BEGIN 1782125908.3788447 EXEC /__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build /usr/local/therock-tools/bin/cmake -E env --unset=ROCM_PATH --unset=ROCM_DIR --unset=HIP_PATH --unset=HIP_DIR -- /usr/local/therock-tools/bin/cmake --build /__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build 1.2 [1/368] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen_inst_gen.dir/GenInstructions.cpp.o 1.2 [2/368] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen_inst_gen.dir/GenInstructionsMain.cpp.o 1.2 [3/368] Building CXX object origami/CMakeFiles/origami.dir/src/origami/gemm.cpp.o 1.3 [4/368] Building CXX object origami/CMakeFiles/origami.dir/src/origami/hardware.cpp.o 1.3 [5/368] Building CXX object origami/CMakeFiles/origami.dir/src/origami/heuristics.cpp.o 1.3 [6/368] Building CXX object origami/CMakeFiles/origami.dir/src/origami/logger.cpp.o 1.3 [7/368] Building CXX object origami/CMakeFiles/origami.dir/src/origami/origami.cpp.o 1.3 [8/368] Building CXX object origami/CMakeFiles/origami.dir/src/origami/streamk.cpp.o 1.3 [9/368] Building CXX object origami/CMakeFiles/origami.dir/src/origami/types.cpp.o 1.4 [10/368] Building CXX object origami/CMakeFiles/origami.dir/src/simulator/tensilelite/formocast_simulator.cpp.o 1.4 [11/368] Building CXX object origami/CMakeFiles/origami.dir/src/simulator/tensilelite/formocast.cpp.o 1.4 [12/368] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static-abi3.dir/__/__/_deps/nanobind-src/src/nb_internals.cpp.o 1.4 [13/368] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static-abi3.dir/__/__/_deps/nanobind-src/src/nb_func.cpp.o 1.4 [14/368] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static-abi3.dir/__/__/_deps/nanobind-src/src/nb_type.cpp.o 1.4 [15/368] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static-abi3.dir/__/__/_deps/nanobind-src/src/nb_enum.cpp.o 1.4 [16/368] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static-abi3.dir/__/__/_deps/nanobind-src/src/nb_ndarray.cpp.o 1.4 [17/368] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static-abi3.dir/__/__/_deps/nanobind-src/src/nb_static_property.cpp.o 1.5 [18/368] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static-abi3.dir/__/__/_deps/nanobind-src/src/nb_ft.cpp.o 1.5 [19/368] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static-abi3.dir/__/__/_deps/nanobind-src/src/common.cpp.o 1.5 [20/368] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static-abi3.dir/__/__/_deps/nanobind-src/src/error.cpp.o 1.5 [21/368] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static-abi3.dir/__/__/_deps/nanobind-src/src/trampoline.cpp.o 1.5 [22/368] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static-abi3.dir/__/__/_deps/nanobind-src/src/implicit.cpp.o 1.6 [23/368] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/parameter_selection.cpp.o 1.6 [24/368] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/custom_kernels.cpp.o 1.6 [25/368] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/gemm.cpp.o 1.6 [26/368] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/runtime_args_selection.cpp.o 1.6 [27/368] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/rocroller_host.cpp.o 1.6 [28/368] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/solution_cache.cpp.o 1.6 [29/368] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/solution_selection.cpp.o 1.7 [30/368] Linking CXX executable tensilelite/rocisa/stinkytofu/tools/tablegen/tablegen_inst_gen 1.7 [31/368] Linking CXX static library origami/liborigami.a 1.7 [32/368] Linking CXX static library tensilelite/rocisa/libnanobind-static-abi3.a 1.8 [33/368] Generating instruction metadata and ISA from .def files... 