generated from yandexdataschool/sphinx-lesson-template
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
2 changed files
with
36 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,13 @@ | ||
# Базовые концепты и написание простого ядра | ||
|
||
> Simple kernel — `hello world` на CUDA aka `elementwise add` с разбором, базовая линейная индексация без разбивки на блоки | ||
## Модель вычислений | ||
|
||
* GPU — отдельное устройство, выполняющее свой (специально для него написанный) код. | ||
* CPU ставит задачи, загружает/выгружает данные и ждёт завершения выполнения (синхронизация). | ||
|
||
## Модель памяти | ||
|
||
* RAM/VRAM — два вида памяти для CPU/GPU. | ||
* Специальные команды для обмена данными (`cudaMemCpy*[Async]`), в которых `cudaMemcpyKind` определяет направление копирования. |