SoylentNews is people
SoylentNews
SiFive reckons its fastest RISC-V processor core yet is closing the gap on being a mainstream computing alternative to x86 and Arm.
The yet-unnamed high-performance design is within reach of Intel's Rocket Lake family, introduced in March, and Arm's Cortex-A78 design, announced last year, in terms of single-core performance, James Prior, senior director of product marketing and communications at SiFive, told The Register.
San Francisco-based SiFive didn't provide specific comparative benchmarks, so you'll have to take their word for it, if you so choose.
[...] SiFive's latest design, which is set to be teased today, will be christened with a formal name at the RISC-V Summit in December.
The CPU core is said to be about 50 per cent faster than its predecessor, the P550, which was introduced in June. We note that the L3 cache memory capacity has been quadrupled, from the 4MB in the P550 to 16MB in the new design. Up to 16 of these new cores can be clustered versus the maximum of four for the P550. The latest design can also run up to 3.5GHz compared to 2.4GHz for the P550.
Intel's Attempt to Acquire SiFive for $2 Billion Fell Apart, Report Claims
While Intel was interested to acquire RISC-V processor developer SiFive and SiFive is considering its strategic options, the companies could not agree neither on financial terms nor on how SiFive technologies could be used at Intel reports Bloomberg. The latter company is still considering both an initial public offering (IPO) as well as a takeover by a larger player.
Previously: SiFive Announces HiFive Unmatched Mini-ITX Motherboard for RISC-V PCs
Intel May Attempt to Acquire SiFive for $2 Billion
Intel Will License SiFive's New P550 RISC-V Core
(Score: 1, Insightful) by Anonymous Coward on Saturday October 23 2021, @05:20AM (2 children)
Instruction set is just one part of computer architecture.
I don't think it's the main factor determining power usage or performance anymore.
(Score: 4, Insightful) by driverless on Saturday October 23 2021, @07:32AM (1 child)
And once they figure out how to get that performance level without GaN chips cooled with liquid helium, they'll be onto a real winner!
Before that gets modded flamebait, I actually rather like the whole RISC-V effort, I just wish they'd be a bit more real-world realistic with their claims.
(Score: 2) by sgleysti on Saturday October 23 2021, @05:25PM
I don't think anyone has a GaN foundry that can reach the process nodes and density required to build these chips. I've only seen GaN used in N-Channel power MOSFETs anyway. I think the higher speed non-Si stuff is usually GaAs; if memory serves, that was used in cellular baseband modems at one point. IBM also has a SiGe graded heterojunction process that is really high speed, but I don't think they've made a CPU out of it. Heterojunction sounds like BJTs anyway, so that might be more targeted at RF and other high speed amplifiers.
These SiFive CPUs were most likely made at one of the Silicon foundries that does contract work, like TSMC or whoever else is in that market. The most they would have done for cooling is use a large, high power cold plate, but I doubt they're pushing the TDP that far.
It'll be good to see better data on computational performance and power dissipation.
(Score: 2, Offtopic) by Frigatebird on Saturday October 23 2021, @06:59AM (4 children)
I owned a Dodge, a 1940's Dodge Truck. Thing about it, or two things about it, I has a 6-volt positive ground electrical system, such as it was. And, it has lug bolts, rather than studs and lug nuts, but that was not the weird thing. The lug bolts on the left/driver's side, were all left hand thread. Taking it in to a modern shop to have the tires replaced was a trip. But the reason my Dodge almost Power wagon had left hand thread lug bolts goes back to wagon wheels. You see, old wagons would have wheel bearings of a sort, usually steel bands running on steel band, in the hub and the spindle. And all that was held together by an axle nut. The nut fastened on the spindle, so on the right side, the motion of the wheel would tend to tighten the wheel nut, since it was right-handed thread. On the other side, the wheel rotated the other way, relative to the spindle, so that wheel nut was given a left-handed thread, so that the forward motion of that wheel would also have the effect of tightening rather than loosening the wheel-nut. So much for Wagons.
So, my 1940's Dodge retained the tradition of left hand thread on the Sinister side, even though the thread direction of the lug-bolts had no bearing on loosing or tightening of the bolts, unlike with the spindle nut. And now for the relevance of our horse buggy whip- railroad guage- left hand wheel-nut automotive analogy: x86 architecture is exactly like the left handed lug-bolts on my '40's Dodge. A left over from the past that no one understand, but one that is getting in the way when we metaphorically take our Power
WagonsBooks into the shop to have new tires put on.It is time to universalize hardware, to virtualize software, and to make sure that anything can run on anything, but not like Javascript does.
(Score: 2) by driverless on Saturday October 23 2021, @08:10AM
Wait, a 1940s Dodge? Joseph Lucas supposedly died (meaning returned to the underworld) in 1902, how did he do electrics for Dodge in the 1940s?
(Score: 2) by ls671 on Saturday October 23 2021, @08:40AM
It reminds me of the oil drilling rigs and a drill string made of pipes. The rotary table is what transfer power to the drill string in order for it to rotate clockwise and cause the drilling bit to dig. In the drill string, everything above the rotary table is left handed for the same reason. I remember seeing this elsewhere, always for the same reason.
Everything I write is lies, read between the lines.
(Score: 1, Informative) by Anonymous Coward on Saturday October 23 2021, @02:22PM
If the wheel-hub pilot wasn't a tight fit, then I believe that your Dodge left hand thread bolts were the correct choice. Imagine the wheel moving slightly relative to the hub, under load....
For yet another example of left hand threads on the left side, see bicycle pedals. In this case the overhung load (foot not in line with crank arm) will quickly unscrew a pedal that is threaded the wrong way. It's a subtle thing, there is an animation on this page -- https://physics.stackexchange.com/questions/6488/why-are-bicycle-pedal-threads-handedness-left-on-the-left-and-right-on-the-righ [stackexchange.com]
(Score: 3, Informative) by sgleysti on Sunday October 24 2021, @03:56AM
I wish there was some middle level between the mechanics and actually working on the car in this analogy... since the vast majority of programming targeting x86 today is done in compiled or interpreted languages, it is only people writing compilers, higher precision math routines, or low level drivers / OS stuff who will actually touch the architecture.
Granted it still affects all of us at some level.
(Score: 0) by Anonymous Coward on Saturday October 23 2021, @07:05AM (1 child)
i hope it's not just a "java chip" like most all ARM chips are ...
(Score: 2) by sgleysti on Sunday October 24 2021, @04:48AM
By "java chip" do you mean only used in Android phones? Because there have been attempts to implement the Java bytecode interpreter in hardware...
(Score: 0) by Anonymous Coward on Sunday October 24 2021, @12:38PM (1 child)
I'm really glad to hear Intel didn't get their grubby paws on RISC-V. Hopefully RISC-V will remain independent; and perhaps one day, we'll have processors without processors in them, minding what our processors do. We'll have some freedom in our hardware to go with the free software running on it.
(Score: 0) by Anonymous Coward on Sunday October 24 2021, @01:16PM
1. Buying SiFive doesn't deprive anyone of the RISC-V ISA.
2. RISC-V is easily extensible and will be used to make proprietary and evil products, including backdoors.
3. RISC-V will end up a poor experience for Linux, just like ARM.