Ciao!
I played a little bit with mpn/x86_64/sqr_basecase.asm, it contains
instructions like:
add $-40, %rsp
mov %rbx, 32(%rsp)
mov %rbp, 24(%rsp)
mov %r12, 16(%rsp)
mov %r13, 8(%rsp)
mov %r14, (%rsp)
From the document I've
Torbjorn Granlund t...@gmplib.org writes:
If GCC generates code that takes advantage if this rule, then I expect
no problems at any standard platform.
GCC 4.7 on FreeBSD generates such code fpr bdiv_qr.c. This is not a
leaf function, so rsp is moved down before the calls. But the fact