1.8 Gfx1250Formats.def: parsed 53 formats 1.8 Gfx1250Instructions.def: parsed 548 instructions 1.8 Successfully generated instruction metadata and ISA for all archs 2.0 [34/368] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/src/gfx/GpuArchManager.cpp.o 2.2 [35/368] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/src/gfx/InstDefDSL.cpp.o 2.4 [36/368] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/src/gfx/Gfx1250/Gfx1250.cpp.o 2.6 [37/368] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/generated/GfxArchDefines.cpp.o 2.9 [38/368] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/generated/GfxLogicalMaps.cpp.o 3.0 [39/368] Linking CXX static library tensilelite/rocisa/stinkytofu/hardware/libgfxisa.a 3.2 [40/368] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/tablegen.cpp.o 3.4 [41/368] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenRocisaHwMapping.cpp.o 3.6 [42/368] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenLogicalToAsmMapping.cpp.o 3.7 [43/368] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenPatterns.cpp.o 4.0 [44/368] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenLogicalIR.cpp.o 4.2 [45/368] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenInstructions.cpp.o 4.4 [46/368] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/src/serialization/asm/IRLexer.cpp.o 4.6 [47/368] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/src/serialization/asm/PatternParser.cpp.o 4.8 [48/368] Linking CXX executable tensilelite/rocisa/stinkytofu/tools/tablegen/tablegen 4.9 [49/368] Generating ISA definitions, IR classes, and pattern matchers with tablegen... 4.9 Generating Rocisa mappings for Gfx1250 in "/__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/stinkytofu/ir/rocisa/RocisaGfx1250Mappings.inc" 4.9 Generating Logical IR -> ASM mappings in "/__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/stinkytofu/ir/LogicalToAsmMappings_generated.inc" 4.9 Parsing patterns from: /__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/tools/tablegen/../../hardware/../src/transforms/asm/PeepholePatterns.pattern 4.9 Found 12 pattern(s) 4.9 Generated 12 pattern matchers: /__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/PeepholePatterns.inc 4.9 Parsing patterns from: /__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/tools/tablegen/../../hardware/../src/transforms/logical/LogicalIRPatterns.pattern 4.9 Found 12 pattern(s) 4.9 Generated 12 pattern matchers: /__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/LogicalIRPatterns.inc 4.9 4.9 === Generating High-Level IR === 4.9 Generated 274 opcode enum values -> LogicalOpcodes_generated.inc 4.9 Generated opcode mapping functions -> LogicalOpcode.cpp 4.9 Generated 274 LogicalInstruction factory functions + 5 special instruction factories (MFMA/MXMFMA/SMFMA/Label/IntrinsicCall) -> LogicalInstructions_generated.hpp 4.9 Generated Python bindings for 274 IR instructions -> PythonBindings_generated.inc 4.9 === High-Level IR generation completed successfully === 4.9 5.1 [50/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/stinkytofu/ir/logical/LogicalOpcode.cpp.o 5.2 [51/368] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/Debug.cpp.o 5.2 [52/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/AnalysisManager.cpp.o 5.4 [53/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/BasicBlock.cpp.o 5.4 [54/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/IRBase.cpp.o 5.6 [55/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/Function.cpp.o 5.6 [56/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/PassManager.cpp.o 5.7 [57/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/DebugPrintInstrumentation.cpp.o 5.8 [58/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/DAGScheduleJsonWriter.cpp.o 5.9 [59/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/bindings/python/LogicalModule.cpp.o 6.1 [60/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/bindings/python/Module.cpp.o 6.1 [61/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/DumpStinkyFunctionPass.cpp.o 6.2 [62/368] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/Debug.cpp.o 6.3 [63/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/LogicalOpcode.cpp.o 6.3 [64/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/LogicalToFunctionConverter.cpp.o 6.4 [65/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/IntrinsicLibrary.cpp.o 6.5 [66/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/IntrinsicRegistry.cpp.o 6.5 [67/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/IntrinsicPatternConverter.cpp.o 6.6 [68/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/asm/AsmSetSymbolMap.cpp.o 6.7 [69/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/asm/StinkyAsmIR.cpp.o 