Go to:
Gentoo Home
Documentation
Forums
Lists
Bugs
Planet
Store
Wiki
Get Gentoo!
Gentoo's Bugzilla – Attachment 188459 Details for
Bug 262603
[toolchain-overlay] Add Intel Atom optimizations support to GCC-4.4 ebuilds
Home
|
New
–
[Ex]
|
Browse
|
Search
|
Privacy Policy
|
[?]
|
Reports
|
Requests
|
Help
|
New Account
|
Log In
[x]
|
Forgot Password
Login:
[x]
[patch]
Stripped-down contents of the commit 145624
gcc-atom.diff (text/plain), 64.28 KB, created by
Alexey Charkov
on 2009-04-15 17:36:59 UTC
(
hide
)
Description:
Stripped-down contents of the commit 145624
Filename:
MIME Type:
Creator:
Alexey Charkov
Created:
2009-04-15 17:36:59 UTC
Size:
64.28 KB
patch
obsolete
>diff --git a/gcc/config.gcc b/gcc/config.gcc >index f243cb3..74e79fc 100644 >--- a/gcc/config.gcc >+++ b/gcc/config.gcc >@@ -1074,7 +1074,7 @@ i[34567]86-*-linux* | i[34567]86-*-kfreebsd*-gnu | i[34567]86-*-knetbsd*-gnu | i > tmake_file="${tmake_file} i386/t-linux64" > need_64bit_hwint=yes > case X"${with_cpu}" in >- Xgeneric|Xcore2|Xnocona|Xx86-64|Xamdfam10|Xbarcelona|Xk8|Xopteron|Xathlon64|Xathlon-fx) >+ Xgeneric|Xatom|Xcore2|Xnocona|Xx86-64|Xamdfam10|Xbarcelona|Xk8|Xopteron|Xathlon64|Xathlon-fx) > ;; > X) > if test x$with_cpu_64 = x; then >@@ -1083,7 +1083,7 @@ i[34567]86-*-linux* | i[34567]86-*-kfreebsd*-gnu | i[34567]86-*-knetbsd*-gnu | i > ;; > *) > echo "Unsupported CPU used in --with-cpu=$with_cpu, supported values:" 1>&2 >- echo "generic core2 nocona x86-64 amdfam10 barcelona k8 opteron athlon64 athlon-fx" 1>&2 >+ echo "generic atom core2 nocona x86-64 amdfam10 barcelona k8 opteron athlon64 athlon-fx" 1>&2 > exit 1 > ;; > esac >@@ -1189,7 +1189,7 @@ i[34567]86-*-solaris2*) > need_64bit_hwint=yes > use_gcc_stdint=wrap > case X"${with_cpu}" in >- Xgeneric|Xcore2|Xnocona|Xx86-64|Xamdfam10|Xbarcelona|Xk8|Xopteron|Xathlon64|Xathlon-fx) >+ Xgeneric|Xatom|Xcore2|Xnocona|Xx86-64|Xamdfam10|Xbarcelona|Xk8|Xopteron|Xathlon64|Xathlon-fx) > ;; > X) > if test x$with_cpu_64 = x; then >@@ -1198,7 +1198,7 @@ i[34567]86-*-solaris2*) > ;; > *) > echo "Unsupported CPU used in --with-cpu=$with_cpu, supported values:" 1>&2 >- echo "generic core2 nocona x86-64 amdfam10 barcelona k8 opteron athlon64 athlon-fx" 1>&2 >+ echo "generic atom core2 nocona x86-64 amdfam10 barcelona k8 opteron athlon64 athlon-fx" 1>&2 > exit 1 > ;; > esac >@@ -2801,7 +2801,7 @@ case "${target}" in > esac > # OK > ;; >- "" | amdfam10 | barcelona | k8 | opteron | athlon64 | athlon-fx | nocona | core2 | generic) >+ "" | amdfam10 | barcelona | k8 | opteron | athlon64 | athlon-fx | nocona | core2 | atom | generic) > # OK > ;; > *) >diff --git a/gcc/config/i386/atom.md b/gcc/config/i386/atom.md >new file mode 100644 >index 0000000..9d5cbf2 >--- /dev/null >+++ b/gcc/config/i386/atom.md >@@ -0,0 +1,770 @@ >+;; Atom Scheduling >+;; Copyright (C) 2009 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/>. >+;; >+;; Atom is an in-order core with two integer pipelines. >+ >+ >+(define_attr "atom_unit" "sishuf,simul,jeu,complex,other" >+ (const_string "other")) >+ >+(define_attr "atom_sse_attr" "rcp,movdup,lfence,fence,prefetch,sqrt,mxcsr,other" >+ (const_string "other")) >+ >+(define_automaton "atom") >+ >+;; Atom has two ports: port 0 and port 1 connecting to all execution units >+(define_cpu_unit "atom-port-0,atom-port-1" "atom") >+ >+;; EU: Execution Unit >+;; Atom EUs are connected by port 0 or port 1. >+ >+(define_cpu_unit "atom-eu-0, atom-eu-1, >+ atom-imul-1, atom-imul-2, atom-imul-3, atom-imul-4" >+ "atom") >+ >+;; Some EUs have duplicated copied and can be accessed via either >+;; port 0 or port 1 >+;; (define_reservation "atom-port-either" "(atom-port-0 | atom-port-1)") >+ >+;;; Some instructions is dual-pipe execution, need both ports >+;;; Complex multi-op macro-instructoins need both ports and all EUs >+(define_reservation "atom-port-dual" "(atom-port-0 + atom-port-1)") >+(define_reservation "atom-all-eu" "(atom-eu-0 + atom-eu-1 + >+ atom-imul-1 + atom-imul-2 + atom-imul-3 + >+ atom-imul-4)") >+ >+;;; Most of simple instructions have 1 cycle latency. Some of them >+;;; issue in port 0, some in port 0 and some in either port. >+(define_reservation "atom-simple-0" "(atom-port-0 + atom-eu-0)") >+(define_reservation "atom-simple-1" "(atom-port-1 + atom-eu-1)") >+(define_reservation "atom-simple-either" "(atom-simple-0 | atom-simple-1)") >+ >+;;; Some insn issues in port 0 with 3 cycle latency and 1 cycle tput >+(define_reservation "atom-eu-0-3-1" "(atom-port-0 + atom-eu-0, nothing*2)") >+ >+;;; fmul insn can have 4 or 5 cycles latency >+(define_reservation "atom-fmul-5c" "(atom-port-0 + atom-eu-0), nothing*4") >+(define_reservation "atom-fmul-4c" "(atom-port-0 + atom-eu-0), nothing*3") >+ >+;;; fadd can has 5 cycles latency depends on instruction forms >+(define_reservation "atom-fadd-5c" "(atom-port-1 + atom-eu-1), nothing*5") >+ >+;;; imul insn has 5 cycles latency >+(define_reservation "atom-imul-32" >+ "atom-imul-1, atom-imul-2, atom-imul-3, atom-imul-4, >+ atom-port-0") >+;;; imul instruction excludes other non-FP instructions. >+(exclusion_set "atom-eu-0, atom-eu-1" >+ "atom-imul-1, atom-imul-2, atom-imul-3, atom-imul-4") >+ >+;;; dual-execution instructions can have 1,2,4,5 cycles latency depends on >+;;; instruction forms >+(define_reservation "atom-dual-1c" "(atom-port-dual + atom-eu-0 + atom-eu-1)") >+(define_reservation "atom-dual-2c" >+ "(atom-port-dual + atom-eu-0 + atom-eu-1, nothing)") >+(define_reservation "atom-dual-5c" >+ "(atom-port-dual + atom-eu-0 + atom-eu-1, nothing*4)") >+ >+;;; Complex macro-instruction has variants of latency, and uses both ports. >+(define_reservation "atom-complex" "(atom-port-dual + atom-all-eu)") >+ >+(define_insn_reservation "atom_other" 9 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "other") >+ (eq_attr "atom_unit" "!jeu"))) >+ "atom-complex, atom-all-eu*8") >+ >+;; return has type "other" with atom_unit "jeu" >+(define_insn_reservation "atom_other_2" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "other") >+ (eq_attr "atom_unit" "jeu"))) >+ "atom-dual-1c") >+ >+(define_insn_reservation "atom_multi" 9 >+ (and (eq_attr "cpu" "atom") >+ (eq_attr "type" "multi")) >+ "atom-complex, atom-all-eu*8") >+ >+;; Normal alu insns without carry >+(define_insn_reservation "atom_alu" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "alu") >+ (and (eq_attr "memory" "none") >+ (eq_attr "use_carry" "0")))) >+ "atom-simple-either") >+ >+;; Normal alu insns without carry >+(define_insn_reservation "atom_alu_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "alu") >+ (and (eq_attr "memory" "!none") >+ (eq_attr "use_carry" "0")))) >+ "atom-simple-either") >+ >+;; Alu insn consuming CF, such as add/sbb >+(define_insn_reservation "atom_alu_carry" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "alu") >+ (and (eq_attr "memory" "none") >+ (eq_attr "use_carry" "1")))) >+ "atom-simple-either") >+ >+;; Alu insn consuming CF, such as add/sbb >+(define_insn_reservation "atom_alu_carry_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "alu") >+ (and (eq_attr "memory" "!none") >+ (eq_attr "use_carry" "1")))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_alu1" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "alu1") >+ (eq_attr "memory" "none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_alu1_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "alu1") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_negnot" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "negnot") >+ (eq_attr "memory" "none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_negnot_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "negnot") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_imov" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "imov") >+ (eq_attr "memory" "none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_imov_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "imov") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-either") >+ >+;; 16<-16, 32<-32 >+(define_insn_reservation "atom_imovx" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "imovx") >+ (and (eq_attr "memory" "none") >+ (ior (and (match_operand:HI 0 "register_operand") >+ (match_operand:HI 1 "general_operand")) >+ (and (match_operand:SI 0 "register_operand") >+ (match_operand:SI 1 "general_operand")))))) >+ "atom-simple-either") >+ >+;; 16<-16, 32<-32, mem >+(define_insn_reservation "atom_imovx_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "imovx") >+ (and (eq_attr "memory" "!none") >+ (ior (and (match_operand:HI 0 "register_operand") >+ (match_operand:HI 1 "general_operand")) >+ (and (match_operand:SI 0 "register_operand") >+ (match_operand:SI 1 "general_operand")))))) >+ "atom-simple-either") >+ >+;; 32<-16, 32<-8, 64<-16, 64<-8, 64<-32, 8<-8 >+(define_insn_reservation "atom_imovx_2" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "imovx") >+ (and (eq_attr "memory" "none") >+ (ior (match_operand:QI 0 "register_operand") >+ (ior (and (match_operand:SI 0 "register_operand") >+ (not (match_operand:SI 1 "general_operand"))) >+ (match_operand:DI 0 "register_operand")))))) >+ "atom-simple-0") >+ >+;; 32<-16, 32<-8, 64<-16, 64<-8, 64<-32, 8<-8, mem >+(define_insn_reservation "atom_imovx_2_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "imovx") >+ (and (eq_attr "memory" "!none") >+ (ior (match_operand:QI 0 "register_operand") >+ (ior (and (match_operand:SI 0 "register_operand") >+ (not (match_operand:SI 1 "general_operand"))) >+ (match_operand:DI 0 "register_operand")))))) >+ "atom-simple-0") >+ >+;; 16<-8 >+(define_insn_reservation "atom_imovx_3" 3 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "imovx") >+ (and (match_operand:HI 0 "register_operand") >+ (match_operand:QI 1 "general_operand")))) >+ "atom-complex, atom-all-eu*2") >+ >+(define_insn_reservation "atom_lea" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "lea") >+ (eq_attr "mode" "!HI"))) >+ "atom-simple-either") >+ >+;; lea 16bit address is complex insn >+(define_insn_reservation "atom_lea_2" 2 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "lea") >+ (eq_attr "mode" "HI"))) >+ "atom-complex, atom-all-eu") >+ >+(define_insn_reservation "atom_incdec" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "incdec") >+ (eq_attr "memory" "none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_incdec_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "incdec") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-either") >+ >+;; simple shift instruction use SHIFT eu, none memory >+(define_insn_reservation "atom_ishift" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ishift") >+ (and (eq_attr "memory" "none") (eq_attr "prefix_0f" "0")))) >+ "atom-simple-0") >+ >+;; simple shift instruction use SHIFT eu, memory >+(define_insn_reservation "atom_ishift_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ishift") >+ (and (eq_attr "memory" "!none") (eq_attr "prefix_0f" "0")))) >+ "atom-simple-0") >+ >+;; DF shift (prefixed with 0f) is complex insn with latency of 7 cycles >+(define_insn_reservation "atom_ishift_3" 7 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ishift") >+ (eq_attr "prefix_0f" "1"))) >+ "atom-complex, atom-all-eu*6") >+ >+(define_insn_reservation "atom_ishift1" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ishift1") >+ (eq_attr "memory" "none"))) >+ "atom-simple-0") >+ >+(define_insn_reservation "atom_ishift1_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ishift1") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-0") >+ >+(define_insn_reservation "atom_rotate" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "rotate") >+ (eq_attr "memory" "none"))) >+ "atom-simple-0") >+ >+(define_insn_reservation "atom_rotate_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "rotate") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-0") >+ >+(define_insn_reservation "atom_rotate1" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "rotate1") >+ (eq_attr "memory" "none"))) >+ "atom-simple-0") >+ >+(define_insn_reservation "atom_rotate1_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "rotate1") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-0") >+ >+(define_insn_reservation "atom_imul" 5 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "imul") >+ (and (eq_attr "memory" "none") (eq_attr "mode" "SI")))) >+ "atom-imul-32") >+ >+(define_insn_reservation "atom_imul_mem" 5 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "imul") >+ (and (eq_attr "memory" "!none") (eq_attr "mode" "SI")))) >+ "atom-imul-32") >+ >+;; latency set to 10 as common 64x64 imul >+(define_insn_reservation "atom_imul_3" 10 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "imul") >+ (eq_attr "mode" "!SI"))) >+ "atom-complex, atom-all-eu*9") >+ >+(define_insn_reservation "atom_idiv" 65 >+ (and (eq_attr "cpu" "atom") >+ (eq_attr "type" "idiv")) >+ "atom-complex, atom-all-eu*32, nothing*32") >+ >+(define_insn_reservation "atom_icmp" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "icmp") >+ (eq_attr "memory" "none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_icmp_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "icmp") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_test" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "test") >+ (eq_attr "memory" "none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_test_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "test") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_ibr" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ibr") >+ (eq_attr "memory" "!load"))) >+ "atom-simple-1") >+ >+;; complex if jump target is from address >+(define_insn_reservation "atom_ibr_2" 2 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ibr") >+ (eq_attr "memory" "load"))) >+ "atom-complex, atom-all-eu") >+ >+(define_insn_reservation "atom_setcc" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "setcc") >+ (eq_attr "memory" "!store"))) >+ "atom-simple-either") >+ >+;; 2 cycles complex if target is in memory >+(define_insn_reservation "atom_setcc_2" 2 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "setcc") >+ (eq_attr "memory" "store"))) >+ "atom-complex, atom-all-eu") >+ >+(define_insn_reservation "atom_icmov" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "icmov") >+ (eq_attr "memory" "none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_icmov_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "icmov") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-either") >+ >+;; UCODE if segreg, ignored >+(define_insn_reservation "atom_push" 2 >+ (and (eq_attr "cpu" "atom") >+ (eq_attr "type" "push")) >+ "atom-dual-2c") >+ >+;; pop r64 is 1 cycle. UCODE if segreg, ignored >+(define_insn_reservation "atom_pop" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "pop") >+ (eq_attr "mode" "DI"))) >+ "atom-dual-1c") >+ >+;; pop non-r64 is 2 cycles. UCODE