From: lkcl <lkcl@web>
Date: Sat, 20 Aug 2022 13:00:21 +0000 (+0100)
Subject: (no commit message)
X-Git-Tag: opf_rfc_ls005_v1~823
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=592005a6b721c34515023eca0c4c1aa847947e42;p=libreriscv.git

---

diff --git a/openpower/sv/normal.mdwn b/openpower/sv/normal.mdwn
index c674542c3..3bfc3e8c1 100644
--- a/openpower/sv/normal.mdwn
+++ b/openpower/sv/normal.mdwn
@@ -199,6 +199,22 @@ truncated based explicitly on whether a test fails.
 This because it is a precise test on which algorithms
 will rely.
 
+**Floating-point Exceptions**
+
+When Floating-point exceptions are enabled VL must be truncated at
+the point where the Exception appears not to have occurred. If `VLi`
+is set then VL must include the faulting element. Although very strongly
+discouraged the Exception Mode that permits Floating Point Exception
+notification to arrive too late to unwind is permitted
+(under protest, due it violating
+the otherwise 100% Deterministic nature of Data-dependent Fail-first).the
+
+**Use of lax FP Exception Notification Mode could result in parallel
+computations proceeding with invalid results that have to be explicitly
+detected, whereas with the strict FP Execption Mode enabled, FFirst
+truncates VL, allows subsequent parallel computation to avoid
+the exceptions entirely**
+
 ## Data-dependent fail-first on CR operations (crand etc)
 
 Operations that actually produce or alter CR Field as a result