List of all items

Structs

• CudaRust
• backend::backend_trait::BackendCapabilities
• backend::native_gpu::NativeGPUBackend
• backend::wasm_runtime::WasmRuntime
• backend::webgpu::WebGPUBackend
• backend::webgpu_optimized::AutoTuneResult
• backend::webgpu_optimized::BackendStats
• backend::webgpu_optimized::CachedKernel
• backend::webgpu_optimized::OptimizedWebGPUBackend
• backend::webgpu_optimized::WebGPUConfig
• kernel::shared_memory::BankConflictDetector
• kernel::shared_memory::DynamicSharedMemory
• kernel::shared_memory::SharedMemory
• kernel::warp::WarpState
• memory::SharedMemory
• memory::device_memory::DeviceBuffer
• memory::device_memory::DevicePtr
• memory::host_memory::HostBuffer
• memory::memory_pool::KernelMemoryManager
• memory::memory_pool::MemoryPool
• memory::memory_pool::PoolConfig
• memory::memory_pool::PoolStats
• memory::texture_memory::TextureDescriptor
• memory::texture_memory::TextureMemory
• memory::unified_memory::ManagedMemory
• memory::unified_memory::UnifiedMemory
• neural_integration::BatchProcessor
• neural_integration::BridgeConfig
• neural_integration::BufferHandle
• neural_integration::CompiledKernel
• neural_integration::DeviceInfo
• neural_integration::MemoryHandle
• neural_integration::MemoryStats
• neural_integration::NeuralBridge
• neural_integration::OperationHandle
• neural_integration::OperationStats
• neural_integration::PerformanceDegradation
• neural_integration::PerformanceStats
• neural_integration::SystemCapabilities
• neural_integration::benchmarks::BenchmarkResult
• neural_integration::benchmarks::BenchmarkSuite
• neural_integration::bridge::WebGpuBackend
• neural_integration::cuda_kernels::KernelConfig
• neural_integration::cuda_kernels::LaunchParams
• neural_integration::cuda_kernels::OptimizedKernels
• neural_integration::memory_manager::HybridMemoryManager
• neural_integration::memory_manager::NoOpMemoryManager
• neural_integration::performance_monitor::BottleneckAnalysis
• neural_integration::performance_monitor::MonitorConfig
• neural_integration::performance_monitor::NoOpMonitor
• neural_integration::performance_monitor::PerformanceTrend
• neural_integration::performance_monitor::RealTimeMonitor
• nutanix::config::DeploymentConfig
• nutanix::config::GpuClusterSummary
• nutanix::config::GpuInfo
• nutanix::config::GpuNode
• nutanix::config::HostCapabilities
• nutanix::config::NutanixConfig
• nutanix::deployment::DeploymentGenerator
• nutanix::discovery::NutanixClient
• nutanix::discovery::PrismBuildInfo
• nutanix::discovery::PrismClusterConfig
• nutanix::discovery::PrismClusterEntity
• nutanix::discovery::PrismClusterResources
• nutanix::discovery::PrismClusterStatus
• nutanix::discovery::PrismControllerVm
• nutanix::discovery::PrismEntityMetadata
• nutanix::discovery::PrismGpuInfo
• nutanix::discovery::PrismHostEntity
• nutanix::discovery::PrismHostResources
• nutanix::discovery::PrismHostStatus
• nutanix::discovery::PrismHypervisor
• nutanix::discovery::PrismListResponse
• nutanix::discovery::PrismMetadata
• nutanix::discovery::PrismReference
• nutanix::monitoring::Alert
• nutanix::monitoring::CapacityForecast
• nutanix::monitoring::GpuMetrics
• nutanix::monitoring::GpuMonitor
• nutanix::monitoring::NodeHealth
• nutanix::nc2::CostEstimate
• nutanix::nc2::Nc2Client
• nutanix::nc2::Nc2Cluster
• nutanix::nc2::WorkloadPlacement
• nutanix::vgpu_scheduler::MigrationPlan
• nutanix::vgpu_scheduler::ScheduleResult
• nutanix::vgpu_scheduler::VgpuScheduler
• nutanix::vgpu_scheduler::WorkloadRequest
• parser::ast::Ast
• parser::ast::Block
• parser::ast::FunctionDef
• parser::ast::GlobalVar
• parser::ast::KernelDef
• parser::ast::Parameter
• parser::ast::TextureType
• parser::ast::TypeDef
• parser::ast::VectorType
• parser::cuda_parser::CudaParser
• parser::kernel_extractor::KernelInfo
• parser::lexer::SpannedToken
• parser::ptx_parser::PtxFunction
• parser::ptx_parser::PtxInstruction
