diff mbox series

[wwwdocs] gcc-16/changes.html - GCN: offload launch overhead reduced

Message ID c54fb9ba-b8eb-4552-a97c-3549875a63cc@baylibre.com
State New
Headers
Series [wwwdocs] gcc-16/changes.html - GCN: offload launch overhead reduced |

Checks

Context Check Description
linaro-tcwg-bot/tcwg_gcc_build--master-aarch64 fail Patch failed to apply
linaro-tcwg-bot/tcwg_gcc_build--master-arm fail Patch failed to apply

Commit Message

Tobias Burnus April 8, 2026, 2:12 p.m. UTC 
  I am not quite sure where to put it - generic, OpenMP/OpenACC language,
but settled for AMD GPU.
I am also not sure how to word it best, one wording variant is attached.

Comments - better suggestions?
OK?

Tobias

Comments

Sandra Loosemore April 9, 2026, 10:52 p.m. UTC | #1 
On 4/8/26 08:12, Tobias Burnus wrote:
> I am not quite sure where to put it - generic, OpenMP/OpenACC language,
> but settled for AMD GPU.
> I am also not sure how to word it best, one wording variant is attached.
> 
> Comments - better suggestions?
> OK?

The wording looks fine to me, but I'd put this either before or after 
the two existing <li> for AMD instead of sandwiched in the middle.

-Sandra
diff mbox series

Patch

gcc-16/changes.html - GCN: offload launch overhead reduced

diff --git a/htdocs/gcc-16/changes.html b/htdocs/gcc-16/changes.html
index a921e805..500ab53a 100644
--- a/htdocs/gcc-16/changes.html
+++ b/htdocs/gcc-16/changes.html
@@ -436,6 +436,8 @@  struct Affected : E
   <li>Experimental support for AMD Instinct MI300 (<code>gfx942</code>) devices
       has been added, including the generic <code>gfx9-4-generic</code> and
       mostly compatible <code>gfx950</code>.</li>
+  <li>For offloading to AMD GPUs: The launch overhead of OpenMP target regions
+      and OpenACC compute regions has been drastically reduced.</li>
   <li>By default, the following multilibs are now built: <code>gfx908</code>,
       <code>gfx90a</code>, <code>gfx9-generic</code>,
       <code>gfx9-4-generic</code>, <code>gfx10-3-generic</code>, and