First complete review of Haswell i7-4770K

Page 5 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

MightyMalus

Senior member
Jan 3, 2013
292
0
0
Actually, weren't thing's like that almost "free" for HSW? Ugh, can't remember what Intel did to the core that was "better" than a GPU to do on its own.

Anyways, why did power consumption increase?

Can't wait to see the "real" review!
 

Fjodor2001

Diamond Member
Feb 6, 2010
3,989
440
126
So when can we expect to see complete reviews from sites like Anandtech and Tom's Hardware? Is that usually on the day of release, or approximately how much before that?
 

john3850

Golden Member
Oct 19, 2002
1,436
21
81
Where do the intel cpus that are used for reviews come from and if they come from intel are they hand picked these days.
On one old anandtech c2d review it stated that those cpus came from a few different stores.
 
Last edited:

IntelUser2000

Elite Member
Oct 14, 2003
8,686
3,786
136
Anyways, why did power consumption increase?

Performance is disappointing, but power consumption is expected. Higher TDP at 84W versus 77W in Ivy Bridge will mean it'll use more in scenarios that are power-virus(code that is designed to make the CPU use max power). In the case of the Intel Burn Test, its a Linpack benchmark, and it'll use TDP to its full.

Side effect of that is though in the IBT Haswell should achieve 2x the FLOPs because of AVX2.
 

blackened23

Diamond Member
Jul 26, 2011
8,548
2
0
The TDP in the desktop version will not be more power efficient than the Ivy Bridge. We already know this.

Only the BGA versions which are intended for portables and AIOs are significantly different in that respect - ultrabooks, macbooks and tablets using Haswell will have vastly improved efficiency over the Ivy Bridge. However, since desktop users generally don't care -that- much, the TDP of the Haswell is a little higher for the 4770k. The BGA version has a much lower TDP, and even has better graphics on die.

This is intel creating an efficienct product for the consumer space that demanded it - mobile. Again, the BGA versions have _vastly_ improved efficiency over Ivy Bridge. But not the desktop versions.
 

blackened23

Diamond Member
Jul 26, 2011
8,548
2
0
Yep. Benchmarking the iGPU on the 4770k is a complete waste of time because the GPU performance isn't much improved over HD4000. Again, intel is creating a product for the intended audience: desktop users don't want iGPU. They want discrete. Therefore, intel put the worse graphics on the 4770k while the best graphics chips go to the BGA and mobile versions of Haswell.

It's all about creating a product for the intended audience. I can safely say that very few of us here would ever use the integrated graphics on the 4770k. So why should intel bother putting the GT3E on die? If no one will use it?

Fact of the matter is, the intended audience for high performance iGPU and efficiency is mobile. And that is where the low TDP and high iGPU performance parts are going. Creating products for the intended audience.
 

A5

Diamond Member
Jun 9, 2000
4,902
5
81
So when can we expect to see complete reviews from sites like Anandtech and Tom's Hardware? Is that usually on the day of release, or approximately how much before that?

No one has said when the NDA expires (probably covered by the NDA ).

For what its worth, Anand's IVB full review went up on 4/23/12, which is 6 days before Amazon's "first available on Amazon.com date". I have to admit that I don't remember the exact "official" retail launch date for the 3770K.

If that pattern holds, we'll see reviews the last week of this month (around May 28th?).
 

Borealis7

Platinum Member
Oct 19, 2006
2,901
205
106
well yes, TDP has risen from 77W to 84W.

to the Chinese guy who reviewed: Y U NO OC THE CHIP??
 

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
I still think there is a market for faster hardware, that gives unique experiences.

Intel have the finest engineering teams in the world, with competences out of this world, and they are working on improving IPC 2-10% with each generation.

What is the meaning of this nonsense?

What do we do our selves to promote faster hardware?

Several reviewers and especially Anand have this eye on IPC, and its excactly that focus that is hindering performance where it could really matter - > multicore the next few years then avx2/hsa/?? full throttle (like inf64 wrote).

