TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Comments on “The Case for the Reduced Instruction Set Computer” [pdf]

2 pointsby spyremeownabout 2 years ago

1 comment

brucehoultabout 2 years ago
FUD at its very best.<p>&gt; A careful comparison between a RISC and a CISC would &gt; seem to us to require a complete design of the hardware and &gt; microcode for both, construction or simulation of the processors, &gt; the writing of compilers and possibly an operating system, and &gt; performance measurement across a variety of applications. &gt; Without this level of effort, claims of increased &gt; cost-effectiveness for a RISC are hard to support<p>Which of course took a while, but June 1987, Acorn Archimedes, £800, 4.5 MIPS (I think that is counting VAX 11&#x2F;780 as 1.0) vs MICROVAX 3500 (also 1987) 2.7 MIPS, $75k. Or VAXSTATION 2000, 0.9 MIPS, $5k.<p>Also in 1987, 68020 Apple Mac II and Sun 3&#x2F;60 were 2-3 MIPS for $8k-$10k, less CISCy than VAX but still crazy CISCy. Much better price&#x2F;performance than VAX, much worse than ARM.<p>&gt; Dense code, of course, offers other advantages as well. Cache &gt; performance and paging performance will be better if there are &gt; more instructions per cache block and per page.<p>They are correct about that.<p>It is interesting that early RISC machines all had 2 instruction lengths and excellent code density: CDC6600, CRAY I, IBM 801, RISC-I. The early commercial RISCs between 1985 and 1992 (ARM, SPARC, MIPS, PA-RISC, Power(PC), Alpha) had just a single instruction length and poor code density.<p>Since 1995, everyone (re)introduced two instruction lengths in one way or another, culminating in the current ARMv7, RISC-V, and the stillborn nanoMIPS (1 chip produced before MIPS abandoned their own ISA in favour of RISC-V).<p>ARMv8 (Aarch64) is a weirdo, introduced in 2012 with a single instruction length and poor code density, ignoring the lessons of the fantastic success of ARMv7. To its credit, it is by far the most dense fixed-length 4-byte instruction ISA, easily beating A32, PowerPC, MIPS, SPARC etc. It also pretty much matches the highly variable length Amd64 which suffers a lot from pasting REX prefixes onto the i686 ISA.<p>But Aarch64 has poor code density compared to RISC-V (or 32 bit ARM) and I think this will ultimately be a large part of its undoing once modern µarch RISC-V SoCs get into mass production (including the various companies who have already announced or are working on 8-wide RISC-V cores).<p>&gt; Here is an example from the VAX-11&#x2F;780: in one time-sharing &gt; benchmark the instruction MOVC3 (a character-move instruction) &gt; accounts for less than 0.4% of the instruction executions, but &gt; for 13% of the time; it is 60th in the frequency ranking, ist in &gt; the time ranking.<p>Not mentioned by them: on the VAX-11&#x2F;780, a decent memcpy() using normal instructions is faster than MOVC3.