cuda-api-wrappers
Thin C++-flavored wrappers for the CUDA Runtime API
cuda::profiling::range Namespace Reference

definitions related to profiled ranges and the range_t class More...

Typedefs

using handle_t = nvtxRangeId_t
 The raw handle of a CUDA profiling range.
 

Enumerations

enum  type_t {
  unspecified,
  kernel,
  pci_express_transfer
}
 Types of profiled ranges we recognize. More...
 

Detailed Description

definitions related to profiled ranges and the range_t class

Enumeration Type Documentation

◆ type_t

Types of profiled ranges we recognize.

Note
The profiler itself does not distinguish between these types of ranges; we use them for different styling