U 9%e4] @sdZddlZddlZddlZddlZddlmZmZmZm Z m Z m Z m Z ddl Z ddlmZddlmZmZmZddlmZmZmZddlmZmZeeZdZdZd Z d Z!d Z"eZ#eZ$d %Z&e'e&D]\Z(Z)e*ej+ee)e(qd Z,dZ-ddZ.e /Z0Gddde1Z2Gddde1Z3dZ4ddddddddddd Z5ddZ6ddZ7dd Z8d!d"Z9d#Z:Gd$d%d%e1Z;d&Zd)Z?d*Z@d+d,ZAd-d.ZBd/d0ZCd1d2ZDd3d4ZEd5d6ZFd7d8ZGeHd9ZId:d;ZJdd?ZLdS)@z( This is a direct translation of nvvm.h N)c_void_pc_intPOINTERc_char_pc_size_tbyrefc_char)ir) NvvmErrorNvvmSupportError NvvmWarning) get_libdeviceopen_libdevice open_cudalib)cgutilsconfiga NVVM_SUCCESS NVVM_ERROR_OUT_OF_MEMORY NVVM_ERROR_PROGRAM_CREATION_FAILURE NVVM_ERROR_IR_VERSION_MISMATCH NVVM_ERROR_INVALID_INPUT NVVM_ERROR_INVALID_PROGRAM NVVM_ERROR_INVALID_IR NVVM_ERROR_INVALID_OPTION NVVM_ERROR_NO_MODULE_IN_PROGRAM NVVM_ERROR_COMPILATION ze-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64ze-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-i128:128:128-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64cCs*z tWntk r YdSXdSdS)z( Return if libNVVM is available FTN)NVVMr rrV/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/numba/cuda/cudadrv/nvvm.py is_available<s  rc@seZdZdZeeeeefeeefeeefeeee efeeee efeeeeefeeee feeefeeee feeefeeeeeeeeefeeeeefd Z dZ ddZ ddZ edd Zed d Zd d ZddZdddZdS)rzProcess-wide singleton. ) nvvmVersionnvvmCreateProgramnvvmDestroyProgramnvvmAddModuleToProgramnvvmLazyAddModuleToProgramnvvmCompileProgramnvvmGetCompiledResultSizenvvmGetCompiledResultnvvmGetProgramLogSizenvvmGetProgramLog nvvmIRVersionnvvmVerifyProgramNc Cst|jdkrt||_}ztd|_Wn8tk rf}zd|_d}t||W5d}~XYnX|j D]8\}}t |j|}|d|_ |dd|_ t |||qrW5QRX|jS)NZnvvmz;libNVVM cannot be found. Do `conda install cudatoolkit`: %srr ) _nvvm_lock_NVVM__INSTANCEobject__new__rdriverOSErrorr _PROTOTYPESitemsgetattrrestypeZargtypessetattr)clsinsteerrmsgnameprotofuncrrrr)s   z NVVM.__new__cCs<|}|d|_|d|_|d|_|d|_t|_dS)Nrr r)get_ir_version_majorIR_minorIRZ _majorDbgZ _minorDbgget_supported_ccs_supported_ccs)self ir_versionsrrr__init__s     z NVVM.__init__cCs|j|jfdkrtStSdS)N)r )r:r;_datalayout_original_datalayout_i128r>rrr data_layoutszNVVM.data_layoutcCs|jSN)r=rDrrr supported_ccsszNVVM.supported_ccscCs8t}t}|t|t|}||d|j|jfS)NzFailed to get version.)rrr check_errorvalue)r>majorminorerrrrr get_versions  zNVVM.get_versioncCsXt}t}t}t}|t|t|t|t|}||d|j|j|j|jfS)NzFailed to get IR version.)rr$rrHrI)r>ZmajorIRZminorIRZmajorDbgZminorDbgrLrrrr9s zNVVM.get_ir_versionFcCs2|r.t|t|}|r*t|tdn|dS)Nr )r RESULT_CODE_NAMESprintsysexit)r>errormsgrQexcrrrrHs  zNVVM.check_error)F)__name__ __module__ __qualname____doc__ nvvm_resultrr nvvm_programrrr,r'r)r@propertyrErGrMr9rHrrrrrKs\   6   rc@sDeZdZddZddZddZddZd d Zd d Zd dZ dS)CompilationUnitcCs4t|_t|_|jt|j}|j|ddS)NzFailed to create CU)rr*rZ_handlerrrH)r>rLrrrr@szCompilationUnit.__init__cCs*t}|t|j}|j|ddddS)NzFailed to destroy CUT)rQ)rrrr]rH)r>r*rLrrr__del__szCompilationUnit.