# Are you kidding?

By: Stubabe (Stubabe.delete@this.nospam.com), October 7, 2015 12:17 am
juanrga (nospam.delete@this.juanrga.com) on October 6, 2015 11:17 am wrote:
> Wouter Tinus (wouter.tinus.delete@this.gmail.com) on October 5, 2015 2:25 pm wrote:
> > juanrga (nospam.delete@this.juanrga.com) on October 5, 2015 10:46 am wrote:
> > > You said that Skylake is
> > >
> > > > > > - 5 wide decode
> > > > > > - 6 wide allocation/decoder queue
> > > > > > - 6 wide ROB
> > > > > > - 8 wide issue
> > > > > > - 8 wide retire (4/thread)
> > >
> > > Using retire as metric, Skylake is then 8-wide. Haswell/Broadwell can
> > > also retire up to 8 uops per cycle. Thus both are 8-wide as well.
> >
> > Are you kidding now? You multiply Haswells number by 2x because of your "unfused"
> > reasoning, but then compare it to Skylakes number *without* doing the same multiplication,
> > and then claim with a straight face that "thus" they are the same width?
> >
> > > There is no way that Skylake can issue and retire 16 ops per cycle, and Anandtech don't say the contrary.
> >
> > We weren't talking about issue at all. And for the record I don't think we should call
> > Skylake 16 wide either, but it *does* follow from *your* logic of multiplying Haswells
> > 4-wide retire rate by 2x, and the fact that Skylake doubled Haswells peak rate.
>
> I am not multiplying anything. Haswell/Broadwell can issue, execute, and retire
> up to 8 uops per cycle. I don't know how many uops can do Skylake per cycle, but
> you said above it can issue and retire 8. Therefore both are same wide.
>
> You are the one that said we have to multiply your number by 2x
> to obtain 16 for Skylake. And said you Skylake is not 16-wide.

using fuops to indicate micro fused uops (e.g. load-exec type uops):

Haswell and Broadwell can only allocate 4 fuops/cycle and retire 4 fuops/cycle
Skylake can allocate 6fuops/cycle and retire 8 fuops/cycle (4/cycle per thread)
Both can issue 8 unfused operations per cycle to execution units.

Considering load-exec type x86 instructions realistically will comprise far less than 50% of instructions it is clear that skylake's back end is significantly wider (50%) than Haswell and in particular Skylake has a 100% wider retirement unit.

So if YOU are claiming Haswell is a 8-wide design by counting fused uops as 2 (and I think you are the only one here that is) then Skylake is 12wide allocate with 16 wide retire. However, these values are clearly unrealistic not least because Haswell cannot sustain 8-issue under any possible non-microcoded x86 code sequence. So a more reasonable description is Haswell is 4 wide and Skylake is 6 wide.

