Timeline for Can a movss instruction be used to replace integer data?
Current License: CC BY-SA 3.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 19, 2016 at 8:24 | audit | Close votes | |||
| Jun 19, 2016 at 8:24 | |||||
| May 23, 2016 at 21:09 | comment | added | Peter Cordes |
@MSalters: Intel finally did this for AVX with __m256 and __m256i intrinsics for vinsertf128. (vinserti128 is only in AVX2). Of course, there's not much you can usefully do with __m256i with only AVX1. But that's a great idea. They should absolutely introduce integer instrinsics for shufps, since there's nothing else like it for combining data from two registers until AVX512's vpermt2d (permute 2 vectors, overwriting the Table).
|
|
| May 23, 2016 at 15:53 | comment | added | NoelC | I know, right? Kind of makes you want to write some new intrinsic inline functions to fill in the gaps. | |
| May 23, 2016 at 7:40 | comment | added | MSalters |
Intel really seems stuck in the assembly age. If the actual instruction shuffles bits without assigning meaning, the C intrinsics should have float and int versions. There's no reason why two intrinsics with different signatures couldn't map to the same instruction.
|
|
| May 23, 2016 at 2:58 | comment | added | Peter Cordes |
See also stackoverflow.com/questions/13153584/…. Not quite a duplicate because there's more to say about movss's weird design and difference from movd.
|
|
| May 23, 2016 at 2:56 | vote | accept | NoelC | ||
| May 23, 2016 at 2:56 | vote | accept | NoelC | ||
| May 23, 2016 at 2:56 | |||||
| May 23, 2016 at 2:55 | answer | added | Peter Cordes | timeline score: 5 | |
| May 23, 2016 at 2:48 | answer | added | paddy | timeline score: 2 | |
| May 23, 2016 at 1:46 | history | asked | NoelC | CC BY-SA 3.0 |