__del__cCs*|j|j|t|d}|j|ddS)z Add a module level NVVM IR to a compilation unit. - The buffer should contain an NVVM module IR either in the bitcode representation (LLVM3.0) or in the text representation. NFailed to add module)r*rr]lenrHr>bufferrLrrr add_modules  zCompilationUnit.add_modulecCs*|j|j|t|d}|j|ddS)z Lazily add an NVVM IR module to a compilation unit. The buffer should contain NVVM module IR either in the bitcode representation or in the text representation. Nr_)r*rr]r`rHrarrrlazy_add_modules  zCompilationUnit.lazy_add_modulec Ksg}d|kr |d|d|dr>|d|dd}|D]8}||krFtt||}|d|dd|fqF|rd tt| }t d |t t |d d |D}|j|jt ||}||d |j|jt ||}||dt} |j|jt| }||dt| j} |j|j| }||d||_|jrttj|jtd| ddS)ajPerform Compilation The valid compiler options are * - -opt= * - 0 (disable optimizations) * - 3 (default, enable optimizations) * - -arch= * - compute_XX where XX is in (35, 37, 50, 52, 53, 60, 61, 62, 70, * 72, 75, 80, 86, 89, 90). * The default is compute_52. * - -ftz= * - 0 (default, preserve denormal values, when performing * single-precision floating-point operations) * - 1 (flush denormal values to zero, when performing * single-precision floating-point operations) * - -prec-sqrt= * - 0 (use a faster approximation for single-precision * floating-point square root) * - 1 (default, use IEEE round-to-nearest mode for * single-precision floating-point square root) * - -prec-div= * - 0 (use a faster approximation for single-precision * floating-point division and reciprocals) * - 1 (default, use IEEE round-to-nearest mode for * single-precision floating-point division and reciprocals) * - -fma= * - 0 (disable FMA contraction) * - 1 (default, enable FMA contraction) * optz-opt=%darchz-arch=%s)ftz prec_sqrtprec_divfmaz-%s=%d_-z, zunsupported option {0}cSsg|]}t|dqS)utf8)rencode).0xrrr $sz+CompilationUnit.compile..zFailed to verify zFailed to compile z&Failed to get size of compiled result.zFailed to get compiled result.)categoryN)appendpopgetintboolreplacejoinmapreprkeysr formatrr`r*r%r] _try_errorrrr rrrIr!get_loglogwarningswarnr ) r>optionsoptsZ other_optionskvZoptstrZc_optsrLreslenZptxbufrrrcompiles<"       zCompilationUnit.compilecCs|j|d||fdS)Nz%s %s)r*rHr)r>rLrSrrrr~?szCompilationUnit._try_errorcCslt}|j|jt|}|j|d|jdkrht|j}|j|j|}|j|d|j dSdS)Nz#Failed to get compilation log size.r zFailed to get compilation log.rm) rr*r"r]rrHrIrr#decode)r>rrLZlogbufrrrrBs   zCompilationUnit.get_logN) rUrVrWr@r^rcrdrr~rrrrrr\s  Vr\)rr)rrr)rr8)rr)r)rr )rr8)rr)rr8)rr)rArrArrAr)rA rr)rr)rr)rr)rr) ) r8)rr)rr)rr)rr)rr)rrA) r)rr )rr8csRz&t|\tfddtDWStk rLtddtDYSXdS)Ncs(g|] }|krkrnq|qSrrroccZmax_ccZmin_ccrrrqms  z(ccs_supported_by_ctk..cSsg|]}|tjkr|qSr)rZCUDA_DEFAULT_PTX_CCrrrrrqrs ) CTK_SUPPORTEDtupleCOMPUTE_CAPABILITIESKeyError)Z ctk_versionrrrccs_supported_by_ctkis  rcCszddlm}|}Wnd}|YSXtt}||krd}|dd|d}d|d|dd|dd}t||St|}|S) Nr)runtimer.r z CUDA Toolkit z is unsupported by Numba - z! is the minimum required version.)Znumba.cuda.cudadrv.runtimerrMminrrrr)rZcudart_versionZ _supported_ccZ min_cudartZctk_verZunsupported_verrrrr<vs     r<cCsxtj}|sd}t|t|D]N\}}||kr8|S||kr |dkr^d||}t|q ||dSq |dS)z Given a compute capability, return the closest compute capability supported by the CUDA toolkit. :param mycc: Compute capability as a tuple ``(MAJOR, MINOR)`` :return: Closest supported CC as a tuple ``(MAJOR, MINOR)`` zmNo supported GPU compute capabilities found. Please check your cudatoolkit version matches your CUDA version.rz?GPU compute capability %d.%d is not supported(requires >=%d.%d)r )rrGr enumerate)ZmyccrGrSirrrrfind_closest_archs rcCs"tjrtj}n t||f}d|S)z1Matches with the closest architecture option z compute_%d%d)rZ FORCE_CUDA_CCr)rJrKrfrrrget_arch_options rz~Missing libdevice file. Please ensure you have package cudatoolkit >= 11.0 Install package by: conda install cudatoolkit c@s eZdZdZddZddZdS) LibDeviceNcCs0|jdkr$tdkrttt|_|j|_dSrF)_cache_r RuntimeErrorMISSING_LIBDEVICE_FILE_MSGrbcrDrrrr@s   zLibDevice.__init__cCs|jSrF)rrDrrrrusz LibDevice.get)rUrVrWrr@rurrrrrsrz %cas_success = cmpxchg volatile {Ti}* %iptr, {Ti} %old, {Ti} %new monotonic monotonic %cas = extractvalue {{ {Ti}, i1 }} %cas_success, 0 a define internal {T} @___numba_atomic_{T}_{FUNC}({T}* %ptr, {T} %val) alwaysinline {{ entry: %iptr = bitcast {T}* %ptr to {Ti}* %old2 = load volatile {Ti}, {Ti}* %iptr br label %attempt attempt: %old = phi {Ti} [ %old2, %entry ], [ %cas, %attempt ] %dold = bitcast {Ti} %old to {T} %dnew = {OP} {T} %dold, %val %new = bitcast {T} %dnew to {Ti} {CAS} %repeat = icmp ne {Ti} %cas, %old br i1 %repeat, label %attempt, label %done done: %result = bitcast {Ti} %old to {T} ret {T} %result }} a define internal {T} @___numba_atomic_{Tu}_inc({T}* %iptr, {T} %val) alwaysinline {{ entry: %old2 = load volatile {T}, {T}* %iptr br label %attempt attempt: %old = phi {T} [ %old2, %entry ], [ %cas, %attempt ] %bndchk = icmp ult {T} %old, %val %inc = add {T} %old, 1 %new = select i1 %bndchk, {T} %inc, {T} 0 {CAS} %repeat = icmp ne {T} %cas, %old br i1 %repeat, label %attempt, label %done done: ret {T} %old }} a define internal {T} @___numba_atomic_{Tu}_dec({T}* %iptr, {T} %val) alwaysinline {{ entry: %old2 = load volatile {T}, {T}* %iptr br label %attempt attempt: %old = phi {T} [ %old2, %entry ], [ %cas, %attempt ] %dec = add {T} %old, -1 %bndchk = icmp ult {T} %dec, %val %new = select i1 %bndchk, {T} %dec, {T} %val {CAS} %repeat = icmp ne {T} %cas, %old br i1 %repeat, label %attempt, label %done done: ret {T} %old }} a define internal {T} @___numba_atomic_{T}_{NAN}{FUNC}({T}* %ptr, {T} %val) alwaysinline {{ entry: %ptrval = load volatile {T}, {T}* %ptr ; Return early when: ; - For nanmin / nanmax when val is a NaN ; - For min / max when val or ptr is a NaN %early_return = fcmp uno {T} %val, %{PTR_OR_VAL}val br i1 %early_return, label %done, label %lt_check lt_check: %dold = phi {T} [ %ptrval, %entry ], [ %dcas, %attempt ] ; Continue attempts if dold less or greater than val (depending on whether min or max) ; or if dold is NaN (for nanmin / nanmax) %cmp = fcmp {OP} {T} %dold, %val br i1 %cmp, label %attempt, label %done attempt: ; Attempt to swap