BEGIN 1778472153.7692132 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 0.1 [1/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x128.s 0.1 [2/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x128_ntA.s 0.1 [3/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x128_ntB.s 0.1 [4/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x384_ntA.s 0.1 [5/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x128_ntB.s 0.1 [6/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x256_ntA.s 0.1 [7/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x384.s 0.1 [8/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x128.s 0.1 [9/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x128_ntA.s 0.1 [10/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x256.s 0.1 [11/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x384_ntB.s 0.1 [12/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x256_ntB.s 0.1 [13/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x256.s 0.1 [14/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x128.s 0.1 [15/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x128_ntA.s 0.1 [16/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x128_ntB.s 0.1 [17/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x128_ntA.s 0.1 [18/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x256_ntA.s 0.1 [19/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x256.s 0.1 [20/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x256_ntB.s 0.1 [21/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x256_ntA.s 0.1 [22/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x256_ntB.s 0.1 [23/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x128_ntB.s 0.1 [24/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x256_ntA.s 0.1 [25/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x256_ntB.s 0.1 [26/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x384.s 0.1 [27/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x384_ntA.s 0.1 [28/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_192x128.s 0.1 [29/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x256.s 0.1 [30/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x384.s 0.1 [31/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_160x384_ntB.s 0.1 [32/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x128.s 0.1 [33/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x128_ntA.s 0.1 [34/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x384_ntA.s 0.1 [35/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x384_ntB.s 0.1 [36/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x128_ntB.s 0.1 [37/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x512_ntA.s 0.1 [38/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x512_ntA.s 0.1 [39/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x256.s 0.1 [40/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x256_ntA.s 0.1 [41/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_224x256_ntB.s 0.1 [42/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x512.s 0.1 [43/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x512_ntB.s 0.1 [44/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x128.s 0.1 [45/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x512_ntB.s 0.1 [46/424] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen_inst_gen.dir/GenInstructionsMain.cpp.o 0.1 [47/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_128x512.s 0.1 [48/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x128_ntA.s 0.1 [49/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x128_ntB.s 0.1 [50/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x1024_ntA.s 0.1 [51/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x640.s 0.1 [52/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x640_ntA.s 0.1 [53/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x640_ntB.s 0.1 [54/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x256.s 0.1 [55/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x256_ntA.s 0.1 [56/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x1024.s 0.1 [57/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x1024_ntB.s 0.1 [58/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x768.s 0.1 [59/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x768_ntA.s 0.1 [60/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x768_ntB.s 0.1 [61/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_256x256_ntB.s 0.1 [62/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x896.s 0.1 [63/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x896_ntA.s 0.1 [64/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x128.s 0.1 [65/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x128_ntA.s 0.1 [66/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x128_ntB.s 0.1 [67/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x256.s 0.1 [68/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x384.s 0.1 [69/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x384_ntB.s 0.1 [70/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x256_ntA.s 0.1 [71/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x384_ntA.s 0.1 [72/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x256_ntB.s 0.1 [73/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x512.s 0.1 [74/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x512_ntA.s 0.1 [75/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x640_ntB.s 0.1 [76/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x1024.s 0.1 [77/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x1024_ntA.s 0.1 [78/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x128.s 0.1 [79/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x512_ntB.s 0.1 [80/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x128_ntB.s 0.1 [81/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x128_ntA.s 0.1 [82/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x640.s 0.1 [83/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_32x896_ntB.s 0.1 [84/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x640_ntA.s 0.1 [85/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x256_ntA.s 0.1 [86/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x1024_ntB.s 0.1 [87/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x256.s 0.1 [88/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x384.s 0.1 [89/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x768_ntA.s 0.1 [90/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x768.s 0.1 [91/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x384_ntA.s 0.1 [92/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x768_ntB.s 0.1 [93/424] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen_inst_gen.dir/GenInstructions.cpp.o 0.1 [94/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x384_ntB.s 0.1 [95/424] cd /__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build && /usr/local/therock-tools/bin/cmake -E rm -f /__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/stamp/stage.stamp 0.1 [96/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x256_ntB.s 0.1 [97/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x896_ntA.s 0.1 [98/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x896_ntB.s 0.1 [99/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_64x896.s 0.1 [100/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x512_ntB.s 0.1 [101/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x512.s 0.1 [102/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x512_ntA.s 0.1 [103/424] Assembling f4gemm_bf16_per1x32Fp4_noBpreShuffle_256x256.s 0.1 [104/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x640_ntA.s 0.1 [105/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x640_ntB.s 0.1 [106/424] Assembling f4gemm_bf16_per1x32Fp4_BpreShuffle_96x640.s 0.1 [107/424] Assembling wave_mxfp4_dynamic_gemm_256x192x256.s 0.2 [108/424] Linking all kernel objects into rr_custom_kernels.co 0.2 [109/424] Linking CXX executable tensilelite/rocisa/stinkytofu/tools/tablegen/tablegen_inst_gen 0.2 [110/424] Copying rr_custom_kernels.co to /__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build/Tensile/library 0.2 [111/424] Generating instruction metadata and ISA from .def files... 0.2 Gfx1250Formats.def: parsed 53 formats 0.2 Gfx1250Instructions.def: parsed 542 instructions 0.2 Successfully generated instruction metadata and ISA for all archs 0.2 [112/424] Building CXX object origami/CMakeFiles/origami.dir/src/origami/logger.cpp.o 0.2 [113/424] Building CXX object origami/CMakeFiles/origami.dir/src/origami/origami.cpp.o 0.2 [114/424] Building CXX object origami/CMakeFiles/origami.dir/src/simulator/tensilelite/formocast.cpp.o 0.2 [115/424] Building CXX object origami/CMakeFiles/origami.dir/src/origami/types.cpp.o 0.2 [116/424] Building CXX object origami/CMakeFiles/origami.dir/src/origami/hardware.cpp.o 0.2 [117/424] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_static_property.cpp.o 0.3 [118/424] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_ndarray.cpp.o 0.3 [119/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/Debug.cpp.o 0.3 [120/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/KernelLanguageTypes.cpp.o 0.3 [121/424] Building CXX object origami/CMakeFiles/origami.dir/src/origami/streamk.cpp.o 0.3 [122/424] Building CXX object origami/CMakeFiles/origami.dir/src/origami/heuristics.cpp.o 0.3 [123/424] Building CXX object origami/CMakeFiles/origami.dir/src/origami/gemm.cpp.o 0.3 [124/424] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/trampoline.cpp.o 0.3 [125/424] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/error.cpp.o 0.3 [126/424] Building CXX object origami/CMakeFiles/origami.dir/src/simulator/tensilelite/formocast_simulator.cpp.o 0.3 [127/424] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_enum.cpp.o 0.3 [128/424] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_internals.cpp.o 0.3 [129/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/Utils.cpp.o 0.3 [130/424] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_type.cpp.o 0.3 [131/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/Activation.cpp.o 0.3 [132/424] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/common.cpp.o 0.3 [133/424] Linking CXX static library origami/liborigami.a 0.3 [134/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/EmbeddedData.cpp.o 0.3 [135/424] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/src/gfx/Gfx1250/Gfx1250.cpp.o 0.3 [136/424] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_ft.cpp.o 0.4 [137/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/hip/HipSolutionAdapter.cpp.o 0.4 [138/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/AMDGPU.cpp.o 0.4 [139/424] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/nb_func.cpp.o 0.4 [140/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/PerformanceMetricTypes.cpp.o 0.4 [141/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/TensorDescriptor.cpp.o 0.4 [142/424] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/src/gfx/InstDefDSL.cpp.o 0.4 [143/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/MLPNet.cpp.o 0.4 [144/424] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/generated/GfxArchDefines.cpp.o 0.4 [145/424] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/solution_selection.cpp.o 0.4 [146/424] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/src/gfx/GpuArchManager.cpp.o 0.4 [147/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/ContractionProblem.cpp.o 0.4 [148/424] Building CXX object tensilelite/rocisa/stinkytofu/hardware/CMakeFiles/gfxisa.dir/generated/GfxLogicalMaps.cpp.o 0.4 [149/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/TensorOps.cpp.o 0.4 [150/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/Debug.cpp.o 0.4 [151/424] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/custom_kernels.cpp.o 0.4 [152/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/msgpack/MessagePack.cpp.o 0.4 [153/424] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/rocroller_host.cpp.o 0.4 [154/424] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenLogicalIR.cpp.o 0.4 [155/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/Tensile.cpp.o 0.4 [156/424] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/solution_cache.cpp.o 0.4 [157/424] Linking CXX static library tensilelite/rocisa/stinkytofu/hardware/libgfxisa.a 0.4 [158/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/KernelArguments.cpp.o 0.4 [159/424] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenRocisaHwMapping.cpp.o 0.4 [160/424] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/runtime_args_selection.cpp.o 0.4 [161/424] Building CXX object tensilelite/rocisa/CMakeFiles/nanobind-static.dir/__/__/_deps/nanobind-src/src/implicit.cpp.o 0.4 [162/424] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/parameter_selection.cpp.o 0.4 [163/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/hipblaslt.cpp.o 0.4 [164/424] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenInstructions.cpp.o 0.4 [165/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/ScalarValueTypes.cpp.o 0.4 [166/424] Building CXX object clients/common/CMakeFiles/hipblaslt-mxdatagen.dir/src/mxDataGen.cpp.o 0.4 [167/424] Building CXX object library/src/amd_detail/rocblaslt/src/rocroller/CMakeFiles/hipblaslt-rocroller.dir/gemm.cpp.o 0.4 [168/424] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/tablegen.cpp.o 0.5 [169/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/DataTypes.cpp.o 0.5 [170/424] Linking CXX static library tensilelite/rocisa/libnanobind-static.a 0.5 [171/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/handle.cpp.o 0.5 [172/424] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/src/serialization/asm/PatternParser.cpp.o 0.5 [173/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/status.cpp.o 0.5 [174/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/rocblaslt_transform.cpp.o 0.5 [175/424] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenLogicalToAsmMapping.cpp.o 0.5 [176/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/hipblaslt-ext.cpp.o 0.5 [177/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/UserDrivenTuningParser.cpp.o 0.5 [178/424] Linking CXX static library clients/common/libhipblaslt-mxdatagen.a 0.5 [179/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/EmbeddedLibrary.cpp.o 0.5 [180/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/tensile_host.cpp.o 0.5 [181/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/ContractionSolution.cpp.o 0.5 [182/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/hipblaslt-ext-op.cpp.o 0.5 [183/424] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/singletons.cpp.o 0.5 [184/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/rocblaslt_auxiliary.cpp.o 0.5 [185/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/MLFeatures.cpp.o 0.5 [186/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/rocblaslt_mat.cpp.o 0.5 [187/424] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/GenPatterns.cpp.o 0.5 [188/424] Building CXX object tensilelite/CMakeFiles/tensilelite-host.dir/src/hip/HipHardware.cpp.o 0.5 [189/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/rocblaslt/src/utility.cpp.o 0.5 [190/424] Building CXX object CMakeFiles/hipblaslt.dir/library/src/amd_detail/hipblaslt_ostream.cpp.o 0.5 [191/424] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/efficiency_monitor.cpp.o 0.5 [192/424] Building CXX object tensilelite/rocisa/stinkytofu/tools/tablegen/CMakeFiles/tablegen.dir/__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/src/serialization/asm/IRLexer.cpp.o 0.5 [193/424] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/argument_model.cpp.o 0.5 [194/424] Building CXX object clients/samples/01_hipblaslt_gemm/CMakeFiles/sample_hipblaslt_gemm.dir/sample_hipblaslt_gemm.cpp.o 0.5 [195/424] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/utility.cpp.o 0.5 [196/424] Building CXX object clients/samples/01_hipblaslt_gemm_ext/CMakeFiles/sample_hipblaslt_gemm_ext.dir/sample_hipblaslt_gemm_ext.cpp.o 