===================================================================
@@ -250,6 +250,9 @@
Enum(processor_type) String(cortex-a15) Value(cortexa15)
EnumValue
+Enum(processor_type) String(cortex-a53) Value(cortexa53)
+
+EnumValue
Enum(processor_type) String(cortex-r4) Value(cortexr4)
EnumValue
===================================================================
@@ -53,6 +53,6 @@
ARM_ARCH("armv7-r", cortexr4, 7R, FL_CO_PROC | FL_FOR_ARCH7R)
ARM_ARCH("armv7-m", cortexm3, 7M, FL_CO_PROC | FL_FOR_ARCH7M)
ARM_ARCH("armv7e-m", cortexm4, 7EM, FL_CO_PROC | FL_FOR_ARCH7EM)
-ARM_ARCH("armv8-a", cortexa15, 8A, FL_CO_PROC | FL_FOR_ARCH8A)
+ARM_ARCH("armv8-a", cortexa53, 8A, FL_CO_PROC | FL_FOR_ARCH8A)
ARM_ARCH("iwmmxt", iwmmxt, 5TE, FL_LDSCHED | FL_STRONG | FL_FOR_ARCH5TE | FL_XSCALE | FL_IWMMXT)
ARM_ARCH("iwmmxt2", iwmmxt2, 5TE, FL_LDSCHED | FL_STRONG | FL_FOR_ARCH5TE | FL_XSCALE | FL_IWMMXT | FL_IWMMXT2)
===================================================================
@@ -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,cortexr7,cortexm4,cortexm3,cortexm1,cortexm0,cortexm0plus,marvell_pj4"
+ "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,cortexa53,cortexr4,cortexr4f,cortexr5,cortexr7,cortexm4,cortexm3,cortexm1,cortexm0,cortexm0plus,marvell_pj4"
(const (symbol_ref "((enum attr_tune) arm_tune)")))
===================================================================
@@ -0,0 +1,296 @@
+;; ARM Cortex-A53 pipeline description
+;; Copyright (C) 2013 Free Software Foundation, Inc.
+;;
+;; Contributed by ARM Ltd.
+;;
+;; 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/>.
+
+(define_automaton "cortex_a53")
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; Functional units.
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+;; There are two main integer execution pipelines, described as
+;; slot 0 and issue slot 1.
+
+(define_cpu_unit "cortex_a53_slot0" "cortex_a53")
+(define_cpu_unit "cortex_a53_slot1" "cortex_a53")
+
+(define_reservation "cortex_a53_slot_any" "cortex_a53_slot0|cortex_a53_slot1")
+(define_reservation "cortex_a53_single_issue" "cortex_a53_slot0+cortex_a53_slot1")
+
+;; The load/store pipeline. Load/store instructions can dual-issue from
+;; either pipeline, but two load/stores cannot simultaneously issue.
+
+(define_cpu_unit "cortex_a53_ls" "cortex_a53")
+
+;; The store pipeline. Shared between both execution pipelines.
+
+(define_cpu_unit "cortex_a53_store" "cortex_a53")
+
+;; The branch pipeline. Branches can dual-issue with other instructions
+;; (except when those instructions take multiple cycles to issue).
+
+(define_cpu_unit "cortex_a53_branch" "cortex_a53")
+
+;; The integer divider.
+
+(define_cpu_unit "cortex_a53_idiv" "cortex_a53")
+
+;; The floating-point add pipeline used to model the usage
+;; of the add pipeline by fmac instructions.
+
+(define_cpu_unit "cortex_a53_fpadd_pipe" "cortex_a53")
+
+;; Floating-point div/sqrt (long latency, out-of-order completion).
+
+(define_cpu_unit "cortex_a53_fp_div_sqrt" "cortex_a53")
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; ALU instructions.
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+(define_insn_reservation "cortex_a53_alu" 2
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "alu_reg,simple_alu_imm"))
+ "cortex_a53_slot_any")
+
+(define_insn_reservation "cortex_a53_alu_shift" 2
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "alu_shift,alu_shift_reg"))
+ "cortex_a53_slot_any")
+
+;; Forwarding path for unshifted operands.
