Home
last modified time | relevance | path

Searched refs:backends (Results 1 – 19 of 19) sorted by relevance

/libCEED/doc/sphinx/source/
H A Dgpu.md3 Runtime selection of libCEED backends allows users to use CPU backends for easier debugging.
4 Code that produces correct results with CPU backends will produce correct results on GPU backends, …
13 …ntents of this source file and all included files are used during JiT compilation for GPU backends.
16 These source file must only contain syntax constructs supported by C99 and all targeted backends (i…
22 GPU backends require stricter adherence to memory access assumptions, but CPU backends may occasion…
30 The `/cpu/self/memcheck` backends explicitly verify read-only and write-only memory access assumpti…
H A DlibCEEDdev.md6 Different Ceed backends are selected by instantiating a different {ref}`Ceed` object to create the …
12 …ith a corresponding `CEED_FTABLE_ENTRY` in `/interface/ceed.c` to allow backends to set their own …
13 …the backend specific implementation of the object, typically found in `/backends/[impl]/ceed-[impl…
14 Any supplemental functions intended to be used in the interface or by the backends may be added to …
51 This backend contains the basic implementations of most objects that other backends rely upon.
52 Most of the other CPU backends only update the {ref}`CeedOperator` and `CeedTensorContract` objects.
54 The `/cpu/self/ref/blockend` and `/cpu/self/opt/*` backends delegate to the `/cpu/self/ref/serial` …
56 The `/cpu/self/opt/*` backends update the {ref}`CeedOperator` to apply the action of the operator i…
59 …he `/cpu/self/avx/*` and `/cpu/self/xsmm/*` backends delegate to the corresponding `/cpu/self/opt/…
60 These backends update the `CeedTensorContract` objects using AVX intrinsics and libXSMM functions, …
[all …]
H A Dreleasenotes.md29 - 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…
[all …]
H A Dintro.md24 … illustrated in {numref}`fig-libCEED-backends`, where a non-exhaustive list of specialized impleme…
27 …tion at run time. Moreover, each process or thread can instantiate an arbitrary number of backends.
29 (fig-libceed-backends)=
H A DlibCEEDapi.md182 …in turn, can represent one or more physical devices, as long as libCEED backends support such conf…
200 … is that it already includes all the finite element information, so the backends can operate on li…
202 The separation of the front- and backends enables applications to easily switch/try different backe…
207 [ceed-ref.c](https://github.com/CEED/libCEED/blob/main/backends/ref/ceed-ref.c).
262 This is used by backends that support Just-In-Time (JIT) compilation (i.e., CUDA and HIP) to compil…
263 For full support across all backends, these {ref}`CeedQFunction` source files must only contain con…
390 LibCEED is intended to be extensible via backends that are packaged with the library and packaged s…
393 ```{literalinclude} ../../../backends/ref/ceed-ref.c
405 We have less experience with external packaging of backends and do not presently guarantee source o…
406 We'd love to talk with you if you're interested in packaging backends externally, and will work wit…
/libCEED/
H A DMakefile289 …ot-$(if $(for_install),default,install).c, $(wildcard interface/ceed*.c backends/weak/*.c gallery/…
295 ref.c := $(sort $(wildcard backends/ref/*.c))
296 blocked.c := $(sort $(wildcard backends/blocked/*.c))
297 ceedmemcheck.c := $(sort $(wildcard backends/memcheck/*.c))
298 opt.c := $(sort $(wildcard backends/opt/*.c))
299 avx.c := $(sort $(wildcard backends/avx/*.c))
300 xsmm.c := $(sort $(wildcard backends/xsmm/*.c))
302 cuda.c := $(sort $(wildcard backends/cuda/*.c))
303 cuda.cpp := $(sort $(wildcard backends/cuda/*.cpp))
304 cuda-ref.c := $(sort $(wildcard backends/cuda-ref/*.c))
[all …]
H A DREADME.md67 Note that SYCL backends require building with oneAPI compilers as well:
