A survey of attacks against Intel x86 over last 10 years (2015) [pdf]
blog.invisiblethings.org
A survey of attacks against Intel x86 over last 10 years (2015) [pdf]
1–10 of 41 posts
Re: A survey of attacks against Intel x86 over last 10 years (2015) [pdf]
#2x86 has had a good run. But it's time for it to go.
I'm hopeful for RISC-V.
Re: A survey of attacks against Intel x86 over last 10 years (2015) [pdf]
#3[PDF] (2015) - Probably better without the URL hash.
Still relevant..
Re: A survey of attacks against Intel x86 over last 10 years (2015) [pdf]
#4x86 has had a good run. But it's time for it to go. I'm hopeful for RISC-V.
Why RISC-V and not e.g. Arm? Why is RISC-V better than x86 from AMD? Serious questions, I have no idea about these topics and would love to learn more.
Re: A survey of attacks against Intel x86 over last 10 years (2015) [pdf]
#5Previous discussion from 3 years ago: https://news.ycombinator.com/item?id=10458318 (169 comments)
Re: A survey of attacks against Intel x86 over last 10 years (2015) [pdf]
#6x86 has had a good run. But it's time for it to go. I'm hopeful for RISC-V.
Why RISC-V and not e.g. Arm? Why is RISC-V better than x86 from AMD? Serious questions, I have no idea about these topics and would love to learn more.
I believe you have to pay royalties for Arm while RISC-V is completely open source.
Re: A survey of attacks against Intel x86 over last 10 years (2015) [pdf]
#7x86 has had a good run. But it's time for it to go. I'm hopeful for RISC-V.
RISC-V inherited all the bad ideas of x86 by now. It has an SMM equivalent, a separate hypervisor mode (instead of full orthogonality which lets you get away without one), resident firmware code outside the OS' control, ...
Re: A survey of attacks against Intel x86 over last 10 years (2015) [pdf]
#8x86 has had a good run. But it's time for it to go. I'm hopeful for RISC-V.
RISC-V inherited all the bad ideas of x86 by now. It has an SMM equivalent, a separate hypervisor mode (instead of full orthogonality which lets you get away without one), resident firmware code outside the OS' control, ...
Is there a different ISA that you would have preferred to see as the basis for an open hardware industry?
Re: A survey of attacks against Intel x86 over last 10 years (2015) [pdf]
#9x86 has had a good run. But it's time for it to go. I'm hopeful for RISC-V.
RISC-V inherited all the bad ideas of x86 by now. It has an SMM equivalent, a separate hypervisor mode (instead of full orthogonality which lets you get away without one), resident firmware code outside the OS' control, ...
> separate hypervisor mode
RISC-V, without the hypervisor extension, meets the requirements for Popek-Goldberg virtualization, unlike x86. The problem is that classic virtualization requires shadow paging for memory virtualization, which can be slow. The hypervisor extension (not yet finalized) only adds two level nested paging, a few shadow CSRs, and IIRC a few more interrupt handling registers. The hypervisor extension itself is virtualizable (again, with shadow page tables).
Re: A survey of attacks against Intel x86 over last 10 years (2015) [pdf]
#10x86 has had a good run. But it's time for it to go. I'm hopeful for RISC-V.
Why RISC-V and not e.g. Arm? Why is RISC-V better than x86 from AMD? Serious questions, I have no idea about these topics and would love to learn more.
RISC-V is simpler, and easier to implement. Instruction density is very good with the compressed extension, and is applicable to many niches, from in-order low power embedded cores, to high performance out of order desktop CPUs. We can expect marginal improvements over x86 and ARM across the board.
On the other hand, it is not finished. A number of extensions have yet to be frozen, and we're just beginning to see commercial processors (I mean, where the ISA is exposed to the end user. NVIDIA already uses RISC-V internally).