In my experience, to achieve large enough scale most systems have to be used in very simple ways. There isn’t space for additional complexity and the result is usually boring systems that work.
The irony here is most modern CISC design are breaking instructions to RISC-like μOps. Moore's law also means - you have more transistors for the same area, now figure out how to use them creatively to increase performance. Workloads are constantly evolving and hardware evolves with it to make those workloads fast.
CISC since around the turn of the millennium is basically a custom tuned high decode speed data compression codec for RISC-like micro-ops. It's been a very long time since anyone designed a CISC processor that actually ran (non-trivial) CISC instructions directly in silicon.
The root of CISC's persistent dominance over true RISC instruction sets is that memory bandwidth is far lower what would be needed to feed micro-ops directly into the CPU. It makes sense to solve that by compressing the instruction stream. RISC looks far better on paper in every other way if you ignore memory bandwidth and latency issues.
That being said, I've wondered for many years about whether a more conscious realization of this might lead to a more interesting design. Maybe instead of CISC we could have CRISC, Compressed Reduced Instruction Set Computer? Instead of CISC you'd have some kind of compression codec that defines macros dynamically. I'm sure X64 and ARM64+cruft are nowhere near optimal compression codecs for the underlying micro-op stream. If someone wants to steal that idea and run with it, be my guest.
The other advantage of the CISC is that it acts like a higher-level API. Many early RISC designs suffered because they were so low-level that early implementation details (like wait states) had to be "emulated" in later processors for compatibility.
It might not be advantageous to just compress a RISC stream of instructions instead of higher level instructions made up of micro-ops for that reason alone.
Dynamically swapping compression like that probably isn't worth it, as now the decode tables are extra state that needs to be compared against, all while inside a critical path.
But most modern RISCs do take a sort of Huffman encoding perspective on ISA design, starting with SH, into Thumb(2), and into RVn-C. I do agree that there's farther we can probably go; stuff like memory referencing ALU ops can be thought of as a way of addressing PRF registers without using any bits in the instruction stream for instance.
Using the Intel Vtune tools you can see how each port is utilized, so you could in theory change your code to mix instructions for best utilization beyond what reordering the CPU can do itself, so I can see some analogy with building a VLIW instruction group.
There's a crazy amount of performance counters you can look at (the perf tool can do that too, but just try running "perf list" to view available counters).
Former audio engineer here. Generally this is the result of high noise floor and poor power management on the amplifier side - not powering down when content isn't playing or incorrect power sequencing on the power down of the amp.
Make your own with a box in AWS or any other cloud provider running something like Strongswan on Linux or iked on OpenBSD.
All the out of the box VPNs I've found have some shortcomings, either being horribly insecure (PPTP, seriously?), overpriced, often abused (which means their entire subnet is banned by pretty much everything) and the providers sometimes seem shady (I want a VPN to escape cancer aka ads, not the government - in this case I'd actually prefer something akin to an ISP complying with local laws versus a "bulletproof" one who could very well be a fly-by-night operation up to no good).
Lots of gaming traffic is also banned. People use AWS for malicious purposes (usually free tier) and then the IP gets recycled, eventually, to a legitimate user.
Popular cloud hosts with a freemium option are a bad idea for personal vpn.
Getting a VPN just means some other company knows your browsing history. Also, I doubt any VPN service can reliably deliver the native speed of my gigabit internet.
This is the key. Look at the roadblocks Google Fiber has hit in their own fiber deployments, pivoting to wireless to bypass the resistance they're getting from incumbents.
I'm interested to see how this plays out. When I looked into it, it seemed hard to compete with wired broadband internet. I think wireless has the best chance in areas where people's only option is satellite or dial-up.
Because there's only so much wireless spectrum and at some point you saturate the link. Plus interference from other carriers reduces the capacity of the link.
I'm not saying it's impossible, but it's also not obvious to me that wireless is better in dense areas, especially since the main cost in wired internet is laying the cable in the first place, which is easier to do cost effectively when you have an urban market to offer service to.
It depends on whether it is licensed or unlicensed spectrum. Some of the technology is in ISM bands that anyone can use.
In either case, the channels still have capacity limits. I'm not saying it's impossible, which is partly why I brought it up in the first place. I was hoping someone more knowledgeable would chime in. The main advantage wires have is you can just run more of them when you reach your capacity (or in some cases you can just change the hardware at either end of the wire to newer technology).
Are there any US carriers that are using unlicensed / shares spectrum?
The bandwidth is only limited per tower, you can easily double the throughput of a given area by doubling the number of cell towers (and reducing power to avoid interference). It’s a lot cheaper to build a new tower than to run new wires to 200 homes (permits and all). On top of that 5g gives 10x bandwidth over 4g in the same band.
You can have 1,000 wires in a bit of pipe, effectively 1,000 "spectrums." The air will always only be a single spectrum.
Cell division does not scale infinitely, and becomes more and more complex to manage.
Running cable you do once, then you can benefit for a long time. Wired will always be the better technical solution, and more economic one, in built up areas.
x86 is not easily swappable by any means. From voltage supplies/rail timing, crystal requirements, different device drivers and FW rewrites, etc. Changing CPUs on a modern design is a huge reset.
And to be clear, the Surface Laptop can be upgraded to Windows 10 Pro as well. Eventually that will be a $50 upgrade, but for the first year after launch, it will be a free upgrade.