BEGIN 1777961894.2131047 EXEC /__w/rocm-libraries/rocm-libraries/TheRock/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/rocm-libraries/rocm-libraries/TheRock/build/math-libs/BLAS/hipBLASLt/build 1.0 [1/420] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen_inst_gen.dir/GenInstructions.cpp.o 1.0 [2/420] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen_inst_gen.dir/GenInstructionsMain.cpp.o 1.0 [3/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x128.s 1.0 [4/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x128_ntA.s 1.0 [5/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x128_ntB.s 1.0 [6/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x256.s 1.0 [7/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x256_ntA.s 1.1 [8/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x256_ntB.s 1.1 [9/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x384.s 1.1 [10/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x384_ntA.s 1.1 [11/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x384_ntB.s 1.1 [12/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x512.s 1.1 [13/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x512_ntA.s 1.1 [14/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x512_ntB.s 1.1 [15/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x128.s 1.1 [16/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x128_ntA.s 1.1 [17/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x128_ntB.s 1.2 [18/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x256.s 1.2 [19/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x256_ntA.s 1.2 [20/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x256_ntB.s 1.2 [21/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x384.s 1.2 [22/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x384_ntA.s 1.2 [23/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x384_ntB.s 1.2 [24/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x128.s 1.2 [25/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x128_ntA.s 1.3 [26/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x128_ntB.s 1.3 [27/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x256.s 1.3 [28/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x256_ntA.s 1.3 [29/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x256_ntB.s 1.3 [30/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x128.s 1.3 [31/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x128_ntA.s 1.3 [32/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x128_ntB.s 1.4 [33/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x256.s 1.4 [34/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x256_ntA.s 1.4 [35/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x256_ntB.s 1.4 [36/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x128.s 1.4 [37/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x128_ntA.s 1.4 [38/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x128_ntB.s 1.4 [39/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x256.s 1.5 [40/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x256_ntA.s 1.5 [41/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x256_ntB.s 1.5 [42/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x1024.s 1.5 [43/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x1024_ntA.s 1.5 [44/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x1024_ntB.s 1.5 [45/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x128.s 1.5 [46/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x128_ntA.s 1.5 [47/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x128_ntB.s 1.6 [48/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x256.s 1.6 [49/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x256_ntA.s 1.6 [50/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x256_ntB.s 1.6 [51/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x384.s 1.6 [52/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x384_ntA.s 1.6 [53/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x384_ntB.s 1.6 [54/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x512.s 1.7 [55/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x512_ntA.s 1.7 [56/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x512_ntB.s 1.7 [57/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x640.s 1.7 [58/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x640_ntA.s 1.7 [59/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x640_ntB.s 1.7 [60/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x768.s 1.7 [61/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x768_ntA.s 1.8 [62/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x768_ntB.s 1.8 [63/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x896.s 1.8 [64/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x896_ntA.s 1.8 [65/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x896_ntB.s 1.8 [66/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x1024.s 1.8 [67/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x1024_ntA.s 1.9 [68/420] Linking CXX executable