From 781a34a4ee716e3b7b585ca694874b3e5cd605d8 Mon Sep 17 00:00:00 2001 From: lkcl Date: Wed, 30 Oct 2019 01:49:49 +0000 Subject: [PATCH] --- openpower.mdwn | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/openpower.mdwn b/openpower.mdwn index ccf8b1d28..200d924c3 100644 --- a/openpower.mdwn +++ b/openpower.mdwn @@ -17,7 +17,7 @@ Hot loops contain significant instruction count, really need new c++11 atomics. # FP16 -Doesn't exist in Power (does - as VLE?), need to work out suitable opcodes, basically means duplicating the entire range of FP32/64 ops, symmetrically. +Doesn't exist in Power, need to work out suitable opcodes, basically means duplicating the entire range of FP32/64 ops, symmetrically. Usually done with a fmt field, 2 bit, last one is FP128 @@ -29,7 +29,7 @@ This will allow extending ISA (see ISAMUX/NS) in a clean fashion # Compressed, 48, 64, VBLOCK -TODO investigate Power VLE +TODO investigate Power VLE (Freescale doc Ref 314-68105) Under Esc Seq, move mulli, twi, tdi out of major OP000 then use the entire row, 2 bits instead of 3. -- 2.30.2