libCEED icon indicating copy to clipboard operation
libCEED copied to clipboard

CEED Library: Code for Efficient Extensible Discretizations

Results 99 libCEED issues
Sort by recently updated
recently updated
newest added

Its not a pressing concern at this time, but I'd like to revisit the performance for BasisApplyAtPoints so we can see if its possible to eliminate the extra copy and/or...

performance

For certain applications using a non-tensor basis, the basis is quite sparse and the basis application can take advantage of this to increase performance. This FsSpMDM implementation in LIBXSMM benchmarks...

performance
CPU
LIBXSMM

The `/cpu/self/opt/*` backends should implement their own version of diagonal/full assembly that assembles by element. A lot of the pieces are all there in the code, but spread out. Current:...

enhancement
performance

Currently, we use header guards (though they are probably redundant in most cases) to protect our JiT files from multiple definitions during creation of the JiTTed code. We could use...

minor
GPU

Yeah, it is. But the important part is that is results in 1 scalar per node rather than 1 scalar per component per node (which is what `CeedElemRestrictionGetMultiplicity` gives out)....

This PR introduces physical entropy variables to libCEED fluids (see [Hughes et al](https://www.sciencedirect.com/science/article/pii/0045782586901271) for full formulation). Support for entropy variables mirrors that of primitive and conservative variables, with conversion and...

examples
1-In Review

This is part of a course project in collaboration with @jnclement and @amandashack . It adds support for computing the error for each component and converts the errors to the...

examples
1-In Review

Clang 16 now supports JIT. An interesting small project could be to create a `/cpu/self/clang-jit` backend that provides JITed tensor contraction kernels. If we see performance that is in the...

performance
CPU

We should design an interface by which a QFunction can have children associated with it that provide the action of submatrices. Then an Operator could automatically create a submatrix operator...

enhancement
interface

Summary --- Our diagonal assembly does more work and memory than it needs when we are working with uncoupled fields. We should have a way to indicate uncoupled fields to...

enhancement
performance