tensilelite/rocisa/stinkytofu/tools/tablegen/tablegen_inst_gen 1.9 [69/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x1024_ntB.s 1.9 [70/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x128.s 1.9 [71/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x128_ntA.s 1.9 [72/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x128_ntB.s 1.9 [73/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x256.s 1.9 [74/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x256_ntA.s 1.9 [75/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x256_ntB.s 2.0 [76/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x384.s 2.0 [77/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x384_ntA.s 2.0 [78/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x384_ntB.s 2.0 [79/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x512.s 2.0 [80/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x512_ntA.s 2.0 [81/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x512_ntB.s 2.0 [82/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x640.s 2.0 [83/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x640_ntA.s 2.0 [84/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x640_ntB.s 2.0 [85/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x768.s 2.1 [86/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x768_ntA.s 2.1 [87/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x768_ntB.s 2.1 [88/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x896.s 2.1 [89/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x896_ntA.s 2.1 [90/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x896_ntB.s 2.1 [91/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x128.s 2.1 [92/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x128_ntA.s 2.1 [93/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x128_ntB.s 2.1 [94/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x256.s 2.1 [95/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x256_ntA.s 2.1 [96/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x256_ntB.s 2.1 [97/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x384.s 2.1 [98/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x384_ntA.s 2.1 [99/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x384_ntB.s 2.1 [100/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x512.s 2.1 [101/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x512_ntA.s 2.1 [102/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x512_ntB.s 2.1 [103/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x640.s 2.1 [104/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x640_ntA.s 2.1 [105/420] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x640_ntB.s 2.1 [106/420] Assembling f4gemm_bf16_per1x32Fp4_noBpreShuffle_256x256.s 2.1 [107/420] Assembling wave_mxfp4_dynamic_gemm_256x192x256.s 2.1 [108/420] Building CXX object origami/CMakeFiles/origami.dir/src/origami/gemm.cpp.o 2.1 [109/420] Building CXX object origami/CMakeFiles/origami.dir/src/origami/hardware.cpp.o 2.1 [110/420] Building CXX object origami/CMakeFiles/origami.dir/src/origami/heuristics.cpp.o 2.1 [111/420] Building CXX object origami/CMakeFiles/origami.dir/src/origami/logger.cpp.o 2.1 [112/420] Building CXX object origami/CMakeFiles/origami.dir/src/origami/origami.cpp.o 2.1 [113/420] Building CXX object origami/CMakeFiles/origami.dir/src/origami/streamk.cpp.o 2.1 [114/420] Building CXX object origami/CMakeFiles/origami.dir/src/origami/types.cpp.o 2.1 [115/420] Building CXX object origami/CMakeFiles/origami.dir/src/simulator/tensilelite/formocast_simulator.cpp.o 2.1 [116/420] Building CXX object origami/CMakeFiles/origami.dir/src/simulator/tensilelite/formocast.cpp.o 2.1 [117/420] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_internals.cpp.o 2.1 [118/420] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_func.cpp.o 2.1 [119/420] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_type.cpp.o 2.1 [120/420] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_enum.cpp.o 2.1 [121/420] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_ndarray.cpp.o 2.1 [122/420] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_static_property.cpp.o 2.1 [123/420] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_ft.cpp.o 2.1 [124/420] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/common.cpp.o 2.1 [125/420] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/error.cpp.o 2.1 [126/420] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/trampoline.cpp.o 2.1 [127/420] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/implicit.cpp.o 2.1 [128/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/msgpack/MessagePack.cpp.o 2.1 [129/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/hip/HipSolutionAdapter.cpp.o 2.1 [130/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/hip/HipHardware.cpp.o 2.1 [131/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/Activation.cpp.o 2.1 [132/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/AMDGPU.cpp.o 2.1 [133/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/ContractionProblem.cpp.o 2.1 [134/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/ContractionSolution.cpp.o 2.1 [135/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/DataTypes.cpp.o 2.1 [136/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/Debug.cpp.o 2.1 [137/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/EmbeddedData.cpp.o 2.1 [138/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/EmbeddedLibrary.cpp.o 2.1 [139/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/KernelArguments.cpp.o 2.1 [140/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/KernelLanguageTypes.cpp.o 2.1 [141/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/MLFeatures.cpp.o 2.1 [142/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/MLPNet.cpp.o 2.1 [143/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/TensorDescriptor.cpp.o 2.1 [144/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/Utils.cpp.o 2.1 [145/420] cd /__w/rocm-libraries/rocm-libraries/TheRock/build/math-libs/BLAS/hipBLASLt/build && /usr/local/therock-tools/bin/cmake -E rm -f /__w/rocm-libraries/rocm-libraries/TheRock/build/math-libs/BLAS/hipBLASLt/stamp/stage.stamp 2.1 [146/420] Generating instruction metadata and ISA from .def files... 2.1 Gfx1250Formats.def: parsed 53 formats 2.1 Gfx1250Instructions.def: parsed 542 instructions 2.1 Successfully generated instruction metadata and ISA for all archs 2.4 [147/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/TensorOps.cpp.o 2.4 [148/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/Tensile.cpp.o 2.4 [149/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/PerformanceMetricTypes.cpp.o 2.4 [150/420] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/ScalarValueTypes.cpp.o 2.4 [151/420] Building CXX object clients/common/CMakeFiles/hipblaslt-mxdatagen.dir/src/mxDataGen.cpp.o 2.4 [152/420] Linking all kernel objects into rr_custom_kernels.co 2.4 [153/420] Linking CXX static library origami/liborigami.a 2.4 [154/420] Linking CXX static library tensilelite/rocisa/libnanobind-static.a 2.4 [155/420] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/src/gfx/GpuArchManager.cpp.o 2.4 [156/420] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/src/gfx/InstDefDSL.cpp.o 2.4 [157/420] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/src/gfx/Gfx1250/Gfx1250.cpp.o 2.4 [158/420] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/generated/GfxArchDefines.cpp.o 2.4 [159/420] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/generated/GfxLogicalMaps.cpp.o 2.4 [160/420] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/tablegen.cpp.o 2.4 [161/420] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenRocisaHwMapping.cpp.o 2.4 [162/420] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenPatterns.cpp.o 2.4 [163/420] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenLogicalToAsmMapping.cpp.o 2.4 [164/420] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenLogicalIR.cpp.o 2.4 [165/420] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenInstructions.cpp.o 2.4 [166/420] Copying rr_custom_kernels.co to /__w/rocm-libraries/rocm-libraries/TheRock/build/math-libs/BLAS/hipBLASLt/build/Tensile/library 3.3 [167/420] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/__w/rocm-libraries/rocm-libraries/shared/stinkytofu/src/serialization/asm/IRLexer.cpp.o 3.3 [168/420] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/__w/rocm-libraries/rocm-libraries/shared/stinkytofu/src/serialization/asm/PatternParser.cpp.o 3.4 [169/420] Linking CXX static library clients/common/libhipblaslt-mxdatagen.a 3.4 [170/420] Linking CXX static library tensilelite/rocisa/stinkytofu/hardware/libgfxisa.a 3.4 [171/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/Debug.cpp.o 3.4 [172/420] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/custom_kernels.cpp.o 3.4 [173/420] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/parameter_selection.cpp.o 3.4 [174/420] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/solution_cache.cpp.o 3.5 [175/420] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/solution_selection.cpp.o 3.5 [176/420] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/singletons.cpp.o 3.5 [177/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/rocblaslt_auxiliary.cpp.o 3.5 [178/420] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/gemm.cpp.o 3.6 [179/420] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/runtime_args_selection.cpp.o 3.6 [180/420] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/rocroller_host.cpp.o 3.6 [181/420] Linking CXX executable tensilelite/rocisa/stinkytofu/tools/tablegen/tablegen 3.6 [182/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/rocblaslt_transform.cpp.o 3.7 [183/420] Generating ISA definitions, IR classes, and pattern matchers with tablegen... 