cik_sdma_emit_fill_buffer(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

πŸ’… cik_sdma_emit_fill_buffer β€” kernel API manual, section 9, bestie

Okay so picture this: you're deep in the kernel API manual (section 9, the driver-functions girlies ✨) and you stumble onto cik_sdma_emit_fill_buffer. That's our main character today. We're filling buffers. With the sDMA engine. It's giving hardware-accelerated glamour, no cap. πŸŽ€


✨ NAME ✨

cik_sdma_emit_fill_buffer β€” literally fills a buffer using the sDMA engine πŸ¦‹


🌸 SYNOPSIS 🌸

void cik_sdma_emit_fill_buffer (struct amdgpu_ib *ib , uint32_t src_data
, uint64_t dst_offset , uint32_t byte_count );

Like, it returns nothing (void) and takes four things. That's it. That's the whole vibe check. πŸ’œ


🫢 ARGUMENTS 🫢

  • ib β€” the indirect buffer we're filling, bestie. This is the one getting the glow-up. ✨
  • src_data β€” the value to write into the buffer. The actual content. The personality, if you will. πŸ’…
  • dst_offset β€” the dst GPU address. Where it's all going down. πŸ“
  • byte_count β€” number of bytes to xfer. How much we're moving. The dosage, lowkey. πŸ”₯

πŸ‘‘ DESCRIPTION πŸ‘‘

Fill GPU buffers using the DMA engine (CIK). That's the whole tea. β˜• The DMA engine does the heavy lifting so you don't have to, and honestly? Iconic behaviour. Not me being obsessed with a memory-fill function fr fr 😭


🌈 SEE ALSO 🌈

The source lives in the kernel file ./drivers/gpu/drm/amd/amdgpu/cik_sdma.c β€” go read it, iykyk 🧚

And here's the whole friend group, all present and accounted for, not one skipped (I would never πŸ™ˆ):


Okay that's the whole page, periodt. πŸ’– This little beauty comes from ./drivers/gpu/drm/amd/amdgpu, dated October 2026, and it's filed under cik_sdma_emit_fill_buffer(9). Go fill some buffers, bestie β€” slay. πŸ¦‹βœ¨

πŸ“¦ where this page comes from