Lines Matching refs:CUDA

2 Compiling CUDA with clang
11 This document describes how to compile CUDA code with clang, and gives some
12 details about LLVM and clang's CUDA implementations.
14 This document assumes a basic familiarity with CUDA. Information about CUDA
16 `CUDA programming guide
19 Compiling CUDA Code
25 CUDA is supported in llvm 3.9, but it's still in active development, so we
29 Before you build CUDA code, you'll need to have installed the appropriate
30 driver for your nvidia GPU and the CUDA SDK.  See `NVIDIA's CUDA installation
33 <https://llvm.org/bugs/show_bug.cgi?id=26966>`_ the CUDA toolkit as installed
36 You will need CUDA 7.0, 7.5, or 8.0 to compile with clang.
38 CUDA compilation is supported on Linux, on MacOS as of 2016-11-18, and on
44 Invoking clang for CUDA compilation works similarly to compiling regular C++.
49 compiling CUDA code by noticing that your filename ends with ``.cu``.
58       -L<CUDA install path>/<lib64 or lib>             \
67 "CUDA driver version is insufficient for CUDA runtime version" errors when you
70 * ``<CUDA install path>`` -- the directory where you installed CUDA SDK.
74   pass e.g. ``-L/usr/local/cuda/lib``.  (In CUDA, the device code and host code
92 the CUDA SDK into ``/usr/local/cuda``, ``/usr/local/cuda-7.0``, or
105   compiling CUDA) Controls whether the compiler emits fused multiply-add
145 <https://github.com/llvm-mirror/test-suite/blob/master/External/CUDA/math_h.cu>`_
147 <https://github.com/llvm-mirror/test-suite/blob/master/External/CUDA/cmath.cu>`_
194 Although clang's CUDA implementation is largely compatible with NVCC's, you may
195 still want to detect when you're compiling CUDA code specifically with clang.
201 When clang is actually compiling CUDA code -- rather than being used as a
204 preprocessor).  So you can use the following incantations to detect clang CUDA
210   // clang compiling CUDA code, host mode.
214   // clang compiling CUDA code, device mode.
217 Both clang and nvcc define ``__CUDACC__`` during CUDA compilation.  You can
223 There is no formal CUDA spec, and clang and nvcc speak slightly different
517   non-generic address space are faster, but pointers in CUDA are not explicitly
558 To obtain help on LLVM in general and its CUDA support, see `the LLVM