 |
CUDAMemoryAllocate
gives CUDAMemory with specified type and single dimension.
gives CUDAMemory with specified type and dimensions.
更多信息
- The CUDALink application must be loaded using Needs["CUDALink`"].
- Possible types for
are: -
Integer Real Complex "Byte" "Bit16" "Integer32" "Byte[2]" "Bit16[2]" "Integer32[2]" "Byte[3]" "Bit16[3]" "Integer32[3]" "Byte[4]" "Bit16[4]" "Integer32[4]" "UnsignedByte" "UnsignedBit16" "UnsignedInteger" "UnsignedByte[2]" "UnsignedBit16[2]" "UnsignedInteger[2]" "UnsignedByte[3]" "UnsignedBit16[3]" "UnsignedInteger[3]" "UnsignedByte[4]" "UnsignedBit16[4]" "UnsignedInteger[4]" "Double" "Float" "Integer64" "Double[2]" "Float[2]" "Integer64[2]" "Double[3]" "Float[3]" "Integer64[3]" "Double[4]" "Float[4]" "Integer64[4]" - The following options can be given:
-
"Device" $CUDADevice CUDA device used in computation "TargetPrecision" Automatic precision used in computation
范例打开所有单元
基本范例 (4)
First, load the CUDALink application:
| In[1]:= |
This allocates a rank 3 tensor with each dimension 10:
| In[2]:= |
| Out[2]= |  |
Information about memory can be retrieved via CUDAMemoryInformation:
| In[3]:= |
| Out[3]= |  |
| In[4]:= |
For a single dimension, the length can be an integer:
| In[1]:= |
| Out[1]= |  |
Link CUDAMemoryLoad; different types are supported:
| In[1]:= |
| Out[1]= |  |
Adding memory as Real or Complex gets the type based on whether the device supports double precision or not:
| In[1]:= |
| Out[1]= |  |
In this case, the CUDA device has double-precision support:
| In[2]:= |
| Out[2]= |  |
The behavior can be forced to change by setting the 
:
| In[3]:= |
| Out[3]= |  |
