Sriram Ramkrishna · @sri
99 followers · 356 posts · Server mast.hpc.social

howdy all! Just wanted to let y'all know that we have an meetup with David Airlie titled

"Why compute needs commoditization and currently sucks?"

Come join us this Friday at 4:30pm PT!

meetup.com/oneapi-community-us

#oneapi #sycl #cuda

Last updated 1 year ago

Sriram Ramkrishna · @sri
87 followers · 328 posts · Server mast.hpc.social

For those who have waited eagerly for the recording of our meetup with @karolherbst - here it is! youtu.be/KUze0JbPSy8
- if you are interested in joining our oneAPI meetup - feel free to subscribe here - meetup.com/oneapi-community-us

Next time we will be meeting with Stephano Cetola who will be talking about RISC-V, onAPI, and other things.

#oneapi #sycl #opencl #rustlang

Last updated 1 year ago

Sriram Ramkrishna · @sri
85 followers · 313 posts · Server mast.hpc.social

Next week Meetup will feature @karolherbst - they'll be talking about rusticl, how openCL works in Mesa, and varriers to and any other questions people want to entertain. :)
meetup.com/oneapi-community-us

Please boost to those who might be interested ! :)

#oneapi #sycl

Last updated 1 year ago

Felix LeClair(received offers) · @fclc
409 followers · 1296 posts · Server mast.hpc.social

(Thread)

Wanted to give a quick thanks to @sri for having me on as part of the Accelerated compute panel yesterday

Had a good time discussing what does and doesn't work across oneAPI, and how to deal with SYCL as a standard.

I also want to reiterate that SYCL or oneAPI as standards are not "magic bullets" for performance across all hardware

The major point of them, like most libraries and software stacks, is to get you to ~90% of performance without having to rewrite the stack

#oneapi #sycl

Last updated 1 year ago

pafurijaz · @pafurijaz
137 followers · 899 posts · Server mstdn.social

This photo is emblematic!
China
1,411,750,000 Estimated population
Indian
1,425,775,850 Estimated population
Europe
745,173,774 population
USA
333,287,557 population

#world #sycl #oneapi

Last updated 1 year ago

Yaroslav Khnygin · @surabax
48 followers · 457 posts · Server mastodon.ie

Intel's Codeplay Announces oneAPI Construction Kit For Bringing SYCL To New Hardware
phoronix.com/news/oneAPI-Const

"This open-source project aims to help ease bringing up SYCL on new processor/accelerator architectures, particularly around HPC and AI. The oneAPI Construction Kit also has a reference implementation for RISC-V."

#iamintel #intel #oneapi #HeterogeneousComputing #gpu #gpgpu #hpc #ai #sycl #riscv

Last updated 1 year ago

Laura Reznikov · @TheAnimator
71 followers · 16 posts · Server graphics.social

Intel Embree 4.1 is now available with real-time through hardware acceleration on Intel GPUs — gain productivity using a single codebase for both CPU and GPU rendering. Learn more: intel.ly/3Mtt7c9

#rendering #raytracing #sycl

Last updated 1 year ago

Giuseppe Bilotta · @giuseppebilotta
147 followers · 248 posts · Server fediscience.org

Corporate at its worst: controls the library and its , and backend. provides rocThrust, that is just Thrust with the CUDA part stripped an a new backend for / . Nobody* is working on a backend for
provides its own alternative as , which is NOT a drop-in replacement.

This is why we can't have nice things.

*there's a dead project here
github.com/wdmapp/syclthrust

#onedpl #oneAPI #intel #sycl #hip #ROCm #amd #tbb #OpenMP #CUDA #thrust #nvidia #floss

Last updated 2 years ago

Andrew Richards · @Codeandrew
106 followers · 39 posts · Server mastodon.gamedev.place

When we work on , we're adding new capabilities to C++ to enable offloading to accelerators like GPUs and get huge performance. But what about mainstream C++ programmers? We're working on bringing these features to ISO C++ so every C++ developer will be able to exploit the performance of accelerators: youtube.com/watch?v=hqhs72ItT6

#sycl

Last updated 2 years ago

Khronos Group · @thekhronosgroup
90 followers · 29 posts · Server fosstodon.org

Just announced at IWOCL / SYCLcon, the Khronos Group has released SYCL 2020 Revision 7.

