Cómo encontrar fugas con memcheck

GPU memory bugs rarely crash loudly, so compute-sanitizer with the memcheck tool watches every access and reports the trouble for you. 🛡️

Run your program under the memcheck tool by prefixing it with compute-sanitizer, the modern replacement for the old cuda-memcheck.

The classic bug memcheck catches is an out-of-bounds access, where a thread reads or writes past the end of a device array.

Forgetting the guard lets extra threads run wild, so this index can stray beyond n and trigger an invalid global write.

memcheck prints the error kind, the offending address, and the thread that caused it, pointing you straight at the bad access.

Compile with -lineinfo so memcheck can map each error back to the exact source line instead of a raw address.

Turn on the --leak-check option and memcheck reports any device memory you allocated but never released before exit.

Allocating without a matching free leaks the buffer, and across many iterations that slowly exhausts device memory.

memcheck also flags passing a host pointer where the kernel expects a device pointer, a mistake that silently corrupts results.

Some loads require aligned addresses, so memcheck warns about a misaligned access that would otherwise produce garbage or a fault.

After each fix, run memcheck again until it reports zero errors. A clean run is your sign the memory bugs are gone.

What kind of bug is the memcheck tool primarily designed to find?

You ran memcheck, added -lineinfo for source lines, enabled leak checking, and learned its common error kinds. Clean runs mean safe memory. ✅