Fouzhan Hosseini
@FouzhanH
Followers
121
Following
4K
Media
28
Statuses
1K
Parallel Programming, Accelerators & HPC - Working @Intel - Opinions mine
UK
Joined January 2011
Happy 5th Anniversary, #oneAPI! Since its launch at Supercomputing 2019, oneAPI has transformed programming with an open, cross-platform model, now supported by millions of developers and the @UXLfoundation. https://t.co/4rHrohqcCJ
#UXLFoundation #SC24
0
9
20
The community-driven #oneAPI DevSummit hosted by the @UXLFoundation is hosting a number of informative keynotes this year, including a state of the union, the shortcomings of open source, and more. Don’t miss out. Get registered today: https://t.co/Zdgpq9RrOY
0
4
3
I appreciate the detailed @ServeTheHome article on the @Intel Xeon 6900P “Intel showed it is extremely competitive with both of AMD’s top-end Genoa and Bergamo Of course, AMD said its Turin processors are launching next quarter so this will change” #HPC #AI
1
2
14
Welcome back, @Intel! Today marks the first time in about 86 months that Intel has a leadership server x86 CPU again https://t.co/j2fm4ZgY1e
#HPC #AI via @ServeTheHome
2
8
38
Intel says Xeon 6900P CPUs, which scale up to 128 cores & 8800 MT/s memory speed, are a big deal for #AI computing, whether it’s for CPU-based #inferencing or serving as the host CPU for Nvidia-accelerated systems https://t.co/Il8Rdq88CA
#LLM #HPC via @DylanOnChips
crn.com
Intel explains why it sees “huge” AI opportunities for its new Xeon 6900P processors, whether it’s for CPU-based inferencing or serving as the head node for an Nvidia-accelerated system.
1
2
10
Improved AI workload performance, increased memory bandwidth, and twice the number of cores – Intel’s latest Xeon 6 processor delivers performance gains like never before. https://t.co/bGz5zOYRDk
2
28
120
Attending #ISC24 next week? Join the Intel special session with Andrew Richards (@codeandrew) on May 14 at 6:45 PM in Hall 4 to learn how developers and #HPC architects can accelerate software today using entirely open platforms. https://t.co/hV4XarcpAe
0
3
5
If you're attending #ISC24, join founder and CEO of @codeplaysoft, Andrew Richards (@codeandrew), for a special session discussing how projects like #UXLFoundation and open platforms can help developers and #HPC architects accelerate software today. https://t.co/KpYDjaCTyV
0
1
1
The #oneAPI Construction Kit lets you bring #SYCL and #oneAPI to new hardware. This introduction from our CEO Andrew shows you what it's all about - and you can try it for yourself here! https://t.co/1OnY5hNk3E
0
9
25
Explore the Supercomputer PACKage manager (Spack) created by @Livermore_Lab and how it streamlines the process of managing different software and package versions for HPC hardware: https://t.co/HpHLPnBKWQ
#oneAPI
0
4
6
Behind the plot to break @Nvidia’s grip on #AI by targeting software UXL Foundation, a consortium of tech companies, plans to build a suite of software and tools that will be able to power multiple types of AI accelerator chips https://t.co/ThFw1TtMEi
reuters.com
Nvidia earned its $2.2 trillion market cap by producing artificial-intelligence chips that have become the lifeblood powering the new era of generative AI developers from startups to Microsoft ,...
0
1
5
In this paper is presented the first performance evaluation of a scientific simulation application at scale on a supercomputer featuring Intel Max series (Ponte Vecchio) GPUs. https://t.co/rTG7qIohJP
3
19
78
Ethernet faces new challenges for #AI and #HPC workloads with new demands and increasing bandwidths. I overview those new requirements and challenges in the Hot Interconnects 2023 @IEEEHOTI Panel "Ethernet vs. Ethernot" talk. 📽️🔗🔜 https://t.co/kodAEyxlD1
2
15
48
Our plugins for #oneAPI are fully open source - you can build them yourself, or use our installer! https://t.co/AXkbkMAWAH
codeplay.com
Codeplay is internationally recognized for expertise in Heterogeneous Systems, and has many years of experience in the development of Compilers, Runtimes, Debuggers, Test Systems, and other special...
0
7
15
See how the new #SYCL Interoperability feature simplifies the process of migrating CUDA code to C++ using SYCLomatic while helping you achieve cross-platform portability and performance. https://t.co/5ddEK4KNVC
#oneAPI @SYCLstd
0
11
14
In the 2024.0.1 update to our #oneAPI plugins, we brought #SYCL-Graphs to Intel GPUs. These graphs can greatly optimize the kernel offloading process, and we've prepared this blog to tell you more! We'll be extending this feature to more GPUs soon. https://t.co/4AmdpsmjW7
codeplay.com
When working with accelerated applications, such as when using GPUs, developers write compute kernels that areexecuted one by one on the accelerator. This is...
0
6
17
Impressions from the #AI house in #Davos. Great discussion with Matthias Troyer about @Microsoft's first #AI-developed battery powering the little clock. Interesting #AI4Science panel with @HPE_Cray and @cscsch. More #AI4Climate #HPC and others 🌎 @ETH_AI_Center @ETH_en @wef
0
4
26
A £2.6 million ($3.3m) project will investigate storing waste heat from an @EPCCed #supercomputer in old mines, before using it to heat local homes https://t.co/M1iozaluMa
#HPC via @dcdnews
datacenterdynamics.com
£2.6m international feasibility study tests storing waste heat underground
0
5
12
