o 1&i%@sddlmZddlmZmZddlmZddlmZm Z ddl m Z ddl m Z ddlmZddlmZd d Zed d Zed dZeddZe eedddddZeddZddZeddZeddZeddZd S)!)ir)cudatypes)cgutils)RequireLiteralValueNumbaValueError) signature)overload_attribute) nvvmutils) intrinsiccCsB|j}|dkr tj}n|dvrttj|}ntdt|tjS)N)zargument can only be 1, 2, 3)Z literal_valuerint64UniTuplerrint32)ndimvalrestyper@C:\wamp64\www\opt\env\Lib\site-packages\numba/cuda/intrinsics.py_type_grid_functions rcCs,t|tjs t|t|}dd}||fS)agrid(ndim) Return the absolute position of the current thread in the entire grid of blocks. *ndim* should correspond to the number of dimensions declared when instantiating the kernel. If *ndim* is 1, a single integer is returned. If *ndim* is 2 or 3, a tuple of the given number of integers is returned. Computation of the first integer is as follows:: cuda.threadIdx.x + cuda.blockIdx.x * cuda.blockDim.x and is similar for the other two indices, but using the ``y`` and ``z`` attributes. cSsJ|j}|tjkrtj|ddSt|tjr#tj||jd}t ||SdS)Nr )dim) return_typerrr Z get_global_id isinstancercountr pack_array)contextbuildersigargsrZidsrrrcodegen1s   zgrid..codegenrrZIntegerLiteralrr typingctxrrr!rrrgrids r%cs8t|tjs t|t|}ddfdd}||fS)agridsize(ndim) Return the absolute size (or shape) in threads of the entire grid of blocks. *ndim* should correspond to the number of dimensions declared when instantiating the kernel. If *ndim* is 1, a single integer is returned. If *ndim* is 2 or 3, a tuple of the given number of integers is returned. Computation of the first integer is as follows:: cuda.blockDim.x * cuda.gridDim.x and is similar for the other two indices, but using the ``y`` and ``z`` attributes. cSsJtd}t|d|}t|d|}|||||||S)N@zntid.znctaid.)rIntTyper call_sregmulZsext)rrZi64ZntidZnctaidrrr_nthreads_for_dimRs z#gridsize.._nthreads_for_dimcs||j}|d}|tjkr|St|tjr:|d}|jdkr't|||fS|jdkr<|d}t||||fSdSdS)Nxyr rz)rrrrrrrr)rrrr rnxnyZnzr*rrr!Xs       zgridsize..codegenr"r#rr0rgridsize<s  r1cCttj}dd}||fS)NcSs t|dS)Nwarpsize)r r()rrrr rrrr!ns z_warpsize..codegen)rrrr$rr!rrr _warpsizejs r5r3r)targetcCs dd}|S)z_ The size of a warp. All architectures implemented to date have a warp size of 32. cSstS)N)r5)modrrrgetzszcuda_warpsize..getr)r7r8rrr cuda_warpsizetsr9cCr2)a Synchronize all threads in the same thread block. This function implements the same pattern as barriers in traditional multi-threaded programming: this function waits until all threads in the block call it, at which point it returns control to all its callers. cSs<d}|j}ttd}t|||}||d|S)Nzllvm.nvvm.barrier0r)moduler FunctionTypeZVoidTyperget_or_insert_functioncallZget_dummy_value)rrrr fnameZlmodfntysyncrrrr!s  zsyncthreads..codegen)rrnoner4rrr syncthreadss rBcs2t|tjsdSttjtj}fdd}||fS)Ncs6ttdtdf}t|j|}|||S)N )rr;r'rr<r:r=)rrrr r?r@r>rrr!s z'_syncthreads_predicate..codegen)rrIntegerri4)r$ predicater>rr!rrDr_syncthreads_predicates  rHcCd}t|||S)z syncthreads_count(predicate) An extension to numba.cuda.syncthreads where the return value is a count of the threads where predicate is true. zllvm.nvvm.barrier0.popcrHr$rGr>rrrsyncthreads_count rLcCrI)z syncthreads_and(predicate) An extension to numba.cuda.syncthreads where 1 is returned if predicate is true for all threads or 0 otherwise. zllvm.nvvm.barrier0.andrJrKrrrsyncthreads_andrMrNcCrI)z syncthreads_or(predicate) An extension to numba.cuda.syncthreads where 1 is returned if predicate is true for any thread or 0 otherwise. zllvm.nvvm.barrier0.orrJrKrrrsyncthreads_orrMrON)ZllvmliterZnumbarrZ numba.corerZnumba.core.errorsrrZnumba.core.typingrZnumba.core.extendingr Z numba.cudar Znumba.cuda.extendingr rr%r1r5Moduler9rBrHrLrNrOrrrrs4        -