RISC-V: Add vectorized binops and insn_expander helpers.

This patch adds basic binary integer operations support.  It is based
on Michael Collison's work and makes use of the existing helpers in
riscv-c.cc.  It introduces emit_nonvlmax_binop which, in turn, uses
emit_pred_binop.  Setting the destination as well as the mask and the
length are factored out into separate functions.

gcc/ChangeLog:

	* config/riscv/autovec.md (<optab><mode>3): Add integer binops.
	* config/riscv/riscv-protos.h (emit_nonvlmax_binop): Declare.
	* config/riscv/riscv-v.cc (emit_pred_op): New function.
	(set_expander_dest_and_mask): New function.
	(emit_pred_binop): New function.
	(emit_nonvlmax_binop): New function.

Co-authored-by: Michael Collison <collison@rivosinc.com>
This commit is contained in:
Robin Dapp 2023-04-24 08:27:52 +02:00
parent af595613ac
commit b75c9e1037
3 changed files with 127 additions and 68 deletions

View file

@ -82,3 +82,40 @@
DONE;
}
)
;; ========================================================================
;; == Vector operations
;; =========================================================================
;; -------------------------------------------------------------------------
;; ---- [INT] Binary operations
;; -------------------------------------------------------------------------
;; Includes:
;; - vadd.vv/vsub.vv/...
;; - vadd.vi/vsub.vi/...
;; -------------------------------------------------------------------------
(define_expand "<optab><mode>3"
[(set (match_operand:VI 0 "register_operand")
(any_int_binop:VI
(match_operand:VI 1 "<binop_rhs1_predicate>")
(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_nonvlmax_binop (code_for_pred_scalar
(<CODE>, <MODE>mode),
operands[0], operands[1], cst,
NULL, <VM>mode,
<VEL>mode);
}
else
riscv_vector::emit_nonvlmax_binop (code_for_pred
(<CODE>, <MODE>mode),
operands[0], operands[1], operands[2],
NULL, <VM>mode);
DONE;
})

View file

@ -169,6 +169,8 @@ void emit_hard_vlmax_vsetvl (machine_mode, rtx);
void emit_vlmax_op (unsigned, rtx, rtx, machine_mode);
void emit_vlmax_op (unsigned, rtx, rtx, rtx, machine_mode);
void emit_nonvlmax_op (unsigned, rtx, rtx, rtx, machine_mode);
void emit_nonvlmax_binop (unsigned, rtx, rtx, rtx, rtx, machine_mode,
machine_mode = VOIDmode);
enum vlmul_type get_vlmul (machine_mode);
unsigned int get_ratio (machine_mode);
unsigned int get_nf (machine_mode);

