| 1319 | <h3>V_EXP_LEGACY_F32</h3> |
| 1320 | <p>Opcode VOP1: 70 (0x46) for GCN 1.1; 75 (0x4b) for GCN 1.2<br /> |
| 1321 | Opcode VOP3A: 454 (0x1c6) for GCN 1.1; 395 (0x18b) for GCN 1.2<br /> |
| 1322 | Syntax: V_EXP_LEGACY_F32 VDST, SRC0<br /> |
| 1323 | Description: Approximate power of two from FP value SRC0 and store it to VDST. Instruction |
| 1324 | for values smaller than -126.0 always returns 0 regardless floatmode in MODE register. |
| 1325 | For some cases this instructions returns slightly less accurate result than V_EXP_F32.<br /> |
| 1326 | Operation:<br /> |
| 1327 | <code>if (ASFLOAT(SRC0)>=-126.0) |
| 1328 | VDST = APPROX_POW2(ASFLOAT(SRC0)) |
| 1329 | else |
| 1330 | VDST = 0.0</code></p> |
| 1496 | <h4>V_LOG_LEGACY_F32</h4> |
| 1497 | <p>Opcode VOP1: 69 (0x45) for GCN 1.1; 76 (0x4c) for GCN 1.2<br /> |
| 1498 | Opcode VOP3A: 453 (0x1c5) for GCN 1.1; 396 (0x18c) for GCN 1.2<br /> |
| 1499 | Syntax: V_LOG_LEGACY_F32 VDST, SRC0<br /> |
| 1500 | Description: Approximate logarithm of base 2 from floating point value SRC0, and store result |
| 1501 | to VDST. If SRC0 is negative then store -NaN to VDST. |
| 1502 | This instruction doesn't handle denormalized values regardless FLOAT MODE register setup. |
| 1503 | This instruction returns slightly different results than V_LOG_F32.<br /> |
| 1504 | Operation:<br /> |
| 1505 | <code>FLOAT F = ASFLOAT(SRC0) |
| 1506 | if (F==1.0) |
| 1507 | VDST = 0.0f |
| 1508 | if (F<0.0) |
| 1509 | VDST = -NaN |
| 1510 | else |
| 1511 | VDST = APPROX_LOG2(F)</code></p> |