[gcc(refs/users/meissner/heads/work162)] Add -mcpu=power11 support.
Michael Meissner
meissner@gcc.gnu.org
Fri Mar 8 22:15:41 GMT 2024
https://gcc.gnu.org/g:0296376c2c19ba06eef70e36bbc41f5cfe947905
commit 0296376c2c19ba06eef70e36bbc41f5cfe947905
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Fri Mar 8 16:42:18 2024 -0500
Add -mcpu=power11 support.
This patch adds the power11 option to the -mcpu= and -mtune= switches.
This patch treats the power11 like a power10 in terms of costs and reassociation
width.
This patch issues a ".machine power11" to the assembly file if you use
-mcpu=power11.
This patch defines _ARCH_PWR11 if the user uses -mcpu=power11.
2024-03-08 Michael Meissner <meissner@linux.ibm.com>
gcc/
* config/rs6000/rs6000-c.cc (rs6000_target_modify_macros): Define
_ARCH_PWR11 if -mcpu=power11.
* config/rs6000/rs6000-cpus.def (ISA_POWER11_MASKS_SERVER): New define.
(POWERPC_MASKS): Add power11 isa bit.
(power11 cpu): Add power11 definition.
* rs6000-opts.h (PROCESSOR_POWER11): Add power11 processor.
* config/rs6000/rs6000-string.cc (expand_compare_loop): Likewise.
* config/rs6000/rs6000-tables.opt: Regenerate.
* config/rs6000/rs6000.cc (power11_cost): Add power11 support.
(rs6000_option_override_internal): Likewise.
(rs6000_machine_from_flags): Likewise.
(rs6000_reassociation_width): Likewise.
(rs6000_adjust_cost): Likewise.
(rs6000_issue_rate): Likewise.
(rs6000_sched_reorder): Likewise.
(rs6000_sched_reorder2): Likewise.
(rs6000_register_move_cost): Likewise.
(rs6000_opt_masks): Likewise.
* config/rs6000/rs6000.md (cpu attribute): Add power11.
* config/rs6000/rs6000.opt (-mpower11): Add internal power11 ISA flag.
* doc/invoke.texi (RS/6000 and PowerPC Options): Document -mcpu=power11.
Diff:
---
gcc/config/rs6000/rs6000-c.cc | 2 ++
gcc/config/rs6000/rs6000-cpus.def | 5 ++++
gcc/config/rs6000/rs6000-opts.h | 3 ++-
gcc/config/rs6000/rs6000-string.cc | 1 +
gcc/config/rs6000/rs6000-tables.opt | 3 +++
gcc/config/rs6000/rs6000.cc | 50 ++++++++++++++++++++++++++++++++-----
gcc/config/rs6000/rs6000.md | 2 +-
gcc/config/rs6000/rs6000.opt | 3 +++
gcc/doc/invoke.texi | 5 ++--
9 files changed, 64 insertions(+), 10 deletions(-)
diff --git a/gcc/config/rs6000/rs6000-c.cc b/gcc/config/rs6000/rs6000-c.cc
index ce0b14a8d37..ebed8b9554a 100644
--- a/gcc/config/rs6000/rs6000-c.cc
+++ b/gcc/config/rs6000/rs6000-c.cc
@@ -447,6 +447,8 @@ rs6000_target_modify_macros (bool define_p, HOST_WIDE_INT flags)
rs6000_define_or_undefine_macro (define_p, "_ARCH_PWR9");
if ((flags & OPTION_MASK_POWER10) != 0)
rs6000_define_or_undefine_macro (define_p, "_ARCH_PWR10");
+ if ((flags & OPTION_MASK_POWER11) != 0)
+ rs6000_define_or_undefine_macro (define_p, "_ARCH_PWR11");
if ((flags & OPTION_MASK_SOFT_FLOAT) != 0)
rs6000_define_or_undefine_macro (define_p, "_SOFT_FLOAT");
if ((flags & OPTION_MASK_RECIP_PRECISION) != 0)
diff --git a/gcc/config/rs6000/rs6000-cpus.def b/gcc/config/rs6000/rs6000-cpus.def
index 28249600318..3237a5ada30 100644
--- a/gcc/config/rs6000/rs6000-cpus.def
+++ b/gcc/config/rs6000/rs6000-cpus.def
@@ -86,6 +86,9 @@
| OPTION_MASK_POWER10 \
| OTHER_POWER10_MASKS)
