find_package(OpenCL REQUIRED)
find_package(Python3 REQUIRED)

set(TARGET_NAME ggml-opencl)

ggml_add_backend_library(${TARGET_NAME}
                         ggml-opencl.cpp
                         ../../include/ggml-opencl.h)
target_link_libraries(${TARGET_NAME} PRIVATE ${OpenCL_LIBRARIES})
target_include_directories(${TARGET_NAME} PRIVATE ${OpenCL_INCLUDE_DIRS})

if (GGML_OPENCL_PROFILING)
    message(STATUS "OpenCL profiling enabled (increases CPU overhead)")
    add_compile_definitions(GGML_OPENCL_PROFILING)
endif ()

add_compile_definitions(GGML_OPENCL_SOA_Q)

if (GGML_OPENCL_USE_ADRENO_KERNELS)
    message(STATUS "OpenCL will use matmul kernels optimized for Adreno")
    add_compile_definitions(GGML_OPENCL_USE_ADRENO_KERNELS)
endif ()

if (GGML_OPENCL_EMBED_KERNELS)
    add_compile_definitions(GGML_OPENCL_EMBED_KERNELS)

    set(OPENCL_CL_SOURCE_EMBED         "${CMAKE_BINARY_DIR}/autogenerated/ggml-opencl.cl.h")
    set(OPENCL_MM_CL_SOURCE_EMBED      "${CMAKE_BINARY_DIR}/autogenerated/ggml-opencl_mm.cl.h")
    set(OPENCL_CVT_CL_SOURCE_EMBED     "${CMAKE_BINARY_DIR}/autogenerated/ggml-opencl_cvt.cl.h")

    set(OPENCL_GEMV_NOSHUFFLE_SOURCE_EMBED             "${CMAKE_BINARY_DIR}/autogenerated/ggml-opencl_gemv_noshuffle.cl.h")
    set(OPENCL_GEMV_NOSHUFFLE_GENERAL_SOURCE_EMBED     "${CMAKE_BINARY_DIR}/autogenerated/ggml-opencl_gemv_noshuffle_general.cl.h")
    set(OPENCL_MUL_MAT_Ab_Bi_8x4_SOURCE_EMBED          "${CMAKE_BINARY_DIR}/autogenerated/ggml-opencl_mul_mat_Ab_Bi_8x4.cl.h")
    set(OPENCL_TRANSPOSE_16_SOURCE_EMBED               "${CMAKE_BINARY_DIR}/autogenerated/ggml-opencl_transpose_16.cl.h")
    set(OPENCL_TRANSPOSE_32_SOURCE_EMBED               "${CMAKE_BINARY_DIR}/autogenerated/ggml-opencl_transpose_32.cl.h")
    set(OPENCL_TRANSPOSE_32_16_SOURCE_EMBED            "${CMAKE_BINARY_DIR}/autogenerated/ggml-opencl_transpose_32_16.cl.h")

    set(EMBED_KERNEL_SCRIPT             "${CMAKE_CURRENT_SOURCE_DIR}/kernels/embed_kernel.py")
    file(MAKE_DIRECTORY                 "${CMAKE_BINARY_DIR}/autogenerated")

    include_directories("${CMAKE_BINARY_DIR}/autogenerated")

    # Python must be accessible from command line
    add_custom_command(
        OUTPUT ${OPENCL_CL_SOURCE_EMBED}
        COMMAND ${Python3_EXECUTABLE} ${EMBED_KERNEL_SCRIPT}
            ${CMAKE_CURRENT_SOURCE_DIR}/kernels/ggml-opencl.cl
            ${OPENCL_CL_SOURCE_EMBED}
        DEPENDS kernels/ggml-opencl.cl ${EMBED_KERNEL_SCRIPT}
        COMMENT "Generate ggml-opencl.cl.h"
    )

    add_custom_command(
        OUTPUT ${OPENCL_MM_CL_SOURCE_EMBED}
        COMMAND ${Python3_EXECUTABLE} ${EMBED_KERNEL_SCRIPT}
            ${CMAKE_CURRENT_SOURCE_DIR}/kernels/ggml-opencl_mm.cl
            ${OPENCL_MM_CL_SOURCE_EMBED}
        DEPENDS kernels/ggml-opencl_mm.cl ${EMBED_KERNEL_SCRIPT}
        COMMENT "Generate ggml-opencl_mm.cl.h"
    )

    add_custom_command(
        OUTPUT ${OPENCL_CVT_CL_SOURCE_EMBED}
        COMMAND ${Python3_EXECUTABLE} ${EMBED_KERNEL_SCRIPT}
            ${CMAKE_CURRENT_SOURCE_DIR}/kernels/ggml-opencl_cvt.cl
            ${OPENCL_CVT_CL_SOURCE_EMBED}
        DEPENDS kernels/ggml-opencl_cvt.cl ${EMBED_KERNEL_SCRIPT}
        COMMENT "Generate ggml-opencl_cvt.cl.h"
    )

    add_custom_command(
        OUTPUT ${OPENCL_GEMV_NOSHUFFLE_SOURCE_EMBED}
        COMMAND ${Python3_EXECUTABLE} ${EMBED_KERNEL_SCRIPT}
            ${CMAKE_CURRENT_SOURCE_DIR}/kernels/ggml-opencl_gemv_noshuffle.cl
            ${OPENCL_GEMV_NOSHUFFLE_SOURCE_EMBED}
        DEPENDS kernels/ggml-opencl_gemv_noshuffle.cl ${EMBED_KERNEL_SCRIPT}
        COMMENT "Generate ggml-opencl_gemv_noshuffle.cl.h"
    )

