;; DFA-based pipeline description for the VR1x000.
;;   Copyright (C) 2005, 2006, 2008, 2012 Free Software Foundation, Inc.
;;
;; This file is part of GCC.

;; GCC is free software; you can redistribute it and/or modify it
;; under the terms of the GNU General Public License as published
;; by the Free Software Foundation; either version 3, or (at your
;; option) any later version.

;; GCC is distributed in the hope that it will be useful, but WITHOUT
;; ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
;; or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public
;; License for more details.

;; You should have received a copy of the GNU General Public License
;; along with GCC; see the file COPYING3.  If not see
;; <http://www.gnu.org/licenses/>.


;; R12K/R14K/R16K are derivatives of R10K, thus copy its description
;; until specific tuning for each is added.

;; R10000 has an int queue, fp queue, address queue.
;; The int queue feeds ALU1 and ALU2.
;; The fp queue feeds the fp-adder and fp-multiplier.
;; The addr queue feeds the Load/Store unit.
;;
;; However, we define the fp-adder and fp-multiplier as
;; separate automatons, because the fp-multiplier is
;; divided into fp-multiplier, fp-division, and
;; fp-squareroot units, all of which share the same
;; issue and completion logic, yet can operate in
;; parallel.
;;
;; This is based on the model described in the R10K Manual
;; and it helps to reduce the size of the automata.
(define_automaton "r10k_a_int, r10k_a_fpadder, r10k_a_addr,
                   r10k_a_fpmpy, r10k_a_fpdiv, r10k_a_fpsqrt")

(define_cpu_unit "r10k_alu1" "r10k_a_int")
(define_cpu_unit "r10k_alu2" "r10k_a_int")
(define_cpu_unit "r10k_fpadd" "r10k_a_fpadder")
(define_cpu_unit "r10k_fpmpy" "r10k_a_fpmpy")
(define_cpu_unit "r10k_fpdiv" "r10k_a_fpdiv")
(define_cpu_unit "r10k_fpsqrt" "r10k_a_fpsqrt")
(define_cpu_unit "r10k_loadstore" "r10k_a_addr")


;; R10k Loads and Stores.
(define_insn_reservation "r10k_load" 2
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "load,prefetch,prefetchx"))
  "r10k_loadstore")

(define_insn_reservation "r10k_store" 0
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "store,fpstore,fpidxstore"))
  "r10k_loadstore")

(define_insn_reservation "r10k_fpload" 3
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "fpload,fpidxload"))
  "r10k_loadstore")


;; Integer add/sub + logic ops, and mt hi/lo can be done by alu1 or alu2.
;; Miscellaneous arith goes here too (this is a guess).
(define_insn_reservation "r10k_arith" 1
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "arith,mthi,mtlo,slt,clz,const,nop,trap,logical"))
  "r10k_alu1 | r10k_alu2")

;; We treat mfhilo differently, because we need to know when
;; it's HI and when it's LO.
(define_insn_reservation "r10k_mfhi" 1
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "mfhi"))
  "r10k_alu1 | r10k_alu2")

(define_insn_reservation "r10k_mflo" 1
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "mflo"))
  "r10k_alu1 | r10k_alu2")


;; ALU1 handles shifts, branch eval, and condmove.
;;
;; Brancher is separate, but part of ALU1, but can only
;; do one branch per cycle (is this even implementable?).
;;
;; Unsure if the brancher handles jumps and calls as well, but since
;; they're related, we'll add them here for now.
(define_insn_reservation "r10k_brancher" 1
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "shift,branch,jump,call"))
  "r10k_alu1")

(define_insn_reservation "r10k_int_cmove" 1
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "condmove")
            (eq_attr "mode" "SI,DI")))
  "r10k_alu1")


;; Coprocessor Moves.
;; mtc1/dmtc1 are handled by ALU1.
;; mfc1/dmfc1 are handled by the fp-multiplier.
(define_insn_reservation "r10k_mt_xfer" 3
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "mtc"))
  "r10k_alu1")

(define_insn_reservation "r10k_mf_xfer" 2
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "mfc"))
  "r10k_fpmpy")


