[PATCH 6/8] aarch64: Add backend support for atomic fetch min/max operations
soumyaa@nvidia.com
soumyaa@nvidia.com
Tue Sep 2 08:59:57 GMT 2025
From: Soumya AR <soumyaa@nvidia.com>
This patch adds support for atomic min/max instructions offered by aarch64 under
LSE.
The implementation provides three execution paths:
1. When LSE is available at compile time (-march=armv8.1-a or later):
Emits LSE atomic min/max instructions (ldsmin, ldsmax, ldumin, ldumax).
2. When LSE availability is unknown at compile time:
Uses outline atomics - calls to libgcc functions that perform runtime
detection for LSE and dispatch to either LSE instructions or LL/SC sequences.
3. When outline atomics are explicitly disabled (-mno-outline-atomics) on
non-LSE targets: Emits inline LL/SC (LDXR, STXR etc) sequences
using conditional select instructions for min/max.
---
For op_fetch varaints, we first generate the appropriate fetch_op variant, then
use aarch64_split_atomic_op to generate the same operation (non-atomically) to
return the updated value. This function is extended to handle the min/max
operations. We have to be careful about QI/HI modes, as ldxr and its variants
do a zero extended load, so it's important to explicitly sign extend the values
before comparing them.
---
lse.S is responsible for emitting the appropriate LSE or non-LSE sequence. For
min/max on non-LSE systems, this is done using a conditional select.
There is, however, a unique case where systems with the CSSC extension have
native min/max instructions as well. In that case, it would be preferable to
emit the LL/SC sequence using the native min/max instructions. But, this would
only occur on targets with CSSC but without LSE, which is quite improbable, and
thus, I haven't added special handling for the CSSC feature.
---
We now overwrite our previous tests since CAS loops will no longer be emitted.
This is done to test for correctness in a consistent manner.
Bootstrapped and regression tested on aarch64-linux-gnu and x86_64-linux-gnu.
Cross-compiled and regression tested for arm-linux-gnueabihf-armv7-a and
aarch64-linux-gnu without LSE.
Signed-off-by: Soumya AR <soumyaa@nvidia.com>
gcc/ChangeLog:
* config/aarch64/aarch64-protos.h: Add declarations for new
outline atomic min/max name structures.
* config/aarch64/aarch64.cc (DEF4): Define names for outline
atomic min/max functions.
(aarch64_ool_ldsmin_names, aarch64_ool_ldsmax_names,
aarch64_ool_ldumin_names, aarch64_ool_ldumax_names): New.
(aarch64_split_atomic_op): Add support for SMIN, SMAX, UMIN,
UMAX operations with sign extension for QI/HI modes.
* config/aarch64/atomics.md: Add LSE and outline atomics
support for atomic fetch min/max operations.
* config/aarch64/iterators.md: Add min/max iterators.
libgcc/ChangeLog:
* config/aarch64/lse.S: Implement outline atomic min/max
functions.
* config/aarch64/t-lse: Add min/max function entries.
gcc/testsuite/ChangeLog:
* gcc.target/aarch64/atomic-minmax-lse.c: Modified for LSE min/max.
* gcc.target/aarch64/atomic-minmax-nolse.c: Modified to check for
non-LSE atomic min/max.
* gcc.target/aarch64/atomic-minmax.c: Modified to check for min/max
libcalls.
