[PATCH] D74156: [llvm-exegesis] Exploring X86::OperandType::OPERAND_COND_CODE

[Roman Lebedev via Phabricator via llvm-commits]

lebedev.ri added a comment.

In D74156#1873657 <https://reviews.llvm.org/D74156#1873657>, @lebedev.ri wrote:

> In D74156#1869502 <https://reviews.llvm.org/D74156#1869502>, @gchatelet wrote:
>
> > In D74156#1864292 <https://reviews.llvm.org/D74156#1864292>, @lebedev.ri wrote:
> >
> > > In D74156#1864096 <https://reviews.llvm.org/D74156#1864096>, @gchatelet wrote:
> > >
> > > > - repetition mode (to see the impact of the decoder)
> > >
> > >
> > > This //appears// to be currently handled via `-repetition-mode` switch (D68125 <https://reviews.llvm.org/D68125>).
> >
> >
> > yes
> >
> > > Does this really have to be accounted for (a dimension in) in the greedy approach?
> >
> > @courbet and I believe that having two measures are better than one and can demonstrate the impact of decoding the instruction.
>
>
> Oh, now i see what you mean. At least for `CMOV`, i'm seeing wildly different results
>
> |           | Latency | RThroughput |
> | duplicate | 1       | 0.8         |
> | loop      | 2       | 0.6         |
> |
>
> where latency=1 seems correct, and i'd expect the througput to be close to 1/2 (since there are two execution units).
>
> So i would personally guess that `--repetition-mode=` shouldn't even be an another measurement,
>  but instead much like what is already done by running the whole snippet a few times
>  and denoising the result (not averaging!), the same should be done with this - run both, take minimum
>  https://github.com/llvm/llvm-project/blob/c55cf4afa9161bb4413b7ca9933d553327f5f069/llvm/tools/llvm-exegesis/lib/LatencyBenchmarkRunner.cpp#L38-L39
>
> What are you thoughts on this?


up


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D74156/new/

https://reviews.llvm.org/D74156