;; Only ALU2 does int multiplications and divisions.
;;
;; According to the Vr10000 series user manual,
;; integer mult and div insns can be issued one
;; cycle earlier if using register Lo.  We model
;; this by using the Lo value by default, as it
;; is the more common value, and use a bypass
;; for the Hi value when needed.
;;
;; Also of note, There are different latencies
;; for MULT/DMULT (Lo 5/Hi 6) and MULTU/DMULTU (Lo 6/Hi 7).
;; However, gcc does not have separate types
;; for these insns.  Thus to strike a balance,
;; we use the Hi latency value for imul
;; operations until the imul type can be split.
(define_insn_reservation "r10k_imul_single" 6
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "imul,imul3")
            (eq_attr "mode" "SI")))
  "r10k_alu2 * 6")

(define_insn_reservation "r10k_imul_double" 10
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "imul,imul3")
            (eq_attr "mode" "DI")))
  "r10k_alu2 * 10")

;; Divides keep ALU2 busy.
(define_insn_reservation "r10k_idiv_single" 34
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "idiv")
            (eq_attr "mode" "SI")))
  "r10k_alu2 * 35")

(define_insn_reservation "r10k_idiv_double" 66
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "idiv")
            (eq_attr "mode" "DI")))
  "r10k_alu2 * 67")

(define_bypass 35 "r10k_idiv_single" "r10k_mfhi")
(define_bypass 67 "r10k_idiv_double" "r10k_mfhi")


;; Floating point add/sub, mul, abs value, neg, comp, & moves.
(define_insn_reservation "r10k_fp_miscadd" 2
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "fadd,fabs,fneg,fcmp"))
  "r10k_fpadd")

(define_insn_reservation "r10k_fp_miscmul" 2
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "fmul,fmove"))
  "r10k_fpmpy")

(define_insn_reservation "r10k_fp_cmove" 2
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "condmove")
            (eq_attr "mode" "SF,DF")))
  "r10k_fpmpy")


;; The fcvt.s.[wl] insn has latency 4, repeat 2.
;; All other fcvt insns have latency 2, repeat 1.
(define_insn_reservation "r10k_fcvt_single" 4
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "fcvt")
            (eq_attr "cnv_mode" "I2S")))
  "r10k_fpadd * 2")

(define_insn_reservation "r10k_fcvt_other" 2
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "fcvt")
            (eq_attr "cnv_mode" "!I2S")))
  "r10k_fpadd")


;; Run the fmadd insn through fp-adder first, then fp-multiplier.
;;
;; The latency for fmadd is 2 cycles if the result is used
;; by another fmadd instruction.
(define_insn_reservation "r10k_fmadd" 4
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "fmadd"))
  "r10k_fpadd, r10k_fpmpy")

(define_bypass 2 "r10k_fmadd" "r10k_fmadd")


;; Floating point Divisions & square roots.
(define_insn_reservation "r10k_fdiv_single" 12
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "fdiv,frdiv")
            (eq_attr "mode" "SF")))
  "r10k_fpdiv * 14")

(define_insn_reservation "r10k_fdiv_double" 19
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "fdiv,frdiv")
            (eq_attr "mode" "DF")))
  "r10k_fpdiv * 21")

(define_insn_reservation "r10k_fsqrt_single" 18
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "fsqrt")
            (eq_attr "mode" "SF")))
  "r10k_fpsqrt * 20")

(define_insn_reservation "r10k_fsqrt_double" 33
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "fsqrt")
            (eq_attr "mode" "DF")))
  "r10k_fpsqrt * 35")

(define_insn_reservation "r10k_frsqrt_single" 30
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "frsqrt")
            (eq_attr "mode" "SF")))
  "r10k_fpsqrt * 20")

(define_insn_reservation "r10k_frsqrt_double" 52
  (and (eq_attr "cpu" "r10000")
       (and (eq_attr "type" "frsqrt")
            (eq_attr "mode" "DF")))
  "r10k_fpsqrt * 35")


;; Handle unknown/multi insns here (this is a guess).
(define_insn_reservation "r10k_unknown" 1
  (and (eq_attr "cpu" "r10000")
       (eq_attr "type" "unknown,multi,atomic,syncloop"))
  "r10k_alu1 + r10k_alu2")