Maybe to prevent fragmentation and confusing readers? You can change the topic of this thread to something like "Future ARM Discussion".It seems to be locked.
Kinda the opposite of what I was going for.Maybe to prevent fragmentation and confusing readers? You can change the topic of this thread to something like "Future ARM Discussion".
How about "index" important stuff or start of relevant discussions in this thread in the first post? That's one way, though it would be pretty cumbersome (for you but everyone else will reap the benefit ).The current title is very specific, people just kept veering off that topic, which makes it harder to find information in older posts without knowing the exact text, or going through each page 1 by 1.
Wait until you start looking for complex points (for instance the use of barriers).Trying to read the ARM developer documentation is an exercise in frustration.
That doesn't work because when you are discussing a dozen of CPUs there are multiple posts discussing other things in the middle of the discussion about one core.How about "index" important stuff or start of relevant discussions in this thread in the first post? That's one way, though it would be pretty cumbersome (for you but everyone else will reap the benefit ).
AMX did you mean?then Apple's AVX that became SME
While ARM did add some instructions like LSE2 that do help with x86 emulation, it should be noted that the lions share of better x86 -> ARM64 emulation (binary translation) performance foudn in M1+ comes from Apple's µArch itself, rather than ISA extensions.Those custom instructions have always been added to the ARM ISA down the road. First the ones that helped with x86 emulation and supported the strong x86 memory model, then Apple's AMX that became SME.
It's a combination of both uarch and instructions. The store ordering is an important uarch thing, but the brain dead flag computation of x86 requires specific instructions.While ARM did add some instructions like LSE2 that do help with x86 emulation, it should be noted that the lions share of better x86 -> ARM64 emulation (binary translation) performance foudn in M1+ comes from Apple's µArch itself, rather than ISA extensions.
Lobotomized X4 very much exists to giving it an actual name was a matter of time, really.The text claims it is just a lower clocked X930 (Travis) core though, which doesn't make any sense, as I can't recall ARM ever giving a codename to a gimped core before now.
That lobotomised cores exist does not surprise me, and I do already know of codenamed lobotomised CPU cores from at least AMD in the past.Lobotomized X4 very much exists to giving it an actual name was a matter of time, really.
Usually around the last week of May, certainly 2nd half.btw, shouldn't we be close to ARM dropping NDA about new cores? They were usually doing that around May from what I remember
IMHO Cix deserves a topic all of its own if they keep this up.What would be the right topic for this?
Arm’s reach across all these markets is made possible by the ubiquitous Armv9 architecture, the foundation of modern computing. Since its introduction four years ago, many of the world’s latest mobile handsets and PCs are now powered by Armv9 CPUs, bringing a range of AI performance benefits to these devices. Later this year, the new Armv9 flagship CPU – Travis – will bring double-digit performance gains, with the further acceleration of AI workloads through our latest architecture feature, Scalable Matrix Extension (SME). This will be paired with Arm’s next-generation GPU – Drage – which unlocks sustained performance for longer gaming and richer multimedia content – to deliver Arm Lumex CSS for the future of edge AI on consumer devices.
ARM will finally beat Apple IPC wide this year if Apple doesn’t improve this year.Confirmed!
Cortex X930/Travis has SME:
View attachment 124128
Something something ARM Lumex CSS mentioned at 29:15 in this video:
Yeah but they clock like poo. The area is also poo.ARM will finally beat Apple IPC wide this year if Apple doesn’t improve this year.
Considering the claimed double digit IPC increase all they need to do is work on clock frequency at this point.ARM will finally beat Apple IPC wide this year if Apple doesn’t improve this year.