\usepackage{sectsty}
\usepackage{appendix}
\usepackage{graphicx}
+\usepackage[firstpage]{draftwatermark}
+\usepackage[printonlyused,withpage]{acronym}
+\usepackage{float}
+\usepackage{url}
+\usepackage[useregional]{datetime2}
\usepackage{anyfontsize}
\usepackage{ifxetex,ifluatex}
\usepackage{fixltx2e} % provides \textsubscript
}{}
\PassOptionsToPackage{hyphens}{url} % url is loaded by hyperref
\usepackage[unicode=true]{hyperref}
-\hypersetup{
- pdfborder={0 0 0},
+\hypersetup{colorlinks=true,
+ linkcolor=blue,
+ filecolor=cyan,
+ urlcolor=magenta,
breaklinks=true}
\usepackage[margin=0.9in]{geometry}
\usepackage{color}
\usepackage{fancyvrb}
\newcommand{\VerbBar}{|}
\newcommand{\VERB}{\Verb[commandchars=\\\{\}]}
-\DefineVerbatimEnvironment{Highlighting}{Verbatim}{commandchars=\\\{\}}
+\DefineVerbatimEnvironment{Highlighting}{Verbatim}{commandchars=\\\{\},xleftmargin=5mm}
% Add ',fontsize=\small' for more characters per line
\newenvironment{Shaded}{}{}
\newcommand{\KeywordTok}[1]{\textcolor[rgb]{0.00,0.44,0.13}{\textbf{#1}}}
\newcommand{\AlertTok}[1]{\textcolor[rgb]{1.00,0.00,0.00}{\textbf{#1}}}
\newcommand{\ErrorTok}[1]{\textcolor[rgb]{1.00,0.00,0.00}{\textbf{#1}}}
\newcommand{\NormalTok}[1]{#1}
+
+% these come from:
+% https://gist.github.com/bgeron/72ebbacf5930537022079d9953f15713
+\usepackage{newunicodechar}
+\newcommand\DeclareUnicodeInv[2]{\DeclareUnicodeCharacter{#2}{#1}}
+
+\DeclareUnicodeCharacter{03A0}{\ensuremath{\Pi}}
+\DeclareUnicodeCharacter{2208}{\ensuremath{\in}}
+\DeclareUnicodeCharacter{03C0}{\ensuremath{\pi}}
+\DeclareUnicodeCharacter{221A}{$\sqrt{}$}
+\DeclareUnicodeCharacter{221B}{$\sqrt[3]{}$}
+\DeclareUnicodeInv{\ensuremath{\mathbb{Z}}}{2124}
+
+% indent all verbatim
+\catcode`\@=11
+\let \saveverbatime \@xverbatim
+\def \@xverbatim {\leftskip = 1cm\relax\saveverbatime}
+\catcode`\@=12
+
\usepackage{longtable,booktabs}
% Fix footnotes in tables (requires footnote package)
\IfFileExists{footnote.sty}{\usepackage{footnote}\makesavenoteenv{long
\def\fps@figure{htbp}
\makeatother
+% graphics path for primer
+\graphicspath{ {svp64-primer/img/} }
\date{}
\chapter*{Preamble}
\addcontentsline{toc}{chapter}{Preamble} \markboth{INTRODUCTION}{}
+\textbf{Last modified date: \today}
+
This document is an auto-generated version of the Draft SVP64
Specification available at
https://git.libre-soc.org/?p=libreriscv.git;a=blob;f=openpower/Makefile;hb=HEAD
\end{verbatim}
+by executing the following commands:
+
+\begin{verbatim}
+ git clone https://git.libre-soc.org/git/libreriscv.git libresoc
+ cd libresoc/libresoc/openpower
+ make pdf
+\end{verbatim}
+
Simple-V Cray-style Vectors have been developed by the Libre-SOC Team,
sponsored by the NLnet Foundation and NGI POINTER under
EU Grants 871528 and 957073.
Process. Funding from NLnet, through their Privacy and Enhanced Trust
Programme, requires full transparency.
