| #
d4cc1845
|
| 30-Dec-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
Merge pull request #1912 from CEED/jeremy/copyright
minor - update copyright to 2026
|
| #
9ba83ac0
|
| 19-Dec-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
minor - update copyright to 2026
|
| #
7f85f93f
|
| 30-Sep-2025 |
James Wright <james@jameswright.xyz> |
Merge pull request #1896 from CEED/jrwrigh/clang-penalty-paren
style: Change clang-format to penalize newline after open ()
|
| #
1a8516d0
|
| 30-Sep-2025 |
James Wright <james@jameswright.xyz> |
style: Change clang-format to penalize newline after open ()
|
| #
41ece66e
|
| 29-Jul-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
Merge pull request #1877 from CEED/jeremy/shared-collocated
Shared/gen Collocated Bases (BP 5/6)
|
| #
02219a08
|
| 28-Jul-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
hip - collocated nodes/qpts for shared
|
| #
297af36d
|
| 06-May-2025 |
Zach Atkins <zach.atkins@colorado.edu> |
Merge pull request #1819 from CEED/zach/mi300a-fixes
Reworks the stream implementation for `/gpu/hip/gen` to avoid creating and destroying streams on every operator apply.
Updates `hipblas` calls t
Merge pull request #1819 from CEED/zach/mi300a-fixes
Reworks the stream implementation for `/gpu/hip/gen` to avoid creating and destroying streams on every operator apply.
Updates `hipblas` calls to only sync stream, this matters on MI300A since `hipblas` seems to use an async stream. Avoids a full device sync.
Also makes working vectors come from the `Vector` object delegate to avoid bad ref behavior.
show more ...
|
| #
b46df0d2
|
| 06-May-2025 |
Zach Atkins <Zach.Atkins@colorado.edu> |
Add missing CeedDestroy
|
| #
20a16a5f
|
| 20-Mar-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
Merge pull request #1786 from CEED/jeremy/copy-headers
minor - upate copyright to 2025
|
| #
d275d636
|
| 19-Mar-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
minor - upate copyright to 2025
|
| #
c48f2a80
|
| 10-Mar-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
Merge pull request #1773 from CEED/jeremy/basis-t1d
Make BASIS_T_1D explicit template parameter
|
| #
6b92dc4b
|
| 10-Mar-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
hip - use BASIS_T_1D in codegen
|
| #
6a744a64
|
| 26-Feb-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
Merge pull request #1758 from CEED/jeremy/gpu-composite
Gen Composite Operators
|
| #
e9c76bdd
|
| 19-Feb-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
gpu - allow running shared kernels on stream
|
| #
f0f0e83c
|
| 13-Feb-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
Merge pull request #1756 from CEED/jeremy/shame-on-me
hip - fix bug, need to actually get kernels
|
| #
a8772291
|
| 13-Feb-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
hip - fix bug, need to actually get kernels
|
| #
8c2d8641
|
| 13-Feb-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
Merge pull request #1754 from CEED/jeremy/shared-points-transpose
gpu - add Transpose/TransposeAdd variants for AtPoints
|
| #
af0e6e89
|
| 13-Feb-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
gpu - add Transpose/TransposeAdd variants for AtPoints
|
| #
39577a10
|
| 11-Feb-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
Merge pull request #1744 from CEED/zach/vec-api
Bases should use Vec APIs
|
| #
759e0bc3
|
| 11-Feb-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
minor - style consistency
|
| #
11ac676f
|
| 24-Jan-2025 |
Zach Atkins <Zach.Atkins@colorado.edu> |
Update hip basis code to conform to vector interfaces
|
| #
20e9c75b
|
| 15-Jan-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
Merge pull request #1729 from CEED/jeremy/shared-null-checks
Check for interp, grad in shared backends
|
| #
4cbc44e0
|
| 15-Jan-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
minor - check for interp, grad in shared backends
|
| #
79881bbe
|
| 14-Jan-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
Merge pull request #1727 from CEED/zach/hip-nontensor-fix
Fix issue in block sizing for GPU shared basis
|
| #
2c98d61c
|
| 14-Jan-2025 |
Jeremy L Thompson <jeremy@jeremylt.org> |
Merge pull request #1726 from CEED/jeremy/shared-fallback
Fallback if nontensor shared uses too much mem
|