TopicPosted ByDate
Update to Intel Optimization ManualSHK2015/09/29 05:38 AM
gather speedEric Bron2015/09/29 09:43 AM
gather speedGabriele Svelto2015/09/29 12:00 PM
Update to Intel Optimization ManualTim McCaffrey2015/09/29 11:18 AM
Update to Intel Optimization ManualSHK2015/09/29 12:04 PM
Update to Intel Optimization ManualAnon2015/09/29 02:23 PM
Update to Intel Optimization Manualnone2015/09/29 10:31 PM
Update to Intel Optimization ManualMichael S2015/09/30 04:24 AM
Update to Intel Optimization ManualMichael S2015/09/30 04:30 AM
Update to Intel Optimization ManualTim McCaffrey2015/09/30 10:01 AM
5-6 wide core, why no mention from Intel?Wouter Tinus2015/09/30 02:14 PM
5-6 wide core, why no mention from Intel?Maynard Handley2015/09/30 03:30 PM
5-6 wide core, why no mention from Intel?Alberto2015/10/01 12:13 AM
5-6 wide core, why no mention from Intel?anon2015/10/01 02:21 AM
5-6 wide core, why no mention from Intel?Alberto2015/10/01 04:41 AM
5-6 wide core, why no mention from Intel?anon2015/10/01 05:27 AM
5-6 wide core, why no mention from Intel?Alberto2015/10/01 08:33 AM
5-6 wide core, why no mention from Intel?juanrga2015/10/01 10:24 AM
5-6 wide core, why no mention from Intel?Maynard Handley2015/10/01 08:57 AM
5-6 wide core, why no mention from Intel?juanrga2015/10/01 03:59 AM
5-6 wide core, why no mention from Intel?Wouter Tinus2015/10/01 02:48 PM
5-6 wide core, why no mention from Intel?juanrga2015/10/03 03:17 AM
5-6 wide core, why no mention from Intel?Wouter Tinus2015/10/03 11:19 AM
Are you kidding? (NT)juanrga2015/10/04 05:30 AM
Are you kidding?Wouter Tinus2015/10/04 03:18 PM
Are you kidding?juanrga2015/10/05 09:46 AM
Are you kidding?David Kanter2015/10/05 11:24 AM
Are you kidding?anon2015/10/05 09:26 PM
Are you kidding?Linus Torvalds2015/10/07 04:49 AM
Are you kidding?juanrga2015/10/07 10:46 AM
Are you kidding?anon2015/10/07 06:21 PM
Are you kidding?Wouter Tinus2015/10/05 01:25 PM
Are you kidding?juanrga2015/10/06 10:17 AM
Are you kidding?Stubabe2015/10/07 12:17 AM
Are you kidding?juanrga2015/10/07 10:56 AM
Amazing...Wouter Tinus2015/10/07 11:31 AM
Amazing...juanrga2015/10/07 03:45 PM
Are you kidding?Stubabe2015/10/07 11:57 AM
Are you kidding?juanrga2015/10/07 03:59 PM
Are you kidding?Wilco2015/10/07 02:07 PM
Are you kidding?juanrga2015/10/07 04:33 PM
5-6 wide core, why no mention from Intel?Eric Bron2015/10/04 04:18 AM
5-6 wide core, why no mention from Intel?David Kanter2015/10/01 09:01 AM
Optimal number and kind of execution unitsjuanrga2015/10/01 10:50 AM
Optimal number and kind of execution unitsPatrick Chase2015/10/01 04:38 PM
Optimal number and kind of execution unitsI.S.T.2015/10/01 05:10 PM
Optimal number and kind of execution unitsPatrick Chase2015/10/01 11:39 PM
Optimal number and kind of execution unitsExophase2015/10/01 10:11 PM
Optimal number and kind of execution unitsjuanrga2015/10/02 05:14 AM
LD/ST unitsSHK2015/10/01 11:11 AM
LD/ST unitsDavid Kanter2015/10/01 12:54 PM
LD/ST unitsSHK2015/10/02 04:55 AM
LD/ST unitsJukka Larja2015/10/02 09:49 PM
LD/ST unitsMaynard Handley2015/10/01 01:01 PM
LD/ST unitsanon2015/10/01 09:54 PM
5-6 wide core, why no mention from Intel?Maynard Handley2015/10/01 12:57 PM
5-6 wide core, why no mention from Intel?David Kanter2015/10/01 03:49 PM
5-6 wide core, why no mention from Intel?Maynard Handley2015/10/01 06:21 PM
5-6 wide core, why no mention from Intel?Exophase2015/10/01 10:07 PM
5-6 wide core, why no mention from Intel?Maynard Handley2015/10/02 12:10 AM
5-6 wide core, why no mention from Intel?Megol2015/10/02 03:39 AM
5-6 wide core, why no mention from Intel?Michael S2015/10/02 04:27 AM
5-6 wide core, why no mention from Intel?Maynard Handley2015/10/02 09:37 AM
5-6 wide core, why no mention from Intel?noko2015/10/02 05:19 PM
5-6 wide core, why no mention from Intel?Exophase2015/10/02 06:43 AM
5-6 wide core, why no mention from Intel?Maynard Handley2015/10/02 09:45 AM
5-6 wide core, why no mention from Intel?Exophase2015/10/02 10:23 AM
5-6 wide core, why no mention from Intel?Wilco2015/10/02 12:48 PM
5-6 wide core, why no mention from Intel?Maynard Handley2015/10/02 01:25 PM
5-6 wide core, why no mention from Intel?Wilco2015/10/02 02:26 PM
5-6 wide core, why no mention from Intel?noko2015/10/02 05:45 PM
5-6 wide core, why no mention from Intel?Maynard Handley2015/10/02 06:54 PM
5-6 wide core, why no mention from Intel?David Kanter2015/10/02 01:59 PM
5-6 wide core, why no mention from Intel?Wilco2015/10/02 02:59 PM
5-6 wide core, why no mention from Intel?David Kanter2015/10/02 03:15 PM
5-6 wide core, why no mention from Intel?Wilco2015/10/02 04:06 PM
LDP/STP usage in AArch64 for 403.gccnone2015/10/03 01:04 AM
LDP/STP usage in AArch64 for 403.gccWilco2015/10/03 03:02 AM
LDP/STP usage in AArch64 for 403.gccnone2015/10/03 03:11 AM
LDP/STP usage in AArch64 for 403.gccWilco2015/10/03 03:37 AM
LDP/STP usage in AArch64 for 403.gccnone2015/10/03 04:37 AM
LDP/STP usage in AArch64 for 403.gccWilco2015/10/03 05:26 AM
5-6 wide core, why no mention from Intel?Maynard Handley2015/10/02 04:24 PM
5-6 wide core, why no mention from Intel?Maynard Handley2015/10/02 03:07 PM
Update to Intel Optimization Manualanon2015/09/30 04:43 PM
Update to Intel Optimization ManualPatrick Chase2015/09/30 09:44 PM
Update to Intel Optimization Manualanon2015/09/30 10:49 PM
Update to Intel Optimization Manualnone2015/09/30 10:50 PM
Update to Intel Optimization ManualDavid Kanter2015/10/01 12:52 PM
Update to Intel Optimization ManualPatrick Chase2015/10/01 04:16 PM
Update to Intel Optimization Manualanon2015/10/01 10:45 PM