@@ -137,3 +137,4 @@ ARM_CORE("cortex-m3", cortexm3, 7M, FL_LDSCHED, cortex)
ARM_CORE("cortex-m1", cortexm1, 6M, FL_LDSCHED, v6m)
ARM_CORE("cortex-m0", cortexm0, 6M, FL_LDSCHED, v6m)
ARM_CORE("cortex-m0plus", cortexm0plus, 6M, FL_LDSCHED, v6m)
+ARM_CORE("marvell-pj4", marvell_pj4, 7A, FL_LDSCHED, 9e)
@@ -273,6 +273,9 @@ Enum(processor_type) String(cortex-m0) Value(cortexm0)
EnumValue
Enum(processor_type) String(cortex-m0plus) Value(cortexm0plus)
+EnumValue
+Enum(processor_type) String(marvell-pj4) Value(marvell_pj4)
+
Enum
Name(arm_arch) Type(int)
Known ARM architectures (for use with the -march= option):
@@ -1,5 +1,5 @@
;; -*- buffer-read-only: t -*-
;; Generated automatically by gentune.sh from arm-cores.def
(define_attr "tune"
- "arm2,arm250,arm3,arm6,arm60,arm600,arm610,arm620,arm7,arm7d,arm7di,arm70,arm700,arm700i,arm710,arm720,arm710c,arm7100,arm7500,arm7500fe,arm7m,arm7dm,arm7dmi,arm8,arm810,strongarm,strongarm110,strongarm1100,strongarm1110,fa526,fa626,arm7tdmi,arm7tdmis,arm710t,arm720t,arm740t,arm9,arm9tdmi,arm920,arm920t,arm922t,arm940t,ep9312,arm10tdmi,arm1020t,arm9e,arm946es,arm966es,arm968es,arm10e,arm1020e,arm1022e,xscale,iwmmxt,iwmmxt2,fa606te,fa626te,fmp626,fa726te,arm926ejs,arm1026ejs,arm1136js,arm1136jfs,arm1176jzs,arm1176jzfs,mpcorenovfp,mpcore,arm1156t2s,arm1156t2fs,genericv7a,cortexa5,cortexa7,cortexa8,cortexa9,cortexa15,cortexr4,cortexr4f,cortexr5,cortexm4,cortexm3,cortexm1,cortexm0,cortexm0plus"
+ "arm2,arm250,arm3,arm6,arm60,arm600,arm610,arm620,arm7,arm7d,arm7di,arm70,arm700,arm700i,arm710,arm720,arm710c,arm7100,arm7500,arm7500fe,arm7m,arm7dm,arm7dmi,arm8,arm810,strongarm,strongarm110,strongarm1100,strongarm1110,fa526,fa626,arm7tdmi,arm7tdmis,arm710t,arm720t,arm740t,arm9,arm9tdmi,arm920,arm920t,arm922t,arm940t,ep9312,arm10tdmi,arm1020t,arm9e,arm946es,arm966es,arm968es,arm10e,arm1020e,arm1022e,xscale,iwmmxt,iwmmxt2,fa606te,fa626te,fmp626,fa726te,arm926ejs,arm1026ejs,arm1136js,arm1136jfs,arm1176jzs,arm1176jzfs,mpcorenovfp,mpcore,arm1156t2s,arm1156t2fs,genericv7a,cortexa5,cortexa7,cortexa8,cortexa9,cortexa15,cortexr4,cortexr4f,cortexr5,cortexm4,cortexm3,cortexm1,cortexm0,cortexm0plus,marvell_pj4"
(const (symbol_ref "((enum attr_tune) arm_tune)")))
@@ -25644,6 +25644,7 @@ arm_issue_rate (void)
case cortexa8:
case cortexa9:
case fa726te:
+ case marvell_pj4:
return 2;
default:
@@ -500,7 +500,7 @@
(define_attr "generic_sched" "yes,no"
(const (if_then_else
- (ior (eq_attr "tune" "fa526,fa626,fa606te,fa626te,fmp626,fa726te,arm926ejs,arm1020e,arm1026ejs,arm1136js,arm1136jfs,cortexa5,cortexa7,cortexa8,cortexa9,cortexa15,cortexm4")
+ (ior (eq_attr "tune" "fa526,fa626,fa606te,fa626te,fmp626,fa726te,arm926ejs,arm1020e,arm1026ejs,arm1136js,arm1136jfs,cortexa5,cortexa7,cortexa8,cortexa9,cortexa15,cortexm4,marvell_pj4")
