[julia-users] Re: ANN: ParallelAccelerator.jl v0.1 released

[Raj Barik]

After Julia's multithreading is ready for release, we will have a native 
path to interface with it. This will hopefully enable multiple shm 
execution paths for users to experiment with.


On Wednesday, October 21, 2015 at 9:12:50 AM UTC-5, Steven Sagaert wrote:
>
> Great news!
> Apart from the focus on parallelism, the architecture seems similar to 
> numba . 
> Good to finally have shared memory parallelism in Julia (not counting the 
> shared memory array under Linux via shm).
> I wonder how this is going to interact with the upcoming multithreading in 
> julia in the future. Will they play nice together or fight each other?
>
> Sincerely,
> Steven Sagaert
>
> On Wednesday, October 21, 2015 at 2:57:17 AM UTC+2, Lindsey Kuper wrote:
>>
>> The High Performance Scripting team at Intel Labs is pleased to announce 
>> the release of version 0.1 of ParallelAccelerator.jl, a package for 
>> high-performance parallel computing in Julia.
>>
>> ParallelAccelerator provides an @acc (short for "accelerate") macro for 
>> annotating Julia functions.  Together with a system C compiler (ICC or 
>> GCC), it compiles @acc-annotated functions to optimized native code.
>>
>> Under the hood, ParallelAccelerator is essentially a domain-specific 
>> compiler written in Julia. It performs additional analysis and optimization 
>> on top of the Julia compiler. ParallelAccelerator discovers and exploits 
>> the implicit parallelism in source programs that use parallel programming 
>> patterns such as map, reduce, comprehension, and stencil. For example, 
>> Julia array operators such as .+, .-, .*, ./ are translated by 
>> ParallelAccelerator internally into data-parallel map operations over all 
>> elements of input arrays. For the most part, these patterns are already 
>> present in standard Julia, so programmers can use ParallelAccelerator to 
>> run the same Julia program without (significantly) modifying the source 
>> code.
>>
>> Version 0.1 should be considered an alpha release, suitable for early 
>> adopters and Julia enthusiasts.  Please file bugs at 
>> https://travis-ci.org/IntelLabs/ParallelAccelerator.jl/issues .
>>
>> ParallelAccelerator requires Julia v0.4.0.  See our GitHub repository at 
>> https://github.com/IntelLabs/ParallelAccelerator.jl for a complete list 
>> of prerequisites, supported platforms, example programs, and documentation.
>>
>> Thanks to our colleagues at Intel and Intel Labs, the Julia team, and the 
>> broader Julia community for their support of our efforts!
>>
>> Best regards,
>> The High Performance Scripting team
>> (Programming Systems Lab, Intel Labs)
>>
>>

Re: [julia-users] ANN: ParallelAccelerator.jl v0.1 released

[Raj Barik]

Agreed.

On Wednesday, October 21, 2015 at 4:03:13 AM UTC-5, Tony Kelman wrote:
>
> The license looks like a totally standard BSD 2 to me, which is as 
> permissive as things get and essentially equivalent to MIT.
>
> Nice work to the Intel Labs team, it's great that this has been publicly 
> released. I hope to see the subset of the language that it can handle grow 
> over time. Leveraging the forthcoming built in Julia threading 
> infrastructure and embedded in-memory clang support should lead to 
> interesting possibilities for this as an analysis and auto parallelization 
> back end.
>