Show / Hide Table of Contents

Enum cudaDataType_t

The cudaDataType_t type is an enumerant to specify the data precision. It is used when the data reference does not carry the type itself (e.g void *) Complete documentation on Nvidia documentation

Namespace: Hybridizer.Runtime.CUDAImports
Assembly: Hybridizer.Runtime.CUDAImports.dll
Syntax
[IntrinsicType("cudaDataType_t")]
public enum cudaDataType_t

Fields

Name Description
CUDA_C_16F = 6

complex as a pair of half

CUDA_C_32F = 4

complex as a pair of float

CUDA_C_32I = 11

complex as a pair of signed int

CUDA_C_32U = 13

complex as a pair of unsigned int numbers

CUDA_C_64F = 5

complex as a pair of double

CUDA_C_8I = 7

complex as a pair of signed char

CUDA_C_8U = 9

complex as a pair of unsigned char

CUDA_R_16F = 2

read as a half

CUDA_R_32F = 0

real as a float

CUDA_R_32I = 10

real as a signed int

CUDA_R_32U = 12

real as an unsigned int

CUDA_R_64F = 1

real as a double

CUDA_R_8I = 3

real as a signed char

CUDA_R_8U = 8

real as an unsigned char

Back to top Generated by DocFX