shakti/m_class/libre_riscv_chennai_2018.tex

   1 \documentclass[slidestop]{beamer}
   2 \usepackage{beamerthemesplit}
   3 \usepackage{graphics}
   4 \usepackage{pstricks}
   5
   6 \title{Commercial Libre-RISCV SoC}
   7 \author{Luke Kenneth Casson Leighton}
   8
   9
  10 \begin{document}
  11
  12 \frame{
  13    \begin{center}
  14     \huge{Designing a Commercial Libre RISC-V SoC}\\
  15     \vspace{32pt}
  16     \Large{Ethical Strategic Leveraging of the benefits}\\
  17     \Large{of Libre and Open SW/HW}\\
  18     \Large{for pure unadulterated Commercial gain}\\
  19     \vspace{24pt}
  20     \Large{Chennai 9th RISC-V Workshop}\\
  21     \vspace{16pt}
  22     \large{\today}
  23   \end{center}
  24 }
  25
  26
  27 \frame{\frametitle{Credits and Acknowledgements}
  28
  29  \begin{itemize}
  30    \item The Designers of RISC-V\vspace{15pt}
  31    \item The Shakti Group\vspace{15pt}
  32    \item Prof. G S Madhusudan\vspace{15pt}
  33    \item Neel Gala\vspace{15pt}
  34    \item Rishabh Jain\vspace{15pt}
  35   \end{itemize}
  36 }
  37
  38
  39 \frame{\frametitle{Why, How, What?}
  40
  41  \begin{itemize}
  42    \item Why? Because these days it's just not necessary to
  43          make [un]ethical compromises in order to make a profitable,
  44          desirable mass-volume product\\
  45          {\it (There's enough companies doing that: where it's got us??)}
  46    \item How? By leveraging the long-establised strategic cost and
  47          maintenance benefits of libre-licensed software (and
  48          HDL) and
  49          {\it making sure that the people who provide it are
  50          financially rewarded}.  Also by empowering diverse team
  51          collaboration
  52    \item What? A 2.5ghz RISC-V 64-bit SoC that has
  53                  a 3D Embedded GPU, 1080p Video decode, and interfaces
  54                  to make it attractive for use in tablets, netbooks, industrial
  55                  embedded and more.  22nm or less, under 400 pins, under USD \$4.\\
  56   {\it All sounds obvious... but is it practical and achievable?}
  57   \end{itemize}
  58 }
  59
  60
  61 \frame{\frametitle{Definitions}
  62
  63  \begin{itemize}
  64    \item {\bf Business}: the provision of a service and being
  65                  commensurately financially rewarded for doing so
  66    \item {\bf Spongeing}: the provision of a service and being
  67                   taken advantage of for doing so {\it (cf: Professor Yunus)}
  68         \item {\bf An ethical act}: an act that increases truth,
  69                   love, awareness or creativity for one or more people
  70                   (including yourself), {\it without} reducing those
  71                   same four qualities {\it for anyone}
  72         \item {\bf The Four Freedoms}: the rights and guarantees
  73                   associated with and embedded within GNU Licenses {\it (cf: FSF)}
  74   \end{itemize}
  75   {\it Is it possible to ethically do business and respect the
  76    Four Freedoms? That's where it gets interesting, as there are
  77    even cases where the Four Freedoms are unethical.  Note: google's
  78    former motto "don't be evil" is clearly (unintentionally) unethical}
  79 }
  80
  81
  82 \frame{\frametitle{Does what we want already exist? Surely this is nonsense!}
  83  \begin{center}
  84   \includegraphics[height=2.4in]{nolibresocs.jpg}\\
  85   {\bf Analysis of SoCs over the past 7+ years (answer: no)}
  86  \end{center}
  87 }
  88
  89
  90 \frame{\frametitle{Breakdown of non-existence of fully-Libre SoCs}
  91
  92  \begin{itemize}
  93    \item {\bf iMX6}: Libre bootable, Vivante 3D GPU (libre etnaviv)
  94             but proprietary VPU (and a power-hungry Cortex A9)
  95         \item {\bf Allwinner SoCs}: mostly Libre bootable,
  96               VPU reverse engineered; GPU: MALI or PowerVR (i.e. proprietary)
  97         \item {\bf Rockchip SoCs}: good but using MALI or PowerVR.
