector_func) (rtx *, rtx))
{
machine_mode scalar_mode = GET_MODE_INNER (vector_mode);
@@ -779,8 +800,9 @@ sew64_scalar_helper (rtx *operands, rtx *scalar_op, rtx vl,
*scalar_op = force_reg (scalar_mode, *scalar_op);
rtx tmp = gen_reg_rtx (vector_mode);
- riscv_vector::emit_len_op (code_for_pred_broadcast (vector_mode), tmp,
- *scalar_op, vl, mask_mode);
+ rtx ops[3] = {tmp, *scalar_op, vl};
+ riscv_vector::emit_nonvlmax_tany_many (code_for_pred_broadcast (vector_mode),
+ RVV_UNOP_NUM, ops);
emit_vector_func (operands, tmp);
return true;
@@ -990,7 +1012,7 @@ gen_avl_for_scalar_move (rtx avl)
/* Expand tuple modes data movement for. */
void
-expand_tuple_move (machine_mode mask_mode, rtx *ops)
+expand_tuple_move (rtx *ops)
{
unsigned int i;
machine_mode tuple_mode = GET_MODE (ops[0]);
@@ -1086,8 +1108,11 @@ expand_tuple_move (machine_mode mask_mode, rtx *ops)
rtx mem = gen_rtx_MEM (subpart_mode, ops[3]);
if (fractional_p)
- emit_vlmax_reg_op (code_for_pred_mov (subpart_mode), subreg, mem,
- ops[4], mask_mode);
+ {
+ rtx operands[3] = {subreg, mem, ops[4]};
+ emit_vlmax_tany_many (code_for_pred_mov (subpart_mode),
+ RVV_UNOP_NUM, operands);
+ }
else
emit_move_insn (subreg, mem);
}
@@ -1108,8 +1133,11 @@ expand_tuple_move (machine_mode mask_mode, rtx *ops)
rtx mem = gen_rtx_MEM (subpart_mode, ops[3]);
if (fractional_p)
- emit_vlmax_reg_op (code_for_pred_mov (subpart_mode), mem, subreg,
- ops[4], mask_mode);
+ {
+ rtx operands[3] = {mem, subreg, ops[4]};
+ emit_vlmax_tany_many (code_for_pred_mov (subpart_mode),
+ RVV_UNOP_NUM, operands);
+ }
else
emit_move_insn (mem, subreg);
}
@@ -1230,7 +1258,6 @@ expand_vector_init_insert_elems (rtx target, const rvv_builder &builder,
int nelts_reqd)
{
machine_mode mode = GET_MODE (target);
- scalar_mode elem_mode = GET_MODE_INNER (mode);
machine_mode mask_mode;
gcc_assert (get_mask_mode (mode).exists (&mask_mode));
rtx dup = expand_vector_broadcast (mode, builder.elt (0));
@@ -1241,8 +1268,8 @@ expand_vector_init_insert_elems (rtx target, const rvv_builder &builder,
unsigned int unspec
= FLOAT_MODE_P (mode) ? UNSPEC_VFSLIDE1DOWN : UNSPEC_VSLIDE1DOWN;
insn_code icode = code_for_pred_slide (unspec, mode);
- emit_len_binop (icode, target, target, builder.elt (i), NULL, mask_mode,
- elem_mode);
+ rtx ops[3] = {target, target, builder.elt (i)};
+ emit_vlmax_tany_many (icode, RVV_BINOP_NUM, ops);
}
}
@@ -7389,9 +7389,6 @@ vector_zero_call_used_regs (HARD_REG_SET need_zeroed_hardregs)
{
rtx target = regno_reg_rtx[regno];
machine_mode mode = GET_MODE (target);
- poly_uint16 nunits = GET_MODE_NUNITS (mode);
- machine_mode mask_mode
- = riscv_vector::get_vector_mode (BImode, nunits).require ();
if (!emitted_vlmax_vsetvl)
{
@@ -7399,8 +7396,9 @@ vector_zero_call_used_regs (HARD_REG_SET need_zeroed_hardregs)
emitted_vlmax_vsetvl = true;
}
- riscv_vector::emit_vlmax_reg_op (code_for_pred_mov (mode), target,
- CONST0_RTX (mode), vl, mask_mode);
+ rtx ops[3] = {target, CONST0_RTX (mode), vl};