+As this document is under continuous rapid revision please check frequently
+at:
+
+\begin{verbatim}
+ https://ftp.libre-soc.org/simple_v_spec.pdf
+\end{verbatim}
+
+\subsection*{Contacts}
+For questions, comments, and clarification, please contact the following:
+\begin{itemize}
+ \itemsep -0.3em
+ \item Libre-SOC ISA Dev Mailing List - libre-soc-isa@lists.libre-soc.org
+ \item Luke Kenneth Casson Leighton - Libre-SOC team lead and Red
+ Semiconductor Ltd Director - lkcl@lkcl.net
+ \item David Calderwood - Red Semiconductor Ltd Director -
+ djac@calderwoodhan.com
+ \item Toshaan Bharvani - OpenPOWER Foundation Technical Chair, VanTosh
+ Director - toshaan@vantosh.com
+ \item Konstantinos Margaritis - Engineer and Founder of VectorCamp, writing optimised assembler for a number of SIMD/Vector ISAs - konstantinos@vectorcamp.gr
+ \item Dmitry Selyutin - Libre-SOC engineer, working on binutils SVP64 assembler - ghostmansd@gmail.com
+ \item Jacob Lifshay - Libre-SOC engineer, CPU arch and verification - programmerjake@gmail.com
+ \item Cesar Strauss - Libre-SOC engineer, CPU arch and verification - cestrauss@gmail.com
+ \item Andrey Miroshnikov - Libre-SOC engineer, assisting with documentation - andrey@technepisteme.xyz
+\end{itemize}
+
+\newpage
+\subsection*{Executive Summary}
+\hypertarget{svux2fexecutive_summary}{}
+\input{tex_out/executive_summary.tex}
+
+\newpage
+\begin{landscape}
+\addcontentsline{toc}{chapter}{Comparison Table} \markboth{INTRODUCTION}{}
+\hypertarget{svux2fcomparison_table}{}
+{
+\fontsize{6}{8}\selectfont
+\input{tex_out/comparison_table.tex}
+}
+\end{landscape}
+
+\part{Scalable Vectors Primer}
+\input{svp64-primer/acronyms}
+%\chapter*{Executive Summary}
+\include{svp64-primer/summary}
+\bibliography{svp64-primer/references}
+\bibliographystyle{ieeetr}
+
\tableofcontents
-\part{Scalable Vectors}
+% Part II
+\part{Scalable Vectors for the Power ISA}
+
+\chapter{Fields and Forms}
+\hypertarget{svux2ffields}{}
+\input{tex_out/fields.tex}
\chapter{Scalable Vectors for the Power ISA}
\hypertarget{svux2fscalvecpowisa}{}
\hypertarget{SVux7csv}{}
\begin{appendices}
\chapter{SVP64 Appendix}\hypertarget{svp64ux2fappendix}{}
+\hypertarget{svux2fsvp64ux2fappendix}{}
\input{tex_out/svp64_appendix.tex}
\chapter{SVP64 Quirks}\hypertarget{svux2fsvp64_quirks}{}
\input{tex_out/svp64_quirks.tex}
+\chapter{REMAP algorithms}\hypertarget{svux2fremapux2fappendix}{}
+\input{tex_out/remap_appendix.tex}
\chapter{Simple-V pseudocode}\hypertarget{svux2fpseudocode_simplev}{}
\input{tex_out/pseudocode_simplev.tex}
+\chapter{Simple-V Analysis}\hypertarget{svux2fsv_analysis}{}
+\input{tex_out/sv_analysis.tex}
+
\chapter{SVP64 Augmentation Table}\hypertarget{opcode_regs_deduped}{}
\begin{landscape}
{
\input{tex_out/opcode_regs_deduped.tex}
}
\end{landscape}
+
\end{appendices}
+% Part III
\part{Scalar Instructions}
-\chapter{Vector Assist ops}\hypertarget{svux2fvector_ops}{}
+\chapter*{Preamble}{}
+
+As explained in the Simple-V introduction
+these are all intentionally and specifically Scalar instructions.
+Each section is free-standing, has no connection, dependence or
+relationship to any other section, including no direct critical dependence
+either way on Simple-V.
+They have with almost no exceptions been specifically crafted to
+have a justification for their inclusion in the Power ISA as Scalar
+instructions purely on their own merit.
+
+\begin{itemize}
+ \item The biginteger multiply-and-add instruction is similar
+ to Intel's mulx in that it produces a pair of results.
+ \item Javascript(tm) rounding is present in ARM as fjcvtzs
+ and would save an astounding 35 instructions with 5 branches.
+ \item Whilst there exist CR bit manipulation and copying
+ instructions there are no CR Field manipulation instructions,
+ putting pressure on GPRs if several CR fits need to be analysed.
+ \item one single instruction, bmask, is proposed that covers
+ the whole of x86 BMI1 and AMD TBM, combined, and provides more.
+\end{itemize}
+
+All of these have nothing to do with Simple-V at all: they make
+the Power ISA better at modern general-purpose compute, bringing
+it up-to-date.
+
+That said: by a wonderful coincidence, should they be included, then
+Simple-V's capabilities increase significantly. For example the CRweird
+instructions combined with the bitmanip instructions, alongside
+Vectorised Rc=1 turn CR Fields into
+extremely powerful Predicate masks. bmask not only
+covers the BMI and TBM instructions of Intel and AMD it also
+includes the RVV set-before-first and set-after-first instructions.
+
+The clean and clear separation between Vectorisation Prefix and Scalar
+Suffix is what makes it possible for both Scalar-only and Scalable-Vectors
+to benefit. It also makes proposal much easier, as there is no
+inter-dependence.
+
+It is however important to note that the rationale for these instructions
+comes from a more general-purpose modern computing paradigm that is
+outside of IBM's much more focussed and specialist traditional customer
+base. We deeply respect IBM's curator role of the Power ISA of the past 25
+years as much as we appreciate their courage in transferring that role
+to the OpenPOWER Foundation ISA Working Group.
+
+\chapter{SV Vector-assist Scalar ops}\hypertarget{svux2fvector_ops}{}
\input{tex_out/vector_ops.tex}
\chapter{CR Weird ops}\hypertarget{svux2fcr_int_predication}{}
+\hypertarget{cr_int_predication}{}
\input{tex_out/cr_int_predication.tex}
\chapter{Bitmanip ops}\hypertarget{svux2fbitmanip}{}
\input{tex_out/bitmanip.tex}
-\chapter{FP/Integer conversion ops}\hypertarget{svux2fint_fp_mv}{}
+\chapter{FP/Int Conversion ops}\hypertarget{svux2fint_fp_mv}{}
\input{tex_out/int_fp_mv.tex}
\chapter{FP Class ops}\hypertarget{svux2ffclass}{}
\input{tex_out/fclass.tex}
-\chapter{Audio/Video ops}\hypertarget{svux2fav_opcodes}{}
+\chapter{Audio and Video Opcodes}\hypertarget{svux2fav_opcodes}{}
+\hypertarget{av_opcodes}{}
\input{tex_out/av_opcodes.tex}
\chapter{Big Integer}\hypertarget{svux2fbiginteger}{}
\input{tex_out/big_integer.tex}
+\chapter{Transcendentals}\hypertarget{transcendentals}{}
+\input{tex_out/transcendentals.tex}
+%\chapter{Acquire/Release Atomic Memory}\hypertarget{atomics}{}
+%\input{tex_out/atomics.tex}
\begin{appendices}
\chapter{Big Integer Analysis}\hypertarget{svux2fbigintegerux2fanalysis}{}
\input{tex_out/big_integer_analysis.tex}
-\chapter{Simple-V FP pseudocode}\hypertarget{svux2fpseudocode_svfparith}{}
+\chapter{Bitmanip pseudocode}\hypertarget{svux2fpseudocode_bitmanip}{}
+\input{tex_out/pseudocode_bitmanip.tex}
+\chapter{Floating Point pseudocode}\hypertarget{isaux2fsvfparith}{}
\input{tex_out/pseudocode_svfparith.tex}
-\chapter{Simple-V Fixed Point pseudocode}
-\hypertarget{svux2fpseudocode_svfixedarith}{}
+\chapter{Fixed Point pseudocode}
+\hypertarget{isaux2fsvfixedarith}{}
\input{tex_out/pseudocode_svfixedarith.tex}
\end{appendices}
+% Part IV
\part{Scalar Power ISA pseudocode}
+\backmatter % temporary fix for too many appenfices
+%\setcounter{chapter}{0}
+%\renewcommand{\thechapter}{\Alph{chapter}}
+
+\chapter*{Preamble}
+\addcontentsline{toc}{chapter}{Preamble} \markboth{INTRODUCTION}{}
This section contains updated pseudocode from the Power ISA Specification
-v3.0B to be executable. Several bugfixes have been created as a direct
-result. A Formal Correctness Proof Research Paper written by Boris
+v3.0B to be executable. Several bugfixes in Power ISA v3.0B have been
+found and reported as a direct result due to actually running the
+pseudocode as executable code in a Simulator.
