marc.glisse at normalesup.org
Wed May 24 13:13:13 CEST 2006
On Tue, 23 May 2006, Torbjorn Granlund wrote:
> If I get the time, I'll reorganize the mpn/sparc64 code, making an
> ultrasparc1234 subdirectory with the various addmul_x and mul_x and
> submul_1 files. Then instruct configure to choose that just of these
> chips, and not for ultrasparct.
> Does mulx work reasonably on ultrasparc t1? Or does that stall other
> processors too? How about the disks, will they continue to spin...?
I have no idea. What do you mean "reasonably"? I don't think it stalls
other processors, no, only FPU (floats, VIS) operations do that. But
please don't do anything based on what I say, I know nothing about
hardware. It is much better to look at opensparc.sunsource.net (or maybe
ask on some Sun forum or newsgroup) if you get the time.
More information about the gmp-bugs