public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc(refs/users/meissner/heads/dmf004)] Add saturating subtract built-in.
@ 2022-11-17 21:53 Michael Meissner
0 siblings, 0 replies; 4+ messages in thread
From: Michael Meissner @ 2022-11-17 21:53 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:28e4cc47506f1fef8111353e34357a0214aa905f
commit 28e4cc47506f1fef8111353e34357a0214aa905f
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Fri Nov 11 19:45:57 2022 -0500
Add saturating subtract built-in.
This patch adds support for a saturating subtract built-in function that may be
added to a future PowerPC processor. Note, if it is added, the name of the
built-in function may change before GCC 13 is released. If the name changes, we
will submit a patch changing the name.
I did add support for providing dense math built-in functions, even though at
present, we have not added any new built-in functions for dense math.
2022-11-11 Michael Meissner <meissner@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin.cc (rs6000_invalid_builtin): Add support
for flagging invalid use of future built-in functions.
(rs6000_builtin_is_supported): Add support for future built-in
functions.
* config/rs6000/rs6000-builtins.def (__builtin_saturate_subtract32): New
built-in function for -mcpu=future.
(__builtin_saturate_subtract64): Likewise.
* config/rs6000/rs6000-gen-builtins.cc (enum bif_stanza): Add stanzas
for -mcpu=future built-ins.
(stanza_map): Likewise.
(enable_string): Likewise.
(struct attrinfo): Likewise.
(parse_bif_attrs): Likewise.
(write_decls): Likewise.
* config/rs6000/rs6000.md (sat_sub<mode>3): Add saturating subtract
built-in insn declarations.
(sat_sub<mode>3_dot): Likewise.
(sat_sub<mode>3_dot2): Likewise.
gcc/testsuite/
* gcc.target/powerpc/subfus-1.c: New test.
* gcc.target/powerpc/subfus-2.c: Likewise.
* lib/target-supports.exp (check_effective_target_powerpc_subfus_ok):
New effective target.
Diff:
---
gcc/config/rs6000/rs6000-builtin.cc | 17 ++++++++
gcc/config/rs6000/rs6000-builtins.def | 11 ++++++
gcc/config/rs6000/rs6000-gen-builtins.cc | 35 ++++++++++++++---
gcc/config/rs6000/rs6000.md | 60 +++++++++++++++++++++++++++++
gcc/testsuite/gcc.target/powerpc/subfus-1.c | 32 +++++++++++++++
gcc/testsuite/gcc.target/powerpc/subfus-2.c | 32 +++++++++++++++
gcc/testsuite/lib/target-supports.exp | 16 ++++++++
7 files changed, 198 insertions(+), 5 deletions(-)
diff --git a/gcc/config/rs6000/rs6000-builtin.cc b/gcc/config/rs6000/rs6000-builtin.cc
index f4eba184db8..1ac00e4b26c 100644
--- a/gcc/config/rs6000/rs6000-builtin.cc
+++ b/gcc/config/rs6000/rs6000-builtin.cc
@@ -139,6 +139,17 @@ rs6000_invalid_builtin (enum rs6000_gen_builtins fncode)
case ENB_MMA:
error ("%qs requires the %qs option", name, "-mmma");
break;
+ case ENB_FUTURE:
+ error ("%qs requires the %qs option", name, "-mcpu=future");
+ break;
+ case ENB_FUTURE_64:
+ error ("%qs requires the %qs option and either the %qs or %qs option",
+ name, "-mcpu=future", "-m64", "-mpowerpc64");
+ break;
+ case ENB_DM:
+ error ("%qs requires the %qs or %qs options", name, "-mcpu=future",
+ "-mdense-math");
+ break;
default:
case ENB_ALWAYS:
gcc_unreachable ();
@@ -194,6 +205,12 @@ rs6000_builtin_is_supported (enum rs6000_gen_builtins fncode)
return TARGET_HTM;
case ENB_MMA:
return TARGET_MMA;
+ case ENB_FUTURE:
+ return TARGET_FUTURE;
+ case ENB_FUTURE_64:
+ return TARGET_FUTURE && TARGET_POWERPC64;
+ case ENB_DM:
+ return TARGET_DENSE_MATH;
default:
gcc_unreachable ();
}
diff --git a/gcc/config/rs6000/rs6000-builtins.def b/gcc/config/rs6000/rs6000-builtins.def
index f76f54793d7..ee141c1d99e 100644
--- a/gcc/config/rs6000/rs6000-builtins.def
+++ b/gcc/config/rs6000/rs6000-builtins.def
@@ -139,6 +139,8 @@
; endian Needs special handling for endianness
; ibmld Restrict usage to the case when TFmode is IBM-128
; ibm128 Restrict usage to the case where __ibm128 is supported or if ibmld
+; future Restrict usage to future instructions
+; dm Restrict usage to dense math
;
; Each attribute corresponds to extra processing required when
; the built-in is expanded. All such special processing should
@@ -4108,3 +4110,12 @@
void __builtin_vsx_stxvp (v256, unsigned long, const v256 *);
STXVP nothing {mma,pair}
+
+[future]
+ const signed int __builtin_saturate_subtract32 (signed int, signed int);
+ SAT_SUBSI sat_subsi3 {}
+
+[future-64]
+ const signed long __builtin_saturate_subtract64 (signed long, signed long);
+ SAT_SUBDI sat_subdi3 {}
+
diff --git a/gcc/config/rs6000/rs6000-gen-builtins.cc b/gcc/config/rs6000/rs6000-gen-builtins.cc
index 0bd7a535e5f..f4020141243 100644
--- a/gcc/config/rs6000/rs6000-gen-builtins.cc
+++ b/gcc/config/rs6000/rs6000-gen-builtins.cc
@@ -233,6 +233,9 @@ enum bif_stanza
BSTZ_P10,
BSTZ_P10_64,
BSTZ_MMA,
+ BSTZ_FUTURE,
+ BSTZ_FUTURE_64,
+ BSTZ_DM,
NUMBIFSTANZAS
};
@@ -266,7 +269,10 @@ static stanza_entry stanza_map[NUMBIFSTANZAS] =
{ "htm", BSTZ_HTM },
{ "power10", BSTZ_P10 },
{ "power10-64", BSTZ_P10_64 },
- { "mma", BSTZ_MMA }
+ { "mma", BSTZ_MMA },
+ { "future", BSTZ_FUTURE },
+ { "future-64", BSTZ_FUTURE_64 },
+ { "dm", BSTZ_DM },
};
static const char *enable_string[NUMBIFSTANZAS] =
@@ -291,7 +297,10 @@ static const char *enable_string[NUMBIFSTANZAS] =
"ENB_HTM",
"ENB_P10",
"ENB_P10_64",
- "ENB_MMA"
+ "ENB_MMA",
+ "ENB_FUTURE",
+ "ENB_FUTURE_64",
+ "ENB_DM",
};
/* Function modifiers provide special handling for const, pure, and fpmath
@@ -395,6 +404,8 @@ struct attrinfo
bool isendian;
bool isibmld;
bool isibm128;
+ bool isfuture;
+ bool isdm;
};
/* Fields associated with a function prototype (bif or overload). */
@@ -1477,7 +1488,8 @@ parse_bif_attrs (attrinfo *attrptr)
"ldvec = %d, stvec = %d, reve = %d, pred = %d, htm = %d, "
"htmspr = %d, htmcr = %d, mma = %d, quad = %d, pair = %d, "
"mmaint = %d, no32bit = %d, 32bit = %d, cpu = %d, ldstmask = %d, "
- "lxvrse = %d, lxvrze = %d, endian = %d, ibmdld = %d, ibm128 = %d.\n",
+ "lxvrse = %d, lxvrze = %d, endian = %d, ibmdld = %d, ibm128 = %d,",
+ "future = %d, dm = %d.\n",
attrptr->isinit, attrptr->isset, attrptr->isextract,
attrptr->isnosoft, attrptr->isldvec, attrptr->isstvec,
attrptr->isreve, attrptr->ispred, attrptr->ishtm, attrptr->ishtmspr,
@@ -1485,7 +1497,7 @@ parse_bif_attrs (attrinfo *attrptr)
attrptr->ismmaint, attrptr->isno32bit, attrptr->is32bit,
attrptr->iscpu, attrptr->isldstmask, attrptr->islxvrse,
attrptr->islxvrze, attrptr->isendian, attrptr->isibmld,
- attrptr->isibm128);
+ attrptr->isibm128, attrptr->isfuture, attrptr->isdm);
#endif
return PC_OK;
@@ -2257,7 +2269,10 @@ write_decls (void)
fprintf (header_file, " ENB_HTM,\n");