in the value %old = bitcast {T} %dold to {Ti} %iptr = bitcast {T}* %ptr to {Ti}* %new = bitcast {T} %val to {Ti} {CAS} %dcas = bitcast {Ti} %cas to {T} br label %lt_check done: ret {T} %ptrval }} cCs tj|dS)NTi)cas_nvvmr}rrrrir_cas7srcCs"t||||t|d}tjf|S)N)TrOPFUNCCAS)dictrir_numba_atomic_binary_templater})rrrrparamsrrrir_numba_atomic_binary;src Cs&t||||||t|d}tjf|S)N)rrNANr PTR_OR_VALrr)rrir_numba_atomic_minmax_templater})rrrrrrrrrrir_numba_atomic_minmax@s  rcCstj||t|dSN)rTur)ir_numba_atomic_inc_templater}rrrrrrir_numba_atomic_incGsrcCstj||t|dSr)ir_numba_atomic_dec_templater}rrrrrir_numba_atomic_decKsrcCs0dtdddddfdtdd d d dfd tddd d dfd tdddfdtdddfdtdd dddddfdtdddddddfdtdd dddddfdtdddddddfdtdd dddddfdtdddddddfd tdd dd!dddfd"tdddd!dddfd#g}|D]\}}|||}q t|}|S)$NzIdeclare double @"___numba_atomic_double_add"(double* %".1", double %".2")doubleZi64Zfaddadd)rrrrzEdeclare float @"___numba_atomic_float_sub"(float* %".1", float %".2")floati32ZfsubsubzIdeclare double @"___numba_atomic_double_sub"(double* %".1", double %".2")z=declare i64 @"___numba_atomic_u64_inc"(i64* %".1", i64 %".2")Zu64rz=declare i64 @"___numba_atomic_u64_dec"(i64* %".1", i64 %".2")zEdeclare float @"___numba_atomic_float_max"(float* %".1", float %".2")rznnan oltZptrmax)rrrrrrzIdeclare double @"___numba_atomic_double_max"(double* %".1", double %".2")zEdeclare float @"___numba_atomic_float_min"(float* %".1", float %".2")znnan ogtrzIdeclare double @"___numba_atomic_double_min"(double* %".1", double %".2")zHdeclare float @"___numba_atomic_float_nanmax"(float* %".1", float %".2")nanZultzLdeclare double @"___numba_atomic_double_nanmax"(double* %".1", double %".2")zHdeclare float @"___numba_atomic_float_nanmin"(float* %".1", float %".2")ZugtzLdeclare double @"___numba_atomic_double_nanmin"(double* %".1", double %".2"))Zimmargr)rrrrrxllvm140_to_70_ir)llvmirZ replacementsdeclfnrrr llvm_replaceOs          & rcKsxt|tr|g}|ddr0|dddddt}t}|D]}t|}||dq@| | |j f|S)NZfastmathFT)rgrjrirhrm) isinstancestrrtupdater\rrrcrnrdrur)rrcuZ libdevicemodrrr llvm_to_ptx~s   rz"^attributes #\d+ = \{ ([\w\s]+)\ }cCsng}|D]V}|drXt|}|d}ddd|D}||d|}||q d|S)z, Convert LLVM 14.0 IR for LLVM 7.0. z attributes #r  css|]}|dkr|VqdS)Z willreturnNr)roarrr sz#llvm140_to_70_ir.. ) splitlines startswithre_attributes_defmatchgroupsplitryrxrs)r buflinemattrsrrrrs    rcCsZ|j}t|d}ttdd}||||f}t|d}|||j ddS)NZkernel r znvvm.annotationsZnoinline) moduler ZMetaDataStringConstantIntType add_metadatarZget_or_insert_named_metadatar attributesdiscard)ZlfuncrZmdstrZmdvaluemdZnmdrrrset_cuda_kernels   rcs<tdfddtD}||}|d|dS)zAdd NVVM IR version to modulercsg|] }|qSrr)rorrrrrqsz"add_ir_version..znvvmir.versionN)r rrr9rZadd_named_metadata)rr?Zmd_verrrradd_ir_versions  r)MrXloggingrerPrctypesrrrrrrr threadingZllvmliter rRr r r ZlibsrrrZ numba.corerr getLoggerrUloggerZADDRSPACE_GENERICZADDRSPACE_GLOBALZADDRSPACE_SHAREDZADDRSPACE_CONSTANTZADDRSPACE_LOCALrZrYrrNrrrr0modulesrBrCrLockr&r(rr\rrrr<rrrrrrrrrrrrrrrrrrrrrrrrrs|$    ~   "  /