What is the limit of pk for malloc() and mmaps?

[NazerkeT]

Hi there!

I was recently heavily using spike with pk and noticed that I cannot run application with large mallocs like 8MB or more with spike + pk any more. Essentially, simulation fails with either load or store segfaults.

Is there any reason that is coming from pk side for it? If yes, how can I change the current malloc/mmap limitations of the pk? In general, is there any hint or advice do you guys have for it?

Thanks, Best wishes,

[aswaterman]

Might be related to your C library, too. Let us know if you find what’s clearly a bug in pk.

On Tue, Feb 28, 2023 at 5:57 PM Nazerke Turtayeva @.***> wrote:

Hi there!

I was recently heavily using spike with pk and noticed that I cannot run application with large mallocs like 8MB or more with spike + pk any more. Essentially, simulation fails with either load or store segfaults.

Is there any reason that is coming from pk side for it? If yes, how can I change the current malloc/mmap limitations of the pk? In general, is there any hint or advice do you guys have for it?

Thanks, Best wishes,

— Reply to this email directly, view it on GitHub https://github.com/riscv-software-src/riscv-pk/issues/291, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAH3XQRJHIKFKZYZDBILZBLWZ2UHDANCNFSM6AAAAAAVLONBIE . You are receiving this because you are subscribed to this thread.Message ID: @.***>