RISC-V has no support for subword atomic operations; code currently generates libatomic library calls.
This patch changes the default behavior to inline subword atomic calls (using the same logic as the existing library call). Behavior can be specified using the -minline-atomics and -mno-inline-atomics command line flags. gcc/libgcc/config/riscv/atomic.c has the same logic implemented in asm. This will need to stay for backwards compatibility and the -mno-inline-atomics flag. 2022-02-15 Patrick O'Neill <patr...@rivosinc.com> PR target/104338 * riscv.opt: Add command-line flag. * invoke.texi: Add blurb regarding command-line flag. * sync.md (atomic_fetch_<atomic_optab><mode>): logic for expanding subword atomic operations. * sync.md (subword_atomic_fetch_strong_<atomic_optab>): LR/SC block for performing atomic operation * atomic.c: Add reference to duplicate logic. * inline-atomics-1.c: New test. * inline-atomics-2.c: Likewise. * inline-atomics-3.c: Likewise. * inline-atomics-4.c: Likewise. * inline-atomics-5.c: Likewise. * inline-atomics-6.c: Likewise. * inline-atomics-7.c: Likewise. * inline-atomics-8.c: Likewise. * inline-atomics-9.c: Likewise. Signed-off-by: Patrick O'Neill <patr...@rivosinc.com> --- There may be further concerns about the memory consistency of these operations, but this patch focuses on simply moving the logic inline. Those concerns can be addressed in a future patch. --- v2 Changelog: - Add texti blurb - Update target flag - add 'UNSPEC_SYNC_OLD_OP_SUBWORD' for subword ops --- gcc/config/riscv/riscv.opt | 4 + gcc/config/riscv/sync.md | 98 +++ gcc/doc/invoke.texi | 7 + .../gcc.target/riscv/inline-atomics-1.c | 11 + .../gcc.target/riscv/inline-atomics-2.c | 12 + .../gcc.target/riscv/inline-atomics-3.c | 569 ++++++++++++++++++ .../gcc.target/riscv/inline-atomics-4.c | 566 +++++++++++++++++ .../gcc.target/riscv/inline-atomics-5.c | 13 + .../gcc.target/riscv/inline-atomics-6.c | 12 + .../gcc.target/riscv/inline-atomics-7.c | 12 + .../gcc.target/riscv/inline-atomics-8.c | 17 + .../gcc.target/riscv/inline-atomics-9.c | 17 + libgcc/config/riscv/atomic.c | 2 + 13 files changed, 1340 insertions(+) create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-1.c create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-2.c create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-3.c create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-4.c create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-5.c create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-6.c create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-7.c create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-8.c create mode 100644 gcc/testsuite/gcc.target/riscv/inline-atomics-9.c diff --git a/gcc/config/riscv/riscv.opt b/gcc/config/riscv/riscv.opt index 9fffc08220d..8378e41aa85 100644 --- a/gcc/config/riscv/riscv.opt +++ b/gcc/config/riscv/riscv.opt @@ -225,3 +225,7 @@ Enum(isa_spec_class) String(20191213) Value(ISA_SPEC_CLASS_20191213) misa-spec= Target RejectNegative Joined Enum(isa_spec_class) Var(riscv_isa_spec) Init(TARGET_DEFAULT_ISA_SPEC) Set the version of RISC-V ISA spec. + +minline-atomics +Target Mask(INLINE_SUBWORD_ATOMIC) +Always inline subword atomic operations. diff --git a/gcc/config/riscv/sync.md b/gcc/config/riscv/sync.md index 86b41e6b00a..05cbdfd5db3 100644 --- a/gcc/config/riscv/sync.md +++ b/gcc/config/riscv/sync.md @@ -22,6 +22,7 @@ (define_c_enum "unspec" [ UNSPEC_COMPARE_AND_SWAP UNSPEC_SYNC_OLD_OP + UNSPEC_SYNC_OLD_OP_SUBWORD UNSPEC_SYNC_EXCHANGE UNSPEC_ATOMIC_STORE UNSPEC_MEMORY_BARRIER @@ -92,6 +93,103 @@ "%F3amo<insn>.<amo>%A3 %0,%z2,%1" [(set (attr "length") (const_int 8))]) +(define_expand "atomic_fetch_<atomic_optab><mode>" + [(set (match_operand:SHORT 0 "register_operand" "=&r") ;; old value at mem + (match_operand:SHORT 1 "memory_operand" "+A")) ;; mem location + (set (match_dup 1) + (unspec_volatile:SHORT + [(any_atomic:SHORT (match_dup 1) + (match_operand:SHORT 2 "reg_or_0_operand" "rJ")) ;; value for op + (match_operand:SI 3 "const_int_operand")] ;; model + UNSPEC_SYNC_OLD_OP_SUBWORD))] + "TARGET_ATOMIC && TARGET_INLINE_SUBWORD_ATOMIC" +{ + /* We have no QImode/HImode atomics, so form a mask, then use + subword_atomic_fetch_strong_<mode> to implement a LR/SC version of the + operation. */ + + /* Logic duplicated in