[Libre-soc-isa] [Bug 701] document Matrix REMAP in SVP64

[bugzilla-daemon at libre-soc.org]

https://bugs.libre-soc.org/show_bug.cgi?id=701

--- Comment #15 from Andrey Miroshnikov <andrey at technepisteme.xyz> ---
(In reply to Luke Kenneth Casson Leighton from comment #13)
> *three* SVSHAPE SPRs are used and they are named SVSHAPEn not SHAPEn
> (i corrected this earlier last week)
> 
> you can see the instruction source code, you do not need me
> to see that:
> 
> https://git.libre-soc.org/?p=openpower-isa.git;a=blob;f=openpower/isa/
> simplev.mdwn;h=33a02e#l137
Thanks for the clarification, I was confused by the "SHAPE Remapping SPRs"
section in openpower/sv/remap/ (I thought only SVSHAPE0 is being used).

> 
> notice how SVSHAPE0-2 are set up?
> one for A, one for B, one for C  in C=AxB...
> 
> otherwise how can we ever do the schedule for A B and C
> unless there is an SVSHAPE for each?
A quick look does show SVSHAPE0-2 being used and setup, yeah.
I'll look over the pseudocode properly on the train. 

> 
> yyeah there it is. that is standalone executable (designed as such).
> sorry, didn't do a similar one for matrix, rempyield.py is much more
> basic it was the first REMAP subsystem i ever did.
Only after studying svshape instruction and SVSHAPE0 did I realise just how
capable and flexible the configuration can be. However getting used to this
paradigm is not easy (kind of frightening when there are so many parameters to
tweak).

-- 
You are receiving this mail because:
You are on the CC list for the bug.