fprintf (header_file, " ENB_P10,\n");
fprintf (header_file, " ENB_P10_64,\n");
- fprintf (header_file, " ENB_MMA\n");
+ fprintf (header_file, " ENB_MMA,\n");
+ fprintf (header_file, " ENB_FUTURE,\n");
+ fprintf (header_file, " ENB_FUTURE_64,\n");
+ fprintf (header_file, " ENB_DM\n");
fprintf (header_file, "};\n\n");
fprintf (header_file, "#define PPC_MAXRESTROPNDS 3\n");
@@ -2301,6 +2316,8 @@ write_decls (void)
fprintf (header_file, "#define bif_endian_bit\t\t(0x00200000)\n");
fprintf (header_file, "#define bif_ibmld_bit\t\t(0x00400000)\n");
fprintf (header_file, "#define bif_ibm128_bit\t\t(0x00800000)\n");
+ fprintf (header_file, "#define bif_future_bit\t\t(0x01000000)\n");
+ fprintf (header_file, "#define bif_dm_bit\t\t(0x02000000)\n");
fprintf (header_file, "\n");
fprintf (header_file,
"#define bif_is_init(x)\t\t((x).bifattrs & bif_init_bit)\n");
@@ -2350,6 +2367,10 @@ write_decls (void)
"#define bif_is_ibmld(x)\t((x).bifattrs & bif_ibmld_bit)\n");
fprintf (header_file,
"#define bif_is_ibm128(x)\t((x).bifattrs & bif_ibm128_bit)\n");
+ fprintf (header_file,
+ "#define bif_is_future(x)\t((x).bifattrs & bif_future_bit)\n");
+ fprintf (header_file,
+ "#define bif_is_dm(x)\t((x).bifattrs & bif_dm_bit)\n");
fprintf (header_file, "\n");
fprintf (header_file,
@@ -2548,6 +2569,10 @@ write_bif_static_init (void)
fprintf (init_file, " | bif_ibmld_bit");
if (bifp->attrs.isibm128)
fprintf (init_file, " | bif_ibm128_bit");
+ if (bifp->attrs.isfuture)
+ fprintf (init_file, " | bif_future_bit");
+ if (bifp->attrs.isdm)
+ fprintf (init_file, " | bif_dm_bit");
fprintf (init_file, ",\n");
fprintf (init_file, " /* restr_opnd */\t{%d, %d, %d},\n",
bifp->proto.restr_opnd[0], bifp->proto.restr_opnd[1],
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 4a5007dc539..e9dfb138603 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -15499,6 +15499,66 @@
}
[(set_attr "type" "load")])
\f
+;; Signed saturation.
+
+;; The subfus instruction is defined as: SUBFUS RT,L,RA,RB. The extended
+;; mnemonic that we use (subdus and subwus) has the arguments RA and RB
+;; reversed (so it becomes a subtract instead of subtract from).
+
+(define_insn "sat_sub<mode>3"
+ [(set (match_operand:GPR 0 "gpc_reg_operand" "=r")
+ (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r")))]
+ "TARGET_FUTURE"
+ "sub<wd>us %0,%1,%2"
+ [(set_attr "type" "add")])
+
+(define_insn_and_split "*sat_sub<mode>3_dot"
+ [(set (match_operand:CC 3 "cc_reg_operand" "=x,?y")
+ (compare:CC (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r,r"))
+ (const_int 0)))
+ (clobber (match_scratch:GPR 0 "=r,r"))]
+ "TARGET_FUTURE"
+ "@
+ sub<wd>us. %0,%1,%2
+ #"
+ "&& reload_completed && cc_reg_not_cr0_operand (operands[3], CCmode)"
+ [(set (match_dup 0)
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 3)
+ (compare:CC (match_dup 0)
+ (const_int 0)))]
+ ""
+ [(set_attr "type" "add")
+ (set_attr "dot" "yes")
+ (set_attr "length" "4,8")])
+
+(define_insn_and_split "*sat_sub<mode>3_dot2"
+ [(set (match_operand:CC 3 "cc_reg_operand" "=x,?y")
+ (compare:CC (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r,r"))
+ (const_int 0)))
+ (set (match_operand:GPR 0 "gpc_reg_operand" "=r,r")
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))]
+ "TARGET_FUTURE"
+ "@
+ sub<wd>us. %0,%1,%2
+ #"
+ "&& reload_completed && cc_reg_not_cr0_operand (operands[3], CCmode)"
+ [(set (match_dup 0)
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 3)
+ (compare:CC (match_dup 0)
+ (const_int 0)))]
+ ""
+ [(set_attr "type" "add")
+ (set_attr "dot" "yes")
+ (set_attr "length" "4,8")])
+\f
(include "sync.md")
(include "vector.md")
diff --git a/gcc/testsuite/gcc.target/powerpc/subfus-1.c b/gcc/testsuite/gcc.target/powerpc/subfus-1.c
new file mode 100644
index 00000000000..68007e96cce
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/subfus-1.c
@@ -0,0 +1,32 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_subfus_ok } */
+/* { dg-options "-mdejagnu-cpu=future -O2" } */
+
+/* Test whether the saturating subtract built-in generates subwus for 32-bit
+ subtracts. */
+
+int do_sat_int (int a, int b)
+{
+ return __builtin_saturate_subtract32 (a, b); /* subwus */
+}
+
+int do_sat_int_dot (int a, int b, int *p)
+{
+ int r = __builtin_saturate_subtract32 (a, b); /* subwus. */
+ if (r == 0)
+ *p = 0;
+
+ return r;
+}
+
+void do_sat_int_dot2 (int a, int b, int *p, int *q)
+{
+ if (__builtin_saturate_subtract32 (a, b)) /* subwus. */
+ *p = 0;
+
+ *q = a + b;
+ return;
+}
+
+/* { dg-final { scan-assembler {\msubwus\M} } } */
+/* { dg-final { scan-assembler-not {\msubf\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/subfus-2.c b/gcc/testsuite/gcc.target/powerpc/subfus-2.c
new file mode 100644
index 00000000000..56e6d237900
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/subfus-2.c
@@ -0,0 +1,32 @@
+/* { dg-do compile { target lp64 } } */
+/* { dg-require-effective-target powerpc_subfus_ok } */
+/* { dg-options "-mdejagnu-cpu=future -O2" } */
+
+/* Test whether the saturating subtract built-in generates subwus for 64-bit
+ subtracts. */
+
+long do_sat_long (long a, long b)
+{
+ return __builtin_saturate_subtract64 (a, b); /* subwus */
+}
+
+long do_sat_long_dot (long a, long b, long *p)
+{
+ long r = __builtin_saturate_subtract64 (a, b); /* subwus. */
+ if (r == 0)
+ *p = 0;
+
+ return r;
+}
+
+void do_sat_long_dot2 (long a, long b, long *p, long *q)
+{
+ if (__builtin_saturate_subtract64 (a, b)) /* subwus. */
+ *p = 0;
+
+ *q = a + b;
+ return;
+}
+
+/* { dg-final { scan-assembler {\msubdus\M} } } */
+/* { dg-final { scan-assembler-not {\msubf\M} } } */
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index b70ebf963f9..8af840d1d3b 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -6553,6 +6553,22 @@ proc check_effective_target_powerpc_dense_math_ok { } {
} "-mcpu=future"]
}
+# Return 1 if this is a PowerPC target supporting -mcpu=future which enables
+# the saturating subtract instruction.
+proc check_effective_target_powerpc_subfus_ok { } {
+ return [check_no_compiler_messages_nocache powerpc_subfus_ok assembly {
+ int test (int a, int b)
+ {
+ #ifndef _ARCH_PWR_FUTURE
+ #error "target does not have saturating subtract support."
+ #else
+ /* Make sure we have saturating subtract support. */
+ return __builtin_saturate_subtract32 (a, b);
+ #endif
+ }
+ } "-mcpu=future"]
+}
+
# Return 1 if this is a PowerPC target supporting -mfloat128 via either
# software emulation on power7/power8 systems or hardware support on power9.
^ permalink raw reply [flat|nested] 4+ messages in thread
* [gcc(refs/users/meissner/heads/dmf004)] Add saturating subtract built-in.