gcc/libgcc/config/riscv/atomic.c for use when inlining + is disabled */ + + rtx old = gen_reg_rtx (SImode); + rtx mem = operands[1]; + rtx value = operands[2]; + rtx mask = gen_reg_rtx (SImode); + rtx notmask = gen_reg_rtx (SImode); + + rtx addr = force_reg (Pmode, XEXP (mem, 0)); + + rtx aligned_addr = gen_reg_rtx (Pmode); + emit_move_insn (aligned_addr, gen_rtx_AND (Pmode, addr, + gen_int_mode (-4, Pmode))); + + rtx aligned_mem = change_address (mem, SImode, aligned_addr); + + rtx shift = gen_reg_rtx (SImode); + emit_move_insn (shift, gen_rtx_AND (SImode, gen_lowpart (SImode, addr), + gen_int_mode (3, SImode))); + emit_move_insn (shift, gen_rtx_ASHIFT (SImode, shift, + gen_int_mode(3, SImode))); + + rtx value_reg = gen_reg_rtx (SImode); + emit_move_insn (value_reg, simplify_gen_subreg (SImode, value, <MODE>mode, 0)); + + rtx shifted_value = gen_reg_rtx (SImode); + emit_move_insn(shifted_value, gen_rtx_ASHIFT(SImode, value_reg, + gen_lowpart (QImode, shift))); + + int unshifted_mask; + if (<MODE>mode == QImode) + unshifted_mask = 0xFF; + else + unshifted_mask = 0xFFFF; + + rtx mask_reg = gen_reg_rtx (SImode); + emit_move_insn (mask_reg, gen_int_mode(unshifted_mask, SImode)); + + emit_move_insn (mask, gen_rtx_ASHIFT(SImode, mask_reg, + gen_lowpart (QImode, shift))); + + emit_move_insn (notmask, gen_rtx_NOT(SImode, mask)); + + emit_insn (gen_subword_atomic_fetch_strong_<atomic_optab> (old, aligned_mem, + shifted_value, + mask, notmask)); + + emit_move_insn (old, gen_rtx_ASHIFTRT(SImode, old, + gen_lowpart(QImode, shift))); + + emit_move_insn (operands[0], gen_lowpart(<MODE>mode, old)); + + DONE; +}) + +(define_insn "subword_atomic_fetch_strong_<atomic_optab>" + [(set (match_operand:SI 0 "register_operand" "=&r") ;; old value at mem + (match_operand:SI 1 "memory_operand" "+A")) ;; mem location + (set (match_dup 1) + (unspec_volatile:SI + [(any_atomic:SI (match_dup 1) + (match_operand:SI 2 "register_operand" "rI")) ;; value for op + (match_operand:SI 3 "register_operand" "rI")] ;; mask + UNSPEC_SYNC_OLD_OP_SUBWORD)) + (match_operand:SI 4 "register_operand" "rI") ;; not_mask + (clobber (match_scratch:SI 5 "=&r")) ;; tmp_1 + (clobber (match_scratch:SI 6 "=&r"))] ;; tmp_2 + "TARGET_ATOMIC && TARGET_INLINE_SUBWORD_ATOMIC" + { + return + "1:\;" + "lr.w.aq\t%0, %1\;" + "<insn>\t%5, %0, %2\;" + "and\t%5, %5, %3\;" + "and\t%6, %0, %4\;" + "or\t%6, %6, %5\;" + "sc.w.rl\t%5, %6, %1\;" + "bnez\t%5, 1b"; + } + [(set (attr "length") (const_int 28))]) + (define_insn "atomic_exchange<mode>" [(set (match_operand:GPR 0 "register_operand" "=&r") (unspec_volatile:GPR diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi index e1a00c80307..1007110aafb 100644 --- a/gcc/doc/invoke.texi +++ b/gcc/doc/invoke.texi @@ -1200,6 +1200,7 @@ See RS/6000 and PowerPC Options. -mbig-endian -mlittle-endian @gol -mstack-protector-guard=@var{guard} -mstack-protector-guard-reg=@var{reg} @gol -mstack-protector-guard-offset=@var{offset}} +-minline-atomics -mno-inline-atomics @gol @emph{RL78 Options} @gccoptlist{-msim -mmul=none -mmul=g13 -mmul=g14 -mallregs @gol @@ -27712,6 +27713,12 @@ Do or don't use smaller but slower prologue and epilogue code that uses library function calls. The default is to use fast inline prologues and epilogues. +@item -minline-atomics +@itemx -mno-inline-atomics +@opindex minline-atomics +Do or don't use smaller but slower subword atomic emulation code that uses +library function calls. The default is to use fast inline subword atomics. + @item -mshorten-memrefs @itemx -mno-shorten-memrefs @opindex mshorten-memrefs diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-1.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-1.c new file mode 100644 index 00000000000..110fdabd313 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-1.c @@ -0,0 +1,11 @@ +/* { dg-do compile } */ +/* { dg-options "-mno-inline-atomics" } */ +/* { dg-final { scan-assembler "\tcall\t__sync_fetch_and_add_1" } } */ + +char bar; + +int +main () +{ + __sync_fetch_and_add(&bar, 1); +} diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-2.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-2.c new file mode 100644 index 00000000000..8d5c31d8b79 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-2.c @@ -0,0 +1,12 @@ +/* { dg-do compile } */ +/* Verify that subword atomics do not generate calls. */ +/* { dg-options "-minline-atomics" } */ +/* { dg-final { scan-assembler-not "\tcall\t__sync_fetch_and_add_1" } } */ + +char bar; + +int +main () +{ + __sync_fetch_and_add(&bar, 1); +} diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-3.