+
+(define_bypass 1 "cortex_a53_alu,cortex_a53_alu_shift"
+ "cortex_a53_alu")
+
+(define_bypass 1 "cortex_a53_alu,cortex_a53_alu_shift"
+ "cortex_a53_alu_shift"
+ "arm_no_early_alu_shift_dep")
+
+;; The multiplier pipeline can forward results so there's no need to specify
+;; bypasses. Multiplies can only single-issue currently.
+
+(define_insn_reservation "cortex_a53_mul" 3
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "mult"))
+ "cortex_a53_single_issue")
+
+;; A multiply with a single-register result or an MLA, followed by an
+;; MLA with an accumulator dependency, has its result forwarded so two
+;; such instructions can issue back-to-back.
+
+(define_bypass 1 "cortex_a53_mul"
+ "cortex_a53_mul"
+ "arm_mac_accumulator_is_mul_result")
+
+;; Punt with a high enough latency for divides.
+(define_insn_reservation "cortex_a53_udiv" 8
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "insn" "udiv"))
+ "(cortex_a53_slot0+cortex_a53_idiv),cortex_a53_idiv*7")
+
+(define_insn_reservation "cortex_a53_sdiv" 9
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "insn" "sdiv"))
+ "(cortex_a53_slot0+cortex_a53_idiv),cortex_a53_idiv*8")
+
+
+(define_bypass 2 "cortex_a53_mul,cortex_a53_udiv,cortex_a53_sdiv"
+ "cortex_a53_alu")
+(define_bypass 2 "cortex_a53_mul,cortex_a53_udiv,cortex_a53_sdiv"
+ "cortex_a53_alu_shift"
+ "arm_no_early_alu_shift_dep")
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; Load/store instructions.
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+;; Address-generation happens in the issue stage.
+
+(define_insn_reservation "cortex_a53_load1" 3
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "load_byte,load1"))
+ "cortex_a53_slot_any+cortex_a53_ls")
+
+(define_insn_reservation "cortex_a53_store1" 2
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "store1"))
+ "cortex_a53_slot_any+cortex_a53_ls+cortex_a53_store")
+
+(define_insn_reservation "cortex_a53_load2" 3
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "load2"))
+ "cortex_a53_single_issue+cortex_a53_ls")
+
+(define_insn_reservation "cortex_a53_store2" 2
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "store2"))
+ "cortex_a53_single_issue+cortex_a53_ls+cortex_a53_store")
+
+(define_insn_reservation "cortex_a53_load3plus" 4
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "load3,load4"))
+ "(cortex_a53_single_issue+cortex_a53_ls)*2")
+
+(define_insn_reservation "cortex_a53_store3plus" 3
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "store3,store4"))
+ "(cortex_a53_single_issue+cortex_a53_ls+cortex_a53_store)*2")
+
+;; Load/store addresses are required early in Issue.
+(define_bypass 3 "cortex_a53_load1,cortex_a53_load2,cortex_a53_load3plus,cortex_a53_alu,cortex_a53_alu_shift"
+ "cortex_a53_load*"
+ "arm_early_load_addr_dep")
+(define_bypass 3 "cortex_a53_load1,cortex_a53_load2,cortex_a53_load3plus,cortex_a53_alu,cortex_a53_alu_shift"
+ "cortex_a53_store*"
+ "arm_early_store_addr_dep")
+
+;; Load data can forward in the ALU pipeline
+(define_bypass 2 "cortex_a53_load1,cortex_a53_load2"
+ "cortex_a53_alu")
+(define_bypass 2 "cortex_a53_load1,cortex_a53_load2"
+ "cortex_a53_alu_shift"
+ "arm_no_early_alu_shift_dep")
+
+;; ALU ops can forward to stores.
+(define_bypass 0 "cortex_a53_alu,cortex_a53_alu_shift"
+ "cortex_a53_store1,cortex_a53_store2,cortex_a53_store3plus"
+ "arm_no_early_store_addr_dep")
+
+(define_bypass 1 "cortex_a53_mul,cortex_a53_udiv,cortex_a53_sdiv,cortex_a53_load1,cortex_a53_load2,cortex_a53_load3plus"
+ "cortex_a53_store1,cortex_a53_store2,cortex_a53_store3plus"
+ "arm_no_early_store_addr_dep")
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; Branches.