@ 2022-11-17 21:53 Michael Meissner
0 siblings, 0 replies; 4+ messages in thread
From: Michael Meissner @ 2022-11-17 21:53 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:08e21237623cb6b52a4bb9920cadb20c344629ae
commit 08e21237623cb6b52a4bb9920cadb20c344629ae
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Fri Nov 11 18:15:09 2022 -0500
Add saturating subtract built-in.
This patch adds support for a saturating subtract built-in function that may be
added to a future PowerPC processor. Note, if it is added, the name of the
built-in function may change before GCC 13 is released. If the name changes, we
will submit a patch changing the name.
I did add support for providing dense math built-in functions, even though at
present, we have not added any new built-in functions for dense math.
2022-11-11 Michael Meissner <meissner@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin.cc (rs6000_invalid_builtin): Add support
for flagging invalid use of future built-in functions.
(rs6000_builtin_is_supported): Add support for future built-in
functions.
* config/rs6000/rs6000-builtins.def (__builtin_saturate_subtract32): New
built-in function for -mcpu=future.
(__builtin_saturate_subtract64): Likewise.
* config/rs6000/rs6000-gen-builtins.cc (enum bif_stanza): Add stanzas
for -mcpu=future built-ins.
(stanza_map): Likewise.
(enable_string): Likewise.
(struct attrinfo): Likewise.
(parse_bif_attrs): Likewise.
(write_decls): Likewise.
* config/rs6000/rs6000.md (sat_sub<mode>3): Add saturating subtract
built-in insn declarations.
(sat_sub<mode>3_dot): Likewise.
(sat_sub<mode>3_dot2): Likewise.
gcc/testsuite/
* gcc.target/powerpc/subfus-1.c: New test.
* gcc.target/powerpc/subfus-2.c: Likewise.
* lib/target-supports.exp (check_effective_target_powerpc_subfus_ok):
New effective target.
Diff:
---
gcc/config/rs6000/rs6000-builtin.cc | 17 ++++++++
gcc/config/rs6000/rs6000-builtins.def | 11 ++++++
gcc/config/rs6000/rs6000-gen-builtins.cc | 35 ++++++++++++++---
gcc/config/rs6000/rs6000.md | 60 +++++++++++++++++++++++++++++
gcc/testsuite/gcc.target/powerpc/subfus-1.c | 31 +++++++++++++++
gcc/testsuite/gcc.target/powerpc/subfus-2.c | 31 +++++++++++++++
gcc/testsuite/lib/target-supports.exp | 16 ++++++++
7 files changed, 196 insertions(+), 5 deletions(-)
diff --git a/gcc/config/rs6000/rs6000-builtin.cc b/gcc/config/rs6000/rs6000-builtin.cc
index f4eba184db8..1ac00e4b26c 100644
--- a/gcc/config/rs6000/rs6000-builtin.cc
+++ b/gcc/config/rs6000/rs6000-builtin.cc
@@ -139,6 +139,17 @@ rs6000_invalid_builtin (enum rs6000_gen_builtins fncode)
case ENB_MMA:
error ("%qs requires the %qs option", name, "-mmma");
break;
+ case ENB_FUTURE:
+ error ("%qs requires the %qs option", name, "-mcpu=future");
+ break;
+ case ENB_FUTURE_64:
+ error ("%qs requires the %qs option and either the %qs or %qs option",
+ name, "-mcpu=future", "-m64", "-mpowerpc64");
+ break;
+ case ENB_DM:
+ error ("%qs requires the %qs or %qs options", name, "-mcpu=future",
+ "-mdense-math");
+ break;
default:
case ENB_ALWAYS:
gcc_unreachable ();
@@ -194,6 +205,12 @@ rs6000_builtin_is_supported (enum rs6000_gen_builtins fncode)
return TARGET_HTM;
case ENB_MMA:
return TARGET_MMA;
+ case ENB_FUTURE:
+ return TARGET_FUTURE;
+ case ENB_FUTURE_64:
+ return TARGET_FUTURE && TARGET_POWERPC64;
+ case ENB_DM:
+ return TARGET_DENSE_MATH;
default:
gcc_unreachable ();
}
diff --git a/gcc/config/rs6000/rs6000-builtins.def b/gcc/config/rs6000/rs6000-builtins.def
index f76f54793d7..ee141c1d99e 100644
--- a/gcc/config/rs6000/rs6000-builtins.def
+++ b/gcc/config/rs6000/rs6000-builtins.def
@@ -139,6 +139,8 @@
; endian Needs special handling for endianness
; ibmld Restrict usage to the case when TFmode is IBM-128
; ibm128 Restrict usage to the case where __ibm128 is supported or if ibmld
+; future Restrict usage to future instructions
+; dm Restrict usage to dense math
;
; Each attribute corresponds to extra processing required when
; the built-in is expanded. All such special processing should
@@ -4108,3 +4110,12 @@
void __builtin_vsx_stxvp (v256, unsigned long, const v256 *);
STXVP nothing {mma,pair}
+
+[future]
+ const signed int __builtin_saturate_subtract32 (signed int, signed int);
+ SAT_SUBSI sat_subsi3 {}
+
+[future-64]
+ const signed long __builtin_saturate_subtract64 (signed long, signed long);
+ SAT_SUBDI sat_subdi3 {}
+
diff --git a/gcc/config/rs6000/rs6000-gen-builtins.cc b/gcc/config/rs6000/rs6000-gen-builtins.cc
index 0bd7a535e5f..f4020141243 100644
--- a/gcc/config/rs6000/rs6000-gen-builtins.cc
+++ b/gcc/config/rs6000/rs6000-gen-builtins.cc
@@ -233,6 +233,9 @@ enum bif_stanza
BSTZ_P10,
BSTZ_P10_64,
BSTZ_MMA,
+ BSTZ_FUTURE,
+ BSTZ_FUTURE_64,
+ BSTZ_DM,
NUMBIFSTANZAS
};
@@ -266,7 +269,10 @@ static stanza_entry stanza_map[NUMBIFSTANZAS] =
{ "htm", BSTZ_HTM },
{ "power10", BSTZ_P10 },
{ "power10-64", BSTZ_P10_64 },
- { "mma", BSTZ_MMA }
+ { "mma", BSTZ_MMA },
+ { "future", BSTZ_FUTURE },
+ { "future-64", BSTZ_FUTURE_64 },
+ { "dm", BSTZ_DM },
};
static const char *enable_string[NUMBIFSTANZAS] =
@@ -291,7 +297,10 @@ static const char *enable_string[NUMBIFSTANZAS] =
"ENB_HTM",
"ENB_P10",
"ENB_P10_64",
- "ENB_MMA"
+ "ENB_MMA",
+ "ENB_FUTURE",
+ "ENB_FUTURE_64",
+ "ENB_DM",
};
/* Function modifiers provide special handling for const, pure, and fpmath
@@ -395,6 +404,8 @@ struct attrinfo
bool isendian;
bool isibmld;
bool isibm128;
+ bool isfuture;
+ bool isdm;
};
/* Fields associated with a function prototype (bif or overload). */
@@ -1477,7 +1488,8 @@ parse_bif_attrs (attrinfo *attrptr)
"ldvec = %d, stvec = %d, reve = %d, pred = %d, htm = %d, "
"htmspr = %d, htmcr = %d, mma = %d, quad = %d, pair = %d, "
"mmaint = %d, no32bit = %d, 32bit = %d, cpu = %d, ldstmask = %d, "
- "lxvrse = %d, lxvrze = %d, endian = %d, ibmdld = %d, ibm128 = %d.\n",
+ "lxvrse = %d, lxvrze = %d, endian = %d, ibmdld = %d, ibm128 = %d,",
+ "future = %d, dm = %d.\n",
attrptr->isinit, attrptr->isset, attrptr->isextract,
attrptr->isnosoft, attrptr->isldvec, attrptr->isstvec,
attrptr->isreve, attrptr->ispred, attrptr->ishtm, attrptr->ishtmspr,
@@ -1485,7 +1497,7 @@ parse_bif_attrs (attrinfo *attrptr)
attrptr->ismmaint, attrptr->isno32bit, attrptr->is32bit,
attrptr->iscpu, attrptr->isldstmask, attrptr->islxvrse,
attrptr->islxvrze, attrptr->isendian, attrptr->isibmld,
- attrptr->isibm128);
+ attrptr->isibm128, attrptr->isfuture, attrptr->isdm);
#endif
return PC_OK;
@@ -2257,7 +2269,10 @@ write_decls (void)
fprintf (header_file, " ENB_HTM,\n");
fprintf (header_file, " ENB_P10,\n");
fprintf (header_file, " ENB_P10_64,\n");
- fprintf (header_file, " ENB_MMA\n");
+ fprintf (header_file, " ENB_MMA,\n");
