From: lkcl <lkcl@web>
Date: Tue, 19 Apr 2022 17:17:35 +0000 (+0100)
Subject: (no commit message)
X-Git-Tag: opf_rfc_ls005_v1~2694
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=416c5401fcf4ca566d9ea74b826d2eeb28d58dce;p=libreriscv.git

---

diff --git a/openpower/sv/biginteger.mdwn b/openpower/sv/biginteger.mdwn
index 670c8dc24..9a7fb0388 100644
--- a/openpower/sv/biginteger.mdwn
+++ b/openpower/sv/biginteger.mdwn
@@ -90,4 +90,15 @@ purpose.
     RT = lowerhalf(product)
     RC = upperhalf(product)
 
-Successive iterations effectively use RC as a 64-bit carry.
+Successive iterations effectively use RC as a 64-bit carry, and
+as noted by Intel in their notes on mulx,
+RA*RB+RC+RD cannot overflow, so does not require
+setting an additional CA flag.
+
+## Divide
+
+The simplest implementation of big-int divide is the standard textbook
+"Long Division", set with RADIX 64 instead of Base 10. Donald Knuth's
+Algorithm D performs estimates which, if wrong, are compensated for
+afterwards.  Essentially however there are three phases:
+