tbb

Using the Intel® Threading Building Blocks Graph Community Preview Feature: Creating a Simple Message Graph.

Intel® Threading Building Blocks (Intel® TBB) Version 3 Update 5 introduced the class graph as a Community Preview (CP) feature. There is an introductory post that provides an overview of the class and the nodes that can be used with it.

TBB 3.0 and processor affinity

A week ago I started telling about a couple of new helpful features in the TBB 3.0 Update 4 task scheduler, and we talked about the support for processor groups – an extension of Win32 API available in 64-bit edition of Windows 7. The main purpose of processor groups is to extend Win32 capabilities to allow applications work with more than 64 logical CPUs.

Intel® Threading Building Blocks Version 3.0 Update 5 Introduces Graph as a Community Preview Feature.

There are some applications that, even on systems with shared memory, are best organized as computations that explicitly pass messages. These messages may contain data or simply act as signals that a computation has completed. The new class graph and its associated nodes can be used to express such applications. These classes are available as a Community Preview (CP) feature in Intel® Threading Building Blocks Version 3.0 Update 5.

TBB 3.0, high end many-cores, and Windows processor groups

Though I wrote my previous TBB task scheduler blog just a few days after TBB 3.0 Update 4 had been released, I ignored that remarkable event, and instead delved into more than two year old past. So today I’m going to redeem that slight, and talk about a couple of small but quite useful improvements in the TBB scheduler behavior made in the aforementioned update.

Article worth checking out: ACM Queue; Photoshop Scalability: Keeping It Simple

There is an interview in ACM discussing parallelism in Adobe Photoshop - "ACM Queue; Photoshop Scalability: Keeping It Simple." I think this article is worth reading if you are interested in parallel programming. It covers the earliest uses of parallelism for what I call "convenience" instead of "performance" and how that evolved when parallel programming could yield performance boosts. The interview also talks about the methods of decomposing algorithms that have worked best for Photoshop.

Pagine

Iscriversi a tbb