View file

@ -53,7 +53,7 @@ namespace riscv_vector {
template <int MAX_OPERANDS> class insn_expander
{
public:
insn_expander () : m_opno (0) {}
insn_expander () : m_opno (0), has_dest(false) {}
void add_output_operand (rtx x, machine_mode mode)
{
create_output_operand (&m_ops[m_opno++], x, mode);
@ -84,6 +84,44 @@ public:
add_input_operand (gen_int_mode (type, Pmode), Pmode);
}
void set_dest_and_mask (rtx mask, rtx dest, machine_mode mask_mode)
{
dest_mode = GET_MODE (dest);
has_dest = true;
add_output_operand (dest, dest_mode);
if (mask)
add_input_operand (mask, GET_MODE (mask));
else
add_all_one_mask_operand (mask_mode);
add_vundef_operand (dest_mode);
}
void set_len_and_policy (rtx len, bool vlmax_p)
{
gcc_assert (has_dest);
gcc_assert (len || vlmax_p);
if (len)
add_input_operand (len, Pmode);
else
{
rtx vlmax = gen_reg_rtx (Pmode);
emit_vlmax_vsetvl (dest_mode, vlmax);
add_input_operand (vlmax, Pmode);
}
if (GET_MODE_CLASS (dest_mode) != MODE_VECTOR_BOOL)
add_policy_operand (get_prefer_tail_policy (), get_prefer_mask_policy ());
if (vlmax_p)
add_avl_type_operand (avl_type::VLMAX);
else
add_avl_type_operand (avl_type::NONVLMAX);
}
void expand (enum insn_code icode, bool temporary_volatile_p = false)
{
if (temporary_volatile_p)
@ -97,6 +135,8 @@ public:
private:
int m_opno;
bool has_dest;
machine_mode dest_mode;
expand_operand m_ops[MAX_OPERANDS];
};
@ -195,39 +235,43 @@ emit_pred_op (unsigned icode, rtx mask, rtx dest, rtx src, rtx len,
machine_mode mask_mode, bool vlmax_p)
{
insn_expander<8> e;
machine_mode mode = GET_MODE (dest);
e.add_output_operand (dest, mode);
if (mask)
e.add_input_operand (mask, GET_MODE (mask));
else
e.add_all_one_mask_operand (mask_mode);
e.add_vundef_operand (mode);
e.set_dest_and_mask (mask, dest, mask_mode);
e.add_input_operand (src, GET_MODE (src));
if (len)
e.add_input_operand (len, Pmode);
else
{
rtx vlmax = gen_reg_rtx (Pmode);
emit_vlmax_vsetvl (mode, vlmax);
e.add_input_operand (vlmax, Pmode);
}
if (GET_MODE_CLASS (mode) != MODE_VECTOR_BOOL)
e.add_policy_operand (get_prefer_tail_policy (), get_prefer_mask_policy ());
if (vlmax_p)
e.add_avl_type_operand (avl_type::VLMAX);
else
e.add_avl_type_operand (avl_type::NONVLMAX);
e.set_len_and_policy (len, vlmax_p);
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,
bool vlmax_p)
{
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, vlmax_p);
e.expand ((enum insn_code) icode, MEM_P (dest) || MEM_P (src1) || MEM_P (src2));
}
void
emit_vlmax_op (unsigned icode, rtx dest, rtx src, machine_mode mask_mode)
{
@ -248,49 +292,25 @@ emit_nonvlmax_op (unsigned icode, rtx dest, rtx src, rtx len,
emit_pred_op (icode, NULL_RTX, dest, src, len, mask_mode, false);
}
/* Emit binary operations. */
static void
emit_binop (unsigned icode, rtx *ops, machine_mode mask_mode,
machine_mode scalar_mode)
void
emit_nonvlmax_binop (unsigned icode, rtx dest, rtx src1, rtx src2, rtx len,
machine_mode mask_mode, machine_mode scalar_mode)
{
insn_expander<9> e;
machine_mode mode = GET_MODE (ops[0]);
e.add_output_operand (ops[0], mode);
e.add_all_one_mask_operand (mask_mode);
e.add_vundef_operand (mode);
if (VECTOR_MODE_P (GET_MODE (ops[1])))
e.add_input_operand (ops[1], GET_MODE (ops[1]));
else
e.add_input_operand (ops[1], scalar_mode);
if (VECTOR_MODE_P (GET_MODE (ops[2])))
e.add_input_operand (ops[2], GET_MODE (ops[2]));
else
e.add_input_operand (ops[2], scalar_mode);
rtx vlmax = gen_reg_rtx (Pmode);
emit_vlmax_vsetvl (mode, vlmax);
e.add_input_operand (vlmax, Pmode);
e.add_policy_operand (get_prefer_tail_policy (), get_prefer_mask_policy ());
e.add_avl_type_operand (avl_type::VLMAX);
e.expand ((enum insn_code) icode, false);
emit_pred_binop (icode, NULL_RTX, dest, src1, src2, len, mask_mode,
scalar_mode, len ? false : true);
}
/* Emit vid.v instruction. */
static void
emit_index_op (rtx target, machine_mode mask_mode)
emit_index_op (rtx dest, machine_mode mask_mode)
{
insn_expander<7> e;
machine_mode mode = GET_MODE (target);
e.add_output_operand (target, mode);
e.add_all_one_mask_operand (mask_mode);
e.add_vundef_operand (mode);
rtx vlmax = gen_reg_rtx (Pmode);
emit_vlmax_vsetvl (mode, vlmax);
e.add_input_operand (vlmax, Pmode);
e.add_policy_operand (get_prefer_tail_policy (), get_prefer_mask_policy ());
e.add_avl_type_operand (avl_type::VLMAX);
e.expand (code_for_pred_series (mode), false);
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);
}
/* Expand series const vector. */
@ -324,15 +344,15 @@ expand_vec_series (rtx dest, rtx base, rtx step)
/* Emit logical left shift operation. */
int shift = exact_log2 (INTVAL (step));
rtx shift_amount = gen_int_mode (shift, Pmode);
rtx ops[3] = {step_adj, vid, shift_amount};
insn_code icode = code_for_pred_scalar (ASHIFT, mode);
emit_binop (icode, ops, mask_mode, Pmode);
emit_nonvlmax_binop (icode, step_adj, vid, shift_amount,
NULL, mask_mode, Pmode);
}
else
{
rtx ops[3] = {step_adj, vid, step};
insn_code icode = code_for_pred_scalar (MULT, mode);
emit_binop (icode, ops, mask_mode, inner_mode);
emit_nonvlmax_binop (icode, step_adj, vid, step,
NULL, mask_mode, inner_mode);
}
}
@ -346,9 +366,9 @@ expand_vec_series (rtx dest, rtx base, rtx step)
else
{
rtx result = gen_reg_rtx (mode);
rtx ops[3] = {result, step_adj, base};
insn_code icode = code_for_pred_scalar (PLUS, mode);
emit_binop (icode, ops, mask_mode, inner_mode);
emit_nonvlmax_binop (icode, result, step_adj, base,
NULL, mask_mode, inner_mode);
emit_move_insn (dest, result);
}
}