5,000 Pages of Intel Haswell Documentation for Linux

Subject: General Tech, Graphics Cards | December 31, 2013 - 05:46 PM |
Tagged: linux, iris pro, iris, Intel, haswell

'Tis the season to be sharing and giving (unless you are Disney).

According to Phoronix, Intel has shipped (heh heh heh, "boatload") over 5,000 pages of documentation and technical specs for their Haswell iGPUs including the HD, Iris, and Iris Pro product lines. The intricacies of the 3D engine, GPGPU computation, and video acceleration are laid bare for the open source community. Video acceleration is something that is oft omit from the manuals of other companies.

11-intel.png

Phoronix believes that Intel is, and has been, the best GPU vendor for open-source drivers. AMD obviously supports their open-source community but Intel edges them out on speed. The Radeon HD 7000 series is just beginning to mature, according to their metric, and Hawaii is far behind that. For NVIDIA, the Nouveau driver is still developed primarily by reverse-engineering. That said, documentation was released a few months ago.

Of course all of these comparisons are only considering the open-source drivers.

NVIDIA prides itself on their proprietary driver offering and AMD pretty much offers both up for the user to chose between. Phoronix claims that Intel employs over two-dozen open-source Linux graphics developers but, of course, that is their only graphics driver for Linux. That is not a bad thing, of course, because a launch open-source GPU driver is really identical to what they would launch for a proprietary driver just without slapping the wrists of anyone who tries to tweak it. It does make sense for Intel, however, because community support will certainly do nothing but help their adoption.

If you would like to check out the documentation, it is available at Intel's 01.org.

Source: Phoronix

It really has been a busy year for CPU reviews

Subject: General Tech | December 31, 2013 - 03:00 PM |
Tagged: 2013, amd, nvidia, Intel, arm, qualcomm

2013 has been an incredible year and when looking at The Inquirer's look back on the releases of this year it is hard to believe that all of these releases took place in 12 short months.  Haswell and Richland were the only two traditional CPU architecture updates for high powered desktop applications which stymied the enthusiasm of some gamers but the real star of 2013 was low powered silicon.  ARM has always held strong in this market and celebrated several major releases such as 28nm dual core Cortex A15s and Qualcomm's raising of the bar on mobile graphics with the dual-core and quad-core Snapdragon 400 chips but they lost market share to three newcomers to the low powered market.  NVIDIA's quad-core Tegra 4 SoC arrived with decent performance and graphics improvements compared to their previous generation and allowed the release of the Shield which has helped them become more than a GPU company that is also dipping its toes into the HPC market.   AMD announced the G series of SoCs for industrial applications with a TDP in the neighbourhood of 6W as well as Temash which will power next generation tablets and hybrid mobile devices but it was really Intel that shone brightest at the low end.  Bay Trail has completely reversed the perception of Atom from a product that is not really good at anything to an impressive low powered chip that provides impressive performance for small mobile devices and might find its self a role in the server room as well.  That only scratches the top layer of silicon, click over for more of the year in review.

SiliconCroda.jpg

"While Intel and AMD battled out their ongoing war, Nvidia took the stage to announce its latest Tegra 4 system on a chip (SoC), a quad-core chip with a significant graphics boost. The firm did its best to play down the fact that its Tegra 4 has the same CPU core count as its previous-generation Tegra 3, and instead it focused on GPU performance, an area where the Tegra 3 was starting to look dated against newer chips from rivals such as Samsung."

Here is some more Tech News from around the web:

Tech Talk

Source: The Register

Hardcoreware Reviews Intel Core i3-4340

Subject: General Tech, Graphics Cards, Processors | December 19, 2013 - 04:05 AM |
Tagged: Intel, haswell

In another review from around the net, Carl Nelson over at Hardcoreware tested the dual-core (4 threads) Intel Core i3-4340 based on the Haswell architecture. This processor slides into the $157 retail price point with a maximum frequency of 3.6GHz and an Intel HD 4600 iGPU clocked at 1150MHz. Obviously this is not intended as top-end performance but, of course, not everyone wants that.

hcw-core-i3-4340-review.jpg

Image Credit: Hardcoreware

One page which I found particularly interesting was the one which benchmarked Battlefield 4 rendering on the iGPU. The AMD A10 6790K (~$130) had slightly lower 99th percentile frame time (characteristic of higher performance) but slightly lower average frames per second (characteristic of lower performance). The graph of frame times shows that AMD is much more consistent than Intel. Perhaps the big blue needs a little Fame Rating? I would be curious to see what is causing the pretty noticeable (in the graph, at least) stutter. AMD's frame pacing seems to be very consistent albeit this is obviously not a Crossfire scenario.

