Skip to content
HHackerTube.videoSurprise me

Industrial Strength High Performance RISC V Processors For Energy Efficient Computing

Industrial Strength High Performance RISC V Processors For Energy Efficient Computing on HackerTube: recommended by 1 Hacker News commenter across 1 month, 2017–2018.

RISC-V International

talk · advanced · dated

Open on YouTube

David Ditzel of Esperanto Technologies presents their massively parallel, energy-efficient RISC-V processors at the 7th RISC-V Workshop in 2017. It covers the high-performance many-core design aimed at machine learning.

Why Hacker News recommends it

Cited in RISC-V and AI hardware threads as the source for Esperanto's ambitious many-core vector design.

people recommended it
1
separate months
1
strong recommendations
0
discussed on HN
2017–2018
“See this talk by David Ditzel”
— nickik, Sep 2018, in “New Libre GPU Effort Based on RISC-V”

What HN commenters said

4 Hacker News comments link this video. Each one links back to its thread.

phkahlerDec 2017Recommends

The work Esperanto is doing take the vector concept to a mind boggling extreme: ▶ this video I want to write code for their chip!

in “RISC-V Vector Extension overview and proposal [video]” · View on HN

nickikSep 2018Cites it

For those interested in the RISC-V and the possibility of GPU type of things. I can mention some stuff that might not be well known. RISC-V is devloping a Vector extension (V) will allow SIMD style programming with a variable vector length. See from the last workshop: Intro: [link] Project Update: [link] Initially part of the standard was also a Vector Type field for each register, and that would have allowed different types, such as Tensors, Matrix and so on. This has been removed from the initial Vector extension proposal but work on this will continue. At least one company is already actively devloping hardware for V with Tensors (see below), sadly not open-source. This Libre GPU project is going a slightly different route targeting the Simple-V, a slimmer version of the Vector extension, Simple-V. See: [link] Esperanto Technology is devloping a chip (and IP) that will do this, but it will be closed source (as far as we know). See this talk by David Ditzel: ▶ this video

in “New Libre GPU Effort Based on RISC-V” · View on HN

DoluJan 2018Cites it

On this talk : - ▶ this video - ▶ this video => yes and no The industry lack's of wide profiles (hardware engineer with good software understanding) is really hurting any new innovative HDL

in “Chisel: Constructing Hardware in a Scala Embedded Language” · View on HN

baobrienDec 2017Cites it

I'm not sure about REX, but Esperanto is pretty far away from greenarrays. From what I got out of their talk at the latest Risc-V workshop[3] (video[1], slides[2]), they're going for the big high-performance end of the spectrum. The chip they were talking about is supposed to have 16 64-bit OoO Risc-V cores and 4096 RV64GC cores with vector units connected by some sort of network on chip. [1] ▶ this video [2] [link] [3] [link]

in “Leveraging RISC-V for AI and Machine Learning” · View on HN

Topics & tags

Computer architecture & CPUsrisc-vesperantomany-coremachine learning hardwarevector extension