https://gcc.gnu.org/g:05f0e9eec9f9beeffe024ecd6566b41200d79cff
commit r15-2204-g05f0e9eec9f9beeffe024ecd6566b41200d79cff
Author: Michael Meissner <meiss...@linux.ibm.com>
Date: Mon Jul 22 12:20:43 2024 -0400
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.
This patch allows GCC to be configured with the --with-cpu=power11 and
--with-tune=power11 options.
This patch passes -mpwr11 to the assembler if the user uses -mcpu=power11.
This patch adds support for using "power11" in the __builtin_cpu_is built-in
function.
2024-07-22 Michael Meissner <meiss...@linux.ibm.com>
gcc/
* config.gcc (powerpc*-*-*): Add support for power11.
* config/rs6000/aix71.h (ASM_CPU_SPEC): Add support for
-mcpu=power11.
* config/rs6000/aix72.h (ASM_CPU_SPEC): Likewise.
* config/rs6000/aix73.h (ASM_CPU_SPEC): Likewise.
* config/rs6000/driver-rs6000.cc (asm_names): Likewise.
* config/rs6000/ppc-auxv.h (PPC_PLATFORM_POWER11): New define.
* config/rs6000/rs6000-builtin.cc (cpu_is_info): Add power11.
* config/rs6000/rs6000-c.cc (rs6000_target_modify_macros): Define
_ARCH_PWR11 if -mcpu=power11.
* config/rs6000/rs6000-cpus.def (POWER11_MASKS_SERVER): New define.
(POWERPC_MASKS): Add power11.
(power11 cpu): Add power11 definition.
* config/rs6000/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 (rs6000_option_override_internal): Add
power11
support.
(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.h (ASM_CPU_SPEC): Likewise.
* config/rs6000/rs6000.md (cpu attribute): Add power11.
* config/rs6000/rs6000.opt (-mpower11): Add internal power11 flag.
* doc/invoke.texi (RS/6000 and PowerPC Options): Document
-mcpu=power11.
* config/rs6000/power10.md (all reservations): Add power11 support.
gcc/testsuite/
* gcc.target/powerpc/power11-1.c: New test.
* gcc.target/powerpc/power11-2.c: Likewise.
* gcc.target/powerpc/power11-3.c: Likewise.
Diff:
---
gcc/config.gcc | 4 +-
gcc/config/rs6000/aix71.h | 1 +
gcc/config/rs6000/aix72.h | 1 +
gcc/config/rs6000/aix73.h | 1 +
gcc/config/rs6000/driver-rs6000.cc | 2 +
gcc/config/rs6000/power10.md | 144 +++++++++++++--------------
gcc/config/rs6000/ppc-auxv.h | 3 +-
gcc/config/rs6000/rs6000-builtin.cc | 1 +
gcc/config/rs6000/rs6000-c.cc | 2 +
gcc/config/rs6000/rs6000-cpus.def | 5 +
gcc/config/rs6000/rs6000-opts.h | 1 +
gcc/config/rs6000/rs6000-string.cc | 1 +
gcc/config/rs6000/rs6000-tables.opt | 11 +-
gcc/config/rs6000/rs6000.cc | 32 ++++--
gcc/config/rs6000/rs6000.h | 1 +
gcc/config/rs6000/rs6000.md | 2 +-
gcc/config/rs6000/rs6000.opt | 6 ++
gcc/doc/invoke.texi | 2 +-
gcc/testsuite/gcc.target/powerpc/power11-1.c | 13 +++
gcc/testsuite/gcc.target/powerpc/power11-2.c | 19 ++++
gcc/testsuite/gcc.target/powerpc/power11-3.c | 9 ++
21 files changed, 171 insertions(+), 90 deletions(-)
diff --git a/gcc/config.gcc b/gcc/config.gcc
index bc45615741b1..7453ade07826 100644
--- a/gcc/config.gcc
+++ b/gcc/config.gcc
@@ -533,7 +533,7 @@ powerpc*-*-*)