---
gcc/config/aarch64/aarch64-protos.h | 4 +
gcc/config/aarch64/aarch64.cc | 51 +++++++++
gcc/config/aarch64/atomics.md | 54 ++++++++-
gcc/config/aarch64/iterators.md | 30 +++--
.../gcc.target/aarch64/atomic-minmax-lse.c | 41 ++++---
.../gcc.target/aarch64/atomic-minmax-nolse.c | 103 ++++++++++--------
.../gcc.target/aarch64/atomic-minmax.c | 41 ++++---
libgcc/config/aarch64/lse.S | 62 ++++++++++-
libgcc/config/aarch64/t-lse | 3 +-
9 files changed, 292 insertions(+), 97 deletions(-)
diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
index 36bd88593ff..a152d76da0e 100644
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -1256,6 +1256,10 @@ extern const atomic_ool_names aarch64_ool_ldadd_names;
extern const atomic_ool_names aarch64_ool_ldset_names;
extern const atomic_ool_names aarch64_ool_ldclr_names;
extern const atomic_ool_names aarch64_ool_ldeor_names;
+extern const atomic_ool_names aarch64_ool_ldsmin_names;
+extern const atomic_ool_names aarch64_ool_ldsmax_names;
+extern const atomic_ool_names aarch64_ool_ldumin_names;
+extern const atomic_ool_names aarch64_ool_ldumax_names;
tree aarch64_resolve_overloaded_builtin_general (location_t, tree, void *);
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 2dbaf4a8e59..99872bf45fe 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -25745,6 +25745,10 @@ const atomic_ool_names aarch64_ool_ldadd_names = { { DEF4(ldadd) } };
const atomic_ool_names aarch64_ool_ldset_names = { { DEF4(ldset) } };
const atomic_ool_names aarch64_ool_ldclr_names = { { DEF4(ldclr) } };
const atomic_ool_names aarch64_ool_ldeor_names = { { DEF4(ldeor) } };
+const atomic_ool_names aarch64_ool_ldsmin_names = { { DEF4(ldsmin) } };
+const atomic_ool_names aarch64_ool_ldsmax_names = { { DEF4(ldsmax) } };
+const atomic_ool_names aarch64_ool_ldumin_names = { { DEF4(ldumin) } };
+const atomic_ool_names aarch64_ool_ldumax_names = { { DEF4(ldumax) } };
#undef DEF0
#undef DEF4
@@ -25997,6 +26001,53 @@ aarch64_split_atomic_op (enum rtx_code code, rtx old_out, rtx new_out, rtx mem,
emit_insn (gen_rtx_SET (new_out, x));
break;
+ case SMIN:
+ case SMAX:
+ case UMIN:
+ case UMAX:
+ {
+ rtx_code cmp_code;
+ switch (code)
+ {
+ case SMIN:
+ cmp_code = LT;
+ break;
+ case SMAX:
+ cmp_code = GT;
+ break;
+ case UMIN:
+ cmp_code = LTU;
+ break;
+ case UMAX:
+ cmp_code = GTU;
+ break;
+ default:
+ gcc_unreachable ();
+ }
+
+ if ((code == SMIN || code == SMAX) && (mode == QImode || mode == HImode))
+ {
+ rtx old_extended = gen_rtx_REG (wmode, REGNO (old_out));
+ emit_insn (
+ gen_rtx_SET (old_extended,
+ gen_rtx_SIGN_EXTEND (wmode,
+ gen_lowpart (mode, old_out))));
+ old_out = old_extended;
+
+ rtx value_extended = gen_rtx_REG (wmode, REGNO (value));
+ emit_insn (
+ gen_rtx_SET (value_extended,
+ gen_rtx_SIGN_EXTEND (wmode,
+ gen_lowpart (mode, value))));
+ value = value_extended;
+ }
+ rtx cc_reg = aarch64_gen_compare_reg (cmp_code, old_out, value);
+ rtx cond = gen_rtx_fmt_ee (cmp_code, VOIDmode, cc_reg, const0_rtx);
+ x = gen_rtx_IF_THEN_ELSE (wmode, cond, old_out, value);
+ emit_insn (gen_rtx_SET (new_out, x));
+ break;
+ }
+
case MINUS:
if (CONST_INT_P (value))
{
diff --git a/gcc/config/aarch64/atomics.md b/gcc/config/aarch64/atomics.md
index ea4a9367fc8..64b76f3df12 100644
--- a/gcc/config/aarch64/atomics.md
+++ b/gcc/config/aarch64/atomics.md
@@ -284,6 +284,18 @@
case XOR:
gen = gen_aarch64_atomic_xor<mode>_lse;
break;
+ case SMAX:
+ gen = gen_aarch64_atomic_smax<mode>_lse;
+ break;
+ case SMIN:
+ gen = gen_aarch64_atomic_smin<mode>_lse;
+ break;
+ case UMAX:
+ gen = gen_aarch64_atomic_umax<mode>_lse;
+ break;