+ fprintf (header_file, " ENB_FUTURE,\n");
+ fprintf (header_file, " ENB_FUTURE_64,\n");
+ fprintf (header_file, " ENB_DM\n");
fprintf (header_file, "};\n\n");
fprintf (header_file, "#define PPC_MAXRESTROPNDS 3\n");
@@ -2301,6 +2316,8 @@ write_decls (void)
fprintf (header_file, "#define bif_endian_bit\t\t(0x00200000)\n");
fprintf (header_file, "#define bif_ibmld_bit\t\t(0x00400000)\n");
fprintf (header_file, "#define bif_ibm128_bit\t\t(0x00800000)\n");
+ fprintf (header_file, "#define bif_future_bit\t\t(0x01000000)\n");
+ fprintf (header_file, "#define bif_dm_bit\t\t(0x02000000)\n");
fprintf (header_file, "\n");
fprintf (header_file,
"#define bif_is_init(x)\t\t((x).bifattrs & bif_init_bit)\n");
@@ -2350,6 +2367,10 @@ write_decls (void)
"#define bif_is_ibmld(x)\t((x).bifattrs & bif_ibmld_bit)\n");
fprintf (header_file,
"#define bif_is_ibm128(x)\t((x).bifattrs & bif_ibm128_bit)\n");
+ fprintf (header_file,
+ "#define bif_is_future(x)\t((x).bifattrs & bif_future_bit)\n");
+ fprintf (header_file,
+ "#define bif_is_dm(x)\t((x).bifattrs & bif_dm_bit)\n");
fprintf (header_file, "\n");
fprintf (header_file,
@@ -2548,6 +2569,10 @@ write_bif_static_init (void)
fprintf (init_file, " | bif_ibmld_bit");
if (bifp->attrs.isibm128)
fprintf (init_file, " | bif_ibm128_bit");
+ if (bifp->attrs.isfuture)
+ fprintf (init_file, " | bif_future_bit");
+ if (bifp->attrs.isdm)
+ fprintf (init_file, " | bif_dm_bit");
fprintf (init_file, ",\n");
fprintf (init_file, " /* restr_opnd */\t{%d, %d, %d},\n",
bifp->proto.restr_opnd[0], bifp->proto.restr_opnd[1],
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 4a5007dc539..e9dfb138603 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -15499,6 +15499,66 @@
}
[(set_attr "type" "load")])
\f
+;; Signed saturation.
+
+;; The subfus instruction is defined as: SUBFUS RT,L,RA,RB. The extended
+;; mnemonic that we use (subdus and subwus) has the arguments RA and RB
+;; reversed (so it becomes a subtract instead of subtract from).
+
+(define_insn "sat_sub<mode>3"
+ [(set (match_operand:GPR 0 "gpc_reg_operand" "=r")
+ (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r")))]
+ "TARGET_FUTURE"
+ "sub<wd>us %0,%1,%2"
+ [(set_attr "type" "add")])
+
+(define_insn_and_split "*sat_sub<mode>3_dot"
+ [(set (match_operand:CC 3 "cc_reg_operand" "=x,?y")
+ (compare:CC (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r,r"))
+ (const_int 0)))
+ (clobber (match_scratch:GPR 0 "=r,r"))]
+ "TARGET_FUTURE"
+ "@
+ sub<wd>us. %0,%1,%2
+ #"
+ "&& reload_completed && cc_reg_not_cr0_operand (operands[3], CCmode)"
+ [(set (match_dup 0)
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 3)
+ (compare:CC (match_dup 0)
+ (const_int 0)))]
+ ""
+ [(set_attr "type" "add")
+ (set_attr "dot" "yes")
+ (set_attr "length" "4,8")])
+
+(define_insn_and_split "*sat_sub<mode>3_dot2"
+ [(set (match_operand:CC 3 "cc_reg_operand" "=x,?y")
+ (compare:CC (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r,r"))
+ (const_int 0)))
+ (set (match_operand:GPR 0 "gpc_reg_operand" "=r,r")
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))]
+ "TARGET_FUTURE"
+ "@
+ sub<wd>us. %0,%1,%2
+ #"
+ "&& reload_completed && cc_reg_not_cr0_operand (operands[3], CCmode)"
+ [(set (match_dup 0)
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 3)
+ (compare:CC (match_dup 0)
+ (const_int 0)))]
+ ""
+ [(set_attr "type" "add")
+ (set_attr "dot" "yes")
+ (set_attr "length" "4,8")])
+\f
(include "sync.md")
(include "vector.md")
diff --git a/gcc/testsuite/gcc.target/powerpc/subfus-1.c b/gcc/testsuite/gcc.target/powerpc/subfus-1.c
new file mode 100644
index 00000000000..dd2cde47570
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/subfus-1.c
@@ -0,0 +1,31 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_subfus_ok } */
+/* { dg-options "-mdejagnu-cpu=future -O2" } */
+
+/* Test whether the saturating subtract built-in generates subwus for 32-bit
+ subtracts. */
+
+int do_sat_int (int a, int b)
+{
+ return __builtin_saturate_subtract32 (a, b); /* subwus */
+}
+
+int do_sat_int_dot (int a, int b, int *p)
+{
+ int r = __builtin_saturate_subtract32 (a, b); /* subwus. */
+ if (r == 0)
+ *p = 0;
+ return r;
+}
+
+void do_sat_int_dot2 (int a, int b, int *p, int *q)
+{
+ if (__builtin_saturate_subtract32 (a, b)) /* subwus. */
+ *p = 0;
+ *q = a + b;
+ return;
+}
+
+/* { dg-final { scan-assembler-times {\msubwus\M} 1 } } */
+/* { dg-final { scan-assembler-times {\msubwus[.]\M} 2 } } */
+/* { dg-final { scan-assembler-not {\msubf\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/subfus-2.c b/gcc/testsuite/gcc.target/powerpc/subfus-2.c
new file mode 100644
index 00000000000..c9511fe22cd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/subfus-2.c
@@ -0,0 +1,31 @@
+/* { dg-do compile { target lp64 } } */
+/* { dg-require-effective-target powerpc_subfus_ok } */
+/* { dg-options "-mdejagnu-cpu=future -O2" } */
+
+/* Test whether the saturating subtract built-in generates subwus for 64-bit
+ subtracts. */
+
+long do_sat_long (long a, long b)
+{
+ return __builtin_saturate_subtract64 (a, b); /* subwus */
+}
+
+long do_sat_long_dot (long a, long b, long *p)
+{
+ long r = __builtin_saturate_subtract64 (a, b); /* subwus. */
+ if (r == 0)
+ *p = 0;
+ return r;
+}
+
+void do_sat_long_dot2 (long a, long b, long *p, long *q)
+{
+ if (__builtin_saturate_subtract64 (a, b)) /* subwus. */
+ *p = 0;
+ *q = a + b;
+ return;
+}
+
+/* { dg-final { scan-assembler-times {\msubdus\M} 1 } } */
+/* { dg-final { scan-assembler-times {\msubdus[.]\M} 2 } } */
+/* { dg-final { scan-assembler-not {\msubf\M} } } */
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index b70ebf963f9..8af840d1d3b 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -6553,6 +6553,22 @@ proc check_effective_target_powerpc_dense_math_ok { } {
} "-mcpu=future"]
}
+# Return 1 if this is a PowerPC target supporting -mcpu=future which enables
+# the saturating subtract instruction.
+proc check_effective_target_powerpc_subfus_ok { } {
+ return [check_no_compiler_messages_nocache powerpc_subfus_ok assembly {
+ int test (int a, int b)
+ {
+ #ifndef _ARCH_PWR_FUTURE
+ #error "target does not have saturating subtract support."
+ #else
+ /* Make sure we have saturating subtract support. */
+ return __builtin_saturate_subtract32 (a, b);
+ #endif
+ }
+ } "-mcpu=future"]
+}
+
# Return 1 if this is a PowerPC target supporting -mfloat128 via either
# software emulation on power7/power8 systems or hardware support on power9.
^ permalink raw reply [flat|nested] 4+ messages in thread
* [gcc(refs/users/meissner/heads/dmf004)] Add saturating subtract built-in.