+A Formal Correctness Proof Research Paper written by Boris
Shingarov.
+Additionally, with SVP64 performing element-width over-rides it is the
+\textit{Scalar} pseudocode that needs adapting to variable-length
+(\textbf{XLEN}). Maintaining duplicate identical copies in every
+respect \textit{except} for an XLEN as part of the Simple-V Specification
+is completely pointless and a waste of time: the updates to include
+XLEN need to be part
+of the Scalar Power ISA Specification. This has the added benefit
+that it makes life much easier for 32-bit implementors, and has an
+additional benefit of making it possible for the Scalar Power ISA
+to extend to 128-bit in future (like RV128).
+
\begin{appendices}
+\chapter{Binary Coded Decimal pseudocode}
+\hypertarget{svux2fpseudocode_bcd}{}
+\input{tex_out/pseudocode_bcd.tex}
+\chapter{Branch pseudocode}
+\hypertarget{openpowerux2fisaux2fbranch}{}
+\hypertarget{svux2fpseudocode_branch}{}
+\input{tex_out/pseudocode_branch.tex}
+\chapter{Fixed Point Compare pseudocode}
+\hypertarget{svux2fpseudocode_comparefixed}{}
+\input{tex_out/pseudocode_comparefixed.tex}
+\chapter{Condition Register pseudocode}
+\hypertarget{svux2fpseudocode_condition}{}
+\input{tex_out/pseudocode_condition.tex}
+
\chapter{Fixed Point Arithmetic pseudocode}
\hypertarget{svux2fpseudocode_fixedarith}{}
\input{tex_out/pseudocode_fixedarith.tex}
+\chapter{Fixed Point Load pseudocode}
+\hypertarget{svux2fpseudocode_fixedload}{}
+\input{tex_out/pseudocode_fixedload.tex}
\chapter{Fixed Point Logical pseudocode}
\hypertarget{svux2fpseudocode_fixedlogical}{}
\input{tex_out/pseudocode_fixedlogical.tex}
+\chapter{Fixed Point Rotate pseudocode}
+\hypertarget{svux2fpseudocode_fixedshift}{}
+\input{tex_out/pseudocode_fixedshift.tex}
+
+\chapter{Fixed Point Store pseudocode}
+\hypertarget{svux2fpseudocode_fixedstore}{}
+\input{tex_out/pseudocode_fixedstore.tex}
+\chapter{Fixed Point Trap pseudocode}
+\hypertarget{svux2fpseudocode_fixedtrap}{}
+\input{tex_out/pseudocode_fixedtrap.tex}
+\chapter{Special Purpose Register pseudocode}
+\hypertarget{svux2fpseudocode_sprset}{}
+\input{tex_out/pseudocode_sprset.tex}
+\chapter{String Load/Store pseudocode}
+\hypertarget{svux2fpseudocode_stringldst}{}
+\input{tex_out/pseudocode_stringldst.tex}
+\chapter{System Call pseudocode}
+\hypertarget{svux2fpseudocode_system}{}
+\input{tex_out/pseudocode_system.tex}
+
+\chapter{Floating Point Load pseudocode}
+\hypertarget{svux2fpseudocode_fpload}{}
+\input{tex_out/pseudocode_fpload.tex}
+\chapter{Floating Point Store pseudocode}
+\hypertarget{svux2fpseudocode_fpstore}{}
+\input{tex_out/pseudocode_fpstore.tex}
+\chapter{Floating Point Move pseudocode}
+\hypertarget{svux2fpseudocode_fpmove}{}
+\input{tex_out/pseudocode_fpmove.tex}
+\chapter{Floating Point Arithmetic pseudocode}
+\hypertarget{svux2fpseudocode_fparith}{}
+\input{tex_out/pseudocode_fparith.tex}
+\chapter{Floating Point Integer Conversion pseudocode}
+\hypertarget{svux2fpseudocode_fpcvt}{}
+\input{tex_out/pseudocode_fpcvt.tex}
+
\end{appendices}