3.7 Generating Rocisa mappings for Gfx1250 in "/__w/rocm-libraries/rocm-libraries/TheRock/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/stinkytofu/ir/rocisa/RocisaGfx1250Mappings.inc" 3.7 Generating Logical IR -> ASM mappings in "/__w/rocm-libraries/rocm-libraries/TheRock/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/stinkytofu/ir/LogicalToAsmMappings_generated.inc" 3.7 Parsing patterns from: /__w/rocm-libraries/rocm-libraries/shared/stinkytofu/tools/tablegen/../../hardware/../src/transforms/asm/PeepholePatterns.pattern 3.7 Found 12 pattern(s) 3.7 Generated 12 pattern matchers: /__w/rocm-libraries/rocm-libraries/TheRock/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/PeepholePatterns.inc 3.7 Parsing patterns from: /__w/rocm-libraries/rocm-libraries/shared/stinkytofu/tools/tablegen/../../hardware/../src/transforms/logical/LogicalIRPatterns.pattern 3.7 Found 12 pattern(s) 3.7 Generated 12 pattern matchers: /__w/rocm-libraries/rocm-libraries/TheRock/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/LogicalIRPatterns.inc 3.7 3.7 === Generating High-Level IR === 3.7 Generated 274 opcode enum values -> LogicalOpcodes_generated.inc 3.7 Generated opcode mapping functions -> LogicalOpcode.cpp 3.7 Generated 274 LogicalInstruction factory functions + 5 special instruction factories (MFMA/MXMFMA/SMFMA/Label/IntrinsicCall) -> LogicalInstructions_generated.hpp 3.7 Generated Python bindings for 274 IR instructions -> PythonBindings_generated.inc 3.7 === High-Level IR generation completed successfully === 3.7 3.7 [184/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/handle.cpp.o 3.8 [185/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/tensile_host.cpp.o 3.8 [186/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/status.cpp.o 3.8 [187/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/stinkytofu/ir/logical/LogicalOpcode.cpp.o 3.9 [188/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/UserDrivenTuningParser.cpp.o 3.9 [189/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/hipblaslt_ostream.cpp.o 3.9 [190/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/hipblaslt-ext.cpp.o 3.9 [191/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/utility.cpp.o 4.0 [192/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/rocblaslt_mat.cpp.o 4.0 [193/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/AnalysisManager.cpp.o 4.0 [194/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/IRBase.cpp.o 4.0 [195/420] Building CXX object clients/samples/01_hipblaslt_gemm/CMakeFiles/sample_hipblaslt_gemm.dir/sample_hipblaslt_gemm.cpp.o 4.1 [196/420] Building CXX object clients/samples/05_hipblaslt_gemm_get_all_algos_ext/CMakeFiles/sample_hipblaslt_gemm_get_all_algos_ext.dir/sample_hipblaslt_gemm_get_all_algos_ext.cpp.o 4.1 [197/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/BasicBlock.cpp.o 4.1 [198/420] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/hipblaslt-ext-op.cpp.o 4.1 [199/420] Building CXX object clients/samples/05_hipblaslt_gemm_get_all_algos/CMakeFiles/sample_hipblaslt_gemm_get_all_algos.dir/sample_hipblaslt_gemm_get_all_algos.cpp.o 4.1 [200/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/Function.cpp.o 4.1 [201/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/PassManager.cpp.o 4.2 [202/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/DebugPrintInstrumentation.cpp.o 4.2 [203/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/DAGScheduleJsonWriter.cpp.o 4.2 [204/420] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/efficiency_monitor.cpp.o 4.2 [205/420] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/argument_model.cpp.o 4.2 [206/420] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/hipblaslt_random.cpp.o 4.2 [207/420] Building CXX object clients/samples/10_hipblaslt_gemm_amax_with_scale_ext/CMakeFiles/sample_hipblaslt_gemm_amax_with_scale_ext.dir/sample_hipblaslt_gemm_amax_with_scale_ext.cpp.o 4.2 [208/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/bindings/python/LogicalModule.cpp.o 4.2 [209/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/bindings/python/Module.cpp.o 4.2 [210/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/DumpStinkyFunctionPass.cpp.o 4.3 [211/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/LogicalToFunctionConverter.cpp.o 4.3 [212/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/LogicalOpcode.cpp.o 4.3 [213/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/IntrinsicPatternConverter.cpp.o 4.3 [214/420] Building CXX object clients/samples/03_hipblaslt_gemm_tuning_splitk_ext/CMakeFiles/sample_hipblaslt_gemm_tuning_splitk_ext.dir/sample_hipblaslt_gemm_tuning_splitk_ext.cpp.o 4.3 [215/420] Building CXX object clients/samples/01_hipblaslt_gemm_ext/CMakeFiles/sample_hipblaslt_gemm_ext.dir/sample_hipblaslt_gemm_ext.cpp.o 4.3 [216/420] Building CXX object clients/samples/02_hipblaslt_gemm_batched/CMakeFiles/sample_hipblaslt_gemm_batched.dir/sample_hipblaslt_gemm_batched.cpp.o 4.3 [217/420] Building CXX object clients/samples/09_hipblaslt_gemm_amax/CMakeFiles/sample_hipblaslt_gemm_amax.dir/sample_hipblaslt_gemm_amax.cpp.o 4.4 [218/420] Building CXX object clients/samples/09_hipblaslt_gemm_amax_ext/CMakeFiles/sample_hipblaslt_gemm_amax_ext.dir/sample_hipblaslt_gemm_amax_ext.cpp.o 4.4 [219/420] Building CXX