[gpu/NVDRV] Finalize, improve AllocObjCtx #333

Merged
CamilleLaVey merged 5 commits from finalize-improve-allocObjCtx into master 2025-08-31 07:32:55 +02:00
Member

Improves object allocation per channel, only allowing max amount of 6 objects contexts per channel.
Previously objects were stored in a heap allocated vector which is sub-optimal for performance reasons.
The new implementation instead uses a stack based array with a O(1) approach.
This should boost performance in games which heavily rely on object context creation.

Improves object allocation per channel, only allowing max amount of 6 objects contexts per channel. Previously objects were stored in a heap allocated vector which is sub-optimal for performance reasons. The new implementation instead uses a stack based array with a O(1) approach. This should boost performance in games which heavily rely on object context creation.
crueter approved these changes 2025-08-28 01:33:54 +02:00
Dismissed
SDK-Chan dismissed crueter's review 2025-08-28 17:24:16 +02:00
Reason:

New commits pushed, approval review dismissed automatically according to repository settings

Lizzie reviewed 2025-08-28 21:57:30 +02:00
@ -132,6 +132,7 @@ void nvhost_gpu::OnOpen(NvCore::SessionId session_id, DeviceFD fd) {
void nvhost_gpu::OnClose(DeviceFD fd) {
sessions.erase(fd);
std::scoped_lock lk(channel_mutex);
Member

consider shared_lock and unique_lock?
misplaced?

consider shared_lock and unique_lock? misplaced?
SDK-Chan marked this conversation as resolved
JPikachu force-pushed finalize-improve-allocObjCtx from 27521818a9 to 8d778ed7f5 2025-08-29 17:42:29 +02:00 Compare
CamilleLaVey force-pushed finalize-improve-allocObjCtx from 8d778ed7f5 to a755043177 2025-08-30 06:29:28 +02:00 Compare
crueter approved these changes 2025-08-31 07:15:00 +02:00
CamilleLaVey approved these changes 2025-08-31 07:32:42 +02:00
CamilleLaVey merged commit 8dba6a2cb4 into master 2025-08-31 07:32:55 +02:00
CamilleLaVey deleted branch finalize-improve-allocObjCtx 2025-08-31 07:32:55 +02:00
Sign in to join this conversation.
No description provided.