Tag: Microsoft
Summer C++ AMP Courses by Acceleware and Microsoft
C++ Accelerated Massive Parallelism (C++ AMP) accelerates the execution of your C++ code by taking advantage of the data-parallel hardware that’s commonly present as a graphics processing unit (GPU) on a discrete graphics card.
GoingNative 7: VC11 Auto-Vectorizer, C++ NOW, Lang.NEXT
Most of the time is spent discussing VC11′s Auto-Vectorizer with a few short forays into other VC compiler improvements (like Auto-Parallelizer).
Microsoft published Accelerated Massive Parallelism for C++ Specs
Microsoft on Friday announced the publication of the C++ Accelerated Massive Parallelism (AMP) specification. This specification lets C++ developers write programs that can compile and execute on data-parallel hardware like discrete graphics cards or the SIMD vector instruction set in a processor.
C++ and Beyond 2011: Concurrency and Parallelism
Watch panel on Concurrency and Parallelism with Scott, Andrei and Herb Sutter at C++ and Beyond 2011 meeting
Microsoft Patents GPU-accelerated Window Manager
Could Windows 8 be getting a GPU-accelerated window manager? Microsoft received a patent that explains a “compositing desktop window manager”. The patent was confirmed on November 15 and was filed about a year ago as an update to a 2007 patent.
Fast Fourier Transforms (FFT) on the GPU Part II: C++ AMP FFT Test Application
his is the second part of Fast Fourier Transforms (FFT) on the GPU tutorial written by Yossi Levanoni of Microsoft. It further demonstrates how to use multi-dimensional transformations, and inverse transformations.
Fast Fourier Transforms (FFT) on the GPU. Part I: C++ AMP FFT Library
This tutorial focused on general application of FFT for graphics processing units (GPUs) with C++ AMP FFT Library.
PTask: operating system abstractions to manage GPUs as compute devices
We propose a new set of OS abstractions to support GPUs and other accelerator devices as first class computing resources. These new abstractions, collectively called the PTask API
GTC Express Webinar: Heterogeneous Data-Parallel Programming
Wednesday, November 16, 2011 9:00 AM – 10:00 AM PST In this webinar, Satnam Singh, Professor of Reconfigurable Computing, School of Computer Science, University of Birmingham (UK), will demonstrate data-parallel programming with Microsoft’s Accelerator system. The system provides a language neutral library for expressing whole-array computations which can be dynamically compiled into code for execution…
SIGGRAPH Asia 2011: GPU-efficient recursive filtering and summed-area tables
This video present a new algorithmic framework for parallel evaluation. It partitions the image into 2D blocks, with a small band of additional data buffered along each block perimeter.
