Home
last modified time | relevance | path

Searched refs:GPU (Results 1 – 25 of 56) sorted by relevance

123

/openbsd/src/gnu/llvm/llvm/lib/Target/AMDGPU/
DR600Subtarget.cpp25 R600Subtarget::R600Subtarget(const Triple &TT, StringRef GPU, StringRef FS, in R600Subtarget() argument
27 : R600GenSubtargetInfo(TT, GPU, /*TuneCPU*/ GPU, FS), AMDGPUSubtarget(TT), in R600Subtarget()
30 TLInfo(TM, initializeSubtargetDependencies(TT, GPU, FS)), in R600Subtarget()
31 InstrItins(getInstrItineraryForCPU(GPU)) { in R600Subtarget()
36 StringRef GPU, in initializeSubtargetDependencies() argument
40 ParseSubtargetFeatures(GPU, /*TuneCPU*/ GPU, FullFS); in initializeSubtargetDependencies()
DR600TargetMachine.cpp68 StringRef GPU = getGPUName(F); in getSubtargetImpl() local
71 SmallString<128> SubtargetKey(GPU); in getSubtargetImpl()
80 I = std::make_unique<R600Subtarget>(TargetTriple, GPU, FS, *this); in getSubtargetImpl()
DAMDGPUSubtarget.cpp65 StringRef GPU, StringRef FS) { in initializeSubtargetDependencies() argument
95 ParseSubtargetFeatures(GPU, /*TuneCPU*/ GPU, FullFS); in initializeSubtargetDependencies()
169 GCNSubtarget::GCNSubtarget(const Triple &TT, StringRef GPU, StringRef FS, in GCNSubtarget() argument
172 AMDGPUGenSubtargetInfo(TT, GPU, /*TuneCPU*/ GPU, FS), in GCNSubtarget()
176 InstrItins(getInstrItineraryForCPU(GPU)), in GCNSubtarget()
177 InstrInfo(initializeSubtargetDependencies(TT, GPU, FS)), in GCNSubtarget()
DAMDGPUFeatures.td46 Value#" GPU generation", Implies>;
DR600Subtarget.h82 StringRef GPU, StringRef FS);
DAMDGPUTargetMachine.cpp516 static StringRef getGPUOrDefault(const Triple &TT, StringRef GPU) { in getGPUOrDefault() argument
517 if (!GPU.empty()) in getGPUOrDefault()
518 return GPU; in getGPUOrDefault()
817 StringRef GPU = getGPUName(F); in getSubtargetImpl() local
820 SmallString<128> SubtargetKey(GPU); in getSubtargetImpl()
829 I = std::make_unique<GCNSubtarget>(TargetTriple, GPU, FS, *this); in getSubtargetImpl()
/openbsd/src/gnu/llvm/clang/lib/Basic/Targets/
DNVPTX.h62 CudaArch GPU; variable
79 Features[CudaArchToString(GPU)] = true; in initFeatureMap()
130 GPU = StringToCudaArch(Name); in setCPU()
131 return GPU != CudaArch::UNKNOWN; in setCPU()
DNVPTX.cpp62 GPU = CudaArch::SM_20; in NVPTXTargetInfo()
172 switch (GPU) { in getTargetDefines()
/openbsd/src/gnu/llvm/llvm/docs/
DUserGuides.rst240 This document describes using the NVPTX backend to compile GPU kernels.
243 This document describes using the AMDGPU backend to compile GPU kernels.
255 This document describes using the SPIR-V target to compile GPU kernels.
258 This document describes using the DirectX target to compile GPU code for the
DCompileCudaWithLLVM.rst58 $ clang++ axpy.cu -o axpy --cuda-gpu-arch=<GPU arch> \
81 * ``<GPU arch>`` -- the `compute capability
82 <https://developer.nvidia.com/cuda-gpus>`_ of your GPU. For example, if you
83 want to run your program on a GPU with compute capability of 3.5, specify
101 GPU hardware allows for more control over numerical operations than most CPUs,
242 * For each GPU architecture ``arch`` that we're compiling for, do:
248 ``S_arch``, containing GPU machine code (SASS) for ``arch``.
262 * For each GPU architecture ``arch`` that we're compiling for, do:
288 host compilation and during device compilation for each GPU architecture.)
503 on a CPU isn't necessarily fast on a GPU. We've made a number of changes to
[all …]
DNVPTXUsage.rst13 To support GPU programming, the NVPTX back-end supports a subset of LLVM IR
14 along with a defined set of conventions used to represent GPU programming
369 The most common way to execute PTX assembly on a GPU device is to use the CUDA
370 Driver API. This API is a low-level interface to the GPU driver and allows for
371 JIT compilation of PTX code to native GPU machine code.
571 an explicit address space specifier. What is address space 1? NVIDIA GPU
594 program), or a `device` function (callable only from GPU code). You can think
595 of `kernel` functions as entry-points in the GPU program. To mark an LLVM IR
624 a real GPU device? The CUDA Driver API provides a convenient mechanism for
625 loading and JIT compiling PTX to a native GPU device, and launching a kernel.
[all …]
DAMDGPUInstructionSyntax.rst197 For detailed information about operands, follow *operand links* in GPU-specific documents.
208 may be found in GPU-specific documents.
DDocker.rst136 preinstalled CUDA libraries and allows to access a GPU, installed on your
142 If you want to use CUDA libraries and have access to a GPU on your machine,
146 to have an access to GPU from a docker container that is running the built
/openbsd/src/gnu/llvm/llvm/docs/AMDGPU/
Dgfx8_vdata_886702.rst15 *Size:* depends on GFX8 GPU revision:
Dgfx8_vdata_f2bf57.rst15 *Size:* depends on GFX8 GPU revision:
Dgfx8_vdata_4f639e.rst15 *Size:* depends on GFX8 GPU revision:
Dgfx8_vdst_6f591e.rst15 *Size:* depends on GFX8 GPU revision:
Dgfx8_vdst_d809e2.rst15 *Size:* depends on GFX8 GPU revision:
Dgfx8_vdst_c360a5.rst15 *Size:* depends on GFX8 GPU revision:
Dgfx8_vdst_b61114.rst15 *Size:* depends on GFX8 GPU revision and :ref:`tfe<amdgpu_synid_tfe>`:
Dgfx8_vdst_de9309.rst15 *Size:* depends on GFX8 GPU revision and :ref:`tfe<amdgpu_synid_tfe>`:
Dgfx8_vdst_2d89ba.rst15 *Size:* depends on GFX8 GPU revision and :ref:`tfe<amdgpu_synid_tfe>`:
/openbsd/src/gnu/llvm/clang/lib/Headers/cuda_wrappers/
Dcmath33 // headers to parse, but would not allow accidental use of them on a GPU.
71 // which we can't handle on GPU. We need to forward those to CUDA-provided
/openbsd/src/gnu/llvm/clang/docs/
DClangOffloadBundler.rst159 intermediate steps of the tool chain. Also used for AMD GPU
166 hipv4 Offload code object for the HIP language. Used for AMD GPU
257 *AMD GPU*
258 AMD GPU supports target ID and target features. See `User Guide for AMDGPU Backend
/openbsd/src/sys/dev/pci/drm/i915/gt/shaders/
DREADME21 IGT GPU tool scripts and the Mesa's i965 instruction assembler tool are used

123