+ case UMIN:
+ gen = gen_aarch64_atomic_umin<mode>_lse;
+ break;
case AND:
operands[1] = expand_simple_unop (<MODE>mode, NOT, operands[1],
NULL, 1);
@@ -317,6 +329,18 @@
NULL, 1);
names = &aarch64_ool_ldclr_names;
break;
+ case SMIN:
+ names = &aarch64_ool_ldsmin_names;
+ break;
+ case SMAX:
+ names = &aarch64_ool_ldsmax_names;
+ break;
+ case UMIN:
+ names = &aarch64_ool_ldumin_names;
+ break;
+ case UMAX:
+ names = &aarch64_ool_ldumax_names;
+ break;
default:
gcc_unreachable ();
}
@@ -442,6 +466,18 @@
case XOR:
gen = gen_aarch64_atomic_fetch_xor<mode>_lse;
break;
+ case SMAX:
+ gen = gen_aarch64_atomic_fetch_smax<mode>_lse;
+ break;
+ case SMIN:
+ gen = gen_aarch64_atomic_fetch_smin<mode>_lse;
+ break;
+ case UMAX:
+ gen = gen_aarch64_atomic_fetch_umax<mode>_lse;
+ break;
+ case UMIN:
+ gen = gen_aarch64_atomic_fetch_umin<mode>_lse;
+ break;
case AND:
operands[2] = expand_simple_unop (<MODE>mode, NOT, operands[2],
NULL, 1);
@@ -475,6 +511,18 @@
NULL, 1);
names = &aarch64_ool_ldclr_names;
break;
+ case SMIN:
+ names = &aarch64_ool_ldsmin_names;
+ break;
+ case SMAX:
+ names = &aarch64_ool_ldsmax_names;
+ break;
+ case UMIN:
+ names = &aarch64_ool_ldumin_names;
+ break;
+ case UMAX:
+ names = &aarch64_ool_ldumax_names;
+ break;
default:
gcc_unreachable ();
}
@@ -581,7 +629,11 @@
operands[2] = force_reg (<MODE>mode, operands[2]);
emit_insn (gen_atomic_fetch_<atomic_optab><mode>
(tmp, operands[1], operands[2], operands[3]));
- tmp = expand_simple_binop (<MODE>mode, <CODE>, tmp, operands[2],
+ if (<CODE> == SMIN || <CODE> == SMAX)
+ tmp = expand_simple_binop (<MODE>mode, <CODE>, tmp, operands[2],
+ operands[0], 0, OPTAB_WIDEN);
+ else
+ tmp = expand_simple_binop (<MODE>mode, <CODE>, tmp, operands[2],
operands[0], 1, OPTAB_WIDEN);
emit_move_insn (operands[0], tmp);
}
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index 8f8237edf6c..fdb15fb212a 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -1302,6 +1302,10 @@
UNSPECV_ATOMIC_LDOP_BIC ; Represent an atomic load-bic
UNSPECV_ATOMIC_LDOP_XOR ; Represent an atomic load-xor
UNSPECV_ATOMIC_LDOP_PLUS ; Represent an atomic load-add
+ UNSPECV_ATOMIC_LDOP_SMAX ; Represent an atomic load-smax
+ UNSPECV_ATOMIC_LDOP_SMIN ; Represent an atomic load-smin
+ UNSPECV_ATOMIC_LDOP_UMAX ; Represent an atomic load-umax
+ UNSPECV_ATOMIC_LDOP_UMIN ; Represent an atomic load-umin
])
;; -------------------------------------------------------------------
@@ -2782,7 +2786,7 @@
;; Iterator for __sync_<op> operations that where the operation can be
;; represented directly RTL. This is all of the sync operations bar
;; nand.
-(define_code_iterator atomic_op [plus minus ior xor and])
+(define_code_iterator atomic_op [plus minus ior xor and smin smax umin umax])
;; Iterator for integer conversions
(define_code_iterator FIXUORS [fix unsigned_fix])
@@ -3095,21 +3099,27 @@
;; Atomic operations
(define_code_attr atomic_optab
- [(ior "or") (xor "xor") (and "and") (plus "add") (minus "sub")])
+ [(ior "or") (xor "xor") (and "and") (plus "add") (minus "sub")
+ (smin "smin") (smax "smax") (umin "umin") (umax "umax")])
(define_code_attr atomic_op_operand
[(ior "aarch64_logical_operand")
(xor "aarch64_logical_operand")
(and "aarch64_logical_operand")
(plus "aarch64_plus_operand")
- (minus "aarch64_plus_operand")])
+ (minus "aarch64_plus_operand")
+ (smin "aarch64_sminmax_operand")
+ (smax "aarch64_sminmax_operand")
+ (umin "aarch64_uminmax_operand")
+ (umax "aarch64_uminmax_operand")])
;; Constants acceptable for atomic operations.
;; This definition must appear in this file before the iterators it refers to.
