Live data from Hacker News

Lichee Console 4A – RISC-V mini laptop: Review, benchmarks and early issues

3.14.by

91–100 of 158 posts

Re: Lichee Console 4A – RISC-V mini laptop: Review, benchmarks and early issues

#91
post #32

[flagged]

In Belarus where the author is from people don't have many options.

I was originally from Belarus, but as you mention - I am indeed in Zürich for some years.

Still, I can assure you, 99% of people in Belarus do work on x86, and cutting edge x86 hardware is being sold freely. Technological sanctions failed many years ago and at some point I will need to write an article about that...

Re: Lichee Console 4A – RISC-V mini laptop: Review, benchmarks and early issues

#92

Earlier quoted context omitted.

Yes. I'm using the old gnu toolchain branch from brucehoult and write the benchmarks such that they work in rvv 1.0 and rvv 0.7.1. To help with that I've got a gnu assembler macro file that does 1 to 1 instruction translation when possible and for the other cases I need to #if/#else/#endif. I'm working on rvv unicode conversions, and plan to release a blog post/article with benchmarks and explanation soon. The proble…

this is a great resource! any chance you can add a matmul benchmark to this?

I was thinking about that, but matmul is so too hardware specific (cache sizes, and the like), and I'm not confident I can get an implementation that can get close to max performance.

Re: Lichee Console 4A – RISC-V mini laptop: Review, benchmarks and early issues

#93
post #30
post #16

This is TH1520, same SoC as the Lichee Pi 4A. A chip that's oddly faster than JH7110 (VisionFive2, Milk-V Mars) in microbenchmarks, but slower in practice (e.g. gcc). Presumably due to smaller cache. It is also less power efficient, and lacks the upstream support JH7110 enjoys[0]. I would look at Pinetab-V, a tablet-laptop based on that SoC, today. Better yet, wait for Milk-V Oasis[1] tba this June, as well as other…

I did a comparison of a few RISC-V single board computers and the Lichee Pi 4A is definitely very slow on real world tasks, even though in theory it ought to be the fastest. I never got to the bottom of exactly why - it might be software issues or non-upstream drivers. At the moment I'd recommend the VF2 for general use. https://rwmj.wordpress.com/2023/07/25/heads-up-lichee-pi-4a-...

Something's definitely "up with" the RISC-V GCC port; in principle maybe there are just some passes or backend options that need to be flipped on in some way?

https://godbolt.org/z/cvc6j1sM6

Re: Lichee Console 4A – RISC-V mini laptop: Review, benchmarks and early issues

#94

Earlier quoted context omitted.

this is a great resource! any chance you can add a matmul benchmark to this?

I was thinking about that, but matmul is so too hardware specific (cache sizes, and the like), and I'm not confident I can get an implementation that can get close to max performance.

getting big matmul good is hard, but up to about 100x100 you don't need to worry about cache sizes, it's all about the microkernel

Re: Lichee Console 4A – RISC-V mini laptop: Review, benchmarks and early issues

#96

The author mentions if you want a small laptop today, you need to go to eBay and buy an old UMPC. This is not correct, there are some modern mini laptops. I purchased a new 8" mini laptop with folding touchscreen and an intel N100 CPU from AliExpress. https://www.aliexpress.us/item/3256805658668421.html Specs: Intel N100 12GB RAM NVME SSD Slot 1280x800 Touchscreen (with pen support) USB-C port (supports charging and…

Here's another example, similar in form factor to old Sony VAIO UMPCs

https://www.ayaneo.com/product/AYANEO-SLIDE.html

Re: Lichee Console 4A – RISC-V mini laptop: Review, benchmarks and early issues

#98

The author mentions if you want a small laptop today, you need to go to eBay and buy an old UMPC. This is not correct, there are some modern mini laptops. I purchased a new 8" mini laptop with folding touchscreen and an intel N100 CPU from AliExpress. https://www.aliexpress.us/item/3256805658668421.html Specs: Intel N100 12GB RAM NVME SSD Slot 1280x800 Touchscreen (with pen support) USB-C port (supports charging and…

A maybe, maybe not, less sketchy alternative could be a Nanote P8 from Japan. They were released in 2021 and can be bought for $200-$230 new and shipped from Japan on ebay.

The downsides are the much slower Intel 4200 CPU and less, slower RAM, slightly smaller 7" screen. I would not be surprised if the manufacturer of the Ali laptop is the same as that of the Nanote.

Re: Lichee Console 4A – RISC-V mini laptop: Review, benchmarks and early issues

#99
post #85
post #63

Earlier quoted context omitted.

RISC-V is becoming a worldwide interop standard, and a real one, namely royalty free and which will be stable in time once we get all the "now we know" features, and all that at the ISA level (x86_64 and ARM are _NOT_ worldwide royalty free). And don't be mistaken, there is no perfect ISA (it is said "average"), it does not exist, only a set of trade-offs and compromises which will not fit all use-cases perfectly. RI…

This is the first time I've ever seen anyone write 'silicium' and sure enough, it's an alternative name for silicon. I wonder if this is a more common name for silicon in some other part of the world (I'm in the US). I don't think I've ever seen this spelling before today, and I'm not a young person.

It is the spelling used in e.g. the Netherlands, a country where the light metal used in aircraft goes by the name Aluminium which also happens to be the correct version [1] of the bastardised Aluminum.

The word Silicon 'feels' wrong to a Dutch speaker because it makes it sound like integrated circuits are made out of the same stuff used to assemble aquariums, fake boobs and heat-resistant flexible cookware. That stuff is called 'siliconenrubber' or 'siliconen' (depending on the application and who you ask) in Dutch.

[1] a bit like vi vs emacs for chemistry in other words

Re: Lichee Console 4A – RISC-V mini laptop: Review, benchmarks and early issues

#100
post #42

Is there a reason for a dearth of PCIe connectivity on these small SoCs? Is it difficult to implement? Perhaps a pincount issue? The big problem with these small and cheap systems is that you can't connect NVMe drives to them and you pay a huge performance penalty.

most SOC CPUs don't really have a huge PCIe capability to begin with- possibly 1 or 2 lanes total; and you probably want USB, Ethernet etc; You wouldn't get very much performance anyway, as you only want many PCIe links in order to get bandwidth through them which you're unlikely to do on an anaemic CPU. to-wit: you wouldn't get good NVMe performance even if you had the pinouts and the CPU had 4x Lanes of PCIe anyway…

> you wouldn't get good NVMe performance even if you had the pinouts and the CPU had 4x Lanes of PCIe anyway.

... compared to eMMc or sata over usb? You won't get the full performance of the ssd, but i guarantee it will be much better.

Post reply on HN