• parser::ptx_parser::PtxModule
• parser::ptx_parser::PtxPredicate
• parser::ptx_parser::PtxRegDecl
• parser::ptx_parser::PtxVariable
• profiling::GlobalProfiler
• profiling::PerformanceCounter
• profiling::ProfileMetrics
• profiling::ScopedTimer
• profiling::kernel_profiler::KernelComparison
• profiling::kernel_profiler::KernelProfiler
• profiling::kernel_profiler::KernelStats
• profiling::kernel_profiler::KernelTimer
• profiling::kernel_profiler::RooflineAnalysis
• profiling::kernel_profiler::RooflineModel
• profiling::memory_profiler::AllocationEvent
• profiling::memory_profiler::FragmentationAnalysis
• profiling::memory_profiler::MemoryPressureEvent
• profiling::memory_profiler::MemoryPressureMonitor
• profiling::memory_profiler::MemoryProfiler
• profiling::performance_monitor::CounterStats
• profiling::performance_monitor::Measurement
• profiling::performance_monitor::MonitorConfig
• profiling::performance_monitor::PerformanceMonitor
• profiling::performance_monitor::PerformanceReport
• profiling::performance_monitor::Timer
• profiling::runtime_profiler::BottleneckAnalysis
• profiling::runtime_profiler::OperationEvent
• profiling::runtime_profiler::OperationStats
• profiling::runtime_profiler::OperationTimer
• profiling::runtime_profiler::OptimizationSuggestions
• profiling::runtime_profiler::RuntimeProfiler
• profiling::runtime_profiler::Suggestion
• runtime::KernelContext
• runtime::Runtime
• runtime::async_pipeline::AsyncPipeline
• runtime::async_pipeline::PipelineBatch
• runtime::async_pipeline::PipelineEvent
• runtime::async_pipeline::PipelineOp
• runtime::async_pipeline::PipelineTimeline
• runtime::async_pipeline::PipelineUtilization
• runtime::benchmark::BenchmarkResult
• runtime::benchmark::BenchmarkRunner
• runtime::benchmark::BenchmarkSuite
• runtime::bfloat16::BFloat16
• runtime::coalescing::AccessRecorder
• runtime::coalescing::AccessSummary
• runtime::coalescing::CoalescingReport
• runtime::coalescing::MemoryAccess
• runtime::cooperative_groups::CooperativeGroup
• runtime::cooperative_groups::GridGroup
• runtime::cooperative_groups::ThreadBlockGroup
• runtime::cooperative_groups::TiledPartition
• runtime::cuda_graph::CudaGraph
• runtime::cuda_graph::GraphExec
• runtime::cuda_graph::GraphExecResult
• runtime::cuda_graph::GraphNode
• runtime::cuda_graph::NodeExecResult
• runtime::device::Device
• runtime::device::DeviceProperties
• runtime::dynamic_parallelism::ChildLaunch
• runtime::dynamic_parallelism::DynamicParallelismContext
• runtime::event::Event
• runtime::flash_attention::FlashAttention
• runtime::flash_attention::FlashAttentionConfig
• runtime::flash_attention::FlashAttentionOutput
• runtime::flash_attention::MemorySavings
• runtime::grid::Block
• runtime::grid::Dim3
• runtime::grid::Grid
• runtime::half::Half
• runtime::kernel::LaunchConfig
• runtime::kernel::ThreadContext
• runtime::kernel_fusion::FusedKernel
• runtime::kernel_fusion::FusionAnalyzer
• runtime::kernel_fusion::FusionNode
• runtime::kernel_fusion::FusionResult
• runtime::multi_gpu::DeviceRange
• runtime::multi_gpu::MultiGpuContext
• runtime::occupancy::BlockSizeSuggestion
• runtime::occupancy::GpuArchSpec
• runtime::occupancy::KernelResources
• runtime::occupancy::OccupancyResult
• runtime::quantization::QuantError
• runtime::quantization::QuantParams
• runtime::stream::Stream
• runtime::tensor_ops::Fragment
• runtime::tensor_ops::FragmentShape
• runtime::tensor_ops::GemmStats
• runtime::tensor_ops::TensorCoreEngine
• simd::detection::SimdCapabilities
• transpiler::CudaTranspiler
• transpiler::Transpiler
• transpiler::ast::Function
• transpiler::ast::Program
• transpiler::builtin_functions::BuiltinMapper
• transpiler::code_generator::CodeGenerator
• transpiler::kernel_translator::KernelTranslator
• transpiler::memory_mapper::MemoryMapper
• transpiler::memory_mapper::MemoryMapping
• transpiler::type_converter::TypeConverter
• transpiler::wgsl::WgslGenerator