extra_headers="${extra_headers} ppu_intrinsics.h spu2vmx.h vec_types.h
si2vmx.h"
extra_headers="${extra_headers} amo.h"
case x$with_cpu in
-
xpowerpc64|xdefault64|x6[23]0|x970|xG5|xpower[3456789]|xpower10|xpower6x|xrs64a|xcell|xa2|xe500mc64|xe5500|xe6500)
+
xpowerpc64|xdefault64|x6[23]0|x970|xG5|xpower[3456789]|xpower1[01]|xpower6x|xrs64a|xcell|xa2|xe500mc64|xe5500|xe6500)
cpu_is_64bit=yes
;;
esac
@@ -5641,7 +5641,7 @@ case "${target}" in
eval "with_$which=405"
;;
"" | common | native \
- | power[3456789] | power10 | power5+ | power6x \
+ | power[3456789] | power1[01] | power5+ | power6x \
| powerpc | powerpc64 | powerpc64le \
| rs64 \
| 401 | 403 | 405 | 405fp | 440 | 440fp | 464 | 464fp \
diff --git a/gcc/config/rs6000/aix71.h b/gcc/config/rs6000/aix71.h
index 24bc301e37d6..41037b3852d7 100644
--- a/gcc/config/rs6000/aix71.h
+++ b/gcc/config/rs6000/aix71.h
@@ -79,6 +79,7 @@ do {
\
#undef ASM_CPU_SPEC
#define ASM_CPU_SPEC \
"%{mcpu=native: %(asm_cpu_native); \
+ mcpu=power11: -mpwr11; \
mcpu=power10: -mpwr10; \
mcpu=power9: -mpwr9; \
mcpu=power8: -mpwr8; \
diff --git a/gcc/config/rs6000/aix72.h b/gcc/config/rs6000/aix72.h
index c43974f577af..fe59f8319b48 100644
--- a/gcc/config/rs6000/aix72.h
+++ b/gcc/config/rs6000/aix72.h
@@ -79,6 +79,7 @@ do {
\
#undef ASM_CPU_SPEC
#define ASM_CPU_SPEC \
"%{mcpu=native: %(asm_cpu_native); \
+ mcpu=power11: -mpwr11; \
mcpu=power10: -mpwr10; \
mcpu=power9: -mpwr9; \
mcpu=power8: -mpwr8; \
diff --git a/gcc/config/rs6000/aix73.h b/gcc/config/rs6000/aix73.h
index b1572bde81f9..1318b0b3662d 100644
--- a/gcc/config/rs6000/aix73.h
+++ b/gcc/config/rs6000/aix73.h
@@ -79,6 +79,7 @@ do {
\
#undef ASM_CPU_SPEC
#define ASM_CPU_SPEC \
"%{mcpu=native: %(asm_cpu_native); \
+ mcpu=power11: -mpwr11; \
mcpu=power10: -mpwr10; \
mcpu=power9: -mpwr9; \
mcpu=power8: -mpwr8; \
diff --git a/gcc/config/rs6000/driver-rs6000.cc
b/gcc/config/rs6000/driver-rs6000.cc
index 3ebbaa42622a..f4900724b98a 100644
--- a/gcc/config/rs6000/driver-rs6000.cc
+++ b/gcc/config/rs6000/driver-rs6000.cc
@@ -451,6 +451,7 @@ static const struct asm_name asm_names[] = {
{ "power8", "-mpwr8" },
{ "power9", "-mpwr9" },
{ "power10", "-mpwr10" },
+ { "power11", "-mpwr11" },
{ "powerpc", "-mppc" },
{ "rs64", "-mppc" },
{ "603", "-m603" },
@@ -479,6 +480,7 @@ static const struct asm_name asm_names[] = {
{ "power8", "-mpower8" },
{ "power9", "-mpower9" },
{ "power10", "-mpower10" },
+ { "power11", "-mpower11" },
{ "a2", "-ma2" },
{ "powerpc", "-mppc" },
{ "powerpc64", "-mppc64" },
diff --git a/gcc/config/rs6000/power10.md b/gcc/config/rs6000/power10.md
index fcc2199ab291..2310c4603457 100644
--- a/gcc/config/rs6000/power10.md
+++ b/gcc/config/rs6000/power10.md
@@ -1,4 +1,4 @@
-;; Scheduling description for the IBM POWER10 processor.
+;; Scheduling description for the IBM Power10 and Power11 processors.
;; Copyright (C) 2020-2024 Free Software Foundation, Inc.
;;
;; Contributed by Pat Haugen (pthau...@us.ibm.com).
