Lines Matching refs:backends

29 - Added non-tensor basis support to code generation backends `/gpu/cuda/gen` and `/gpu/hip/gen`.
30 - Added support to code generation backends `/gpu/cuda/gen` and `/gpu/hip/gen` for operators with b…
40 - OCCA backends were retired.
55 - Update `/cpu/self/memcheck/*` backends to help verify `CeedVector` array access assumptions and `…
57 - Added Sycl backends `/gpu/sycl/ref`, `/gpu/sycl/shared`, and `/gpu/sycl/gen`.
98 - Update `/cpu/self/memcheck/*` backends to help verify `CeedQFunctionContext` data sizes provided …
108 - Fix bug in setting device id for GPU backends.
109 - Fix storing of indices for `CeedElemRestriction` on the host with GPU backends.
134 - Enabled support for `p > 8` for `/gpu/*/shared` backends.
148 … MAGMA backends to use runtime compilation for tensor basis kernels (and element restriction kerne…
181 - Added JiT utilities in `ceed/jit-tools.h` to reduce duplicated code in GPU backends.
183 - Remove need to guard library headers in QFunction source for code generation backends.
189 - Added support for element matrix assembly in GPU backends.
210 …UNCTION_HELPER` macro to properly annotate QFunction helper functions for code generation backends.
221 ### Deprecated backends
223 …backends have been removed. These backends were intially added to test the backend inheritance mec…
242 - New HIP MAGMA backends for hipMAGMA library users: `/gpu/hip/magma` and `/gpu/hip/magma/det`.
243 - New HIP backends for improved tensor basis performance: `/gpu/hip/shared` and `/gpu/hip/gen`.
274 - CeedQFunction support for user `CUfunction`s in some backends
285 ### Deprecated backends
316   backends.  (Single source is coming soon for OCCA backends.)
374 For this release, several improvements were made. Two new CUDA backends were added to
375 the family of backends, of which, the new `cuda-gen` backend achieves state-of-the-art
385 Additionally, new CPU backends
386 were included in this release, such as the `/cpu/self/opt/*` backends (which are
461 four new CPU backends, two new GPU backends, CPU backend optimizations, initial
463 The new CPU backends in this release came in two families. The `/cpu/self/*/serial`
464 backends process one element at a time and are intended for meshes with a smaller number
465 of high order elements. The `/cpu/self/*/blocked` backends process blocked batches of
467 The `/cpu/self/avx/*` backends rely upon AVX instructions to provide vectorized CPU
468 performance. The `/cpu/self/xsmm/*` backends rely upon the
470 performance. The `/gpu/cuda/*` backends provide GPU performance strictly using CUDA.
590 libCEED functionality through MAGMA kernels as one of libCEED’s computational backends.
681 This release contained several backends: `/cpu/self`, and backends which rely upon the