HPC Guru (Twitter)

👇🧵 by @HatemLtaief on redesigning algorithms to utilize large L3 cache of AMD Milan-X to get a significant performance boost

Poster on temporal blocking using multicore #wavefront diamond (MWD) tiling technique
accepted at #SC22

#HPC
-----------
@HatemLtaief:
🚨 Latest results of #stencil computations using temporal blocking on @AMD #Epyc #MilanX 🚨

Expected but still wow! 🤩

Joint work w/ @LongQU and D. Keyes @KAUST_ECRC

#HPC #x86 #KAUSTResearch https://t.co/AwYG43VO5w

‌HPC Guru (Twitter)

RT @KAUST_ECRC: Exciting week ahead w/ #GTC23!
3 talks for fans on
- #astronomy Mar 22 10am CET
-#climate Mar 23 9am CET
- #genomics Mar 23 2pm CET

#HPC linear algebra are the 1st marines on the beach to accelerate them all💪

@yuxihong @Rabab_Mohammad @sameh_abdulah @HatemLtaief #KAUSTResearch https://t.co/weYANEBmxr

‌HPC Guru (Twitter)

RT @KAUST_ECRC: #HPC Status update of KSA by David Keyes.

Welcoming shaheen-3 by 2023-2024: #AMD Genoa CPU partition + #NVIDIA Grace-Hopper super chip #GPU partition.

#ISC23

@KAUST_HPC #KAUSTResearch https://t.co/Y4dJPLKCd1

HPC Guru (Twitter)

RT @HatemLtaief: ‼️Application bandwidth lovers❤️📣

🫣: #seismic app sustained bw scored on 6 CS-2 @CerebrasSystems (needed to host entirely our dataset) Vs NVIDIA A100, Fujitsu A64FX, NEC Aurora, AMD Rome, and Intel ice lake.

#CO2 Sequestration 🌍 w/ #MVM
#KAUSTResearch
#SRAM #HPC #SC23 #GB23 https://t.co/zSQBM5oNjr