if segreg, ignored >+(define_insn_reservation "atom_pop_2" 2 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "pop") >+ (eq_attr "mode" "!DI"))) >+ "atom-dual-2c") >+ >+;; UCODE if segreg, ignored >+(define_insn_reservation "atom_call" 1 >+ (and (eq_attr "cpu" "atom") >+ (eq_attr "type" "call")) >+ "atom-dual-1c") >+ >+(define_insn_reservation "atom_callv" 1 >+ (and (eq_attr "cpu" "atom") >+ (eq_attr "type" "callv")) >+ "atom-dual-1c") >+ >+(define_insn_reservation "atom_leave" 3 >+ (and (eq_attr "cpu" "atom") >+ (eq_attr "type" "leave")) >+ "atom-complex, atom-all-eu*2") >+ >+(define_insn_reservation "atom_str" 3 >+ (and (eq_attr "cpu" "atom") >+ (eq_attr "type" "str")) >+ "atom-complex, atom-all-eu*2") >+ >+(define_insn_reservation "atom_sselog" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sselog") >+ (eq_attr "memory" "none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_sselog_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sselog") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_sselog1" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sselog1") >+ (eq_attr "memory" "none"))) >+ "atom-simple-0") >+ >+(define_insn_reservation "atom_sselog1_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sselog1") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-0") >+ >+;; not pmad, not psad >+(define_insn_reservation "atom_sseiadd" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseiadd") >+ (and (not (match_operand:V2DI 0 "register_operand")) >+ (and (eq_attr "atom_unit" "!simul") >+ (eq_attr "atom_unit" "!complex"))))) >+ "atom-simple-either") >+ >+;; pmad, psad and 64 >+(define_insn_reservation "atom_sseiadd_2" 4 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseiadd") >+ (and (not (match_operand:V2DI 0 "register_operand")) >+ (and (eq_attr "atom_unit" "simul" ) >+ (eq_attr "mode" "DI"))))) >+ "atom-fmul-4c") >+ >+;; pmad, psad and 128 >+(define_insn_reservation "atom_sseiadd_3" 5 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseiadd") >+ (and (not (match_operand:V2DI 0 "register_operand")) >+ (and (eq_attr "atom_unit" "simul" ) >+ (eq_attr "mode" "TI"))))) >+ "atom-fmul-5c") >+ >+;; if paddq(64 bit op), phadd/phsub >+(define_insn_reservation "atom_sseiadd_4" 6 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseiadd") >+ (ior (match_operand:V2DI 0 "register_operand") >+ (eq_attr "atom_unit" "complex")))) >+ "atom-complex, atom-all-eu*5") >+ >+;; if immediate op. >+(define_insn_reservation "atom_sseishft" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseishft") >+ (and (eq_attr "atom_unit" "!sishuf") >+ (match_operand 2 "immediate_operand")))) >+ "atom-simple-either") >+ >+;; if palignr or psrldq >+(define_insn_reservation "atom_sseishft_2" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseishft") >+ (and (eq_attr "atom_unit" "sishuf") >+ (match_operand 2 "immediate_operand")))) >+ "atom-simple-0") >+ >+;; if reg/mem op >+(define_insn_reservation "atom_sseishft_3" 2 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseishft") >+ (not (match_operand 2 "immediate_operand")))) >+ "atom-complex, atom-all-eu") >+ >+(define_insn_reservation "atom_sseimul" 1 >+ (and (eq_attr "cpu" "atom") >+ (eq_attr "type" "sseimul")) >+ "atom-simple-0") >+ >+;; rcpss or rsqrtss >+(define_insn_reservation "atom_sse" 4 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sse") >+ (and (eq_attr "atom_sse_attr" "rcp") (eq_attr "mode" "SF")))) >+ "atom-fmul-4c") >+ >+;; movshdup, movsldup. Suggest to type sseishft >+(define_insn_reservation "atom_sse_2" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sse") >+ (eq_attr "atom_sse_attr" "movdup"))) >+ "atom-simple-0") >+ >+;; lfence >+(define_insn_reservation "atom_sse_3" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sse") >+ (eq_attr "atom_sse_attr" "lfence"))) >+ "atom-simple-either") >+ >+;; sfence,clflush,mfence, prefetch >+(define_insn_reservation "atom_sse_4" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sse") >+ (ior (eq_attr "atom_sse_attr" "fence") >+ (eq_attr "atom_sse_attr" "prefetch")))) >+ "atom-simple-0") >+ >+;; rcpps, rsqrtss, sqrt, ldmxcsr >+(define_insn_reservation "atom_sse_5" 7 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sse") >+ (ior (ior (eq_attr "atom_sse_attr" "sqrt") >+ (eq_attr "atom_sse_attr" "mxcsr")) >+ (and (eq_attr "atom_sse_attr" "rcp") >+ (eq_attr "mode" "V4SF"))))) >+ "atom-complex, atom-all-eu*6") >+ >+;; xmm->xmm >+(define_insn_reservation "atom_ssemov" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ssemov") >+ (and (match_operand 0 "register_operand" "xy") (match_operand 1 "register_operand" "xy")))) >+ "atom-simple-either") >+ >+;; reg->xmm >+(define_insn_reservation "atom_ssemov_2" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ssemov") >+ (and (match_operand 0 "register_operand" "xy") (match_operand 1 "register_operand" "r")))) >+ "atom-simple-0") >+ >+;; xmm->reg >+(define_insn_reservation "atom_ssemov_3" 3 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ssemov") >+ (and (match_operand 0 "register_operand" "r") (match_operand 1 "register_operand" "xy")))) >+ "atom-eu-0-3-1") >+ >+;; mov mem >+(define_insn_reservation "atom_ssemov_4" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ssemov") >+ (and (eq_attr "movu" "0") (eq_attr "memory" "!none")))) >+ "atom-simple-0") >+ >+;; movu mem >+(define_insn_reservation "atom_ssemov_5" 2 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ssemov") >+ (ior (eq_attr "movu" "1") (eq_attr "memory" "!none")))) >+ "atom-complex, atom-all-eu") >+ >+;; no memory simple >+(define_insn_reservation "atom_sseadd" 5 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseadd") >+ (and (eq_attr "memory" "none") >+ (and (eq_attr "mode" "!V2DF") >+ (eq_attr "atom_unit" "!complex"))))) >+ "atom-fadd-5c") >+ >+;; memory simple >+(define_insn_reservation "atom_sseadd_mem" 5 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseadd") >+ (and (eq_attr "memory" "!none") >+ (and (eq_attr "mode" "!V2DF") >+ (eq_attr "atom_unit" "!complex"))))) >+ "atom-dual-5c") >+ >+;; maxps, minps, *pd, hadd, hsub >+(define_insn_reservation "atom_sseadd_3" 8 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseadd") >+ (ior (eq_attr "mode" "V2DF") (eq_attr "atom_unit" "complex")))) >+ "atom-complex, atom-all-eu*7") >+ >+;; Except dppd/dpps >+(define_insn_reservation "atom_ssemul" 5 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ssemul") >+ (eq_attr "mode" "!SF"))) >+ "atom-fmul-5c") >+ >+;; Except dppd/dpps, 4 cycle if mulss >+(define_insn_reservation "atom_ssemul_2" 4 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ssemul") >+ (eq_attr "mode" "SF"))) >+ "atom-fmul-4c") >+ >+(define_insn_reservation "atom_ssecmp" 1 >+ (and (eq_attr "cpu" "atom") >+ (eq_attr "type" "ssecmp")) >+ "atom-simple-either") >+ >+(define_insn_reservation "atom_ssecomi" 10 >+ (and (eq_attr "cpu" "atom") >+ (eq_attr "type" "ssecomi")) >+ "atom-complex, atom-all-eu*9") >+ >+;; no memory and cvtpi2ps, cvtps2pi, cvttps2pi >+(define_insn_reservation "atom_ssecvt" 5 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ssecvt") >+ (ior (and (match_operand:V2SI 0 "register_operand") >+ (match_operand:V4SF 1 "register_operand")) >+ (and (match_operand:V4SF 0 "register_operand") >+ (match_operand:V2SI 1 "register_operand"))))) >+ "atom-fadd-5c") >+ >+;; memory and cvtpi2ps, cvtps2pi, cvttps2pi >+(define_insn_reservation "atom_ssecvt_2" 5 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ssecvt") >+ (ior (and (match_operand:V2SI 0 "register_operand") >+ (match_operand:V4SF 1 "memory_operand")) >+ (and (match_operand:V4SF 0 "register_operand") >+ (match_operand:V2SI 1 "memory_operand"))))) >+ "atom-dual-5c") >+ >+;; otherwise. 