(eq_attr "tune_cortexr4" "yes"))
(const_string "no")
(const_string "yes"))))
@@ -508,7 +508,7 @@
(define_attr "generic_vfp" "yes,no"
(const (if_then_else
(and (eq_attr "fpu" "vfp")
- (eq_attr "tune" "!arm1020e,arm1022e,cortexa5,cortexa7,cortexa8,cortexa9,cortexm4")
+ (eq_attr "tune" "!arm1020e,arm1022e,cortexa5,cortexa7,cortexa8,cortexa9,cortexm4,marvell_pj4")
(eq_attr "tune_cortexr4" "no"))
(const_string "yes")
(const_string "no"))))
@@ -534,6 +534,7 @@
(include "cortex-m4.md")
(include "cortex-m4-fpu.md")
(include "vfp11.md")
+(include "marvell-pj4.md")
;;---------------------------------------------------------------------------
@@ -59,6 +59,7 @@
" %{!mlittle-endian:%{march=armv7-a|mcpu=cortex-a5 \
|mcpu=cortex-a7 \
|mcpu=cortex-a8|mcpu=cortex-a9|mcpu=cortex-a15 \
+ |mcpu=marvell-pj4 \
|mcpu=generic-armv7-a \
|march=armv7-m|mcpu=cortex-m3 \
|march=armv7e-m|mcpu=cortex-m4 \
@@ -70,6 +71,7 @@
" %{mbig-endian:%{march=armv7-a|mcpu=cortex-a5 \
|mcpu=cortex-a7 \
|mcpu=cortex-a8|mcpu=cortex-a9|mcpu=cortex-a15 \
+ |mcpu=marvell-pj4 \
|mcpu=generic-armv7-a \
|march=armv7-m|mcpu=cortex-m3 \
|march=armv7e-m|mcpu=cortex-m4 \
new file mode 100644
@@ -0,0 +1,205 @@
+;; Marvell ARM Processor Pipeline Description
+;; Copyright (C) 2010, 2011, 2012 Free Software Foundation, Inc.
+;; Contributed by Marvell.
+
+;; 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 Marvell PJ4, aka "Flareon".
+(define_automaton "pj4")
+
+;; Issue resources
+(define_cpu_unit "pj4_is1,pj4_is2" "pj4")
+(define_reservation "pj4_is" "(pj4_is1|pj4_is2)")
+(define_reservation "pj4_isb" "(pj4_is1+pj4_is2)")
+
+;; Functional units
+(define_cpu_unit "pj4_alu1,pj4_alu2,pj4_mul,pj4_div" "pj4")
+
+;; Completion ports
+(define_cpu_unit "pj4_w1,pj4_w2" "pj4")
+
+;; Complete/Retire control
+(define_cpu_unit "pj4_c1,pj4_c2" "pj4")
+(define_reservation "pj4_cp" "(pj4_c1|pj4_c2)")
+(define_reservation "pj4_cpb" "(pj4_c1+pj4_c2)")
+
+;; Integer arithmetic instructions
+
+(define_insn_reservation "pj4_alu_e1" 1
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "alu_reg,simple_alu_imm")
+ (not (eq_attr "conds" "set"))
+ (eq_attr "insn" "mov,mvn"))
+ "pj4_is,(pj4_alu1,pj4_w1+pj4_cp)|(pj4_alu2,pj4_w2+pj4_cp)")
+
+(define_insn_reservation "pj4_alu_e1_conds" 4
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "alu_reg,simple_alu_imm")
+ (eq_attr "conds" "set")
+ (eq_attr "insn" "mov,mvn"))
+ "pj4_is,(pj4_alu1,pj4_w1+pj4_cp)|(pj4_alu2,pj4_w2+pj4_cp)")
+
+(define_insn_reservation "pj4_alu" 1
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "alu_reg,simple_alu_imm")
+ (not (eq_attr "conds" "set"))
+ (not (eq_attr "insn" "mov,mvn")))
+ "pj4_is,(pj4_alu1,pj4_w1+pj4_cp)|(pj4_alu2,pj4_w2+pj4_cp)")
+
+(define_insn_reservation "pj4_alu_conds" 4
