[Patch ARM] Add initial tuning for Cortex-A55 and Cortex-A75

Much like my AArch64 patch a few weeks ago, this patch adds support
for the ARM Cortex-A75 and Cortex-A55 processors through the
-mcpu/-mtune values cortex-a55 and cortex-a75, and an
ARM DynamIQ big.LITTLE configuration of these two processors through
the -mcpu/-mtune value cortex-a75.cortex-a55

Both Cortex-A55 and Cortex-A75 support ARMv8-A with the ARM8.1-A and
ARMv8.2-A extensions. This is reflected in the patch, -mcpu=cortex-a75 is
treated as equivalent to passing -mtune=cortex-a75 -march=armv8.2-a+fp16

gcc/

2017-07-04  James Greenhalgh  <james.greenhalgh@arm.com>

	* config/arm/arm-cpus.in (cortex-a55): New.
	(cortex-a75): Likewise.
	(cortex-a75.cortex-a55): Likewise.
	* config/arm/driver-arm.c (arm_cpu_table): Add cortex-a55 and
	cortex-a75.
	* doc/invoke.texi (-mcpu): Document cortex-a55 and cortex-a75.

	* config/arm/arm-cpu-cdata.h: Regenerate.
	* config/arm/arm-cpu-data.h: Regenerate.
	* config/arm/arm-cpu.h: Regenerate.
	* config/arm/arm-tables.opt: Regenerate.
	* config/arm/arm-tune.md: Regenerate.

From-SVN: r249970
This commit is contained in:
James Greenhalgh 2017-07-04 14:05:31 +00:00 committed by James Greenhalgh
parent cea768b0ca
commit 1d79dcb813
9 changed files with 154 additions and 8 deletions

View file

@ -1,3 +1,17 @@
2017-07-04 James Greenhalgh <james.greenhalgh@arm.com>
* config/arm/arm-cpus.in (cortex-a55): New.
(cortex-a75): Likewise.
(cortex-a75.cortex-a55): Likewise.
* config/arm/driver-arm.c (arm_cpu_table): Add cortex-a55 and
cortex-a75.
* doc/invoke.texi (-mcpu): Document cortex-a55 and cortex-a75.
* config/arm/arm-cpu-cdata.h: Regenerate.
* config/arm/arm-cpu-data.h: Regenerate.
* config/arm/arm-cpu.h: Regenerate.
* config/arm/arm-tables.opt: Regenerate.
* config/arm/arm-tune.md: Regenerate.
2017-07-04 Jan Hubicka <hubicka@ucw.cz>
* haifa-sched.c (sched_create_recovery_edges): Update profile.

View file

@ -388,6 +388,34 @@ static const cpu_arch_extension cpu_opttab_cortexa73cortexa53[] = {
{ NULL, false, false, {isa_nobit}}
};
static const cpu_arch_extension cpu_opttab_cortexa55[] = {
{
"crypto", false, false,
{ ISA_FP_ARMv8,ISA_CRYPTO, isa_nobit }
},
{
"nofp", true, false,
{ ISA_ALL_FP, isa_nobit }
},
{ NULL, false, false, {isa_nobit}}
};
static const cpu_arch_extension cpu_opttab_cortexa75[] = {
{
"crypto", false, false,
{ ISA_FP_ARMv8,ISA_CRYPTO, isa_nobit }
},
{ NULL, false, false, {isa_nobit}}
};
static const cpu_arch_extension cpu_opttab_cortexa75cortexa55[] = {
{
"crypto", false, false,
{ ISA_FP_ARMv8,ISA_CRYPTO, isa_nobit }
},
{ NULL, false, false, {isa_nobit}}
};
static const cpu_arch_extension cpu_opttab_cortexm33[] = {
{
"nofp", true, false,
@ -1622,6 +1650,45 @@ const cpu_option all_cores[] =
},
TARGET_ARCH_armv8_a
},
{
{
"cortex-a55",
cpu_opttab_cortexa55,
{
ISA_ARMv8_2a,
isa_bit_fp16,ISA_FP_ARMv8,ISA_NEON,
ISA_FP_ARMv8,ISA_NEON,
isa_nobit
}
},
TARGET_ARCH_armv8_2_a
},
{
{
"cortex-a75",
cpu_opttab_cortexa75,
{
ISA_ARMv8_2a,
isa_bit_fp16,ISA_FP_ARMv8,ISA_NEON,
ISA_FP_ARMv8,ISA_NEON,
isa_nobit
}
},
TARGET_ARCH_armv8_2_a
},
{
{
"cortex-a75.cortex-a55",
cpu_opttab_cortexa75cortexa55,
{
ISA_ARMv8_2a,
isa_bit_fp16,ISA_FP_ARMv8,ISA_NEON,
ISA_FP_ARMv8,ISA_NEON,
isa_nobit
}
},
TARGET_ARCH_armv8_2_a
},
{
{
"cortex-m23",

