FCLChere we go!
AI counter within 2 sentences? 2
LMAO, freudian slip:
AI Error instead of Era
Ok so software devs are important to colab with: can haz software roadmap pweaze? 😻
Mi300X is "launching"
TF32 FP8, sparsity support on top of fp/bf16 and ofc int8
Dozen chiplets (including HBM stacks?)
4 io dies with vcache built in (!!!!)
8 GPU tiles
17TB/s mesh, 5.3 TB/s memory BW
ehhh properly calling the functions "kernels", big <3 to Lisa Sue and/or the script writers
Some AI inference benchmarks, kind of cool but not super shocking.
comparison with H100 (not surprising) but back of the envelop puts Mi300 as within a few dozen percentage points of H200 when both in an SPR host machine with 8x GPGPU
building the foundation of AI for "x" years? sure.
We've been waiting/working on them since the fifth gen language discussions of the 80 and 90's
DAT DENSITY
OCP compliant is pretty pog NGL
NGL a little surprised to see oracle at an AI thing with AMD of all folks
"Open, proven and ready" is one way to put ROCm 😬
Love you guys and galls, but I hard disagree with the claim
You can't claim it's FOSS and that you accept work from FOSS when you won't accept patches from anyone :/
ROCm 6: adds support for FP8 (which ones?)
Graph compiler is cool but not that new.
still good to see as long as it gets *delivered*
Software partners is good, running natively* with pytorch and requiring no code is also good.
native support for Mi300 in trident from OpenAI
Meh, how many times has "software" 2.0 been brought up?
first with high level langs, then run time langs etc.
will "Ai" change some parts of software developement, probably?
"reshape" the enterprise, maybe? but every "new" thing has changed some parts of the enterprise, question is always how much
Back to the real presentation
ROCm 6 is "SoonTM" (next year? next quarter? etc.)
Ehhhhhhh dell getting Mi300! (knew it was coming, still good to see)
8xMi300X
LMAO, this guy from SM is a hoot xD
holy shit, 100 KW in a single Rack?!?!?!?! 😳
Can the term "Ai PC" die already? It's beyond cringe
ok so at this point looks like Mi300X maxes out at 8x GPUs
New plan for smart doorbells:
use different voice clips of VPs, principal engineers, CEOs etc. for saying "good morning"
opening up of infinity fabric is super cool.
I assume this is GPGPU infinity fabric, not chiplet to chiplet IF?
( @philparkbot ?)
@philparkbot ok, starting to think this is just Ultra Ethernet
Yeah, this is just ultra eth from the looks of it
#HPC MENTIONED LETS GOOOOOOOOOOOOOOOOO
MI300A in volume
4 IO dies (256 MB of L3 cache, also proably how they're buffering CPU to GPU cache coherence?)
3 Zen4 CCDs
6 GPU CCD
A little sad that Mi300A is "only" getting HBM3 and not 3e
Sort of expect it, but Mi300X is getting the "fun stuff"
#OpenFOAM mentioned LETS GOOOOOOOOOO
How many (max) Mi300As in a blade/node? 1? 2? 4? 8?
IIRC el cap is ~10% public science?
Either way, el cap will be an interesting machine
Also weird seeing LLNL referred to as a DOE lab, thought they were primarily an NNSA lab? (could be wrong)
ok now GIVE ME THE MI300C COWARDS
*please don't call it AI PCs, please, please, please*
but for real: ROCm on RDNA? please?
The first AI processor on x86 is wrong IIRC, intel was first with their AI voice processor based on movidius IP, tigerlake era IIRC?
Ok so we're now calling it "AI tops"
not a terrible name for int8?
39 ai tops I think is number one unless you go to dGPUs?
Even above Apples offerings IIRC
Clarification here, that's across the SoC, not just the NPU.
so would be number 2 to Apple
Still time for a "one more thing"
please do it lisa 🥺 gib Mi300C
Next time!
That's all folks!
Alan Sill@fclc “AI laptops”
Tom Hayward@fclc NNSA is part of DOE
Valentin Churavy 
@fclc NNSA is an organization within the DoE. So LLNL is a DoE lab. The big divisor is DoD vs DoE lab.
@fclc oh. I thought it was 3e indeed
@hattom yeah, Mi300A will be comparable to Grace Hopper *100*
Mi300X is against H200 (none Grace version)
Phil Park@fclc I believe that’s 256 MB of Infinity Cache aka MALL, not to be confused with the CPU L3/LLC.