On Thu, 2024-03-07 at 09:12 +0800, Lulu Cheng wrote:
> + output_asm_insn ("1:", operands);
> + output_asm_insn ("ll.<amo>\t%0,%1", operands);
> +
> + /* Like the test case atomic-cas-int.C, in loongarch64, O1 and higher, the
> + return value of the val_without_const_folding will not be truncated and
> + will be passed directly to the function compare_exchange_strong.
> + However, the instruction 'bne' does not distinguish between 32-bit and
> + 64-bit operations. so if the upper 32 bits of the register are not
> + extended by the 32nd bit symbol, then the comparison may not be valid
> + here. This will affect the result of the operation. */
> +
> + if (TARGET_64BIT && REG_P (operands[2])
> + && GET_MODE (operands[2]) == SImode)
> + {
> + output_asm_insn ("addi.w\t%5,%2,0", operands);
> + output_asm_insn ("bne\t%0,%5,2f", operands);
It should be better to extend the expected value before the ll/sc loop
(like what LLVM does), instead of repeating the extending in each
iteration. Something like:
diff --git a/gcc/config/loongarch/sync.md b/gcc/config/loongarch/sync.md
index 8f35a5b48d2..c21781947fd 100644
--- a/gcc/config/loongarch/sync.md
+++ b/gcc/config/loongarch/sync.md
@@ -234,11 +234,11 @@ (define_insn "atomic_exchange<mode>_short"
"amswap%A3.<amo>\t%0,%z2,%1"
[(set (attr "length") (const_int 4))])
-(define_insn "atomic_cas_value_strong<mode>"
+(define_insn "atomic_cas_value_strong<GPR:mode><X:mode>"
[(set (match_operand:GPR 0 "register_operand" "=&r")
(match_operand:GPR 1 "memory_operand" "+ZC"))
(set (match_dup 1)
- (unspec_volatile:GPR [(match_operand:GPR 2 "reg_or_0_operand" "rJ")
+ (unspec_volatile:GPR [(match_operand:X 2 "reg_or_0_operand" "rJ")
(match_operand:GPR 3 "reg_or_0_operand" "rJ")
(match_operand:SI 4 "const_int_operand")] ;;
mod_s
UNSPEC_COMPARE_AND_SWAP))
@@ -246,10 +246,10 @@ (define_insn "atomic_cas_value_strong<mode>"
""
{
return "1:\\n\\t"
- "ll.<amo>\\t%0,%1\\n\\t"
+ "ll.<GPR:amo>\\t%0,%1\\n\\t"
"bne\\t%0,%z2,2f\\n\\t"
"or%i3\\t%5,$zero,%3\\n\\t"
- "sc.<amo>\\t%5,%1\\n\\t"
+ "sc.<GPR:amo>\\t%5,%1\\n\\t"
"beqz\\t%5,1b\\n\\t"
"b\\t3f\\n\\t"
"2:\\n\\t"
@@ -301,9 +301,23 @@ (define_expand "atomic_compare_and_swap<mode>"
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 (*cas)(rtx, rtx, rtx, rtx, rtx) =
+ TARGET_64BIT ? gen_atomic_cas_value_strong<mode>di
+ : gen_atomic_cas_value_strong<mode>si;
+ rtx expect = operands[3];
+
+ if (<MODE>mode == SImode
+ && TARGET_64BIT
+ && operands[3] != const0_rtx)
+ {
+ expect = gen_reg_rtx (DImode);
+ emit_insn (gen_extendsidi2 (expect, operands[3]));
+ }
+
+ emit_insn (cas (operands[1], operands[2], expect, operands[4],
+ operands[6]));
+ }
rtx compare = operands[1];
if (operands[3] != const0_rtx)
It produces:
slli.w $r4,$r4,0
1:
ll.w $r14,$r3,0
bne $r14,$r4,2f
or $r15,$zero,$r12
sc.w $r15,$r3,0
beqz $r15,1b
b 3f
2:
dbar 0b10100
3:
for the test case and the compiled test case runs successfully. I've
not done a full bootstrap yet though.
--
Xi Ruoyao <[email protected]>
School of Aerospace Science and Technology, Xidian University
