| Issue |
141638
|
| Summary |
Code with goto is 3x faster than code with continue
|
| Labels |
new issue
|
| Assignees |
|
| Reporter |
gbaraldi
|
While debugging https://github.com/JuliaLang/julia/issues/47542 I managed to reproduce the same slowdown with C code, https://godbolt.org/z/789GdG3bE.
The code is
```c
__attribute__((noinline)) size_t foo(int64_t *arr, size_t len) {
size_t i = 0;
foo:
while (i < len) {
if (arr[i] == 0) {
i += 1;
goto foo;
}
i += 2;
}
return i;
}
__attribute__((noinline)) size_t bar(int64_t *arr, size_t len) {
size_t i = 0;
while (i < len) {
if (arr[i] == 0) {
i += 1;
continue;
}
i += 2;
}
return i;
}
```
The difference is that code with continue gets compiled to a select where the goto keeps the branch. I imagine this is a choice done in SimplifyCFG but I imagine that branch prediction/speculation on this is good enough that the conditional increment done on the continue case is much worse. Goto was faster on everything I tested (2 aarch64 cpus and 2 x86 cpus)
![]()
_______________________________________________
llvm-bugs mailing list
llvm-bugs@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
