[
https://issues.apache.org/jira/browse/ARROW-4861?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antoine Pitrou updated ARROW-4861:
----------------------------------
Description:
Exposing such a method could be useful to initialize a buffer without going
through a CPU-to-device memory copy.
For example CUDA expose several memset-like APIs to initialize GPU memory with
different initializer widths:
https://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__MEM.html#group__CUDA__MEM_1g6e582bf866e9e2fb014297bfaf354d7b
was:
One can define a device MemoryPool subclass (say, CudaMemoryPool) that can be
used for creating a Buffer representing a device memory. The prerequisite for
this to work is that all Buffer memory operations (allocation, deallocation,
reallocation, etc) can be redefined to use the corresponding device specific
operations. No host specific operation would be allowed as the device memory
would be inaccesible from host.
Currently, this is almost possible. Namely, `Buffer::ZeroPadding` uses host
specific `memset` function for zero-padding the allocated Buffer memory.
Suggestion: introduce a new method `MemoryPool::Memset` that
`Buffer::ZeroPadding` can use.
The Memset method would use `memset` by default but device specific MemoryPool
subclasses can override the method to use device driver version of the memset
function.
> [C++] Introduce MemoryManager::Memset method.
> ---------------------------------------------
>
> Key: ARROW-4861
> URL: https://issues.apache.org/jira/browse/ARROW-4861
> Project: Apache Arrow
> Issue Type: Improvement
> Components: C++
> Reporter: Pearu Peterson
> Assignee: Pearu Peterson
> Priority: Major
> Labels: C++
> Fix For: 2.0.0
>
>
> Exposing such a method could be useful to initialize a buffer without going
> through a CPU-to-device memory copy.
> For example CUDA expose several memset-like APIs to initialize GPU memory
> with different initializer widths:
> https://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__MEM.html#group__CUDA__MEM_1g6e582bf866e9e2fb014297bfaf354d7b
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