6.8 [70/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/asm/StinkyModifiers.cpp.o 6.8 [71/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/asm/StinkySignature.cpp.o 6.8 [72/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/IntrinsicExpansionPass.cpp.o 7.0 [73/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/ToStinkyAsmPass.cpp.o 7.0 [74/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/CompositeInstructionLoweringPass.cpp.o 7.0 [75/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/LogicalPeepholePass.cpp.o 7.1 [76/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/InstructionSizeCosting.cpp.o 7.2 [77/368] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/Activation.cpp.o 7.2 [78/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/AccumulateInstructionSizePass.cpp.o 7.3 [79/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/SwPrefetchInsertionPass.cpp.o 7.4 [80/368] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/EmbeddedData.cpp.o 7.4 [81/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/PassOrderSnapshotJson.cpp.o 7.4 [82/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/PhiPlacement.cpp.o 7.5 [83/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/BuildDefUseChain.cpp.o 7.5 [84/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/CFGBuilderPass.cpp.o 7.6 [85/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/LongBranchLoweringPass.cpp.o 7.6 [86/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/PeepholeOptimizationPass.cpp.o 7.7 [87/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/DeadCodeEliminationPass.cpp.o 7.7 [88/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/LegalizationUtils.cpp.o 7.7 [89/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/RedundantMovEliminationPass.cpp.o 7.8 [90/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/ScheduleLastLRsPass.cpp.o 7.8 [91/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyDAGSchedulerPass.cpp.o 7.8 [92/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/SetMatrixReusePass.cpp.o 7.9 [93/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyConfigurableWaitCntPass.cpp.o 7.9 [94/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/ScheduleFirstLRsPass.cpp.o 8.0 [95/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyWaitCntInsertionPass.cpp.o 8.0 [96/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/waitcnt/ShallowPredPromotion.cpp.o 8.1 [97/368] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/singletons.cpp.o 8.1 [98/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyRemoveNopPass.cpp.o 8.1 [99/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/waitcnt/WaitDataflow.cpp.o 8.2 [100/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyRemoveWaitCntPass.cpp.o 8.2 [101/368] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/Utils.cpp.o 8.3 [102/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/MemTokenConsistencyCheckPass.cpp.o 8.3 [103/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyBuildImplicitDependencyPass.cpp.o 8.3 [104/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/RaiseVgprMsbPass.cpp.o 8.3 [105/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/InsertVgprMsbPass.cpp.o 8.4 [106/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/InsertClusterBarrierPass.cpp.o 8.4 [107/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/RemoveDelayAluPass.cpp.o 8.4 [108/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/InsertDelayAluPass.cpp.o 8.5 [109/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/InsertWaitAluPass.cpp.o 8.5 [110/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/LoopRegionRemarkPass.cpp.o 8.5 [111/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/RemoveWaitAluPass.cpp.o 8.5 [112/368] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/PerformanceMetricTypes.cpp.o 8.6 [113/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/EstimateAsmCyclesPass.cpp.o 8.6 [114/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/RederiveExpertScopePass.cpp.o 8.6 [115/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/pipeline/PassBuilder.cpp.o 8.6 [116/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/pipeline/backend/Backend.cpp.o 