  98         \item {\bf TI OMAP}: good but using PowerVR.  and expensive.
  99         \item {\bf Samsung}: good but using MALI.
 100         \item {\bf Ingenic jz4775}: GREAT! performance
 101                   sucks (1ghz MIPS32).
 102         \item {\bf Broadcom SoCs}: Cartelled. and boots from the GPU
 103   \end{itemize}
 104   {\it Basically there does not exist one single commercial SoC that
 105    provides full source code for all functions (CPU, GPU, VPU)
 106    with modern performance. Which is kinda bizarre if you think about it}
 107 }
 108
 109
 110 \frame{\frametitle{What would a good (Libre) boring, mundane SoC have?}
 111
 112  \begin{itemize}
 113    \item Cover a lot of different scenarios (embedded, tablets, industrial,
 114          netbooks, crypto-currency mining).
 115         \item Decent performance with high efficiency.  RISC-V: 40 \%
 116                   more efficient than ARM / Intel.  Shakti a good
 117               candidate: 2.5ghz and 120mW per core @ 22nm.
 118         \item 1080p video: y'all gotta watch cute kittens on youtube, right?
 119         \item 3D GPU: y'all gotta play Angri Burds, right? (or Minecraft)
 120         \item No spying back-door co-processors (to steal crypto-wallets)
 121         \item No Spectres, no Meltdowns.
 122   \end{itemize}
 123   {\it Basically quite boring and mundane.  No Monster Performance,
 124    no AI stuff, no special sauce. Just a plain-old SoC,
 125    40\% more power efficient than ARM/Intel,
 126    and not spying on end-users, that's all}
 127 }
 128
 129
 130 \frame{\frametitle{How on earth does an ethical Libre SoC make money???}
 131
 132  \begin{itemize}
 133    \item Simple answer: Mask Rights.
 134    \item Without Mask Rights: by having a desirable
 135          product, and packaging it for a customer (i.e. by being a middle-man
 136          a service is still being provided for which payment etc. etc.)
 137    \item Without a desirable product or customer(s): err... you don't.\\
 138              (cf: definition of Business)
 139    \item By not having high NREs (leveraging back-to-back deals,
 140              and helping others fulfil their needs and goals)
 141   \end{itemize}
 142   {\it Detachment from the goal also helps. If someone else makes this
 143    product then GREAT! I can go do something else}\\
 144    \vspace{4pt}
 145   {\bf Main point: please do not automatically assume Ethical and Libre is
 146    non-commercial. It's not nice, and it's not helping }
 147
 148 }
 149
 150 \frame{\frametitle{Things wot are "off-limits"}
 151
 152  \begin{itemize}
 153    \item Customer entrapment (through proprietary software).\\
 154          Strong business case for not entrapping customers:\\
 155              https://tinyurl.com/most-productive-meeting-ever
 156    \item Funding, endorsing, supporting or empowering unethical
 157          Companies, Organisations, Cartels and Individuals.\\
 158              (cf: definition of an ethical act).
 159         \item Being totally inflexible / unrealistic.  Goals have
 160              to be met: it's no good being an idiot about that. e.g. if
 161              a Libre 3D GPU really can't be made, use Vivante GC800
 162              (with etnaviv).