Enums

• backend::backend_trait::MemcpyKind
• backend::native_gpu::GpuApi
• error::CudaRustError
• memory::texture_memory::AddressMode
• memory::texture_memory::FilterMode
• neural_integration::ActivationFunction
• neural_integration::BindingType
• neural_integration::GpuDevice
• neural_integration::NeuralIntegrationError
• neural_integration::NeuralOperation
• neural_integration::Precision
• neural_integration::performance_monitor::BottleneckType
• nutanix::config::GpuModel
• nutanix::config::GpuVendor
• nutanix::monitoring::AlertSeverity
• nutanix::monitoring::HealthStatus
• nutanix::nc2::CloudProvider
• nutanix::nc2::ClusterStatus
• nutanix::nc2::MigrationStatus
• nutanix::vgpu_scheduler::SchedulingPolicy
• nutanix::vgpu_scheduler::VgpuProfile
• parser::ast::BinaryOp
• parser::ast::Dimension
• parser::ast::Expression
• parser::ast::FloatType
• parser::ast::FunctionQualifier
• parser::ast::IntType
• parser::ast::Item
• parser::ast::KernelAttribute
• parser::ast::Literal
• parser::ast::ParamQualifier
• parser::ast::Statement
• parser::ast::StorageClass
• parser::ast::TextureDim
• parser::ast::Type
• parser::ast::UnaryOp
• parser::ast::WarpOp
• parser::lexer::Token
• parser::ptx_parser::PtxDirective
• parser::ptx_parser::PtxOperand
• parser::ptx_parser::PtxSpace
• parser::ptx_parser::PtxStatement
• parser::ptx_parser::PtxType
• profiling::memory_profiler::AllocationType
• profiling::memory_profiler::PressureLevel
• profiling::performance_monitor::CounterType
• profiling::runtime_profiler::OperationType
• profiling::runtime_profiler::SuggestionCategory
• profiling::runtime_profiler::SuggestionSeverity
• runtime::async_pipeline::PipelineStage
• runtime::coalescing::AccessPattern
• runtime::cuda_graph::MemcpyDirection
• runtime::cuda_graph::NodeKind
• runtime::cuda_graph::NodeState
• runtime::device::BackendType
• runtime::kernel_fusion::BinaryOp
• runtime::kernel_fusion::FusableOp
• runtime::kernel_fusion::MemOp
• runtime::kernel_fusion::PrecisionType
• runtime::kernel_fusion::ReduceOp
• runtime::kernel_fusion::UnaryOp
• runtime::occupancy::LimitingFactor
• runtime::quantization::QuantBits
• runtime::quantization::QuantScheme
• runtime::tensor_ops::MmaPrecision
• simd::detection::SimdLevel
• transpiler::ast::Expr
• transpiler::ast::ForInit
• transpiler::ast::Stmt
• transpiler::kernel_translator::KernelPattern

Traits

• backend::backend_trait::BackendTrait
• neural_integration::GpuBackendTrait
• neural_integration::MemoryManagerTrait
• neural_integration::PerformanceMonitorTrait
• runtime::dynamic_parallelism::ChildKernel
• runtime::kernel::KernelFunction

Macros

• kernel::kernel_function
• kernel_function
• memory_error
• parse_error
• profile_scope
• runtime_error
• time_block
• translation_error

