7852ebc088
Before llvm20, (void)__sync_fetch_and_add(...) always generates locked xadd insns. In linux kernel upstream discussion [1], it is found that for arm64 architecture, the original semantics of (void)__sync_fetch_and_add(...), i.e., __atomic_fetch_add(...), is preferred in order for jit to emit proper native barrier insns. In llvm commits [2] and [3], (void)__sync_fetch_and_add(...) will generate the following insns: - for cpu v1/v2: locked xadd insns to keep backward compatibility - for cpu v3/v4: __atomic_fetch_add() insns To ensure proper barrier semantics for (void)__sync_fetch_and_add(...), cpu v3/v4 is recommended. This patch enables cpu=v3 as the default cpu version. For users wanting to use cpu v1, -mcpu=v1 needs to be explicitly added to clang/llc command line. [1] https://lore.kernel.org/bpf/ZqqiQQWRnz7H93Hc@google.com/T/#mb68d67bc8f39e35a0c3db52468b9de59b79f021f [2] https://github.com/llvm/llvm-project/pull/101428 [3] https://github.com/llvm/llvm-project/pull/106494
19 lines
378 B
LLVM
19 lines
378 B
LLVM
; RUN: llc -mtriple=bpfel -mcpu=v1 -filetype=obj -o - %s | llvm-objdump --no-print-imm-hex -d - | FileCheck %s
|
|
|
|
; CHECK: if r2 s> r1 goto
|
|
; CHECK: call 1
|
|
; CHECK: exit
|
|
; CHECK: call 2
|
|
; CHECK: exit
|
|
|
|
define void @foo(i32 %a) {
|
|
%b = icmp sgt i32 %a, -1
|
|
br i1 %b, label %x, label %y
|
|
x:
|
|
call void inttoptr (i64 1 to ptr)()
|
|
ret void
|
|
y:
|
|
call void inttoptr (i64 2 to ptr)()
|
|
ret void
|
|
}
|