Home
last modified time | relevance | path

Searched refs:parallelism (Results 1 – 25 of 27) sorted by relevance

12

/llvm-project-15.0.7/openmp/docs/remarks/
H A DOMP131.rst11 machine can be used if it is known that there is no nested parallelism and the
19 parallelism.
/llvm-project-15.0.7/llvm/utils/lit/tests/Inputs/parallelism-groups/
H A Dlit.cfg2 config.name = 'parallelism-groups'
/llvm-project-15.0.7/polly/test/CodeGen/LoopParallelMD/
H A Dsingle_loop_param_parallel.ll47 ; analysis to detect the parallelism.
/llvm-project-15.0.7/llvm/docs/
H A DVectorizers.rst352 high degree of parallelism can fully utilize the entire width of the machine.
353 The Loop Vectorizer increases the instruction level parallelism (ILP) by
428 The goal of SLP vectorization (a.k.a. superword-level parallelism) is
H A DHowToAddABuilder.rst67 of parallelism (-j param) would give the fastest build. You can build
H A DCMake.rst258 to restrict the parallelism. For example, to avoid OOMs or going
/llvm-project-15.0.7/clang/runtime/
H A DCMakeLists.txt17 # Use special command for Makefiles to support parallelism.
/llvm-project-15.0.7/llvm/docs/HistoricalNotes/
H A D2001-02-09-AdveComments.txt98 o About explicit parallelism:
/llvm-project-15.0.7/llvm/cmake/modules/
H A DLLVMExternalProjectUtils.cmake11 # Use special command for Makefiles to support parallelism.
/llvm-project-15.0.7/polly/docs/
H A DUsingPollyWithClang.rst186 for data-locality and parallelism using the Pluto algorithm.
/llvm-project-15.0.7/llvm/test/Transforms/LoopInterchange/
H A Dloop-interchange-optimization-remarks.ll74 …N-NEXT: - String: Interchanging loops is too costly and it does not improve parallelism.
/llvm-project-15.0.7/clang/test/SemaOpenCL/
H A Dcl20-device-side-enqueue.cl171 …stic tests for get_kernel_work_group_size and allowed block parameter types in dynamic parallelism.
/llvm-project-15.0.7/clang/docs/
H A DThinLTO.rst114 may be too aggressive, in which case the amount of parallelism can
H A DHLSLSupport.rst126 (SPMD) language relying on the implicit parallelism provided by GPU hardware.
H A DOpenMPSupport.rst96 - Nested parallelism: inner parallel regions are executed sequentially.
H A DClangCommandLineReference.rst1952 Controls the backend parallelism of -flto=thin (default of 0 means the number of threads will be de…
2475 Enable the superword-level parallelism vectorization passes
H A DLanguageExtensions.rst3896 improve instruction-level parallelism (ILP) using advanced hardware features,
4031 parallelism could be reduced by sequentializing the execution of the
/llvm-project-15.0.7/llvm/docs/Proposals/
H A DVectorizationPlan.rst234 .. [4] "Exploiting mixed SIMD parallelism by reducing data reorganization
/llvm-project-15.0.7/polly/lib/External/ppcg/
H A Dgpu.c4170 int parallelism; in get_non_parallel_subtree_filters() local
4173 parallelism = subtree_has_permutable_bands(node); in get_non_parallel_subtree_filters()
4174 if (parallelism < 0) { in get_non_parallel_subtree_filters()
4176 } else if (!parallelism) { in get_non_parallel_subtree_filters()
/llvm-project-15.0.7/openmp/docs/design/
H A DRuntimes.rst89 Deprecated. Please use ``OMP_MAX_ACTIVE_LEVELS`` to control nested parallelism
91 Enables (``true``) or disables (``false``) nested parallelism.
448 For values of 2 and above, nested parallelism should be enabled.
/llvm-project-15.0.7/openmp/docs/
H A DSupportAndFAQ.rst327 is too complex, containing recursive calls or nested parallelism, this analysis
/llvm-project-15.0.7/mlir/docs/Rationale/
H A DRationaleLinalgDialect.md87 supporting parallelism, reductions and sliding windows around arbitrary MLIR
286 algorithms to perform fusion and favor multi-level parallelism and
H A DMLIRForGraphAlgorithms.md387 parallelism?
/llvm-project-15.0.7/mlir/include/mlir/Dialect/SCF/IR/
H A DSCFOps.td346 async parallelism). At this time, the specification is backend-dependent and
/llvm-project-15.0.7/llvm/docs/CommandGuide/
H A Dllvm-mca.rst432 and 'uOps Per Cycle' are limited by the amount of hardware parallelism. The

12