[arsTechnica] Write AI code once, run anywhere—it’s not Java, it’s Intel’s oneAPI - Overclock.net - An Overclocking Community

Forum Jump: 

[arsTechnica] Write AI code once, run anywhere—it’s not Java, it’s Intel’s oneAPI

 
Thread Tools
post #1 of 3 (permalink) Old 11-20-2019, 08:06 AM - Thread Starter
sudo apt install sl
 
WannaBeOCer's Avatar
 
Join Date: Dec 2009
Posts: 5,737
Rep: 179 (Unique: 123)
[arsTechnica] Write AI code once, run anywhere—it’s not Java, it’s Intel’s oneAPI

Source: https://arstechnica.com/gadgets/2019...rate-hardware/

Quote:
Saturday afternoon (Nov. 16) at Supercomputing 2019, Intel launched a new programming model called oneAPI. Intel describes the necessity of tightly coupling middleware and frameworks directly to specific hardware as one of the largest pain points of AI/Machine Learning development. The oneAPI model is intended to abstract that tight coupling away, allowing developers to focus on their actual project and re-use the same code when the underlying hardware changes.

This sort of "write once, run anywhere" mantra is reminiscent of Sun's early pitches for the Java language. However, Bill Savage, general manager of compute performance for Intel, told Ars that's not an accurate characterization. Although each approach addresses the same basic problem—tight coupling to machine hardware making developers' lives more difficult and getting in the way of code re-use—the approaches are very different.

Silent
(20 items)
CPU
Core i9 9900K... CoffeeTime! @ 5.1Ghz w/ 1.36v
Motherboard
Maximus VIII Formula
GPU
Radeon VII @ 2100Mhz/1250Mhz w/ 1218mV
RAM
TeamGroup Xtreem 32GB 3200Mhz CL15
Hard Drive
HP EX950 2TB
Hard Drive
Samsung 850 Evo 1TB
Hard Drive
Samsung 850 Evo 1TB
Power Supply
EVGA SuperNova 1200w P2
Cooling
EK Supremacy Full Copper Clean
Cooling
XSPC D5 Photon v2
Cooling
Black Ice Gen 2 GTX360 x2
Cooling
EK-Vector Radeon VII - Copper + Plexi
Case
Thermaltake Core X5 Tempered Glass Edition
Operating System
Clear Linux
Monitor
Acer XF270HUA
Keyboard
Cherry MX Board 6.0
Mouse
Logitech G600
Mouse
Alugraphics GamerArt
Audio
Definitive Technology Incline
Audio
SMSL M8A
▲ hide details ▲
WannaBeOCer is online now  
Sponsored Links
Advertisement
 
post #2 of 3 (permalink) Old 11-20-2019, 10:17 AM
Overclocker
 
JackCY's Avatar
 
Join Date: Jun 2014
Posts: 10,241
Rep: 344 (Unique: 243)
There is more to it than that.
You want fast code and control, you need low level = you write for specific hardware.
You can't do that? You leave it up to others = compiler does it for you with some degree of success.
You don't want compiled code? You end up with intermediate code and interpreters aka slow Java, Python, etc.
Still too much? You put it on the web And say good bye to any sensible performance.

Just like others have middleware and APIs, now Intel is making their own stab at AI as it is trying to go after that market segment after being side railed by Nvidia for so long.

OneAPI has been around a while, no idea what's so new about it. Yet another marketing announcement really.

It's just Intel's API/middleware while others have their own. It's not a universal hardware agnostic API that tries to run well on all hardware like one could say about Vulkan, OGL, etc.


All in all so far it looks like AMD sold their GPU engineers to Intel and they are replicating their work there, same things done under different brand name with a bigger budget. It's a shame AMD threw the towel in so badly on the GPU front. But then NV has already killed off ATI long ago and AMD doesn't have the will to fight on GPUs.
JackCY is offline  
post #3 of 3 (permalink) Old 11-20-2019, 10:32 AM - Thread Starter
sudo apt install sl
 
WannaBeOCer's Avatar
 
Join Date: Dec 2009
Posts: 5,737
Rep: 179 (Unique: 123)
Quote: Originally Posted by JackCY View Post
There is more to it than that.
You want fast code and control, you need low level = you write for specific hardware.
You can't do that? You leave it up to others = compiler does it for you with some degree of success.
You don't want compiled code? You end up with intermediate code and interpreters aka slow Java, Python, etc.
Still too much? You put it on the web And say good bye to any sensible performance.

