Changes between Version 19 and Version 20 of GcnInstrsVop1
- Timestamp:
- 05/20/16 22:00:21 (8 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
GcnInstrsVop1
v19 v20 1097 1097 F += 1.0 1098 1098 VDST = F</code></p> 1099 <h4>V_CEIL_F64</h4> 1100 <p>Opcode VOP1: 24 (0x18) for GCN 1.1/1.2<br /> 1101 Opcode VOP3A: 408 (0x198) for GCN 1.1; 344 (0x158) for GCN 1.2<br /> 1102 Syntax: V_CEIL_F64 VDST(2), SRC0(2)<br /> 1103 Description: Truncate double floating point valu from SRC0 with rounding to 1104 positive infinity (ceilling), and store result to VDST. Implemented by flooring. 1105 If SRC0 is infinity or NaN then copy SRC0 to VDST.<br /> 1106 Operation:<br /> 1107 <code>DOUBLE F = FLOOR(ASDOUBLE(SRC0)) 1108 if (ASDOUBLE(SRC0) > 0.0 && ASDOUBLE(SRC0) != F) 1109 F += 1.0 1110 VDST = F</code></p> 1099 1111 <h4>V_CLREXCP</h4> 1100 1112 <p>Opcode VOP1: 65 (0x41) for GCN 1.0/1.1; 53 (0x35) for GCN 1.2<br /> … … 1347 1359 Operation:<br /> 1348 1360 <code>VDST = FLOOR(ASFLOAT(SRC0))</code></p> 1361 <h4>V_FLOOR_F64</h4> 1362 <p>Opcode VOP1: 26 (0x1a) for GCN 1.1/1.2<br /> 1363 Opcode VOP3A: 410 (0x19a) for GCN 1.1; 346 (0x15a) for GCN 1.2<br /> 1364 Syntax: V_FLOOR_F64 VDST(2), SRC0(2)<br /> 1365 Description: Truncate double floating point value SRC0 with rounding to positive infinity 1366 (flooring), and store result to VDST. If SRC0 is infinity or NaN then copy SRC0 to VDST.<br /> 1367 Operation:<br /> 1368 <code>VDST = FLOOR(ASDOUBLE(SRC0))</code></p> 1349 1369 <h4>V_FRACT_F32</h4> 1350 1370 <p>Opcode VOP1: 32 (0x20) for GCN 1.0/1.1; 27 (0x1b) for GCN 1.2<br /> … … 1589 1609 Description: Round floating point value SRC0 to nearest even integer, and store result to 1590 1610 VDST. If SRC0 is infinity or NaN then copy SRC0 to VDST.<br /> 1591 Operation: 1611 Operation:<br /> 1592 1612 <code>VDST = RNDNE(ASFLOAT(SRC0))</code></p> 1613 <h4>V_RNDNE_F64</h4> 1614 <p>Opcode VOP1: 25 (0x19) for GCN 1.1/1.2<br /> 1615 Opcode VOP3A: 409 (0x199) for GCN 1.1; 345 (0x159) for GCN 1.2<br /> 1616 Syntax: V_RNDNE_F64 VDST(2), SRC0(2)<br /> 1617 Description: Round double floating point value SRC0 to nearest even integer, 1618 and store result to VDST. If SRC0 is infinity or NaN then copy SRC0 to VDST.<br /> 1619 Operation:<br /> 1620 <code>VDST = RNDNE(ASDOUBLE(SRC0))</code></p> 1593 1621 <h4>V_RSQ_CLAMP_F32</h4> 1594 1622 <p>Opcode VOP1: 44 (0x2c) for GCN 1.0/1.1<br /> … … 1690 1718 Operation:<br /> 1691 1719 <code>VDST = RNDTZ(ASFLOAT(SRC0))</code></p> 1720 <h4>V_TRUNC_F64</h4> 1721 <p>Opcode VOP1: 23 (0x17) for GCN 1.1/1.2<br /> 1722 Opcode VOP3A: 407 (0x197) for GCN 1.1; 343 (0x157) for GCN 1.2<br /> 1723 Syntax: V_TRUNC_F64 VDST(2), SRC0(2)<br /> 1724 Description: Get integer value from double floating point value SRC0, and store (as float) 1725 it to VDST. If SRC0 is infinity or NaN then copy SRC0 to VDST.<br /> 1726 Operation:<br /> 1727 <code>VDST = RNDTZ(ASDOUBLE(SRC0))</code></p> 1692 1728 }}}