search for: novecremaind

Displaying 4 results from an estimated 4 matches for "novecremaind".

Did you mean: novecremainder
2019 Aug 13
2
[LLVM] (RFC) Addition/Support of new Vectorization Pragmas in LLVM
vecremainder/novecremainder: Should the pragma simply call the vectorizer to attempt to vectorize the remainder loop, or should the vectorizer use a different method? > > Something like that. There were patches posted at some point to enable tail-loop vectorization. At this point, I imagine that you'd construct...
2019 Aug 08
3
[LLVM] (RFC) Addition/Support of new Vectorization Pragmas in LLVM
...to use nontemporal accesses? Any help would be greatly appreciated. If you're asking about the pragma, then what analysis is necessary? In general, you're looking for accesses that won't benefit from caching (e.g., streaming data which is not accessed again). * * vecremainder/novecremainder: Should the pragma simply call the vectorizer to attempt to vectorize the remainder loop, or should the vectorizer use a different method? Something like that. There were patches posted at some point to enable tail-loop vectorization. At this point, I imagine that you'd construct a VPlan w...
2019 Aug 08
4
[LLVM] (RFC) Addition/Support of new Vectorization Pragmas in LLVM
Hello all, We are students from Indian Institute of Technology(IIT), Hyderabad, we would like to propose the addition of the following pragmas in LLVM that aide in (or possibly increase the scope of) vectorization in LLVM (in comparison with other compilers). 1. ivdep 2. Nontemporal 3. [no]vecremainder 4. [no]mask_readwrite 5. [un]aligned Could you please
2019 Aug 09
3
[LLVM] (RFC) Addition/Support of new Vectorization Pragmas in LLVM
...re asking about the pragma, then what analysis is necessary? In >> general, you're looking for accesses that won't benefit from caching (e.g., >> streaming data which is not accessed again). >> >> >> >> - >> - >> >> vecremainder/novecremainder: Should the pragma simply call the >> vectorizer to attempt to vectorize the remainder loop, or should the >> vectorizer use a different method? >> >> >> >> Something like that. There were patches posted at some point to enable >> tail-loop vectoriz...