(define_code_attr const_atomic
[(plus "IJ") (minus "IJ")
(xor "<lconst_atomic>") (ior "<lconst_atomic>")
- (and "<lconst_atomic>")])
+ (and "<lconst_atomic>")
+ (smin "") (smax "") (umin "") (umax "")])
;; Attribute to describe constants acceptable in atomic logical operations
(define_mode_attr lconst_atomic [(QI "K") (HI "K") (SI "K") (DI "L")])
@@ -3948,7 +3958,9 @@
(define_int_iterator ATOMIC_LDOP
[UNSPECV_ATOMIC_LDOP_OR UNSPECV_ATOMIC_LDOP_BIC
- UNSPECV_ATOMIC_LDOP_XOR UNSPECV_ATOMIC_LDOP_PLUS])
+ UNSPECV_ATOMIC_LDOP_XOR UNSPECV_ATOMIC_LDOP_PLUS
+ UNSPECV_ATOMIC_LDOP_SMAX UNSPECV_ATOMIC_LDOP_SMIN
+ UNSPECV_ATOMIC_LDOP_UMAX UNSPECV_ATOMIC_LDOP_UMIN])
(define_int_iterator SUBDI_BITS [8 16 32])
@@ -4994,11 +5006,15 @@
(define_int_attr atomic_ldop
[(UNSPECV_ATOMIC_LDOP_OR "set") (UNSPECV_ATOMIC_LDOP_BIC "clr")
- (UNSPECV_ATOMIC_LDOP_XOR "eor") (UNSPECV_ATOMIC_LDOP_PLUS "add")])
+ (UNSPECV_ATOMIC_LDOP_XOR "eor") (UNSPECV_ATOMIC_LDOP_PLUS "add")
+ (UNSPECV_ATOMIC_LDOP_SMAX "smax") (UNSPECV_ATOMIC_LDOP_SMIN "smin")
+ (UNSPECV_ATOMIC_LDOP_UMAX "umax") (UNSPECV_ATOMIC_LDOP_UMIN "umin")])
(define_int_attr atomic_ldoptab
[(UNSPECV_ATOMIC_LDOP_OR "ior") (UNSPECV_ATOMIC_LDOP_BIC "bic")
- (UNSPECV_ATOMIC_LDOP_XOR "xor") (UNSPECV_ATOMIC_LDOP_PLUS "add")])
+ (UNSPECV_ATOMIC_LDOP_XOR "xor") (UNSPECV_ATOMIC_LDOP_PLUS "add")
+ (UNSPECV_ATOMIC_LDOP_SMAX "smax") (UNSPECV_ATOMIC_LDOP_SMIN "smin")
+ (UNSPECV_ATOMIC_LDOP_UMAX "umax") (UNSPECV_ATOMIC_LDOP_UMIN "umin")])
(define_int_attr fp8_cvt_uns_op
[(UNSPEC_F1CVT "f1cvt")
diff --git a/gcc/testsuite/gcc.target/aarch64/atomic-minmax-lse.c b/gcc/testsuite/gcc.target/aarch64/atomic-minmax-lse.c
index 19e078d0ee9..6d579f8360a 100644
--- a/gcc/testsuite/gcc.target/aarch64/atomic-minmax-lse.c
+++ b/gcc/testsuite/gcc.target/aarch64/atomic-minmax-lse.c
@@ -1,123 +1,122 @@
/* { dg-do compile } */
-/* { dg-require-effective-target aarch64_asm_lse_ok } */
/* { dg-options "-march=armv8-a+lse" } */
/* { dg-final { check-function-bodies "**" "" } } */
#include "atomic-minmax.x"
-/* { dg-final { scan-assembler-not "\tldxr*" } } */
-/* { dg-final { scan-assembler-not "\tldaxr*" } } */
-/* { dg-final { scan-assembler-not "\tstxr*" } } */
-/* { dg-final { scan-assembler-not "\tstlxr*" } } */
+/* { dg-final { scan-assembler-not "\tldxr" } } */
+/* { dg-final { scan-assembler-not "\tldaxr" } } */
+/* { dg-final { scan-assembler-not "\tstxr" } } */
+/* { dg-final { scan-assembler-not "\tstlxr" } } */
/*
** test_smin_s8:
** ...
-** casalb w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldsminb w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_smax_s8:
** ...
-** casalb w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldsmaxlb w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_smin_s16:
** ...
-** casalh w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldsminah w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_smax_s16:
