packages/gcc
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
gcc/0033-LoongArch-Implement-atomic-operations-using-LoongArc.patch
Peng Fan f653243538 LoongArch: Sync to upstream 
Signed-off-by: Peng Fan <fanpeng@loongson.cn>
2024-11-12 08:44:01 +08:00

363 lines
13 KiB
Diff
Raw Blame History

From 704e67084fcd7f3ea89321e17dfafa7e907c907c Mon Sep 17 00:00:00 2001
From: Lulu Cheng <chenglulu@loongson.cn>
Date: Fri, 17 Nov 2023 15:42:53 +0800
Subject: [PATCH 033/188] LoongArch: Implement atomic operations using
LoongArch1.1 instructions.
1. short and char type calls for atomic_add_fetch and __atomic_fetch_add are
implemented using amadd{_db}.{b/h}.
2. Use amcas{_db}.{b/h/w/d} to implement __atomic_compare_exchange_n and __atomic_compare_exchange.
3. The short and char types of the functions __atomic_exchange and __atomic_exchange_n are
implemented using amswap{_db}.{b/h}.
gcc/ChangeLog:
* config/loongarch/loongarch-def.h: Add comments.
* config/loongarch/loongarch-opts.h (ISA_BASE_IS_LA64V110): Define macro.
* config/loongarch/loongarch.cc (loongarch_memmodel_needs_rel_acq_fence):
Remove redundant code implementations.
* config/loongarch/sync.md (d): Added QI, HI support.
(atomic_add<mode>): New template.
(atomic_exchange<mode>_short): Likewise.
(atomic_cas_value_strong<mode>_amcas): Likewise..
(atomic_fetch_add<mode>_short): Likewise.
---
gcc/config/loongarch/loongarch-def.h | 2 +
gcc/config/loongarch/loongarch-opts.h | 2 +-
gcc/config/loongarch/loongarch.cc | 6 +-
gcc/config/loongarch/sync.md | 186 ++++++++++++++++++++------
4 files changed, 147 insertions(+), 49 deletions(-)
diff --git a/gcc/config/loongarch/loongarch-def.h b/gcc/config/loongarch/loongarch-def.h
index 4757de14b..078d8607d 100644
--- a/gcc/config/loongarch/loongarch-def.h
+++ b/gcc/config/loongarch/loongarch-def.h
@@ -54,7 +54,9 @@ extern "C" {
/* enum isa_base */
extern const char* loongarch_isa_base_strings[];
+/* LoongArch V1.00. */
#define ISA_BASE_LA64V100 0
+/* LoongArch V1.10. */
#define ISA_BASE_LA64V110 1
#define N_ISA_BASE_TYPES 2
diff --git a/gcc/config/loongarch/loongarch-opts.h b/gcc/config/loongarch/loongarch-opts.h
index 22ce1a122..9b3d023ac 100644
--- a/gcc/config/loongarch/loongarch-opts.h
+++ b/gcc/config/loongarch/loongarch-opts.h
@@ -86,10 +86,10 @@ loongarch_update_gcc_opt_status (struct loongarch_target *target,
|| la_target.isa.simd == ISA_EXT_SIMD_LASX)
#define ISA_HAS_LASX (la_target.isa.simd == ISA_EXT_SIMD_LASX)
-
/* TARGET_ macros for use in *.md template conditionals */
#define TARGET_uARCH_LA464 (la_target.cpu_tune == CPU_LA464)
#define TARGET_uARCH_LA664 (la_target.cpu_tune == CPU_LA664)
+#define ISA_BASE_IS_LA64V110 (la_target.isa.base == ISA_BASE_LA64V110)
/* Note: optimize_size may vary across functions,
while -m[no]-memcpy imposes a global constraint. */
diff --git a/gcc/config/loongarch/loongarch.cc b/gcc/config/loongarch/loongarch.cc
index 43f0e82ba..7bb46a45d 100644
--- a/gcc/config/loongarch/loongarch.cc
+++ b/gcc/config/loongarch/loongarch.cc
@@ -5813,16 +5813,12 @@ loongarch_print_operand_punct_valid_p (unsigned char code)
static bool
loongarch_memmodel_needs_rel_acq_fence (enum memmodel model)
{
- switch (model)
+ switch (memmodel_base (model))
{
case MEMMODEL_ACQ_REL:
case MEMMODEL_SEQ_CST:
- case MEMMODEL_SYNC_SEQ_CST:
case MEMMODEL_RELEASE:
- case MEMMODEL_SYNC_RELEASE:
case MEMMODEL_ACQUIRE:
- case MEMMODEL_CONSUME:
- case MEMMODEL_SYNC_ACQUIRE:
return true;
case MEMMODEL_RELAXED:
diff --git a/gcc/config/loongarch/sync.md b/gcc/config/loongarch/sync.md
index dd1f98946..1eabaec04 100644
--- a/gcc/config/loongarch/sync.md
+++ b/gcc/config/loongarch/sync.md
@@ -38,7 +38,7 @@
[(plus "add") (ior "or") (xor "xor") (and "and")])
;; This attribute gives the format suffix for atomic memory operations.