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "alu_reg,simple_alu_imm")
+ (eq_attr "conds" "set")
+ (not (eq_attr "insn" "mov,mvn")))
+ "pj4_is,(pj4_alu1,pj4_w1+pj4_cp)|(pj4_alu2,pj4_w2+pj4_cp)")
+
+(define_insn_reservation "pj4_shift" 1
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "alu_shift,alu_shift_reg")
+ (not (eq_attr "conds" "set"))
+ (eq_attr "shift" "1")) "pj4_is,(pj4_alu1,pj4_w1+pj4_cp)|(pj4_alu2,pj4_w2+pj4_cp)")
+
+(define_insn_reservation "pj4_shift_conds" 4
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "alu_shift,alu_shift_reg")
+ (eq_attr "conds" "set")
+ (eq_attr "shift" "1")) "pj4_is,(pj4_alu1,pj4_w1+pj4_cp)|(pj4_alu2,pj4_w2+pj4_cp)")
+
+(define_insn_reservation "pj4_alu_shift" 1
+ (and (eq_attr "tune" "marvell_pj4")
+ (not (eq_attr "conds" "set"))
+ (eq_attr "type" "alu_shift,alu_shift_reg"))
+ "pj4_is,(pj4_alu1,nothing,pj4_w1+pj4_cp)|(pj4_alu2,nothing,pj4_w2+pj4_cp)")
+
+(define_insn_reservation "pj4_alu_shift_conds" 4
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "conds" "set")
+ (eq_attr "type" "alu_shift,alu_shift_reg"))
+ "pj4_is,(pj4_alu1,nothing,pj4_w1+pj4_cp)|(pj4_alu2,nothing,pj4_w2+pj4_cp)")
+
+(define_bypass 2 "pj4_alu_shift,pj4_shift"
+ "pj4_ir_mul,pj4_ir_div,pj4_core_to_vfp")
+
+(define_insn_reservation "pj4_ir_mul" 3
+ (and (eq_attr "tune" "marvell_pj4") (eq_attr "type" "mult")) "pj4_is,pj4_mul,nothing*2,pj4_cp")
+
+(define_insn_reservation "pj4_ir_div" 20
+ (and (eq_attr "tune" "marvell_pj4") (eq_attr "insn" "udiv,sdiv")) "pj4_is,pj4_div*19,pj4_cp")
+
+;; Branches and calls.
+
+(define_insn_reservation "pj4_branches" 0
+ (and (eq_attr "tune" "marvell_pj4") (eq_attr "type" "branch")) "pj4_is")
+
+(define_insn_reservation "pj4_calls" 32
+ (and (eq_attr "tune" "marvell_pj4") (eq_attr "type" "call")) "pj4_is")
+
+;; Load/store instructions
+
+(define_insn_reservation "pj4_ldr" 3
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "load_byte,load1"))
+ "pj4_is,pj4_alu1,nothing*2,pj4_cp")
+
+(define_insn_reservation "pj4_ldrd" 3
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "load2"))
+ "pj4_is,pj4_alu1,nothing*2,pj4_cpb")
+
+(define_insn_reservation "pj4_str" 1
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "store1"))
+ "pj4_is,pj4_alu1,nothing*2,pj4_cp")
+
+(define_insn_reservation "pj4_strd" 1
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "store2"))
+ "pj4_is,pj4_alu1,nothing*2,pj4_cpb")
+
+(define_insn_reservation "pj4_ldm" 4
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "load3,load4")) "pj4_isb,pj4_isb+pj4_alu1,pj4_alu1,nothing,pj4_cp,pj4_cp")
+
+(define_insn_reservation "pj4_stm" 2
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "store3,store4")) "pj4_isb,pj4_isb+pj4_alu1,pj4_alu1,nothing,pj4_cp,pj4_cp")
+
+;; Loads forward at WR-stage to ALU pipes