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-3.c new file mode 100644 index 00000000000..19b382d45b0 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-3.c @@ -0,0 +1,569 @@ +/* Check all char alignments. */ +/* Duplicate logic as libatomic/testsuite/libatomic.c/atomic-op-1.c */ +/* Test __atomic routines for existence and proper execution on 1 byte + values with each valid memory model. */ +/* { dg-do run } */ +/* { dg-options "-latomic -minline-atomics -Wno-address-of-packed-member" } */ + +/* Test the execution of the __atomic_*OP builtin routines for a char. */ + +extern void abort(void); + +char count, res; +const char init = ~0; + +struct A +{ + char a; + char b; + char c; + char d; +} __attribute__ ((packed)) A; + +/* The fetch_op routines return the original value before the operation. */ + +void +test_fetch_add (char* v) +{ + *v = 0; + count = 1; + + if (__atomic_fetch_add (v, count, __ATOMIC_RELAXED) != 0) + abort (); + + if (__atomic_fetch_add (v, 1, __ATOMIC_CONSUME) != 1) + abort (); + + if (__atomic_fetch_add (v, count, __ATOMIC_ACQUIRE) != 2) + abort (); + + if (__atomic_fetch_add (v, 1, __ATOMIC_RELEASE) != 3) + abort (); + + if (__atomic_fetch_add (v, count, __ATOMIC_ACQ_REL) != 4) + abort (); + + if (__atomic_fetch_add (v, 1, __ATOMIC_SEQ_CST) != 5) + abort (); +} + + +void +test_fetch_sub (char* v) +{ + *v = res = 20; + count = 0; + + if (__atomic_fetch_sub (v, count + 1, __ATOMIC_RELAXED) != res--) + abort (); + + if (__atomic_fetch_sub (v, 1, __ATOMIC_CONSUME) != res--) + abort (); + + if (__atomic_fetch_sub (v, count + 1, __ATOMIC_ACQUIRE) != res--) + abort (); + + if (__atomic_fetch_sub (v, 1, __ATOMIC_RELEASE) != res--) + abort (); + + if (__atomic_fetch_sub (v, count + 1, __ATOMIC_ACQ_REL) != res--) + abort (); + + if (__atomic_fetch_sub (v, 1, __ATOMIC_SEQ_CST) != res--) + abort (); +} + +void +test_fetch_and (char* v) +{ + *v = init; + + if (__atomic_fetch_and (v, 0, __ATOMIC_RELAXED) != init) + abort (); + + if (__atomic_fetch_and (v, init, __ATOMIC_CONSUME) != 0) + abort (); + + if (__atomic_fetch_and (v, 0, __ATOMIC_ACQUIRE) != 0) + abort (); + + *v = ~*v; + if (__atomic_fetch_and (v, init, __ATOMIC_RELEASE) != init) + abort (); + + if (__atomic_fetch_and (v, 0, __ATOMIC_ACQ_REL) != init) + abort (); + + if (__atomic_fetch_and (v, 0, __ATOMIC_SEQ_CST) != 0) + abort (); +} + +void +test_fetch_nand (char* v) +{ + *v = init; + + if (__atomic_fetch_nand (v, 0, __ATOMIC_RELAXED) != init) + abort (); + + if (__atomic_fetch_nand (v, init, __ATOMIC_CONSUME) != init) + abort (); + + if (__atomic_fetch_nand (v, 0, __ATOMIC_ACQUIRE) != 0 ) + abort (); + + if (__atomic_fetch_nand (v, init, __ATOMIC_RELEASE) != init) + abort (); + + if (__atomic_fetch_nand (v, init, __ATOMIC_ACQ_REL) != 0) + abort (); + + if (__atomic_fetch_nand (v, 0, __ATOMIC_SEQ_CST) != init) + abort (); +} + +void +test_fetch_xor (char* v) +{ + *v = init; + count = 0; + + if (__atomic_fetch_xor (v, count, __ATOMIC_RELAXED) != init) + abort (); + + if (__atomic_fetch_xor (v, ~count, __ATOMIC_CONSUME) != init) + abort (); + + if (__atomic_fetch_xor (v, 0, __ATOMIC_ACQUIRE) != 0) + abort (); + + if (__atomic_fetch_xor (v, ~count, __ATOMIC_RELEASE) != 0) + abort (); + + if (__atomic_fetch_xor (v, 0, __ATOMIC_ACQ_REL) != init) + abort (); + + if (__atomic_fetch_xor (v, ~count, __ATOMIC_SEQ_CST) != init) + abort (); +} + +void +test_fetch_or (char* v) +{ + *v = 0; + count = 1; + + if (__atomic_fetch_or (v, count, __ATOMIC_RELAXED) != 0) + abort (); + + count *= 2; + if (__atomic_fetch_or (v, 2, __ATOMIC_CONSUME) != 1) + abort (); + + count *= 2; + if (__atomic_fetch_or (v, count, __ATOMIC_ACQUIRE) != 3) + abort (); + + count *= 2; + if (__atomic_fetch_or (v, 8, __ATOMIC_RELEASE) != 7) + abort (); + + count *= 2; + if (__atomic_fetch_or (v, count, __ATOMIC_ACQ_REL) != 15) + abort (); + + count *= 2; + if (__atomic_fetch_or (v, count, __ATOMIC_SEQ_CST) != 31) + abort (); +} + +/* The OP_fetch routines return the new value after the operation. */ + +void +test_add_fetch (char* v) +{ + *v = 0; + count = 1; + + if (__atomic_add_fetch (v, count, __ATOMIC_RELAXED) != 1) + abort (); + + if (__atomic_add_fetch (v, 1, __ATOMIC_CONSUME) != 2) + abort (); + + if (__atomic_add_fetch (v, count, __ATOMIC_ACQUIRE) != 3) + abort (); + + if (__atomic_add_fetch (v, 1, __ATOMIC_RELEASE) != 4) + abort (); + + if (__atomic_add_fetch (v, count, __ATOMIC_ACQ_REL) != 5) + abort (); + + if (__atomic_add_fetch (v, count, __ATOMIC_SEQ_CST) != 6) + abort (); +} + + +void +test_sub_fetch (char* v) +{ + *v = res = 20; + count = 0; + + if (__atomic_sub_fetch (v, count + 1, __ATOMIC_RELAXED) != --res) + abort (); + + if (__atomic_sub_fetch (v, 1, __ATOMIC_CONSUME) != --res) + abort (); + + if (__atomic_sub_fetch (v, count + 1, __ATOMIC_ACQUIRE) != --res) + abort (); + + if (__atomic_sub_fetch (v, 1, __ATOMIC_RELEASE) != --res) + abort (); + + if (__atomic_sub_fetch (v, count + 1, __ATOMIC_ACQ_REL) != --res) + abort (); + + if (__atomic_sub_fetch (v, count + 1, __ATOMIC_SEQ_CST) != --res) + abort (); +} + +void +test_and_fetch (char* v) +{ + *v = init; + + if (__atomic_and_fetch (v, 0, __ATOMIC_RELAXED) != 0) + abort (); + + *v = init; + if (__atomic_and_fetch (v, init, __ATOMIC_CONSUME) != init) + abort (); + + if (__atomic_and_fetch (v, 0, __ATOMIC_ACQUIRE) != 0) + abort (); + + *v = ~*v; + if (__atomic_and_fetch (v, init, __ATOMIC_RELEASE) != init) + abort (); + + if (__atomic_and_fetch (v, 0, __ATOMIC_ACQ_REL) != 0) + abort (); + + *v = ~*v; + if (__atomic_and_fetch (v, 0, __ATOMIC_SEQ_CST) != 0) + abort (); +} + +void +test_nand_fetch (char* v) +{ + *v = init; + + if (__atomic_nand_fetch (v, 0, __ATOMIC_RELAXED) != init) + abort (); + + if (__atomic_nand_fetch (v, init, __ATOMIC_CONSUME) != 0) + abort (); + + if (__atomic_nand_fetch (v, 0, __ATOMIC_ACQUIRE) != init) + abort (); + + if (__atomic_nand_fetch (v, init, __ATOMIC_RELEASE) != 0) + abort (); + + if (__atomic_nand_fetch (v, init, __ATOMIC_ACQ_REL) != init) + abort (); + + if (__atomic_nand_fetch (v, 0, __ATOMIC_SEQ_CST) != init) + abort (); +} + + + +void +test_xor_fetch (char* v) +{ + *v = init; + count = 0; + + if (__atomic_xor_fetch (v, count, __ATOMIC_RELAXED) != init) + abort (); + + if (__atomic_xor_fetch (v, ~count, __ATOMIC_CONSUME) != 0) + abort (); + + if (__atomic_xor_fetch (v, 0, __ATOMIC_ACQUIRE) != 0) + abort (); + + if (__atomic_xor_fetch (v, ~count, __ATOMIC_RELEASE) != init) + abort (); + + if (__atomic_xor_fetch (v, 0, __ATOMIC_ACQ_REL) != init) + abort (); + + if (__atomic_xor_fetch (v, ~count, __ATOMIC_SEQ_CST) != 0) + abort (); +} + +void +test_or_fetch (char* v) +{ + *v = 0; + count = 1; + + if (__atomic_or_fetch (v, count, __ATOMIC_RELAXED) != 1) + abort (); + + count *= 2; + if (__atomic_or_fetch (v, 2, __ATOMIC_CONSUME) != 3) + abort (); + + count *= 2; + if (__atomic_or_fetch (v, count, __ATOMIC_ACQUIRE) != 7) + abort (); + + count *= 2; + if (__atomic_or_fetch (v, 8, __ATOMIC_RELEASE) != 15) + abort (); + + count *= 2; + if (__atomic_or_fetch (v, count, __ATOMIC_ACQ_REL) != 31) + abort (); + + count *= 2; + if (__atomic_or_fetch (v, count, __ATOMIC_SEQ_CST) != 63) + abort (); +} + + +/* Test the OP routines with a result which isn't used. Use both variations + within each function. */ + +void +test_add (char* v) +{ + *v = 0; + count = 1; + + __atomic_add_fetch (v, count, __ATOMIC_RELAXED); + if (*v != 1) + abort (); + + __atomic_fetch_add (v, count, __ATOMIC_CONSUME); + if (*v != 2) + abort (); + + __atomic_add_fetch (v, 1 , __ATOMIC_ACQUIRE); + if (*v != 3) + abort (); + + __atomic_fetch_add (v, 1, __ATOMIC_RELEASE); + if (*v != 4) + abort (); + + __atomic_add_fetch (v, count, __ATOMIC_ACQ_REL); + if (*v != 5) + abort (); + + __atomic_fetch_add (v, count, __ATOMIC_SEQ_CST); + if (*v != 6) + abort (); +} + + +void +test_sub (char* v) +{ + *v = res = 20; + count = 0; + + __atomic_sub_fetch (v, count + 1, __ATOMIC_RELAXED); + if (*v != --res) + abort (); + + __atomic_fetch_sub (v, count + 1, __ATOMIC_CONSUME); + if (*v != --res) + abort (); + + __atomic_sub_fetch (v, 1, __ATOMIC_ACQUIRE); + if (*v != --res) + abort (); + + __atomic_fetch_sub (v, 1, __ATOMIC_RELEASE); + if (*v != --res) + abort (); + + __atomic_sub_fetch (v, count + 1, __ATOMIC_ACQ_REL); + if (*v != --res) + abort (); + + __atomic_fetch_sub (v, count + 1, __ATOMIC_SEQ_CST); + if (*v != --res) + abort (); +} + +void +test_and (char* v) +{ + *v = init; + + __atomic_and_fetch (v, 0, __ATOMIC_RELAXED); + if (*v != 0) + abort (); + + *v = init; + __atomic_fetch_and (v, init, __ATOMIC_CONSUME); + if (*v != init) + abort (); + + __atomic_and_fetch (v, 0, __ATOMIC_ACQUIRE); + if (*v != 0) + abort (); + + *v = ~*v; + __atomic_fetch_and (v, init, __ATOMIC_RELEASE); + if (*v != init) + abort (); + + __atomic_and_fetch (v, 0, __ATOMIC_ACQ_REL); + if (*v != 0) + abort (); + + *v = ~*v; + __atomic_fetch_and (v, 0, __ATOMIC_SEQ_CST); + if (*v != 0) + abort (); +} + +void +test_nand (char* v) +{ + *v = init; + + __atomic_fetch_nand (v, 0, __ATOMIC_RELAXED); + if (*v != init) + abort (); + + __atomic_fetch_nand (v, init, __ATOMIC_CONSUME); + if (*v != 0) + abort (); + + __atomic_nand_fetch (v, 0, __ATOMIC_ACQUIRE); + if (*v != init) + abort (); + + __atomic_nand_fetch (v, init, __ATOMIC_RELEASE); + if (*v != 0) + abort (); + + __atomic_fetch_nand (v, init, __ATOMIC_ACQ_REL); + if (*v != init) + abort (); + + __atomic_nand_fetch (v, 0, __ATOMIC_SEQ_CST); + if (*v != init) + abort (); +} + + + +void +test_xor (char* v) +{ + *v = init; + count = 0; + + __atomic_xor_fetch (v, count, __ATOMIC_RELAXED); + if (*v != init) + abort (); + + __atomic_fetch_xor (v, ~count, __ATOMIC_CONSUME); + if (*v != 0) + abort (); + + __atomic_xor_fetch (v, 0, __ATOMIC_ACQUIRE); + if (*v != 0) + abort (); + + __atomic_fetch_xor (v, ~count, __ATOMIC_RELEASE); + if (*v != init) + abort (); + + __atomic_fetch_xor (v, 0, __ATOMIC_ACQ_REL); + if (*v != init) + abort (); + + __atomic_xor_fetch (v, ~count, __ATOMIC_SEQ_CST); + if (*v != 0) + abort (); +} + +void +test_or (char* v) +{ + *v = 0; + count = 1; + + __atomic_or_fetch (v, count, __ATOMIC_RELAXED); + if (*v != 1) + abort (); + + count *= 2; + __atomic_fetch_or (v, count, __ATOMIC_CONSUME); + if (*v != 3) + abort (); + + count *= 2; + __atomic_or_fetch (v, 4, __ATOMIC_ACQUIRE); + if (*v != 7) + abort (); + + count *= 2; + __atomic_fetch_or (v, 8, __ATOMIC_RELEASE); + if (*v != 15) + abort (); + + count *= 2; + __atomic_or_fetch (v, count, __ATOMIC_ACQ_REL); + if (*v != 31) + abort (); + + count *= 2; + __atomic_fetch_or (v, count, __ATOMIC_SEQ_CST); + if (*v != 63) + abort (); +} + +int +main () +{ + char* V[] = {&A.a, &A.b, &A.c, &A.d}; + + for (int i = 0; i < 4; i++) { + test_fetch_add (V[i]); + test_fetch_sub (V[i]); + test_fetch_and (V[i]); + test_fetch_nand (V[i]); + test_fetch_xor (V[i]); + test_fetch_or (V[i]); + + test_add_fetch (V[i]); + test_sub_fetch (V[i]); + test_and_fetch (V[i]); + test_nand_fetch (V[i]); + test_xor_fetch (V[i]); + test_or_fetch (V[i]); + + test_add (V[i]); + test_sub (V[i]); + test_and (V[i]); + test_nand (V[i]); + test_xor (V[i]); + test_or (V[i]); + } + + return 0; +} diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-4.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-4.c new file mode 100644 index 00000000000..619cf1f86ca --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-4.c @@ -0,0 +1,566 @@ +/* Check all short alignments. */ +/* Duplicate logic as libatomic/testsuite/libatomic.c/atomic-op-2.c */ +/* Test __atomic routines for existence and proper execution on 2 byte + values with each valid memory model. */ +/* { dg-do run } */ +/* { dg-options "-latomic -minline-atomics -Wno-address-of-packed-member" } */ + +/* Test the execution of the __atomic_*OP builtin routines for a short. */ + +extern void abort(void); + +short count, res; +const short init = ~0; + +struct A +{ + short a; + short b; +} __attribute__ ((packed)) A; + +/* The fetch_op routines return the original value before the operation. */ + +void +test_fetch_add (short* v) +{ + *v = 0; + count = 1; + + if (__atomic_fetch_add (v, count, __ATOMIC_RELAXED) != 0) + abort (); + + if (__atomic_fetch_add (v, 1, __ATOMIC_CONSUME) != 1) + abort (); + + if (__atomic_fetch_add (v, count, __ATOMIC_ACQUIRE) != 2) + abort (); + + if (__atomic_fetch_add (v, 1, __ATOMIC_RELEASE) != 3) + abort (); + + if (__atomic_fetch_add (v, count, __ATOMIC_ACQ_REL) != 4) + abort (); + + if (__atomic_fetch_add (v, 1, __ATOMIC_SEQ_CST) != 5) + abort (); +} + + +void +test_fetch_sub (short* v) +{ + *v = res = 20; + count = 0; + + if (__atomic_fetch_sub (v, count + 1, __ATOMIC_RELAXED) != res--) + abort (); + + if (__atomic_fetch_sub (v, 1, __ATOMIC_CONSUME) != res--) + abort (); + + if (__atomic_fetch_sub (v, count + 