191af6c254
The llvm.cond.loop intrinsic is semantically equivalent to a conditional branch conditioned on ``pred`` to a basic block consisting only of an unconditional branch to itself. Unlike such a branch, it is guaranteed to use specific instructions. This allows an interrupt handler or other introspection mechanism to straightforwardly detect whether the program is currently spinning in the infinite loop and possibly terminate the program if so. The intent is that this intrinsic may be used as a more efficient alternative to a conditional branch to a call to ``llvm.trap`` in circumstances where the loop detection is guaranteed to be present. This construct has been experimentally determined to be executed more efficiently (when the branch is not taken) than a conditional branch to a trap instruction on AMD and older Intel microarchitectures, and is also more code size efficient by avoiding the need to emit a trap instruction and possibly a long branch instruction. On i386 and x86_64, the infinite loop is guaranteed to consist of a short conditional branch instruction that branches to itself. Specifically, the first byte of the instruction will be between 0x70 and 0x7F, and the second byte will be 0xFE. Part of this RFC: https://discourse.llvm.org/t/rfc-optimizing-conditional-traps/89456 Reviewers: arsenm, RKSimon, fmayer, vitalybuka Pull Request: https://github.com/llvm/llvm-project/pull/177686
51 lines
1.2 KiB
LLVM
51 lines
1.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: llc < %s -mtriple=x86_64 | FileCheck %s
|
|
|
|
define void @f1(i64 %a, i64 %b) {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: cmpq %rsi, %rdi
|
|
; CHECK-NEXT: .Ltmp0:
|
|
; CHECK-NEXT: jb .Ltmp0
|
|
; CHECK-NEXT: retq
|
|
%cmp = icmp ult i64 %a, %b
|
|
call void @llvm.cond.loop(i1 %cmp)
|
|
ret void
|
|
}
|
|
|
|
define void @f2() {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: movb $1, %al
|
|
; CHECK-NEXT: testb %al, %al
|
|
; CHECK-NEXT: .Ltmp1:
|
|
; CHECK-NEXT: jne .Ltmp1
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.cond.loop(i1 true)
|
|
ret void
|
|
}
|
|
|
|
define void @f3(i1 %p) {
|
|
; CHECK-LABEL: f3:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: testb $1, %dil
|
|
; CHECK-NEXT: .Ltmp2:
|
|
; CHECK-NEXT: jne .Ltmp2
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.cond.loop(i1 %p)
|
|
ret void
|
|
}
|
|
|
|
define void @f4(i32 %a, i32 %b) {
|
|
; CHECK-LABEL: f4:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: addl %esi, %edi
|
|
; CHECK-NEXT: .Ltmp3:
|
|
; CHECK-NEXT: jo .Ltmp3
|
|
; CHECK-NEXT: retq
|
|
%add = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 %a, i32 %b)
|
|
%overflow = extractvalue { i32, i1 } %add, 1
|
|
tail call void @llvm.cond.loop(i1 %overflow)
|
|
ret void
|
|
}
|