Just like others have middleware and APIs, now Intel is making their own stab at AI as it is trying to go after that market segment after being side railed by Nvidia for so long.

OneAPI has been around a while, no idea what's so new about it. Yet another marketing announcement really.

It's just Intel's API/middleware while others have their own. It's not a universal hardware agnostic API that tries to run well on all hardware like one could say about Vulkan, OGL, etc.


All in all so far it looks like AMD sold their GPU engineers to Intel and they are replicating their work there, same things done under different brand name with a bigger budget. It's a shame AMD threw the towel in so badly on the GPU front. But then NV has already killed off ATI long ago and AMD doesn't have the will to fight on GPUs.
Intel announced that OneAPI was in development December of 2018 and their Toolkit was just released two days ago: https://software.intel.com/en-us/oneapi/base-kit. So no, OneAPI hasn't been around for a while. The tools inside of OneAPI might be old but many of them are new. You're absolutely right that OneAPI/ROCm even though they're open source they are still hardware dependent.

AMD didn't quit and they also announced some awesome updates in ROCm 3.0 two days ago as well. https://www.phoronix.com/scan.php?pa...-3.0-Announced

Quote:
AMD mentions the ROCm 3.0 highlights as:
- Introduction of ROCm 3.0 with new innovations to support HIP-clang – a compiler built upon LLVM, improved CUDA conversion capability with hipify-clang, library optimizations for both HPC and ML.
- ROCm upstream integration into leading TensorFlow and PyTorch machine learning frameworks for applications like reinforcement learning, autonomous driving, and image and video detection.
- Expanded acceleration support for HPC programing models and applications like OpenMP programing, LAMMPS, and NAMD.
- New support for system and workload deployment tools like Kubernetes, Singularity, SLURM, TAU and others.

Silent
(20 items)
CPU
Core i9 9900K... CoffeeTime! @ 5.1Ghz w/ 1.36v
Motherboard
Maximus VIII Formula
GPU
Radeon VII @ 2100Mhz/1250Mhz w/ 1218mV
RAM
TeamGroup Xtreem 32GB 3200Mhz CL15
Hard Drive
HP EX950 2TB
Hard Drive
Samsung 850 Evo 1TB
Hard Drive
Samsung 850 Evo 1TB
Power Supply
EVGA SuperNova 1200w P2
Cooling
EK Supremacy Full Copper Clean
Cooling
XSPC D5 Photon v2
Cooling
Black Ice Gen 2 GTX360 x2
Cooling
EK-Vector Radeon VII - Copper + Plexi
Case
Thermaltake Core X5 Tempered Glass Edition
Operating System
Clear Linux
Monitor
Acer XF270HUA
Keyboard
Cherry MX Board 6.0
Mouse
Logitech G600
Mouse
Alugraphics GamerArt
Audio
Definitive Technology Incline
Audio
SMSL M8A
▲ hide details ▲

Last edited by WannaBeOCer; 11-20-2019 at 10:37 AM.
WannaBeOCer is online now  
Reply

Quick Reply
Message:
Options

Register Now

In order to be able to post messages on the Overclock.net - An Overclocking Community forums, you must first register.
Please enter your desired user name, your email address and other required details in the form below.
User Name:
If you do not want to register, fill this field only and the name will be used as user name for your post.
Password
Please enter a password for your user account. Note that passwords are case-sensitive.
Password:
Confirm Password:
Email Address
Please enter a valid email address for yourself.
Email Address:

Log-in



Currently Active Users Viewing This Thread: 1 (0 members and 1 guests)
 
Thread Tools
Show Printable Version Show Printable Version
Email this Page Email this Page


Forum Jump: 

Posting Rules  
You may post new threads
You may post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are Off
Pingbacks are Off
Refbacks are Off