7 cycles average for cvtss2sd >+(define_insn_reservation "atom_ssecvt_3" 7 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "ssecvt") >+ (not (ior (and (match_operand:V2SI 0 "register_operand") >+ (match_operand:V4SF 1 "nonimmediate_operand")) >+ (and (match_operand:V4SF 0 "register_operand") >+ (match_operand:V2SI 1 "nonimmediate_operand")))))) >+ "atom-complex, atom-all-eu*6") >+ >+;; memory and cvtsi2sd >+(define_insn_reservation "atom_sseicvt" 5 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseicvt") >+ (and (match_operand:V2DF 0 "register_operand") >+ (match_operand:SI 1 "memory_operand")))) >+ "atom-dual-5c") >+ >+;; otherwise. 8 cycles average for cvtsd2si >+(define_insn_reservation "atom_sseicvt_2" 8 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "sseicvt") >+ (not (and (match_operand:V2DF 0 "register_operand") >+ (match_operand:SI 1 "memory_operand"))))) >+ "atom-complex, atom-all-eu*7") >+ >+(define_insn_reservation "atom_ssediv" 62 >+ (and (eq_attr "cpu" "atom") >+ (eq_attr "type" "ssediv")) >+ "atom-complex, atom-all-eu*12, nothing*49") >+ >+;; simple for fmov >+(define_insn_reservation "atom_fmov" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "fmov") >+ (eq_attr "memory" "none"))) >+ "atom-simple-either") >+ >+;; simple for fmov >+(define_insn_reservation "atom_fmov_mem" 1 >+ (and (eq_attr "cpu" "atom") >+ (and (eq_attr "type" "fmov") >+ (eq_attr "memory" "!none"))) >+ "atom-simple-either") >+ >+;; Define bypass here >+ >+;; There will be no stall from lea to non-mem EX insns >+(define_bypass 0 "atom_lea" >+ "atom_alu_carry, >+ atom_alu,atom_alu1,atom_negnot,atom_imov,atom_imovx, >+ atom_incdec, atom_setcc, atom_icmov, atom_pop") >+ >+(define_bypass 0 "atom_lea" >+ "atom_alu_mem, atom_alu_carry_mem, atom_alu1_mem, >+ atom_imovx_mem, atom_imovx_2_mem, >+ atom_imov_mem, atom_icmov_mem, atom_fmov_mem" >+ "!ix86_agi_dependent") >+ >+;; There will be 3 cycles stall from EX insns to AGAN insns LEA >+(define_bypass 4 "atom_alu_carry, >+ atom_alu,atom_alu1,atom_negnot,atom_imov,atom_imovx, >+ atom_incdec,atom_ishift,atom_ishift1,atom_rotate, >+ atom_rotate1, atom_setcc, atom_icmov, atom_pop, >+ atom_alu_mem, atom_alu_carry_mem, atom_alu1_mem, >+ atom_imovx_mem, atom_imovx_2_mem, >+ atom_imov_mem, atom_icmov_mem, atom_fmov_mem" >+ "atom_lea") >+ >+;; There will be 3 cycles stall from EX insns to insns need addr calculation >+(define_bypass 4 "atom_alu_carry, >+ atom_alu,atom_alu1,atom_negnot,atom_imov,atom_imovx, >+ atom_incdec,atom_ishift,atom_ishift1,atom_rotate, >+ atom_rotate1, atom_setcc, atom_icmov, atom_pop, >+ atom_imovx_mem, atom_imovx_2_mem, >+ atom_alu_mem, atom_alu_carry_mem, atom_alu1_mem, >+ atom_imov_mem, atom_icmov_mem, atom_fmov_mem" >+ "atom_alu_mem, atom_alu_carry_mem, atom_alu1_mem, >+ atom_negnot_mem, atom_imov_mem, atom_incdec_mem, >+ atom_imovx_mem, atom_imovx_2_mem, >+ atom_imul_mem, atom_icmp_mem, >+ atom_test_mem, atom_icmov_mem, atom_sselog_mem, >+ atom_sselog1_mem, atom_fmov_mem, atom_sseadd_mem, >+ atom_ishift_mem, atom_ishift1_mem, >+ atom_rotate_mem, atom_rotate1_mem" >+ "ix86_agi_dependent") >+ >+;; Stall from imul to lea is 8 cycles. >+(define_bypass 9 "atom_imul, atom_imul_mem" "atom_lea") >+ >+;; Stall from imul to memory address is 8 cycles. >+(define_bypass 9 "atom_imul, atom_imul_mem" >+ "atom_alu_mem, atom_alu_carry_mem, atom_alu1_mem, >+ atom_negnot_mem, atom_imov_mem, atom_incdec_mem, >+ atom_ishift_mem, atom_ishift1_mem, atom_rotate_mem, >+ atom_rotate1_mem, atom_imul_mem, atom_icmp_mem, >+ atom_test_mem, atom_icmov_mem, atom_sselog_mem, >+ atom_sselog1_mem, atom_fmov_mem, atom_sseadd_mem" >+ "ix86_agi_dependent") >+ >+;; There will be 0 cycle stall from cmp/test to jcc >+ >+;; There will be 1 cycle stall from flag producer to cmov and adc/sbb >+(define_bypass 2 "atom_icmp, atom_test, atom_alu, atom_alu_carry, >+ atom_alu1, atom_negnot, atom_incdec, atom_ishift, >+ atom_ishift1, atom_rotate, atom_rotate1" >+ "atom_icmov, atom_alu_carry") >diff --git a/gcc/config/i386/i386-c.c b/gcc/config/i386/i386-c.c >index 3d17c10..0c59b2f 100644 >--- a/gcc/config/i386/i386-c.c >+++ b/gcc/config/i386/i386-c.c >@@ -119,6 +119,10 @@ ix86_target_macros_internal (int isa_flag, > def_or_undef (parse_in, "__core2"); > def_or_undef (parse_in, "__core2__"); > break; >+ case PROCESSOR_ATOM: >+ def_or_undef (parse_in, "__atom"); >+ def_or_undef (parse_in, "__atom__"); >+ break; > /* use PROCESSOR_max to not set/unset the arch macro. */ > case PROCESSOR_max: > break; >@@ -187,6 +191,9 @@ ix86_target_macros_internal (int isa_flag, > case PROCESSOR_CORE2: > def_or_undef (parse_in, "__tune_core2__"); > break; >+ case PROCESSOR_ATOM: >+ def_or_undef (parse_in, "__tune_atom__"); >+ break; > case PROCESSOR_GENERIC32: > case PROCESSOR_GENERIC64: > break; >diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c >index 154c324..ea9d35e 100644 >--- a/gcc/config/i386/i386.c >+++ b/gcc/config/i386/i386.c >@@ -1036,6 +1036,79 @@ struct processor_costs core2_cost = { > 1, /* cond_not_taken_branch_cost. */ > }; > >+static const >+struct processor_costs atom_cost = { >+ COSTS_N_INSNS (1), /* cost of an add instruction */ >+ COSTS_N_INSNS (1) + 1, /* cost of a lea instruction */ >+ COSTS_N_INSNS (1), /* variable shift costs */ >+ COSTS_N_INSNS (1), /* constant shift costs */ >+ {COSTS_N_INSNS (3), /* cost of starting multiply for QI */ >+ COSTS_N_INSNS (4), /* HI */ >+ COSTS_N_INSNS (3), /* SI */ >+ COSTS_N_INSNS (4), /* DI */ >+ COSTS_N_INSNS (2)}, /* other */ >+ 0, /* cost of multiply per each bit set */ >+ {COSTS_N_INSNS (18), /* cost of a divide/mod for QI */ >+ COSTS_N_INSNS (26), /* HI */ >+ COSTS_N_INSNS (42), /* SI */ >+ COSTS_N_INSNS (74), /* DI */ >+ COSTS_N_INSNS (74)}, /* other */ >+ COSTS_N_INSNS (1), /* cost of movsx */ >+ COSTS_N_INSNS (1), /* cost of movzx */ >+ 8, /* "large" insn */ >+ 17, /* MOVE_RATIO */ >+ 2, /* cost for loading QImode using movzbl */ >+ {4, 4, 4}, /* cost of loading integer registers >+ in QImode, HImode and SImode. >+ Relative to reg-reg move (2). */ >+ {4, 4, 4}, /* cost of storing integer registers */ >+ 4, /* cost of reg,reg fld/fst */ >+ {12, 12, 12}, /* cost of loading fp registers >+ in SFmode, DFmode and XFmode */ >+ {6, 6, 8}, /* cost of storing fp registers >+ in SFmode, DFmode and XFmode */ >+ 2, /* cost of moving MMX register */ >+ {8, 8}, /* cost of loading MMX registers >+ in SImode and DImode */ >+ {8, 8}, /* cost of storing MMX registers >+ in SImode and DImode */ >+ 2, /* cost of moving SSE register */ >+ {8, 8, 8}, /* cost of loading SSE registers >+ in SImode, DImode and TImode */ >+ {8, 8, 8}, /* cost of storing SSE registers >+ in SImode, DImode and TImode */ >+ 5, /* MMX or SSE register to integer */ >+ 32, /* size of l1 cache. */ >+ 256, /* size of l2 cache. */ >+ 64, /* size of prefetch block */ >+ 6, /* number of parallel prefetches */ >+ 3, /* Branch cost */ >+ COSTS_N_INSNS (8), /* cost of FADD and FSUB insns. */ >+ COSTS_N_INSNS (8), /* cost of FMUL instruction. */ >+ COSTS_N_INSNS (20), /* cost of FDIV instruction. */ >+ COSTS_N_INSNS (8), /* cost of FABS instruction. */ >+ COSTS_N_INSNS (8), /* cost of FCHS instruction. */ >+ COSTS_N_INSNS (40), /* cost of FSQRT instruction. */ >+ {{libcall, {{11, loop}, {-1, rep_prefix_4_byte}}}, >+ {libcall, {{32, loop}, {64, rep_prefix_4_byte}, >+ {8192, rep_prefix_8_byte}, {-1, libcall}}}}, >+ {{libcall, {{8, loop}, {15, unrolled_loop}, >+ {2048, rep_prefix_4_byte}, {-1, libcall}}}, >+ {libcall, {{24, loop}, {32, unrolled_loop}, >+ {8192, rep_prefix_8_byte}, {-1, libcall}}}}, >+ 1, /* scalar_stmt_cost. */ >+ 1, /* scalar load_cost. */ >+ 1, /* scalar_store_cost. */ >+ 1, /* vec_stmt_cost. */ >+ 1, /* vec_to_scalar_cost. */ >+ 1, /* scalar_to_vec_cost. */ >+ 1, /* vec_align_load_cost. */ >+ 2, /* vec_unalign_load_cost. */ >+ 1, /* vec_store_cost. */ >+ 3, /* cond_taken_branch_cost. */ >+ 1, /* cond_not_taken_branch_cost. */ >+}; >+ > /* Generic64 should produce code tuned for Nocona and K8. */ > static const > struct processor_costs generic64_cost = { >@@ -1194,6 +1267,7 @@ const struct processor_costs *ix86_cost = &pentium_cost; > #define m_PENT4 (1<<PROCESSOR_PENTIUM4) > #define m_NOCONA (1<<PROCESSOR_NOCONA) > #define m_CORE2 (1<<PROCESSOR_CORE2) >+#define m_ATOM (1<<PROCESSOR_ATOM) > > #define m_GEODE (1<<PROCESSOR_GEODE) > #define m_K6 (1<<PROCESSOR_K6) >@@ -1231,10 +1305,11 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = { > m_486 | m_PENT, > > /* X86_TUNE_UNROLL_STRLEN */ >- m_486 | m_PENT | m_PPRO | m_AMD_MULTIPLE | m_K6 | m_CORE2 | m_GENERIC, >+ m_486 | m_PENT | m_ATOM | m_PPRO | m_AMD_MULTIPLE | m_K6 >+ | m_CORE2 | m_GENERIC, > > /* X86_TUNE_DEEP_BRANCH_PREDICTION */ >- m_PPRO | m_K6_GEODE | m_AMD_MULTIPLE | m_PENT4 | m_GENERIC, >+ m_ATOM | m_PPRO | m_K6_GEODE | m_AMD_MULTIPLE | m_PENT4 | m_GENERIC, > > /* X86_TUNE_BRANCH_PREDICTION_HINTS: Branch hints were put in P4 based > on simulation result. But after P4 was made, no performance benefit >@@ -1246,12 +1321,12 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = { > ~m_386, > > /* X86_TUNE_USE_SAHF */ >- m_PPRO | m_K6_GEODE | m_K8 | m_AMDFAM10 | m_PENT4 >+ m_ATOM | m_PPRO | m_K6_GEODE | m_K8 | m_AMDFAM10 | m_PENT4 > | m_NOCONA | m_CORE2 | m_GENERIC, > > /* X86_TUNE_MOVX: Enable to zero extend integer registers to avoid > partial dependencies. */ >- m_AMD_MULTIPLE | m_PPRO | m_PENT4 | m_NOCONA >+ m_AMD_MULTIPLE | m_ATOM | m_PPRO | m_PENT4 | m_NOCONA > | m_CORE2 | m_GENERIC | m_GEODE /* m_386 | m_K6 */, > > /* X86_TUNE_PARTIAL_REG_STALL: We probably ought to watch for partial >@@ -1271,13 +1346,13 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = { > m_386 | m_486 | m_K6_GEODE, > > /* X86_TUNE_USE_SIMODE_FIOP */ >- ~(m_PPRO | m_AMD_MULTIPLE | m_PENT | m_CORE2 | m_GENERIC), >+ ~(m_PPRO | m_AMD_MULTIPLE | m_PENT | m_ATOM | m_CORE2 | m_GENERIC), > > /* X86_TUNE_USE_MOV0 */ > m_K6, > > /* X86_TUNE_USE_CLTD */ >- ~(m_PENT | m_K6 | m_CORE2 | m_GENERIC), >+ ~(m_PENT | m_ATOM | m_K6 | m_CORE2 | m_GENERIC), > > /* X86_TUNE_USE_XCHGB: Use xchgb %rh,%rl instead of rolw/rorw $8,rx. */ > m_PENT4, >@@ -1292,8 +1367,8 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = { > ~(m_PENT | m_PPRO), > > /* X86_TUNE_PROMOTE_QIMODE */ >- m_K6_GEODE | m_PENT | m_386 | m_486 | m_AMD_MULTIPLE | m_CORE2 >- | m_GENERIC /* | m_PENT4 ? */, >+ m_K6_GEODE | m_PENT | m_ATOM | m_386 | m_486 | m_AMD_MULTIPLE >+ | m_CORE2 | m_GENERIC /* | m_PENT4 ? */, > > /* X86_TUNE_FAST_PREFIX */ > ~(m_PENT | m_486 | m_386), >@@ -1317,26 +1392,28 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = { > m_PPRO, > > /* X86_TUNE_ADD_ESP_4: Enable if add/sub is preferred over 1/2 push/pop. */ >- m_AMD_MULTIPLE | m_K6_GEODE | m_PENT4 | m_NOCONA | m_CORE2 | m_GENERIC, >+ m_ATOM | m_AMD_MULTIPLE | m_K6_GEODE | m_PENT4 | m_NOCONA >+ | m_CORE2 | m_GENERIC, > > /* X86_TUNE_ADD_ESP_8 */ >- m_AMD_MULTIPLE | m_PPRO | m_K6_GEODE | m_386 >+ m_AMD_MULTIPLE | m_ATOM | m_PPRO | m_K6_GEODE | m_386 > | m_486 | m_PENT4 | m_NOCONA | m_CORE2 | m_GENERIC, > > /* X86_TUNE_SUB_ESP_4 */ >- m_AMD_MULTIPLE | m_PPRO | m_PENT4 | m_NOCONA | m_CORE2 | m_GENERIC, >+ m_AMD_MULTIPLE | m_ATOM | m_PPRO | m_PENT4 | m_NOCONA | m_CORE2 >+ | m_GENERIC, > > /* X86_TUNE_SUB_ESP_8 */ >- m_AMD_MULTIPLE | m_PPRO | m_386 | m_486 >+ m_AMD_MULTIPLE | m_ATOM | m_PPRO | m_386 | m_486 > | m_PENT4 | m_NOCONA | m_CORE2 | m_GENERIC, > > /* X86_TUNE_INTEGER_DFMODE_MOVES: Enable if integer moves are preferred > for DFmode copies */ >- ~(m_AMD_MULTIPLE | m_PENT4 | m_NOCONA | m_PPRO | m_CORE2 >+ ~(m_AMD_MULTIPLE | m_ATOM | m_PENT4 | m_NOCONA | m_PPRO | m_CORE2 > | m_GENERIC | m_GEODE), > > /* X86_TUNE_PARTIAL_REG_DEPENDENCY */ >- m_AMD_MULTIPLE | m_PENT4 | m_NOCONA | m_CORE2 | m_GENERIC, >+ m_AMD_MULTIPLE | m_ATOM | m_PENT4 | m_NOCONA | m_CORE2 | m_GENERIC, > > /* X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY: In the Generic model we have a > conflict here in between PPro/Pentium4 based chips that thread 128bit >@@ -1347,7 +1424,8 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = { > shows that disabling this option on P4 brings over 20% SPECfp regression, > while enabling it on K8 brings roughly 2.4% regression that can be partly > masked by careful scheduling of moves. */ >- m_PENT4 | m_NOCONA | m_PPRO | m_CORE2 | m_GENERIC | m_AMDFAM10, >+ m_ATOM | m_PENT4 | m_NOCONA | m_PPRO | m_CORE2 | m_GENERIC >+ | m_AMDFAM10, > > /* X86_TUNE_SSE_UNALIGNED_MOVE_OPTIMAL */ > m_AMDFAM10, >@@ -1365,13 +1443,13 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = { > m_PPRO | m_PENT4 | m_NOCONA, > > /* X86_TUNE_MEMORY_MISMATCH_STALL */ >- m_AMD_MULTIPLE | m_PENT4 | m_NOCONA | m_CORE2 | m_GENERIC, >+ m_AMD_MULTIPLE | m_ATOM | m_PENT4 | m_NOCONA | m_CORE2 | m_GENERIC, > > /* X86_TUNE_PROLOGUE_USING_MOVE */ >- m_ATHLON_K8 | m_PPRO | m_CORE2 | m_GENERIC, >+ m_ATHLON_K8 | m_ATOM | m_PPRO | m_CORE2 | m_GENERIC, > > /* X86_TUNE_EPILOGUE_USING_MOVE */ >- m_ATHLON_K8 | m_PPRO | m_CORE2 | m_GENERIC, >+ m_ATHLON_K8 | m_ATOM | m_PPRO | m_CORE2 | m_GENERIC, > > /* X86_TUNE_SHIFT1 */ > ~m_486, >@@ -1380,29 +1458,32 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = { > m_AMD_MULTIPLE, > > /* X86_TUNE_INTER_UNIT_MOVES */ >- ~(m_AMD_MULTIPLE | m_GENERIC), >+ ~(m_AMD_MULTIPLE | m_ATOM | m_GENERIC), > > /* X86_TUNE_INTER_UNIT_CONVERSIONS */ > ~(m_AMDFAM10), > > /* X86_TUNE_FOUR_JUMP_LIMIT: Some CPU cores are not able to predict more > than 4 branch instructions in the 16 byte window. */ >- m_PPRO | m_AMD_MULTIPLE | m_PENT4 | m_NOCONA | m_CORE2 | m_GENERIC, >+ m_ATOM | m_PPRO | m_AMD_MULTIPLE | m_PENT4 | m_NOCONA | m_CORE2 >+ | m_GENERIC, > > /* X86_TUNE_SCHEDULE */ >- m_PPRO | m_AMD_MULTIPLE | m_K6_GEODE | m_PENT | m_CORE2 | m_GENERIC, >+ m_PPRO | m_AMD_MULTIPLE | m_K6_GEODE | m_PENT | m_ATOM | m_CORE2 >+ | m_GENERIC, > > /* X86_TUNE_USE_BT */ >- m_AMD_MULTIPLE | m_CORE2 | m_GENERIC, >+ m_AMD_MULTIPLE | m_ATOM | m_CORE2 | m_GENERIC, > > /* X86_TUNE_USE_INCDEC */ >- ~(m_PENT4 | m_NOCONA | m_GENERIC), >+ ~(m_PENT4 | m_NOCONA | m_GENERIC | m_ATOM), > > /* X86_TUNE_PAD_RETURNS */ > m_AMD_MULTIPLE | m_CORE2 | m_GENERIC, > > /* X86_TUNE_EXT_80387_CONSTANTS */ >- m_K6_GEODE | m_ATHLON_K8 | m_PENT4 | m_NOCONA | m_PPRO | m_CORE2 | m_GENERIC, >+ m_K6_GEODE | m_ATHLON_K8 | m_ATOM | m_PENT4 | m_NOCONA | m_PPRO >+ | m_CORE2 | m_GENERIC, > > /* X86_TUNE_SHORTEN_X87_SSE */ > ~m_K8, >@@ -1447,6 +1528,10 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = { > with a subsequent conditional jump instruction into a single > compare-and-branch uop. */ > m_CORE2, >+ >+ /* X86_TUNE_OPT_AGU: Optimize for Address Generation Unit. This flag >+ will