8.6 [117/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/pipeline/backend/BackendRegistry.cpp.o 8.7 [118/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/pipeline/backend/Gfx1250Backend.cpp.o 8.7 [119/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/logical/IRSerializer.cpp.o 8.7 [120/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/StinkyAsmPrinter.cpp.o 8.7 [121/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/StinkyAsmEmitter.cpp.o 8.8 [122/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/IRLexer.cpp.o 8.8 [123/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/ModifierSerializer.cpp.o 8.8 [124/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/IRParser.cpp.o 8.9 [125/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/PatternParser.cpp.o 8.9 [126/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/IRConverter.cpp.o 8.9 [127/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/RawAsmParser.cpp.o 8.9 [128/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/analysis/asm/AsmVerifierPass.cpp.o 8.9 [129/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/analysis/controlflow/Dominance.cpp.o 9.0 [130/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/analysis/logical/IRVerifierPass.cpp.o 9.0 [131/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/hardware/ArchHelper.cpp.o 9.1 [132/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/hardware/ToolchainCaps.cpp.o 9.1 [133/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/hardware/ComgrProbe.cpp.o 9.1 [134/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/main.cpp.o 9.1 [135/368] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/hardware/HwReg.cpp.o 9.1 [136/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/base.cpp.o 9.2 [137/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/code.cpp.o 9.2 [138/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/count.cpp.o 9.2 /__w/rockrel/rockrel/rocm-libraries/projects/hipblaslt/tensilelite/rocisa/rocisa/src/count.cpp:149:34: warning: expression with side effects will be evaluated despite being used as an operand to 'typeid' [-Wpotentially-evaluated-expression] 9.2 149 | const auto& tid = typeid(*item); 9.2 | ^ 9.2 1 warning generated. 9.2 [139/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/container.cpp.o 9.3 [140/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/enum.cpp.o 9.3 [141/368] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/KernelLanguageTypes.cpp.o 9.3 [142/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/helper.cpp.o 9.3 [143/368] Linking CXX shared library tensilelite/rocisa/stinkytofu/libstinkytofu.so.0.1.0 9.3 [144/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/label.cpp.o 9.4 [145/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/macro.cpp.o 9.4 [146/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/instruction.cpp.o 9.4 [147/368] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/hipblaslt_bench_options.cpp.o 9.5 [148/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/register.cpp.o 9.5 [149/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/common.cpp.o 9.5 [150/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/branch.cpp.o 9.5 [151/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/extension.cpp.o 9.5 [152/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/cmp.cpp.o 9.6 [153/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/mfma.cpp.o 9.6 [154/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/mem.cpp.o 9.7 [155/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/cvt.cpp.o 9.7 [156/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/pass.cpp.o 9.7 [157/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/cycle.cpp.o 9.7 [158/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/remove.cpp.o 9.7 [159/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/graph.cpp.o 9.7 [160/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/composite.cpp.o 9.8 [161/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/insert_delay_alu.cpp.o 9.8 [162/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/macro_inline.cpp.o 9.8 [163/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/functions.cpp.o 