Searched defs:compute_capability (Results 1 – 13 of 13) sorted by relevance
| /aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/service/gpu/llvm_gpu_backend/ |
| H A D | gpu_backend_lib.cc | 89 static std::string GetSmName(se::CudaComputeCapability compute_capability) { in GetSmName()
360 llvm::Triple target_triple, se::CudaComputeCapability compute_capability, in NVPTXGetTargetMachine()
535 auto compute_capability = in CompileToPtx() local
793 auto compute_capability = in AMDGPUTargetModuleLinker() local
863 auto compute_capability = in AMDGPUGetTargetMachine() local
923 auto compute_capability = in CompileToHsaco() local
|
| /aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/service/gpu/ |
| H A D | cudnn_vectorize_convolutions.cc | 261 const se::CudaComputeCapability& compute_capability, in TryRevectorizeConv()
399 const se::CudaComputeCapability& compute_capability, in TryVectorizeConv()
|
| H A D | cudnn_vectorize_convolutions.h | 49 se::CudaComputeCapability compute_capability) in CudnnVectorizeConvolutions()
|
| H A D | cudnn_pad_for_convolutions.h | 34 explicit CudnnPadForConvolutions(se::CudaComputeCapability compute_capability) in CudnnPadForConvolutions()
|
| H A D | cudnn_support_utils.cc | 28 const se::CudaComputeCapability& compute_capability, in CudnnSupportsOptimizedIntegerConvolution()
|
| H A D | cudnn_vectorize_convolutions_test.cc | 37 StatusOr<bool> Run(std::pair<int, int> compute_capability, in Run() argument
|
| H A D | cudnn_pad_for_convolutions.cc | 295 int pad_to, const se::CudaComputeCapability& compute_capability, in TryResolvePaddedShapesForIntegerConvolution()
|
| H A D | cudnn_simplify_padding_test.cc | 46 StatusOr<bool> RunEndToEnd(std::pair<int, int> compute_capability, in RunEndToEnd() argument
|
| /aosp_15_r20/external/tensorflow/tensorflow/core/profiler/protobuf/ |
| H A D | hardware_types.proto | 29 GPUComputeCapability compute_capability = 5; field
|
| /aosp_15_r20/external/tensorflow/tensorflow/core/protobuf/ |
| H A D | autotuning.proto | 98 ComputeCapability compute_capability = 4; field
|
| /aosp_15_r20/external/pytorch/c10/cuda/ |
| H A D | CUDADeviceAssertionHost.cpp | 50 int compute_capability = -1; in dsa_get_device_compute_capability() local
|
| /aosp_15_r20/external/tensorflow/tensorflow/core/grappler/optimizers/ |
| H A D | generic_layout_optimizer.cc | 63 double compute_capability = 0.0; in GetNumGPUs() local
|
| H A D | remapper.cc | 423 double compute_capability = 0.0; in RuntimeFusionEnabled() local
|