@@ -97,12 +97,12 @@
(eq_attr "update" "no")
(eq_attr "size" "!128")
(eq_attr "prefixed" "no")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,LU_power10")
(define_insn_reservation "power10-fused-load" 4
(and (eq_attr "type" "fused_load_cmpi,fused_addis_load,fused_load_load")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,LU_power10")
(define_insn_reservation "power10-prefixed-load" 4
@@ -110,13 +110,13 @@
(eq_attr "update" "no")
(eq_attr "size" "!128")
(eq_attr "prefixed" "yes")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,LU_power10")
(define_insn_reservation "power10-load-update" 4
(and (eq_attr "type" "load")
(eq_attr "update" "yes")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,LU_power10+SXU_power10")
(define_insn_reservation "power10-fpload-double" 4
@@ -124,7 +124,7 @@
(eq_attr "update" "no")
(eq_attr "size" "64")
(eq_attr "prefixed" "no")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,LU_power10")
(define_insn_reservation "power10-prefixed-fpload-double" 4
@@ -132,14 +132,14 @@
(eq_attr "update" "no")
(eq_attr "size" "64")
(eq_attr "prefixed" "yes")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,LU_power10")
(define_insn_reservation "power10-fpload-update-double" 4
(and (eq_attr "type" "fpload")
(eq_attr "update" "yes")
(eq_attr "size" "64")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,LU_power10+SXU_power10")
; SFmode loads are cracked and have additional 3 cycles over DFmode
@@ -148,27 +148,27 @@
(and (eq_attr "type" "fpload")
(eq_attr "update" "no")
(eq_attr "size" "32")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,LU_power10")
(define_insn_reservation "power10-fpload-update-single" 7
(and (eq_attr "type" "fpload")
(eq_attr "update" "yes")
(eq_attr "size" "32")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,LU_power10+SXU_power10")
(define_insn_reservation "power10-vecload" 4
(and (eq_attr "type" "vecload")
(eq_attr "size" "!256")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,LU_power10")
; lxvp
(define_insn_reservation "power10-vecload-pair" 4
(and (eq_attr "type" "vecload")
(eq_attr "size" "256")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,LU_power10+SXU_power10")
; Store Unit
@@ -178,12 +178,12 @@
(eq_attr "prefixed" "no")
(eq_attr "size" "!128")
(eq_attr "size" "!256")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,STU_power10")
(define_insn_reservation "power10-fused-store" 0
(and (eq_attr "type" "fused_store_store")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,STU_power10")
(define_insn_reservation "power10-prefixed-store" 0
@@ -191,52 +191,52 @@
(eq_attr "prefixed" "yes")
(eq_attr "size" "!128")
(eq_attr "size" "!256")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,STU_power10")
; Update forms have 2 cycle latency for updated addr reg
(define_insn_reservation "power10-store-update" 2
(and (eq_attr "type" "store,fpstore")
(eq_attr "update" "yes")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,STU_power10")
; stxvp
(define_insn_reservation "power10-vecstore-pair" 0
(and (eq_attr "type" "vecstore")
(eq_attr "size" "256")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,stu0_power10+stu1_power10")
(define_insn_reservation "power10-larx" 4
(and (eq_attr "type" "load_l")
(eq_attr "size" "!128")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,LU_power10")
; All load quad forms
(define_insn_reservation "power10-lq" 4
(and (eq_attr "type" "load,load_l")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,LU_power10+SXU_power10")
(define_insn_reservation "power10-stcx" 0
(and (eq_attr "type" "store_c")
(eq_attr "size" "!128")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,STU_power10")
; All store quad forms
(define_insn_reservation "power10-stq" 0
(and (eq_attr "type" "store,store_c")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,stu0_power10+stu1_power10")
(define_insn_reservation "power10-sync" 1
(and (eq_attr "type" "sync,isync")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,STU_power10")
@@ -248,7 +248,7 @@
(define_insn_reservation "power10-alu" 2
