<feed xmlns='http://www.w3.org/2005/Atom'>
<title>cda4210_lisp_coproc/Makefile, branch master</title>
<subtitle>A primitive Lisp accelerator in a full-custom physical design (Electric VLSI MOSIS 350nm) and RTL digital design (Librelane Sky130nm PDK)</subtitle>
<link rel='alternate' type='text/html' href='https://git.vineetk.net/cda4210_lisp_coproc/'/>
<entry>
<title>migrate from electric vlsi to librelane/sky130 flow</title>
<updated>2025-12-10T21:39:36+00:00</updated>
<author>
<name>vin</name>
<email>git@vineetk.net</email>
</author>
<published>2025-12-10T21:35:42+00:00</published>
<link rel='alternate' type='text/html' href='https://git.vineetk.net/cda4210_lisp_coproc/commit/?id=06b6b116934cc8341676f52f5f6040a038020c32'/>
<id>06b6b116934cc8341676f52f5f6040a038020c32</id>
<content type='text'>
this is quite a major shift. moves the project from a manual,
full-custom layout workflow to a more modern automated flow and a more
modern process (130nm vs 350nm). also improved the testbench.
migration also resolves previous manual routing-caused errors (like
the CONS logic bug and difficulty in implementing TG
logic).

this nearly halved the transistor count from 15k to 8k and reduced
area size by 300x.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
this is quite a major shift. moves the project from a manual,
full-custom layout workflow to a more modern automated flow and a more
modern process (130nm vs 350nm). also improved the testbench.
migration also resolves previous manual routing-caused errors (like
the CONS logic bug and difficulty in implementing TG
logic).

this nearly halved the transistor count from 15k to 8k and reduced
area size by 300x.
</pre>
</div>
</content>
</entry>
</feed>