1, __ATOMIC_ACQUIRE) != res--) + abort (); + + if (__atomic_fetch_sub (v, 1, __ATOMIC_RELEASE) != res--) + abort (); + + if (__atomic_fetch_sub (v, count + 1, __ATOMIC_ACQ_REL) != res--) + abort (); + + if (__atomic_fetch_sub (v, 1, __ATOMIC_SEQ_CST) != res--) + abort (); +} + +void +test_fetch_and (short* v) +{ + *v = init; + + if (__atomic_fetch_and (v, 0, __ATOMIC_RELAXED) != init) + abort (); + + if (__atomic_fetch_and (v, init, __ATOMIC_CONSUME) != 0) + abort (); + + if (__atomic_fetch_and (v, 0, __ATOMIC_ACQUIRE) != 0) + abort (); + + *v = ~*v; + if (__atomic_fetch_and (v, init, __ATOMIC_RELEASE) != init) + abort (); + + if (__atomic_fetch_and (v, 0, __ATOMIC_ACQ_REL) != init) + abort (); + + if (__atomic_fetch_and (v, 0, __ATOMIC_SEQ_CST) != 0) + abort (); +} + +void +test_fetch_nand (short* v) +{ + *v = init; + + if (__atomic_fetch_nand (v, 0, __ATOMIC_RELAXED) != init) + abort (); + + if (__atomic_fetch_nand (v, init, __ATOMIC_CONSUME) != init) + abort (); + + if (__atomic_fetch_nand (v, 0, __ATOMIC_ACQUIRE) != 0 ) + abort (); + + if (__atomic_fetch_nand (v, init, __ATOMIC_RELEASE) != init) + abort (); + + if (__atomic_fetch_nand (v, init, __ATOMIC_ACQ_REL) != 0) + abort (); + + if (__atomic_fetch_nand (v, 0, __ATOMIC_SEQ_CST) != init) + abort (); +} + +void +test_fetch_xor (short* v) +{ + *v = init; + count = 0; + + if (__atomic_fetch_xor (v, count, __ATOMIC_RELAXED) != init) + abort (); + + if (__atomic_fetch_xor (v, ~count, __ATOMIC_CONSUME) != init) + abort (); + + if (__atomic_fetch_xor (v, 0, __ATOMIC_ACQUIRE) != 0) + abort (); + + if (__atomic_fetch_xor (v, ~count, __ATOMIC_RELEASE) != 0) + abort (); + + if (__atomic_fetch_xor (v, 0, __ATOMIC_ACQ_REL) != init) + abort (); + + if (__atomic_fetch_xor (v, ~count, __ATOMIC_SEQ_CST) != init) + abort (); +} + +void +test_fetch_or (short* v) +{ + *v = 0; + count = 1; + + if (__atomic_fetch_or (v, count, __ATOMIC_RELAXED) != 0) + abort (); + + count *= 2; + if (__atomic_fetch_or (v, 2, __ATOMIC_CONSUME) != 1) + abort (); + + count *= 2; + if (__atomic_fetch_or (v, count, __ATOMIC_ACQUIRE) != 3) + abort (); + + count *= 2; + if (__atomic_fetch_or (v, 8, __ATOMIC_RELEASE) != 7) + abort (); + + count *= 2; + if (__atomic_fetch_or (v, count, __ATOMIC_ACQ_REL) != 15) + abort (); + + count *= 2; + if (__atomic_fetch_or (v, count, __ATOMIC_SEQ_CST) != 31) + abort (); +} + +/* The OP_fetch routines return the new value after the operation. */ + +void +test_add_fetch (short* v) +{ + *v = 0; + count = 1; + + if (__atomic_add_fetch (v, count, __ATOMIC_RELAXED) != 1) + abort (); + + if (__atomic_add_fetch (v, 1, __ATOMIC_CONSUME) != 2) + abort (); + + if (__atomic_add_fetch (v, count, __ATOMIC_ACQUIRE) != 3) + abort (); + + if (__atomic_add_fetch (v, 1, __ATOMIC_RELEASE) != 4) + abort (); + + if (__atomic_add_fetch (v, count, __ATOMIC_ACQ_REL) != 5) + abort (); + + if (__atomic_add_fetch (v, count, __ATOMIC_SEQ_CST) != 6) + abort (); +} + + +void +test_sub_fetch (short* v) +{ + *v = res = 20; + count = 0; + + if (__atomic_sub_fetch (v, count + 1, __ATOMIC_RELAXED) != --res) + abort (); + + if (__atomic_sub_fetch (v, 1, __ATOMIC_CONSUME) != --res) + abort (); + + if (__atomic_sub_fetch (v, count + 1, __ATOMIC_ACQUIRE) != --res) + abort (); + + if (__atomic_sub_fetch (v, 1, __ATOMIC_RELEASE) != --res) + abort (); + + if (__atomic_sub_fetch (v, count + 1, __ATOMIC_ACQ_REL) != --res) + abort (); + + if (__atomic_sub_fetch (v, count + 1, __ATOMIC_SEQ_CST) != --res) + abort (); +} + +void +test_and_fetch (short* v) +{ + *v = init; + + if (__atomic_and_fetch (v, 0, __ATOMIC_RELAXED) != 0) + abort (); + + *v = init; + if (__atomic_and_fetch (v, init, __ATOMIC_CONSUME) != init) + abort (); + + if (__atomic_and_fetch (v, 0, __ATOMIC_ACQUIRE) != 0) + abort (); + + *v = ~*v; + if (__atomic_and_fetch (v, init, __ATOMIC_RELEASE) != init) + abort (); + + if (__atomic_and_fetch (v, 0, __ATOMIC_ACQ_REL) != 0) + abort (); + + *v = ~*v; + if (__atomic_and_fetch (v, 0, __ATOMIC_SEQ_CST) != 0) + abort (); +} + +void +test_nand_fetch (short* v) +{ + *v = init; + + if (__atomic_nand_fetch (v, 0, __ATOMIC_RELAXED) != init) + abort (); + + if (__atomic_nand_fetch (v, init, __ATOMIC_CONSUME) != 0) + abort (); + + if (__atomic_nand_fetch (v, 0, __ATOMIC_ACQUIRE) != init) + abort (); + + if (__atomic_nand_fetch (v, init, __ATOMIC_RELEASE) != 0) + abort (); + + if (__atomic_nand_fetch (v, init, __ATOMIC_ACQ_REL) != init) + abort (); + + if (__atomic_nand_fetch (v, 0, __ATOMIC_SEQ_CST) != init) + abort (); +} + + + +void +test_xor_fetch (short* v) +{ + *v = init; + count = 0; + + if (__atomic_xor_fetch (v, count, __ATOMIC_RELAXED) != init) + abort (); + + if (__atomic_xor_fetch (v, ~count, __ATOMIC_CONSUME) != 0) + abort (); + + if (__atomic_xor_fetch (v, 0, __ATOMIC_ACQUIRE) != 0) + abort (); + + if (__atomic_xor_fetch (v, ~count, __ATOMIC_RELEASE) != init) + abort (); + + if (__atomic_xor_fetch (v, 0, __ATOMIC_ACQ_REL) != init) + abort (); + + if (__atomic_xor_fetch (v, ~count, __ATOMIC_SEQ_CST) != 0) + abort (); +} + +void +test_or_fetch (short* v) +{ + *v = 0; + count = 1; + + if (__atomic_or_fetch (v, count, __ATOMIC_RELAXED) != 1) + abort (); + + count *= 2; + if (__atomic_or_fetch (v, 2, __ATOMIC_CONSUME) != 3) + abort (); + + count *= 2; + if (__atomic_or_fetch (v, count, __ATOMIC_ACQUIRE) != 7) + abort (); + + count *= 2; + if (__atomic_or_fetch (v, 8, __ATOMIC_RELEASE) != 15) + abort (); + + count *= 2; + if (__atomic_or_fetch (v, count, __ATOMIC_ACQ_REL) != 31) + abort (); + + count *= 2; + if (__atomic_or_fetch (v, count, __ATOMIC_SEQ_CST) != 63) + abort (); +} + + +/* Test the OP routines with a result which isn't used. Use both variations + within each function. */ + +void +test_add (short* v) +{ + *v = 0; + count = 1; + + __atomic_add_fetch (v, count, __ATOMIC_RELAXED); + if (*v != 1) + abort (); + + __atomic_fetch_add (v, count, __ATOMIC_CONSUME); + if (*v != 2) + abort (); + + __atomic_add_fetch (v, 1 , __ATOMIC_ACQUIRE); + if (*v != 3) + abort (); + + __atomic_fetch_add (v, 1, __ATOMIC_RELEASE); + if (*v != 4) + abort (); + + __atomic_add_fetch (v, count, __ATOMIC_ACQ_REL); + if (*v != 5) + abort (); + + __atomic_fetch_add (v, count, __ATOMIC_SEQ_CST); + if (*v != 6) + abort (); +} + + +void +test_sub (short* v) +{ + *v = res = 20; + count = 0; + + __atomic_sub_fetch (v, count + 1, __ATOMIC_RELAXED); + if (*v != --res) + abort (); + + __atomic_fetch_sub (v, count + 1, __ATOMIC_CONSUME); + if (*v != --res) + abort (); + + __atomic_sub_fetch (v, 1, __ATOMIC_ACQUIRE); + if (*v != --res) + abort (); + + __atomic_fetch_sub (v, 1, __ATOMIC_RELEASE); + if (*v != --res) + abort (); + + __atomic_sub_fetch (v, count + 1, __ATOMIC_ACQ_REL); + if (*v != --res) + abort (); + + __atomic_fetch_sub (v, count + 1, __ATOMIC_SEQ_CST); + if (*v != --res) + abort (); +} + +void +test_and (short* v) +{ + *v = init; + + __atomic_and_fetch (v, 0, __ATOMIC_RELAXED); + if (*v != 0) + abort (); + + *v = init; + __atomic_fetch_and (v, init, __ATOMIC_CONSUME); + if (*v != init) + abort (); + + __atomic_and_fetch (v, 0, __ATOMIC_ACQUIRE); + if (*v != 0) + abort (); + + *v = ~*v; + __atomic_fetch_and (v, init, __ATOMIC_RELEASE); + if (*v != init) + abort (); + + __atomic_and_fetch (v, 0, __ATOMIC_ACQ_REL); + if (*v != 0) + abort (); + + *v = ~*v; + __atomic_fetch_and (v, 0, __ATOMIC_SEQ_CST); + if (*v != 0) + abort (); +} + +void +test_nand (short* v) +{ + *v = init; + + __atomic_fetch_nand (v, 0, __ATOMIC_RELAXED); + if (*v != init) + abort (); + + __atomic_fetch_nand (v, init, __ATOMIC_CONSUME); + if (*v != 0) + abort (); + + __atomic_nand_fetch (v, 0, __ATOMIC_ACQUIRE); + if (*v != init) + abort (); + + __atomic_nand_fetch (v, init, __ATOMIC_RELEASE); + if (*v != 0) + abort (); + + __atomic_fetch_nand (v, init, __ATOMIC_ACQ_REL); + if (*v != init) + abort (); + + __atomic_nand_fetch (v, 0, __ATOMIC_SEQ_CST); + if (*v != init) + abort (); +} + + + +void +test_xor (short* v) +{ + *v = init; + count = 0; + + __atomic_xor_fetch (v, count, __ATOMIC_RELAXED); + if (*v != init) + abort (); + + __atomic_fetch_xor (v, ~count, __ATOMIC_CONSUME); + if (*v != 0) + abort (); + + __atomic_xor_fetch (v, 0, __ATOMIC_ACQUIRE); + if (*v != 0) + abort (); + + __atomic_fetch_xor (v, ~count, __ATOMIC_RELEASE); + if (*v != init) + abort (); + + __atomic_fetch_xor (v, 0, __ATOMIC_ACQ_REL); + if (*v != init) + abort (); + + __atomic_xor_fetch (v, ~count, __ATOMIC_SEQ_CST); + if (*v != 0) + abort (); +} + +void +test_or (short* v) +{ + *v = 0; + count = 1; + + __atomic_or_fetch (v, count, __ATOMIC_RELAXED); + if (*v != 1) + abort (); + + count *= 2; + __atomic_fetch_or (v, count, __ATOMIC_CONSUME); + if (*v != 3) + abort (); + + count *= 