All, and that includes us, got their eyes on this IPC. If we had moved that years ago, all that valuable competence could have focused more productively elsewhere. Its next to useless. Imagine what could have been invented for the PC if the competences had looked elsewhere.

The effect is a monopoly market that gives average consumers no benefit, and therefore they are going away fx. to mobile -> Arm. Typically Otellinie strategy, and we were dancing to his tune, but the long time eroding of the pc market was one effect. Otellini was a killer of all innovation, no wonder JHH called Intel a money machine.

After all the market reacts to this nonsense. And now Quallcomm have same market cap as Intel. No wonder.

You guys remember what adding a fpu to x86 meant for performance? OoO? Integrated memory controller? Accerated 2D or 3D? We have the tech and the programming today to give us the same huge jump, we just have to stop looking at that idiotic IPC. Its a mental prison.

You're being way too hard on Intel. One of the main reasons why there is very little increase in CPU performance each generation is because AMD has basically dropped the ball. Since Conroe, AMD hasn't really been able to compete with Intel, and as such, Intel feels no particular need for substantial performance gains as their incremental gains still give AMD a good beating.

Hopefully Steamroller will give a better showing.

The other reason of course, is that besides a few niche applications like video encoding and certain games (which relatively fewer people use), consumer apps don't really leverage the enormous processing power of these CPUs.

Most consumers use PCs primarily to check e-mails, face book, surf the web etc... You can do all of that on tablets, smartphones, laptops etc with the added advantage of being mobile.

That's precisely why the desktop market is drying up and Intel and AMD are both focusing the majority of their engineering resources in mobile computing.

At any rate I'm suspicious of these benchmarks. Like others have pointed out, the hardware they used is likely not final and still has a few performance bugs to iron out.

Also, the main performance boost (AVX2) for Haswell will take time to materialize. When it does, we should be seeing very large performance gains.
 

ShintaiDK

Lifer
Apr 22, 2012
20,378
145
106
You're being way too hard on Intel. One of the main reasons why there is very little increase in CPU performance each generation is because AMD has basically dropped the ball. Since Conroe, AMD hasn't really been able to compete with Intel, and as such, Intel feels no particular need for substantial performance gains as their incremental gains still give AMD a good beating.

Hopefully Steamroller will give a better showing.

The other reason of course, is that besides a few niche applications like video encoding and certain games (which relatively fewer people use), consumer apps don't really leverage the enormous processing power of these CPUs.

Most consumers use PCs primarily to check e-mails, face book, surf the web etc... You can do all of that on tablets, smartphones, laptops etc with the added advantage of being mobile.

That's precisely why the desktop market is drying up and Intel and AMD are both focusing the majority of their engineering resources in mobile computing.

At any rate I'm suspicious of these benchmarks. Like others have pointed out, the hardware they used is likely not final and still has a few performance bugs to iron out.

Also, the main performance boost (AVX2) for Haswell will take time to materialize. When it does, we should be seeing very large performance gains.

I think you misunderstand what the market asks for, if you think Intel is giving you no performance due to no competition from AMD.

Consumers demand better performance/watt as the single most important thing.
 

Gikaseixas

Platinum Member
Jul 1, 2004
2,836
218
106
I think you misunderstand what the market asks for, if you think Intel is giving you no performance due to no competition from AMD.

Consumers demand better performance/watt as the single most important thing.

Be honest please. Do you really think that if there was a FX 8450 that performed better than the i7 3770 we would see what we're seeing here?

Consumers demand higher performance first and foremost. In your country the reality might be that but you're a minority (like someone pointed out already)
 

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
I think you misunderstand what the market asks for, if you think Intel is giving you no performance due to no competition from AMD.

Consumers demand better performance/watt as the single most important thing.

I was speaking mainly for PC enthusiasts who care mostly about overall performance rather than the market at large.

If AMD was matching Intel, then we would be seeing much larger performance gains period and not just performance/watt..
 