+#define ISA_POWER11_MASKS_SERVER (ISA_3_1_MASKS_SERVER \
+ | OPTION_MASK_POWER11)
+
/* Flags that need to be turned off if -mno-vsx. */
#define OTHER_VSX_VECTOR_MASKS (OPTION_MASK_EFFICIENT_UNALIGNED_VSX \
| OPTION_MASK_FLOAT128_KEYWORD \
@@ -125,6 +128,7 @@
| OPTION_MASK_FLOAT128_KEYWORD \
| OPTION_MASK_FPRND \
| OPTION_MASK_POWER10 \
+ | OPTION_MASK_POWER11 \
| OPTION_MASK_P10_FUSION \
| OPTION_MASK_HTM \
| OPTION_MASK_ISEL \
@@ -257,3 +261,4 @@ RS6000_CPU ("powerpc64", PROCESSOR_POWERPC64, OPTION_MASK_PPC_GFXOPT
RS6000_CPU ("powerpc64le", PROCESSOR_POWER8, MASK_POWERPC64
| ISA_2_7_MASKS_SERVER | OPTION_MASK_HTM)
RS6000_CPU ("rs64", PROCESSOR_RS64A, OPTION_MASK_PPC_GFXOPT | MASK_POWERPC64)
+RS6000_CPU ("power11", PROCESSOR_POWER11, MASK_POWERPC64 | ISA_POWER11_MASKS_SERVER)
diff --git a/gcc/config/rs6000/rs6000-opts.h b/gcc/config/rs6000/rs6000-opts.h
index 33fd0efc936..4f5af57ae1a 100644
--- a/gcc/config/rs6000/rs6000-opts.h
+++ b/gcc/config/rs6000/rs6000-opts.h
@@ -67,7 +67,8 @@ enum processor_type
PROCESSOR_MPCCORE,
PROCESSOR_CELL,
PROCESSOR_PPCA2,
- PROCESSOR_TITAN
+ PROCESSOR_TITAN,
+ PROCESSOR_POWER11
};
diff --git a/gcc/config/rs6000/rs6000-string.cc b/gcc/config/rs6000/rs6000-string.cc
index 917f5572a6d..9c8a81172e3 100644
--- a/gcc/config/rs6000/rs6000-string.cc
+++ b/gcc/config/rs6000/rs6000-string.cc
@@ -964,6 +964,7 @@ expand_compare_loop (rtx operands[])
break;
case PROCESSOR_POWER9:
case PROCESSOR_POWER10:
+ case PROCESSOR_POWER11:
if (bytes_is_const)
max_bytes = 191;
else
diff --git a/gcc/config/rs6000/rs6000-tables.opt b/gcc/config/rs6000/rs6000-tables.opt
index 65f46709716..7e5bb6e7658 100644
--- a/gcc/config/rs6000/rs6000-tables.opt
+++ b/gcc/config/rs6000/rs6000-tables.opt
@@ -197,3 +197,6 @@ Enum(rs6000_cpu_opt_value) String(powerpc64le) Value(55)
EnumValue
Enum(rs6000_cpu_opt_value) String(rs64) Value(56)
+EnumValue
+Enum(rs6000_cpu_opt_value) String(power11) Value(57)
+
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index 6ba9df4f02e..5380dce7a07 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -1087,6 +1087,26 @@ struct processor_costs power10_cost = {
COSTS_N_INSNS (2), /* SF->DF convert */
};
+/* Instruction costs on POWER11 processors. */
+static const
+struct processor_costs power11_cost = {
+ COSTS_N_INSNS (2), /* mulsi */
+ COSTS_N_INSNS (2), /* mulsi_const */
+ COSTS_N_INSNS (2), /* mulsi_const9 */
+ COSTS_N_INSNS (2), /* muldi */
+ COSTS_N_INSNS (6), /* divsi */
+ COSTS_N_INSNS (6), /* divdi */
+ COSTS_N_INSNS (2), /* fp */
+ COSTS_N_INSNS (2), /* dmul */
+ COSTS_N_INSNS (11), /* sdiv */
+ COSTS_N_INSNS (13), /* ddiv */
+ 128, /* cache line size */
+ 32, /* l1 cache */
+ 512, /* l2 cache */
+ 16, /* prefetch streams */
+ COSTS_N_INSNS (2), /* SF->DF convert */
+};
+
/* Instruction costs on POWER A2 processors. */
static const
struct processor_costs ppca2_cost = {
@@ -4379,7 +4399,8 @@ rs6000_option_override_internal (bool global_init_p)
generating power10 instructions. */
if (!(rs6000_isa_flags_explicit & OPTION_MASK_P10_FUSION))
{
- if (rs6000_tune == PROCESSOR_POWER10)
+ if (rs6000_tune == PROCESSOR_POWER10
+ || rs6000_tune == PROCESSOR_POWER11)
