gcc/config/mips/4130.md

;; Copyright (C) 2004-2021 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/>.  */
;;
;; Pipeline description for the VR4130 family.
;;
;; The processor issues each 8-byte aligned pair of instructions together,
;; stalling the second instruction if it depends on the first.  Thus, if we
;; want two instructions to issue in parallel, we need to make sure that the
;; first one is 8-byte aligned.
;;
;; For the purposes of this pipeline description, we treat the processor
;; like a standard two-way superscalar architecture.  If scheduling were
;; the last pass to run, we could use the scheduler hooks to vary the
;; issue rate depending on whether an instruction is at an aligned or
;; unaligned address.  Unfortunately, delayed branch scheduling and
;; hazard avoidance are done after the final scheduling pass, and they
;; can change the addresses of many instructions.
;;
;; We get around this in two ways:
;;
;;   (1) By running an extra pass at the end of compilation.  This pass goes
;;	 through the function looking for pairs of instructions that could
;;	 execute in parallel.  It makes sure that the first instruction in
;;	 each pair is suitably aligned, inserting nops if necessary.  Doing
;;	 this gives the same kind of pipeline behavior we would see on a
;;	 normal superscalar target.
;;
;;	 This pass is generally a speed improvement, but the extra nops will
;;	 obviously make the program bigger.  It is therefore unsuitable for
;;	 -Os (at the very least).
;;
;;   (2) By modifying the scheduler hooks so that, where possible:
;;
;;	 (a) dependent instructions are separated by a non-dependent
;;	     instruction;
;;
;;	 (b) instructions that use the multiplication unit are separated
;;	     by non-multiplication instructions; and
;;
;;	 (c) memory access instructions are separated by non-memory
;;	     instructions.
;;
;;	 The idea is to keep conflicting instructions apart wherever possible
;;	 and thus make the schedule less dependent on alignment.

(define_automaton "vr4130_main, vr4130_muldiv, vr4130_mulpre")

(define_cpu_unit "vr4130_alu1, vr4130_alu2, vr4130_dcache" "vr4130_main")
(define_cpu_unit "vr4130_muldiv" "vr4130_muldiv")

;; This is a fake unit for pre-reload scheduling of multiplications.
;; It enforces the true post-reload repeat rate.
(define_cpu_unit "vr4130_mulpre" "vr4130_mulpre")

;; The scheduling hooks use this attribute for (b) above.
(define_attr "vr4130_class" "mul,mem,alu"
  (cond [(eq_attr "type" "load,store")
	 (const_string "mem")

	 (eq_attr "type" "mfhi,mflo,mthi,mtlo,imul,imul3,imadd,idiv")
	 (const_string "mul")]
	(const_string "alu")))

(define_insn_reservation "vr4130_multi" 1
  (and (eq_attr "cpu" "r4130")
       (eq_attr "type" "multi,unknown,atomic,syncloop"))
  "vr4130_alu1 + vr4130_alu2 + vr4130_dcache + vr4130_muldiv")

(define_insn_reservation "vr4130_int" 1
  (and (eq_attr "cpu" "r4130")
       (eq_attr "type" "arith,const,logical,move,nop,shift,signext,slt"))
  "vr4130_alu1 | vr4130_alu2")

(define_insn_reservation "vr4130_load" 3
  (and (eq_attr "cpu" "r4130")
       (eq_attr "type" "load"))
  "vr4130_dcache")

(define_insn_reservation "vr4130_store" 1
  (and (eq_attr "cpu" "r4130")
       (eq_attr "type" "store"))
  "vr4130_dcache")

(define_insn_reservation "vr4130_mfhilo" 3
  (and (eq_attr "cpu" "r4130")
       (eq_attr "type" "mfhi,mflo"))
  "vr4130_muldiv")

(define_insn_reservation "vr4130_mthilo" 1
  (and (eq_attr "cpu" "r4130")
       (eq_attr "type" "mthi,mtlo"))
  "vr4130_muldiv")

;; The product is available in LO & HI after one cycle.  Moving the result
;; into an integer register will take an additional three cycles, see mflo
;; & mfhi above.  Note that the same latencies and repeat rates apply if we
;; use "mtlo; macc" instead of "mult; mflo".
(define_insn_reservation "vr4130_mulsi" 4
  (and (eq_attr "cpu" "r4130")
       (and (eq_attr "type" "imul,imul3")
	    (eq_attr "mode" "SI")))
  "vr4130_muldiv + (vr4130_mulpre * 2)")

;; As for vr4130_mulsi, but the product is available in LO and HI
;; after 3 cycles.
(define_insn_reservation "vr4130_muldi" 6
  (and (eq_attr "cpu" "r4130")
       (and (eq_attr "type" "imul,imul3")
	    (eq_attr "mode" "DI")))
  "(vr4130_muldiv * 3) + (vr4130_mulpre * 4)")

;; maccs can execute in consecutive cycles without stalling, but it
;; is 3 cycles before the integer destination can be read.
(define_insn_reservation "vr4130_macc" 3
  (and (eq_attr "cpu" "r4130")
       (eq_attr "type" "imadd"))
  "vr4130_muldiv")

(define_bypass 1 "vr4130_mulsi,vr4130_macc" "vr4130_macc" "mips_linked_madd_p")
(define_bypass 1 "vr4130_mulsi,vr4130_macc" "vr4130_mfhilo")
(define_bypass 3 "vr4130_muldi" "vr4130_mfhilo")

(define_insn_reservation "vr4130_divsi" 36
  (and (eq_attr "cpu" "r4130")
       (and (eq_attr "type" "idiv")
	    (eq_attr "mode" "SI")))
  "vr4130_muldiv * 36")

(define_insn_reservation "vr4130_divdi" 72
  (and (eq_attr "cpu" "r4130")
       (and (eq_attr "type" "idiv")
	    (eq_attr "mode" "DI")))
  "vr4130_muldiv * 72")

(define_insn_reservation "vr4130_branch" 0
  (and (eq_attr "cpu" "r4130")
       (eq_attr "type" "branch,jump,call"))
  "vr4130_alu1 | vr4130_alu2")