Core i7-4770K: Haswell's Performance, Previewed

[cangelini]

A recent trip got us access to an early sample of Intel’s upcoming Core i7-4770K. We compare its performance to Ivy Bridge- and Sandy Bridge-based processors, so you have some idea what to expect when Intel officially introduces its Haswell architecture.

Core i7-4770K: Haswell's Performance, Previewed : Read more

 

[twelve25]

Obviously with AMD striggling, Intel has no need to really stretch here. This is another simple incremental upgrade. Good jump from socket 1156, but I doubt many 1155 owners will feel the need to buy a new motherboard for this.

 

[EzioAs]

Thanks for the preview!

So all of these results are what most people expected already: minimal increase in CPU performance while the iGPU shows significant increase? I'm not surprised really (and I believe most people have speculated this), since Haswell mostly targets the mobile segment.

@twelve25

In my opinion though, unless LGA1156 i5/i7 users really want to upgrade (native USB 3.0, more SATA 3, etc), they can still hold out with their current CPUs. Although upgrading to Haswell rather than IB does make much more sense if they really want to but there's also the reported USB 3.0 bug and we haven't seen the thermals and overclocking capability on this chip so it might actually be a turn off for some people. And yeah, I don't think many SB or IB users will upgrade to Haswell.

 

[dagamer34]

@twelve25 But who does Intel really need to convince here? Trying to chase after people who upgrade every year is a fools errand because its such a small piece of the pie compared to the overall larger market. Besides, most of Intel's resources are clearly going towards making mobile chips better, where there energy really needs to be anyway.

 

[dagamer34]

To add to EzioAs's point, I don't see most people on SB/IVB systems upgrading until Intel makes chips that have a good 10-15% better performance than 4.2-4.5Ghz SB/IVB systems or they decide to go down the APU route like AMD is (and also find/create workloads which an APU would beat those systems). In other words, not for another 2+ years.

 

[killerchickens]

Does Haswell run hot as Ivy Bridge?

 

[Adroid]

[citation][nom]killerchickens[/nom]Does Haswell run hot as Ivy Bridge?[/citation]
That = the million dollar question. Did they do away with the bird poop and return to fluxless solder.

Intel should stop throwing insults to the overclocking crowd. We will pay another 10$ for the fluxless solder.

 

[mayankleoboy1]

@ Chris Angelini : Man, you are amazing for this preview! +1 to Toms.


There is no surprise at Intel excluding TSX from the unlocked K parts. They removed teh VT-d in the Sb/IB too. Just so that people not use teh $300 chip in servers, but have to buy th e$2000 chip.
Intel are fucked up

i dont think Intel will be too happy with Toms for this preview....

 

[universal remonster]

Excellent!! Thanks very much for the preview! Been waiting for this =)

 

[sixdegree]

Good preview. I kinda hoped that Toms includes the power consumption figure for Haswell. It's the biggest selling point of Haswell, after all.

 

[mayankleoboy1]

[citation][nom]sixdegree[/nom]Good preview. I kinda hoped that Toms includes the power consumption figure for Haswell. It's the biggest selling point of Haswell, after all.[/citation]

Power consumptions is a lot dependent on the BIOS optimizations, which are far from final.

 

[cangelini]

[citation][nom]mayankleoboy1[/nom]@ Chris Angelini : Man, you are amazing for this preview! +1 to Toms.There is no surprise at Intel excluding TSX from the unlocked K parts. They removed teh VT-d in the Sb/IB too. Just so that people not use teh $300 chip in servers, but have to buy th e$2000 chip. Intel are fucked up i dont think Intel will be too happy with Toms for this preview....[/citation]
Thanks--and yeah, VT-d is being excluded from these K-series parts, too. Funny thing is that it'll be enabled on the -4770, but not the -4770K.

 

[tomfreak]

I could not understand the meaning of 3.5GHz vs 3.7GHz on 4770K 4 core turbo. which one is the right clock?

 

[EzioAs]

I could not understand the meaning of 3.5GHz vs 3.7GHz on 4770K 4 core turbo. which one is the right clock?

If all 4 cores are being stressed (used), each core can boost itself up to 3.7GHz?

 

[LORD_ORION]

If you actually care about VT-d, why not get an 8350? 8 Cores for $200, and the IOMMU boards from Gigabyte start at $120.

 

[mayankleoboy1]

Do Microsoft Compilers even have specific optimisations for AVX2 and FMA3 ?

@ Chris Angelini : Can you build a few applications in linux (like 7z and h.264) with -core-avx2 optimisation and test that ? Iam eager to know how much boost pre-written, integer heavy code can get with only compiler optimisations.

 

[mayankleoboy1]

[citation][nom]LORD_ORION[/nom]If you actually care about VT-d, why not get an 8350? 8 Cores for $200, and the IOMMU boards from Gigabyte start at $120.[/citation]

Because their performance sucks in comparison to the latest Xeons, as tested by Anandtech a few days back.

 

[de5_Roy]

nice preview!
i was expecting something richland related. this came outta nowhere.

 

[ascension505]

tick-tock, nuff said

 

[cangelini]

[citation][nom]mayankleoboy1[/nom]Do Microsoft Compilers even have specific optimisations for AVX2 and FMA3 ? @ Chris Angelini : Can you build a few applications in linux (like 7z and h.264) with -core-avx2 optimisation and test that ? Iam eager to know how much boost pre-written, integer heavy code can get with only compiler optimisations.[/citation]
Let me see what I can do there.

 

[mayankleoboy1]

No info on QuickSync 3.0 ?

I am assuming that :

1. No proper working drivers.
2. ISV's not willing to release pre-alpha builds over fear of Intels NDA wrath.

Do you know if the QS3.0 performance will depend on the whether the chip has GT1/2/3 ?

 

[beetlejuicegr]

Stupid question but how much backward compatible with motherboards and chipsets of ivy bridge and/or sandy bridge are these new cpus?

 

[JAYDEEJOHN]

This may be a 1 time perf jump on the gfx end.
New prosses will help, but the BW problems are right around the corner, this has to be solved by them and no more low hanging fruit on the power layout either

 

[mayankleoboy1]

[citation][nom]beetlejuicegr[/nom]Stupid question but how much backward compatible with motherboards and chipsets of ivy bridge and/or sandy bridge are these new cpus?[/citation]

0% compatible.

 

[de5_Roy]

[citation][nom]LORD_ORION[/nom]If you actually care about VT-d, why not get an 8350? 8 Cores for $200, and the IOMMU boards from Gigabyte start at $120.[/citation]

Because their performance sucks in comparison to the latest Xeons, as tested by Anandtech a few days back.

iirc fx is cheaper than a lot of xeons, builds can be more flexible (as in vm to rendering to gaming etc) compared to xeons as well.

Stupid question but how much backward compatible with motherboards and chipsets of ivy bridge and/or sandy bridge are these new cpus?

sb/ivb supports lga 1155 socket. haswell supports lga 1150 socket. so haswell is not backwards compatible with sb/ivb.
why did haswell lose 5 pins? is it because of integrated vrm or changes in the display outputs?