rs6000_isa_flags |= OPTION_MASK_P10_FUSION;
else
rs6000_isa_flags &= ~OPTION_MASK_P10_FUSION;
@@ -4408,6 +4429,7 @@ rs6000_option_override_internal (bool global_init_p)
&& rs6000_tune != PROCESSOR_POWER8
&& rs6000_tune != PROCESSOR_POWER9
&& rs6000_tune != PROCESSOR_POWER10
+ && rs6000_tune != PROCESSOR_POWER11
&& rs6000_tune != PROCESSOR_PPCA2
&& rs6000_tune != PROCESSOR_CELL
&& rs6000_tune != PROCESSOR_PPC476);
@@ -4422,6 +4444,7 @@ rs6000_option_override_internal (bool global_init_p)
|| rs6000_tune == PROCESSOR_POWER8
|| rs6000_tune == PROCESSOR_POWER9
|| rs6000_tune == PROCESSOR_POWER10
+ || rs6000_tune == PROCESSOR_POWER11
|| rs6000_tune == PROCESSOR_PPCE500MC
|| rs6000_tune == PROCESSOR_PPCE500MC64
|| rs6000_tune == PROCESSOR_PPCE5500
@@ -4724,6 +4747,10 @@ rs6000_option_override_internal (bool global_init_p)
rs6000_cost = &power10_cost;
break;
+ case PROCESSOR_POWER11:
+ rs6000_cost = &power11_cost;
+ break;
+
case PROCESSOR_PPCA2:
rs6000_cost = &ppca2_cost;
break;
@@ -5880,6 +5907,8 @@ rs6000_machine_from_flags (void)
/* Disable the flags that should never influence the .machine selection. */
flags &= ~(OPTION_MASK_PPC_GFXOPT | OPTION_MASK_PPC_GPOPT | OPTION_MASK_ISEL);
+ if ((flags & (ISA_POWER11_MASKS_SERVER & ~ISA_3_1_MASKS_SERVER)) != 0)
+ return "power11";
if ((flags & (ISA_3_1_MASKS_SERVER & ~ISA_3_0_MASKS_SERVER)) != 0)
return "power10";
if ((flags & (ISA_3_0_MASKS_SERVER & ~ISA_2_7_MASKS_SERVER)) != 0)
@@ -10126,6 +10155,7 @@ rs6000_reassociation_width (unsigned int opc ATTRIBUTE_UNUSED,
case PROCESSOR_POWER8:
case PROCESSOR_POWER9:
case PROCESSOR_POWER10:
+ case PROCESSOR_POWER11:
if (DECIMAL_FLOAT_MODE_P (mode))
return 1;
if (VECTOR_MODE_P (mode))
@@ -18207,7 +18237,8 @@ rs6000_adjust_cost (rtx_insn *insn, int dep_type, rtx_insn *dep_insn, int cost,
/* Separate a load from a narrower, dependent store. */
if ((rs6000_sched_groups || rs6000_tune == PROCESSOR_POWER9
- || rs6000_tune == PROCESSOR_POWER10)
+ || rs6000_tune == PROCESSOR_POWER10
+ || rs6000_tune == PROCESSOR_POWER11)
&& GET_CODE (PATTERN (insn)) == SET
&& GET_CODE (PATTERN (dep_insn)) == SET
&& MEM_P (XEXP (PATTERN (insn), 1))
@@ -18246,6 +18277,7 @@ rs6000_adjust_cost (rtx_insn *insn, int dep_type, rtx_insn *dep_insn, int cost,
|| rs6000_tune == PROCESSOR_POWER8
|| rs6000_tune == PROCESSOR_POWER9
|| rs6000_tune == PROCESSOR_POWER10
+ || rs6000_tune == PROCESSOR_POWER11
|| rs6000_tune == PROCESSOR_CELL)
&& recog_memoized (dep_insn)
&& (INSN_CODE (dep_insn) >= 0))
@@ -18820,6 +18852,7 @@ rs6000_issue_rate (void)
case PROCESSOR_POWER9:
return 6;
case PROCESSOR_POWER10:
+ case PROCESSOR_POWER11:
return 8;
default:
return 1;
@@ -19536,7 +19569,9 @@ rs6000_sched_reorder (FILE *dump ATTRIBUTE_UNUSED, int sched_verbose,
load_store_pendulum = 0;
/* Do Power10 dependent reordering. */
- if (rs6000_tune == PROCESSOR_POWER10 && last_scheduled_insn)
+ if (last_scheduled_insn
+ && (rs6000_tune == PROCESSOR_POWER10
+ || rs6000_tune == PROCESSOR_POWER11))
power10_sched_reorder (ready, n_ready - 1);
return rs6000_issue_rate ();
@@ -19560,8 +19595,9 @@ rs6000_sched_reorder2 (FILE *dump, int sched_verbose, rtx_insn **ready,