 163   \end{itemize}
 164   {\it Still no real show-stoppers to making money (or product):
 165     it's just slightly harder, that's all.  Ultimately it's about
 166     confidence. }
 167 }
 168
 169
 170 \frame{\frametitle{Interfaces, Block Diagram, of the Libre-RISCV SoC}
 171  \begin{center}
 172   \includegraphics[height=2.1in]{../shakti_libre_riscv.jpg}\\
 173   {\bf Separate Power Domains for GPIO banks, Variable voltages
 174     required, low-power sleep states etc.  Quite involved}
 175  \end{center}
 176 }
 177
 178
 179 \frame{\frametitle{Hardware / Development Complexity Comparison}
 180
 181  \begin{itemize}
 182    \item {\bf Server}: relatively easy. PCIe, RapidIO, XAUI, SATA, GbE, 10GE,
 183                  DDR3/4 (or HMC) etc. etc. No multiplexing: all interfaces dedicated
 184                  and high-speed differential pairs.
 185    \item {\bf Desktop}: really just a variant of Server.
 186              Graphics is a PCIe Card (except if integrated).  Peripherals
 187              often done in dedicated external ICs ("Southbridge" concept)
 188    \item {\bf Embedded}: also pretty easy.  Really needs a pinmux.  Low clock
 189          rate, low power mode.  e.g. SiFive Freedom U310.
 190    \item {\bf Mobile}: HARD. Performance/Watt matters $=>$ variable core
 191                  voltage domains {\it per core}.  Number of pins matters (affects
 192                  yield and package cost).  Cost
 193                  matters.  Pinmux critical.
 194   \end{itemize}
 195   {\it Bottom line: Mobile-class processors are challenging!}
 196 }
 197
 198
 199 \frame{\frametitle{Proprietary vs Libre-licensed Interface HDL}
 200
 201  \begin{itemize}
 202    \item DDR3/4: challenging! \$1m for single-use, single instance.\\
 203          Symbiotic EDA: \$600k for PHY; CERN developed a Controller\\
 204          http://libre-riscv.org/shakti/m\_class/DDR/
 205    \item HyperRAM (JEDEC xSPI): lower risk than DDR3/4\\
 206            http://libre-riscv.org/shakti/m\_class/HyperRAM/
 207    \item RGMII: several available (saves \$50k)\\
 208            http://libre-riscv.org/shakti/m\_class/RGMII/
 209    \item UART, SPI, I2C, PWM, SD/MMC: all libre (except eMMC).
 210    \item Shakti Group has FlexBus, QuadSPI, SRAM, many more.
 211    \item RGB/TTL: R. Herveille (SSD2828, SN75LVDS83b, TFP410a)
 212   \end{itemize}
 213   {\it Basically there's no compelling reason to spend vast sums
 214    on proprietary HDL.  Sorry Cadence / Mentor / Synopsis / whoever}
 215 }
 216
 217
 218 \frame{\frametitle{Challenging Stuff [1] - Memory Interfaces}
 219
 220  \begin{itemize}
 221    \item DDR3/4 PHYs are analog and very high speed.
 222                    Impedance training.  Extreme timing tolerances on parallel buses.\\
 223                    No surprise they cost USD \$1m and above.
 224    \item Symbiotic EDA will do (Libre) PHY layout for USD \$300k,
 225              time to completion for chosen geometry: 8-12 months.
 226   \end{itemize}
 227    {\it Silicon-proven but still risky.  What are the alternatives?}
 228    \vspace{4pt}
 229  \begin{itemize}
 230    \item 133mhz 32-bit SDRAM (um...) maybe even FlexBus?
