|
|
ArrayFire Whitepaper:
High-level GPU Computing in C,
C++, Fortran, and Python
|
|
ArrayFire is a software platform developed at AccelerEyes that allows
users and programmers to rapidly develop data-parallel programs in C,
C++, Fortran, and Python. ArrayFire provides a simple, high-level
matrix abstraction over low-level GPU APIs such as CUDA, OpenCL, and
OpenGL along with thousands of GPU-tuned functions to allow users in
science, engineering, and finance to take full advantage of GPU
hardware. The combination of an easy-to-use array interface, automatic
memory management, on-the-fly compilation, parallel GPU FOR-loop
construction, and interactive hardware-accelerated graphics library,
make ArrayFire well suited to rapid prototyping of data-parallel
algorithms and building end-to-end applications.
|
|
|
Jacket Whitepaper:
High-level GPU Computing with
Matlab®
|
|
The emergence of new software tools and cost-effective GPU-based computers are
ushering in a new era for scientists, engineers and analysts working on
technical problems. The platform, Jacket, described in this paper offers a
more productive platform for non-computer scientists looking for ways to
leverage the computational capabilities of GPUs. Jacket utilizes the
M-language, and the flexibility of MATLAB from The MathWorks, to provide much
larger population of users the benefit of GPU technology. Jacket abstracts all
of the complexity of GPU and CUDA programming from the user and addresses the
underlying challenges associated with programming GPUs. The Jacket
architecture takes into account all of the possible roadblocks associated with
high performance GPU applications so that the technical computing user can
focus on science, engineering or analytics.
|
