ed/manual_slop
Private
Public Access
0
0
Fork 0
Code Activity

docs(twitter): add 1858715434436227544 corpus (NOTimothyLottes NV front-buffer bringup + 'cart file' origin)

Browse Source 
8-post thread on NV-specific 1-deep swap with IMMEDIATE presentation,
after previous AMD-tuned impl stopped working. One descriptor set
always bound (resources static after init). Dropped
VK_DESCRIPTOR_SET_LAYOUT_CREATE_UPDATE_AFTER_BIND_POOL_BIT_EXT
('god awful naming length') to avoid NV indirection perf hit.
2700 lines of engine, embedded headers, one-file compile. 0.25 sec
hot-load on NV dGPU: 4 MiB 'cart' file from pagecache, 512 MiB GPU
buffer, all PSOs, image alloc, command buffer copy+clear. Load-time
parallelism: {instance create, cart map, TLB warming by walking pages,
window bringup} = 0.08 sec. After VK device, signal background SPIR-V
load while building descriptor set layout, then PSO compile
parallel. Earliest documented use of 'cart file' term - 9 months
before the Aug 2025 public announcement.
This commit is contained in:
ed
2026-07-27 01:48:44 -04:00
parent d3460e3b53
commit a9335928c7
2 changed files with 181 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/twitter/1858715434436227544/thread.md
+47
View File
@@ -0,0 +1,47 @@
---
title: "After VK device is open, I signal a background thread to load the SPIR-V module,"
author: "NOTimothyLottes"
handle: "@NOTimothyLottes"
post_url: "https://x.com/NOTimothyLottes/status/1858715434436227544"
post_id: "1858715434436227544"
timestamp: "2024-11-19 03:34:27"
post_count: 8
reply_count: 0
repost_count: 0
like_count: 2
view_count: 424
---
# @NOTimothyLottes — After VK device is open, I signal a background thread to load the SPIR-V module,
## Post 1 (2024-11-19 03:10:28)
Working towards a new bring up of front-buffering on NV via VK. My last implementation had been tuned on AMD and didn't work on NV any more. NV does seem to accept a 1-deep swap with IMMEDIATE presentation at least on latest drivers, so that is a good start.
## Post 2 (2024-11-19 03:13:21) — reply to Post 1
Since my image resources are static after init time, only swap images change when the driver kills the swap chain (which once upon a time seemed to happen on ALT+TAB maybe). So it's one descriptor set always bound.
## Post 3 (2024-11-19 03:15:43) — reply to Post 2
Stopped using VK_DESCRIPTOR_SET_LAYOUT_CREATE_UPDATE_AFTER_BIND_POOL_BIT_EXT (god awful naming length people), because I think it could be a perf hit on NV due to extra indirection. NV driver is free to bake down the single set now before the command buffer is sent over.
## Post 4 (2024-11-19 03:21:26) — reply to Post 3
At this stage, to the point of having everything loaded and swap chain created, it's 2700 lines of engine code. That includes embedding headers (no external includes), so it's a one file compile. People claim rolling your own engine is hard? Not really if you keep it focused.
## Post 5 (2024-11-19 03:26:46) — reply to Post 4
So far it's a 0.25 sec hot load time on this NV dGPU laptop. Includes mapping a 4 MiB 'cart' file from pagecache, doing a 512 MiB buffer for GPU usage, hits on all PSOs, allocating some images, and kicking the command buffer that copies in the cart, and clears everything.
## Post 6 (2024-11-19 03:29:11) — reply to Post 5
Everything at load-time is multi-threaded to try to minimize start to in-game time. This is in sharp contrast to runtime where the only multi-threading being used is to separate things that are blocking.
## Post 7 (2024-11-19 03:32:22) — reply to Post 6
I get some utility on parallelizing {vulkan instance creation, mapping the cart file, warming the TLBs by walking all the pages, bringing up the window} it's about 0.08 seconds in at that point
## Post 8 (2024-11-19 03:34:27) — reply to Post 7
After VK device is open, I signal a background thread to load the SPIR-V module, while building the descriptor set layout, which then unblocks PSO compile on background threads. And the rest of the VK setup runs in parallel. Working towards swap creation.
