Searched refs:kernels (Results 1 – 18 of 18) sorted by relevance
| /hardware/google/gfxstream/codegen/vulkan/vulkan-docs-next/appendices/ |
| D | VK_NV_cuda_kernel_launch.adoc | 18 This extension targets deployment of existing CUDA kernels via Vulkan, with
19 a way to directly upload PTX kernels and dispatch the kernels from Vulkan's
|
| /hardware/google/gfxstream/codegen/vulkan/vulkan-docs-next/proposals/ |
| D | VK_KHR_cooperative_matrix.asciidoc | 25 matrix multiplication kernels but, while technically possible on some hardware,
26 this approach often does not make it possible to write optimal kernels and
|
| D | VK_QCOM_image_processing.adoc | 20 higher-order filtering kernels or advanced image algorithms are required.
51 …kernels can be expressed as a mathematically equivalent 1D separable kernel. Separable filters of…
|
| D | VK_EXT_frame_boundary.adoc | 28 of compute kernels dispatches that treat one unit of work.
|
| /hardware/google/gfxstream/codegen/vulkan/vulkan-docs-next/chapters/VK_NV_cuda_kernel_launch/ |
| D | dispatch.adoc | 8 Compute kernels can: be provided in SPIR-V or PTX code.
9 When using PTX kernels the dispatch mechanism is different than with regular
|
| D | module.adoc | 233 kernels relying on exceptions
234 * CUDA kernels submitted to Vulkan are limited to the amount of shared
|
| /hardware/interfaces/renderscript/1.0/vts/functional/ |
| D | VtsScriptTests.cpp | 393 hidl_vec<ScriptKernelID> kernels = {blendKID, blurKID}; in TEST_P() local
398 ScriptGroup scriptGroup = context->scriptGroupCreate(kernels, srcK, dstK, dstF, types); in TEST_P()
|
| /hardware/interfaces/renderscript/1.0/default/ |
| D | Context.h | 109 …Return<ScriptGroup> scriptGroupCreate(const hidl_vec<ScriptKernelID>& kernels, const hidl_vec<Scri…
|
| D | Context.cpp | 575 Return<ScriptGroup> Context::scriptGroupCreate(const hidl_vec<ScriptKernelID>& kernels, const hidl_… in scriptGroupCreate() argument
576 …std::vector<RsScriptKernelID> _kernels = hidl_to_rs<RsScriptKernelID>(kernels, [](ScriptFieldID va… in scriptGroupCreate()
|
| /hardware/interfaces/renderscript/1.0/ |
| D | IContext.hal | 898 * @param kernels Collection of Scripts' Kernel identifiers
906 scriptGroupCreate(vec<ScriptKernelID> kernels, vec<ScriptKernelID> srcK,
930 * used for the kernels that require an output Allocation visible after the
942 * used for kernels that require an input Allocation provided from outside
|
| /hardware/google/gfxstream/guest/mesa/include/CL/ |
| D | cl_icd.h | 361 cl_program program, cl_uint num_kernels, cl_kernel *kernels,
|
| D | cl.h | 1366 cl_kernel * kernels,
|
| D | opencl.hpp | 6877 cl_int createKernels(vector<Kernel>* kernels) in createKernels() argument
6893 if (kernels) { in createKernels()
6894 kernels->resize(value.size()); in createKernels()
6901 (*kernels)[i] = Kernel(value[i], false); in createKernels()
|
| D | cl.hpp | 5366 cl_int createKernels(VECTOR_CLASS<Kernel>* kernels) in createKernels() argument
5381 kernels->assign(&value[0], &value[numKernels]); in createKernels()
|
| /hardware/google/gfxstream/guest/mesa/ |
| D | meson.build | 857 # On Android, seccomp kills the process on kernels without
|
| /hardware/google/gfxstream/codegen/vulkan/vulkan-docs-next/chapters/ |
| D | textures.adoc | 3422 an array of kernels, one set of filter weights per phase.
|
| /hardware/interfaces/neuralnetworks/1.2/ |
| D | types.hal | 2679 * Three NMS kernels are supported:
|
| /hardware/interfaces/neuralnetworks/1.3/ |
| D | types.hal | 2839 * Three NMS kernels are supported:
|