object clients/samples/12_hipblaslt_gemm_drelu_bgrad/CMakeFiles/sample_hipblaslt_gemm_drelu_bgrad.dir/sample_hipblaslt_gemm_drelu_bgrad.cpp.o 4.4 [220/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/IntrinsicLibrary.cpp.o 4.4 [221/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/asm/StinkyAsmIR.cpp.o 4.4 [222/420] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/hipblaslt_arguments.cpp.o 4.4 [223/420] Building CXX object clients/CMakeFiles/hipblaslt-bench-extop-matrixtransform.dir/bench/src/client_extop_matrixtransform.cpp.o 4.5 [224/420] Building CXX object clients/samples/04_hipblaslt_gemm_bias/CMakeFiles/sample_hipblaslt_gemm_bias.dir/sample_hipblaslt_gemm_bias.cpp.o 4.5 [225/420] Building CXX object clients/samples/04_hipblaslt_gemm_bias_ext/CMakeFiles/sample_hipblaslt_gemm_bias_ext.dir/sample_hipblaslt_gemm_bias_ext.cpp.o 4.5 [226/420] Building CXX object clients/samples/07_hipblaslt_gemm_alphavec_ext/CMakeFiles/sample_hipblaslt_gemm_alphavec_ext.dir/sample_hipblaslt_gemm_alphavec_ext.cpp.o 4.5 [227/420] Building CXX object clients/samples/08_hipblaslt_gemm_gelu_aux_bias_ext/CMakeFiles/sample_hipblaslt_gemm_gelu_aux_bias_ext.dir/sample_hipblaslt_gemm_gelu_aux_bias_ext.cpp.o 4.5 [228/420] Building CXX object clients/samples/11_hipblaslt_gemm_bgradb/CMakeFiles/sample_hipblaslt_gemm_bgradb.dir/sample_hipblaslt_gemm_bgradb.cpp.o 4.5 [229/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/IntrinsicRegistry.cpp.o 4.5 [230/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/asm/StinkySignature.cpp.o 4.6 [231/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/IntrinsicExpansionPass.cpp.o 4.6 [232/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/ToStinkyAsmPass.cpp.o 4.6 [233/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/CompositeInstructionLoweringPass.cpp.o 4.6 [234/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/LogicalPeepholePass.cpp.o 4.6 [235/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/PassOrderSnapshotJson.cpp.o 4.6 [236/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/PhiPlacement.cpp.o 4.7 [237/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/BuildDefUseChain.cpp.o 4.7 [238/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/CFGBuilderPass.cpp.o 4.7 [239/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/PeepholeOptimizationPass.cpp.o 4.7 [240/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/DeadCodeEliminationPass.cpp.o 4.7 [241/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/RedundantMovEliminationPass.cpp.o 4.7 [242/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/LegalizationUtils.cpp.o 4.7 [243/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/ScheduleLastLRsPass.cpp.o 4.8 [244/420] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/cblas_interface.cpp.o 4.8 [245/420] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/hipblaslt_parse_data.cpp.o 4.8 [246/420] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/hipblaslt_init_device.cpp.o 4.8 [247/420] Building CXX object clients/CMakeFiles/hipblaslt-api-overhead.dir/bench/src/client_api_overhead.cpp.o 4.8 [248/420] Building CXX object clients/CMakeFiles/hipblaslt-bench-groupedgemm-fixed-mk.dir/bench/src/client_groupedgemm_fixed_mk.cpp.o 4.8 [249/420] Building CXX object clients/CMakeFiles/hipblaslt-bench-extop-layernorm.dir/bench/src/client_extop_layernorm.cpp.o 4.8 [250/420] Building CXX object clients/CMakeFiles/hipblaslt-bench-extop-softmax.dir/bench/src/client_extop_softmax.cpp.o 4.8 [251/420] Building CXX object clients/CMakeFiles/hipblaslt-bench-extop-amax.dir/bench/src/client_extop_amax.cpp.o 4.8 [252/420] Building CXX object clients/samples/02_hipblaslt_gemm_batched_ext/CMakeFiles/sample_hipblaslt_gemm_batched_ext.dir/sample_hipblaslt_gemm_batched_ext.cpp.o 4.8 [253/420] Building CXX object clients/samples/06_hipblaslt_gemm_get_algo_by_index_ext/CMakeFiles/sample_hipblaslt_gemm_get_algo_by_index_ext.dir/sample_hipblaslt_gemm_get_algo_by_index_ext.cpp.o 4.9 [254/420] Building CXX object clients/samples/08_hipblaslt_gemm_gelu_aux_bias/CMakeFiles/sample_hipblaslt_gemm_gelu_aux_bias.dir/sample_hipblaslt_gemm_gelu_aux_bias.cpp.o 4.9 [255/420] Building CXX object clients/samples/10_hipblaslt_gemm_amax_with_scale/CMakeFiles/sample_hipblaslt_gemm_amax_with_scale.dir/sample_hipblaslt_gemm_amax_with_scale.cpp.o 4.9 [256/420] Building CXX object clients/samples/11_hipblaslt_gemm_ext_bgradb/CMakeFiles/sample_hipblaslt_gemm_ext_bgradb.dir/sample_hipblaslt_gemm_ext_bgradb.cpp.o 4.9 [257/420] Building CXX object clients/samples/12_hipblaslt_gemm_dgelu_bgrad/CMakeFiles/sample_hipblaslt_gemm_dgelu_bgrad.dir/sample_hipblaslt_gemm_dgelu_bgrad.cpp.o 4.9 [258/420] Building CXX object clients/samples/12_hipblaslt_gemm_dgelu_bgrad_ext/CMakeFiles/sample_hipblaslt_gemm_dgelu_bgrad_ext.dir/sample_hipblaslt_gemm_dgelu_bgrad_ext.cpp.o 5.0 [259/420] Building CXX object clients/samples/12_hipblaslt_gemm_drelu_bgrad_ext/CMakeFiles/sample_hipblaslt_gemm_drelu_bgrad_ext.dir/sample_hipblaslt_gemm_drelu_bgrad_ext.cpp.o 5.0 [260/420] Building CXX object clients/samples/13_hipblaslt_gemm_is_tuned_ext/CMakeFiles/sample_hipblaslt_gemm_is_tuned_ext.dir/sample_hipblaslt_gemm_is_tuned_ext.cpp.o 5.0 [261/420] Building CXX object clients/samples/14_hipblaslt_gemm_tuning_wgm_ext/CMakeFiles/sample_hipblaslt_gemm_tuning_wgm_ext.dir/sample_hipblaslt_gemm_tuning_wgm_ext.cpp.o 5.0 [262/420] Building CXX object clients/samples/15_hipblaslt_gemm_with_scale_a_b/CMakeFiles/sample_hipblaslt_gemm_with_scale_a_b.dir/sample_hipblaslt_gemm_with_scale_a_b.cpp.o 5.0 [263/420] Building CXX object clients/samples/15_hipblaslt_gemm_with_scale_a_b_ext/CMakeFiles/sample_hipblaslt_gemm_with_scale_a_b_ext.dir/sample_hipblaslt_gemm_with_scale_a_b_ext.cpp.o 5.0 [264/420] Building CXX object clients/samples/15_hipblaslt_gemm_with_scale_a_b_vector/CMakeFiles/sample_hipblaslt_gemm_with_scale_a_b_vector.dir/sample_hipblaslt_gemm_with_scale_a_b_vector.cpp.o 5.1 [265/420] Building CXX object clients/samples/15_hipblaslt_gemm_with_scale_a_b_vector/CMakeFiles/sample_hipblaslt_gemm_swizzleA_with_scale_a_b_vector.dir/sample_hipblaslt_gemm_swizzleA_with_scale_a_b_vector.cpp.o 5.1 [266/420] Building CXX object clients/samples/16_hipblaslt_groupedgemm_ext/CMakeFiles/sample_hipblaslt_groupedgemm_ext.dir/sample_hipblaslt_groupedgemm_ext.cpp.o 5.1 [267/420] Building CXX object clients/samples/18_hipblaslt_groupedgemm_get_all_algos_ext/CMakeFiles/sample_hipblaslt_groupedgemm_get_all_algos_ext.dir/sample_hipblaslt_groupedgemm_get_all_algos_ext.cpp.o 5.1 [268/420] Building CXX object clients/samples/19_hipblaslt_gemm_mix_precision_ext/CMakeFiles/sample_hipblaslt_gemm_mix_precision_ext.dir/sample_hipblaslt_gemm_mix_precision_ext.cpp.o 5.1 [269/420] Building CXX object clients/samples/21_hipblaslt_gemm_attr_tciA_tciB/CMakeFiles/sample_hipblaslt_gemm_attr_tciA_tciB.dir/sample_hipblaslt_gemm_attr_tciA_tciB.cpp.o 5.1 [270/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyDAGSchedulerPass.cpp.o 5.1 [271/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyConfigurableWaitCntPass.cpp.o 5.2 [272/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/ScheduleFirstLRsPass.cpp.o 5.2 [273/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyWaitCntInsertionPass.cpp.o 5.2 [274/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyRemoveWaitCntPass.cpp.o 5.2 [275/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyBuildImplicitDependencyPass.cpp.o 5.2 [276/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/InsertVgprMsbPass.cpp.o 5.2 [277/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/pipeline/backend/Backend.cpp.o 5.2 [278/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/pipeline/backend/BackendRegistry.cpp.o 5.2 [279/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/pipeline/backend/Gfx1250Backend.cpp.o 5.2 [280/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/logical/IRSerializer.cpp.o 5.2 [281/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/StinkyAsmPrinter.cpp.o 5.2 [282/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/StinkyAsmEmitter.cpp.o 5.2 [283/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/IRLexer.cpp.o 5.2 [284/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/IRParser.cpp.o 5.2 [285/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/IRConverter.cpp.o 5.2 [286/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/ModifierSerializer.cpp.o 5.2 [287/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/PatternParser.cpp.o 5.2 [288/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/analysis/asm/AsmVerifierPass.cpp.o 5.2 [289/420] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/utility.cpp.o 5.2 [290/420] Building CXX object clients/CMakeFiles/hipblaslt-bench.dir/bench/src/client.cpp.o 5.2 [291/420] Building CXX object clients/samples/17_hipblaslt_groupedgemm_fixed_mk_ext/CMakeFiles/sample_hipblaslt_groupedgemm_fixed_mk_ext.dir/sample_hipblaslt_groupedgemm_fixed_mk_ext.cpp.o 5.2 [292/420] Building CXX object clients/samples/19_hipblaslt_gemm_mix_precision/CMakeFiles/sample_hipblaslt_gemm_mix_precision.dir/sample_hipblaslt_gemm_mix_precision.cpp.o 5.2 [293/420] Building CXX object clients/samples/20_hipblaslt_gemm_mix_precision_with_amax_ext/CMakeFiles/sample_hipblaslt_gemm_mix_precision_with_amax_ext.dir/sample_hipblaslt_gemm_mix_precision_with_amax_ext.cpp.o 5.2 [294/420] Building CXX object clients/samples/23_hipblaslt_ext_op_amax/CMakeFiles/sample_hipblaslt_ext_op_amax.dir/sample_hipblaslt_ext_op_amax.cpp.o 5.2 [295/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/RawAsmParser.cpp.o 5.2 [296/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/analysis/controlflow/Dominance.cpp.o 5.2 [297/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/analysis/logical/IRVerifierPass.cpp.o 5.2 [298/420] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/hardware/ArchHelper.cpp.o 5.2 [299/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/main.cpp.o 5.2 [300/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/base.cpp.o 5.2 [301/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/code.cpp.o 5.2 [302/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/container.cpp.o 5.2 [303/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/count.cpp.o 5.2 [304/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/enum.cpp.o 5.2 [305/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/helper.cpp.o 5.2 [306/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/label.cpp.o 5.2 [307/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/macro.cpp.o 5.2 [308/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/register.cpp.o 5.2 [309/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/instruction.cpp.o 5.2 [310/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/common.cpp.o 5.2 [311/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/branch.cpp.o 5.2 [312/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/cmp.cpp.o 5.2 [313/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/cvt.cpp.o 5.2 [314/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/mem.cpp.o 5.2 [315/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/mfma.cpp.o 5.2 [316/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/extension.cpp.o 5.2 [317/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/pass.cpp.o 5.2 [318/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/graph.cpp.o 5.2 [319/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/composite.cpp.o 5.2 [320/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/cycle.cpp.o 5.2 [321/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/remove.cpp.o 5.2 [322/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/insert_delay_alu.cpp.o 5.2 [323/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/functions.cpp.o 5.2 [324/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/argument.cpp.o 5.2 [325/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/f_math.cpp.o 5.2 [326/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/f_branch.cpp.o 5.2 [327/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/f_cast.cpp.o 5.2 [328/420] Building CXX object clients/samples/22_hipblaslt_ext_op_layernorm/CMakeFiles/sample_hipblaslt_ext_op_layernorm.dir/sample_hipblaslt_ext_op_layernorm.cpp.o 5.3 [329/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/__w/rocm-libraries/rocm-libraries/shared/stinkytofu/src/conversion/rocisa/AllHwMappings.cpp.o 5.3 [330/420] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/__w/rocm-libraries/rocm-libraries/shared/stinkytofu/src/conversion/rocisa/ToStinkyTofuUtils.cpp.o 5.3 [331/420] Building CXX object clients/samples/25_hipblaslt_weight_swizzle_padding/CMakeFiles/sample_hipblaslt_weight_swizzle_padding.dir/sample_hipblaslt_weight_swizzle_padding.cpp.o 5.4 [332/420] Linking CXX shared library tensilelite/rocisa/stinkytofu/libstinkytofu.so 5.6 [333/420] Linking CXX shared module tensilelite/rocisa/rocisa/_rocisa.cpython-312-x86_64-linux-gnu.so 5.6 [333/420] Building device libraries to /__w/rocm-libraries/rocm-libraries/TheRock/build/math-libs/BLAS/hipBLASLt/build/Tensile ... 7.4 7.4 ################################################################################ 7.4 # Tensile Create Library 18.2 Capability gfx942 18.2 HasMFMA_bf16_1k 1 18.2 HasAddLshl 1 18.2 HasAtomicAdd 1 18.2 HasBF16CVT - 18.2 HasCvtFP8toF16 - 18.2 HasDLCModifier - 18.2 HasDirectToLds 1 18.2 HasDirectToLdsx4 - 18.2 HasExplicitCO 1 18.2 HasExplicitNC - 18.2 HasGLCModifier - 18.2 HasGLTr16B128 - 18.2 HasGLTr8B64 - 18.2 HasLDSTr - 18.2 HasLDSTrB128B16 - 18.2 HasLDSTrB64B16 - 18.2 HasLDSTrB64B4 - 18.2 HasLDSTrB64B8 - 18.2 HasLDSTrB96B6 - 18.2 HasLshlOr 1 18.2 HasMFMA 1 18.2 HasMUBUFConst 1 18.2 HasNTModifier 1 18.2 HasNewBarrier - 18.2 HasPartialOOB 1 18.2 HasPkF16CVT - 18.2 HasSC0Modifier 1 18.2 HasSCMPK 1 18.2 HasSCOPEModifier - 18.2 HasSMFMA 1 18.2 HasSMulHi 1 18.2 HasSWMMAC - 18.2 HasScalarStore 1 18.2 HasTDM - 18.2 HasVgprMSB - 18.2 HasVgprMSB16 - 18.2 HasWMMA - 18.2 MaxLgkmcnt 1 18.2 MaxVmcnt 1 18.2 SeparateLGKMcnt - 18.2 SeparateVMcnt - 18.2 SeparateVscnt - 18.2 ShortBranchMaxLength 1 18.2 SupportedISA 1 18.2 SupportedSource 1 18.2 HasWMMA_V1 - 18.2 HasWMMA_V2 - 18.2 HasWMMA_V3 - 18.2 s_delay_alu - 18.2 v_prng_b32 - 18.2 v_mov_b64 1 18.2 HasMFMA_b8 1 18.2 v_dot2_f32_bf16 - 18.2 v_dot2c_f32_bf16 - 18.2 HasMFMA_explictB 1 18.2 Hascvtfp8_f16 - 18.2 v_dot2_f32_f16 1 18.2 v_dot2c_f32_f16 1 18.2 v_fma_f16 1 18.2 v_fmac_f16 - 18.2 v_mac_f16 1 18.2 v_pk_fma_f16 1 18.2 v_pk_fmac_f16 - 18.2 v_fma_f32 1 18.2 v_fma_mix_f32 1 18.2 v_fmac_f32 1 18.2 v_mac_f32 - 18.2 v_mad_mix_f32 - 18.2 v_pk_add_f32 1 18.2 v_pk_mul_f32 1 18.2 HasMFMA_f64 1 18.2 HasWMMA_V3_f64 - 18.2 v_fma_f64 1 18.2 HasMFMA_f8 1 18.2 HasMFMA_f8f6f4 - 18.2 HasWMMA_f8f6f4 - 18.2 HasSWMMAC_gfx1250 - 18.2 HasAdd_PC_i64 - 18.2 VOP3v_dot4_i32_i8 1 18.2 v_dot4_i32_i8 - 18.2 v_dot4c_i32_i8 1 18.2 Hascvtf16_fp8_sf32 - 18.2 s_sub_u64 - 18.2 HasMFMA_xf32 1 18.2 ArchAccUnifiedRegs 1 18.2 CMPXWritesSGPR 1 18.2 CrosslaneWait 1 18.2 DSLow16NotPreserve - 18.2 DeviceLDS 1 18.2 HasAccCD 1 18.2 HasEccHalf 1 18.2 HasF32XEmulation - 18.2 HasFP8_OCP - 18.2 HasInvWbDevFences - 18.2 HasSchedMode - 18.2 