impact LEA instruction selection. */ >+ m_ATOM, > }; > > /* Feature tests against the various architecture variations. */ >@@ -1472,10 +1557,11 @@ static unsigned int initial_ix86_arch_features[X86_ARCH_LAST] = { > }; > > static const unsigned int x86_accumulate_outgoing_args >- = m_AMD_MULTIPLE | m_PENT4 | m_NOCONA | m_PPRO | m_CORE2 | m_GENERIC; >+ = m_AMD_MULTIPLE | m_ATOM | m_PENT4 | m_NOCONA | m_PPRO | m_CORE2 >+ | m_GENERIC; > > static const unsigned int x86_arch_always_fancy_math_387 >- = m_PENT | m_PPRO | m_AMD_MULTIPLE | m_PENT4 >+ = m_PENT | m_ATOM | m_PPRO | m_AMD_MULTIPLE | m_PENT4 > | m_NOCONA | m_CORE2 | m_GENERIC; > > static enum stringop_alg stringop_alg = no_stringop; >@@ -1958,7 +2044,8 @@ static const struct ptt processor_target_table[PROCESSOR_max] = > {&core2_cost, 16, 10, 16, 10, 16}, > {&generic32_cost, 16, 7, 16, 7, 16}, > {&generic64_cost, 16, 10, 16, 10, 16}, >- {&amdfam10_cost, 32, 24, 32, 7, 32} >+ {&amdfam10_cost, 32, 24, 32, 7, 32}, >+ {&atom_cost, 16, 7, 16, 7, 16} > }; > > static const char *const cpu_names[TARGET_CPU_DEFAULT_max] = >@@ -1976,6 +2063,7 @@ static const char *const cpu_names[TARGET_CPU_DEFAULT_max] = > "prescott", > "nocona", > "core2", >+ "atom", > "geode", > "k6", > "k6-2", >@@ -2534,6 +2622,9 @@ override_options (bool main_args_p) > {"core2", PROCESSOR_CORE2, CPU_CORE2, > PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3 > | PTA_SSSE3 | PTA_CX16}, >+ {"atom", PROCESSOR_ATOM, CPU_ATOM, >+ PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3 >+ | PTA_SSSE3 | PTA_CX16}, > {"geode", PROCESSOR_GEODE, CPU_GEODE, > PTA_MMX | PTA_3DNOW | PTA_3DNOW_A |PTA_PREFETCH_SSE}, > {"k6", PROCESSOR_K6, CPU_K6, PTA_MMX}, >@@ -19026,6 +19117,7 @@ ix86_issue_rate (void) > switch (ix86_tune) > { > case PROCESSOR_PENTIUM: >+ case PROCESSOR_ATOM: > case PROCESSOR_K6: > return 2; > >@@ -19226,6 +19318,7 @@ ix86_adjust_cost (rtx insn, rtx link, rtx dep_insn, int cost) > case PROCESSOR_ATHLON: > case PROCESSOR_K8: > case PROCESSOR_AMDFAM10: >+ case PROCESSOR_ATOM: > case PROCESSOR_GENERIC32: > case PROCESSOR_GENERIC64: > memory = get_attr_memory (insn); >diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h >index 89e26f6..9746e15 100644 >--- a/gcc/config/i386/i386.h >+++ b/gcc/config/i386/i386.h >@@ -231,6 +231,7 @@ extern const struct processor_costs ix86_size_cost; > #define TARGET_GENERIC64 (ix86_tune == PROCESSOR_GENERIC64) > #define TARGET_GENERIC (TARGET_GENERIC32 || TARGET_GENERIC64) > #define TARGET_AMDFAM10 (ix86_tune == PROCESSOR_AMDFAM10) >+#define TARGET_ATOM (ix86_tune == PROCESSOR_ATOM) > > /* Feature tests against the various tunings. */ > enum ix86_tune_indices { >@@ -295,6 +296,7 @@ enum ix86_tune_indices { > X86_TUNE_USE_VECTOR_FP_CONVERTS, > X86_TUNE_USE_VECTOR_CONVERTS, > X86_TUNE_FUSE_CMP_AND_BRANCH, >+ X86_TUNE_OPT_AGU, > > X86_TUNE_LAST > }; >@@ -382,6 +384,7 @@ extern unsigned char ix86_tune_features[X86_TUNE_LAST]; > ix86_tune_features[X86_TUNE_USE_VECTOR_CONVERTS] > #define TARGET_FUSE_CMP_AND_BRANCH \ > ix86_tune_features[X86_TUNE_FUSE_CMP_AND_BRANCH] >+#define TARGET_OPT_AGU ix86_tune_features[X86_TUNE_OPT_AGU] > > /* Feature tests against the various architecture variations. */ > enum ix86_arch_indices { >@@ -567,6 +570,7 @@ enum target_cpu_default > TARGET_CPU_DEFAULT_prescott, > TARGET_CPU_DEFAULT_nocona, > TARGET_CPU_DEFAULT_core2, >+ TARGET_CPU_DEFAULT_atom, > > TARGET_CPU_DEFAULT_geode, > TARGET_CPU_DEFAULT_k6, >@@ -2272,6 +2276,7 @@ enum processor_type > PROCESSOR_GENERIC32, > PROCESSOR_GENERIC64, > PROCESSOR_AMDFAM10, >+ PROCESSOR_ATOM, > PROCESSOR_max > }; > >diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md >index c43f336..792d0f3 100644 >--- a/gcc/config/i386/i386.md >+++ b/gcc/config/i386/i386.md >@@ -316,7 +316,7 @@ > > > ;; Processor type. >-(define_attr "cpu" "none,pentium,pentiumpro,geode,k6,athlon,k8,core2, >+(define_attr "cpu" "none,pentium,pentiumpro,geode,k6,athlon,k8,core2,atom, > generic64,amdfam10" > (const (symbol_ref "ix86_schedule"))) > >@@ -612,6 +612,12 @@ > (define_attr "i387_cw" "trunc,floor,ceil,mask_pm,uninitialized,any" > (const_string "any")) > >+;; Define attribute to classify add/sub insns that consumes carry flag (CF) >+(define_attr "use_carry" "0,1" (const_string "0")) >+ >+;; Define attribute to indicate unaligned ssemov insns >+(define_attr "movu" "0,1" (const_string "0")) >+ > ;; Describe a user's asm statement. > (define_asm_attributes > [(set_attr "length" "128") >@@ -727,6 +733,7 @@ > (include "k6.md") > (include "athlon.md") > (include "geode.md") >+(include "atom.md") > > > ;; Operand and operator predicates and constraints >@@ -5816,6 +5823,7 @@ > "TARGET_64BIT && ix86_binary_operator_ok (PLUS, DImode, operands)" > "adc{q}\t{%2, %0|%0, %2}" > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "mode" "DI")]) > >@@ -5890,6 +5898,7 @@ > "ix86_binary_operator_ok (PLUS, QImode, operands)" > "adc{b}\t{%2, %0|%0, %2}" > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "mode" "QI")]) > >@@ -5902,6 +5911,7 @@ > "ix86_binary_operator_ok (PLUS, HImode, operands)" > "adc{w}\t{%2, %0|%0, %2}" > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "mode" "HI")]) > >@@ -5914,6 +5924,7 @@ > "ix86_binary_operator_ok (PLUS, SImode, operands)" > "adc{l}\t{%2, %0|%0, %2}" > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "mode" "SI")]) > >@@ -5927,6 +5938,7 @@ > "TARGET_64BIT && ix86_binary_operator_ok (PLUS, SImode, operands)" > "adc{l}\t{%2, %k0|%k0, %2}" > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "mode" "SI")]) > >@@ -6156,9 +6168,9 @@ > (set_attr "mode" "SI")]) > > (define_insn "*adddi_1_rex64" >- [(set (match_operand:DI 0 "nonimmediate_operand" "=r,rm,r") >- (plus:DI (match_operand:DI 1 "nonimmediate_operand" "%0,0,r") >- (match_operand:DI 2 "x86_64_general_operand" "rme,re,le"))) >+ [(set (match_operand:DI 0 "nonimmediate_operand" "=r,rm,r,r") >+ (plus:DI (match_operand:DI 1 "nonimmediate_operand" "%0,0,r,r") >+ (match_operand:DI 2 "x86_64_general_operand" "rme,re,0,le"))) > (clobber (reg:CC FLAGS_REG))] > "TARGET_64BIT && ix86_binary_operator_ok (PLUS, DImode, operands)" > { >@@ -6179,6 +6191,10 @@ > } > > default: >+ /* Use add as much as possible to replace lea for AGU optimization. */ >+ if (which_alternative == 2 && TARGET_OPT_AGU) >+ return "add{q}\t{%1, %0|%0, %1}"; >+ > gcc_assert (rtx_equal_p (operands[0], operands[1])); > > /* Make things pretty and `subl $4,%eax' rather than `addl $-4, %eax'. >@@ -6197,8 +6213,11 @@ > } > } > [(set (attr "type") >- (cond [(eq_attr "alternative" "2") >+ (cond [(and (eq_attr "alternative" "2") >+ (eq (symbol_ref "TARGET_OPT_AGU") (const_int 0))) > (const_string "lea") >+ (eq_attr "alternative" "3") >+ (const_string "lea") > ; Current assemblers are broken and do not allow @GOTOFF in > ; ought but a memory context. > (match_operand:DI 2 "pic_symbolic_operand" "") >@@ -6215,8 +6234,7 @@ > (plus:DI (match_operand:DI 1 "register_operand" "") > (match_operand:DI 2 "x86_64_nonmemory_operand" ""))) > (clobber (reg:CC FLAGS_REG))] >- "TARGET_64BIT && reload_completed >- && true_regnum (operands[0]) != true_regnum (operands[1])" >+ "TARGET_64BIT && reload_completed" > [(set (match_dup 0) > (plus:DI (match_dup 1) > (match_dup 2)))] >@@ -6420,9 +6438,9 @@ > > > (define_insn "*addsi_1" >- [(set (match_operand:SI 0 "nonimmediate_operand" "=r,rm,r") >- (plus:SI (match_operand:SI 1 "nonimmediate_operand" "%0,0,r") >- (match_operand:SI 2 "general_operand" "g,ri,li"))) >+ [(set (match_operand:SI 0 "nonimmediate_operand" "=r,rm,r,r") >+ (plus:SI (match_operand:SI 1 "nonimmediate_operand" "%0,0,r,r") >+ (match_operand:SI 2 "general_operand" "g,ri,0,li"))) > (clobber (reg:CC FLAGS_REG))] > "ix86_binary_operator_ok (PLUS, SImode, operands)" > { >@@ -6443,6 +6461,10 @@ > } > > default: >+ /* Use add as much as possible to replace lea for AGU optimization. */ >+ if (which_alternative == 2 && TARGET_OPT_AGU) >+ return "add{l}\t{%1, %0|%0, %1}"; >+ > gcc_assert (rtx_equal_p (operands[0], operands[1])); > > /* Make things pretty and `subl $4,%eax' rather than `addl $-4, %eax'. >@@ -6459,7 +6481,10 @@ > } > } > [(set (attr "type") >- (cond [(eq_attr "alternative" "2") >+ (cond [(and (eq_attr "alternative" "2") >+ (eq (symbol_ref "TARGET_OPT_AGU") (const_int 0))) >+ (const_string "lea") >+ (eq_attr "alternative" "3") > (const_string "lea") > ; Current assemblers are broken and do not allow @GOTOFF in > ; ought but a memory context. >@@ -6477,8 +6502,7 @@ > (plus (match_operand 1 "register_operand" "") > (match_operand 2 "nonmemory_operand" ""))) > (clobber (reg:CC FLAGS_REG))] >- "reload_completed >- && true_regnum (operands[0]) != true_regnum (operands[1])" >+ "reload_completed" > [(const_int 0)] > { > rtx pat; >@@ -7580,6 +7604,7 @@ > "TARGET_64BIT && ix86_binary_operator_ok (MINUS, DImode, operands)" > "sbb{q}\t{%2, %0|%0, %2}" > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "mode" "DI")]) > >@@ -7628,6 +7653,7 @@ > "ix86_binary_operator_ok (MINUS, QImode, operands)" > "sbb{b}\t{%2, %0|%0, %2}" > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "mode" "QI")]) > >@@ -7640,6 +7666,7 @@ > "ix86_binary_operator_ok (MINUS, HImode, operands)" > "sbb{w}\t{%2, %0|%0, %2}" > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "mode" "HI")]) > >@@ -7652,6 +7679,7 @@ > "ix86_binary_operator_ok (MINUS, SImode, operands)" > "sbb{l}\t{%2, %0|%0, %2}" > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "mode" "SI")]) > >@@ -15275,6 +15303,7 @@ > "reload_completed" > "ret" > [(set_attr "length" "1") >+ (set_attr "atom_unit" "jeu") > (set_attr "length_immediate" "0") > (set_attr "modrm" "0")]) > >@@ -15287,6 +15316,7 @@ > "reload_completed" > "rep\;ret" > [(set_attr "length" "1") >+ (set_attr "atom_unit" "jeu") > (set_attr "length_immediate" "0") > (set_attr "prefix_rep" "1") > (set_attr "modrm" "0")]) >@@ -15297,6 +15327,7 @@ > "reload_completed" > "ret\t%0" > [(set_attr "length" "3") >+ (set_attr "atom_unit" "jeu") > (set_attr "length_immediate" "2") > (set_attr "modrm" "0")]) > >@@ -16418,6 +16449,7 @@ > "TARGET_SSE_MATH" > "%vrcpss\t{%1, %d0|%d0, %1}" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "rcp") > (set_attr "prefix" "maybe_vex") > (set_attr "mode" "SF")]) > >@@ -16777,6 +16809,7 @@ > "TARGET_SSE_MATH" > "%vrsqrtss\t{%1, %d0|%d0, %1}" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "rcp") > (set_attr "prefix" "maybe_vex") > (set_attr "mode" "SF")]) > >@@ -16797,6 +16830,7 @@ > "SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH" > "%vsqrts<ssemodefsuffix>\t{%1, %d0|%d0, %1}" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "sqrt") > (set_attr "prefix" "maybe_vex") > (set_attr "mode" "<MODE>") > (set_attr "athlon_decode" "*") >@@ -19850,6 +19884,7 @@ > ; Since we don't have the proper number of operands for an alu insn, > ; fill in all the blanks. > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "memory" "none") > (set_attr "imm_disp" "false") >@@ -19865,6 +19900,7 @@ > "" > "sbb{q}\t%0, %0" > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "memory" "none") > (set_attr "imm_disp" "false") >@@ -19908,6 +19944,7 @@ > ; Since we don't have the proper number of operands for an alu insn, > ; fill in all the blanks. > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "memory" "none") > (set_attr "imm_disp" "false") >@@ -19923,6 +19960,7 @@ > "" > "sbb{l}\t%0, %0" > [(set_attr "type" "alu") >+ (set_attr "use_carry" "1") > (set_attr "pent_pair" "pu") > (set_attr "memory" "none") > (set_attr "imm_disp" "false") >@@ -20255,7 +20293,8 @@ > } > } > [(set (attr "type") >- (cond [(eq_attr "alternative" "0") >+ (cond [(and (eq_attr "alternative" "0") >+ (eq (symbol_ref "TARGET_OPT_AGU") (const_int 0))) > (const_string "alu") > (match_operand:SI 2 "const0_operand" "") > (const_string "imov") >@@ -20298,7 +20337,8 @@ > } > } > [(set (attr "type") >- (cond [(eq_attr "alternative" "0") >+ (cond [(and (eq_attr "alternative" "0") >+ (eq (symbol_ref "TARGET_OPT_AGU") (const_int 0))) > (const_string "alu") > (match_operand:DI 2 "const0_operand" "") > (const_string "imov") >@@ -21790,6 +21830,7 @@ > return patterns[locality]; > } > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "prefetch") > (set_attr "memory" "none")]) > > (define_insn "*prefetch_sse_rex" >@@ -21808,6 +21849,7 @@ > return patterns[locality]; > } > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "prefetch") > (set_attr "memory" "none")]) > > (define_insn "*prefetch_3dnow" >diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md >index e6d1fd1..977a23c 100644 >--- a/gcc/config/i386/sse.md >+++ b/gcc/config/i386/sse.md >@@ -338,6 +338,7 @@ > && !(MEM_P (operands[0]) && MEM_P (operands[1]))" > "vmovup<avxmodesuffixf2c>\t{%1, %0|%0, %1}" > [(set_attr "type" "ssemov") >+ (set_attr "movu" "1") > (set_attr "prefix" "vex") > (set_attr "mode" "<MODE>")]) > >@@ -363,6 +364,7 @@ > && !(MEM_P (operands[0]) && MEM_P (operands[1]))" > "movup<ssemodesuffixf2c>\t{%1, %0|%0, %1}" > [(set_attr "type" "ssemov") >+ (set_attr "movu" "1") > (set_attr "mode" "<MODE>")]) > > (define_insn "avx_movdqu<avxmodesuffix>" >@@ -373,6 +375,7 @@ > "TARGET_AVX && !(MEM_P (operands[0]) && MEM_P (operands[1]))" > "vmovdqu\t{%1, %0|%0, %1}" > [(set_attr "type" "ssemov") >+ (set_attr "movu" "1") > (set_attr "prefix" "vex") > (set_attr "mode" "<avxvecmode>")]) > >@@ -383,6 +386,7 @@ > "TARGET_SSE2 && !(MEM_P (operands[0]) && MEM_P (operands[1]))" > "movdqu\t{%1, %0|%0, %1}" > [(set_attr "type" "ssemov") >+ (set_attr "movu" "1") > (set_attr "prefix_data16" "1") > (set_attr "mode" "TI")]) > >@@ -424,7 +428,7 @@ > UNSPEC_MOVNT))] > "TARGET_SSE2" > "movntdq\t{%1, %0|%0, %1}" >- [(set_attr "type" "ssecvt") >+ [(set_attr "type" "ssemov") > (set_attr "prefix_data16" "1") > (set_attr "mode" "TI")]) > >@@ -434,7 +438,7 @@ > UNSPEC_MOVNT))] > "TARGET_SSE2" > "movnti\t{%1, %0|%0, %1}" >- [(set_attr "type" "ssecvt") >+ [(set_attr "type" "ssemov") > (set_attr "mode" "V2DF")]) > > (define_insn "avx_lddqu<avxmodesuffix>" >@@ -445,6 +449,7 @@ > "TARGET_AVX" > "vlddqu\t{%1, %0|%0, %1}" > [(set_attr "type" "ssecvt") >+ (set_attr "movu" "1") > (set_attr "prefix" "vex") > (set_attr "mode" "<avxvecmode>")]) > >@@ -454,7 +459,8 @@ > UNSPEC_LDDQU))] > "TARGET_SSE3" > "lddqu\t{%1, %0|%0, %1}" >- [(set_attr "type" "ssecvt") >+ [(set_attr "type" "ssemov") >+ (set_attr "movu" "1") > (set_attr "prefix_rep" "1") > (set_attr "mode" "TI")]) > >@@ -761,6 +767,7 @@ > "TARGET_SSE" > "%vrcpps\t{%1, %0|%0, %1}" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "rcp") > (set_attr "prefix" "maybe_vex") > (set_attr "mode" "V4SF")]) > >@@ -787,6 +794,7 @@ > "TARGET_SSE" > "rcpss\t{%1, %0|%0, %1}" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "rcp") > (set_attr "mode" "SF")]) > > (define_expand "sqrtv8sf2" >@@ -832,6 +840,7 @@ > "TARGET_SSE" > "%vsqrtps\t{%1, %0|%0, %1}" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "sqrt") > (set_attr "prefix" "maybe_vex") > (set_attr "mode" "V4SF")]) > >@@ -876,6 +885,7 @@ > "SSE_VEC_FLOAT_MODE_P (<MODE>mode)" > "sqrts<ssemodesuffixf2c>\t{%1, %0|%0, %1}" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "sqrt") > (set_attr "mode" "<ssescalarmode>")]) > > (define_expand "rsqrtv8sf2" >@@ -1039,7 +1049,7 @@ > (const_int 1)))] > "SSE_VEC_FLOAT_MODE_P (<MODE>mode)" > "<maxminfprefix>s<ssemodesuffixf2c>\t{%2, %0|%0, %2}" >- [(set_attr "type" "sse") >+ [(set_attr "type" "sseadd") > (set_attr "mode" "<ssescalarmode>")]) > > ;; These versions of the min/max patterns implement exactly the operations >@@ -1175,6 +1185,7 @@ > "TARGET_SSE3" > "addsubpd\t{%2, %0|%0, %2}" > [(set_attr "type" "sseadd") >+ (set_attr "atom_unit" "complex") > (set_attr "mode" "V2DF")]) > > (define_insn "avx_h<plusminus_insn>v4df3" >@@ -1298,6 +1309,7 @@ > "TARGET_SSE3" > "h<plusminus_mnemonic>ps\t{%2, %0|%0, %2}" > [(set_attr "type" "sseadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_rep" "1") > (set_attr "mode" "V4SF")]) > >@@ -5066,6 +5078,7 @@ > "TARGET_SSE2 && ix86_binary_operator_ok (MULT, V8HImode, operands)" > "pmaddwd\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "simul") > (set_attr "prefix_data16" "1") > (set_attr "mode" "TI")]) > >@@ -7025,6 +7038,7 @@ > movq\t{%H1, %0|%0, %H1} > mov{q}\t{%H1, %0|%0, %H1}" > [(set_attr "type" "ssemov,sseishft,ssemov,imov") >+ (set_attr "atom_unit" "*,sishuf,*,*") > (set_attr "memory" "*,none,*,*") > (set_attr "mode" "V2SF,TI,TI,DI")]) > >@@ -7057,6 +7071,7 @@ > psrldq\t{$8, %0|%0, 8} > movq\t{%H1, %0|%0, %H1}" > [(set_attr "type" "ssemov,sseishft,ssemov") >+ (set_attr "atom_unit" "*,sishuf,*") > (set_attr "memory" "*,none,*") > (set_attr "mode" "V2SF,TI,TI")]) > >@@ -7614,6 +7629,7 @@ > "TARGET_SSE2" > "psadbw\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "simul") > (set_attr "prefix_data16" "1") > (set_attr "mode" "TI")]) > >@@ -7635,7 +7651,7 @@ > UNSPEC_MOVMSK))] > "SSE_VEC_FLOAT_MODE_P (<MODE>mode)" > "%vmovmskp<ssemodesuffixf2c>\t{%1, %0|%0, %1}" >- [(set_attr "type" "ssecvt") >+ [(set_attr "type" "ssemov") > (set_attr "prefix" "maybe_vex") > (set_attr "mode" "<MODE>")]) > >@@ -7645,7 +7661,7 @@ > UNSPEC_MOVMSK))] > "TARGET_SSE2" > "%vpmovmskb\t{%1, %0|%0, %1}" >- [(set_attr "type" "ssecvt") >+ [(set_attr "type" "ssemov") > (set_attr "prefix_data16" "1") > (set_attr "prefix" "maybe_vex") > (set_attr "mode" "SI")]) >@@ -7668,7 +7684,7 @@ > "TARGET_SSE2 && !TARGET_64BIT" > ;; @@@ check ordering of operands in intel/nonintel syntax > "%vmaskmovdqu\t{%2, %1|%1, %2}" >- [(set_attr "type" "ssecvt") >+ [(set_attr "type" "ssemov") > (set_attr "prefix_data16" "1") > (set_attr "prefix" "maybe_vex") > (set_attr "mode" "TI")]) >@@ -7682,7 +7698,7 @@ > "TARGET_SSE2 && TARGET_64BIT" > ;; @@@ check ordering of operands in intel/nonintel syntax > "%vmaskmovdqu\t{%2, %1|%1, %2}" >- [(set_attr "type" "ssecvt") >+ [(set_attr "type" "ssemov") > (set_attr "prefix_data16" "1") > (set_attr "prefix" "maybe_vex") > (set_attr "mode" "TI")]) >@@ -7693,6 +7709,7 @@ > "TARGET_SSE" > "%vldmxcsr\t%0" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "mxcsr") > (set_attr "prefix" "maybe_vex") > (set_attr "memory" "load")]) > >@@ -7702,6 +7719,7 @@ > "TARGET_SSE" > "%vstmxcsr\t%0" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "mxcsr") > (set_attr "prefix" "maybe_vex") > (set_attr "memory" "store")]) > >@@ -7720,6 +7738,7 @@ > "TARGET_SSE || TARGET_3DNOW_A" > "sfence" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "fence") > (set_attr "memory" "unknown")]) > > (define_insn "sse2_clflush" >@@ -7728,6 +7747,7 @@ > "TARGET_SSE2" > "clflush\t%a0" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "fence") > (set_attr "memory" "unknown")]) > > (define_expand "sse2_mfence" >@@ -7745,6 +7765,7 @@ > "TARGET_64BIT || TARGET_SSE2" > "mfence" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "fence") > (set_attr "memory" "unknown")]) > > (define_expand "sse2_lfence" >@@ -7762,6 +7783,7 @@ > "TARGET_SSE2" > "lfence" > [(set_attr "type" "sse") >+ (set_attr "atom_sse_attr" "lfence") > (set_attr "memory" "unknown")]) > > (define_insn "sse3_mwait" >@@ -7885,6 +7907,7 @@ > "TARGET_SSSE3" > "phaddw\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_data16" "1") > (set_attr "prefix_extra" "1") > (set_attr "mode" "TI")]) >@@ -7913,6 +7936,7 @@ > "TARGET_SSSE3" > "phaddw\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_extra" "1") > (set_attr "mode" "DI")]) > >@@ -7967,6 +7991,7 @@ > "TARGET_SSSE3" > "phaddd\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_data16" "1") > (set_attr "prefix_extra" "1") > (set_attr "mode" "TI")]) >@@ -7987,6 +8012,7 @@ > "TARGET_SSSE3" > "phaddd\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_extra" "1") > (set_attr "mode" "DI")]) > >@@ -8073,6 +8099,7 @@ > "TARGET_SSSE3" > "phaddsw\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_data16" "1") > (set_attr "prefix_extra" "1") > (set_attr "mode" "TI")]) >@@ -8101,6 +8128,7 @@ > "TARGET_SSSE3" > "phaddsw\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_extra" "1") > (set_attr "mode" "DI")]) > >@@ -8187,6 +8215,7 @@ > "TARGET_SSSE3" > "phsubw\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_data16" "1") > (set_attr "prefix_extra" "1") > (set_attr "mode" "TI")]) >@@ -8215,6 +8244,7 @@ > "TARGET_SSSE3" > "phsubw\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_extra" "1") > (set_attr "mode" "DI")]) > >@@ -8269,6 +8299,7 @@ > "TARGET_SSSE3" > "phsubd\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_data16" "1") > (set_attr "prefix_extra" "1") > (set_attr "mode" "TI")]) >@@ -8289,6 +8320,7 @@ > "TARGET_SSSE3" > "phsubd\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_extra" "1") > (set_attr "mode" "DI")]) > >@@ -8375,6 +8407,7 @@ > "TARGET_SSSE3" > "phsubsw\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_data16" "1") > (set_attr "prefix_extra" "1") > (set_attr "mode" "TI")]) >@@ -8403,6 +8436,7 @@ > "TARGET_SSSE3" > "phsubsw\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "complex") > (set_attr "prefix_extra" "1") > (set_attr "mode" "DI")]) > >@@ -8509,6 +8543,7 @@ > "TARGET_SSSE3" > "pmaddubsw\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "simul") > (set_attr "prefix_data16" "1") > (set_attr "prefix_extra" "1") > (set_attr "mode" "TI")]) >@@ -8547,6 +8582,7 @@ > "TARGET_SSSE3" > "pmaddubsw\t{%2, %0|%0, %2}" > [(set_attr "type" "sseiadd") >+ (set_attr "atom_unit" "simul") > (set_attr "prefix_extra" "1") > (set_attr "mode" "DI")]) > >@@ -8754,6 +8790,7 @@ > return "palignr\t{%3, %2, %0|%0, %2, %3}"; > } > [(set_attr "type" "sseishft") >+ (set_attr "atom_unit" "sishuf") > (set_attr "prefix_data16" "1") > (set_attr "prefix_extra" "1") > (set_attr "mode" "TI")]) >@@ -8770,6 +8807,7 @@ > return "palignr\t{%3, %2, %0|%0, %2, %3}"; > } > [(set_attr "type" "sseishft") >+ (set_attr "atom_unit" "sishuf") > (set_attr "prefix_extra" "1") > (set_attr "mode" "DI")]) > >@@ -8956,7 +8994,7 @@ > UNSPEC_MOVNTDQA))] > "TARGET_SSE4_1" > "%vmovntdqa\t{%1, %0|%0, %1}" >- [(set_attr "type" "ssecvt") >+ [(set_attr "type" "ssemov") > (set_attr "prefix_extra" "1") > (set_attr "prefix" "maybe_vex") > (set_attr "mode" "TI")])
You cannot view the attachment while viewing its details because your browser does not support IFRAMEs.
View the attachment on a separate page
.
View Attachment As Diff
View Attachment As Raw
Actions:
View
|
Diff
Attachments on
bug 262603
:
185113
| 188459