;; Copyright (C) 2007 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/>.  */
;;
;; .........................
;;
;; DFA-based pipeline description for MIPS64 model R20Kc.
;; Contributed by Jason Eckhardt (jle@cygnus.com).
;;
;; The R20Kc is a dual-issue processor that can generally bundle
;; instructions as follows:
;;   1. integer with integer
;;   2. integer with fp
;;   3. fp with fpload/fpstore 
;;
;; Of course, there are various restrictions.
;; Reference:
;;   "Ruby (R20K) Technical Specification Rev. 1.2, December 28, 1999."
;;
;; .........................

;; Use three automata to isolate long latency operations, reducing space.
(define_automaton "r20kc_other, r20kc_fdiv, r20kc_idiv")

;;
;; Describe the resources.
;;

;; Global.
(define_cpu_unit "r20kc_iss0, r20kc_iss1" "r20kc_other")

;; Integer execution unit (pipeline A).
(define_cpu_unit "r20kc_ixua_addsub_agen" "r20kc_other")
(define_cpu_unit "r20kc_ixua_shift"	  "r20kc_other")

(exclusion_set "r20kc_ixua_addsub_agen" "r20kc_ixua_shift")

;; Integer execution unit (pipeline B).
(define_cpu_unit "r20kc_ixub_addsub"	  "r20kc_other")
(define_cpu_unit "r20kc_ixub_branch"	  "r20kc_other")
(define_cpu_unit "r20kc_ixub_mpydiv"	  "r20kc_other")
(define_cpu_unit "r20kc_ixub_mpydiv_iter" "r20kc_idiv")

(exclusion_set "r20kc_ixub_addsub" "r20kc_ixub_branch, r20kc_ixub_mpydiv")
(exclusion_set "r20kc_ixub_branch" "r20kc_ixub_mpydiv")

;; Cache / memory interface.
(define_cpu_unit "r20kc_cache"	    "r20kc_other")

;; Floating-point unit.
(define_cpu_unit "r20kc_fpu_add"	  "r20kc_other")
(define_cpu_unit "r20kc_fpu_mpy"	  "r20kc_other")
(define_cpu_unit "r20kc_fpu_mpy_iter"	  "r20kc_fdiv")
(define_cpu_unit "r20kc_fpu_divsqrt"	  "r20kc_other")
(define_cpu_unit "r20kc_fpu_divsqrt_iter" "r20kc_fdiv")

(exclusion_set "r20kc_fpu_add" "r20kc_fpu_mpy, r20kc_fpu_divsqrt")
(exclusion_set "r20kc_fpu_mpy" "r20kc_fpu_divsqrt")

;; After branch any insn can not be issued.
(absence_set "r20kc_iss0,r20kc_iss1" "r20kc_ixub_branch")

;;
;; Define reservations for unit name mnemonics or combinations.
;;

(define_reservation "r20kc_iss"
  "r20kc_iss0|r20kc_iss1")
(define_reservation "r20kc_single_dispatch"
  "r20kc_iss0+r20kc_iss1")
(define_reservation "r20kc_iaddsub"
  "r20kc_iss+(r20kc_ixua_addsub_agen|r20kc_ixub_addsub)")
(define_reservation "r20kc_ishift"
  "r20kc_iss+r20kc_ixua_shift")
(define_reservation "r20kc_fpmove"
  "r20kc_iss+r20kc_ixua_addsub_agen")
(define_reservation "r20kc_imem"
  "r20kc_iss+r20kc_ixua_addsub_agen+r20kc_cache")
(define_reservation "r20kc_icache"
  "r20kc_cache")
(define_reservation "r20kc_impydiv"
  "r20kc_iss+r20kc_ixub_mpydiv")
(define_reservation "r20kc_impydiv_iter"
  "r20kc_ixub_mpydiv_iter")
(define_reservation "r20kc_ibranch"
  "r20kc_iss+r20kc_ixub_branch")

(define_reservation "r20kc_fpadd"
  "r20kc_iss+r20kc_fpu_add")
(define_reservation "r20kc_fpmpy"
  "r20kc_iss+r20kc_fpu_mpy")
(define_reservation "r20kc_fpmpy_iter"
  "r20kc_fpu_mpy_iter")
(define_reservation "r20kc_fpdivsqrt"
  "r20kc_iss+r20kc_fpu_divsqrt")
(define_reservation "r20kc_fpdivsqrt_iter"
  "r20kc_fpu_divsqrt_iter")

;;
;; Describe instruction reservations for integer operations.
;;

;; Conditional moves always force single-dispatch.
(define_insn_reservation "r20kc_cond_move_int" 1 
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "condmove")
				   (eq_attr "mode" "!SF,DF")))
			 "r20kc_single_dispatch")

(define_insn_reservation "r20kc_cond_move_fp" 4 
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "condmove")
				   (eq_attr "mode" "SF,DF")))
			 "r20kc_single_dispatch")

(define_insn_reservation "r20kc_int_other" 1
			  (and (eq_attr "cpu" "20kc")
			       (eq_attr "type" "move,arith,const,nop"))
			  "r20kc_iaddsub")

;; Shifts can only execute on ixu pipeline A.
(define_insn_reservation "r20kc_int_shift" 1
			  (and (eq_attr "cpu" "20kc")
			       (eq_attr "type" "shift"))
			  "r20kc_ishift")

(define_insn_reservation "r20kc_ld" 2 
			 (and (eq_attr "cpu" "20kc")
			      (eq_attr "type" "load,prefetch,prefetchx"))
			 "r20kc_imem")