(and (eq_attr "type" "add,exts,integer,logical,isel")
(eq_attr "prefixed" "no")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
; 4 cycle CR latency
(define_bypass 4 "power10-alu"
@@ -256,28 +256,28 @@
(define_insn_reservation "power10-fused_alu" 2
(and (eq_attr "type" "fused_arith_logical,fused_cmp_isel,fused_carry")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,EXU_power10")
; paddi
(define_insn_reservation "power10-paddi" 2
(and (eq_attr "type" "add")
(eq_attr "prefixed" "yes")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,EXU_power10")
; Rotate/shift (non-record form)
(define_insn_reservation "power10-rot" 2
(and (eq_attr "type" "insert,shift")
(eq_attr "dot" "no")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
; Record form rotate/shift
(define_insn_reservation "power10-rot-compare" 3
(and (eq_attr "type" "insert,shift")
(eq_attr "dot" "yes")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
; 5 cycle CR latency
(define_bypass 5 "power10-rot-compare"
@@ -285,7 +285,7 @@
(define_insn_reservation "power10-alu2" 3
(and (eq_attr "type" "cntlz,popcnt,trap")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
; 5 cycle CR latency
(define_bypass 5 "power10-alu2"
@@ -293,24 +293,24 @@
(define_insn_reservation "power10-cmp" 2
(and (eq_attr "type" "cmp")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
; Treat 'two' and 'three' types as 2 or 3 way cracked
(define_insn_reservation "power10-two" 4
(and (eq_attr "type" "two")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,EXU_power10")
(define_insn_reservation "power10-three" 6
(and (eq_attr "type" "three")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_all_power10,EXU_power10")
(define_insn_reservation "power10-mul" 5
(and (eq_attr "type" "mul")
(eq_attr "dot" "no")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
; 4 cycle MUL->MUL latency
(define_bypass 4 "power10-mul"
@@ -319,7 +319,7 @@
(define_insn_reservation "power10-mul-compare" 5
(and (eq_attr "type" "mul")
(eq_attr "dot" "yes")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,EXU_power10")
; 4 cycle MUL->MUL latency
(define_bypass 4 "power10-mul-compare"
@@ -331,13 +331,13 @@
(define_insn_reservation "power10-div" 12
(and (eq_attr "type" "div")
(eq_attr "dot" "no")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-div-compare" 12
(and (eq_attr "type" "div")
(eq_attr "dot" "yes")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,EXU_power10")
; 14 cycle CR latency
(define_bypass 14 "power10-div-compare"
@@ -345,34 +345,34 @@
(define_insn_reservation "power10-crlogical" 2
(and (eq_attr "type" "cr_logical")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mfcrf" 2
(and (eq_attr "type" "mfcrf")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mfcr" 3
(and (eq_attr "type" "mfcr")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,EXU_power10")
; Should differentiate between 1 cr field and > 1 since target of > 1 cr
; is cracked
(define_insn_reservation "power10-mtcr" 3
(and (eq_attr "type" "mtcr")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mtjmpr" 3
(and (eq_attr "type" "mtjmpr")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mfjmpr" 2
(and (eq_attr "type" "mfjmpr")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
@@ -380,126 +380,126 @@
(define_insn_reservation "power10-fpsimple" 3
(and (eq_attr "type" "fpsimple")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-fp" 5
(and (eq_attr "type" "fp,dmul")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-fpcompare" 3
(and (eq_attr "type" "fpcompare")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-sdiv" 22
(and (eq_attr "type" "sdiv")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-ddiv" 27
(and (eq_attr "type" "ddiv")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-sqrt" 26
(and (eq_attr "type" "ssqrt")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-dsqrt" 36
(and (eq_attr "type" "dsqrt")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vec-2cyc" 2
(and (eq_attr "type" "vecmove,veclogical,vecexts,veccmpfx")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-fused-vec" 2
