From: Jacob Lifshay <programmerjake@gmail.com>
Date: Wed, 12 Apr 2023 20:37:47 +0000 (-0700)
Subject: shift-add is useful even with LD-ST-indexed-shifted
X-Git-Tag: opf_rfc_ls010_v1~43
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=9a4dec12f0d7f5d47291925094f5dcb187fb965a;p=libreriscv.git

shift-add is useful even with LD-ST-indexed-shifted
---

diff --git a/openpower/sv/rfc/ls004.mdwn b/openpower/sv/rfc/ls004.mdwn
index fe8c1513e..24c35769e 100644
--- a/openpower/sv/rfc/ls004.mdwn
+++ b/openpower/sv/rfc/ls004.mdwn
@@ -73,6 +73,10 @@ add shift-and-add.  Replaces a pair of explicit instructions in hot-loops.
    as the second operand is constrained to lower 32-bits
    and zero-extended.
 3. Both are 2-in 1-out instructions.
+4. shift-add operations are present in both x86 and aarch64,
+  since they are useful for both general arithmetic and for
+  computing addresses even when not immediately followed
+  with a load/store.
 
 TODO: signed 32-bit shift-and-add should be added, this needs to be addressed
 before submitting the RFC: <https://bugs.libre-soc.org/show_bug.cgi?id=996>