llvm.org GIT mirror llvm / release_90 docs / AMDGPU / gfx8_data_buf_d16_96.rst
release_90

Tree @release_90 (Download .tar.gz)

gfx8_data_buf_d16_96.rst @release_90view markup · raw · history · blame

vdata

16-bit data to store by a buffer instruction.

Size: depends on GFX8 GPU revision:

  • 3 dwords for GFX8.0. This H/W supports no packing.
  • 2 dwords for GFX8.1+. This H/W supports data packing.

Operands: :ref:`v<amdgpu_synid_v>`