(and (eq_attr "type" "fused_vector")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,EXU_power10")
(define_insn_reservation "power10-veccmp" 3
(and (eq_attr "type" "veccmp")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecsimple" 2
(and (eq_attr "type" "vecsimple")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecnormal" 5
(and (eq_attr "type" "vecfloat,vecdouble")
(eq_attr "size" "!128")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-qp" 12
(and (eq_attr "type" "vecfloat,vecdouble")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecperm" 3
(and (eq_attr "type" "vecperm")
(eq_attr "prefixed" "no")
(eq_attr "dot" "no")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecperm-compare" 3
(and (eq_attr "type" "vecperm")
(eq_attr "dot" "yes")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,EXU_power10")
(define_insn_reservation "power10-prefixed-vecperm" 3
(and (eq_attr "type" "vecperm")
(eq_attr "prefixed" "yes")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,EXU_power10")
(define_insn_reservation "power10-veccomplex" 6
(and (eq_attr "type" "veccomplex")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecfdiv" 24
(and (eq_attr "type" "vecfdiv")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-vecdiv" 27
(and (eq_attr "type" "vecdiv")
(eq_attr "size" "!128")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-qpdiv" 56
(and (eq_attr "type" "vecdiv")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-qpmul" 24
(and (eq_attr "type" "qmul")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mtvsr" 2
(and (eq_attr "type" "mtvsr")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-mfvsr" 2
(and (eq_attr "type" "mfvsr")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
@@ -507,26 +507,26 @@
; Branch is 2 cycles, grouped with STU for issue
(define_insn_reservation "power10-branch" 2
(and (eq_attr "type" "jmpreg,branch")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,STU_power10")
(define_insn_reservation "power10-fused-branch" 3
(and (eq_attr "type" "fused_mtbc")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,STU_power10")
; Crypto
(define_insn_reservation "power10-crypto" 4
(and (eq_attr "type" "crypto")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
; HTM
(define_insn_reservation "power10-htm" 2
(and (eq_attr "type" "htmsimple,htm")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
@@ -535,26 +535,26 @@
(define_insn_reservation "power10-dfp" 12
(and (eq_attr "type" "dfp")
(eq_attr "size" "!128")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_power10")
(define_insn_reservation "power10-dfpq" 12
(and (eq_attr "type" "dfp")
(eq_attr "size" "128")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,EXU_power10")
; MMA
(define_insn_reservation "power10-mma" 9
(and (eq_attr "type" "mma")
(eq_attr "prefixed" "no")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_any_power10,EXU_super_power10")
(define_insn_reservation "power10-prefixed-mma" 9
(and (eq_attr "type" "mma")
(eq_attr "prefixed" "yes")
- (eq_attr "cpu" "power10"))
+ (eq_attr "cpu" "power10,power11"))
"DU_even_power10,EXU_super_power10")
; 4 cycle MMA->MMA latency
(define_bypass 4 "power10-mma,power10-prefixed-mma"
diff --git a/gcc/config/rs6000/ppc-auxv.h b/gcc/config/rs6000/ppc-auxv.h
index 364bba427d14..ed269e3b72b3 100644
--- a/gcc/config/rs6000/ppc-auxv.h
+++ b/gcc/config/rs6000/ppc-auxv.h
@@ -47,9 +47,8 @@
#define PPC_PLATFORM_PPC476 12
#define PPC_PLATFORM_POWER8 13
#define PPC_PLATFORM_POWER9 14
-
-/* This is not yet official. */
#define PPC_PLATFORM_POWER10 15
+#define PPC_PLATFORM_POWER11 16
/* AT_HWCAP bits. These must match the values defined in the Linux kernel. */
#define PPC_FEATURE_32 0x80000000
diff --git a/gcc/config/rs6000/rs6000-builtin.cc
b/gcc/config/rs6000/rs6000-builtin.cc
index 0a24d20a58c4..117cf0125f86 100644
--- a/gcc/config/rs6000/rs6000-builtin.cc
+++ b/gcc/config/rs6000/rs6000-builtin.cc
@@ -2442,6 +2442,7 @@ static const struct
const char *cpu;
unsigned int cpuid;
} cpu_is_info[] = {
+ { "power11", PPC_PLATFORM_POWER11 },
{ "power10", PPC_PLATFORM_POWER10 },