View file

@ -552,6 +552,21 @@ static const cpu_tune all_tunes[] =
(TF_LDSCHED),
&arm_cortex_a73_tune
},
{ /* cortex-a55. */
TARGET_CPU_cortexa53,
(TF_LDSCHED),
&arm_cortex_a53_tune
},
{ /* cortex-a75. */
TARGET_CPU_cortexa57,
(TF_LDSCHED),
&arm_cortex_a73_tune
},
{ /* cortex-a75.cortex-a55. */
TARGET_CPU_cortexa53,
(TF_LDSCHED),
&arm_cortex_a73_tune
},
{ /* cortex-m23. */
TARGET_CPU_cortexm23,
(TF_LDSCHED),

View file

@ -128,6 +128,9 @@ enum processor_type
TARGET_CPU_cortexa72cortexa53,
TARGET_CPU_cortexa73cortexa35,
TARGET_CPU_cortexa73cortexa53,
TARGET_CPU_cortexa55,
TARGET_CPU_cortexa75,
TARGET_CPU_cortexa75cortexa55,
TARGET_CPU_cortexm23,
TARGET_CPU_cortexm33,
TARGET_CPU_arm_none

View file

@ -1206,7 +1206,6 @@ begin cpu xgene1
costs xgene1
end cpu xgene1
# V8 A-profile big.LITTLE implementations
begin cpu cortex-a57.cortex-a53
cname cortexa57cortexa53
@ -1249,6 +1248,40 @@ begin cpu cortex-a73.cortex-a53
end cpu cortex-a73.cortex-a53
# ARMv8.2 A-profile Architecture Processors
begin cpu cortex-a55
cname cortexa55
tune for cortex-a53
tune flags LDSCHED
architecture armv8.2-a+fp16
fpu neon-fp-armv8
option crypto add FP_ARMv8 CRYPTO
option nofp remove ALL_FP
costs cortex_a53
end cpu cortex-a55
begin cpu cortex-a75
cname cortexa75
tune for cortex-a57
tune flags LDSCHED
architecture armv8.2-a+fp16
fpu neon-fp-armv8
option crypto add FP_ARMv8 CRYPTO
costs cortex_a73
end cpu cortex-a75
# ARMv8.2 A-profile ARM DynamIQ big.LITTLE implementations
begin cpu cortex-a75.cortex-a55
cname cortexa75cortexa55
tune for cortex-a53
tune flags LDSCHED
architecture armv8.2-a+fp16
fpu neon-fp-armv8
option crypto add FP_ARMv8 CRYPTO
costs cortex_a73
end cpu cortex-a75.cortex-a55
# V8 M-profile implementations.
begin cpu cortex-m23
cname cortexm23

View file

@ -342,6 +342,15 @@ Enum(processor_type) String(cortex-a73.cortex-a35) Value( TARGET_CPU_cortexa73co
EnumValue
Enum(processor_type) String(cortex-a73.cortex-a53) Value( TARGET_CPU_cortexa73cortexa53)
EnumValue
Enum(processor_type) String(cortex-a55) Value( TARGET_CPU_cortexa55)
EnumValue
Enum(processor_type) String(cortex-a75) Value( TARGET_CPU_cortexa75)
EnumValue
Enum(processor_type) String(cortex-a75.cortex-a55) Value( TARGET_CPU_cortexa75cortexa55)
EnumValue
Enum(processor_type) String(cortex-m23) Value( TARGET_CPU_cortexm23)

