[Libre-soc-isa] [Bug 1057] split out all int/fp min/max ops into their own RFC ls013

bugzilla-daemon at libre-soc.org bugzilla-daemon at libre-soc.org
Wed Apr 26 05:54:32 BST 2023


--- Comment #32 from Jacob Lifshay <programmerjake at gmail.com> ---
(In reply to Luke Kenneth Casson Leighton from comment #31)
>  6.10.2 Vector Floating-Point Maximum/ Minimum Instructions  . . . 424
> these are FP32 only
> MnemonicInstruction NamePage 
> xsmaxcdpVSX Scalar Maximum Type-C Double-Precision736 
> xsmaxcqpVSX Scalar Maximum Type-C Quad-Precision738 
> xsmaxdpVSX Scalar Maximum Double-Precision734 
> xsmaxjdpVSX Scalar Maximum Type-J Double-Precision739 
> xsmincdpVSX Scalar Minimum Type-C Double-Precision743 
> xsmincqpVSX Scalar Minimum Type-C Quad-Precision745 
> xsmindpVSX Scalar Minimum Double-Precision741 
> xsminjdpVSX Scalar Minimum Type-J Double-Precision746 
> Table 29.VSX Scalar BFP Maximum/Minimum Instructions
> looks like they do but more because SIMD. and type J and C
> whatever those are?

type C is basically fminc/fmaxc
type J is IEEE 754-2019 minimum/maximum aka. fmin19/fmax19 -- J because that's
Java's Math.max

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

More information about the Libre-SOC-ISA mailing list