@ 2022-11-12 0:46 Michael Meissner
0 siblings, 0 replies; 4+ messages in thread
From: Michael Meissner @ 2022-11-12 0:46 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:694e282516d28933354db5824ad07c16785c8a36
commit 694e282516d28933354db5824ad07c16785c8a36
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Fri Nov 11 19:45:57 2022 -0500
Add saturating subtract built-in.
This patch adds support for a saturating subtract built-in function that may be
added to a future PowerPC processor. Note, if it is added, the name of the
built-in function may change before GCC 13 is released. If the name changes, we
will submit a patch changing the name.
I did add support for providing dense math built-in functions, even though at
present, we have not added any new built-in functions for dense math.
2022-11-11 Michael Meissner <meissner@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin.cc (rs6000_invalid_builtin): Add support
for flagging invalid use of future built-in functions.
(rs6000_builtin_is_supported): Add support for future built-in
functions.
* config/rs6000/rs6000-builtins.def (__builtin_saturate_subtract32): New
built-in function for -mcpu=future.
(__builtin_saturate_subtract64): Likewise.
* config/rs6000/rs6000-gen-builtins.cc (enum bif_stanza): Add stanzas
for -mcpu=future built-ins.
(stanza_map): Likewise.
(enable_string): Likewise.
(struct attrinfo): Likewise.
(parse_bif_attrs): Likewise.
(write_decls): Likewise.
* config/rs6000/rs6000.md (sat_sub<mode>3): Add saturating subtract
built-in insn declarations.
(sat_sub<mode>3_dot): Likewise.
(sat_sub<mode>3_dot2): Likewise.
gcc/testsuite/
* gcc.target/powerpc/subfus-1.c: New test.
* gcc.target/powerpc/subfus-2.c: Likewise.
* lib/target-supports.exp (check_effective_target_powerpc_subfus_ok):
New effective target.
Diff:
---
gcc/config/rs6000/rs6000-builtin.cc | 17 ++++++++
gcc/config/rs6000/rs6000-builtins.def | 11 ++++++
gcc/config/rs6000/rs6000-gen-builtins.cc | 35 ++++++++++++++---
gcc/config/rs6000/rs6000.md | 60 +++++++++++++++++++++++++++++
gcc/testsuite/gcc.target/powerpc/subfus-1.c | 32 +++++++++++++++
gcc/testsuite/gcc.target/powerpc/subfus-2.c | 32 +++++++++++++++
gcc/testsuite/lib/target-supports.exp | 16 ++++++++
7 files changed, 198 insertions(+), 5 deletions(-)
diff --git a/gcc/config/rs6000/rs6000-builtin.cc b/gcc/config/rs6000/rs6000-builtin.cc
index f4eba184db8..1ac00e4b26c 100644
--- a/gcc/config/rs6000/rs6000-builtin.cc
+++ b/gcc/config/rs6000/rs6000-builtin.cc
@@ -139,6 +139,17 @@ rs6000_invalid_builtin (enum rs6000_gen_builtins fncode)
case ENB_MMA:
error ("%qs requires the %qs option", name, "-mmma");
break;
+ case ENB_FUTURE:
+ error ("%qs requires the %qs option", name, "-mcpu=future");
+ break;
+ case ENB_FUTURE_64:
+ error ("%qs requires the %qs option and either the %qs or %qs option",
+ name, "-mcpu=future", "-m64", "-mpowerpc64");
+ break;
+ case ENB_DM:
+ error ("%qs requires the %qs or %qs options", name, "-mcpu=future",
+ "-mdense-math");
+ break;
default:
case ENB_ALWAYS:
gcc_unreachable ();
@@ -194,6 +205,12 @@ rs6000_builtin_is_supported (enum rs6000_gen_builtins fncode)
return TARGET_HTM;
case ENB_MMA:
return TARGET_MMA;
+ case ENB_FUTURE:
+ return TARGET_FUTURE;
+ case ENB_FUTURE_64:
+ return TARGET_FUTURE && TARGET_POWERPC64;
+ case ENB_DM:
+ return TARGET_DENSE_MATH;
default:
gcc_unreachable ();
}
diff --git a/gcc/config/rs6000/rs6000-builtins.def b/gcc/config/rs6000/rs6000-builtins.def
index f76f54793d7..ee141c1d99e 100644
--- a/gcc/config/rs6000/rs6000-builtins.def
+++ b/gcc/config/rs6000/rs6000-builtins.def
@@ -139,6 +139,8 @@
; endian Needs special handling for endianness
; ibmld Restrict usage to the case when TFmode is IBM-128
; ibm128 Restrict usage to the case where __ibm128 is supported or if ibmld
+; future Restrict usage to future instructions
+; dm Restrict usage to dense math
;
; Each attribute corresponds to extra processing required when
; the built-in is expanded. All such special processing should
@@ -4108,3 +4110,12 @@
void __builtin_vsx_stxvp (v256, unsigned long, const v256 *);
STXVP nothing {mma,pair}
+
+[future]
+ const signed int __builtin_saturate_subtract32 (signed int, signed int);
+ SAT_SUBSI sat_subsi3 {}
+
+[future-64]
+ const signed long __builtin_saturate_subtract64 (signed long, signed long);
+ SAT_SUBDI sat_subdi3 {}
+
diff --git a/gcc/config/rs6000/rs6000-gen-builtins.cc b/gcc/config/rs6000/rs6000-gen-builtins.cc
index 0bd7a535e5f..f4020141243 100644
--- a/gcc/config/rs6000/rs6000-gen-builtins.cc
+++ b/gcc/config/rs6000/rs6000-gen-builtins.cc
@@ -233,6 +233,9 @@ enum bif_stanza
BSTZ_P10,
BSTZ_P10_64,
BSTZ_MMA,
+ BSTZ_FUTURE,
+ BSTZ_FUTURE_64,
+ BSTZ_DM,
NUMBIFSTANZAS
};
@@ -266,7 +269,10 @@ static stanza_entry stanza_map[NUMBIFSTANZAS] =
{ "htm", BSTZ_HTM },
{ "power10", BSTZ_P10 },
{ "power10-64", BSTZ_P10_64 },
- { "mma", BSTZ_MMA }
+ { "mma", BSTZ_MMA },
+ { "future", BSTZ_FUTURE },
+ { "future-64", BSTZ_FUTURE_64 },
+ { "dm", BSTZ_DM },
};
static const char *enable_string[NUMBIFSTANZAS] =
@@ -291,7 +297,10 @@ static const char *enable_string[NUMBIFSTANZAS] =
"ENB_HTM",
"ENB_P10",
"ENB_P10_64",
- "ENB_MMA"
+ "ENB_MMA",
+ "ENB_FUTURE",
+ "ENB_FUTURE_64",
+ "ENB_DM",
};
/* Function modifiers provide special handling for const, pure, and fpmath
@@ -395,6 +404,8 @@ struct attrinfo
bool isendian;
bool isibmld;
bool isibm128;
+ bool isfuture;
+ bool isdm;
};
/* Fields associated with a function prototype (bif or overload). */
@@ -1477,7 +1488,8 @@ parse_bif_attrs (attrinfo *attrptr)
"ldvec = %d, stvec = %d, reve = %d, pred = %d, htm = %d, "
"htmspr = %d, htmcr = %d, mma = %d, quad = %d, pair = %d, "
"mmaint = %d, no32bit = %d, 32bit = %d, cpu = %d, ldstmask = %d, "
- "lxvrse = %d, lxvrze = %d, endian = %d, ibmdld = %d, ibm128 = %d.\n",
+ "lxvrse = %d, lxvrze = %d, endian = %d, ibmdld = %d, ibm128 = %d,",
+ "future = %d, dm = %d.\n",
attrptr->isinit, attrptr->isset, attrptr->isextract,
attrptr->isnosoft, attrptr->isldvec, attrptr->isstvec,
attrptr->isreve, attrptr->ispred, attrptr->ishtm, attrptr->ishtmspr,
@@ -1485,7 +1497,7 @@ parse_bif_attrs (attrinfo *attrptr)
attrptr->ismmaint, attrptr->isno32bit, attrptr->is32bit,
attrptr->iscpu, attrptr->isldstmask, attrptr->islxvrse,
attrptr->islxvrze, attrptr->isendian, attrptr->isibmld,
- attrptr->isibm128);
+ attrptr->isibm128, attrptr->isfuture, attrptr->isdm);
#endif
return PC_OK;
@@ -2257,7 +2269,10 @@ write_decls (void)
fprintf (header_file, " ENB_HTM,\n");
fprintf (header_file, " ENB_P10,\n");
fprintf (header_file, " ENB_P10_64,\n");
- fprintf (header_file, " ENB_MMA\n");
+ fprintf (header_file, " ENB_MMA,\n");
+ fprintf (header_file, " ENB_FUTURE,\n");
+ fprintf (header_file, " ENB_FUTURE_64,\n");
+ fprintf (header_file, " ENB_DM\n");
fprintf (header_file, "};\n\n");
fprintf (header_file, "#define PPC_MAXRESTROPNDS 3\n");
@@ -2301,6 +2316,8 @@ write_decls (void)
fprintf (header_file, "#define bif_endian_bit\t\t(0x00200000)\n");
fprintf (header_file, "#define bif_ibmld_bit\t\t(0x00400000)\n");
fprintf (header_file, "#define bif_ibm128_bit\t\t(0x00800000)\n");
+ fprintf (header_file, "#define bif_future_bit\t\t(0x01000000)\n");
+ fprintf (header_file, "#define bif_dm_bit\t\t(0x02000000)\n");
fprintf (header_file, "\n");
fprintf (header_file,
"#define bif_is_init(x)\t\t((x).bifattrs & bif_init_bit)\n");
@@ -2350,6 +2367,10 @@ write_decls (void)
"#define bif_is_ibmld(x)\t((x).bifattrs & bif_ibmld_bit)\n");
fprintf (header_file,
"#define bif_is_ibm128(x)\t((x).bifattrs & bif_ibm128_bit)\n");
+ fprintf (header_file,
+ "#define bif_is_future(x)\t((x).bifattrs & bif_future_bit)\n");
+ fprintf (header_file,
+ "#define bif_is_dm(x)\t((x).bifattrs & bif_dm_bit)\n");
fprintf (header_file, "\n");
fprintf (header_file,
@@ -2548,6 +2569,10 @@ write_bif_static_init (void)
fprintf (init_file, " | bif_ibmld_bit");
if (bifp->attrs.isibm128)
fprintf (init_file, " | bif_ibm128_bit");
+ if (bifp->attrs.isfuture)
+ fprintf (init_file, " | bif_future_bit");
+ if (bifp->attrs.isdm)
+ fprintf (init_file, " | bif_dm_bit");
fprintf (init_file, ",\n");
fprintf (init_file, " /* restr_opnd */\t{%d, %d, %d},\n",
bifp->proto.restr_opnd[0], bifp->proto.restr_opnd[1],
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 4a5007dc539..e9dfb138603 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -15499,6 +15499,66 @@
}
[(set_attr "type" "load")])
\f
+;; Signed saturation.