{ "power9", PPC_PLATFORM_POWER9 },
{ "power8", PPC_PLATFORM_POWER8 },
diff --git a/gcc/config/rs6000/rs6000-c.cc b/gcc/config/rs6000/rs6000-c.cc
index 6229c503bd0f..68519e1397f1 100644
--- a/gcc/config/rs6000/rs6000-c.cc
+++ b/gcc/config/rs6000/rs6000-c.cc
@@ -435,6 +435,8 @@ 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 6ee678e69c32..84fac8bdac1d 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 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 \
@@ -123,6 +126,7 @@
| OPTION_MASK_FLOAT128_KEYWORD \
| OPTION_MASK_FPRND \
| OPTION_MASK_POWER10 \
+ | OPTION_MASK_POWER11 \
| OPTION_MASK_P10_FUSION \
| OPTION_MASK_HTM \
| OPTION_MASK_ISEL \
@@ -250,6 +254,7 @@ RS6000_CPU ("power8", PROCESSOR_POWER8, MASK_POWERPC64 |
ISA_2_7_MASKS_SERVER
RS6000_CPU ("power9", PROCESSOR_POWER9, MASK_POWERPC64 | ISA_3_0_MASKS_SERVER
| OPTION_MASK_HTM)
RS6000_CPU ("power10", PROCESSOR_POWER10, MASK_POWERPC64 |
ISA_3_1_MASKS_SERVER)
+RS6000_CPU ("power11", PROCESSOR_POWER11, MASK_POWERPC64 |
POWER11_MASKS_SERVER)
RS6000_CPU ("powerpc", PROCESSOR_POWERPC, 0)
RS6000_CPU ("powerpc64", PROCESSOR_POWERPC64, OPTION_MASK_PPC_GFXOPT
| MASK_POWERPC64)
diff --git a/gcc/config/rs6000/rs6000-opts.h b/gcc/config/rs6000/rs6000-opts.h
index 33fd0efc936f..88e357835a5c 100644
--- a/gcc/config/rs6000/rs6000-opts.h
+++ b/gcc/config/rs6000/rs6000-opts.h
@@ -62,6 +62,7 @@ enum processor_type
PROCESSOR_POWER8,
PROCESSOR_POWER9,
PROCESSOR_POWER10,
+ PROCESSOR_POWER11,
PROCESSOR_RS64A,
PROCESSOR_MPCCORE,
diff --git a/gcc/config/rs6000/rs6000-string.cc
b/gcc/config/rs6000/rs6000-string.cc
index c4c62e8e2f94..0f992902f38c 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 65f46709716f..a5649fef1ece 100644
--- a/gcc/config/rs6000/rs6000-tables.opt
+++ b/gcc/config/rs6000/rs6000-tables.opt
@@ -186,14 +186,17 @@ EnumValue
Enum(rs6000_cpu_opt_value) String(power10) Value(52)
EnumValue
-Enum(rs6000_cpu_opt_value) String(powerpc) Value(53)
+Enum(rs6000_cpu_opt_value) String(power11) Value(53)
EnumValue
-Enum(rs6000_cpu_opt_value) String(powerpc64) Value(54)
+Enum(rs6000_cpu_opt_value) String(powerpc) Value(54)
EnumValue
-Enum(rs6000_cpu_opt_value) String(powerpc64le) Value(55)
+Enum(rs6000_cpu_opt_value) String(powerpc64) Value(55)
EnumValue
-Enum(rs6000_cpu_opt_value) String(rs64) Value(56)
+Enum(rs6000_cpu_opt_value) String(powerpc64le) Value(56)
+
+EnumValue
+Enum(rs6000_cpu_opt_value) String(rs64) Value(57)
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index 5ed64b1e6866..eddd2adbab59 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -1067,7 +1067,7 @@ struct processor_costs power9_cost = {
COSTS_N_INSNS (3), /* SF->DF convert */
};
-/* Instruction costs on POWER10 processors. */
+/* Instruction costs on Power10/Power11 processors. */
static const
struct processor_costs power10_cost = {
COSTS_N_INSNS (2), /* mulsi */
@@ -4385,7 +4385,8 @@ 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;
@@ -4414,6 +4415,7 @@ 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);
@@ -4428,6 +4430,7 @@ 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
@@ -4727,6 +4730,7 @@ rs6000_option_override_internal (bool global_init_p)
break;
case PROCESSOR_POWER10:
+ case PROCESSOR_POWER11:
rs6000_cost = &power10_cost;
break;
@@ -5899,6 +5903,8 @@ rs6000_machine_from_flags (void)
flags &= ~(OPTION_MASK_PPC_GFXOPT | OPTION_MASK_PPC_GPOPT | OPTION_MASK_ISEL
| OPTION_MASK_ALTIVEC);
+ if ((flags & (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)
@@ -10147,6 +10153,7 @@ 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))
@@ -18228,7 +18235,8 @@ 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))
@@ -18267,6 +18275,7 @@ 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))
@@ -18841,6 +18850,7 @@ rs6000_issue_rate (void)
case PROCESSOR_POWER9:
return 6;
case PROCESSOR_POWER10:
+ case PROCESSOR_POWER11:
return 8;
default:
return 1;
@@ -19556,8 +19566,10 @@ rs6000_sched_reorder (FILE *dump ATTRIBUTE_UNUSED, int
sched_verbose,
if (rs6000_tune == PROCESSOR_POWER6)
load_store_pendulum = 0;
- /* Do Power10 dependent reordering. */
