On 2020-Nov-10, David Rowley wrote: > On Mon, 9 Nov 2020 at 16:29, Andy Fan <zhihui.fan1...@gmail.com> wrote:
> > However I believe v9 > > should be no worse than v8 all the time, Is there any theory to explain > > your result? > > Nothing jumps out at me from looking at profiles. The only thing I > noticed was the tuple deforming is more costly with v9. I'm not sure > why. Are you taking into account the possibility that generated machine code is a small percent slower out of mere bad luck? I remember someone suggesting that they can make code 2% faster or so by inserting random no-op instructions in the binary, or something like that. So if the difference between v8 and v9 is that small, then it might be due to this kind of effect. I don't know what is a good technique to test this hypothesis.