See what changes were made: khronos.org/news/permalink/khr

#sycl

Last updated 2 years ago

Sriram Ramkrishna · @sri
82 followers · 295 posts · Server mast.hpc.social

Please to announce the CfP for the DevSummit on June 13th 2023 Online is open! Looking forward to seeing your submitted talks!

easychair.org/cfp/ODS23

#oneapi #hpc #sycl #oneapidev

Last updated 2 years ago

Felix LeClair (Wants a job😊) · @fclc
379 followers · 863 posts · Server mast.hpc.social

OK but for real: Since the name DPCPP is being deprecated in favor of ICPX with the -fsycl flag, can we please move to the name iSYCL?

Upstream name of the DPCPP project is staying as the reference implementation.

The intel packaged version no longer has a catchy name 😔

#isycl #intel #sycl #dpcpp

Last updated 2 years ago

Felix LeClair (Wants a job😊) · @fclc
379 followers · 861 posts · Server mast.hpc.social

In slight need of spec/language lawyers: Reading this line ( registry.khronos.org/OpenCL/sp), do you think:
A: that the minimum allocation of the max mem allocation flag is 1:4?
B: that the max allocation must be max(min(1024 × 1024 × 1024, 1/4th of CL_DEVICE_GLOBAL_MEM_SIZE), 32 × 1024 × 1024)

in other words, given a 16GB card, should the maximum allocation be 4GB, or should the minimum of the max allocation be 4GB?





#opencl #sycl #khronos #hpc #gpgpu

Last updated 2 years ago

Khronos Group · @thekhronosgroup
70 followers · 17 posts · Server fosstodon.org

Introducing Khronos Discord! A new way for the community to interact with each other and learn more about Khronos related APIs (glTF, OpenXR, OpenCL, SYCL, etc...)

Help us build the community, join today!

khr.io/khrdiscord

#gltf #openxr #opencl #api #sycl #opengl

Last updated 2 years ago

Giuseppe Bilotta · @giuseppebilotta
140 followers · 190 posts · Server fediscience.org

Why am I so interested in for ? (See also my nudge nudge wink wink at @sri <fediscience.org/@giuseppebilot>)
Because SYCL is today the best bet we have at a unified API, and introducing such a backend would have great potential for our aims of “universal hardware support”.

#gpgpu #GPUSPH #sycl

Last updated 2 years ago

Giuseppe Bilotta · @giuseppebilotta
140 followers · 189 posts · Server fediscience.org

The most important is definitely our dependency on in a couple of places, but the extensive use of constant and shared memory is also a problem, since the syntax for their use in is very different from the one in , which would pose a problem for our plans to keep the device source code unified across APIs.

#CUDA #sycl #thrust

Last updated 2 years ago

Giuseppe Bilotta · @giuseppebilotta
140 followers · 188 posts · Server fediscience.org

Here's another interesting thing about on : currently, it uses the backend, because the only backends available in are for and through . I've actually looked at adding support too, but there are a few structural issues that currently prevent a solution as straightforward as the one used to implement CPU and HIP support.

#sycl #hip #amd #CUDA #nvidia #gpu #cpu #android #GPUSPH

Last updated 2 years ago

Sriram Ramkrishna · @sri
79 followers · 273 posts · Server mast.hpc.social

The meetup this week is going to rock - we have @illuhad giving a talk, but we also have Ronan from Tri-SYCL also showing up - mini con, ya'll? :-)
meetup.com/oneapi-community-us

#sycl

Last updated 2 years ago

Sriram Ramkrishna · @sri
79 followers · 271 posts · Server mast.hpc.social

Excited to have @illuhad on our meetup to talk about "Open SYCL"! Come join us this friday at 11:30am PT and have a conversation with Aksel and others as we talk about.

#sycl #oneapi

Last updated 2 years ago

Sriram Ramkrishna · @sri
79 followers · 268 posts · Server mast.hpc.social

I wrote the (maybe final?) post on modern software development tools for oneAPI on Linux -
dev.to/oneapi/modern-software-

#sycl #oneapi #gnome #linuxapps

Last updated 2 years ago