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+;; Currently models all branches as dual-issuable from either execution
+;; slot, which isn't true for all cases. We still need to model indirect
+;; branches.
+
+(define_insn_reservation "cortex_a53_branch" 0
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "branch,call"))
+ "cortex_a53_slot_any+cortex_a53_branch")
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; Floating-point arithmetic.
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+(define_insn_reservation "cortex_a53_fpalu" 4
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "ffariths, fadds, ffarithd, faddd, fcpys, fmuls, f_cvt,\
+ fcmps, fcmpd"))
+ "cortex_a53_slot0+cortex_a53_fpadd_pipe")
+
+(define_insn_reservation "cortex_a53_fconst" 2
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "fconsts,fconstd"))
+ "cortex_a53_slot0+cortex_a53_fpadd_pipe")
+
+(define_insn_reservation "cortex_a53_fpmul" 4
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "fmuls,fmuld"))
+ "cortex_a53_slot0")
+
+;; For single-precision multiply-accumulate, the add (accumulate) is issued after
+;; the multiply completes. Model that accordingly.
+
+(define_insn_reservation "cortex_a53_fpmac" 8
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "fmacs,fmacd,ffmas,ffmad"))
+ "cortex_a53_slot0, nothing*3, cortex_a53_fpadd_pipe")
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; Floating-point divide/square root instructions.
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; fsqrt really takes one cycle less, but that is not modelled.
+
+(define_insn_reservation "cortex_a53_fdivs" 14
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "fdivs"))
+ "cortex_a53_slot0, cortex_a53_fp_div_sqrt * 13")
+
+(define_insn_reservation "cortex_a53_fdivd" 29
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "fdivd"))
+ "cortex_a53_slot0, cortex_a53_fp_div_sqrt * 28")
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; VFP to/from core transfers.
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+(define_insn_reservation "cortex_a53_r2f" 4
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "r_2_f"))
+ "cortex_a53_slot0")
+
+(define_insn_reservation "cortex_a53_f2r" 2
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "f_2_r"))
+ "cortex_a53_slot0")
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; VFP flag transfer.
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+(define_insn_reservation "cortex_a53_f_flags" 4
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "f_flag"))
+ "cortex_a53_slot0")
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; VFP load/store.
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+(define_insn_reservation "cortex_a53_f_loads" 4
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "f_loads"))
+ "cortex_a53_slot0")
+
+(define_insn_reservation "cortex_a53_f_loadd" 5
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "f_loadd"))
+ "cortex_a53_slot0")
+
+(define_insn_reservation "cortex_a53_f_stores" 0
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "f_stores"))
+ "cortex_a53_slot0")
+
+(define_insn_reservation "cortex_a53_f_stored" 0
+ (and (eq_attr "tune" "cortexa53")
+ (eq_attr "type" "f_stored"))
+ "cortex_a53_slot0")
+
+;; Load-to-use for floating-point values has a penalty of one cycle,
+;; i.e. a latency of two.
