Very interesting. It sounds like tuning at the PTX level can increase workload efficiencies, such as quote "Specifically, we employ customized PTX (Parallel Thread Execution) instructions" from the DeepSeek folks https://arxiv.org/abs/2412.19437.
This is a good read. Dr. Blaise Agüera y Arcas was a keynote speaker at https://attend.ieee.org/newera/program/ here in Seattle a week ago but he didn't really get a chance to delve deeply into his position. During his slot there ended up being a lot of back-and-forth about whether AGI truly achieved or just seeing ACI, etc, among the folks from MS, Meta, Google, UW, and even https://www.dia.mil/ rep.
There is still support for CSM in the open source https://github.com/tianocore/tianocore.github.io/wiki/Compat... and even nice projects like https://github.com/coreboot/seabiosto fabricate the CSM16 binary, but many vendors have stopped validating this path, including production of legacy BIOS option roms for adapters (net, gfx, etc) https://www.phoronix.com/news/Intel-Legacy-BIOS-EOL-2020. I still believe CSP's maintain some of this support in their hypervisors' guest firmware for legacy OS binaries/ISO boot support? Also since Windows requires UEFI Secure boot enabled by default and CSM has to be disabled for the UEFI secure boot path, this is another reason legacy BIOS boot isn't exercised so much these days.
We could have added legacy oroms hashes to UEFI Secure boot implementations https://patents.google.com/patent/US8694761B2/en, too, but again folks pushed back in their zeal to remove legacy BIOS overall.
We didn't add the CSM spec https://www.intel.com/content/dam/www/public/us/en/documents... to the PI https://uefi.org/specs/PI/1.8A/ since folks were hoping UEFI would remove the need for CSM. I still remember being challenged in the early 2000's by a long-time BIOS mgr at Intel "Is removing legacy a good idea with EFI? You know, we're really at legacy."
I recall trying to debug a crash in QNX during the mid-90's. I was impressed by the svelte OS that could load from a 3.5" floppy. The failure scenario was coincident with one of my first tasks as a BIOS engineer and it entailed adding some custom error logging in System Management Mode (SMM). Luckily for me it turned out that I had forgotten to save/restore certain general purpose registers around my SMM logic. Fun times.
SMM is pretty good at 'breaking' operating systems :)