Changes between Version 13 and Version 14 of GcnInstrsVop1


Ignore:
Timestamp:
Dec 2, 2015, 11:00:19 PM (4 years ago)
Author:
trac
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • GcnInstrsVop1

    v13 v14  
    181181<li>CLAMP - clamps destination floating point value in range 0.0-1.0</li>
    182182<li>MUL:2, MUL:4, DIV:2 - OMOD modifiers. Multiply destination floating point value by
    183 2.0, 4.0 or 0.5 respectively</li>
     1832.0, 4.0 or 0.5 respectively.</li>
    184184<li>-SRC - negate floating point value from source operand</li>
    185185<li>ABS(SRC) - apply absolute value to source operand</li>
    186186</ul>
     187<p>NOTE: OMOD modifier doesn't work if output denormals are allowed
     188(5 bit of MODE register for single precision or 7 bit for double precision).</p>
    187189<p>Negation and absolute value can be combined: <code>-ABS(V0)</code>. Modifiers CLAMP and
    188190OMOD (MUL:2, MUL:4 and DIV:2) can be given in random order.</p>