+(define_bypass 2 "pj4_ldr,pj4_ldrd" "pj4_alu")
+(define_bypass 2 "pj4_ldr,pj4_ldrd" "pj4_alu_shift" "arm_no_early_alu_shift_dep")
+
+(define_bypass 4 "pj4_ldr,pj4_ldrd" "pj4_ir_mul,pj4_ir_div,pj4_core_to_vfp")
+(define_bypass 5 "pj4_ldm" "pj4_ir_mul,pj4_ir_div,pj4_core_to_vfp")
+
+;; Loads to stores can back-to-back forward
+(define_bypass 1 "pj4_ldr,pj4_ldrd" "pj4_str,pj4_strd" "arm_no_early_store_addr_dep")
+
+;; PJ4 VFP floating point unit
+(define_automaton "pj4_vfp")
+
+(define_cpu_unit "vissue" "pj4_vfp")
+(define_cpu_unit "vadd" "pj4_vfp")
+(define_cpu_unit "vmul" "pj4_vfp")
+(define_cpu_unit "vdiv" "pj4_vfp")
+(define_cpu_unit "vfast" "pj4_vfp")
+
+(define_insn_reservation "pj4_vfp_add" 5
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "fadds,faddd")) "pj4_is,nothing*2,vissue,vadd,nothing*3")
+
+(define_insn_reservation "pj4_vfp_mul" 6
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "fmuls,fmuld")) "pj4_is,nothing*2,vissue,vmul,nothing*4")
+
+(define_insn_reservation "pj4_vfp_divs" 20
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "fdivs")) "pj4_is,nothing*2,vissue,vdiv*18,nothing")
+
+(define_insn_reservation "pj4_vfp_divd" 34
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "fdivd")) "pj4_is,nothing*2,vissue,vdiv*32,nothing")
+
+(define_insn_reservation "pj4_vfp_mac" 9
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "fmacs,fmacd"))
+ "pj4_is,nothing*2,vissue,vmul,nothing*3,vadd,nothing*3")
+
+(define_bypass 5 "pj4_vfp_mac" "pj4_vfp_mac" "arm_no_early_mul_dep")
+
+(define_insn_reservation "pj4_vfp_cpy" 4
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "fcpys,ffariths,ffarithd,fconsts,fconstd,\
+ fcmps,fcmpd,f_cvt")) "pj4_is,nothing*2,vissue,vfast,nothing*2")
+
+;; Enlarge latency, and wish that more nondependent insns are
+;; scheduled immediately after VFP load.
+(define_insn_reservation "pj4_vfp_load" 4
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "f_loads,f_loadd")) "pj4_isb,pj4_alu1,nothing,vissue,pj4_cp")
+
+(define_insn_reservation "pj4_vfp_store" 1
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "f_stores,f_stored")) "pj4_isb,pj4_alu1,nothing,vissue,pj4_cp")
+
+(define_insn_reservation "pj4_vfp_to_core" 7
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "f_2_r,f_flag")) "pj4_isb,nothing,nothing,vissue,vfast,nothing*2")
+
+(define_insn_reservation "pj4_core_to_vfp" 2
+ (and (eq_attr "tune" "marvell_pj4")
+ (eq_attr "type" "r_2_f")) "pj4_isb,pj4_alu1,pj4_w1,vissue,pj4_cp")
+
@@ -11242,6 +11242,7 @@ assembly code. Permissible names are: @samp{arm2}, @samp{arm250},
@samp{cortex-m1},
@samp{cortex-m0},
@samp{cortex-m0plus},
+@samp{marvell-pj4},
@samp{xscale}, @samp{iwmmxt}, @samp{iwmmxt2}, @samp{ep9312},
@samp{fa526}, @samp{fa626},
@samp{fa606te}, @samp{fa626te}, @samp{fmp626}, @samp{fa726te}.