9.8 [164/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/argument.cpp.o 9.8 [165/368] Creating library symlink tensilelite/rocisa/stinkytofu/libstinkytofu.so.0 tensilelite/rocisa/stinkytofu/libstinkytofu.so 9.9 [166/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/f_cast.cpp.o 9.9 [167/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/src/conversion/rocisa/AllHwMappings.cpp.o 9.9 [168/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/f_branch.cpp.o 9.9 [169/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/f_math.cpp.o 9.9 [170/368] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/src/conversion/rocisa/ToStinkyTofuUtils.cpp.o 10.2 [171/368] Linking CXX shared module tensilelite/rocisa/rocisa/_rocisa.abi3.so 11.6 [172/368] Building CXX object tensilelite/client/CMakeFiles/tensilelite-client-common.dir/src/CSVStackFile.cpp.o 11.6 [172/368] Validating library logic (TensileLogic --check-all) ... 363.4 Launching 64 threads for 420 tasks... 790.5 Validating library logic... 5s elapsed Validating library logic... 10s elapsed Validating library logic... 15s elapsed Validating library logic... 20s elapsed Validating library logic... 25s elapsed Validating library logic... 30s elapsed Validating library logic... 35s elapsed Validating library logic... 40s elapsed Validating library logic... 45s elapsed Validating library logic... 50s elapsed Validating library logic... 55s elapsed Validating library logic... 60s elapsed Validating library logic... 65s elapsed Validating library logic... 70s elapsed Validating library logic... 75s elapsed Validating library logic... 80s elapsed Validating library logic... 85s elapsed Validating library logic... 90s elapsed Validating library logic... 95s elapsed Validating library logic... 100s elapsed Validating library logic... 105s elapsed Validating library logic... 110s elapsed Validating library logic... 115s elapsed Validating library logic... 120s elapsed Validating library logic... 125s elapsed Validating library logic... 130s elapsed Validating library logic... 135s elapsed Validating library logic... 140s elapsed Validating library logic... 145s elapsed Validating library logic... 150s elapsed Validating library logic... 155s elapsed Validating library logic... 160s elapsed Validating library logic... 165s elapsed Validating library logic... 170s elapsed Validating library logic... 175s elapsed Validating library logic... 180s elapsed Validating library logic... 185s elapsed Validating library logic... 190s elapsed Validating library logic... 195s elapsed Validating library logic... 200s elapsed Validating library logic... 205s elapsed Validating library logic... 210s elapsed Validating library logic... 215s elapsed Validating library logic... 220s elapsed Validating library logic... 225s elapsed Validating library logic... 230s elapsed Validating library logic... 235s elapsed Validating library logic... 240s elapsed Validating library logic... 245s elapsed Validating library logic... 250s elapsed Validating library logic... 255s elapsed Validating library logic... 260s elapsed Validating library logic... 265s elapsed Validating library logic... 270s elapsed Validating library logic... 275s elapsed Validating library logic... 280s elapsed Validating library logic... 285s elapsed Validating library logic... 290s elapsed Validating library logic... 295s elapsed Validating library logic... 300s elapsed Validating library logic... 305s elapsed Validating library logic... 310s elapsed Validating library logic... 315s elapsed Validating library logic... 320s elapsed Validating library logic... 325s elapsed Validating library logic... 330s elapsed Validating library logic... 335s elapsed Validating library logic... 340s elapsed Validating library logic... 345s elapsed Validating library logic... 350s elapsed Validating library logic... 355s elapsed Validating library logic... 360s elapsed Validating library logic... 365s elapsed Validating library logic... 370s elapsed Validating library logic... 375s elapsed Validating library logic... 380s elapsed Validating library logic... 385s elapsed Validating library logic... 