0.6 [197/424] Building CXX object clients/CMakeFiles/hipblaslt-api-overhead.dir/bench/src/client_api_overhead.cpp.o 0.6 [198/424] Building CXX object clients/samples/09_hipblaslt_gemm_amax/CMakeFiles/sample_hipblaslt_gemm_amax.dir/sample_hipblaslt_gemm_amax.cpp.o 0.6 [199/424] 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 0.6 [200/424] 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 0.6 [201/424] 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 0.6 [202/424] Building CXX object clients/samples/07_hipblaslt_gemm_alphavec_ext/CMakeFiles/sample_hipblaslt_gemm_alphavec_ext.dir/sample_hipblaslt_gemm_alphavec_ext.cpp.o 0.6 [203/424] 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 0.6 [204/424] Building CXX object clients/CMakeFiles/hipblaslt-bench-extop-softmax.dir/bench/src/client_extop_softmax.cpp.o 0.6 [205/424] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/cblas_interface.cpp.o 0.6 [206/424] Building CXX object clients/samples/09_hipblaslt_gemm_amax_ext/CMakeFiles/sample_hipblaslt_gemm_amax_ext.dir/sample_hipblaslt_gemm_amax_ext.cpp.o 0.6 [207/424] Linking CXX executable tensilelite/rocisa/stinkytofu/tools/tablegen/tablegen 0.6 [208/424] 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 0.6 [209/424] Building CXX object clients/CMakeFiles/hipblaslt-bench-extop-layernorm.dir/bench/src/client_extop_layernorm.cpp.o 0.6 [210/424] 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 0.6 [211/424] 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 0.6 [212/424] Building CXX object clients/samples/16_hipblaslt_groupedgemm_ext/CMakeFiles/sample_hipblaslt_groupedgemm_ext.dir/sample_hipblaslt_groupedgemm_ext.cpp.o 0.6 [213/424] Building CXX object clients/samples/25_hipblaslt_gemm_swizzle_b/CMakeFiles/sample_hipblaslt_gemm_swizzle_b.dir/sample_hipblaslt_gemm_swizzle_b.cpp.o 0.6 [214/424] Building CXX object clients/samples/12_hipblaslt_gemm_dgelu_bgrad/CMakeFiles/sample_hipblaslt_gemm_dgelu_bgrad.dir/sample_hipblaslt_gemm_dgelu_bgrad.cpp.o 0.6 [215/424] Building CXX object clients/samples/25_hipblaslt_weight_swizzle_padding/CMakeFiles/sample_hipblaslt_weight_swizzle_padding.dir/sample_hipblaslt_weight_swizzle_padding.cpp.o 0.6 [216/424] Building CXX object clients/samples/25_hipblaslt_gemm_swizzle_a/CMakeFiles/sample_hipblaslt_gemm_swizzle_a.dir/sample_hipblaslt_gemm_swizzle_a.cpp.o 0.6 [217/424] Building CXX object clients/samples/12_hipblaslt_gemm_drelu_bgrad/CMakeFiles/sample_hipblaslt_gemm_drelu_bgrad.dir/sample_hipblaslt_gemm_drelu_bgrad.cpp.o 0.6 [218/424] Building CXX object clients/samples/02_hipblaslt_gemm_batched_ext/CMakeFiles/sample_hipblaslt_gemm_batched_ext.dir/sample_hipblaslt_gemm_batched_ext.cpp.o 0.6 [219/424] Building CXX object clients/samples/27_hipblaslt_gemm_clamp_bias/CMakeFiles/sample_hipblaslt_gemm_clamp_bias.dir/sample_hipblaslt_gemm_clamp_bias.cpp.o 0.6 [220/424] 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 0.6 [221/424] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/hipblaslt_arguments.cpp.o 0.6 [222/424] 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 0.6 [223/424] 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 0.6 [224/424] Generating ISA definitions, IR classes, and pattern matchers with tablegen... 0.6 Generating Rocisa mappings for Gfx1250 in "/__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/stinkytofu/ir/rocisa/RocisaGfx1250Mappings.inc" 0.6 Generating Logical IR -> ASM mappings in "/__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/stinkytofu/ir/LogicalToAsmMappings_generated.inc" 0.6 Parsing patterns from: /__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/tools/tablegen/../../hardware/../src/transforms/asm/PeepholePatterns.pattern 0.6 Found 12 pattern(s) 0.6 Generated 12 pattern matchers: /__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/PeepholePatterns.inc 0.6 Parsing patterns from: /__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/tools/tablegen/../../hardware/../src/transforms/logical/LogicalIRPatterns.pattern 0.6 Found 12 pattern(s) 0.6 Generated 12 pattern matchers: /__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build/tensilelite/rocisa/stinkytofu/LogicalIRPatterns.inc 0.6 0.6 === Generating High-Level IR === 0.6 Generated 274 opcode enum values -> LogicalOpcodes_generated.inc 0.6 Generated opcode mapping functions -> LogicalOpcode.cpp 0.6 Generated 274 LogicalInstruction factory functions + 5 special instruction factories (MFMA/MXMFMA/SMFMA/Label/IntrinsicCall) -> LogicalInstructions_generated.hpp 0.6 Generated Python bindings for 274 IR instructions -> PythonBindings_generated.inc 0.6 === High-Level IR generation completed successfully === 0.6 0.6 [225/424] 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 0.6 [226/424] Building CXX object clients/samples/11_hipblaslt_gemm_bgradb/CMakeFiles/sample_hipblaslt_gemm_bgradb.dir/sample_hipblaslt_gemm_bgradb.cpp.o 0.6 [227/424] Building CXX object clients/samples/11_hipblaslt_gemm_ext_bgradb/CMakeFiles/sample_hipblaslt_gemm_ext_bgradb.dir/sample_hipblaslt_gemm_ext_bgradb.cpp.o 0.6 [228/424] 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 0.6 [229/424] 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 0.6 [230/424] Building CXX object clients/samples/22_hipblaslt_ext_op_layernorm/CMakeFiles/sample_hipblaslt_ext_op_layernorm.dir/sample_hipblaslt_ext_op_layernorm.cpp.o 