+ riscv_vector::emit_vlmax_tany_many (code_for_pred_mov (mode),
+ RVV_UNOP_NUM, ops);
SET_HARD_REG_BIT (zeroed_hardregs, regno);
}
@@ -662,7 +662,7 @@
before spilling. The clobber scratch is used by spilling fractional
registers in IRA/LRA so it's too early. */
- if (riscv_vector::legitimize_move (operands[0], operands[1], <VM>mode))
+ if (riscv_vector::legitimize_move (operands[0], operands[1]))
DONE;
})
@@ -718,7 +718,7 @@
(match_operand:VB 1 "general_operand"))]
"TARGET_VECTOR"
{
- if (riscv_vector::legitimize_move (operands[0], operands[1], <MODE>mode))
+ if (riscv_vector::legitimize_move (operands[0], operands[1]))
DONE;
})
@@ -760,9 +760,8 @@
else
{
riscv_vector::emit_vlmax_vsetvl (<V_FRACT:MODE>mode, operands[2]);
- riscv_vector::emit_vlmax_reg_op (code_for_pred_mov (<V_FRACT:MODE>mode),
- operands[0], operands[1], operands[2],
- <VM>mode);
+ riscv_vector::emit_vlmax_tany_many (code_for_pred_mov (<V_FRACT:MODE>mode),
+ RVV_UNOP_NUM, operands);
}
DONE;
})
@@ -781,9 +780,8 @@
else
{
riscv_vector::emit_vlmax_vsetvl (<VB:MODE>mode, operands[2]);
- riscv_vector::emit_vlmax_reg_op (code_for_pred_mov (<VB:MODE>mode),
- operands[0], operands[1], operands[2],
- <VB:MODE>mode);
+ riscv_vector::emit_vlmax_tany_many (code_for_pred_mov (<VB:MODE>mode),
+ RVV_UNOP_NUM, operands);
}
DONE;
})
@@ -806,7 +804,7 @@
if (GET_CODE (operands[1]) == CONST_VECTOR)
{
- riscv_vector::expand_tuple_move (<VM>mode, operands);
+ riscv_vector::expand_tuple_move (operands);
DONE;
}
@@ -826,7 +824,7 @@
"&& reload_completed"
[(const_int 0)]
{
- riscv_vector::expand_tuple_move (<VM>mode, operands);
+ riscv_vector::expand_tuple_move (operands);
DONE;
}
[(set_attr "type" "vmov,vlde,vste")
@@ -846,8 +844,8 @@
(match_operand:<VEL> 1 "direct_broadcast_operand")))]
"TARGET_VECTOR"
{
- riscv_vector::emit_vlmax_op (code_for_pred_broadcast (<MODE>mode),
- operands[0], operands[1], <VM>mode);
+ riscv_vector::emit_vlmax_tany_many (code_for_pred_broadcast (<MODE>mode),
+ RVV_UNOP_NUM, operands);
DONE;
}
)
@@ -1272,7 +1270,6 @@
/* scalar op */&operands[3],
/* vl */operands[5],
<MODE>mode,
- <VM>mode,
riscv_vector::simm5_p (operands[3]),
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_merge<mode> (operands[0], operands[1],
@@ -1983,7 +1980,6 @@
/* scalar op */&operands[4],
/* vl */operands[5],
<MODE>mode,
- <VM>mode,
riscv_vector::has_vi_variant_p (<CODE>, operands[4]),
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_<optab><mode> (operands[0], operands[1],
@@ -2059,7 +2055,6 @@
/* scalar op */&operands[4],
/* vl */operands[5],
<MODE>mode,
- <VM>mode,
riscv_vector::has_vi_variant_p (<CODE>, operands[4]),
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_<optab><mode> (operands[0], operands[1],
@@ -2135,7 +2130,6 @@
/* scalar op */&operands[4],
/* vl */operands[5],
<MODE>mode,
- <VM>mode,
riscv_vector::neg_simm5_p (operands[4]),
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_sub<mode> (operands[0], operands[1],
@@ -2253,7 +2247,6 @@
/* scalar op */&operands[4],