** ...
-** casalh w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldsmaxalh w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_smin_s32:
** ...
-** casal w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldsmin w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_smax_s32:
** ...
-** casal w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldsmaxal w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_smin_s64:
** ...
-** casal x[0-9]+, x[0-9]+, \[x[0-9]+\]
+** ldsmina x[0-9]+, x[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_smax_s64:
** ...
-** casal x[0-9]+, x[0-9]+, \[x[0-9]+\]
+** ldsmax x[0-9]+, x[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_umin_u8:
** ...
-** casalb w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** lduminb w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_umax_u8:
** ...
-** casalb w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldumaxab w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_umin_u16:
** ...
-** casalh w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** lduminah w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_umax_u16:
** ...
-** casalh w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldumaxlh w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_umin_u32:
** ...
-** casal w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** lduminal w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_umax_u32:
** ...
-** casal w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldumax w[0-9]+, w[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_umin_u64:
** ...
-** casal x[0-9]+, x[0-9]+, \[x[0-9]+\]
+** ldumin x[0-9]+, x[0-9]+, \[x[0-9]+\]
** ...
*/
/*
** test_umax_u64:
** ...
-** casal x[0-9]+, x[0-9]+, \[x[0-9]+\]
+** ldumaxal x[0-9]+, x[0-9]+, \[x[0-9]+\]
** ...
*/
\ No newline at end of file
diff --git a/gcc/testsuite/gcc.target/aarch64/atomic-minmax-nolse.c b/gcc/testsuite/gcc.target/aarch64/atomic-minmax-nolse.c
index 74ec877adce..e4962974ea3 100644
--- a/gcc/testsuite/gcc.target/aarch64/atomic-minmax-nolse.c
+++ b/gcc/testsuite/gcc.target/aarch64/atomic-minmax-nolse.c
@@ -4,16 +4,22 @@
#include "atomic-minmax.x"
-/* { dg-final { scan-assembler-not "\tcas*" } } */
-/* { dg-final { scan-assembler-not "__aarch64_*" } } */
+/* { dg-final { scan-assembler-not "\tldsmin" } } */
+/* { dg-final { scan-assembler-not "\tldsmax" } } */
+/* { dg-final { scan-assembler-not "\tldumin" } } */
+/* { dg-final { scan-assembler-not "\tldumax" } } */
+
+/* { dg-final { scan-assembler-not "__aarch64_" } } */
/*
** test_smin_s8:
** ...
** ldxrb w[0-9]+, \[x[0-9]+\]
-** cmp w[0-9]+, w[0-9]+, uxtb
-** bne .*
-** stlxrb w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** sxtb w[0-9]+, w[0-9]+
+** sxtb w[0-9]+, w[0-9]+
+** cmp w[0-9]+, w[0-9]+
+** csel w[0-9]+, w[0-9]+, w[0-9]+, lt
+** stxrb w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
*/
@@ -22,8 +28,10 @@
** test_smax_s8:
** ...
** ldxrb w[0-9]+, \[x[0-9]+\]
-** cmp w[0-9]+, w[0-9]+, uxtb
-** bne .*
+** sxtb w[0-9]+, w[0-9]+
+** sxtb w[0-9]+, w[0-9]+
+** cmp w[0-9]+, w[0-9]+
+** csel w[0-9]+, w[0-9]+, w[0-9]+, gt
** stlxrb w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
@@ -32,10 +40,12 @@
/*
** test_smin_s16:
** ...
-** ldxrh w[0-9]+, \[x[0-9]+\]
-** cmp w[0-9]+, w[0-9]+, uxth
-** bne .*
-** stlxrh w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldaxrh w[0-9]+, \[x[0-9]+\]
+** sxth w[0-9]+, w[0-9]+
+** sxth w[0-9]+, w[0-9]+
+** cmp w[0-9]+, w[0-9]+
+** csel w[0-9]+, w[0-9]+, w[0-9]+, lt
+** stxrh w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
*/
@@ -43,20 +53,23 @@
/*
** test_smax_s16:
** ...
-** ldxrh w[0-9]+, \[x[0-9]+\]
-** cmp w[0-9]+, w[0-9]+, uxth
-** bne .*
+** ldaxrh w[0-9]+, \[x[0-9]+\]
