Files
2026-08-26 18:50:44 -04:00

2.1 KiB

title, type, source, source_url, author, handle, post_id, date, archived, draft, tags, description, in_reply_to
title type source source_url author handle post_id date archived draft tags description in_reply_to
Two great graphs from https://chipsandcheese.com/2023/12/23/nintendo-switchs-igpu-maxwell-nerfed-edition/ - Why I always manually vectorize 16-bit code, and also why you always need to manually check disassembly. archive twitter https://x.com/NOTimothyLottes/status/1738744404414759381 NOTimothyLottes NOTimothyLottes 1738744404414759381 2023-12-24 2026-08-26 false
archive
twitter
NOTimothyLottes
Two great graphs from https://chipsandcheese.com/2023/12/23/nintendo-switchs-igpu-maxwell-nerfed-edition/ - Why I always manually vectorize 16-bit code, and also why you always need to manually check disassembly.

Source

Thread

1/ @NOTimothyLottes ^1738744404414759381

Two great graphs from https://chipsandcheese.com/2023/12/23/nintendo-switchs-igpu-maxwell-nerfed-edition/ - Why I always manually vectorize 16-bit code, and also why you always need to manually check disassembly.

Branches: archive/threads/NOTimothyLottes/2023-12-24-two-great-graphs-from-https-chipsandcheese-com/2023-12-24-BrettRidel-do-you-know-other-equivalent-graphs-or-ressources

2/ @AgileJebrim ^1738750536302670083

@NOTimothyLottes

Why are float16s so much faster than int16s?

3/ @NOTimothyLottes ^1738756633738522752

@AgileJebrim

Same bit width, FMA needs smaller multipler than IMAD. Thus HW mul24 fast paths that never get exposed. But 16-bit is small enough already. I thought on AMD, packed 16-bit int or float are the same perf. Some vendors though try area savings by de-throughputing integer/etc ALUs

4/ @AgileJebrim ^1738757938376761652

@NOTimothyLottes

Oh are you only comparing FMA? If it was just additions, would they be on par?