At #ISC23, @intel's Jeff McVeigh going through AI-accelerated #hpc. Either AI helping reduce large problems, or AI hardware being used for reduced precision in HPC
If you hadn't seen it, Intel's AI roadmap. Falcon Shores is the output of GPU+AI.
GPU Max.
128 Xe Cores
128 GB HBM2e
52 TF FP64
839 TOP BF16
And just to clarify, Falcon shores first gen is a converged Xe + AI (habana) IP design. First point here. Even though its called a GPU overall.
The status on #aurora: 10000 blades delivered, each with 2 CPU + 6 GPU. Blades initially shipped with regular @intel CPU, now 75% replaced with Max CPU (hence why no #Top500 sub).
But 63744 GPUs at 52 TF/GPU means an Rpeak of around 3.3 ExaFLOP FP64!! That's not counting CPUs
(That's assuming each GPU is the full fat 600W node - I need to go back to my original estimates I did on AnandTech where I calculated 560W ea)
• • •
Missing some Tweet in this thread? You can try to
force a refresh
➡️ Data Center $1.3b
- down 11% YoY
- up 2% QoQ
➡️Client $997m
- down 54% YoY
- up 35% QoQ
➡️Gaming $1.6b
- down 4% YoY
- down 10% QoQ
➡️Embedded $1.5b
- up 16% YoY
- down 7% QoQ
Overall strong results vs expectation, but operating loss of $20m, yet net income gain of $27m. A mix of weakness in some markets and good strength in others.
Also, $135m to expand adaptive computing research operations in Ireland.
So Data Center:
➡️ Revenue $1.3b
- lower 3rd Gen EPYC sales
-- Enterprise demand was soft
-- Cloud inventory was elevated
- But revenue up 2% QoQ
-- 4th Gen EPYC CPU sales doubled
-- offset a decline in adaptive SoC DC
- MI300A and MI300X are sampling to HPC, cloud, and AI