docs(twitter): add 2075769880092037309 corpus (NOTimothyLottes Vulkan queue-choice rethink)

4-post thread, highest-engagement NOTimothyLottes thread in the corpus (42 likes, 5063 views, 2 reposts). Don't search for the ideal {presentation,graphics,compute} queue - just use queue 0. AMD: render via compute on queue 0, present on queue 1, decouple for front-buffer racing. NVIDIA: queue 1 is DMA, queue 2 is compute; queue 0 = gfx + present, dispatch on queue 2 by default. Tangent: someone complaining about the bitmap font in Post 1 looking like a captcha.
2026-07-26 21:37:42 -04:00
parent ffc39fc6a2
commit b3e4c9c1c6
8 changed files with 119 additions and 0 deletions
@@ -0,0 +1,40 @@
+---
+title: "Rethinking Vulkan queue choice. Traditional double-buffered games might do somet"
+author: "NOTimothyLottes"
+handle: "@NOTimothyLottes"
+post_url: "https://x.com/NOTimothyLottes/status/2075769880092037309"
+post_id: "2075769880092037309"
+timestamp: "2026-07-11 02:31:20"
+post_count: 4
+reply_count: 2
+repost_count: 2
+like_count: 42
+view_count: 5063
+---
+
+# @NOTimothyLottes — Rethinking Vulkan queue choice. Traditional double-buffered games might do somet
+
+## Post 1 (2026-07-11 02:31:20)
+
+Rethinking Vulkan queue choice. Traditional double-buffered games might do something like the code below. Find the queue that does {presentation,graphics,compute}. First off this seems like a lot of unnecessary work when one could just choose queue 0 and be done with it ...
+
+![Media 1](./media/2075769880092037309_1.png)
+
+## Post 2 (2026-07-11 02:34:19) — reply to Post 1
+
+AMD on Linux (RADV) and Windows. Queue 0 just works. But note both platforms support doing present on queue 1. So on AMD I'm likely going to render via compute on queue 0 [to reduce chance of preemption] and present on queue 1. And have both decoupled (for front buffer rendering)
+
+![Media 1](./media/2075770634349527454_1.jpg)
+![Media 2](./media/2075770634349527454_2.jpg)
+
+## Post 3 (2026-07-11 02:37:24) — reply to Post 2
+
+NVIDIA is more complex. They put a DMA engine in queue 1 slot, and compute engine in queue 2 slot. Some sometimes queue 2 slot can or cannot do present (varies by driver). So maybe present on 0 (gfx queue), and dispatch on queue 2 by default for NV.
+
+![Media 1](./media/2075771407510773906_1.jpg)
+![Media 2](./media/2075771407510773906_2.jpg)
+![Media 3](./media/2075771407510773906_3.jpg)
+
+## Post 4 (2026-07-11 06:31:23) — reply to Post 1
+
+@NOTimothyLottes Am I having a stroke? What is this font? It feels like reading a captcha. Is it only me?
@@ -0,0 +1,79 @@
+{
+  "root_post_id": "2075769880092037309",
+  "posts": [
+    {
+      "post_id": "2075769880092037309",
+      "author": "NOTimothyLottes",
+      "handle": "NOTimothyLottes",
+      "text": "Rethinking Vulkan queue choice. Traditional double-buffered games might do something like the code below. Find the queue that does {presentation,graphics,compute}. First off this seems like a lot of unnecessary work when one could just choose queue 0 and be done with it ...",
+      "timestamp": "2026-07-11 02:31:20",
+      "media_urls": [
+        "https://pbs.twimg.com/media/HM6desTW0AAHA_H?format=png&name=orig"
+      ],
+      "reply_to_id": null,
+      "quote_of_id": null,
+      "metrics": {
+        "reply_count": 2,
+        "repost_count": 2,
+        "like_count": 42,
+        "view_count": 5063
+      }
+    },
+    {
+      "post_id": "2075770634349527454",
+      "author": "NOTimothyLottes",
+      "handle": "NOTimothyLottes",
+      "text": "AMD on Linux (RADV) and Windows. Queue 0 just works. But note both platforms support doing present on queue 1. So on AMD I'm likely going to render via compute on queue 0 [to reduce chance of preemption] and present on queue 1. And have both decoupled (for front buffer rendering)",
+      "timestamp": "2026-07-11 02:34:19",
+      "media_urls": [
+        "https://pbs.twimg.com/media/HM6d5GnWAAAGOmg?format=jpg&name=orig",
+        "https://pbs.twimg.com/media/HM6d8lcXsAA-8LJ?format=jpg&name=orig"
+      ],
+      "reply_to_id": "2075769880092037309",
+      "quote_of_id": null,
+      "metrics": {
+        "reply_count": 1,
+        "repost_count": 0,
+        "like_count": 7,
+        "view_count": 1230
+      }
+    },
+    {
+      "post_id": "2075771407510773906",
+      "author": "NOTimothyLottes",
+      "handle": "NOTimothyLottes",
+      "text": "NVIDIA is more complex. They put a DMA engine in queue 1 slot, and compute engine in queue 2 slot. Some sometimes queue 2 slot can or cannot do present (varies by driver). So maybe present on 0 (gfx queue), and dispatch on queue 2 by default for NV.",
+      "timestamp": "2026-07-11 02:37:24",
+      "media_urls": [
+        "https://pbs.twimg.com/media/HM6egsMWcAAkjOq?format=jpg&name=orig",
+        "https://pbs.twimg.com/media/HM6ex2jXwAAkmI6?format=jpg&name=orig",
+        "https://pbs.twimg.com/media/HM6e5EdXwAAuOG5?format=jpg&name=orig"
+      ],
+      "reply_to_id": "2075770634349527454",
+      "quote_of_id": null,
+      "metrics": {
+        "reply_count": 1,
+        "repost_count": 0,
+        "like_count": 4,
+        "view_count": 1100
+      }
+    },
+    {
+      "post_id": "2075830291499737598",
+      "author": "Konrad Kubacki",
+      "handle": "konrad_kubacki_",
+      "text": "@NOTimothyLottes Am I having a stroke? What is this font? It feels like reading a captcha. Is it only me?",
+      "timestamp": "2026-07-11 06:31:23",
+      "media_urls": [],
+      "reply_to_id": "2075769880092037309",
+      "quote_of_id": null,
+      "metrics": {
+        "reply_count": 2,
+        "repost_count": 0,
+        "like_count": 19,
+        "view_count": 437
+      }
+    }
+  ],
+  "source_url": "https://x.com/NOTimothyLottes/status/2075769880092037309"
+}