R0H1T

Platinum Member
Jan 12, 2013
2,582
162
106
Be honest please. Do you really think that if there was a FX 8450 that performed better than the i7 3770 we would see what we're seeing here?

Consumers demand higher performance first and foremost. In your country the reality might be that but you're a minority (like someone pointed out already)
Actually he's right, only partially though, & you can't apply the minority number to my part of the world :biggrin:

The consumers, most of'em, are perfectly fine with an IGP like HD5200, heck even HD4000 would be enough for them, & the CPU is overkill for everyone but the enthusiast & professional segments. AMD is out of the equation & Intel doesn't consider them when going for their mobile/APU roadmap !
 

blackened23

Diamond Member
Jul 26, 2011
8,548
2
0
Consumers demand better performance/watt as the single most important thing.

Mobile, maybe...not desktop. Nobody wants a space heater for their PC but i'll easily take a CPU that performs 2x better, on a desktop, for 100W more power. Problem is, AMD doesn't have such a product.

The efficiency design is for mobile. The architecture has to be used for mobile, desktop, and servers, therefore the baseline is designed for efficiency. Nothing more, nothing less. It has a side effect of benefiting desktop, but that's not the primary intent (making desktop more efficient). The primary intent is for mobile. I'd say by and large, desktop users don't care, but again, I won't put AMD under this category because their CPUs don't beat intel by any metric.
 

R0H1T

Platinum Member
Jan 12, 2013
2,582
162
106
Mobile, maybe...not desktop. Nobody wants a space heater for their PC but i'll easily take a CPU that performs 2x better, on a desktop, for 100W more power. Problem is, AMD doesn't have such a product.
The problem isn't about desktop or mobile rather the software which isn't tuned to take advantage of your quad core, let alone octa cores, so until & unless that bottleneck is resolved you won't see such high performance chips because the market, number/volumes specifically, simply isn't there !
 

ShintaiDK

Lifer
Apr 22, 2012
20,378
145
106
We already know the limit. The 3970X is a 150W part.

Intel is not holding back on anything. They also spend record R&D to improve the CPUs.

Not to mention if you could redo all software over night, Haswell with AVX2 and TSX would be a huge upgrade. But extracing more IPC out of legacy code is simply an almost impossible task.
 

Fjodor2001

Diamond Member
Feb 6, 2010
3,989
440
126
We already know the limit. The 3970X is a 150W part.

Intel is not holding back on anything. They also spend record R&D to improve the CPUs.

Not to mention if you could redo all software over night, Haswell with AVX2 and TSX would be a huge upgrade. But extracing more IPC out of legacy code is simply an almost impossible task.

Unfortunately we're not seeing higher CPU frequency either on the mainstream desktop CPUs. Up until a couple of years ago that was one of the main reasons the CPUs got faster going from one generation to the next.
 

ShintaiDK

Lifer
Apr 22, 2012
20,378
145
106
Unfortunately we're not seeing higher CPU frequency either on the mainstream desktop CPUs. Up until a couple of years ago that was one of the main reasons the CPUs got faster going from one generation to the next.

It was also the time where power consumption went crazy upwards. It was a low hanging fruit.

The frequency race took its last breath in 2008 or so.
 
Last edited:

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
It was also the time where power consumption went crazy upwards. It was a low hanging fruit.

The frequency race took its last breath in 2008 or so.

I think that increasing the width and efficiency of the SIMD instructions like what we see with AVX2 is a good way to increase performance without increasing power usage that much.

Eventually, we might see 512 bit SIMD/MIMD units on CPUs, which would put them even closer to GPUs..
 

ShintaiDK

Lifer
Apr 22, 2012
20,378
145
106
I think that increasing the width and efficiency of the SIMD instructions like what we see with AVX2 is a good way to increase performance without increasing power usage that much.

Eventually, we might see 512 bit SIMD/MIMD units on CPUs, which would put them even closer to GPUs..

Thats one way. Something like IA64 is another possible option.
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |