ed
a6229e9308
5-post thread, 2 JPGs, 2023-08-03. SPC: 8-deep swap all aliasing same BO (image) fixes Game Mode crash with external display. Pipelined load: 2 ms to black screen; 460 ms to allocate 4 GiB GTT video RAM; 558 ms to copy 256 MiB cart from page cache to USWC (page faults), all in parallel. Cold-launch worst case (cache cleared): 1.5 sec to read 256 MiB from stock SSD; no compile after this, 'literally in game at this point.' 3-thread load: (1.) X11 then spin present/ keyboard, (2.) AMDgpu device open + SDMA after CART read then dispatch, (3.) CART disk->USWC GTT read(). SSD needs linear reads to be fast so don't manually thread read(). Sibling to SPC project intro (1687257354490818561).
1.9 KiB
title, author, handle, post_url, post_id, timestamp, post_count, reply_count, repost_count, like_count, view_count
| title | author | handle | post_url | post_id | timestamp | post_count | reply_count | repost_count | like_count | view_count |
|---|---|---|---|---|---|---|---|---|---|---|
| SPC: Using 8 deep swap all aliasing same BO (image) fixes Game Mode crash with e | NOTimothyLottes | @NOTimothyLottes | https://x.com/NOTimothyLottes/status/1687062786273062912 | 1687062786273062912 | 2023-08-03 11:28:07 | 5 | 1 | 1 | 4 | 654 |
@NOTimothyLottes — SPC: Using 8 deep swap all aliasing same BO (image) fixes Game Mode crash with e
Post 1 (2023-08-03 11:28:07)
SPC: Using 8 deep swap all aliasing same BO (image) fixes Game Mode crash with external display. Pipelined load gets to black screen in 2 ms. Takes 460 ms to allocate 4 GiB GTT video ram, 558 ms to copy 256 MiB cart from page cache to USWC (page faults), all in parallel.
Post 2 (2023-08-03 11:40:20) — reply to Post 1
Clearing page cache to simulate a cold launch: Takes 1.5 sec to read 256 MiB from the stock SSD. This is worst case load time in desktop mode. Won't be any compile/etc after this. So literally in game at this point. Speed of light. This is how it is done.
Post 3 (2023-08-03 11:41:23) — reply to Post 2
Forgot the timing capture ... Load from SSD.
Post 4 (2023-08-03 11:50:33) — reply to Post 3
There are only 3 threads on load: (1.) to open X11 then spin doing present/keyboard, (2.) to open the AMDgpu device, SDMA copy after CART read, and then eventually spin doing dispatchs, (3.) one to load the CART from disk to mapped USWC GTT via read().
Post 5 (2023-08-03 11:53:14) — reply to Post 4
Something I don't know: does read() since it's kernel- side automatically get some multi-core parallelism? Not a good idea to manually thread the read() because SSD needs linear reads to be fast. Not possible to know if the reads are page cache hits in advance either ...