- if (rs6000_tune == PROCESSOR_POWER10 && last_scheduled_insn)
+ /* Do Power10/Power11 dependent reordering. */
+ if (last_scheduled_insn
+ && (rs6000_tune == PROCESSOR_POWER10
+ || rs6000_tune == PROCESSOR_POWER11))
power10_sched_reorder (ready, n_ready - 1);
return rs6000_issue_rate ();
@@ -19581,8 +19593,10 @@ 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)
+ /* Do Power10/Power11 dependent reordering. */
+ 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;
@@ -22799,7 +22813,8 @@ 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);
@@ -24470,6 +24485,7 @@ 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, false },
{ "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.h b/gcc/config/rs6000/rs6000.h
index 8ea9ac1707ea..703be908d944 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -101,6 +101,7 @@
you make changes here, make them also there. */
#define ASM_CPU_SPEC \
"%{mcpu=native: %(asm_cpu_native); \
+ mcpu=power11: -mpower11; \
mcpu=power10: -mpower10; \
mcpu=power9: -mpower9; \
mcpu=power8|mcpu=powerpc64le: -mpower8; \
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index f59be5365708..637a8591e775 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -350,7 +350,7 @@
ppc750,ppc7400,ppc7450,
ppc403,ppc405,ppc440,ppc476,
ppc8540,ppc8548,ppce300c2,ppce300c3,ppce500mc,ppce500mc64,ppce5500,ppce6500,
- power4,power5,power6,power7,power8,power9,power10,
+ power4,power5,power6,power7,power8,power9,power10,power11,
rs64a,mpccore,cell,ppca2,titan"
(const (symbol_ref "(enum attr_cpu) rs6000_tune")))
diff --git a/gcc/config/rs6000/rs6000.opt b/gcc/config/rs6000/rs6000.opt
index e8ca70340df3..94323bd1db26 100644
--- a/gcc/config/rs6000/rs6000.opt
+++ b/gcc/config/rs6000/rs6000.opt
@@ -585,6 +585,12 @@ Target Undocumented Var(rs6000_speculate_indirect_jumps)
Init(1) Save
mpower10
Target Undocumented Mask(POWER10) Var(rs6000_isa_flags) WarnRemoved
+;; Users should not use -mpower11, but we need to use a bit to identify when
+;; the user changes the default cpu via #pragma GCC target("cpu=power11")
+;; and then resets it later.
+mpower11
+Target Undocumented Mask(POWER11) Var(rs6000_isa_flags) WarnRemoved
+
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 3f6634ce5ec2..e0a641213ae4 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -31558,7 +31558,7 @@ 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{power9}, @samp{power10}, @samp{power11}, @samp{powerpc},
@samp{powerpc64},
@samp{powerpc64le}, @samp{rs64}, and @samp{native}.
@option{-mcpu=powerpc}, @option{-mcpu=powerpc64}, and
diff --git a/gcc/testsuite/gcc.target/powerpc/power11-1.c
b/gcc/testsuite/gcc.target/powerpc/power11-1.c
new file mode 100644
index 000000000000..029a59639b1d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/power11-1.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-mdejagnu-cpu=power11 -O2" } */
+
+/* Basic check to see if the compiler supports -mcpu=power11 and if it defines
+ _ARCH_PWR11. */
+
+#ifndef _ARCH_PWR11
+#error "-mcpu=power11 is not supported"
+#endif
+
+void foo (void)
+{
+}
diff --git a/gcc/testsuite/gcc.target/powerpc/power11-2.c
b/gcc/testsuite/gcc.target/powerpc/power11-2.c
new file mode 100644
index 000000000000..e3438e350151
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/power11-2.c
@@ -0,0 +1,19 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+/* Check if we can set the power11 target via a target attribute. */
+
+__attribute__((__target__("cpu=power9")))
+void foo_p9 (void)
+{
+}
+
+__attribute__((__target__("cpu=power10")))
+void foo_p10 (void)
+{
+}
+
+__attribute__((__target__("cpu=power11")))
+void foo_p11 (void)
+{
+}
diff --git a/gcc/testsuite/gcc.target/powerpc/power11-3.c
b/gcc/testsuite/gcc.target/powerpc/power11-3.c
new file mode 100644
index 000000000000..fa1aedd04299
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/power11-3.c
@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-mdejagnu-cpu=power8 -O2" } */
+
+/* Check if we can set the power11 target via a target_clones attribute. */
+
+__attribute__((__target_clones__("cpu=power11,cpu=power9,default")))
+void foo (void)
+{
+}