View file

@ -56,5 +56,6 @@
cortexa53,cortexa57,cortexa72,
cortexa73,exynosm1,xgene1,
cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,
cortexa73cortexa53,cortexm23,cortexm33"
cortexa73cortexa53,cortexa55,cortexa75,
cortexa75cortexa55,cortexm23,cortexm33"
(const (symbol_ref "((enum attr_tune) arm_tune)")))

View file

@ -52,6 +52,8 @@ static struct vendor_cpu arm_cpu_table[] = {
{"0xd07", "armv8-a+crc", "cortex-a57"},
{"0xd08", "armv8-a+crc", "cortex-a72"},
{"0xd09", "armv8-a+crc", "cortex-a73"},
{"0xd05", "armv8.2-a+fp16", "cortex-a55"},
{"0xd0a", "armv8.2-a+fp16", "cortex-a75"},
{"0xc14", "armv7-r", "cortex-r4"},
{"0xc15", "armv7-r", "cortex-r5"},
{"0xc20", "armv6-m", "cortex-m0"},

View file

@ -15519,9 +15519,10 @@ Permissible names are: @samp{arm2}, @samp{arm250},
@samp{arm1156t2-s}, @samp{arm1156t2f-s}, @samp{arm1176jz-s}, @samp{arm1176jzf-s},
@samp{generic-armv7-a}, @samp{cortex-a5}, @samp{cortex-a7}, @samp{cortex-a8},
@samp{cortex-a9}, @samp{cortex-a12}, @samp{cortex-a15}, @samp{cortex-a17},
@samp{cortex-a32}, @samp{cortex-a35}, @samp{cortex-a53}, @samp{cortex-a57},
@samp{cortex-a72}, @samp{cortex-a73}, @samp{cortex-r4},
@samp{cortex-r4f}, @samp{cortex-r5}, @samp{cortex-r7}, @samp{cortex-r8},
@samp{cortex-a32}, @samp{cortex-a35}, @samp{cortex-a53}, @samp{cortex-a55},
@samp{cortex-a57}, @samp{cortex-a72}, @samp{cortex-a73}, @samp{cortex-a75},
@samp{cortex-r4}, @samp{cortex-r4f}, @samp{cortex-r5}, @samp{cortex-r7},
@samp{cortex-r8},
@samp{cortex-m33},
@samp{cortex-m23},
@samp{cortex-m7},
@ -15544,7 +15545,8 @@ Additionally, this option can specify that GCC should tune the performance
of the code for a big.LITTLE system. Permissible names are:
@samp{cortex-a15.cortex-a7}, @samp{cortex-a17.cortex-a7},
@samp{cortex-a57.cortex-a53}, @samp{cortex-a72.cortex-a53},
@samp{cortex-a72.cortex-a35}, @samp{cortex-a73.cortex-a53}.
@samp{cortex-a72.cortex-a35}, @samp{cortex-a73.cortex-a53},
@samp{cortex-a75.cortex-a55}.
@option{-mtune=generic-@var{arch}} specifies that GCC should tune the
performance for a blend of processors within architecture @var{arch}.
@ -15605,8 +15607,8 @@ Disables the floating-point and SIMD instructions on
@samp{generic-armv7-a}, @samp{cortex-a5}, @samp{cortex-a7},
@samp{cortex-a8}, @samp{cortex-a9}, @samp{cortex-a12},
@samp{cortex-a15}, @samp{cortex-a17}, @samp{cortex-a15.cortex-a7},
@samp{cortex-a17.cortex-a7}, @samp{cortex-a32}, @samp{cortex-a35}
and @samp{cortex-a53}.
@samp{cortex-a17.cortex-a7}, @samp{cortex-a32}, @samp{cortex-a35},
@samp{cortex-a53} and @samp{cortex-a55}.
@item +nofp.dp
Disables the double-precision component of the floating-point instructions