HasWave32 - 18.2 HasWmmaArbStallBit - 18.2 NoSDWA - 18.2 RequiresXCntForVolatileVMEM - 18.2 SDWAWait 1 18.2 TransOpWait 1 18.2 VOP3ByteSel - 18.2 VgprBank - 18.2 Waitcnt0Disabled 1 18.2 WorkGroupIdFromTTM - 18.2 vL1DCacheLineBytes 1 18.2 # Found hipcc version 7.13.26174-ca17aa89d6 18.4 ROCm 7.13.26174 Component path: /__w/rocm-libraries/rocm-libraries/TheRock/build/core/clr/dist/lib/llvm/bin/clang++ version: 23.0.0 18.4 ROCm 7.13.26174 Component path: /__w/rocm-libraries/rocm-libraries/TheRock/build/compiler/amd-llvm/dist/lib/llvm/bin/clang-offload-bundler version: 23.0.0 18.4 # LogicFilter: /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/**/*.yaml 18.8 # Experimental: False 18.8 # Archs: gfx942 18.8 # LibraryLogicFiles: 805 18.8 Loading Logics...: Launching 64 threads... 19.7 Loading Logics...: Done. (0.9 secs elapsed) 20.5 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942_80cu/Equality/aquavanjaram_Cijk_Alik_Bljk_HHS_STA_BH_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 20.6 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942_80cu/Equality/aquavanjaram_Cijk_Alik_Bljk_BBS_STA_BH_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 30.4 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942_80cu/GridBased/aquavanjaram_Cijk_Alik_Bljk_BSS_STA_BH_Bias_HA_S_SAV_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 30.7 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942_80cu/GridBased/aquavanjaram_Cijk_Alik_Bljk_BSS_STA_BH_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 31.7 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942_80cu/GridBased/aquavanjaram_Cijk_Alik_Bljk_HHS_STA_BH_Bias_HA_S_SAV_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 31.8 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942_80cu/GridBased/aquavanjaram_Cijk_Alik_Bljk_BBS_STA_BH_Bias_HA_S_SAV_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 32.8 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942_80cu/GridBased/aquavanjaram_Cijk_Alik_Bljk_HSS_STA_BH_Bias_HA_S_SAV_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 33.3 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942_80cu/GridBased/aquavanjaram_Cijk_Alik_Bljk_HSS_STA_BH_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 33.5 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942_80cu/GridBased/aquavanjaram_Cijk_Alik_Bljk_BBS_STA_BH_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 34.4 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942_80cu/GridBased/aquavanjaram_Cijk_Alik_Bljk_HHS_STA_BH_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 103.0 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942/Equality/aquavanjaram_Cijk_Alik_Bljk_B8F8NBS_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 543.1 Tensile::WARNING: Version = /__w/rocm-libraries/rocm-libraries/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/aquavanjaram/gfx942/GridBased/aquavanjaram_Cijk_Alik_Bljk_BBS_STA_BH_UserArgs.yaml in library logic file 4.33.0 does not match Tensile version = 5.0.0 643.5 /opt/python/cp312-cp312/lib/python3.12/site-packages/joblib/externals/loky/process_executor.py:782: UserWarning: A worker stopped while some jobs were given to the executor. This can be caused by a too short worker timeout or by a memory leak. 643.5 warnings.warn( 854.9 854.9 =========================================================== 854.9 WARNING: YAML parameter type mismatches detected (59 total across 6 files): 854.9 =========================================================== 854.9 NoReject: found int in 55 solutions (values: 1) - expected bool 854.9 PreloadKernArgs: found int in 4 solutions (values: 0, 1) - expected bool 854.9 ----------------------------------------------------------- 854.9 This will cause std::bad_cast at runtime because msgpack 854.9 serializes bool and int as different wire types. 854.9 Fix these to prevent future build failures. 854.9 =========================================================== 891.2 Number of solutions parsed: 312964 891.2 Number of unique solutions: 301096 943.1 Time to load yaml files (s): 872.55 943.1 Number of duplicate kernels: 17576 943.1 Generating assembly kernels: Launching 64 threads for 168621 tasks... 3095.9 Generating assembly kernels: Done. (2152.8 secs elapsed) 3275.0 # Helper kernel cache MISS (1175096d28ae...) 3457.8 buildSourceCodeObjectFile time (s): 182.85 3528.4 Time to generate kernels (s): 2530.78 3528.4 Time to pass kernel info to library (s): 41.91 3528.4 Writing master solution libraries: Launching 64 threads for 567 tasks... 3661.6 Writing master solution libraries: Done. (133.3 secs elapsed) 3691.7 Time to write master solution libraries (s): 133.30 3691.7 # Tensile Library Writer DONE 3691.7 ################################################################################ 3691.7 3691.7 Total time (s): 3667.68 3691.7 Total kernels processed: 168621 3691.7 Kernels processed per second: 45.97 3691.7 KernelHelperObjs: 259 3693.4 [419/420] Creating hipblasltExtOpLibrary_gfx942.dat END 1777965587.6506803 3693.4375755786896 0