2; + __atomic_or_fetch (v, 4, __ATOMIC_ACQUIRE); + if (*v != 7) + abort (); + + count *= 2; + __atomic_fetch_or (v, 8, __ATOMIC_RELEASE); + if (*v != 15) + abort (); + + count *= 2; + __atomic_or_fetch (v, count, __ATOMIC_ACQ_REL); + if (*v != 31) + abort (); + + count *= 2; + __atomic_fetch_or (v, count, __ATOMIC_SEQ_CST); + if (*v != 63) + abort (); +} + +int +main () { + short* V[] = {&A.a, &A.b}; + + for (int i = 0; i < 2; i++) { + test_fetch_add (V[i]); + test_fetch_sub (V[i]); + test_fetch_and (V[i]); + test_fetch_nand (V[i]); + test_fetch_xor (V[i]); + test_fetch_or (V[i]); + + test_add_fetch (V[i]); + test_sub_fetch (V[i]); + test_and_fetch (V[i]); + test_nand_fetch (V[i]); + test_xor_fetch (V[i]); + test_or_fetch (V[i]); + + test_add (V[i]); + test_sub (V[i]); + test_and (V[i]); + test_nand (V[i]); + test_xor (V[i]); + test_or (V[i]); + } + + return 0; +} diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-5.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-5.c new file mode 100644 index 00000000000..c2751235dbf --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-5.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* Verify that constant propogation is functioning. */ +/* The -4 should be propogated into an ANDI statement. */ +/* { dg-options "-minline-atomics" } */ +/* { dg-final { scan-assembler-not "\tli\t[at]\d,-4" } } */ + +char bar; + +int +main () +{ + __sync_fetch_and_add(&bar, 1); +} diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-6.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-6.c new file mode 100644 index 00000000000..18249bae7d1 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-6.c @@ -0,0 +1,12 @@ +/* { dg-do compile } */ +/* Verify that masks are generated to the correct size. */ +/* { dg-options "-O3 -minline-atomics" } */ +/* Check for mask */ +/* { dg-final { scan-assembler "\tli\t[at]\d,255" } } */ + +int +main () +{ + char bar __attribute__((aligned (32))); + __sync_fetch_and_add(&bar, 0); +} diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-7.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-7.c new file mode 100644 index 00000000000..81bbf4badce --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-7.c @@ -0,0 +1,12 @@ +/* { dg-do compile } */ +/* Verify that masks are generated to the correct size. */ +/* { dg-options "-O3 -minline-atomics" } */ +/* Check for mask */ +/* { dg-final { scan-assembler "\tli\t[at]\d,65535" } } */ + +int +main () +{ + short bar __attribute__((aligned (32))); + __sync_fetch_and_add(&bar, 0); +} diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-8.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-8.c new file mode 100644 index 00000000000..d27562ed981 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-8.c @@ -0,0 +1,17 @@ +/* { dg-do compile } */ +/* Verify that masks are aligned properly. */ +/* { dg-options "-O3 -minline-atomics" } */ +/* Check for mask */ +/* { dg-final { scan-assembler "\tli\t[at]\d,16711680" } } */ + +int +main () +{ + struct A { + char a; + char b; + char c; + char d; + } __attribute__ ((packed)) __attribute__((aligned (32))) A; + __sync_fetch_and_add(&A.c, 0); +} diff --git a/gcc/testsuite/gcc.target/riscv/inline-atomics-9.c b/gcc/testsuite/gcc.target/riscv/inline-atomics-9.c new file mode 100644 index 00000000000..382849702ca --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/inline-atomics-9.c @@ -0,0 +1,17 @@ +/* { dg-do compile } */ +/* Verify that masks are aligned properly. */ +/* { dg-options "-O3 -minline-atomics" } */ +/* Check for mask */ +/* { dg-final { scan-assembler "\tli\t[at]\d,-16777216" } } */ + +int +main () +{ + struct A { + char a; + char b; + char c; + char d; + } __attribute__ ((packed)) __attribute__((aligned (32))) A; + __sync_fetch_and_add(&A.d, 0); +} diff --git a/libgcc/config/riscv/atomic.c b/libgcc/config/riscv/atomic.c index 7007e7a20e4..a29909b97b5 100644 --- a/libgcc/config/riscv/atomic.c +++ b/libgcc/config/riscv/atomic.c @@ -30,6 +30,8 @@ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see #define INVERT "not %[tmp1], %[tmp1]\n\t" #define DONT_INVERT "" +/* Logic duplicated in gcc/gcc/config/riscv/sync.md for use when inlining is enabled */ + #define GENERATE_FETCH_AND_OP(type, size, opname, insn, invert, cop) \ type __sync_fetch_and_ ## opname ## _ ## size (type *p, type v) \ { \ -- 2.25.1