    add_custom_command(
        OUTPUT ${OPENCL_GEMV_NOSHUFFLE_GENERAL_SOURCE_EMBED}
        COMMAND ${Python3_EXECUTABLE} ${EMBED_KERNEL_SCRIPT}
            ${CMAKE_CURRENT_SOURCE_DIR}/kernels/ggml-opencl_gemv_noshuffle_general.cl
            ${OPENCL_GEMV_NOSHUFFLE_GENERAL_SOURCE_EMBED}
        DEPENDS kernels/ggml-opencl_gemv_noshuffle_general.cl ${EMBED_KERNEL_SCRIPT}
        COMMENT "Generate ggml-opencl_gemv_noshuffle_general.cl.h"
    )

    add_custom_command(
        OUTPUT ${OPENCL_MUL_MAT_Ab_Bi_8x4_SOURCE_EMBED}
        COMMAND ${Python3_EXECUTABLE} ${EMBED_KERNEL_SCRIPT}
            ${CMAKE_CURRENT_SOURCE_DIR}/kernels/ggml-opencl_mul_mat_Ab_Bi_8x4.cl
            ${OPENCL_MUL_MAT_Ab_Bi_8x4_SOURCE_EMBED}
        DEPENDS kernels/ggml-opencl_mul_mat_Ab_Bi_8x4.cl ${EMBED_KERNEL_SCRIPT}
        COMMENT "Generate ggml-opencl_mul_mat_Ab_Bi_8x4.cl.cl.h"
    )

    add_custom_command(
        OUTPUT ${OPENCL_TRANSPOSE_16_SOURCE_EMBED}
        COMMAND ${Python3_EXECUTABLE} ${EMBED_KERNEL_SCRIPT}
            ${CMAKE_CURRENT_SOURCE_DIR}/kernels/ggml-opencl_transpose_16.cl
            ${OPENCL_TRANSPOSE_16_SOURCE_EMBED}
        DEPENDS kernels/ggml-opencl_transpose_16.cl ${EMBED_KERNEL_SCRIPT}
        COMMENT "Generate ggml-opencl_transpose_16.cl.h"
    )

    add_custom_command(
        OUTPUT ${OPENCL_TRANSPOSE_32_SOURCE_EMBED}
        COMMAND ${Python3_EXECUTABLE} ${EMBED_KERNEL_SCRIPT}
            ${CMAKE_CURRENT_SOURCE_DIR}/kernels/ggml-opencl_transpose_32.cl
            ${OPENCL_TRANSPOSE_32_SOURCE_EMBED}
        DEPENDS kernels/ggml-opencl_transpose_32.cl ${EMBED_KERNEL_SCRIPT}
        COMMENT "Generate ggml-opencl_transpose_32.cl.h"
    )

    add_custom_command(
        OUTPUT ${OPENCL_TRANSPOSE_32_16_SOURCE_EMBED}
        COMMAND ${Python3_EXECUTABLE} ${EMBED_KERNEL_SCRIPT}
            ${CMAKE_CURRENT_SOURCE_DIR}/kernels/ggml-opencl_transpose_32_16.cl
            ${OPENCL_TRANSPOSE_32_16_SOURCE_EMBED}
        DEPENDS kernels/ggml-opencl_transpose_32_16.cl ${EMBED_KERNEL_SCRIPT}
        COMMENT "Generate ggml-opencl_transpose_32_16.cl.h"
    )

    target_sources(${TARGET_NAME} PRIVATE
                   ${OPENCL_CL_SOURCE_EMBED}
                   ${OPENCL_MM_CL_SOURCE_EMBED}
                   ${OPENCL_CVT_CL_SOURCE_EMBED}
                   ${OPENCL_GEMV_NOSHUFFLE_SOURCE_EMBED}
                   ${OPENCL_GEMV_NOSHUFFLE_GENERAL_SOURCE_EMBED}
                   ${OPENCL_MUL_MAT_Ab_Bi_8x4_SOURCE_EMBED}
                   ${OPENCL_TRANSPOSE_16_SOURCE_EMBED}
                   ${OPENCL_TRANSPOSE_32_SOURCE_EMBED}
                   ${OPENCL_TRANSPOSE_32_16_SOURCE_EMBED})
else ()
    # copy ggml-opencl.cl to bin directory
    configure_file(kernels/ggml-opencl.cl ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-opencl.cl COPYONLY)
    configure_file(kernels/ggml-opencl_mm.cl ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-opencl_mm.cl COPYONLY)
    configure_file(kernels/ggml-opencl_cvt.cl ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-opencl_cvt.cl COPYONLY)

    configure_file(kernels/ggml-opencl_gemv_noshuffle.cl ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-opencl_gemv_noshuffle.cl COPYONLY)
    configure_file(kernels/ggml-opencl_gemv_noshuffle_general.cl ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-opencl_gemv_noshuffle_general.cl COPYONLY)
    configure_file(kernels/ggml-opencl_mul_mat_Ab_Bi_8x4.cl ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-opencl_mul_mat_Ab_Bi_8x4.cl COPYONLY)
    configure_file(kernels/ggml-opencl_transpose_16.cl ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-opencl_transpose_16.cl COPYONLY)
    configure_file(kernels/ggml-opencl_transpose_32.cl ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-opencl_transpose_32.cl COPYONLY)
    configure_file(kernels/ggml-opencl_transpose_32_16.cl ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-opencl_transpose_32_16.cl COPYONLY)
endif ()