390s elapsed Validating library logic... 395s elapsed Validating library logic... 400s elapsed Validating library logic... 405s elapsed Validating library logic... 410s elapsed Validating library logic... 415s elapsed Validating library logic... 420s elapsed Validating library logic... 425s elapsed Done. (427.0 secs elapsed) 790.5 Total 571571 solutions 790.5 Keep 571571 solutions 790.5 Reject 0 solutions 790.5 Known-bugs skip 14 solutions (see --known-bugs YAML) 793.5 [230/368] Building CXX object tensilelite/client/CMakeFiles/tensilelite-client-common.dir/src/ClientProblemFactory.cpp.o 793.5 /__w/rockrel/rockrel/rocm-libraries/projects/hipblaslt/tensilelite/client/src/ClientProblemFactory.cpp:73:17: warning: ignoring return value of type 'hipError_t' declared with 'nodiscard' attribute [-Wunused-value] 793.5 73 | hipGetDeviceProperties(&prop, deviceIdx); 793.5 | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 793.5 /__w/rockrel/rockrel/build/core/clr/dist/include/hip/hip_runtime_api.h:87:32: note: expanded from macro 'hipGetDeviceProperties' 793.5 87 | #define hipGetDeviceProperties hipGetDevicePropertiesR0600 793.5 | ^ 793.5 1 warning generated when compiling for gfx1151. 793.5 /__w/rockrel/rockrel/rocm-libraries/projects/hipblaslt/tensilelite/client/src/ClientProblemFactory.cpp:73:17: warning: ignoring return value of type 'hipError_t' declared with 'nodiscard' attribute [-Wunused-value] 793.5 73 | hipGetDeviceProperties(&prop, deviceIdx); 793.5 | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 793.5 /__w/rockrel/rockrel/build/core/clr/dist/include/hip/hip_runtime_api.h:87:32: note: expanded from macro 'hipGetDeviceProperties' 793.5 87 | #define hipGetDeviceProperties hipGetDevicePropertiesR0600 793.5 | ^ 793.5 1 warning generated when compiling for host. 793.5 [280/368] Building CXX object tensilelite/client/CMakeFiles/tensilelite-client-common.dir/src/DataInitialization.cpp.o 793.5 /__w/rockrel/rockrel/rocm-libraries/projects/hipblaslt/tensilelite/client/src/DataInitialization.cpp:963:17: warning: ignoring return value of type 'hipError_t' declared with 'nodiscard' attribute [-Wunused-value] 793.5 963 | hipGetDeviceProperties(&prop, deviceIdx); 793.5 | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 793.5 /__w/rockrel/rockrel/build/core/clr/dist/include/hip/hip_runtime_api.h:87:32: note: expanded from macro 'hipGetDeviceProperties' 793.5 87 | #define hipGetDeviceProperties hipGetDevicePropertiesR0600 793.5 | ^ 793.5 1 warning generated when compiling for gfx1151. 793.5 /__w/rockrel/rockrel/rocm-libraries/projects/hipblaslt/tensilelite/client/src/DataInitialization.cpp:963:17: warning: ignoring return value of type 'hipError_t' declared with 'nodiscard' attribute [-Wunused-value] 793.5 963 | hipGetDeviceProperties(&prop, deviceIdx); 793.5 | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 793.5 /__w/rockrel/rockrel/build/core/clr/dist/include/hip/hip_runtime_api.h:87:32: note: expanded from macro 'hipGetDeviceProperties' 793.5 87 | #define hipGetDeviceProperties hipGetDevicePropertiesR0600 793.5 | ^ 793.5 1 warning generated when compiling for host. 793.5 [366/368] Linking CXX executable clients/hipblaslt-test 793.5 [367/368] Building device libraries to /__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build/Tensile ... 797.3 797.3 ################################################################################ 797.3 # Tensile Create Library 812.5 Capability gfx1151 812.5 HasMFMA_bf16_1k - 812.5 HasWMMA_AccImmZero - 812.5 HasAddLshl 1 812.5 HasAtomicAdd 1 812.5 HasBF16CVT - 812.5 HasClusterBarrier - 812.5 HasCvtFP8toF16 - 812.5 HasDLCModifier 1 812.5 HasDirectToLds - 812.5 HasDirectToLdsx4 - 812.5 HasExplicitCO 1 812.5 HasExplicitNC 1 812.5 HasGLCModifier 1 812.5 HasGLTr16B128 - 812.5 HasGLTr8B64 - 812.5 HasGlobalPrefetch - 812.5 HasLDSTr - 812.5 HasLDSTrB128B16 - 812.5 HasLDSTrB64B16 - 812.5 HasLDSTrB64B4 - 812.5 HasLDSTrB64B8 - 812.5 HasLDSTrB96B6 - 812.5 HasLshlOr 1 812.5 HasMFMA - 812.5 HasMUBUFConst 1 812.5 HasNTModifier - 812.5 HasNVModifier - 812.5 HasNewBarrier - 812.5 HasPartialOOB 1 812.5 HasPkF16CVT - 812.5 HasSAtomic - 812.5 HasSC0Modifier - 812.5 HasSCMPK 1 812.5 HasSCOPEModifier - 812.5 HasSMFMA - 