Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ESP32-S31

espressif.com

Post reply on HN
Print view View original

51–60 of 207 posts

Re: ESP32-S31

#51

Post by NekkoDroid »

cassepipe wrote: post #35
mentalpagefault wrote: post #15

Earlier quoted context omitted.

IMAC are the RISC-V extensions supported: I = Base integer instruction set, 32-bit M = Standard extension for integer multiplication and division A = Standard extension for atomic instructions C = Standard extension for compressed instructions https://en.wikipedia.org/wiki/RISC-V#ISA_base_and_extensions

Thanks.I can't believe they chose non-arcane, memory-friendly letters. Kind of rare in naming hardware I feel (unless it's not ?)

I see you are unfamiliar with `rv64mafdcbvh_zicsr_zicntr_zihpm_ziccif_ziccrse_ziccrse_ziccamoa_zicclsm_za64rs_zihintpause_zic64b_zicbom_zicbop_zicboz_zfhmin_zkt_zihintntl_zicond_zimop_zcmop_zcb_zfa_zawrs_supm_svade_ssccptr_sstvecd_sstvala_sscounterenw_svpbmt_svinval_svnapot_sstc_sscofpmf_ssnpm_ssu64xl_sstateen_shcounterenw_shvstvala_shtvala_shvstvecd_shvsatpa_shgatpa` also known as `RVA23`

Re: ESP32-S31

#52

Post by chrisco255 »

kjlldld wrote: post #50

Is anyone else worried that these chips are all made in China?

For what its worth, Espressif chips are open source, but yes, I wouldn't run national security or government devices on these.

Edit: I take it back on OS comment, they are not OS but some components of the SDK are:

https://zeus.ugent.be/blog/23-24/open-source-esp32-wifi-mac/

Re: ESP32-S31

#53

Post by alnwlsn »

I kind of wish these all weren't called ESP32. ESP8266 and ESP8285 -> ESP32 made sense, but now we have 10+ different versions with different features and different architectures.

Kind of like how in every thread involving a Raspberry Pi Pico (RP2030/RP2350), there's always someone confusing it with the single board computer version.

The ESP32 (Classic, usually WROOM-32E) is still usually what comes to mind when I hear ESP32.

Re: ESP32-S31

#54

Post by topspin »

orphea wrote: post #32

It being RISC-V is awesome, but how does it make sense that it's S series when S series have been Xtensa cores? Why is it not C series?

S has never implied Xtensa, and C doesn't imply RISC-V. That's a widely held misunderstanding. S, C, P, etc. are product categories, not ISAs. S devices are high performance SoCs; large feature set, high frequency, not the lowest power or cost.

Just appending 1 to S3 is odd though. This MCU is step change for Espressif. S4 or something would make more sense.

Re: ESP32-S31

#55

Post by thehk »

> ESP32-S31 is particularly well suited for edge AI and machine learning workloads, including neural network inference

Any way to know what kind of performance one could expect running e.g. a depth anything model on there?

Re: ESP32-S31

#56

Post by jon-wood »

wiml wrote: post #48
hart_russell wrote: post #26

Any reason why this device wouldn't have Z-Wave? Is the wireless protocol significantly different than Thread and Zigbee?

As I understand it, Z-Wave is substantially more closed/proprietary. Both Thread and Zigbee are protocols that run on top of 802.15.4, which Espressif already has in other products.

I think Z-Wave is a bit more open now but everything I’m seeing indicates Zigbee has pretty thoroughly killed it by not requiring arduous certification processes and being generally easier to work with. Z-Wave is technically superior with the ability to have devices directly communicate with each other for basic functionality but at least for me that wasn’t worth the massive markup and I’m slowly replacing anything z-wave with Zigbee equivalents.

Re: ESP32-S31

#57

Post by BenjiWiebe »

phkahler wrote: post #13
randomint64 wrote: post #3

Espressif is on fire! And the CPU even has SIMD instructions! RISC-V cores is a big deal for embedded systems because now compiling for SoCs is only a matter of `rustup target add riscv32imac-unknown-none-elf` instead of downloading half-broken proprietary toolchains and SDKs. Take a look at https://kerkour.com/introduction-to-embedded-development-wit... and https://kerkour.com/rust-esp32-pentest to get started with…

>> And the CPU even has SIMD instructions! Yes, but it looks like there is no hardware floating point. The description of the CORDIC module indicates fixed-point calculations, which is consistent with the lack of any reference to floating point. I am happy the have CAN-FD and Motor PWM module, but nowhere did I see conversion times listed for the ADC. For motor control I demand 1uS conversion time or less, and in the…

Also why do you need 1uS for motor control? 1uS is 0.1 degrees of rotation at 16,666 RPM if I did the math right.

I don't know much about motor control, is it normal to need that fast of feedback?

Re: ESP32-S31

#58

Post by jon-wood »

KZerda wrote: post #36
Imustaskforhelp wrote: post #4

The 1GB bandwidth is interesting. It also has Simd instructions too. Could this theoretically be used as a router or wireguard vpn instance?

Theoretically, yeah. Though at 320Mhz, with only 2.4ghz wireless, even with two cores, I doubt it's going to get anywhere near the throughput to fill the gigabit connection.

Yeah, I’m not entirely sure what use cases there are which include both an ESP32 and gigabit networking.

Re: ESP32-S31

#59

Post by otterdude »

thehk wrote: post #55

> ESP32-S31 is particularly well suited for edge AI and machine learning workloads, including neural network inference Any way to know what kind of performance one could expect running e.g. a depth anything model on there?

I was wondering this as well. What exactly makes this a good AI chip vs others.

Unless they're not listing a major feature in their spec, a dual core 320Mhz microcontroller is not bad but youre not going to be running any kind of vision model on it, at least very fast.

Re: ESP32-S31

#60

Post by greenavocado »

BenjiWiebe wrote: post #57
phkahler wrote: post #13

Earlier quoted context omitted.

>> And the CPU even has SIMD instructions! Yes, but it looks like there is no hardware floating point. The description of the CORDIC module indicates fixed-point calculations, which is consistent with the lack of any reference to floating point. I am happy the have CAN-FD and Motor PWM module, but nowhere did I see conversion times listed for the ADC. For motor control I demand 1uS conversion time or less, and in the…

Also why do you need 1uS for motor control? 1uS is 0.1 degrees of rotation at 16,666 RPM if I did the math right. I don't know much about motor control, is it normal to need that fast of feedback?

People will always find a reason to complain or pretend they are controlling rocket motor servos with their ESP32
Post reply on HN