mirror of
https://github.com/capstone-engine/llvm-capstone.git
synced 2024-12-24 17:01:07 +00:00
8ea3e9d9a2
Summary of changes: - Added f16 omod modifier (bug 51386). - Corrected names of data types (bug 48638). - Enabled a16 with most GFX10 MIMG opcodes (see https://reviews.llvm.org/D102231). - Corrected description of integer operands (bug 51130). - Corrected description of 8-bit DS offsets (bug 51536). - Improved PERMLANE op_sel description. - Corrected *SAD* opcode types.
29 lines
903 B
ReStructuredText
29 lines
903 B
ReStructuredText
..
|
|
**************************************************
|
|
* *
|
|
* Automatically generated file, do not edit! *
|
|
* *
|
|
**************************************************
|
|
|
|
.. _amdgpu_synid_gfx7_vsrc:
|
|
|
|
vsrc
|
|
====
|
|
|
|
Data to copy to export buffers. This is an optional operand. Must be specified as :ref:`off<amdgpu_synid_off>` if not used.
|
|
|
|
:ref:`compr<amdgpu_synid_compr>` modifier indicates use of compressed (16-bit) data. This limits number of source operands from 4 to 2:
|
|
|
|
* src0 and src1 must specify the first register (or :ref:`off<amdgpu_synid_off>`).
|
|
* src2 and src3 must specify the second register (or :ref:`off<amdgpu_synid_off>`).
|
|
|
|
An example:
|
|
|
|
.. parsed-literal::
|
|
|
|
exp mrtz v3, v3, off, off compr
|
|
|
|
*Size:* 1 dword.
|
|
|
|
*Operands:* :ref:`v<amdgpu_synid_v>`, :ref:`off<amdgpu_synid_off>`
|