docs/twitter/1858715434436227544/thread_data.json
+134
View File
@@ -0,0 +1,134 @@
{
"root_post_id": "1858715434436227544",
"posts": [
{
"post_id": "1858709400791261630",
"author": "NOTimothyLottes",
"handle": "NOTimothyLottes",
"text": "Working towards a new bring up of front-buffering on NV via VK. My last implementation had been tuned on AMD and didn't work on NV any more. NV does seem to accept a 1-deep swap with IMMEDIATE presentation at least on latest drivers, so that is a good start.",
"timestamp": "2024-11-19 03:10:28",
"media_urls": [],
"reply_to_id": null,
"quote_of_id": null,
"metrics": {
"reply_count": 1,
"repost_count": 0,
"like_count": 2,
"view_count": 686
}
},
{
"post_id": "1858710122727391666",
"author": "NOTimothyLottes",
"handle": "NOTimothyLottes",
"text": "Since my image resources are static after init time, only swap images change when the driver kills the swap chain (which once upon a time seemed to happen on ALT+TAB maybe). So it's one descriptor set always bound.",
"timestamp": "2024-11-19 03:13:21",
"media_urls": [],
"reply_to_id": "1858709400791261630",
"quote_of_id": null,
"metrics": {
"reply_count": 1,
"repost_count": 0,
"like_count": 0,
"view_count": 86
}
},
{
"post_id": "1858710719018979651",
"author": "NOTimothyLottes",
"handle": "NOTimothyLottes",
"text": "Stopped using VK_DESCRIPTOR_SET_LAYOUT_CREATE_UPDATE_AFTER_BIND_POOL_BIT_EXT (god awful naming length people), because I think it could be a perf hit on NV due to extra indirection. NV driver is free to bake down the single set now before the command buffer is sent over.",
"timestamp": "2024-11-19 03:15:43",
"media_urls": [],
"reply_to_id": "1858710122727391666",
"quote_of_id": null,
"metrics": {
"reply_count": 1,
"repost_count": 0,
"like_count": 0,
"view_count": 105
}
},
{
"post_id": "1858712158004994552",
"author": "NOTimothyLottes",
"handle": "NOTimothyLottes",
"text": "At this stage, to the point of having everything loaded and swap chain created, it's 2700 lines of engine code. That includes embedding headers (no external includes), so it's a one file compile. People claim rolling your own engine is hard? Not really if you keep it focused.",
"timestamp": "2024-11-19 03:21:26",
"media_urls": [],
"reply_to_id": "1858710719018979651",
"quote_of_id": null,
"metrics": {
"reply_count": 1,
"repost_count": 0,
"like_count": 2,
"view_count": 101
}
},
{
"post_id": "1858713499716694264",
"author": "NOTimothyLottes",
"handle": "NOTimothyLottes",
"text": "So far it's a 0.25 sec hot load time on this NV dGPU laptop. Includes mapping a 4 MiB 'cart' file from pagecache, doing a 512 MiB buffer for GPU usage, hits on all PSOs, allocating some images, and kicking the command buffer that copies in the cart, and clears everything.",
"timestamp": "2024-11-19 03:26:46",
"media_urls": [],
"reply_to_id": "1858712158004994552",
"quote_of_id": null,
"metrics": {
"reply_count": 1,
"repost_count": 0,
"like_count": 0,
"view_count": 98
}
},
{
"post_id": "1858714108415119495",
"author": "NOTimothyLottes",
"handle": "NOTimothyLottes",
"text": "Everything at load-time is multi-threaded to try to minimize start to in-game time. This is in sharp contrast to runtime where the only multi-threading being used is to separate things that are blocking.",
"timestamp": "2024-11-19 03:29:11",
"media_urls": [],
"reply_to_id": "1858713499716694264",
"quote_of_id": null,
"metrics": {
"reply_count": 1,
"repost_count": 0,
"like_count": 3,
"view_count": 105
}
},
{
"post_id": "1858714908516381114",
"author": "NOTimothyLottes",
"handle": "NOTimothyLottes",
"text": "I get some utility on parallelizing {vulkan instance creation, mapping the cart file, warming the TLBs by walking all the pages, bringing up the window} it's about 0.08 seconds in at that point",
"timestamp": "2024-11-19 03:32:22",
"media_urls": [],
"reply_to_id": "1858714108415119495",
"quote_of_id": null,
"metrics": {
"reply_count": 1,
"repost_count": 0,
"like_count": 1,
"view_count": 443
}
},
{
"post_id": "1858715434436227544",
"author": "NOTimothyLottes",
"handle": "NOTimothyLottes",
"text": "After VK device is open, I signal a background thread to load the SPIR-V module, while building the descriptor set layout, which then unblocks PSO compile on background threads. And the rest of the VK setup runs in parallel. Working towards swap creation.",
"timestamp": "2024-11-19 03:34:27",
"media_urls": [],
"reply_to_id": "1858714908516381114",
"quote_of_id": null,
"metrics": {
"reply_count": 0,
"repost_count": 0,
"like_count": 2,
"view_count": 424
}
}
],
"source_url": "https://x.com/NOTimothyLottes/status/1858715434436227544"
}