+** sxth w[0-9]+, w[0-9]+
+** sxth w[0-9]+, w[0-9]+
+** cmp w[0-9]+, w[0-9]+
+** csel w[0-9]+, w[0-9]+, w[0-9]+, gt
** stlxrh w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
*/
+
/*
** test_smin_s32:
** ...
** ldxr w[0-9]+, \[x[0-9]+\]
** cmp w[0-9]+, w[0-9]+
-** bne .*
-** stlxr w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** csel w[0-9]+, w[0-9]+, w[0-9]+, lt
+** stxr w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
*/
@@ -64,9 +77,9 @@
/*
** test_smax_s32:
** ...
-** ldxr w[0-9]+, \[x[0-9]+\]
+** ldaxr w[0-9]+, \[x[0-9]+\]
** cmp w[0-9]+, w[0-9]+
-** bne .*
+** csel w[0-9]+, w[0-9]+, w[0-9]+, gt
** stlxr w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
@@ -75,21 +88,21 @@
/*
** test_smin_s64:
** ...
-** ldxr x[0-9]+, \[x[0-9]+\]
+** ldaxr x[0-9]+, \[x[0-9]+\]
** cmp x[0-9]+, x[0-9]+
-** bne .*
-** stlxr w[0-9]+, x[0-9]+, \[x[0-9]+\]
+** csel x[0-9]+, x[0-9]+, x[0-9]+, lt
+** stxr w[0-9]+, x[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
*/
/*
-** test_smin_s64:
+** test_smax_s64:
** ...
** ldxr x[0-9]+, \[x[0-9]+\]
** cmp x[0-9]+, x[0-9]+
-** bne .*
-** stlxr w[0-9]+, x[0-9]+, \[x[0-9]+\]
+** csel x[0-9]+, x[0-9]+, x[0-9]+, gt
+** stxr w[0-9]+, x[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
*/
@@ -98,9 +111,9 @@
** test_umin_u8:
** ...
** ldxrb w[0-9]+, \[x[0-9]+\]
-** cmp w[0-9]+, w[0-9]+, uxtb
-** bne .*
-** stlxrb w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** cmp w[0-9]+, w[0-9]+
+** csel w[0-9]+, w[0-9]+, w[0-9]+, cc
+** stxrb w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
*/
@@ -108,10 +121,10 @@
/*
** test_umax_u8:
** ...
-** ldxrb w[0-9]+, \[x[0-9]+\]
-** cmp w[0-9]+, w[0-9]+, uxtb
-** bne .*
-** stlxrb w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldaxrb w[0-9]+, \[x[0-9]+\]
+** cmp w[0-9]+, w[0-9]+
+** csel w[0-9]+, w[0-9]+, w[0-9]+, hi
+** stxrb w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
*/
@@ -119,10 +132,10 @@
/*
** test_umin_u16:
** ...
-** ldxrh w[0-9]+, \[x[0-9]+\]
-** cmp w[0-9]+, w[0-9]+, uxth
-** bne .*
-** stlxrh w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** ldaxrh w[0-9]+, \[x[0-9]+\]
+** cmp w[0-9]+, w[0-9]+
+** csel w[0-9]+, w[0-9]+, w[0-9]+, cc
+** stxrh w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
*/
@@ -131,8 +144,8 @@
** test_umax_u16:
** ...
** ldxrh w[0-9]+, \[x[0-9]+\]
-** cmp w[0-9]+, w[0-9]+, uxth
-** bne .*
+** cmp w[0-9]+, w[0-9]+
+** csel w[0-9]+, w[0-9]+, w[0-9]+, hi
** stlxrh w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
@@ -141,9 +154,9 @@
/*
** test_umin_u32:
** ...
-** ldxr w[0-9]+, \[x[0-9]+\]
+** ldaxr w[0-9]+, \[x[0-9]+\]
** cmp w[0-9]+, w[0-9]+
-** bne .*
+** csel w[0-9]+, w[0-9]+, w[0-9]+, cc
** stlxr w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
@@ -154,8 +167,8 @@
** ...
** ldxr w[0-9]+, \[x[0-9]+\]
** cmp w[0-9]+, w[0-9]+
-** bne .*
-** stlxr w[0-9]+, w[0-9]+, \[x[0-9]+\]