-(define_mode_attr amo [(SI "w") (DI "d")])
+(define_mode_attr amo [(QI "b") (HI "h") (SI "w") (DI "d")])
;; <amop> expands to the name of the atomic operand that implements a
;; particular code.
@@ -123,7 +123,18 @@
UNSPEC_SYNC_OLD_OP))]
""
"am<amop>%A2.<amo>\t$zero,%z1,%0"
- [(set (attr "length") (const_int 8))])
+ [(set (attr "length") (const_int 4))])
+
+(define_insn "atomic_add<mode>"
+ [(set (match_operand:SHORT 0 "memory_operand" "+ZB")
+ (unspec_volatile:SHORT
+ [(plus:SHORT (match_dup 0)
+ (match_operand:SHORT 1 "reg_or_0_operand" "rJ"))
+ (match_operand:SI 2 "const_int_operand")] ;; model
+ UNSPEC_SYNC_OLD_OP))]
+ "ISA_BASE_IS_LA64V110"
+ "amadd%A2.<amo>\t$zero,%z1,%0"
+ [(set (attr "length") (const_int 4))])
(define_insn "atomic_fetch_<atomic_optab><mode>"
[(set (match_operand:GPR 0 "register_operand" "=&r")
@@ -131,12 +142,12 @@
(set (match_dup 1)
(unspec_volatile:GPR
[(any_atomic:GPR (match_dup 1)
- (match_operand:GPR 2 "reg_or_0_operand" "rJ"))
+ (match_operand:GPR 2 "reg_or_0_operand" "rJ"))
(match_operand:SI 3 "const_int_operand")] ;; model
UNSPEC_SYNC_OLD_OP))]
""
"am<amop>%A3.<amo>\t%0,%z2,%1"
- [(set (attr "length") (const_int 8))])
+ [(set (attr "length") (const_int 4))])
(define_insn "atomic_exchange<mode>"
[(set (match_operand:GPR 0 "register_operand" "=&r")
@@ -148,7 +159,19 @@
(match_operand:GPR 2 "register_operand" "r"))]
""
"amswap%A3.<amo>\t%0,%z2,%1"
- [(set (attr "length") (const_int 8))])
+ [(set (attr "length") (const_int 4))])
+
+(define_insn "atomic_exchange<mode>_short"
+ [(set (match_operand:SHORT 0 "register_operand" "=&r")
+ (unspec_volatile:SHORT
+ [(match_operand:SHORT 1 "memory_operand" "+ZB")
+ (match_operand:SI 3 "const_int_operand")] ;; model
+ UNSPEC_SYNC_EXCHANGE))
+ (set (match_dup 1)
+ (match_operand:SHORT 2 "register_operand" "r"))]
+ "ISA_BASE_IS_LA64V110"
+ "amswap%A3.<amo>\t%0,%z2,%1"
+ [(set (attr "length") (const_int 4))])
(define_insn "atomic_cas_value_strong<mode>"
[(set (match_operand:GPR 0 "register_operand" "=&r")
@@ -156,25 +179,36 @@
(set (match_dup 1)
(unspec_volatile:GPR [(match_operand:GPR 2 "reg_or_0_operand" "rJ")
(match_operand:GPR 3 "reg_or_0_operand" "rJ")
- (match_operand:SI 4 "const_int_operand") ;; mod_s
- (match_operand:SI 5 "const_int_operand")] ;; mod_f
+ (match_operand:SI 4 "const_int_operand")] ;; mod_s
UNSPEC_COMPARE_AND_SWAP))
- (clobber (match_scratch:GPR 6 "=&r"))]
+ (clobber (match_scratch:GPR 5 "=&r"))]
""
{
return "1:\\n\\t"
"ll.<amo>\\t%0,%1\\n\\t"
"bne\\t%0,%z2,2f\\n\\t"
- "or%i3\\t%6,$zero,%3\\n\\t"
- "sc.<amo>\\t%6,%1\\n\\t"
- "beqz\\t%6,1b\\n\\t"
+ "or%i3\\t%5,$zero,%3\\n\\t"
+ "sc.<amo>\\t%5,%1\\n\\t"
+ "beqz\\t%5,1b\\n\\t"
"b\\t3f\\n\\t"
"2:\\n\\t"
- "%G5\\n\\t"
+ "%G4\\n\\t"
"3:\\n\\t";
}
[(set (attr "length") (const_int 28))])
+(define_insn "atomic_cas_value_strong<mode>_amcas"
+ [(set (match_operand:QHWD 0 "register_operand" "=&r")
+ (match_operand:QHWD 1 "memory_operand" "+ZB"))