146 There are multiple supported backends, which can be selected at runtime in the examples:
160 | `/cpu/self/memcheck/*` | Memcheck backends, undefined value checks | Yes …
187 The `/cpu/self/*/serial` backends process one element at a time and are intended for meshes with a …
188 The `/cpu/self/*/blocked` backends process blocked batches of eight interlaced elements and are int…
190 The `/cpu/self/ref/*` backends are written in pure C and provide basic functionality.
192 The `/cpu/self/opt/*` backends are written in pure C and use partial e-vectors to improve performan…
194 The `/cpu/self/avx/*` backends rely upon AVX instructions to provide vectorized CPU performance.
196 The `/cpu/self/memcheck/*` backends rely upon the [Valgrind](https://valgrind.org/) Memcheck tool t…
197 To use, run your code with Valgrind and the Memcheck backends, e.g. `valgrind ./build/ex1 -ceed /cp…
[all …]
H A Dcoverage.info2 SF:/home/jeremy/Dev/libCEED/backends/blocked/ceed-blocked-operator.c
426 SF:/home/jeremy/Dev/libCEED/backends/blocked/ceed-blocked.c
446 SF:/home/jeremy/Dev/libCEED/backends/ceed-backend-list-avx.h
459 SF:/home/jeremy/Dev/libCEED/backends/ceed-backend-list-cuda.h
475 SF:/home/jeremy/Dev/libCEED/backends/ceed-backend-list-hip.h
491 SF:/home/jeremy/Dev/libCEED/backends/ceed-backend-list-magma.h
504 SF:/home/jeremy/Dev/libCEED/backends/ceed-backend-list-memcheck.h
517 SF:/home/jeremy/Dev/libCEED/backends/ceed-backend-list-ref.h
528 SF:/home/jeremy/Dev/libCEED/backends/ceed-backend-list-sycl.h
544 SF:/home/jeremy/Dev/libCEED/backends/ceed-backend-list-xsmm.h
[all …]
H A DDoxyfile914 backends \
1049 backends/ref
/libCEED/rust/libceed-sys/c-src/
H A DMakefile289 …ot-$(if $(for_install),default,install).c, $(wildcard interface/ceed*.c backends/weak/*.c gallery/…
295 ref.c := $(sort $(wildcard backends/ref/*.c))
296 blocked.c := $(sort $(wildcard backends/blocked/*.c))
297 ceedmemcheck.c := $(sort $(wildcard backends/memcheck/*.c))
298 opt.c := $(sort $(wildcard backends/opt/*.c))
299 avx.c := $(sort $(wildcard backends/avx/*.c))
300 xsmm.c := $(sort $(wildcard backends/xsmm/*.c))
302 cuda.c := $(sort $(wildcard backends/cuda/*.c))
303 cuda.cpp := $(sort $(wildcard backends/cuda/*.cpp))
304 cuda-ref.c := $(sort $(wildcard backends/cuda-ref/*.c))
[all …]
/libCEED/interface/
H A Dceed.c28 } backends[32]; variable
127 if (num_backends < sizeof(backends) / sizeof(backends[0])) { in CeedRegisterImpl()
128 strncpy(backends[num_backends].prefix, prefix, CEED_MAX_RESOURCE_LEN); in CeedRegisterImpl()
129 backends[num_backends].prefix[CEED_MAX_RESOURCE_LEN - 1] = 0; in CeedRegisterImpl()
130 backends[num_backends].init = init; in CeedRegisterImpl()
131 backends[num_backends].priority = priority; in CeedRegisterImpl()
1140 if (backends[i].priority < CEED_MAX_BACKEND_PRIORITY) { in CeedRegistryGetList()
1141 *resources[i] = backends[i].prefix; in CeedRegistryGetList()
1142 if (priorities) *priorities[i] = backends[i].priority; in CeedRegistryGetList()
1188 …if (backends[i].priority < CEED_MAX_BACKEND_PRIORITY) fprintf(stderr, " %s\n", backends[i].prefix… in CeedInit()
[all …]
/libCEED/benchmarks/
H A DREADME.md4 backends.
17 Multiple backends, benchmark problems, and processor configurations can be
/libCEED/rust/libceed/
H A DREADME.md40 …on](https://libceed.org/en/latest/gettingstarted/#backends) for more information on available back…
/libCEED/backends/magma/tuning/
H A DREADME.md36 Note that in order for the benchmarks to make sense for `magma` backends, the
/libCEED/julia/LibCEED.jl/
H A DREADME.md11 **Warning:** the pre-built libCEED binaries do not support CUDA backends
/libCEED/doc/papers/joss/
H A Dpaper.md110 `libCEED` implementations ("backends") are free to reorder and fuse computational steps (including …
141 \autoref{fig:libCEEDBackends} shows a subset of the backend implementations (backends) available in…
142 …Moreover, each process or thread can instantiate an arbitrary number of backends on an arbitrary n…
145 (backends) for heterogeneous architectures.\label{fig:libCEEDBackends}](img/libCEEDBackends.png)
165 …ass `-d ceed-cuda:/gpu/cuda/gen` to use a `libCEED` CUDA backend, and similarly for other backends.
/libCEED/julia/LibCEED.jl/docs/src/
H A Dindex.md21 !!! warning "The pre-built libCEED binaries do not support CUDA backends"
H A DUserQFunctions.md6 backends.
/libCEED/julia/LibCEED.jl/src/
H A DUserQFunction.jl121 "User Q-functions with CUDA backends require the CUDA.jl package to be ",