Home
last modified time | relevance | path

Searched refs:executions (Results 1 – 25 of 34) sorted by relevance

12

/llvm-project/lldb/source/Plugins/Trace/intel-pt/
H A DLibiptDecoder.cpp589 const std::vector<IntelPTThreadContinousExecution> &executions) { in DecodeSystemWideTraceForThread() argument
591 for (size_t i = 0; i < executions.size(); i++) { in DecodeSystemWideTraceForThread()
592 const IntelPTThreadContinousExecution &execution = executions[i]; in DecodeSystemWideTraceForThread()
658 if (i + 1 != executions.size() && in DecodeSystemWideTraceForThread()
699 std::vector<PSBBlock> executions; in SplitTraceIntoPSBBlock() local
742 executions.push_back({ in SplitTraceIntoPSBBlock()
749 if (!executions.empty()) { in SplitTraceIntoPSBBlock()
751 executions.back().size = buffer.size() - executions.back().psb_offset; in SplitTraceIntoPSBBlock()
752 for (int i = (int)executions.size() - 2; i >= 0; i--) { in SplitTraceIntoPSBBlock()
753 executions[i].size = in SplitTraceIntoPSBBlock()
[all …]
H A DTraceIntelPTMultiCpuDecoder.cpp156 Expected<std::vector<ThreadContinuousExecution>> executions = in DoCorrelateContextSwitchesAndIntelPtTraces() local
158 if (!executions) in DoCorrelateContextSwitchesAndIntelPtTraces()
159 return executions.takeError(); in DoCorrelateContextSwitchesAndIntelPtTraces()
160 for (const ThreadContinuousExecution &exec : *executions) in DoCorrelateContextSwitchesAndIntelPtTraces()
H A DPerfContextSwitchDecoder.cpp250 std::vector<ThreadContinuousExecution> executions; in DecodePerfContextSwitchTrace() local
276 executions.push_back(execution); in DecodePerfContextSwitchTrace()
287 executions.push_back(ThreadContinuousExecution::CreateOnlyStartExecution( in DecodePerfContextSwitchTrace()
298 return executions; in DecodePerfContextSwitchTrace()
H A DTraceIntelPTBundleLoader.cpp355 Expected<std::vector<ThreadContinuousExecution>> executions = in AugmentThreadsFromContextSwitches() local
358 if (!executions) in AugmentThreadsFromContextSwitches()
359 return executions.takeError(); in AugmentThreadsFromContextSwitches()
360 for (const ThreadContinuousExecution &execution : *executions) in AugmentThreadsFromContextSwitches()
H A DLibiptDecoder.h89 const std::vector<IntelPTThreadContinousExecution> &executions);
/llvm-project/bolt/test/X86/
H A Dtail-duplication-cache.s20 …licated 1 blocks (13 bytes) responsible for 50 dynamic executions ({{.*}}% of all block executions)
29 … duplicated 0 blocks (0 bytes) responsible for 0 dynamic executions (0.00% of all block executions)
H A Dtail-duplication-pass.s16 …ated 1 blocks (1 bytes) responsible for {{.*}} dynamic executions ({{.*}}% of all block executions)
H A Dtail-duplication-complex.s17 … 1 blocks ({{.*}} bytes) responsible for {{.*}} dynamic executions ({{.*}} of all block executions)
H A Dshrinkwrapping-pop-order.s37 # CHECK: BOLT-INFO: Shrink wrapping reduced 6 store executions (28.6% total instructions executed, …
38 # CHECK: BOLT-INFO: Shrink wrapping failed at reducing 0 store executions (0.0% total instructions …
/llvm-project/llvm/test/Transforms/PGOProfile/
H A Dmisexpect-branch.ll13 … llvm.expect intrinsic: Annotation was correct on 19.98% (399668 / 2000000) of profiled executions.
16 … llvm.expect intrinsic: Annotation was correct on 19.98% (399668 / 2000000) of profiled executions.
19 … llvm.expect intrinsic: Annotation was correct on 19.98% (399668 / 2000000) of profiled executions.
22 … llvm.expect intrinsic: Annotation was correct on 19.98% (399668 / 2000000) of profiled executions.
25 … llvm.expect intrinsic: Annotation was correct on 19.98% (399668 / 2000000) of profiled executions.
H A Dmisexpect-branch-stripped.ll11 … llvm.expect intrinsic: Annotation was correct on 19.98% (399668 / 2000000) of profiled executions.
14 … llvm.expect intrinsic: Annotation was correct on 19.98% (399668 / 2000000) of profiled executions.
17 … llvm.expect intrinsic: Annotation was correct on 19.98% (399668 / 2000000) of profiled executions.
20 … llvm.expect intrinsic: Annotation was correct on 19.98% (399668 / 2000000) of profiled executions.
H A Dmisexpect-switch-default.ll11 …e of the llvm.expect intrinsic: Annotation was correct on 0.00% (0 / 27943) of profiled executions.
14 …e of the llvm.expect intrinsic: Annotation was correct on 0.00% (0 / 27943) of profiled executions.
17 …e of the llvm.expect intrinsic: Annotation was correct on 0.00% (0 / 27943) of profiled executions.
20 …e of the llvm.expect intrinsic: Annotation was correct on 0.00% (0 / 27943) of profiled executions.
23 …e of the llvm.expect intrinsic: Annotation was correct on 0.00% (0 / 27943) of profiled executions.
H A Dmisexpect-switch.ll14 …se of the llvm.expect intrinsic: Annotation was correct on 0.00% (0 / 8112) of profiled executions.
17 …se of the llvm.expect intrinsic: Annotation was correct on 0.00% (0 / 8112) of profiled executions.
20 …se of the llvm.expect intrinsic: Annotation was correct on 0.00% (0 / 8112) of profiled executions.
23 …se of the llvm.expect intrinsic: Annotation was correct on 0.00% (0 / 8112) of profiled executions.
26 …se of the llvm.expect intrinsic: Annotation was correct on 0.00% (0 / 8112) of profiled executions.
H A Dmisexpect-branch-overflow.ll8 …xpect intrinsic: Annotation was correct on 50.00% (2147483648 / 4294967296) of profiled executions.
/llvm-project/bolt/test/runtime/X86/
H A Dtail-duplication-constant-prop.s16 …1 blocks ({{.*}} bytes) responsible for {{.*}} dynamic executions ({{.*}}% of all block executions)
/llvm-project/mlir/docs/
H A DActionTracing.md157 initial executions of a debug action. The "count" value is used to prevent a
159 including any executions that have been skipped). If the "skip" value is
163 47 executions, then execute twice, and finally prevent any further executions.
186 The above configuration would skip the first 47 executions of
188 executions.
/llvm-project/clang/tools/clang-fuzzer/
H A DREADME.txt143 Note: To get a higher number of executions per second with llvm-proto-fuzzer it
/llvm-project/llvm/docs/
H A DLoopTerminology.rst230 * The number of executions of the loop header before leaving the loop is
241 number of header executions of the code below for a non-positive n
252 the trip count for executions that enter the header.
H A DWritingAnLLVMPass.rst151 overlap with any other pass executions (thus it should be very fast).
217 overlap with any other pass executions (thus it should be very fast).
286 pass executions (thus it should be very fast). ``LPPassManager`` interface
339 pass executions (thus it should be very fast). ``RPPassManager`` interface
H A DConvergentOperations.rst1054 so it also implies that ``I1 != J2`` and ``I2 != J1``, because those executions
1129 different executions by the same thread happen in different dynamic
1179 instructions given in the program, the executions of the threads can be
/llvm-project/mlir/include/mlir/Dialect/GPU/IR/
H A DGPUOps.td175 If `upper_bound` is set, executions where the bblock size along `dimension`
193 annotations in context, executions where the block index in `dimension` would
220 If `upper_bound` is set, executions where the grid size in `dimension` would
238 annotations in context, executions where the thread index would be greater
255 If `upper_bound` is set, executions with more than `upper_bound` lanes per
320 If `upper_bound` is set, executions with more than `upper_bound` subgroups
/llvm-project/clang/include/clang/Basic/
H A DDiagnosticFrontendKinds.td367 "annotation was correct on %0 of profiled executions">,
/llvm-project/mlir/include/mlir/Transforms/
H A DPasses.td63 executions paths where their results are not needed do not perform
/llvm-project/mlir/docs/Tutorials/transform/
H A DCh0.md133 …e `out` operand and is available as the last block argument for future executions of the region. N…
/llvm-project/llvm/include/llvm/Target/
H A DTargetSchedule.td177 // Use BufferSize > 1 for out-of-order executions units with a

12