+ (set (match_dup 1)
+ (unspec_volatile:QHWD [(match_operand:QHWD 2 "reg_or_0_operand" "rJ")
+ (match_operand:QHWD 3 "reg_or_0_operand" "rJ")
+ (match_operand:SI 4 "const_int_operand")] ;; mod_s
+ UNSPEC_COMPARE_AND_SWAP))]
+ "ISA_BASE_IS_LA64V110"
+ "ori\t%0,%z2,0\n\tamcas%A4.<amo>\t%0,%z3,%1"
+ [(set (attr "length") (const_int 8))])
+
(define_expand "atomic_compare_and_swap<mode>"
[(match_operand:SI 0 "register_operand" "") ;; bool output
(match_operand:GPR 1 "register_operand" "") ;; val output
@@ -186,9 +220,29 @@
(match_operand:SI 7 "const_int_operand" "")] ;; mod_f
""
{
- emit_insn (gen_atomic_cas_value_strong<mode> (operands[1], operands[2],
- operands[3], operands[4],
- operands[6], operands[7]));
+ rtx mod_s, mod_f;
+
+ mod_s = operands[6];
+ mod_f = operands[7];
+
+ /* Normally the succ memory model must be stronger than fail, but in the
+ unlikely event of fail being ACQUIRE and succ being RELEASE we need to
+ promote succ to ACQ_REL so that we don't lose the acquire semantics. */
+
+ if (is_mm_acquire (memmodel_base (INTVAL (mod_f)))
+ && is_mm_release (memmodel_base (INTVAL (mod_s))))
+ mod_s = GEN_INT (MEMMODEL_ACQ_REL);
+
+ operands[6] = mod_s;
+
+ if (ISA_BASE_IS_LA64V110)
+ emit_insn (gen_atomic_cas_value_strong<mode>_amcas (operands[1], operands[2],
+ operands[3], operands[4],
+ operands[6]));
+ else
+ emit_insn (gen_atomic_cas_value_strong<mode> (operands[1], operands[2],
+ operands[3], operands[4],
+ operands[6]));
rtx compare = operands[1];
if (operands[3] != const0_rtx)
@@ -292,31 +346,53 @@
(match_operand:SI 7 "const_int_operand" "")] ;; mod_f
""
{
- union loongarch_gen_fn_ptrs generator;
- generator.fn_7 = gen_atomic_cas_value_cmp_and_7_si;
- loongarch_expand_atomic_qihi (generator, operands[1], operands[2],
- operands[3], operands[4], operands[7]);
+ rtx mod_s, mod_f;
- rtx compare = operands[1];
- if (operands[3] != const0_rtx)
- {
- machine_mode mode = GET_MODE (operands[3]);
- rtx op1 = convert_modes (SImode, mode, operands[1], true);
- rtx op3 = convert_modes (SImode, mode, operands[3], true);
- rtx difference = gen_rtx_MINUS (SImode, op1, op3);
- compare = gen_reg_rtx (SImode);
- emit_insn (gen_rtx_SET (compare, difference));
- }
+ mod_s = operands[6];
+ mod_f = operands[7];
- if (word_mode != <MODE>mode)
+ /* Normally the succ memory model must be stronger than fail, but in the
+ unlikely event of fail being ACQUIRE and succ being RELEASE we need to
+ promote succ to ACQ_REL so that we don't lose the acquire semantics. */
+
+ if (is_mm_acquire (memmodel_base (INTVAL (mod_f)))
+ && is_mm_release (memmodel_base (INTVAL (mod_s))))
+ mod_s = GEN_INT (MEMMODEL_ACQ_REL);
+
+ operands[6] = mod_s;
+
+ if (ISA_BASE_IS_LA64V110)
+ emit_insn (gen_atomic_cas_value_strong<mode>_amcas (operands[1], operands[2],
+ operands[3], operands[4],
+ operands[6]));
+ else
{
- rtx reg = gen_reg_rtx (word_mode);