+
+;; The subfus instruction is defined as: SUBFUS RT,L,RA,RB. The extended
+;; mnemonic that we use (subdus and subwus) has the arguments RA and RB
+;; reversed (so it becomes a subtract instead of subtract from).
+
+(define_insn "sat_sub<mode>3"
+ [(set (match_operand:GPR 0 "gpc_reg_operand" "=r")
+ (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r")))]
+ "TARGET_FUTURE"
+ "sub<wd>us %0,%1,%2"
+ [(set_attr "type" "add")])
+
+(define_insn_and_split "*sat_sub<mode>3_dot"
+ [(set (match_operand:CC 3 "cc_reg_operand" "=x,?y")
+ (compare:CC (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r,r"))
+ (const_int 0)))
+ (clobber (match_scratch:GPR 0 "=r,r"))]
+ "TARGET_FUTURE"
+ "@
+ sub<wd>us. %0,%1,%2
+ #"
+ "&& reload_completed && cc_reg_not_cr0_operand (operands[3], CCmode)"
+ [(set (match_dup 0)
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 3)
+ (compare:CC (match_dup 0)
+ (const_int 0)))]
+ ""
+ [(set_attr "type" "add")
+ (set_attr "dot" "yes")
+ (set_attr "length" "4,8")])
+
+(define_insn_and_split "*sat_sub<mode>3_dot2"
+ [(set (match_operand:CC 3 "cc_reg_operand" "=x,?y")
+ (compare:CC (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r,r"))
+ (const_int 0)))
+ (set (match_operand:GPR 0 "gpc_reg_operand" "=r,r")
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))]
+ "TARGET_FUTURE"
+ "@
+ sub<wd>us. %0,%1,%2
+ #"
+ "&& reload_completed && cc_reg_not_cr0_operand (operands[3], CCmode)"
+ [(set (match_dup 0)
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 3)
+ (compare:CC (match_dup 0)
+ (const_int 0)))]
+ ""
+ [(set_attr "type" "add")
+ (set_attr "dot" "yes")
+ (set_attr "length" "4,8")])
+\f
(include "sync.md")
(include "vector.md")
diff --git a/gcc/testsuite/gcc.target/powerpc/subfus-1.c b/gcc/testsuite/gcc.target/powerpc/subfus-1.c
new file mode 100644
index 00000000000..68007e96cce
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/subfus-1.c
@@ -0,0 +1,32 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_subfus_ok } */
+/* { dg-options "-mdejagnu-cpu=future -O2" } */
+
+/* Test whether the saturating subtract built-in generates subwus for 32-bit
+ subtracts. */
+
+int do_sat_int (int a, int b)
+{
+ return __builtin_saturate_subtract32 (a, b); /* subwus */
+}
+
+int do_sat_int_dot (int a, int b, int *p)
+{
+ int r = __builtin_saturate_subtract32 (a, b); /* subwus. */
+ if (r == 0)
+ *p = 0;
+
+ return r;
+}
+
+void do_sat_int_dot2 (int a, int b, int *p, int *q)
+{
+ if (__builtin_saturate_subtract32 (a, b)) /* subwus. */
+ *p = 0;
+
+ *q = a + b;
+ return;
+}
+
+/* { dg-final { scan-assembler {\msubwus\M} } } */
+/* { dg-final { scan-assembler-not {\msubf\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/subfus-2.c b/gcc/testsuite/gcc.target/powerpc/subfus-2.c
new file mode 100644
index 00000000000..56e6d237900
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/subfus-2.c
@@ -0,0 +1,32 @@
+/* { dg-do compile { target lp64 } } */
+/* { dg-require-effective-target powerpc_subfus_ok } */
+/* { dg-options "-mdejagnu-cpu=future -O2" } */
+
+/* Test whether the saturating subtract built-in generates subwus for 64-bit
+ subtracts. */
+
+long do_sat_long (long a, long b)
+{
+ return __builtin_saturate_subtract64 (a, b); /* subwus */
+}
+
+long do_sat_long_dot (long a, long b, long *p)
+{
+ long r = __builtin_saturate_subtract64 (a, b); /* subwus. */
+ if (r == 0)
+ *p = 0;
+
+ return r;
+}
+
+void do_sat_long_dot2 (long a, long b, long *p, long *q)
+{
+ if (__builtin_saturate_subtract64 (a, b)) /* subwus. */
+ *p = 0;
+
+ *q = a + b;
+ return;
+}
+
+/* { dg-final { scan-assembler {\msubdus\M} } } */
+/* { dg-final { scan-assembler-not {\msubf\M} } } */
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index b70ebf963f9..8af840d1d3b 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -6553,6 +6553,22 @@ proc check_effective_target_powerpc_dense_math_ok { } {
} "-mcpu=future"]
}
+# Return 1 if this is a PowerPC target supporting -mcpu=future which enables
+# the saturating subtract instruction.
+proc check_effective_target_powerpc_subfus_ok { } {
+ return [check_no_compiler_messages_nocache powerpc_subfus_ok assembly {
+ int test (int a, int b)
+ {
+ #ifndef _ARCH_PWR_FUTURE
+ #error "target does not have saturating subtract support."
+ #else
+ /* Make sure we have saturating subtract support. */
+ return __builtin_saturate_subtract32 (a, b);
+ #endif
+ }
+ } "-mcpu=future"]
+}
+
# Return 1 if this is a PowerPC target supporting -mfloat128 via either
# software emulation on power7/power8 systems or hardware support on power9.
^ permalink raw reply [flat|nested] 4+ messages in thread
* [gcc(refs/users/meissner/heads/dmf004)] Add saturating subtract built-in.
@ 2022-11-11 23:15 Michael Meissner
0 siblings, 0 replies; 4+ messages in thread
From: Michael Meissner @ 2022-11-11 23:15 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:a0ba0af6b6612cf8f86c8abf30e1057cfa99803e
commit a0ba0af6b6612cf8f86c8abf30e1057cfa99803e
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Fri Nov 11 18:15:09 2022 -0500
Add saturating subtract built-in.
