- Sort Score
- Result 10 results
- Languages All
Results 1 - 10 of 200 for hardwareID (0.17 sec)
-
src/cmd/vendor/golang.org/x/sys/windows/setupapi_windows.go
infFileName [MAX_PATH]uint16 drvDescription [LINE_LEN]uint16 hardwareID [1]uint16 } func (*DrvInfoDetailData) unsafeSizeOf() uint32 { if unsafe.Sizeof(uintptr(0)) == 4 { // Windows declares this with pshpack1.h return uint32(unsafe.Offsetof(DrvInfoDetailData{}.hardwareID) + unsafe.Sizeof(DrvInfoDetailData{}.hardwareID)) } return uint32(unsafe.Sizeof(DrvInfoDetailData{})) }
Registered: Wed Jun 12 16:32:35 UTC 2024 - Last Modified: Wed Oct 26 00:11:50 UTC 2022 - 67.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/hardwares/target_hardware.cc
auto* registered_hardwares = GetRegisteredHardwares(); for (auto& hardware : *registered_hardwares) { if (hardware.unique_name == unique_name) { llvm::errs() << "Ignoring duplicate hardware. Hardware " << unique_name << " already registered\n"; hardware.target_hardware_factory = target_hardware_factory; return; } }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 09 21:39:59 UTC 2023 - 9.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/runtime_metadata.fbs
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jul 21 01:22:53 UTC 2021 - 2.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/execution_metadata_exporter.cc
} }); } // Build the flatbuffer. std::vector<flatbuffers::Offset<flatbuffers::String>> hardwares; for (const auto& kv : *hardware_names) { hardwares.push_back(builder->CreateString(kv.first)); } return CreateHardwareMetadata(*builder, builder->CreateVector(hardwares)); } } // namespace std::optional<std::string> ExportRuntimeMetadata(mlir::ModuleOp module) {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 06:11:34 UTC 2024 - 7.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/hardwares/target_hardware.h
virtual double GetFuncCost(func::FuncOp* func) const; // Returns true if 'op' can run on this Hardware. virtual bool IsOpSupported(mlir::Operation* op) const; // Switching cost between from hardware and this hardware. // If both the hardwares are the same, the transfer cost is basically 0. virtual double GetHardwareSwitchingCost(const TargetHardware* from, size_t buffer_size) const = 0;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 09 21:39:59 UTC 2023 - 7.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/README.md
# Target Aware Conversion (TAC) Different hardwares have different capabilities and restrictions. TAC is designed to leverage hardwares' capabilities to: * Perform device-specific optimizations (such as unsupported ops lowering, layout transformations, etc.) * Graph partitioning based on the hardware costs modeling. * It supports general import/export where you can hook your own
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Mar 29 18:32:13 UTC 2022 - 11.6K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/tac_module.h
absl::Status RunTacPasses(mlir::ModuleOp* module, bool debug_mode = false); // Create instances of all registered hardwares. std::vector<std::unique_ptr<tac::TargetHardware>> InstantiateBackends(); std::unique_ptr<TacImporter> importer_; std::unique_ptr<TacExporter> exporter_; // Owned list of all target hardware backends. std::vector<std::unique_ptr<tac::TargetHardware>> backends_;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jun 08 01:19:25 UTC 2023 - 4.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/transforms/device_transform.h
namespace TFL { namespace tac { // Returns true if 'op' is supported to run on 'hardware'. bool IsSupported(Operation* op, const std::string& hardware); // Return proper rewriter patterns for different hardwares. RewritePatternSet GetHardwareRewritePatterns(MLIRContext* context, const std::string& hardware); // Convert quantized ops to float, this will essentially insert dequantize &
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 07 18:43:51 UTC 2022 - 2K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/tac_filter.proto
// A list of filters for TAC users to run ops/functions on ML hardwares. The // intuition is that, for ops/functions that can be run on ML hardware (e.g. // EdgeTPU) and TFLite CPU, TAC users give a hint that they're more performant // to run on TFLite CPU. These filters give the TAC users freedom to specify the // parts that they want to use other hardware to accelerate. message TacFilters {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 19 19:32:06 UTC 2023 - 1.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/hardwares/simple_hardware.h
#define TENSORFLOW_COMPILER_MLIR_LITE_EXPERIMENTAL_TAC_HARDWARES_SIMPLE_HARDWARE_H_ #include "tensorflow/compiler/mlir/lite/experimental/tac/hardwares/target_hardware.h" namespace mlir { namespace TFL { namespace tac { // A simple hardware is an interface makes you add a target backend easily if // you don't want too much customization. // // It allows you to easily specify the ops capabilities (by
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jul 21 01:22:53 UTC 2021 - 2.5K bytes - Viewed (0)