search for: vni8

...nd on this with an example?  There seems to be an awful lot of > shuffle patterns and predicates in PPCInstrAltivec.td.  What do you mean by, > "Canonicalize to byte ops?"  Can you walk me through how that works with > Altivec? The basic idea is quite simple - lower everything to vNi8 and write all the patterns using only these types. -- With best regards, Anton Korobeynikov Faculty of Mathematics and Mechanics, Saint Petersburg State University

On Thursday 17 December 2009 17:16, Nate Begeman wrote: > David, this is probably the wrong approach, based on the accreted awfulness > of the X86 shuffle lowering code, Ha! I have no issue believing this statement. :) > The correct approach is probably a rewrite based around what > AltiVec does: Canonicalize to byte ops, and write all the patterns once > rather than having to

...e?  There seems to be an awful lot > > of shuffle patterns and predicates in PPCInstrAltivec.td.  What do you > > mean by, "Canonicalize to byte ops?"  Can you walk me through how that > > works with Altivec? > > The basic idea is quite simple - lower everything to vNi8 and write > all the patterns using only these types. Yeah, I figured that out after thinking a bit more. However, I think in this case we only want to lower to vNi32 since there are no immediate-mask shuffles in X86 that operate on smaller element types. Doing it at the byte level would just...

...llvm-dev < llvm-dev at lists.llvm.org> wrote: > The problem can happen when you want to build a vector of i8, but i8 > itself is not legal on your target. All operands to BUILD_VECTOR will be > legalized to the next legal integer type, so you can end up with a > BUILD_VECTOR of vNi8 where all operands are i32, for example. > > Actual mixed types are less likely to happen, but if you are doing your > own target-specific lowering, you can end up with mixed types, simply > because your code doesn't have to make them all the same. > > -- > Krzysztof Parzys...

Thanks for the clarification. The `except` seemed dangling to me, but it's early here. Just curious... how do we end up with a mixed type BUILD_VECTOR? That's counterintuitive. On Tue, Jul 7, 2020 at 10:58 AM Krzysztof Parzyszek via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > Mixed integer types are ok, but the values will get truncated to the element type of the output

...be an awful lot >>> of shuffle patterns and predicates in PPCInstrAltivec.td. What do you >>> mean by, "Canonicalize to byte ops?" Can you walk me through how that >>> works with Altivec? >> >> The basic idea is quite simple - lower everything to vNi8 and write >> all the patterns using only these types. > > Yeah, I figured that out after thinking a bit more. However, I think in this > case we only want to lower to vNi32 since there are no immediate-mask shuffles > in X86 that operate on smaller element types. Doing it at th...