This patch adds support for a saturating subtract built-in function that may be
added to a future PowerPC processor. Note, if it is added, the name of the
built-in function may change before GCC 13 is released. If the name changes, we
will submit a patch changing the name.
I did add support for providing dense math built-in functions, even though at
present, we have not added any new built-in functions for dense math.
2022-11-11 Michael Meissner <meissner@linux.ibm.com>
gcc/
* config/rs6000/rs6000-builtin.cc (rs6000_invalid_builtin): Add support
for flagging invalid use of future built-in functions.
(rs6000_builtin_is_supported): Add support for future built-in
functions.
* config/rs6000/rs6000-builtins.def (__builtin_saturate_subtract32): New
built-in function for -mcpu=future.
(__builtin_saturate_subtract64): Likewise.
* config/rs6000/rs6000-gen-builtins.cc (enum bif_stanza): Add stanzas
for -mcpu=future built-ins.
(stanza_map): Likewise.
(enable_string): Likewise.
(struct attrinfo): Likewise.
(parse_bif_attrs): Likewise.
(write_decls): Likewise.
* config/rs6000/rs6000.md (sat_sub<mode>3): Add saturating subtract
built-in insn declarations.
(sat_sub<mode>3_dot): Likewise.
(sat_sub<mode>3_dot2): Likewise.
gcc/testsuite/
* gcc.target/powerpc/subfus-1.c: New test.
* gcc.target/powerpc/subfus-2.c: Likewise.
* lib/target-supports.exp (check_effective_target_powerpc_subfus_ok):
New effective target.
Diff:
---
gcc/config/rs6000/rs6000-builtin.cc | 17 ++++++++
gcc/config/rs6000/rs6000-builtins.def | 11 ++++++
gcc/config/rs6000/rs6000-gen-builtins.cc | 35 ++++++++++++++---
gcc/config/rs6000/rs6000.md | 60 +++++++++++++++++++++++++++++
gcc/testsuite/gcc.target/powerpc/subfus-1.c | 31 +++++++++++++++
gcc/testsuite/gcc.target/powerpc/subfus-2.c | 31 +++++++++++++++
gcc/testsuite/lib/target-supports.exp | 16 ++++++++
7 files changed, 196 insertions(+), 5 deletions(-)
diff --git a/gcc/config/rs6000/rs6000-builtin.cc b/gcc/config/rs6000/rs6000-builtin.cc
index f4eba184db8..1ac00e4b26c 100644
--- a/gcc/config/rs6000/rs6000-builtin.cc
+++ b/gcc/config/rs6000/rs6000-builtin.cc
@@ -139,6 +139,17 @@ rs6000_invalid_builtin (enum rs6000_gen_builtins fncode)
case ENB_MMA:
error ("%qs requires the %qs option", name, "-mmma");
break;
+ case ENB_FUTURE:
+ error ("%qs requires the %qs option", name, "-mcpu=future");
+ break;
+ case ENB_FUTURE_64:
+ error ("%qs requires the %qs option and either the %qs or %qs option",
+ name, "-mcpu=future", "-m64", "-mpowerpc64");
+ break;
+ case ENB_DM:
+ error ("%qs requires the %qs or %qs options", name, "-mcpu=future",
+ "-mdense-math");
+ break;
default:
case ENB_ALWAYS:
gcc_unreachable ();
@@ -194,6 +205,12 @@ rs6000_builtin_is_supported (enum rs6000_gen_builtins fncode)
return TARGET_HTM;
case ENB_MMA:
return TARGET_MMA;
+ case ENB_FUTURE:
+ return TARGET_FUTURE;
+ case ENB_FUTURE_64:
+ return TARGET_FUTURE && TARGET_POWERPC64;
+ case ENB_DM:
+ return TARGET_DENSE_MATH;
default:
gcc_unreachable ();
}
diff --git a/gcc/config/rs6000/rs6000-builtins.def b/gcc/config/rs6000/rs6000-builtins.def
index f76f54793d7..ee141c1d99e 100644
--- a/gcc/config/rs6000/rs6000-builtins.def
+++ b/gcc/config/rs6000/rs6000-builtins.def
@@ -139,6 +139,8 @@
; endian Needs special handling for endianness
; ibmld Restrict usage to the case when TFmode is IBM-128
; ibm128 Restrict usage to the case where __ibm128 is supported or if ibmld
+; future Restrict usage to future instructions
+; dm Restrict usage to dense math
;
; Each attribute corresponds to extra processing required when
; the built-in is expanded. All such special processing should
@@ -4108,3 +4110,12 @@
void __builtin_vsx_stxvp (v256, unsigned long, const v256 *);
STXVP nothing {mma,pair}
+
+[future]
+ const signed int __builtin_saturate_subtract32 (signed int, signed int);
+ SAT_SUBSI sat_subsi3 {}
+
+[future-64]
+ const signed long __builtin_saturate_subtract64 (signed long, signed long);
+ SAT_SUBDI sat_subdi3 {}
+
diff --git a/gcc/config/rs6000/rs6000-gen-builtins.cc b/gcc/config/rs6000/rs6000-gen-builtins.cc
index 0bd7a535e5f..f4020141243 100644
--- a/gcc/config/rs6000/rs6000-gen-builtins.cc
+++ b/gcc/config/rs6000/rs6000-gen-builtins.cc
@@ -233,6 +233,9 @@ enum bif_stanza
BSTZ_P10,
BSTZ_P10_64,
BSTZ_MMA,
+ BSTZ_FUTURE,
+ BSTZ_FUTURE_64,
+ BSTZ_DM,
NUMBIFSTANZAS
};
@@ -266,7 +269,10 @@ static stanza_entry stanza_map[NUMBIFSTANZAS] =
{ "htm", BSTZ_HTM },
{ "power10", BSTZ_P10 },
{ "power10-64", BSTZ_P10_64 },
- { "mma", BSTZ_MMA }
+ { "mma", BSTZ_MMA },
+ { "future", BSTZ_FUTURE },
+ { "future-64", BSTZ_FUTURE_64 },
+ { "dm", BSTZ_DM },
};
static const char *enable_string[NUMBIFSTANZAS] =
@@ -291,7 +297,10 @@ static const char *enable_string[NUMBIFSTANZAS] =
"ENB_HTM",
"ENB_P10",
"ENB_P10_64",
- "ENB_MMA"
+ "ENB_MMA",
+ "ENB_FUTURE",
+ "ENB_FUTURE_64",
+ "ENB_DM",
};
/* Function modifiers provide special handling for const, pure, and fpmath
@@ -395,6 +404,8 @@ struct attrinfo
bool isendian;
bool isibmld;
bool isibm128;
+ bool isfuture;
+ bool isdm;
};
/* Fields associated with a function prototype (bif or overload). */
@@ -1477,7 +1488,8 @@ parse_bif_attrs (attrinfo *attrptr)
"ldvec = %d, stvec = %d, reve = %d, pred = %d, htm = %d, "
"htmspr = %d, htmcr = %d, mma = %d, quad = %d, pair = %d, "
"mmaint = %d, no32bit = %d, 32bit = %d, cpu = %d, ldstmask = %d, "
- "lxvrse = %d, lxvrze = %d, endian = %d, ibmdld = %d, ibm128 = %d.\n",
+ "lxvrse = %d, lxvrze = %d, endian = %d, ibmdld = %d, ibm128 = %d,",
+ "future = %d, dm = %d.\n",
attrptr->isinit, attrptr->isset, attrptr->isextract,
attrptr->isnosoft, attrptr->isldvec, attrptr->isstvec,
attrptr->isreve, attrptr->ispred, attrptr->ishtm, attrptr->ishtmspr,
@@ -1485,7 +1497,7 @@ parse_bif_attrs (attrinfo *attrptr)
attrptr->ismmaint, attrptr->isno32bit, attrptr->is32bit,
attrptr->iscpu, attrptr->isldstmask, attrptr->islxvrse,
attrptr->islxvrze, attrptr->isendian, attrptr->isibmld,
- attrptr->isibm128);
+ attrptr->isibm128, attrptr->isfuture, attrptr->isdm);
#endif
return PC_OK;
@@ -2257,7 +2269,10 @@ write_decls (void)
fprintf (header_file, " ENB_HTM,\n");
fprintf (header_file, " ENB_P10,\n");
fprintf (header_file, " ENB_P10_64,\n");
- fprintf (header_file, " ENB_MMA\n");
+ fprintf (header_file, " ENB_MMA,\n");
+ fprintf (header_file, " ENB_FUTURE,\n");
+ fprintf (header_file, " ENB_FUTURE_64,\n");
+ fprintf (header_file, " ENB_DM\n");
fprintf (header_file, "};\n\n");
fprintf (header_file, "#define PPC_MAXRESTROPNDS 3\n");
@@ -2301,6 +2316,8 @@ write_decls (void)
fprintf (header_file, "#define bif_endian_bit\t\t(0x00200000)\n");
fprintf (header_file, "#define bif_ibmld_bit\t\t(0x00400000)\n");
fprintf (header_file, "#define bif_ibm128_bit\t\t(0x00800000)\n");
+ fprintf (header_file, "#define bif_future_bit\t\t(0x01000000)\n");
+ fprintf (header_file, "#define bif_dm_bit\t\t(0x02000000)\n");
fprintf (header_file, "\n");
fprintf (header_file,
"#define bif_is_init(x)\t\t((x).bifattrs & bif_init_bit)\n");
@@ -2350,6 +2367,10 @@ write_decls (void)
"#define bif_is_ibmld(x)\t((x).bifattrs & bif_ibmld_bit)\n");
fprintf (header_file,
"#define bif_is_ibm128(x)\t((x).bifattrs & bif_ibm128_bit)\n");
+ fprintf (header_file,
+ "#define bif_is_future(x)\t((x).bifattrs & bif_future_bit)\n");
+ fprintf (header_file,
+ "#define bif_is_dm(x)\t((x).bifattrs & bif_dm_bit)\n");
fprintf (header_file, "\n");
fprintf (header_file,
@@ -2548,6 +2569,10 @@ write_bif_static_init (void)
fprintf (init_file, " | bif_ibmld_bit");
if (bifp->attrs.isibm128)
fprintf (init_file, " | bif_ibm128_bit");
+ if (bifp->attrs.isfuture)
+ fprintf (init_file, " | bif_future_bit");
+ if (bifp->attrs.isdm)
+ fprintf (init_file, " | bif_dm_bit");
fprintf (init_file, ",\n");
fprintf (init_file, " /* restr_opnd */\t{%d, %d, %d},\n",
bifp->proto.restr_opnd[0], bifp->proto.restr_opnd[1],
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 4a5007dc539..e9dfb138603 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -15499,6 +15499,66 @@
}
[(set_attr "type" "load")])
\f
+;; Signed saturation.
