Torbjorn Granlund writes:
> There are no 64-bit subtraction instruction that take a useful
> carry-in.
> More recently, as part of a special "visual instruction set 3", Oracle
> added 64-bit addition instructions which take a useful carry-in...
And one can use the 64-bit add-with-carry to do a
ni...@lysator.liu.se (Niels Möller) writes:
Torbjorn Granlund writes:
> I optimised submul_1.asm, and then edited both addmul_1 and submul_1 to
> use as similar operand order as possible.
So remaining differences are necessary?
Some differences need to remain, yes...
I don't rem
Torbjorn Granlund writes:
> I optimised submul_1.asm, and then edited both addmul_1 and submul_1 to
> use as similar operand order as possible.
So remaining differences are necessary? I don't remember much sparc
assembly, but it seems carry handling is done slightly differently. But
appearantly
David Miller writes:
From: David Miller
Date: Thu, 07 Mar 2013 01:06:55 -0500 (EST)
> I'll test your routines with the obvious fix in a moment.
With the one-liner fix both of your new implementations work.
Thanks for testing!
submul_1 is now much better, about 5.8 cycles per
From: David Miller
Date: Thu, 07 Mar 2013 01:06:55 -0500 (EST)
> I'll test your routines with the obvious fix in a moment.
With the one-liner fix both of your new implementations work.
submul_1 is now much better, about 5.8 cycles per limb on T4.
___
From: Torbjorn Granlund
Date: Thu, 07 Mar 2013 07:00:00 +0100
> Why doesn't your functions use the 'return' insns, btw?
They were expensive at one point, but I just checked and on T4 using
return appears to be quite cheap.
> PS. I have created a poor man's T3 with some m4 macros. This will all
David Miller writes:
> I optimised submul_1.asm, and then edited both addmul_1 and submul_1 to
> use as similar operand order as possible. Please test these using
> tests/devel/try, and please time this new submul_1.
The testsuite starts failing very early with these changes.
Sorry
From: Torbjorn Granlund
Date: Thu, 07 Mar 2013 00:51:24 +0100
> David Miller writes:
>
> From: Torbjorn Granlund
> Date: Wed, 06 Mar 2013 12:36:34 +0100
>
> > I think all you T3/T4 changes are now in. Please check that I didn't
> > mess something up.
> >
> > Thanks for this con
David Miller writes:
From: Torbjorn Granlund
Date: Wed, 06 Mar 2013 12:36:34 +0100
> I think all you T3/T4 changes are now in. Please check that I didn't
> mess something up.
>
> Thanks for this contribution!
Looks good, there is some trailing whitespace in the ChangeLog but
From: Torbjorn Granlund
Date: Wed, 06 Mar 2013 12:36:34 +0100
> I think all you T3/T4 changes are now in. Please check that I didn't
> mess something up.
>
> Thanks for this contribution!
Looks good, there is some trailing whitespace in the ChangeLog but
that's probably my fault:
diff -r 84dd2
I think all you T3/T4 changes are now in. Please check that I didn't
mess something up.
Thanks for this contribution!
--
Torbjörn
___
gmp-devel mailing list
gmp-devel@gmplib.org
http://gmplib.org/mailman/listinfo/gmp-devel
* mpn/sparc64/ultrasparct3/add_n.asm: New file.
* mpn/sparc64/ultrasparct3/sub_n.asm: New file.
---
diff --git a/mpn/sparc64/ultrasparct3/add_n.asm
b/mpn/sparc64/ultrasparct3/add_n.asm
new file mode 100644
index 000..16bd0c4
--- /dev/null
+++ b/mpn/sparc64/ultrasparct3/add_n.
12 matches
Mail list logo
