+\documentclass[slidestop]{beamer}
+\usepackage{beamerthemesplit}
+\usepackage{graphics}
+\usepackage{pstricks}
+\usepackage{pgffor}
+\usepackage{listings}
+
+\graphicspath{{./}}
+
+\title{Data-Dependent-Fail-First}
+\author{Luke Kenneth Casson Leighton and Shriya Sharma}
+
+
+\begin{document}
+
+\frame{
+ \begin{center}
+ \huge{The Libre-SOC Hybrid 3D CPU}\\
+ \vspace{32pt}
+ \Large{Data-Dependent-Fail-First}\\
+
+ \vspace{24pt}
+ \Large{FOSDEM2024}\\
+ \vspace{16pt}
+ \large{Sponsored by NLnet's PET Programme}\\
+ \vspace{6pt}
+ \large{\today}
+ \end{center}
+}
+
+
+\frame{\frametitle{Why another SoC?}
+
+ \begin{itemize}
+ \item Intel Management Engine, Apple QA issues, Spectre\vspace{6pt}
+ \item Endless proprietary drivers, "simplest" solution: \\
+ License proprietary hard macros (with proprietary firmware)\\
+ Adversely affects product development cost\\
+ due to opaque driver bugs (Samsung S3C6410 / S5P100)
+ \vspace{6pt}
+ \item Alternative: Intel and Valve-Steam collaboration\\
+ "Most productive business meeting ever!"\\
+ https://tinyurl.com/valve-steam-intel
+ \vspace{6pt}
+ \item Because for 30 years I Always Wanted To Design A CPU
+ \vspace{6pt}
+ \item Ultimately it is a strategic \textit{business} objective to
+ develop entirely Libre hardware, firmware and drivers.
+ \end{itemize}
+}
+
+
+
+\frame{\frametitle{How can you help?}
+
+\vspace{5pt}
+
+ \begin{itemize}
+ \item Start here! https://libre-soc.org \\
+ Mailing lists https://lists.libre-soc.org \\
+ IRC Freenode libre-soc \\
+ etc. etc. (it's a Libre project, go figure) \\
+ \vspace{3pt}
+ \item Can I get paid? Yes! NLnet funded\\
+ See https://libre-soc.org/nlnet/\#faq \\
+ \vspace{3pt}
+ \item Also profit-sharing in any commercial ventures \\
+ \vspace{3pt}
+ \item How many opportunities to develop Libre SoCs exist,\\
+ and actually get paid for it?
+ \vspace{3pt}
+ \item I'm not a developer, how can I help?\\
+ - Plenty of research needed, artwork, website \\
+ - Help find customers and OEMs willing to commit (LOI)
+ \end{itemize}
+}
+
+
+
+\frame{\frametitle{What goes into a typical SoC?}
+\vspace{9pt}
+ \begin{itemize}
+ \item 15 to 20mm BGA package: 2.5 to 5 watt power consumption\\
+ heat sink normally not required (simplifies overall design)
+ \vspace{3pt}
+ \item Fully-integrated peripherals (not Northbridge/Southbridge)\\
+ USB, HDMI, RGB/TTL, SD/MMC, I2C, UART, SPI, GPIO etc. etc.
+ \vspace{3pt}
+ \item Built-in GPU (shared memory bus, 3rd party licensed) \vspace{3pt}
+ \item Built-in VPU (likewise, proprietary)\vspace{3pt}
+ \item Target price between \$2.50 and \$30 depending on market\\
+ Radically different from IBM POWER9 Core (200 Watt)
+ \vspace{3pt}
+ \item We're doing the same, just with a hybrid architecture.\\
+ CPU == GPU == VPU
+ \end{itemize}
+}
+
+
+
+\begin{frame}[fragile]
+\frametitle{Simple-V CMPI in a nutshell}
+
+\begin{semiverbatim}
+function op\_cmpi(BA, RA, SI) # cmpi not vector-cmpi!
+ (assuming you know power-isa)
+ int i, id=0, ira=0;
+ for (i = 0; i < VL; i++)
+ CR[BA+id] <= compare(ireg[RA+ira], SI);
+ if (reg\_is\_vectorised[BA] ) \{ id += 1; \}
+ if (reg\_is\_vectorised[RA]) \{ ira += 1; \}
+\end{semiverbatim}
+
+ \begin{itemize}
+ \item Above is oversimplified: predication etc. left out
+ \item Scalar-scalar and scalar-vector and vector-vector now all in one
+ \item OoO may choose to push CMPIs into instr. queue (v. busy!)
+ \end{itemize}
+\end{frame}
+
+
+\frame{\frametitle{Load/Store Fault-First}
+
+ \begin{itemize}
+ \item Problem: vector load and store can cause a page fault
+ \item Solution: a protocol that allows optional load/store
+ \item instruction \textit{requests} a number of elements
+ \item instruction \textit{informs} the number actually loaded
+ \item first element load/store is not optional (cannot fail)
+ \item ARM SVE: https://arxiv.org/pdf/1803.06185.pdf
+ \item more: wikipedia Vector processor page: Fault/Fail First
+ \vspace{10pt}
+ \item Load/Store is Memory to/from Register, what about
+ Register to Register?