812.5 HasSMulHi 1 812.5 HasSWMMAC - 812.5 HasScalarStore - 812.5 HasTDM - 812.5 HasTHModifier - 812.5 HasVgprMSB - 812.5 HasVgprMSB16 - 812.5 HasWMMA 1 812.5 HasXcnt - 812.5 MaxLgkmcnt 1 812.5 MaxVmcnt 1 812.5 MaxVscnt 1 812.5 SeparateLGKMcnt - 812.5 SeparateVMcnt - 812.5 SeparateVscnt 1 812.5 ShortBranchMaxLength 1 812.5 SupportedISA 1 812.5 SupportedSource 1 812.5 HasWMMA_V1 1 812.5 HasWMMA_V2 - 812.5 HasWMMA_V3 - 812.5 s_delay_alu 1 812.5 v_prng_b32 - 812.5 v_mov_b64 - 812.5 HasMFMA_b8 - 812.5 v_dot2_f32_bf16 1 812.5 v_dot2c_f32_bf16 - 812.5 HasMFMA_explictB - 812.5 Hascvtfp8_f16 - 812.5 v_dot2_f32_f16 1 812.5 v_dot2c_f32_f16 1 812.5 v_fma_f16 1 812.5 v_fmac_f16 - 812.5 v_mac_f16 - 812.5 v_pk_fma_f16 1 812.5 v_pk_fmac_f16 - 812.5 v_fma_f32 1 812.5 v_fma_mix_f32 1 812.5 v_fmac_f32 1 812.5 v_mac_f32 - 812.5 v_mad_mix_f32 - 812.5 v_pk_add_f32 - 812.5 v_pk_mul_f32 - 812.5 HasMFMA_f64 - 812.5 HasWMMA_V3_f64 - 812.5 v_fma_f64 1 812.5 HasMFMA_f8 - 812.5 HasMFMA_f8f6f4 - 812.5 HasWMMA_f8f6f4 - 812.5 HasSWMMAC_gfx1250 - 812.5 HasAdd_PC_i64 - 812.5 VOP3v_dot4_i32_i8 1 812.5 v_dot4_i32_i8 - 812.5 v_dot4c_i32_i8 - 812.5 Hascvtf16_fp8_sf32 - 812.5 s_add_u64 - 812.5 s_sub_u64 - 812.5 v_add_nc_u64 - 812.5 HasMFMA_xf32 - 812.5 ArchAccUnifiedRegs - 812.5 CMPXWritesSGPR - 812.5 CrosslaneWait - 812.5 DSLow16NotPreserve - 812.5 DefaultScopeIsCULocal - 812.5 DeviceLDS 1 812.5 HasAccCD - 812.5 HasEccHalf - 812.5 HasF32XEmulation - 812.5 HasFP8_OCP - 812.5 HasInvWbDevFences - 812.5 HasMXScaleSwizzle - 812.5 HasSchedMode - 812.5 HasWave32 1 812.5 HasWmmaArbStallBit - 812.5 LDSBankCount 1 812.5 LDSBankWidth 1 812.5 MaxSgprPreload 1 812.5 MaxWavesPerSimd 1 812.5 NoSDWA 1 812.5 RequiresXCntForVolatileVMEM - 812.5 SDWAWait - 812.5 SgprPreloadPad - 812.5 TransOpWait - 812.5 VOP3ByteSel - 812.5 VgprBank 1 812.5 Waitcnt0Disabled - 812.5 WorkGroupIdFromTTM - 812.5 # Found hipcc version 7.14.60850-0000000 812.8 ROCm 7.14.60850 Component path: /__w/rockrel/rockrel/build/core/clr/dist/lib/llvm/bin/clang++ version: 23.0.0 812.8 ROCm 7.14.60850 Component path: /__w/rockrel/rockrel/build/compiler/amd-llvm/dist/lib/llvm/bin/clang-offload-bundler version: 23.0.0 812.8 # LogicFilter: /__w/rockrel/rockrel/rocm-libraries/projects/hipblaslt/library/**/*.yaml 813.8 # Experimental: False 813.8 # Archs: gfx1151 813.8 # LibraryLogicFiles: 49 813.8 Loading Logics...: Launching 64 threads... 815.0 Loading Logics...: Done. (1.1 secs elapsed) 827.3 827.3 =========================================================== 827.3 WARNING: YAML parameter type mismatches detected (1418 total across 5 files): 827.3 =========================================================== 827.3 ExpandPointerSwap: found int in 428 solutions (values: 0, 1) - expected bool 827.3 GlobalReadPerMfma: found int in 512 solutions (values: 1) - expected float 827.3 SourceSwap: found int in 478 solutions (values: 0, 1) - expected bool 827.3 ----------------------------------------------------------- 827.3 This will cause std::bad_cast at runtime because msgpack 827.3 serializes bool and int as different wire types. 827.3 Fix these to prevent future build failures. 827.3 =========================================================== 829.6 Number of solutions parsed: 2931 829.6 Number of unique solutions: 2931 835.0 Time to load yaml files (s): 15.81 835.0 Number of duplicate kernels: 0 835.0 Generating assembly kernels: Launching 64 threads for 2502 tasks... 891.0 Generating assembly kernels: Done. (55.9 secs elapsed) 904.7 # Helper kernel cache MISS (29996dd38610...) 1097.8 buildSourceCodeObjectFile time (s): 193.16 1104.8 Time to generate kernels (s): 264.99 1104.8 Time to pass kernel info to library (s): 4.63 1104.8 Writing master solution libraries: Launching 64 threads for 47 tasks... 1108.7 Writing master solution libraries: Done. (3.9 secs elapsed) 1110.1 Time to write master solution libraries (s): 3.91 1110.1 # Tensile Library Writer DONE 1110.1 ################################################################################ 1110.1 1110.1 Total time (s): 311.61 1110.1 Total kernels processed: 2502 1110.1 Kernels processed per second: 8.03 1110.1 KernelHelperObjs: 59 END 1782127018.8615487 1110.482703924179 0