+
+;; The subfus instruction is defined as: SUBFUS RT,L,RA,RB. The extended
+;; mnemonic that we use (subdus and subwus) has the arguments RA and RB
+;; reversed (so it becomes a subtract instead of subtract from).
+
+(define_insn "sat_sub<mode>3"
+ [(set (match_operand:GPR 0 "gpc_reg_operand" "=r")
+ (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r")))]
+ "TARGET_FUTURE"
+ "sub<wd>us %0,%1,%2"
+ [(set_attr "type" "add")])
+
+(define_insn_and_split "*sat_sub<mode>3_dot"
+ [(set (match_operand:CC 3 "cc_reg_operand" "=x,?y")
+ (compare:CC (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r,r"))
+ (const_int 0)))
+ (clobber (match_scratch:GPR 0 "=r,r"))]
+ "TARGET_FUTURE"
+ "@
+ sub<wd>us. %0,%1,%2
+ #"
+ "&& reload_completed && cc_reg_not_cr0_operand (operands[3], CCmode)"
+ [(set (match_dup 0)
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 3)
+ (compare:CC (match_dup 0)
+ (const_int 0)))]
+ ""
+ [(set_attr "type" "add")
+ (set_attr "dot" "yes")
+ (set_attr "length" "4,8")])
+
+(define_insn_and_split "*sat_sub<mode>3_dot2"
+ [(set (match_operand:CC 3 "cc_reg_operand" "=x,?y")
+ (compare:CC (ss_minus:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
+ (match_operand:GPR 2 "gpc_reg_operand" "r,r"))
+ (const_int 0)))
+ (set (match_operand:GPR 0 "gpc_reg_operand" "=r,r")
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))]
+ "TARGET_FUTURE"
+ "@
+ sub<wd>us. %0,%1,%2
+ #"
+ "&& reload_completed && cc_reg_not_cr0_operand (operands[3], CCmode)"
+ [(set (match_dup 0)
+ (ss_minus:GPR (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 3)
+ (compare:CC (match_dup 0)
+ (const_int 0)))]
+ ""
+ [(set_attr "type" "add")
+ (set_attr "dot" "yes")
+ (set_attr "length" "4,8")])
+\f
(include "sync.md")
(include "vector.md")
diff --git a/gcc/testsuite/gcc.target/powerpc/subfus-1.c b/gcc/testsuite/gcc.target/powerpc/subfus-1.c
new file mode 100644
index 00000000000..dd2cde47570
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/subfus-1.c
@@ -0,0 +1,31 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_subfus_ok } */
+/* { dg-options "-mdejagnu-cpu=future -O2" } */
+
+/* Test whether the saturating subtract built-in generates subwus for 32-bit
+ subtracts. */
+
+int do_sat_int (int a, int b)
+{
+ return __builtin_saturate_subtract32 (a, b); /* subwus */
+}
+
+int do_sat_int_dot (int a, int b, int *p)
+{
+ int r = __builtin_saturate_subtract32 (a, b); /* subwus. */
+ if (r == 0)
+ *p = 0;
+ return r;
+}
+
+void do_sat_int_dot2 (int a, int b, int *p, int *q)
+{
+ if (__builtin_saturate_subtract32 (a, b)) /* subwus. */
+ *p = 0;
+ *q = a + b;
+ return;
+}
+
+/* { dg-final { scan-assembler-times {\msubwus\M} 1 } } */
+/* { dg-final { scan-assembler-times {\msubwus[.]\M} 2 } } */
+/* { dg-final { scan-assembler-not {\msubf\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/subfus-2.c b/gcc/testsuite/gcc.target/powerpc/subfus-2.c
new file mode 100644
index 00000000000..c9511fe22cd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/subfus-2.c
@@ -0,0 +1,31 @@
+/* { dg-do compile { target lp64 } } */
+/* { dg-require-effective-target powerpc_subfus_ok } */
+/* { dg-options "-mdejagnu-cpu=future -O2" } */
+
+/* Test whether the saturating subtract built-in generates subwus for 64-bit
+ subtracts. */
+
+long do_sat_long (long a, long b)
+{
+ return __builtin_saturate_subtract64 (a, b); /* subwus */
+}
+
+long do_sat_long_dot (long a, long b, long *p)
+{
+ long r = __builtin_saturate_subtract64 (a, b); /* subwus. */
+ if (r == 0)
+ *p = 0;
+ return r;
+}
+
+void do_sat_long_dot2 (long a, long b, long *p, long *q)
+{
+ if (__builtin_saturate_subtract64 (a, b)) /* subwus. */
+ *p = 0;
+ *q = a + b;
+ return;
+}
+
+/* { dg-final { scan-assembler-times {\msubdus\M} 1 } } */
+/* { dg-final { scan-assembler-times {\msubdus[.]\M} 2 } } */
+/* { dg-final { scan-assembler-not {\msubf\M} } } */
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index b70ebf963f9..8af840d1d3b 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -6553,6 +6553,22 @@ proc check_effective_target_powerpc_dense_math_ok { } {
} "-mcpu=future"]
}
+# Return 1 if this is a PowerPC target supporting -mcpu=future which enables
+# the saturating subtract instruction.
+proc check_effective_target_powerpc_subfus_ok { } {
+ return [check_no_compiler_messages_nocache powerpc_subfus_ok assembly {
+ int test (int a, int b)
+ {
+ #ifndef _ARCH_PWR_FUTURE
+ #error "target does not have saturating subtract support."
+ #else
+ /* Make sure we have saturating subtract support. */
+ return __builtin_saturate_subtract32 (a, b);
+ #endif
+ }
+ } "-mcpu=future"]
+}
+
# Return 1 if this is a PowerPC target supporting -mfloat128 via either
# software emulation on power7/power8 systems or hardware support on power9.
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2022-11-17 21:53 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-11-17 21:53 [gcc(refs/users/meissner/heads/dmf004)] Add saturating subtract built-in Michael Meissner
-- strict thread matches above, loose matches on Subject: below --
2022-11-17 21:53 Michael Meissner
2022-11-12 0:46 Michael Meissner
2022-11-11 23:15 Michael Meissner
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).