;; A load immediately following a store will stall, so
;; say that a store uses the cache for an extra cycle.
(define_insn_reservation "r20kc_st" 2 
			  (and (eq_attr "cpu" "20kc")
			       (eq_attr "type" "store"))
			  "r20kc_imem,r20kc_icache")

(define_insn_reservation "r20kc_fld" 3 
			 (and (eq_attr "cpu" "20kc")
			      (eq_attr "type" "fpload"))
			 "r20kc_imem")

(define_insn_reservation "r20kc_ffst" 3 
			 (and (eq_attr "cpu" "20kc")
			      (eq_attr "type" "fpstore"))
			 "r20kc_imem,r20kc_icache*2")

;; Integer divide latency is between 13 and 42 cycles for DIV[U] and between
;; 13 and 72 cycles for DDIV[U]. This depends on the value of the inputs
;; so we just choose the worst case latency.
(define_insn_reservation "r20kc_idiv_si" 42 
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "idiv")
				   (eq_attr "mode" "SI")))
			 "r20kc_impydiv+(r20kc_impydiv_iter*42)")

(define_insn_reservation "r20kc_idiv_di" 72 
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "idiv")
				   (eq_attr "mode" "DI")))
			 "r20kc_impydiv+(r20kc_impydiv_iter*72)")

;; Integer multiply latency is 4 or 7 cycles for word and double-word
;; respectively.
(define_insn_reservation "r20kc_impy_si" 4 
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "imadd,imul,imul3")
				   (eq_attr "mode" "SI")))
			 "r20kc_impydiv+(r20kc_impydiv_iter*2)")

(define_insn_reservation "r20kc_impy_di" 7 
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "imadd,imul,imul3")
				   (eq_attr "mode" "DI")))
			 "r20kc_impydiv+(r20kc_impydiv_iter*7)")

;; Move to/from HI/LO.
;; Moving to HI/LO has a 3 cycle latency while moving from only has a 1
;; cycle latency.  Repeat rate is 3 for both.
(define_insn_reservation "r20kc_imthilo" 3 
			 (and (eq_attr "cpu" "20kc")
			      (eq_attr "type" "mthilo"))
			 "r20kc_impydiv+(r20kc_impydiv_iter*3)")

(define_insn_reservation "r20kc_imfhilo" 1
			 (and (eq_attr "cpu" "20kc")
			      (eq_attr "type" "mfhilo"))
			 "r20kc_impydiv+(r20kc_impydiv_iter*3)")

;; Move to fp coprocessor.
(define_insn_reservation "r20kc_ixfer_mt" 3 
			 (and (eq_attr "cpu" "20kc")
			      (eq_attr "type" "mtc"))
			 "r20kc_fpmove")

;; Move from fp coprocessor.
(define_insn_reservation "r20kc_ixfer_mf" 2 
			  (and (eq_attr "cpu" "20kc")
			       (eq_attr "type" "mfc"))
			"r20kc_fpmove")

;; Assume branch predicted correctly.
(define_insn_reservation "r20kc_ibr" 1 
			 (and (eq_attr "cpu" "20kc")
			      (eq_attr "type" "branch,jump,call"))
			 "r20kc_ibranch")

;;
;; Describe instruction reservations for the floating-point operations.
;;
(define_insn_reservation "r20kc_fp_other" 4
			 (and (eq_attr "cpu" "20kc")
			      (eq_attr "type" "fmove,fadd,fabs,fneg,fcmp"))
			 "r20kc_fpadd")

(define_insn_reservation "r20kc_fp_cvt_a" 4
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "fcvt")
				   (eq_attr "cnv_mode" "I2S,I2D,S2D")))
			 "r20kc_fpadd")

(define_insn_reservation "r20kc_fp_cvt_b" 5
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "fcvt")
				   (eq_attr "cnv_mode" "D2S,S2I")))
			 "r20kc_fpadd")

(define_insn_reservation "r20kc_fp_divsqrt_df" 32
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "fdiv,fsqrt")
				   (eq_attr "mode" "DF")))
			 "r20kc_fpdivsqrt+(r20kc_fpdivsqrt_iter*32)")

(define_insn_reservation "r20kc_fp_divsqrt_sf" 17
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "fdiv,fsqrt")
				   (eq_attr "mode" "SF")))
			 "r20kc_fpdivsqrt+(r20kc_fpdivsqrt_iter*17)")

(define_insn_reservation "r20kc_fp_rsqrt_df" 35 
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "frsqrt")
				   (eq_attr "mode" "DF")))
			 "r20kc_fpdivsqrt+(r20kc_fpdivsqrt_iter*35)")

(define_insn_reservation "r20kc_fp_rsqrt_sf" 17
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "frsqrt")
				   (eq_attr "mode" "SF")))
			 "r20kc_fpdivsqrt+(r20kc_fpdivsqrt_iter*17)")

(define_insn_reservation "r20kc_fp_mpy_sf" 4
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "fmul,fmadd")
				   (eq_attr "mode" "SF")))
			 "r20kc_fpmpy+r20kc_fpmpy_iter")

(define_insn_reservation "r20kc_fp_mpy_df" 5
			 (and (eq_attr "cpu" "20kc")
			      (and (eq_attr "type" "fmul,fmadd")
				   (eq_attr "mode" "DF")))
			 "r20kc_fpmpy+(r20kc_fpmpy_iter*2)")

;; Force single-dispatch for unknown or multi.
(define_insn_reservation "r20kc_unknown" 1 
			 (and (eq_attr "cpu" "20kc")
			      (eq_attr "type" "unknown,multi"))
			 "r20kc_single_dispatch")