/* vl */operands[5],
<MODE>mode,
- <VM>mode,
false,
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_mulh<v_su><mode> (operands[0], operands[1],
@@ -2428,7 +2421,6 @@
/* scalar op */&operands[3],
/* vl */operands[5],
<MODE>mode,
- <VM>mode,
riscv_vector::simm5_p (operands[3]),
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_adc<mode> (operands[0], operands[1],
@@ -2512,7 +2504,6 @@
/* scalar op */&operands[3],
/* vl */operands[5],
<MODE>mode,
- <VM>mode,
false,
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_sbc<mode> (operands[0], operands[1],
@@ -2671,7 +2662,6 @@
/* scalar op */&operands[2],
/* vl */operands[4],
<MODE>mode,
- <VM>mode,
riscv_vector::simm5_p (operands[2]),
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_madc<mode> (operands[0], operands[1],
@@ -2741,7 +2731,6 @@
/* scalar op */&operands[2],
/* vl */operands[4],
<MODE>mode,
- <VM>mode,
false,
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_msbc<mode> (operands[0], operands[1],
@@ -2884,7 +2873,6 @@
/* scalar op */&operands[2],
/* vl */operands[3],
<MODE>mode,
- <VM>mode,
riscv_vector::simm5_p (operands[2]),
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_madc<mode>_overflow (operands[0], operands[1],
@@ -2951,7 +2939,6 @@
/* scalar op */&operands[2],
/* vl */operands[3],
<MODE>mode,
- <VM>mode,
false,
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_msbc<mode>_overflow (operands[0], operands[1],
@@ -3449,7 +3436,6 @@
/* scalar op */&operands[4],
/* vl */operands[5],
<MODE>mode,
- <VM>mode,
riscv_vector::has_vi_variant_p (<CODE>, operands[4]),
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_<optab><mode> (operands[0], operands[1],
@@ -3531,7 +3517,6 @@
/* scalar op */&operands[4],
/* vl */operands[5],
<MODE>mode,
- <VM>mode,
riscv_vector::has_vi_variant_p (<CODE>, operands[4]),
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_<optab><mode> (operands[0], operands[1],
@@ -3681,7 +3666,6 @@
/* scalar op */&operands[4],
/* vl */operands[5],
<MODE>mode,
- <VM>mode,
false,
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_<sat_op><mode> (operands[0], operands[1],
@@ -4141,7 +4125,6 @@
/* scalar op */&operands[5],
/* vl */operands[6],
<MODE>mode,
- <VM>mode,
riscv_vector::has_vi_variant_p (code, operands[5]),
code == LT || code == LTU ?
[] (rtx *operands, rtx boardcast_scalar) {
@@ -4181,7 +4164,6 @@
/* scalar op */&operands[5],
/* vl */operands[6],
<MODE>mode,
- <VM>mode,
riscv_vector::has_vi_variant_p (code, operands[5]),
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_cmp<mode> (operands[0], operands[1],
@@ -4880,7 +4862,6 @@
/* scalar op */&operands[2],
/* vl */operands[6],
<MODE>mode,
- <VM>mode,
false,
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_mul_plus<mode> (operands[0], operands[1],
@@ -5301,7 +5282,6 @@
/* scalar op */&operands[2],
/* vl */operands[6],
<MODE>mode,
- <VM>mode,
false,
[] (rtx *operands, rtx boardcast_scalar) {
emit_insn (gen_pred_minus_mul<mode> (operands[0], operands[1],