 231    \item HyperRAM (aka JEDEC xSPI) 8-bit SPI 166mhz or DDR-300.\\
 232            300mbyte/sec for only 13 wires, not bad!  (We'll take several)\\
 233            http://libre-riscv.org/shakti/m\_class/HyperRAM/
 234    \item HMC: insanely fast, very low power.  OpenHMC (LGPL)
 235            https://opencores.org/project/openhmc
 236   \end{itemize}
 237 }
 238
 239
 240 \frame{\frametitle{Challenging Stuff [2] - Video Decode Engine}
 241
 242  \begin{itemize}
 243    \item Richard Herveille's Video Core Blocks\\
 244             https://opencores.org/project/video\_systems
 245    \item Symbiotic EDA MP4 decoder in FPGA
 246    \item H.264 seems to have been done...\\
 247          https://github.com/adsc-hls/synthesizable\_h264
 248    \item Really needs SIMD (or better, not-SIMD)\\
 249          {http://libre-riscv.org/simple\_v\_extension/}
 250    \item Definitely needs xBitManip (parallelised by Simple-V)\\
 251          https://github.com/cliffordwolf/xbitmanip
 252   \end{itemize}
 253    {\it SIMD is insane. $O(N^6)$ opcode proliferation.  See\\
 254      https://www.sigarch.org/simd-instructions-considered-harmful/ \\
 255      (1): P-Ext designed for Audio. (2): Investigate RI5CY's SIMD
 256    }
 257 }
 258
 259
 260 \frame{\frametitle{Challenging Stuff [3] - Libre 3D GPU.  Sigh.}
 261
 262  \begin{itemize}
 263    \item Actual requirements quite modest: 30MP/s 100MT/s 5GFLOPS
 264          but power/area is crucial ($2mm^2$ @ 40nm)
 265    \item Nyuzi, MIAOW, GPLGPU (Number Nine), OGP.
 266    \item Nyuzi based on Larrabee. Jeff Bush really helpful.
 267    \item MIAOW is an OpenCL engine.  GPLGPU is fixed-function
 268    \item Nyuzi lessons: Software-only rendering not enough.
 269              Getting through L1 cache takes most power. Fixed functions
 270              such as parallel FP-Quad to ARGB Pixel, and Z-Buffer
 271              needed.
 272    \item Fallback is GC800 (\$250k) {\it contact me if you can do better!}
 273   \end{itemize}
 274    {\it Jacob Bachmeyer's Cache-control proposal turns L1 Cache into
 275    scratchpad RAM.  RVV is just too heavy (sorry!), Simple-V much
 276    more light-weight and flexible ($O(1)$ ISA proliferation)
 277    }
 278 }
 279
 280
 281 \frame{\frametitle{TODO}
 282
 283  \begin{itemize}
 284    \item TODO\vspace{8pt}
 285   \end{itemize}
 286 }
 287
 288
 289 \frame{\frametitle{Summary}
 290
 291  \begin{itemize}
 292    \item Making a commercially-desirable SoC is neither academically
 293          nor standard-investor sexy!  No AI. Boring. zzzz
 294    \item Luckily there is an anonymous sponsor who needs an SoC that
 295              doesn't exist (who knows the commercial benefits of Libre)
 296    \item Shakti Group know the benefits (cost, sovereignty) of a Libre
 297          Mobile-Class SoC as well (No spying on India citizens!)
 298    \item A Libre GPU, even a modest performer (100T/s etc.)
 299              is the biggest technical risk/unknown (besides DDR3/4).\\
 300              (fall-back is GC800. Do please help with a Libre GPU!)
 301     \item DDR3/4 and eMMC are the main high-risk interfaces\\
 302              (there are fall-back strategies in place)
 303         \item Ultimately the strategy is all about cost reduction
 304               vs risk mitigation,
 305               with Libre/Ethical prioritised over "convenience"
 306   \end{itemize}
 307 }
 308
 309
 310 \frame{
 311   \begin{center}
 312     {\Huge The end\vspace{20pt}\\
 313                    Thank you\vspace{20pt}\\
 314                    Questions?\vspace{20pt}
 315         }
 316   \end{center}
 317
 318   \begin{itemize}
 319         \item Discussion:
 320         \item http://libre-riscv.org/shakti/m\_class/
 321   \end{itemize}
 322 }
 323
 324
 325 \end{document}