+** csel w[0-9]+, w[0-9]+, w[0-9]+, hi
+** stxr w[0-9]+, w[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
*/
@@ -165,8 +178,8 @@
** ...
** ldxr x[0-9]+, \[x[0-9]+\]
** cmp x[0-9]+, x[0-9]+
-** bne .*
-** stlxr w[0-9]+, x[0-9]+, \[x[0-9]+\]
+** csel x[0-9]+, x[0-9]+, x[0-9]+, cc
+** stxr w[0-9]+, x[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
*/
@@ -174,9 +187,9 @@
/*
** test_umax_u64:
** ...
-** ldxr x[0-9]+, \[x[0-9]+\]
+** ldaxr x[0-9]+, \[x[0-9]+\]
** cmp x[0-9]+, x[0-9]+
-** bne .*
+** csel x[0-9]+, x[0-9]+, x[0-9]+, hi
** stlxr w[0-9]+, x[0-9]+, \[x[0-9]+\]
** cbnz w[0-9]+, .*
** ...
diff --git a/gcc/testsuite/gcc.target/aarch64/atomic-minmax.c b/gcc/testsuite/gcc.target/aarch64/atomic-minmax.c
index f61082e288b..225816b63bd 100644
--- a/gcc/testsuite/gcc.target/aarch64/atomic-minmax.c
+++ b/gcc/testsuite/gcc.target/aarch64/atomic-minmax.c
@@ -10,120 +10,119 @@ int main ()
return 0;
