Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

addpatch: composable-kernel, ver=6.2.4-1 #464

Open
wants to merge 1 commit into
base: master
Choose a base branch
from

Conversation

wszqkzqk
Copy link
Member

@wszqkzqk wszqkzqk commented Feb 21, 2025

  • Switch to mold to avoid lld's error
    • unknown relocation (102) against symbol

* Switch to mold to avoid lld's errror
  * `unknown relocation (102) against symbol`

Signed-off-by: Zhou Qiankang <wszqkzqk@qq.com>
@wszqkzqk
Copy link
Member Author

[592/783] Building CXX object library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeFiles/device_grouped_gemm_instance.dir/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp.o
FAILED: library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeFiles/device_grouped_gemm_instance.dir/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp.o 
/opt/rocm/bin/hipcc -DCK_ENABLE_BF16 -DCK_ENABLE_BF8 -DCK_ENABLE_FP16 -DCK_ENABLE_FP32 -DCK_ENABLE_FP64 -DCK_ENABLE_FP8 -DCK_ENABLE_INT8 -DCK_USE_WMMA -DCK_USE_XDL -DINSTANCES_ONLY -DUSE_PROF_API=1 -D__HIP_PLATFORM_AMD__=1 -D__HIP_PLATFORM_HCC__=1 -I/build/composable-kernel/src/composable_kernel-rocm-6.2.4/library/include -I/build/composable-kernel/src/composable_kernel-rocm-6.2.4/include -I/build/composable-kernel/src/build/include -O3 -DNDEBUG -std=c++17 -fPIC   -Wall -Wextra -Wcomment -Wendif-labels -Wformat -Winit-self -Wreturn-type -Wsequence-point -Wswitch -Wtrigraphs -Wundef -Wuninitialized -Wunreachable-code -Wunused -Wno-reserved-identifier -Werror -Wno-option-ignored -Wsign-compare -Wno-extra-semi-stmt -Wno-unused-template -Wno-missing-field-initializers -Wno-deprecated-declarations -Wall -Wextra -Wcomment -Wendif-labels -Wformat -Winit-self -Wreturn-type -Wsequence-point -Wswitch -Wtrigraphs -Wundef -Wuninitialized -Wunreachable-code -Wunused -Wno-reserved-identifier -Werror -Wno-option-ignored -Wsign-compare -Wno-extra-semi-stmt -Wno-unused-template -Weverything -Wno-c++98-compat -Wno-c++98-compat-pedantic -Wno-conversion -Wno-double-promotion -Wno-exit-time-destructors -Wno-extra-semi -Wno-float-conversion -Wno-gnu-anonymous-struct -Wno-gnu-zero-variadic-macro-arguments -Wno-missing-prototypes -Wno-nested-anon-types -Wno-padded -Wno-return-std-move-in-c++11 -Wno-shorten-64-to-32 -Wno-sign-conversion -Wno-unknown-warning-option -Wno-unused-command-line-argument -Wno-weak-vtables -Wno-covered-switch-default -Wno-unsafe-buffer-usage -Wno-unused-lambda-capture -Wno-bit-int-extension -Wno-pass-failed -Wno-switch-default -fno-offload-uniform-block -mllvm -enable-post-misched=0 -x hip --offload-arch=gfx908 --offload-arch=gfx90a --offload-arch=gfx940 --offload-arch=gfx941 --offload-arch=gfx942 -MD -MT library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeFiles/device_grouped_gemm_instance.dir/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp.o -MF library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeFiles/device_grouped_gemm_instance.dir/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp.o.d -o library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeFiles/device_grouped_gemm_instance.dir/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp.o -c /build/composable-kernel/src/composable_kernel-rocm-6.2.4/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp
fatal error: error in backend: Cannot select: t11: i64 = addrspacecast[0 -> 4] t10
  t10: i64,ch = load<(dereferenceable load (s64) from %ir.sunkaddr493, !tbaa !50)> t0, t9, undef:i64
    t9: i64 = add nuw t2, Constant:i64<8>
