[ / / / / / / / / / / / / / ] [ dir / animu / asmr / ausneets / leftpol / roze / travis2k / vg / ztg ][Options][ watchlist ]

/tech/ - Technology

You can now write text to your AI-generated image at https://aiproto.com It is currently free to use for Proto members.
Name
Email
Subject
Comment *
File
Select/drop/paste files here
* = required field[▶ Show post options & limits]
Confused? See the FAQ.
Expand all images

File (hide): 66bd67d07675419⋯.jpg (412.61 KB, 2300x1002, 1150:501, KL_Hitachi_HD68000.jpg) (h) (u)

File (hide): ec7ab05be4217d1⋯.jpg (19.57 KB, 790x287, 790:287, MOS_6502AD_4585_top.jpg) (h) (u)

File (hide): 1a097d7855db7fc⋯.png (87.12 KB, 230x195, 46:39, Z84C0010FEC_LQFP.png) (h) (u)

[–]

 No.886062>>886097 >>886169 [Watch Thread][Show All Posts]

Is there any merit to non-x86 CISC architectures?

 No.886063

There is no merit to computers


 No.886073

If you are too flexible for ASICs but too specialized for ARM and alternatives, I'd say so.


 No.886075

when I read about CISC's It feels like most of them either were inspired by intel8080 or were aping it directly.


 No.886097>>886104

>>886062 (OP)

>glorious 680xx, comfy MOS65xx/Z80

x86 was a mistake.


 No.886104>>886241

>>886097

>actually becoming a seagull

He must not have died even once to get the best ending.

>x86 was a mistake

The momentum of the IBM behemoth made it a fight that was futile for non-x86 to begin with. IBM chose Intel as their chip provider and based their PC's architecture on the 8086 (they could have picked Motorola's 68000 instead but didn't).


 No.886116>>886138

2 ARMs on one silicon is the future


 No.886122>>886146

An argument I've heard is that cisc acts like a layer of abstraction that allows the underlying risc instruction set to be modified without having to change the compilers.


 No.886138

File (hide): baa0787796db4ae⋯.png (495.46 KB, 953x1282, 953:1282, pathetic.png) (h) (u)

>>886116

>not putting 1 m68k, 1 Z80, 2 PPC and 8 RISC-V cores on a single die


 No.886146

>>886122

This is equivalent to running your software in a virtual machine, just on a more close to the metal level.


 No.886169

>>886062 (OP)

Well RISC is still currently the best way to hack Gibsons, so no.


 No.886170>>886179

We need somebody to clone the VAX and make a SOC integrating the CPU and common peripherals. The software is already there.


 No.886179>>886184

File (hide): cef80b1c4bf1ee0⋯.jpg (167.71 KB, 1300x1220, 65:61, blog-happy-man-face.jpg) (h) (u)

>>886170

Yes, someone with enough knowhow from this board should do it.

We can collaborate after the initial architecture is drawn up.

If budget is a problem, we can ask our moms for initial investment capital. What do you say??


 No.886184

File (hide): f0979172cdcd42a⋯.jpeg (77.33 KB, 1218x685, 1218:685, D91D47A4-799E-48AA-B5FF-C….jpeg) (h) (u)

>>886179

I’d say that I can tell you’re Jewish. Much of the work is already done if you surf on over to opencores.


 No.886241

>>886104

>IBM chose intel as their chip provider

IBM made their own chips though.


 No.886248>>886251 >>886255 >>886286 >>886396

RISC came about because UNIX weenies can't make a complex chip run fast or a compiler that can use those instructions. CISC was coined by RISC weenies to mean anything that's not RISC. Lisp machines are CISC, which makes them bad. Mainframes are CISC, which makes them bad. When you get rid of all the buzzwords and weenie bullshit, "complex" means any instruction that's not used by C compilers.

There's a lot of merit to Lisp machines. There's a lot of merit to more conventional CISCs too.

https://people.eecs.berkeley.edu/~kubitron/cs252/handouts/papers/symbolics.pdf

    "RISC is to hardware what the UNIX operating system
[sic] is to software."

Subject: Wait, I thought RISC was a *good* idea


No, the quote is exactly right. RISC is a lazy solution
along the lines of "well, we don't know how to write
compilers that use complex instructions efficiently, and we
don't know how to design complex hardware that runs fast, so
we'll make everything simple, and we can advertise we run at
80Mhz even though the system supports fewer user than a 1
MIP DEC-20."

It's exactly analagous to "you can use pipes and
redirection shell scripts to do anything, so we don't have
to write any REAL programs" and "portability is more
important that usability" philosophies so rampant in the
unix world.

(Was I properly vitrolic this time?)


 No.886251

>>886248

>words

Wow that's annoying.


 No.886255>>886287 >>886291

>>886248

Is VLIW bad too?


 No.886261

File (hide): 222b639621c2ff0⋯.mp4 (13.4 MB, 480x360, 4:3, Xmas 2007 for the Amstrad ….mp4) (h) (u) [play once] [loop]

Before getting a PC, I had an Amiga, and before that an Amstrad CPC. Both were a lot nicer than x86 when it comes down to it. Doing DOS and Turbo Pascal on the 486 was still okay, but recent hardware is just no fun for me. I'm just not at all into modern games and web.


 No.886286

>>886248

Meanwhile the Unix approach really was better in the long term, with x86 becoming RISC internally and Microsoft cramming more and more Unix/Linuxisms into Windows.


 No.886287

>>886255

Bad according to the weenies or bad according to me? I think VLIWs are mostly bad because they have the same problems as RISC but worse. Itanium was also optimized for C and UNIX.

Subject: Hating Unix Means Hating Risc

Date: Fri, 22 Mar 91 21:34:47 EST
From: JW

Hey. This is unix-haters, not RISC-haters.

Look, those guys at berkeley decided to optimise their
chip for C and Unix programs. It says so right in their
paper. They looked at how C programs tended to behave, and
(later) how Unix behaved, and made a chip that worked that
way. So what if it's hard to make downward lexical funargs
when you have register windows? It's a special-purpose
chip, remember?

Only then companies like Sun push their snazzy RISC
machines. To make their machines more attractive they
proudly point out "and of course it uses the great
general-purpose RISC. Why it's so general purpose that it
runs Unix and C just great!"

This, I suppose, is a variation on the usual "the way
it's done in unix is by definition the general case"
disease.


 No.886291>>886295

>>886255

VLIW is basically only for DSPs nowadays. The Mill CPU guys could make one capable of running C and Linux effectively if they ever start shipping silicon.


 No.886295

>>886291

>what is Transmeta

I think they were snatched up by the defense industry.


 No.886396

>>886248

Read another book already.

Something about Forth for example.




[Return][Go to top][Catalog][Screencap][Nerve Center][Cancer][Update] ( Scroll to new posts) ( Auto) 5
23 replies | 5 images | Page ?
[Post a Reply]
[ / / / / / / / / / / / / / ] [ dir / animu / asmr / ausneets / leftpol / roze / travis2k / vg / ztg ][ watchlist ]