Hi,
at our March meeting (18.3. in the C-Base) we will have Peter Gottschling from Dresden with a talk about productive scientific computing in general and the matrix template library (MTL) in detail, see below. Peter is the head of the german delegation in the C++ standard commitee and he is very well known for his contributions to the scientific programming community. As always, we meet at 7, the talk starts at 8.
Abstract:
The Matrix Template Library v4 (MTL4) has been proven to provide high
performance on different platforms while -- maybe even more
importantly -- allowing for high productivity in the development
process. The intuitive notation provides an easy entry level and quick
programming progress while scientists do not need to waste their time
with deep technical details. We will demonstrate how applications
can be written as easily as in Matlab. Multi-threading acceleration
can be enabled by compiler flags. The CUDA version of MTL4 is designed with
the goal to enable the same productivity on GPGPUs while allowing for
maximal performance. MTL4 has the same interface on GPUs as on
CPUs so that all applications can use CUDA without
program modifications. The talk shall give an overview of intuitive
MTL4 programming and an easy way for cross-platform portability.
at our March meeting (18.3. in the C-Base) we will have Peter Gottschling from Dresden with a talk about productive scientific computing in general and the matrix template library (MTL) in detail, see below. Peter is the head of the german delegation in the C++ standard commitee and he is very well known for his contributions to the scientific programming community. As always, we meet at 7, the talk starts at 8.
Abstract:
The Matrix Template Library v4 (MTL4) has been proven to provide high
performance on different platforms while -- maybe even more
importantly -- allowing for high productivity in the development
process. The intuitive notation provides an easy entry level and quick
programming progress while scientists do not need to waste their time
with deep technical details. We will demonstrate how applications
can be written as easily as in Matlab. Multi-threading acceleration
can be enabled by compiler flags. The CUDA version of MTL4 is designed with
the goal to enable the same productivity on GPGPUs while allowing for
maximal performance. MTL4 has the same interface on GPUs as on
CPUs so that all applications can use CUDA without
program modifications. The talk shall give an overview of intuitive
MTL4 programming and an easy way for cross-platform portability.
Keine Kommentare:
Kommentar veröffentlichen