Difference between revisions of "Instruction Set/narrowdn"
From Mill Computing Wiki
| Line 4: | Line 4: | ||
</div> | </div> | ||
| − | + | Half the width of a decimal float value. Rounding towards negative infinity. | |
| + | |||
| + | Can produce the [http://en.wikipedia.org/wiki/IEEE_floating_point IEEE 754] 32bit decimal float interchange format. | ||
| + | |||
| + | This is not a [[Speculable]] operation. The reason for this is the impossibility to fit all of the [[NaR]] payload into values smaller than 32bit. | ||
| + | Nominally this would only require the narrowing of 32bit values to be not speculable, but for simplicity reasons in hardware and compiler this is not so. | ||
| + | If narrowing should prove a big bottleneck this can be revisited. | ||
| + | |||
---- | ---- | ||
<code style="font-size:130%"><b style="color:#050">narrowdn</b>(<span style="color:#009">[[Domains#d|d]]</span> <span title="belt operand from ops window">v</span>) → [[Domains#d|d]] r<sub>0</sub></code> | <code style="font-size:130%"><b style="color:#050">narrowdn</b>(<span style="color:#009">[[Domains#d|d]]</span> <span title="belt operand from ops window">v</span>) → [[Domains#d|d]] r<sub>0</sub></code> | ||
Revision as of 00:00, 3 January 2015
realizing exu stream exu block compute phase operation in the decimal floating point value domain and rounds toward negative infinity
Half the width of a decimal float value. Rounding towards negative infinity.
Can produce the IEEE 754 32bit decimal float interchange format.
This is not a Speculable operation. The reason for this is the impossibility to fit all of the NaR payload into values smaller than 32bit. Nominally this would only require the narrowing of 32bit values to be not speculable, but for simplicity reasons in hardware and compiler this is not so. If narrowing should prove a big bottleneck this can be revisited.
operands: like Narrowd [dd:½d]
| Core | In Slots | Latencies |
|---|---|---|
| Decimal8 | E0 E1 | d:w=4 q:d=5 |
| Decimal16 | E0 E1 | d:w=4 q:d=5 |
operands: like Narrowvd [DD:½D]
| Core | In Slots | Latencies |
|---|---|---|
| Decimal8 | E0 E1 | dv,dv:wv=4 qv,qv:dv=5 |
| Decimal16 | E0 E1 | dv,dv:wv=4 qv,qv:dv=5 |
Instruction Set, alphabetical, Instruction Set by Category, Instruction Set, sortable, filterable