&& recog_memoized (last_scheduled_insn) >= 0)
return power9_sched_reorder2 (ready, *pn_ready - 1);
- /* Do Power10 dependent reordering. */
- if (rs6000_tune == PROCESSOR_POWER10 && last_scheduled_insn)
+ if (last_scheduled_insn
+ && (rs6000_tune == PROCESSOR_POWER10
+ || rs6000_tune == PROCESSOR_POWER11))
return power10_sched_reorder (ready, *pn_ready - 1);
return cached_can_issue_more;
@@ -22778,7 +22814,8 @@ rs6000_register_move_cost (machine_mode mode,
allocation a move within the same class might turn
out to be a nop. */
if (rs6000_tune == PROCESSOR_POWER9
- || rs6000_tune == PROCESSOR_POWER10)
+ || rs6000_tune == PROCESSOR_POWER10
+ || rs6000_tune == PROCESSOR_POWER11)
ret = 3 * hard_regno_nregs (FIRST_GPR_REGNO, mode);
else
ret = 4 * hard_regno_nregs (FIRST_GPR_REGNO, mode);
@@ -24437,6 +24474,7 @@ static struct rs6000_opt_mask const rs6000_opt_masks[] =
{ "float128-hardware", OPTION_MASK_FLOAT128_HW, false, true },
{ "fprnd", OPTION_MASK_FPRND, false, true },
{ "power10", OPTION_MASK_POWER10, false, true },
+ { "power11", OPTION_MASK_POWER11, false, true },
{ "hard-dfp", OPTION_MASK_DFP, false, true },
{ "htm", OPTION_MASK_HTM, false, true },
{ "isel", OPTION_MASK_ISEL, false, true },
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index bc8bc6ab060..ea4add5b283 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -351,7 +351,7 @@
ppc403,ppc405,ppc440,ppc476,
ppc8540,ppc8548,ppce300c2,ppce300c3,ppce500mc,ppce500mc64,ppce5500,ppce6500,
power4,power5,power6,power7,power8,power9,power10,
- rs64a,mpccore,cell,ppca2,titan"
+ rs64a,mpccore,cell,ppca2,titan,power11"
(const (symbol_ref "(enum attr_cpu) rs6000_tune")))
;; The ISA we implement.
diff --git a/gcc/config/rs6000/rs6000.opt b/gcc/config/rs6000/rs6000.opt
index 83197681b66..e7a4e4a2ddd 100644
--- a/gcc/config/rs6000/rs6000.opt
+++ b/gcc/config/rs6000/rs6000.opt
@@ -581,6 +581,9 @@ Target Undocumented Var(rs6000_speculate_indirect_jumps) Init(1) Save
mpower10
Target Undocumented Mask(POWER10) Var(rs6000_isa_flags) WarnRemoved
+mpower11
+Target Undocumented Mask(POWER11) Var(rs6000_isa_flags) Warn(Do not use %<-mpower11>)
+
mprefixed
Target Mask(PREFIXED) Var(rs6000_isa_flags)
Generate (do not generate) prefixed memory instructions.
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 2390d478121..162e63cd149 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -31153,8 +31153,9 @@ Supported values for @var{cpu_type} are @samp{401}, @samp{403},
@samp{e6500}, @samp{ec603e}, @samp{G3}, @samp{G4}, @samp{G5},
@samp{titan}, @samp{power3}, @samp{power4}, @samp{power5}, @samp{power5+},
@samp{power6}, @samp{power6x}, @samp{power7}, @samp{power8},
-@samp{power9}, @samp{power10}, @samp{powerpc}, @samp{powerpc64},
-@samp{powerpc64le}, @samp{rs64}, and @samp{native}.
+@samp{power9}, @samp{power10}, @samp{power11},
+@samp{powerpc}, @samp{powerpc64}, @samp{powerpc64le},
+@samp{rs64}, @samp{future}, and @samp{native}.
@option{-mcpu=powerpc}, @option{-mcpu=powerpc64}, and
@option{-mcpu=powerpc64le} specify pure 32-bit PowerPC (either
More information about the Gcc-cvs
mailing list