+ \item Register-to-register: "Data-Dependent Fail-First."
+ \item Z80 LDIR: Mem-Register, CPIR: Register-Register
+ \end{itemize}
+}
+
+\begin{frame}[fragile]
+ \frametitle{Data-Dependent-Fail-First in a nutshell}
+
+ \begin{semiverbatim}
+function op\_cmpi(BA, RA, SI) # cmpi not vector-cmpi!
+int i, id=0, ira=0;
+for (i = 0; i < VL; i++)
+ CR[BA+id] <= compare(ireg[RA+ira], SI);
+ if (reg\_is\_vectorised[BA] ) \{ id += 1; \}
+ if (reg\_is\_vectorised[RA]) \{ ira += 1; \}
+ if test (CR[BA+id]) == FAIL: \{ VL = i + 1; break \}
+ \end{semiverbatim}
+
+ \begin{itemize}
+ \item Parallelism still perfectly possible
+ ("hold" writing results until sequential post-analysis
+ carried out. Best done with OoO)
+ \item VL truncation can be inclusive or exclusive
+ (include or exclude a NULL pointer or a
+ string-end character, or overflow result)
+ \item \textit{Truncation can be to zero Vector Length}
+ \end{itemize}
+\end{frame}
+
+\frame{\frametitle{Power ISA v3.1 vstribr}
+
+ \lstinputlisting[language={}]{vstribr.txt}
+
+ \begin{itemize}
+ \item ironically this hard-coded instruction is
+ identical to general-purpose Simple-V DD-FFirst...
+ \end{itemize}
+
+}Po
+
+\frame{\frametitle{maxloc}
+ \begin{itemize}
+ \item "TODO
+ \end{itemize}
+}
+
+\frame{\frametitle{Pospopcount}
+
+ \begin{itemize}
+ \item Positional popcount adds up the totals of each bit set to 1 in each bit-position, of an array of input values.
+ \item Notoriously difficult to do in SIMD assembler: typically 550 lines
+
+ \end{itemize}
+
+ \lstinputlisting[language={}]{pospopcount.c}
+
+}
+
+\frame{\frametitle{Pospopcount}
+
+ \begin{center}
+ \includegraphics[width=0.6\textwidth]{pospopcount.png}
+ \end{center}
+ \begin{itemize}
+ \item The challenge is to perform an appropriate transpose of the data (the CPU can only work on registers, horizontally),
+ in blocks that suit the processor and the ISA capacity.
+
+
+ \end{itemize}
+}
+
+\frame{\frametitle{Pospopcount}
+
+ \begin{center}
+ \includegraphics[width=0.6\textwidth]{array_popcnt.png}
+ \end{center}
+
+ \begin{itemize}
+
+ \item The draft gbbd instruction implements the transpose (shown above),
+ preparing the data to use the standard popcount instruction.
+
+
+ \end{itemize}
+
+}
+
+\frame{\frametitle{Pospopcount.s}
+
+
+\lstinputlisting[language={}]{pospopcount.s}
+
+}
+
+
+\frame{\frametitle{strncpy}
+
+ \lstinputlisting[language={}]{strncpy.c}
+ \begin{itemize}
+ \item "TODO
+ \end{itemize}
+}
+
+
+
+\frame{\frametitle{strncpy assembler}
+
+\lstinputlisting[language={}]{strncpy.s}
+
+}
+
+\frame{\frametitle{linked-list walking}
+ \begin{itemize}
+ \item "TODO
+ \end{itemize}
+}
+\frame{\frametitle{Summary}
+
+ \begin{itemize}
+ \item Goal is to create a mass-volume low-power embedded SoC suitable
+ for use in netbooks, chromebooks, tablets, smartphones, IoT SBCs.
+ \item No way we could implement a project of this magnitude without
+ nmigen (being able to use python OO to HDL)
+ \item Collaboration with OpenPOWER Foundation and Members absolutely
+ essential. No short-cuts. Standards to be developed and ratified
+ so that everyone benefits.
+ \item Riding the wave of huge stability of OpenPOWER ecosystem
+ \item Greatly simplified open 3D and Video drivers reduces product
+ development costs for customers
+ \item It also happens to be fascinating, deeply rewarding technically
+ challenging, and funded by NLnet
+
+ \end{itemize}
+}
+
+
+\frame{
+ \begin{center}
+ {\Huge The end\vspace{12pt}\\
+ Thank you\vspace{12pt}\\
+ Questions?\vspace{12pt}
+ }
+ \end{center}
+
+ \begin{itemize}
+ \item Discussion: http://lists.libre-soc.org
+ \item Freenode IRC \#libre-soc
+ \item http://libre-soc.org/
+ \item http://nlnet.nl/PET
+ \item https://libre-soc.org/nlnet/\#faq
+ \end{itemize}
+}
+
+
+\end{document}