      t2: i64,ch = CopyFromReg t0, Register:i64 %79
        t1: i64 = Register %79
      t8: i64 = Constant<8>
    t6: i64 = undef
In function: _ZN2ck16tensor_operation6device34DeviceGroupedGemmXdlSplitKCShuffleINS_13tensor_layout4gemm8RowMajorES5_NS_5TupleIJEEES5_DF16_DF16_fDF16_S7_DF16_NS0_12element_wise11PassThroughES9_S9_LNS1_18GemmSpecializationE0ELi1ELi256ELi64ELi128ELi32ELi8ELi8ELi32ELi32ELi1ELi2ENS_8SequenceIJLi1ELi4ELi64ELi1EEEENSB_IJLi0ELi2ELi1ELi3EEEESD_Li3ELi8ELi8ELb1ESC_NSB_IJLi0ELi1ELi3ELi2EEEESE_Li2ELi2ELi8ELb1ELi1ELi1ENSB_IJLi1ELi32ELi1ELi8EEEELi8ELNS_15PipelineVersionE0ELNS_13LoopSchedulerE0ELb0EE7Invoker3RunERKNSI_8ArgumentERK12StreamConfig
clang++: error: clang frontend command failed with exit code 70 (use -v to see invocation)
clang version 18.0.0git (/startdir/rocm-llvm 1e2c94795ee0d6ab8e2ff3035965a6b74e11b475)
Target: loongarch64-unknown-linux-gnu
Thread model: posix
InstalledDir: /opt/rocm/lib/llvm/bin
clang++: note: diagnostic msg: Error generating preprocessed source(s).
failed to execute:/opt/rocm/lib/llvm/bin/clang++  -isystem "/opt/rocm/include" --offload-arch=gfx908 --offload-arch=gfx90a --offload-arch=gfx940 --offload-arch=gfx941 --offload-arch=gfx942  -DCK_ENABLE_BF16 -DCK_ENABLE_BF8 -DCK_ENABLE_FP16 -DCK_ENABLE_FP32 -DCK_ENABLE_FP64 -DCK_ENABLE_FP8 -DCK_ENABLE_INT8 -DCK_USE_WMMA -DCK_USE_XDL -DINSTANCES_ONLY -DUSE_PROF_API=1 -D__HIP_PLATFORM_AMD__=1 -D__HIP_PLATFORM_HCC__=1 -I/build/composable-kernel/src/composable_kernel-rocm-6.2.4/library/include -I/build/composable-kernel/src/composable_kernel-rocm-6.2.4/include -I/build/composable-kernel/src/build/include -O3 -DNDEBUG -std=c++17 -fPIC -Wall -Wextra -Wcomment -Wendif-labels -Wformat -Winit-self -Wreturn-type -Wsequence-point -Wswitch -Wtrigraphs -Wundef -Wuninitialized -Wunreachable-code -Wunused -Wno-reserved-identifier -Werror -Wno-option-ignored -Wsign-compare -Wno-extra-semi-stmt -Wno-unused-template -Wno-missing-field-initializers -Wno-deprecated-declarations -Wall -Wextra -Wcomment -Wendif-labels -Wformat -Winit-self -Wreturn-type -Wsequence-point -Wswitch -Wtrigraphs -Wundef -Wuninitialized -Wunreachable-code -Wunused -Wno-reserved-identifier -Werror -Wno-option-ignored -Wsign-compare -Wno-extra-semi-stmt -Wno-unused-template -Weverything -Wno-c++98-compat -Wno-c++98-compat-pedantic -Wno-conversion -Wno-double-promotion -Wno-exit-time-destructors -Wno-extra-semi -Wno-float-conversion -Wno-gnu-anonymous-struct -Wno-gnu-zero-variadic-macro-arguments -Wno-missing-prototypes -Wno-nested-anon-types -Wno-padded -Wno-return-std-move-in-c++11 -Wno-shorten-64-to-32 -Wno-sign-conversion -Wno-unknown-warning-option -Wno-unused-command-line-argument -Wno-weak-vtables -Wno-covered-switch-default -Wno-unsafe-buffer-usage -Wno-unused-lambda-capture -Wno-bit-int-extension -Wno-pass-failed -Wno-switch-default -fno-offload-uniform-block -mllvm -enable-post-misched=0 -x hip -MD -MT library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeFiles/device_grouped_gemm_instance.dir/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp.o -MF library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeFiles/device_grouped_gemm_instance.dir/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp.o.d -o "library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeFiles/device_grouped_gemm_instance.dir/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp.o" -c /build/composable-kernel/src/composable_kernel-rocm-6.2.4/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp

# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant