From 2abc2e973396548e9a8124b07dcb324893453626 Mon Sep 17 00:00:00 2001 From: lkcl Date: Sat, 11 Jun 2022 19:06:07 +0100 Subject: [PATCH] --- openpower/sv/mv.vec.mdwn | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/openpower/sv/mv.vec.mdwn b/openpower/sv/mv.vec.mdwn index 87464f572..ec398bcb8 100644 --- a/openpower/sv/mv.vec.mdwn +++ b/openpower/sv/mv.vec.mdwn @@ -7,7 +7,7 @@ In the SIMD VSX set, section 6.8.1 and 6.8.2 p254 of v3.0B has a series of pack * See * -Pack and unpack may be covered by [[remap]] by using Matrix 2D layouts on either source or destination but is quite expensive to do so. Additionally, +Pack and unpack may be covered by [[sv/remap]] by using Matrix 2D layouts on either source or destination but is quite expensive to do so. Additionally, with pressure on the Scalar 32-bit opcode space it is more appropriate to compromise by adding required capability in SVP64 on top of a base pre-existing Scalar mv instruction. [[sv/mv.swizzle]] is sufficiently @@ -65,6 +65,10 @@ This results in a 3-element "pack" Both examples become particularly fun when Twin Predication is thrown into the mix. +There exists room within the `svshape` instruction of [[sv/remap]] +to request some alternative Matrix mappings, and there is also +room within the reserved bits of `svremap` as well. + # RM Mode Concept: MVRM-2P-2S1D: -- 2.30.2