Threadwell

Recent Notes

  • DemetriSpanos

    Oct 06, 2026

    • archive
    • twitter
    • demetrispanos
  • NOTimothyLottes

    Oct 06, 2026

    • archive
    • twitter
    • notimothylottes
  • bonzajplc

    Oct 06, 2026

    • archive
    • twitter
    • bonzajplc
Home

❯

Archive

❯

Threads

❯

NOTimothyLottes

❯

One of the downsides of V_CNDMASK_B32 on AMD is that you burn the SGPRs on the VCC bool, so if you are selecting between constants, those require extra V_MOV_B32 ops.

❯

After a few hours of trying workaround and seeing a whole lot of perf bugs in the process.

After a few hours of trying workaround and seeing a whole lot of perf bugs in the process.

Properties5
typearchive
sourcetwitter
date2025-01-06
tagsarchive, twitter, notimothylottes
descriptionAfter a few hours of trying workaround and seeing a whole lot of perf bugs in the process.

Jan 06, 20251 min read

  • archive
  • twitter
  • notimothylottes

Source

  • URL: https://x.com/NOTimothyLottes/status/1876127044972728402
  • Author: NOTimothyLottes (@NOTimothyLottes)
  • Posted: 2025-01-06 04:41:58

Branch

1/ @NOTimothyLottes

After a few hours of trying workaround and seeing a whole lot of perf bugs in the process. The irony is this is just a trivial HEX dump print shader. And if I can find this many problems in just one shader, image how many you’d find in a whole application!

Related

  • Spine: 2025-01-06-one-of-the-downsides-of-v-cndmask-b32-on-amd-is

Graph View

  • Source
  • Branch
  • Related

Backlinks

  • One of the downsides of V_CNDMASK_B32 on AMD is that you burn the SGPRs on the VCC bool, so if you are selecting between constants, those require extra V_MOV_B32 ops.

Created with Quartz v5.0.0 © 2026

  • GitHub