0.6 [231/424] 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 0.6 [232/424] Building CXX object clients/samples/23_hipblaslt_ext_op_amax/CMakeFiles/sample_hipblaslt_ext_op_amax.dir/sample_hipblaslt_ext_op_amax.cpp.o 0.6 [233/424] Building CXX object clients/samples/19_hipblaslt_gemm_mix_precision/CMakeFiles/sample_hipblaslt_gemm_mix_precision.dir/sample_hipblaslt_gemm_mix_precision.cpp.o 0.6 [234/424] Building CXX object clients/samples/02_hipblaslt_gemm_batched/CMakeFiles/sample_hipblaslt_gemm_batched.dir/sample_hipblaslt_gemm_batched.cpp.o 0.6 [235/424] 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 0.6 [236/424] Building CXX object clients/samples/04_hipblaslt_gemm_bias_ext/CMakeFiles/sample_hipblaslt_gemm_bias_ext.dir/sample_hipblaslt_gemm_bias_ext.cpp.o 0.6 [237/424] 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 0.6 [238/424] 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 0.6 [239/424] 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 0.6 [240/424] 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 0.6 [241/424] Building CXX object clients/CMakeFiles/hipblaslt-bench-extop-matrixtransform.dir/bench/src/client_extop_matrixtransform.cpp.o 0.6 [242/424] Building CXX object clients/samples/04_hipblaslt_gemm_bias/CMakeFiles/sample_hipblaslt_gemm_bias.dir/sample_hipblaslt_gemm_bias.cpp.o 0.6 [243/424] Building CXX object clients/CMakeFiles/hipblaslt-bench-groupedgemm-fixed-mk.dir/bench/src/client_groupedgemm_fixed_mk.cpp.o 0.6 [244/424] 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 0.6 [245/424] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/hipblaslt_random.cpp.o 0.6 [246/424] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/hipblaslt_parse_data.cpp.o 0.6 [247/424] Building CXX object clients/samples/26_hipblaslt_gemm_swish_bias/CMakeFiles/sample_hipblaslt_gemm_swish_bias.dir/sample_hipblaslt_gemm_swish_bias.cpp.o 0.6 [248/424] Building CXX object clients/CMakeFiles/hipblaslt-clients-common.dir/common/src/hipblaslt_init_device.cpp.o 0.6 [249/424] Building CXX object clients/samples/25_hipblaslt_gemm_bias_swizzle_a_ext/CMakeFiles/sample_hipblaslt_gemm_bias_swizzle_a_ext.dir/sample_hipblaslt_gemm_bias_swizzle_a_ext.cpp.o 0.6 [250/424] 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 0.6 [251/424] Building CXX object clients/CMakeFiles/hipblaslt-bench.dir/bench/src/client.cpp.o 0.6 [252/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/stinkytofu/ir/logical/LogicalOpcode.cpp.o 0.6 [253/424] Building CXX object clients/CMakeFiles/hipblaslt-bench-extop-amax.dir/bench/src/client_extop_amax.cpp.o 0.6 [254/424] Building CXX object clients/samples/24_hipblaslt_gemm_with_TF32/CMakeFiles/sample_hipblaslt_gemm_with_TF32.dir/sample_hipblaslt_gemm_with_TF32.cpp.o 0.7 [255/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/AnalysisManager.cpp.o 0.7 [256/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/BasicBlock.cpp.o 0.7 [257/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/DAGScheduleJsonWriter.cpp.o 0.7 [258/424] Linking CXX shared library library/libhipblaslt.so.1.3 0.7 [259/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/asm/StinkyAsmIR.cpp.o 0.7 [260/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/PassManager.cpp.o 0.7 [261/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/DebugPrintInstrumentation.cpp.o 0.7 [262/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/PhiPlacement.cpp.o 0.7 [263/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/LegalizationUtils.cpp.o 0.7 [264/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/ScheduleLastLRsPass.cpp.o 0.7 [265/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/IRLexer.cpp.o 0.7 [266/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/IntrinsicLibrary.cpp.o 0.7 [267/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/CompositeInstructionLoweringPass.cpp.o 0.7 [268/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/ModifierSerializer.cpp.o 0.7 [269/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/pipeline/backend/Gfx1250Backend.cpp.o 0.7 [270/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/InsertDelayAluPass.cpp.o 0.7 [271/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/main.cpp.o 0.7 [272/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/DumpStinkyFunctionPass.cpp.o 0.7 [273/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/IntrinsicRegistry.cpp.o 0.7 [274/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/IntrinsicExpansionPass.cpp.o 0.7 [275/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/IRParser.cpp.o 0.7 [276/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/enum.cpp.o 0.7 [277/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/count.cpp.o 0.7 [278/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/code.cpp.o 0.7 [279/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/ScheduleFirstLRsPass.cpp.o 0.7 [280/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/StinkyAsmPrinter.cpp.o 0.7 [281/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/PeepholeOptimizationPass.cpp.o 0.7 [282/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/IntrinsicPatternConverter.cpp.o 0.7 [283/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/LogicalOpcode.cpp.o 0.7 [284/424] Creating library symlink library/libhipblaslt.so.1 library/libhipblaslt.so 0.7 [285/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/RedundantMovEliminationPass.cpp.o 0.7 [286/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/ToStinkyAsmPass.cpp.o 0.7 [287/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/IRConverter.cpp.o 0.7 [288/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/macro.cpp.o 0.7 [289/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/logical/IRSerializer.cpp.o 0.7 [290/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/InsertVgprMsbPass.cpp.o 0.7 [291/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/RawAsmParser.cpp.o 0.7 [292/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/CFGBuilderPass.cpp.o 0.7 [293/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/PatternParser.cpp.o 0.7 [294/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/pipeline/backend/BackendRegistry.cpp.o 0.7 [295/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/hardware/ArchHelper.cpp.o 0.7 [296/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/container.cpp.o 0.7 [297/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/serialization/asm/StinkyAsmEmitter.cpp.o 0.7 [298/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyBuildImplicitDependencyPass.cpp.o 0.7 [299/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/instruction.cpp.o 0.7 [300/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/analysis/asm/AsmVerifierPass.cpp.o 0.7 [301/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/logical/LogicalToFunctionConverter.cpp.o 0.8 [302/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/bindings/python/LogicalModule.cpp.o 0.8 [303/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/bindings/python/Module.cpp.o 0.8 [304/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/logical/LogicalPeepholePass.cpp.o 0.8 [305/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/PassOrderSnapshotJson.cpp.o 0.8 [306/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/analysis/logical/IRVerifierPass.cpp.o 0.8 [307/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/RemoveDelayAluPass.cpp.o 0.8 [308/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyWaitCntInsertionPass.cpp.o 0.8 [309/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyConfigurableWaitCntPass.cpp.o 0.8 [310/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/ir/asm/StinkySignature.cpp.o 0.8 [311/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/DeadCodeEliminationPass.cpp.o 0.8 [312/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/analysis/controlflow/Dominance.cpp.o 0.8 [313/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/common.cpp.o 0.8 [314/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/Function.cpp.o 0.8 [315/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/label.cpp.o 0.8 [316/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/core/IRBase.cpp.o 0.8 [317/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyRemoveWaitCntPass.cpp.o 0.8 [318/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/StinkyDAGSchedulerPass.cpp.o 0.8 [319/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/base.cpp.o 0.8 [320/424] Linking CXX executable clients/samples/01_hipblaslt_gemm_ext/sample_hipblaslt_gemm_ext 0.8 [321/424] Linking CXX executable clients/samples/05_hipblaslt_gemm_get_all_algos/sample_hipblaslt_gemm_get_all_algos 0.8 [322/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/branch.cpp.o 0.8 [323/424] Linking CXX executable clients/samples/01_hipblaslt_gemm/sample_hipblaslt_gemm 0.8 [324/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/cvt.cpp.o 0.8 [325/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/pass.cpp.o 0.8 [326/424] Linking CXX executable clients/samples/03_hipblaslt_gemm_tuning_splitk_ext/sample_hipblaslt_gemm_tuning_splitk_ext 0.8 [327/424] Linking CXX executable clients/samples/04_hipblaslt_gemm_bias/sample_hipblaslt_gemm_bias 0.8 [328/424] Linking CXX executable clients/samples/06_hipblaslt_gemm_get_algo_by_index_ext/sample_hipblaslt_gemm_get_algo_by_index_ext 0.8 [329/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/transforms/asm/BuildDefUseChain.cpp.o 0.8 [330/424] Linking CXX executable clients/samples/02_hipblaslt_gemm_batched/sample_hipblaslt_gemm_batched 0.8 [331/424] Linking CXX executable clients/samples/02_hipblaslt_gemm_batched_ext/sample_hipblaslt_gemm_batched_ext 0.8 [332/424] Linking CXX executable clients/samples/04_hipblaslt_gemm_bias_ext/sample_hipblaslt_gemm_bias_ext 0.8 [333/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/graph.cpp.o 0.8 [334/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/insert_delay_alu.cpp.o 0.8 [335/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/helper.cpp.o 0.8 [336/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/remove.cpp.o 0.8 [337/424] Linking CXX executable clients/samples/07_hipblaslt_gemm_alphavec_ext/sample_hipblaslt_gemm_alphavec_ext 0.8 [338/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/register.cpp.o 0.8 [339/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/argument.cpp.o 0.8 [340/424] Linking CXX executable clients/samples/08_hipblaslt_gemm_gelu_aux_bias/sample_hipblaslt_gemm_gelu_aux_bias 0.8 [341/424] Linking CXX executable clients/samples/10_hipblaslt_gemm_amax_with_scale/sample_hipblaslt_gemm_amax_with_scale 0.8 [342/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/mem.cpp.o 0.8 [343/424] Linking CXX executable clients/samples/05_hipblaslt_gemm_get_all_algos_ext/sample_hipblaslt_gemm_get_all_algos_ext 0.8 [344/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/composite.cpp.o 0.8 [345/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/src/conversion/rocisa/AllHwMappings.cpp.o 0.8 [346/424] Linking CXX executable clients/samples/08_hipblaslt_gemm_gelu_aux_bias_ext/sample_hipblaslt_gemm_gelu_aux_bias_ext 0.8 [347/424] Linking CXX executable clients/samples/10_hipblaslt_gemm_amax_with_scale_ext/sample_hipblaslt_gemm_amax_with_scale_ext 0.8 [348/424] Linking CXX static library clients/libhipblaslt-clients-common.a 0.8 [349/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/cmp.cpp.o 0.8 [350/424] Linking CXX executable clients/samples/09_hipblaslt_gemm_amax_ext/sample_hipblaslt_gemm_amax_ext 0.8 [351/424] Linking CXX executable clients/samples/12_hipblaslt_gemm_dgelu_bgrad_ext/sample_hipblaslt_gemm_dgelu_bgrad_ext 0.8 [352/424] Linking CXX executable clients/samples/11_hipblaslt_gemm_ext_bgradb/sample_hipblaslt_gemm_ext_bgradb 0.8 [353/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/f_cast.cpp.o 0.8 [354/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/functions.cpp.o 0.8 [355/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/__w/rockrel/rockrel/rocm-libraries/shared/stinkytofu/src/conversion/rocisa/ToStinkyTofuUtils.cpp.o 0.8 [356/424] Linking CXX executable clients/samples/09_hipblaslt_gemm_amax/sample_hipblaslt_gemm_amax 0.8 [357/424] Linking CXX executable clients/samples/11_hipblaslt_gemm_bgradb/sample_hipblaslt_gemm_bgradb 0.8 [358/424] Linking CXX executable clients/samples/12_hipblaslt_gemm_dgelu_bgrad/sample_hipblaslt_gemm_dgelu_bgrad 0.8 [359/424] Linking CXX executable clients/samples/12_hipblaslt_gemm_drelu_bgrad/sample_hipblaslt_gemm_drelu_bgrad 0.8 [360/424] Building CXX object tensilelite/rocisa/stinkytofu/CMakeFiles/stinkytofu.dir/src/pipeline/backend/Backend.cpp.o 0.8 [361/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/f_branch.cpp.o 0.8 [362/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/pass/cycle.cpp.o 0.8 [363/424] Linking CXX executable clients/samples/12_hipblaslt_gemm_drelu_bgrad_ext/sample_hipblaslt_gemm_drelu_bgrad_ext 0.8 [364/424] Linking CXX executable clients/samples/13_hipblaslt_gemm_is_tuned_ext/sample_hipblaslt_gemm_is_tuned_ext 0.8 [365/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/functions/f_math.cpp.o 0.8 [366/424] Linking CXX executable clients/samples/15_hipblaslt_gemm_with_scale_a_b/sample_hipblaslt_gemm_with_scale_a_b 0.8 [367/424] Linking CXX executable clients/samples/15_hipblaslt_gemm_with_scale_a_b_vector/sample_hipblaslt_gemm_with_scale_a_b_vector 0.8 [368/424] Linking CXX executable clients/samples/15_hipblaslt_gemm_with_scale_a_b_ext/sample_hipblaslt_gemm_with_scale_a_b_ext 0.8 [369/424] Linking CXX executable clients/samples/15_hipblaslt_gemm_with_scale_a_b_vector/sample_hipblaslt_gemm_swizzleA_with_scale_a_b_vector 0.8 [370/424] Linking CXX executable clients/samples/18_hipblaslt_groupedgemm_get_all_algos_ext/sample_hipblaslt_groupedgemm_get_all_algos_ext 0.8 [371/424] Linking CXX executable clients/samples/16_hipblaslt_groupedgemm_ext/sample_hipblaslt_groupedgemm_ext 0.8 [372/424] Linking CXX executable clients/samples/17_hipblaslt_groupedgemm_fixed_mk_ext/sample_hipblaslt_groupedgemm_fixed_mk_ext 0.8 [373/424] Linking CXX executable clients/samples/14_hipblaslt_gemm_tuning_wgm_ext/sample_hipblaslt_gemm_tuning_wgm_ext 0.8 [374/424] Linking CXX executable clients/samples/19_hipblaslt_gemm_mix_precision_ext/sample_hipblaslt_gemm_mix_precision_ext 0.8 [375/424] Linking CXX executable clients/samples/19_hipblaslt_gemm_mix_precision/sample_hipblaslt_gemm_mix_precision 0.8 [376/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/mfma.cpp.o 0.8 [377/424] Linking CXX executable clients/samples/22_hipblaslt_ext_op_layernorm/sample_hipblaslt_ext_op_layernorm 0.8 [378/424] Linking CXX executable clients/samples/20_hipblaslt_gemm_mix_precision_with_amax_ext/sample_hipblaslt_gemm_mix_precision_with_amax_ext 0.8 [379/424] Linking CXX executable clients/samples/23_hipblaslt_ext_op_amax/sample_hipblaslt_ext_op_amax 0.8 [380/424] Linking CXX executable clients/samples/21_hipblaslt_gemm_attr_tciA_tciB/sample_hipblaslt_gemm_attr_tciA_tciB 0.8 [381/424] Linking CXX executable clients/samples/25_hipblaslt_gemm_swizzle_b/sample_hipblaslt_gemm_swizzle_b 0.8 [382/424] Linking CXX executable clients/samples/25_hipblaslt_weight_swizzle_padding/sample_hipblaslt_weight_swizzle_padding 0.8 [383/424] Linking CXX executable clients/samples/24_hipblaslt_gemm_with_TF32/sample_hipblaslt_gemm_with_TF32 0.8 [384/424] Linking CXX executable clients/samples/25_hipblaslt_gemm_swizzle_a/sample_hipblaslt_gemm_swizzle_a 0.8 [385/424] Linking CXX executable clients/samples/25_hipblaslt_gemm_bias_swizzle_a_ext/sample_hipblaslt_gemm_bias_swizzle_a_ext 0.8 [386/424] Linking CXX executable clients/samples/27_hipblaslt_gemm_clamp_bias/sample_hipblaslt_gemm_clamp_bias 0.8 [387/424] Linking CXX executable clients/samples/26_hipblaslt_gemm_swish_bias/sample_hipblaslt_gemm_swish_bias 0.8 [388/424] Building CXX object tensilelite/rocisa/CMakeFiles/_rocisa.dir/rocisa/src/instruction/extension.cpp.o 0.9 [389/424] Linking CXX executable clients/hipblaslt-bench-extop-layernorm 0.9 [390/424] Linking CXX executable clients/hipblaslt-bench-extop-softmax 0.9 [391/424] Linking CXX executable clients/hipblaslt-api-overhead 0.9 [392/424] Linking CXX executable clients/hipblaslt-bench-groupedgemm-fixed-mk 0.9 [393/424] Linking CXX executable clients/hipblaslt-bench-extop-matrixtransform 0.9 [394/424] Linking CXX executable clients/hipblaslt-bench-extop-amax 0.9 [395/424] Linking CXX shared library tensilelite/rocisa/stinkytofu/libstinkytofu.so.0.1.0 0.9 [396/424] Creating library symlink tensilelite/rocisa/stinkytofu/libstinkytofu.so.0 tensilelite/rocisa/stinkytofu/libstinkytofu.so 0.9 [397/424] Linking CXX executable clients/hipblaslt-bench 0.9 [398/424] Linking CXX shared module tensilelite/rocisa/rocisa/_rocisa.cpython-312-x86_64-linux-gnu.so 0.9 [398/424] Validating library logic (TensileLogic --check-all) ... 72.4 Launching 64 threads for 411 tasks... 277.3 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 Done. (204.9 secs elapsed) 277.3 Total 563866 solutions 277.3 Keep 563866 solutions 277.3 Reject 0 solutions 277.3 Known-bugs skip 14 solutions (see --known-bugs YAML) 278.9 [422/424] Creating hipblasltExtOpLibrary_gfx1152.dat 278.9 [423/424] Building device libraries to /__w/rockrel/rockrel/build/math-libs/BLAS/hipBLASLt/build/Tensile ... 279.7 279.7 ################################################################################ 279.7 # Tensile Create Library 282.5 Capability gfx1152 282.5 HasMFMA_bf16_1k - 282.5 HasAddLshl 1 282.5 HasAtomicAdd 1 282.5 HasBF16CVT - 282.5 HasCvtFP8toF16 - 282.5 HasDLCModifier 1 282.5 HasDirectToLds - 282.5 HasDirectToLdsx4 - 282.5 HasExplicitCO 1 282.5 HasExplicitNC 1 282.5 HasGLCModifier 1 282.5 HasGLTr16B128 - 282.5 HasGLTr8B64 - 282.5 HasLDSTr - 282.5 HasLDSTrB128B16 - 282.5 HasLDSTrB64B16 - 282.5 HasLDSTrB64B4 - 282.5 HasLDSTrB64B8 - 282.5 HasLDSTrB96B6 - 282.5 HasLshlOr 1 282.5 HasMFMA - 282.5 HasMUBUFConst 1 282.5 HasNTModifier - 282.5 HasNewBarrier - 282.5 HasPartialOOB 1 282.5 HasPkF16CVT - 282.5 HasSC0Modifier - 282.5 HasSCMPK 1 282.5 HasSCOPEModifier - 282.5 HasSMFMA - 282.5 HasSMulHi 1 282.5 HasSWMMAC - 282.5 HasScalarStore - 282.5 HasTDM - 282.5 HasVgprMSB - 282.5 HasVgprMSB16 - 282.5 HasWMMA 1 282.5 MaxLgkmcnt 1 282.5 MaxVmcnt 1 282.5 MaxVscnt 1 282.5 SeparateLGKMcnt - 282.5 SeparateVMcnt - 282.5 SeparateVscnt 1 282.5 ShortBranchMaxLength 1 282.5 SupportedISA 1 282.5 SupportedSource 1 282.5 HasWMMA_V1 1 282.5 HasWMMA_V2 - 282.5 HasWMMA_V3 - 282.5 s_delay_alu 1 282.5 v_prng_b32 - 282.5 v_mov_b64 - 282.5 HasMFMA_b8 - 282.5 v_dot2_f32_bf16 1 282.5 v_dot2c_f32_bf16 - 282.5 HasMFMA_explictB - 282.5 Hascvtfp8_f16 - 282.5 v_dot2_f32_f16 1 282.5 v_dot2c_f32_f16 1 282.5 v_fma_f16 1 282.5 v_fmac_f16 - 282.5 v_mac_f16 - 282.5 v_pk_fma_f16 1 282.5 v_pk_fmac_f16 - 282.5 v_fma_f32 1 282.5 v_fma_mix_f32 1 282.5 v_fmac_f32 1 282.5 v_mac_f32 - 282.5 v_mad_mix_f32 - 282.5 v_pk_add_f32 - 282.5 v_pk_mul_f32 - 282.5 HasMFMA_f64 - 282.5 HasWMMA_V3_f64 - 282.5 v_fma_f64 1 282.5 HasMFMA_f8 - 282.5 HasMFMA_f8f6f4 - 282.5 HasWMMA_f8f6f4 - 282.5 HasSWMMAC_gfx1250 - 282.5 HasAdd_PC_i64 - 282.5 VOP3v_dot4_i32_i8 1 282.5 v_dot4_i32_i8 - 282.5 v_dot4c_i32_i8 - 282.5 Hascvtf16_fp8_sf32 - 282.5 s_sub_u64 - 282.5 HasMFMA_xf32 - 282.5 ArchAccUnifiedRegs - 282.5 CMPXWritesSGPR - 282.5 CrosslaneWait - 282.5 DSLow16NotPreserve - 282.5 DeviceLDS 1 282.5 HasAccCD - 282.5 HasEccHalf - 282.5 HasF32XEmulation - 282.5 HasFP8_OCP - 282.5 HasInvWbDevFences - 282.5 HasSchedMode - 282.5 HasWave32 1 282.5 HasWmmaArbStallBit - 282.5 LDSBankCount 1 282.5 LDSBankWidth 1 282.5 NoSDWA 1 282.5 RequiresXCntForVolatileVMEM - 282.5 SDWAWait - 282.5 TransOpWait - 282.5 VOP3ByteSel - 282.5 VgprBank 1 282.5 Waitcnt0Disabled - 282.5 WorkGroupIdFromTTM - 282.5 vL1DCacheLineBytes 1 282.5 # Found hipcc version 7.13.26176-79e85e14 282.6 ROCm 7.13.26176 Component path: /__w/rockrel/rockrel/build/core/clr/dist/lib/llvm/bin/clang++ version: 23.0.0 282.6 ROCm 7.13.26176 Component path: /__w/rockrel/rockrel/build/compiler/amd-llvm/dist/lib/llvm/bin/clang-offload-bundler version: 23.0.0 282.6 # LogicFilter: /__w/rockrel/rockrel/rocm-libraries/projects/hipblaslt/library/**/*.yaml 282.9 # Experimental: False 282.9 # Archs: gfx1152 282.9 # LibraryLogicFiles: 46 282.9 Loading Logics...: Launching 64 threads... 283.0 Loading Logics...: Done. (0.2 secs elapsed) 284.2 Checked 46 YAML logic files - no type mismatches found. 284.4 Number of solutions parsed: 1223 284.4 Number of unique solutions: 1223 284.7 Time to load yaml files (s): 1.49 284.7 Number of duplicate kernels: 0 284.7 Generating assembly kernels: Launching 64 threads for 1019 tasks... 290.3 Generating assembly kernels: Done. (5.6 secs elapsed) 292.6 # Helper kernel cache MISS (d8bb6b881e94...) 338.2 buildSourceCodeObjectFile time (s): 45.69 338.6 Time to generate kernels (s): 53.62 338.6 Time to pass kernel info to library (s): 0.26 338.6 Writing master solution libraries: Launching 64 threads for 46 tasks... 339.0 Writing master solution libraries: Done. (0.3 secs elapsed) 339.3 Time to write master solution libraries (s): 0.31 339.3 # Tensile Library Writer DONE 339.3 ################################################################################ 339.3 339.3 Total time (s): 59.29 339.3 Total kernels processed: 1019 339.3 Kernels processed per second: 17.19 339.3 KernelHelperObjs: 56 END 1778472493.156532 339.3873188495636 0