}
-/* { dg-final { scan-assembler-not "\tcas*" } } */
-/* { dg-final { scan-assembler-not "\tldxr*" } } */
-/* { dg-final { scan-assembler-not "\tldaxr*" } } */
-/* { dg-final { scan-assembler-not "\tstxr*" } } */
-/* { dg-final { scan-assembler-not "\tstlxr*" } } */
+/* { dg-final { scan-assembler-not "\tldsmin" } } */
+/* { dg-final { scan-assembler-not "\tldsmax" } } */
+/* { dg-final { scan-assembler-not "\tldumin" } } */
+/* { dg-final { scan-assembler-not "\tldumax" } } */
/*
** test_smin_s8:
** ...
-** bl __aarch64_cas1_sync
+** bl __aarch64_ldsmin1_relax
** ...
*/
/*
** test_smax_s8:
** ...
-** bl __aarch64_cas1_sync
+** bl __aarch64_ldsmax1_rel
** ...
*/
/*
** test_smin_s16:
** ...
-** bl __aarch64_cas2_sync
+** bl __aarch64_ldsmin2_acq
** ...
*/
/*
** test_smax_s16:
** ...
-** bl __aarch64_cas2_sync
+** bl __aarch64_ldsmax2_acq_rel
** ...
*/
/*
** test_smin_s32:
** ...
-** bl __aarch64_cas4_sync
+** bl __aarch64_ldsmin4_relax
** ...
*/
/*
** test_smax_s32:
** ...
-** bl __aarch64_cas4_sync
+** bl __aarch64_ldsmax4_acq_rel
** ...
*/
/*
** test_smin_s64:
** ...
-** bl __aarch64_cas8_sync
+** bl __aarch64_ldsmin8_acq
** ...
*/
/*
** test_smax_s64:
** ...
-** bl __aarch64_cas8_sync
+** bl __aarch64_ldsmax8_relax
** ...
*/
/*
** test_umin_u8:
** ...
-** bl __aarch64_cas1_sync
+** bl __aarch64_ldumin1_relax
** ...
*/
/*
** test_umax_u8:
** ...
-** bl __aarch64_cas1_sync
+** bl __aarch64_ldumax1_acq
** ...
*/
/*
** test_umin_u16:
** ...
-** bl __aarch64_cas2_sync
+** bl __aarch64_ldumin2_acq
** ...
*/
/*
** test_umax_u16:
** ...
-** bl __aarch64_cas2_sync
+** bl __aarch64_ldumax2_rel
** ...
*/
/*
** test_umin_u32:
** ...
-** bl __aarch64_cas4_sync
+** bl __aarch64_ldumin4_acq_rel
** ...
*/
/*
** test_umax_u32:
** ...
-** bl __aarch64_cas4_sync
+** bl __aarch64_ldumax4_relax
** ...
*/
/*
** test_umin_u64:
** ...
-** bl __aarch64_cas8_sync
+** bl __aarch64_ldumin8_relax
** ...
*/
/*
** test_umax_u64:
** ...
-** bl __aarch64_cas8_sync
+** bl __aarch64_ldumax8_acq_rel
** ...
*/
diff --git a/libgcc/config/aarch64/lse.S b/libgcc/config/aarch64/lse.S
index cb24011d883..c251d5d0188 100644
--- a/libgcc/config/aarch64/lse.S
+++ b/libgcc/config/aarch64/lse.S
@@ -276,7 +276,9 @@ ENDFN NAME(swp)
#endif
#if defined(L_ldadd) || defined(L_ldclr) \
- || defined(L_ldeor) || defined(L_ldset)
+ || defined(L_ldeor) || defined(L_ldset) \
+ || defined(L_ldsmin) || defined(L_ldsmax) \
+ || defined(L_ldumin) || defined(L_ldumax)
#ifdef L_ldadd
#define LDNM ldadd
@@ -294,6 +296,26 @@ ENDFN NAME(swp)
#define LDNM ldset
#define OP orr
#define OPN 0x3000
+#elif defined(L_ldsmin)
+#define LDNM ldsmin
+#define OP smin
+#define OPN 0x5000
+#define IS_MINMAX 1
+#elif defined(L_ldsmax)
+#define LDNM ldsmax
+#define OP smax
+#define OPN 0x4000
+#define IS_MINMAX 1
+#elif defined(L_ldumin)
+#define LDNM ldumin
+#define OP umin
+#define OPN 0x7000
+#define IS_MINMAX 1
+#elif defined(L_ldumax)
+#define LDNM ldumax
+#define OP umax
+#define OPN 0x6000
+#define IS_MINMAX 1
#else
#error
#endif
@@ -311,7 +333,45 @@ STARTFN NAME(LDNM)
8: mov s(tmp0), s(0)
0: LDXR s(0), [x1]
+#ifdef IS_MINMAX
+ /* For min/max, extend if needed, compare, and select. */
+#if SIZE < 4
+ #if defined(L_ldsmin) || defined(L_ldsmax)
+ /* Sign extend for signed comparisons. */
+ #if SIZE == 1
+ sxtb w(tmp1), w(0)
+ sxtb w(tmp3), w(tmp0)
+ #else /* SIZE == 2 */
+ sxth w(tmp1), w(0)
+ sxth w(tmp3), w(tmp0)
+ #endif
+ #else /* L_ldumin || L_ldumax */
+ /* Zero extend for unsigned comparisons. */
+ #if SIZE == 1
+ uxtb w(tmp1), w(0)
+ uxtb w(tmp3), w(tmp0)
+ #else /* SIZE == 2 */
+ uxth w(tmp1), w(0)
+ uxth w(tmp3), w(tmp0)
+ #endif
+ #endif
+ cmp w(tmp3), w(tmp1)
+#else /* SIZE >= 4 */
+ cmp s(tmp0), s(0)
+#endif
+ /* Select based on condition. */
+ #if defined(L_ldsmin)
+ csel s(tmp1), s(tmp0), s(0), lt
+ #elif defined(L_ldsmax)
+ csel s(tmp1), s(tmp0), s(0), gt
+ #elif defined(L_ldumin)
+ csel s(tmp1), s(tmp0), s(0), lo
+ #elif defined(L_ldumax)
+ csel s(tmp1), s(tmp0), s(0), hi
+ #endif
+#else /* Not IS_MINMAX */
OP s(tmp1), s(0), s(tmp0)
+#endif /* IS_MINMAX */
STXR w(tmp2), s(tmp1), [x1]
cbnz w(tmp2), 0b
BARRIER
diff --git a/libgcc/config/aarch64/t-lse b/libgcc/config/aarch64/t-lse
index 58908dcabfb..cc0544cf0c8 100644
--- a/libgcc/config/aarch64/t-lse
+++ b/libgcc/config/aarch64/t-lse
@@ -23,7 +23,8 @@ S0 := $(foreach s, 1 2 4 8 16, $(addsuffix _$(s), cas))
O0 := $(foreach m, 1 2 3 4 5, $(addsuffix _$(m)$(objext), $(S0)))
# Swap, Load-and-operate have 4 sizes and 5 memory models
-S1 := $(foreach s, 1 2 4 8, $(addsuffix _$(s), swp ldadd ldclr ldeor ldset))
+S1 := $(foreach s, 1 2 4 8, $(addsuffix _$(s), swp ldadd ldclr ldeor ldset \
+ ldsmin ldsmax ldumin ldumax))
O1 := $(foreach m, 1 2 3 4 5, $(addsuffix _$(m)$(objext), $(S1)))
LSE_OBJS := $(O0) $(O1)
--
2.44.0
More information about the Libstdc++
mailing list