- emit_insn (gen_rtx_SET (reg, gen_rtx_SIGN_EXTEND (word_mode, compare)));
- compare = reg;
+ union loongarch_gen_fn_ptrs generator;
+ generator.fn_7 = gen_atomic_cas_value_cmp_and_7_si;
+ loongarch_expand_atomic_qihi (generator, operands[1], operands[2],
+ operands[3], operands[4], operands[6]);
}
- emit_insn (gen_rtx_SET (operands[0],
- gen_rtx_EQ (SImode, compare, const0_rtx)));
+ rtx compare = operands[1];
+ if (operands[3] != const0_rtx)
+ {
+ machine_mode mode = GET_MODE (operands[3]);
+ rtx op1 = convert_modes (SImode, mode, operands[1], true);
+ rtx op3 = convert_modes (SImode, mode, operands[3], true);
+ rtx difference = gen_rtx_MINUS (SImode, op1, op3);
+ compare = gen_reg_rtx (SImode);
+ emit_insn (gen_rtx_SET (compare, difference));
+ }
+
+ if (word_mode != <MODE>mode)
+ {
+ rtx reg = gen_reg_rtx (word_mode);
+ emit_insn (gen_rtx_SET (reg, gen_rtx_SIGN_EXTEND (word_mode, compare)));
+ compare = reg;
+ }
+
+ emit_insn (gen_rtx_SET (operands[0],
+ gen_rtx_EQ (SImode, compare, const0_rtx)));
DONE;
})
@@ -505,13 +581,31 @@
(match_operand:SHORT 2 "register_operand"))]
""
{
- union loongarch_gen_fn_ptrs generator;
- generator.fn_7 = gen_atomic_cas_value_exchange_7_si;
- loongarch_expand_atomic_qihi (generator, operands[0], operands[1],
- const0_rtx, operands[2], operands[3]);
+ if (ISA_BASE_IS_LA64V110)
+ emit_insn (gen_atomic_exchange<mode>_short (operands[0], operands[1], operands[2], operands[3]));
+ else
+ {
+ union loongarch_gen_fn_ptrs generator;
+ generator.fn_7 = gen_atomic_cas_value_exchange_7_si;
+ loongarch_expand_atomic_qihi (generator, operands[0], operands[1],
+ const0_rtx, operands[2], operands[3]);
+ }
DONE;
})
+(define_insn "atomic_fetch_add<mode>_short"
+ [(set (match_operand:SHORT 0 "register_operand" "=&r")
+ (match_operand:SHORT 1 "memory_operand" "+ZB"))
+ (set (match_dup 1)
+ (unspec_volatile:SHORT
+ [(plus:SHORT (match_dup 1)
+ (match_operand:SHORT 2 "reg_or_0_operand" "rJ"))
+ (match_operand:SI 3 "const_int_operand")] ;; model
+ UNSPEC_SYNC_OLD_OP))]
+ "ISA_BASE_IS_LA64V110"
+ "amadd%A3.<amo>\t%0,%z2,%1"
+ [(set (attr "length") (const_int 4))])
+
(define_expand "atomic_fetch_add<mode>"
[(set (match_operand:SHORT 0 "register_operand" "=&r")
(match_operand:SHORT 1 "memory_operand" "+ZB"))
@@ -523,10 +617,16 @@
UNSPEC_SYNC_OLD_OP))]
""
{
- union loongarch_gen_fn_ptrs generator;
- generator.fn_7 = gen_atomic_cas_value_add_7_si;
- loongarch_expand_atomic_qihi (generator, operands[0], operands[1],
- operands[1], operands[2], operands[3]);
+ if (ISA_BASE_IS_LA64V110)
+ emit_insn (gen_atomic_fetch_add<mode>_short (operands[0], operands[1],
+ operands[2], operands[3]));
+ else
+ {
+ union loongarch_gen_fn_ptrs generator;
+ generator.fn_7 = gen_atomic_cas_value_add_7_si;
+ loongarch_expand_atomic_qihi (generator, operands[0], operands[1],
+ operands[1], operands[2], operands[3]);
+ }
DONE;
})
--
2.43.0
Reference in New Issue View Git Blame Copy Permalink