OpenVDB  10.0.1
Classes | Namespaces | Macros | Functions
CudaDeviceBuffer.h File Reference

Implements a simple CUDA allocator! More...

#include "HostBuffer.h"
#include <cuda_runtime_api.h>

Go to the source code of this file.

Classes

class  CudaDeviceBuffer
 Simple memory buffer using un-managed pinned host memory when compiled with NVCC. Obviously this class is making explicit used of CUDA so replace it with your own memory allocator if you are not using CUDA. More...
 
struct  BufferTraits< CudaDeviceBuffer >
 

Namespaces

 nanovdb
 

Macros

#define cudaCheck(ans)
 
#define checkPtr(ptr, msg)
 

Functions

static void gpuAssert (cudaError_t, const char *, int, bool=true)
 
static void ptrAssert (void *, const char *, const char *, int, bool=true)
 

Detailed Description

Implements a simple CUDA allocator!

Author
Ken Museth
Date
January 8, 2020
  CudaDeviceBuffer - a class for simple cuda buffer allocation and management

Macro Definition Documentation

#define checkPtr (   ptr,
  msg 
)
Value:
{ \
ptrAssert((ptr), (msg), __FILE__, __LINE__); \
}
#define cudaCheck (   ans)
Value:
{ \
gpuAssert((ans), __FILE__, __LINE__); \
}

Function Documentation

static void gpuAssert ( cudaError_t  ,
const char *  ,
int  ,
bool  = true 
)
inlinestatic
static void ptrAssert ( void *  ,
const char *  ,
const char *  ,
int  ,
bool  = true 
)
inlinestatic