Functions

• backend::get_backend
• backend::native_gpu::is_cuda_available
• backend::native_gpu::is_rocm_available
• backend::native_gpu::is_vulkan_available
• init
• memory::memory_pool::allocate
• memory::memory_pool::deallocate
• memory::memory_pool::global_pool
• memory::memory_pool::global_stats
• memory::unified_memory::allocate_unified
• neural_integration::benchmarks::run_quick_benchmark
• neural_integration::bridge::execute_cpu_fallback
• neural_integration::bridge::extract_wgsl_from_rust
• neural_integration::examples::batch_processing_example
• neural_integration::examples::custom_kernel_example
• neural_integration::examples::error_handling_example
• neural_integration::examples::matrix_operations_example
• neural_integration::examples::neural_network_example
• neural_integration::examples::performance_benchmark_example
• neural_integration::examples::run_all_examples
• neural_integration::examples::training_simulation_example
• neural_integration::get_capabilities
• neural_integration::gpu_neural_ops::execute_operation
• neural_integration::gpu_neural_ops::process_batch
• neural_integration::initialize
• nutanix::deployment::gpu_resource_key
• parser::kernel_extractor::extract_device_functions
• parser::kernel_extractor::extract_kernel_by_name
• parser::kernel_extractor::extract_kernels
• parser::lexer::tokenize
• parser::parse
• parser::ptx_parser::parse_ptx
• parser::ptx_parser::ptx_to_ast
• profiling::performance_monitor::global_monitor
• profiling::performance_monitor::global_report
• profiling::performance_monitor::record_measurement
• profiling::performance_monitor::time_operation
• runtime::benchmark::run_builtin_benchmarks
• runtime::bfloat16::bf16_dot
• runtime::bfloat16::bf16_gemm
• runtime::bfloat16::bf16_gemv
• runtime::bfloat16::bf16_to_f32_slice
• runtime::bfloat16::f32_to_bf16_slice
• runtime::block::dim
• runtime::block::index
• runtime::clear_kernel_context
• runtime::coalescing::analyze_warp_access
• runtime::coalescing::simulate_column_access
• runtime::coalescing::simulate_linear_access
• runtime::cooperative_groups::this_grid
• runtime::cooperative_groups::this_thread_block
• runtime::grid_dim::dim
• runtime::half::f32_to_half_slice
• runtime::half::half_dot
• runtime::half::half_gemv
• runtime::half::half_to_f32_slice
• runtime::kernel::launch_kernel
• runtime::memory::allocate
• runtime::memory::copy
• runtime::memory::free
• runtime::multi_gpu::memcpy_peer
• runtime::occupancy::calculate_occupancy
• runtime::occupancy::suggest_block_size
• runtime::quantization::dequantize_int4
• runtime::quantization::dequantize_int8
• runtime::quantization::quantization_error
• runtime::quantization::quantize_int4
• runtime::quantization::quantize_int8
• runtime::quantization::quantized_gemm_int8
• runtime::set_kernel_context
• runtime::sync_threads
• runtime::thread::index
• runtime::warp_intrinsics::all_sync
• runtime::warp_intrinsics::any_sync
• runtime::warp_intrinsics::ballot_sync
• runtime::warp_intrinsics::clz
• runtime::warp_intrinsics::exclusive_scan_sync
• runtime::warp_intrinsics::ffs
• runtime::warp_intrinsics::inclusive_scan_sync
• runtime::warp_intrinsics::lanemask_gt
• runtime::warp_intrinsics::lanemask_le
• runtime::warp_intrinsics::lanemask_lt
• runtime::warp_intrinsics::match_all_sync
• runtime::warp_intrinsics::match_any_sync
• runtime::warp_intrinsics::popc
• runtime::warp_intrinsics::reduce_add_sync
• runtime::warp_intrinsics::reduce_and_sync
• runtime::warp_intrinsics::reduce_max_sync
• runtime::warp_intrinsics::reduce_min_sync
• runtime::warp_intrinsics::reduce_or_sync
• runtime::warp_intrinsics::reduce_xor_sync
• runtime::with_kernel_context
• simd::matrix_ops::matrix_multiply_f32
• simd::vector_ops::vector_add_f32
• simd::vector_ops::vector_dot_f32
• simd::vector_ops::vector_mul_f32
• simd::vector_ops::vector_reduce_sum_f32
• simd::vector_ops::vector_scale_f32
• utils::calculate_block_size
• utils::calculate_grid_size
• utils::round_up

Type Aliases

• error::Result
• memory::texture_memory::SharedTexture
• memory::unified_memory::SharedUnifiedMemory
• neural_integration::NeuralResult
• neural_integration::wasm_types::WasmBridgeConfig
• runtime::cuda_graph::NodeId

Constants

• kernel::shared_memory::BANK_WIDTH_BYTES
• kernel::shared_memory::NUM_BANKS
• kernel::warp::WARP_SIZE
• runtime::warp_intrinsics::FULL_MASK
• runtime::warp_intrinsics::WARP_SIZE