+
+(define_bypass 2 "cortex_a53_f_loads"
+ "cortex_a53_fpalu, cortex_a53_fpmac, cortex_a53_fpmul,\
+ cortex_a53_fdivs, cortex_a53_fdivd,\
+ cortex_a53_f2r")
+
+(define_bypass 2 "cortex_a53_f_loadd"
+ "cortex_a53_fpalu, cortex_a53_fpmac, cortex_a53_fpmul,\
+ cortex_a53_fdivs, cortex_a53_fdivd,\
+ cortex_a53_f2r")
+
===================================================================
@@ -60,6 +60,7 @@
|mcpu=cortex-a7 \
|mcpu=cortex-a8|mcpu=cortex-a9|mcpu=cortex-a15 \
|mcpu=marvell-pj4 \
+ |mcpu=cortex-a53 \
|mcpu=generic-armv7-a \
|march=armv7-m|mcpu=cortex-m3 \
|march=armv7e-m|mcpu=cortex-m4 \
@@ -71,6 +72,7 @@
" %{mbig-endian:%{march=armv7-a|mcpu=cortex-a5 \
|mcpu=cortex-a7 \
|mcpu=cortex-a8|mcpu=cortex-a9|mcpu=cortex-a15 \
+ |mcpu=cortex-a53 \
|mcpu=marvell-pj4 \
|mcpu=generic-armv7-a \
|march=armv7-m|mcpu=cortex-m3 \
===================================================================
@@ -25873,6 +25873,7 @@
case cortexa7:
case cortexa8:
case cortexa9:
+ case cortexa53:
case fa726te:
case marvell_pj4:
return 2;
===================================================================
@@ -496,7 +496,7 @@
(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,marvell_pj4")
+ (ior (eq_attr "tune" "fa526,fa626,fa606te,fa626te,fmp626,fa726te,arm926ejs,arm1020e,arm1026ejs,arm1136js,arm1136jfs,cortexa5,cortexa7,cortexa8,cortexa9,cortexa15,cortexa53,cortexm4,marvell_pj4")
(eq_attr "tune_cortexr4" "yes"))
(const_string "no")
(const_string "yes"))))
@@ -504,7 +504,7 @@
(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,marvell_pj4")
+ (eq_attr "tune" "!arm1020e,arm1022e,cortexa5,cortexa7,cortexa8,cortexa9,cortexa53,cortexm4,marvell_pj4")
(eq_attr "tune_cortexr4" "no"))
(const_string "yes")
(const_string "no"))))
@@ -525,6 +525,7 @@
(include "cortex-a8.md")
(include "cortex-a9.md")
(include "cortex-a15.md")
+(include "cortex-a53.md")
(include "cortex-r4.md")
(include "cortex-r4f.md")
(include "cortex-m4.md")
===================================================================
@@ -129,6 +129,7 @@
ARM_CORE("cortex-a8", cortexa8, 7A, FL_LDSCHED, cortex)
ARM_CORE("cortex-a9", cortexa9, 7A, FL_LDSCHED, cortex_a9)
ARM_CORE("cortex-a15", cortexa15, 7A, FL_LDSCHED | FL_THUMB_DIV | FL_ARM_DIV, cortex_a15)
+ARM_CORE("cortex-a53", cortexa53, 8A, FL_LDSCHED, cortex_a5)
ARM_CORE("cortex-r4", cortexr4, 7R, FL_LDSCHED, cortex)
ARM_CORE("cortex-r4f", cortexr4f, 7R, FL_LDSCHED, cortex)
ARM_CORE("cortex-r5", cortexr5, 7R, FL_LDSCHED | FL_ARM_DIV, cortex)
===================================================================
@@ -39,6 +39,7 @@
$(srcdir)/config/arm/cortex-a8-neon.md \
$(srcdir)/config/arm/cortex-a9.md \
$(srcdir)/config/arm/cortex-a9-neon.md \
+ $(srcdir)/config/arm/cortex-a53.md \
$(srcdir)/config/arm/cortex-m4-fpu.md \
$(srcdir)/config/arm/cortex-m4.md \
$(srcdir)/config/arm/cortex-r4f.md \
Hi, This patch adds support for the Cortex-A53. Tested with a simple build of arm-none-eabi for no regressions on a version before the builds broke with PR56809. We have been carrying this internally for quite some time now - so I'm ok with it's stability. The default tuning for -march=armv8-a is now the Cortex-A53 rather than the A15. Applied to trunk. regards Ramana 2013-04-02 Ian Caulfield <ian.caulfield@arm.com> Ramana Radhakrishnan <ramana.radhakrishnan@arm.com> * config/arm/arm-arches.def (armv8-a): Default to cortex-a53. * config/arm/t-arm (MD_INCLUDES): Depend on cortex-a53.md. * config/arm/cortex-a53.md: New file. * config/arm/bpabi.h (BE8_LINK_SPEC): Handle cortex-a53. * config/arm/arm.md (generic_sched, generic_vfp): Handle cortex-a53. * config/arm/arm.c (arm_issue_rate): Likewise. * config/arm/arm-tune.md: Regenerate * config/arm/arm-tables.opt: Regenerate. * config/arm/arm-cores.def: Add cortex-a53.