Translations:OpenACC Tutorial - Adding directives/50/en: Difference between revisions
(Importing a new version from external source) |
(Importing a new version from external source) |
||
(One intermediate revision by the same user not shown) | |||
Line 1: | Line 1: | ||
The NVidia compilers use the < | The NVidia compilers use the <code>-acc</code> (target accelerator) option to enable compilation for an accelerator. | ||
We use the sub-option <code>-gpu=managed</code> to tell the compiler that we want to use [https://developer.nvidia.com/blog/unified-memory-cuda-beginners/ managed memory]. | |||
This ''managed memory'' simplifies the process of transferring data to and from the device. | |||
We will remove this option in a later example. | |||
We also use the option <code>-fast</code>, which is an optimization option. |
Latest revision as of 13:04, 16 May 2023
The NVidia compilers use the -acc
(target accelerator) option to enable compilation for an accelerator.
We use the sub-option -gpu=managed
to tell the compiler that we want to use managed memory.
This managed memory simplifies the process of transferring data to and from the device.
We will remove this option in a later example.
We also use the option -fast
, which is an optimization option.