Home
last modified time | relevance | path

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

/llvm-project-15.0.7/llvm/test/CodeGen/AArch64/
H A Darm64-sitofp-combine-chains.ll3 ; ARM64ISelLowering.cpp was creating a new (floating-point) load for efficiency
H A Daddsub.ll4 ; Note that this should be refactored (for efficiency if nothing else)
/llvm-project-15.0.7/llvm/lib/Support/Unix/
H A DThreading.inc272 // class emphasizes energy efficiency.
276 // offers a balance between responsiveness, performance, and energy efficiency.
/llvm-project-15.0.7/openmp/runtime/src/
H A Dkmp_affinity.cpp1696 int efficiency; in __kmp_affinity_create_hwloc_map() member
1708 cpukinds[idx].efficiency = -1; in __kmp_affinity_create_hwloc_map()
1712 &cpukinds[idx].efficiency, &nr_infos, &infos, in __kmp_affinity_create_hwloc_map()
1801 hw_thread.attrs.set_core_eff(cpukinds[cpukind_index].efficiency); in __kmp_affinity_create_hwloc_map()
2380 static void __kmp_get_hybrid_info(kmp_hw_core_type_t *type, int *efficiency, in __kmp_get_hybrid_info() argument
2387 *efficiency = 0; in __kmp_get_hybrid_info()
2390 *efficiency = 1; in __kmp_get_hybrid_info()
2393 *efficiency = 0; in __kmp_get_hybrid_info()
2671 int efficiency; in __kmp_affinity_create_x2apicid_map() local
2672 __kmp_get_hybrid_info(&type, &efficiency, &native_model_id); in __kmp_affinity_create_x2apicid_map()
[all …]
H A Dkmp_settings.cpp5049 int efficiency = atoi(number); in __kmp_stg_parse_hw_subset() local
5050 attr.set_core_eff(efficiency); in __kmp_stg_parse_hw_subset()
/llvm-project-15.0.7/mlir/include/mlir/Dialect/SparseTensor/Transforms/
H A DPasses.td73 "Enable i32 indexing into vectors (for efficiency)">,
/llvm-project-15.0.7/polly/lib/External/isl/doc/
H A Disl.bib137 estimator of the efficiency of this data distribution.
338 it is important to keep the number of disjuncts small, both for efficiency
/llvm-project-15.0.7/openmp/docs/design/
H A DRuntimes.rst506 * **Core efficiency** - This is specified as ``eff``:emphasis:`num` where :emphasis:`num` is a numb…
508 E.g., ``eff0``. The greater the efficiency number the more performant the core. There may be
563 * ``2c:eff0@1,3c:eff1``: Use all available sockets, skip the first core with efficiency 0
564 and use the next 2 cores with efficiency 0 and 3 cores with efficiency 1 per socket.
572 efficiency 1, and then use the rest of the available cores of efficiency 1.
/llvm-project-15.0.7/llvm/lib/Target/AArch64/
H A DAArch64InstrAtomics.td28 // standard modes would be valid and may give efficiency gains.
163 // standard modes would be valid and may give efficiency gains.
/llvm-project-15.0.7/llvm/test/Transforms/InstCombine/
H A Dstrcall-no-nul.ll8 ; for efficiency and prevents sanitizers from detecting and reporting
/llvm-project-15.0.7/mlir/docs/Tutorials/Toy/
H A DCh-5.md298 efficiency. For example, the lowering of `toy.mul` has generated some redundant
/llvm-project-15.0.7/llvm/
H A DCREDITS.TXT192 D: Improvements for space efficiency
/llvm-project-15.0.7/mlir/docs/
H A DDataLayout.md224 efficiency and layering reasons. Instead, `DataLayout` can be constructed for
H A DPassManagement.md454 that need to be scheduled, as well as increasing the efficiency of each job.
/llvm-project-15.0.7/lld/docs/
H A DNewLLD.rst136 On the other hand, you don't have to pursue efficiency
/llvm-project-15.0.7/libcxx/include/
H A Dformat192 // improves the efficiency of the header. However since the header is still
/llvm-project-15.0.7/llvm/lib/Target/ARM/
H A DREADME.txt38 2. There might be some compile-time efficiency to be had by representing
/llvm-project-15.0.7/libcxx/docs/DesignDocs/
H A DAtomicDesign.rst21 Ultimate efficiency is preferred over run time error checking. Undefined
/llvm-project-15.0.7/openmp/runtime/src/i18n/
H A Den_US.txt364 TopologyHybridCoreEff "%1$s: %2$d with core efficiency %3$d."
/llvm-project-15.0.7/mlir/docs/Rationale/
H A DMLIRForGraphAlgorithms.md36 with a specific focus on compile time and memory efficiency, accurate
/llvm-project-15.0.7/llvm/docs/
H A DTestingGuide.rst95 efficiency of the programs generated as well as the speed with which
H A DAliasAnalysis.rst487 `alias`_ method directly if possible) to get the best precision and efficiency.
H A DProgrammersManual.rst1998 gracefully handles extremely large sets without loss of efficiency.
H A DAMDGPUDwarfExtensionsForHeterogeneousDebugging.rst482 For efficiency, the expression calculates the source location the wavefront as a
/llvm-project-15.0.7/clang/docs/
H A DAutomaticReferenceCounting.rst2187 some classes offer their users direct access for efficiency. If ARC is not