diff options
author | Stéphane Marchesin <marcheu@chromium.org> | 2012-08-25 14:42:55 -0700 |
---|---|---|
committer | Stéphane Marchesin <marcheu@chromium.org> | 2012-08-25 14:44:32 -0700 |
commit | 128b257aeef70cfca0e897fbc49581cba13bde6b (patch) | |
tree | 1f0026ae7a8770401bda41d4aa25ce70aa4f38ad | |
parent | fc98e98591590dbc1bdad08774c7f3fad1c42ecd (diff) |
Add comments from Martin Peres <martin.peres@labri.fr>
-rw-r--r-- | linuxgraphicsdrivers.lyx | 21 |
1 files changed, 16 insertions, 5 deletions
diff --git a/linuxgraphicsdrivers.lyx b/linuxgraphicsdrivers.lyx index 9110e59..2d51b7c 100644 --- a/linuxgraphicsdrivers.lyx +++ b/linuxgraphicsdrivers.lyx @@ -1317,7 +1317,7 @@ reference "sec:Virtual-and-Physical" It allows taking a (non contiguous) set of physical memory pages out of system memory and exposing it to the GPU for its use as a contiguous area. This increases the amount of memory usable by the GPU at little cost, and - creates an convenient area for sharing data between the CPU and the GPU + creates a convenient area for sharing data between the CPU and the GPU (AGP graphics cards can do fast DMA to/from this area, and since the GART area is a chunk of system RAM, CPU access is a lot faster than VRAM). One notable drawback is that the GART area is not coherent, and therefore @@ -3147,7 +3147,7 @@ MMIO MMIO is the most direct access to the card. A range of addresses is exposed to the CPU, where each write goes directly to the GPU. - This allows the simplest for of communication of commands from the CPU + This allows the simplest form of communication of commands from the CPU to the GPU. This type of programming is synchronous; writes are done by the CPU and executed on the GPU in a lockstep fashion. @@ -3771,7 +3771,7 @@ status open \begin_layout Plain Layout \lang english -aide à faire des figures : http://www.texample.net/tikz/examples/ +Tikz documentation : http://www.texample.net/tikz/examples/ \end_layout \end_inset @@ -5548,7 +5548,7 @@ The kernel has the ability to move memory areas around to handle high memory \begin_layout Itemize If the hardware has complete memory protection and virtualization, then it is possible to page in memory resources into the GPU as they get allocated - and isolate the per-process. + and isolate them per-process. Therefore not much is required to support memory protection of GPU memory. \end_layout @@ -5666,7 +5666,18 @@ Also, on embedded or old hardware, it is common to have encoders and connectors \begin_layout Standard \lang english -+++ Ajouter ici un schema crtc-encoder-connector +\begin_inset Note Note +status open + +\begin_layout Plain Layout + +\lang english +Here add a crtc-encoder-connector figure +\end_layout + +\end_inset + + \end_layout \begin_layout Section |