If you are in the low-to-mid $100 price point be sure to check out his review. Also, of course, Kaveri should be coming next month so that is something to look out for.

Source: Hardcoreware

Intel Broadwell-EP Xeon E5 v4 Because Why Not?

Subject: General Tech, Processors | December 16, 2013 - 09:17 PM |
Tagged: Intel, Haswell-EP, Broadwell-EP, Broadwell

Intel has made its way on to our news feed several times over the last few days. The ticking and the tocking seem to be back on schedule. Was Intel held back by the complexity of 14nm? Was it too difficult for them to focus on both high-performance and mobile development? Was it a mix of both?

VR-Zone, who knows how to get a hold of Intel slides, just leaked details about Broadwell-EP. This product line is predicted to replace Haswell-EP at some point in the summer of 2015 (they expect right around Intel Developer Forum). They claim it will be Intel's first 14nm Xeon processor which obviously suggests that it will not be preceded by Broadwell in the lower performance server categories.

intel-broadwellep.png

Image Credit: VR-Zone

Broadwell-EP will have up to 18 cores per socket (Hyper-Threading allows up to 36 threads). Its top level cache, which we assume is L3, will be up to 45MB large. TDPs will be the same as Haswell-EP which range from 70W to 145W for server parts and from 70W to 160W for workstations. The current parts based on Ivy Bridge, as far as I can tell, peak at 150W and 25MB of cache. Intel will apparently allow Haswell and Broadwell to give off a little more heat than their predecessors. This could be a very good sign for performance.

VR-Zone expects that a dual-socket Broadwell-EP Xeon system could support up to 2TB of DDR4 memory. They expect close to 1 TFLOP per socket of double precision FP performance. This meets or exceeds the performance available by Kaveri including its GPU. Sure, the AMD solution will be available over a year earlier and cost a fraction of the multi-thousand-dollar server processor, but it is somewhat ridiculous to think that a CPU has the theoretical performance available to software render the equivalent of Battlefield 4's medium settings without a GPU (if the software was written with said rendering engine, which it is not... of course).

This is obviously two generations off as we have just received the much anticipated Ivy Bridge-E. Still, it is good to see that Intel is keeping themselves moving ahead and developing new top-end performance parts for enthusiasts and high-end servers.

Source: VR-Zone

Google to Develop CPUs (For Themselves)?

Subject: General Tech, Processors | December 15, 2013 - 04:27 AM |
Tagged: Intel, google, arm

Amazon, Facebook, and Google are three members of a fairly exclusive club. These three companies order custom server processors from Intel (and other companies). Jason Waxman of Intel was quoted by Wired, "Sometimes OEMs and end customers ask us to put a feature into the silicon and it sort of depends upon how big a deal it is and whether it has to be invisible or proprietary to a customer. We're always happy to, if we can find a way to get it into the silicon".

Google.png

Now, it would seem, that Google is interested in developing their own server processors based on architecture licensed from ARM. This could be a big deal for Intel as Bloomberg believes Google accounts for a whole 4.3% of the chip giant's revenue.

Ouch.

Of course this probably does not mean Google will spring up a fabrication lab somewhere. That would just be nutty. It is still unclear whether they will cut in ARM design houses, such as AMD or Qualcomm, or whether they will take ARM's design and run straight to TSMC, GlobalFoundries, or IBM with it.

I am sure there would be many takers for some sizable fraction of 4.3% of Intel's revenue.

Source: Bloomberg

Intel Broadwell to Reach 3.5W and Other Details!

Subject: General Tech, Processors, Mobile | December 14, 2013 - 04:07 AM |
Tagged: Intel, Broadwell

This leak is from China DIY and, thus, machine-translated into English from Chinese. They claim that Broadwell is coming in the second half of 2014 and will be introduced in three four series:

  • H will be the high performance offerings
  • U and Y have very low power consumption
  • M will fit mainstream performance

The high performance offerings will have up to four CPU cores, 6MB of L3 cache, support for up to 32GB of memory, and thermal rating of 47W. The leak claims that some will be configurable down to 37W which is pretty clearly its "SDP" rating. The problem, of course, is whether 47W is its actual TDP or, rather, another SDP rating. Who knows.

Intel-logo.svg_.png

The H series is said to be available in either one or two chips.  Both a separate PCH and CPU version will exist as well as a single-chip solution that integrates the PCH on-die.

There is basically nothing said about the M series beyond acknowledging its existence.

The U and Y series will be up to dual-core with 4MB L3 cache. The U series will have a thermal rating of 15W to 28W. The Y series will be substantially lower at 4.5W configurable down to 3.5W. No clue about which of these numbers are TDPs and which are SDPs. You can compare this earlier reports that Haswell will reach as low as 4.5W SDP.

Hopefully we will learn more about these soon and, perhaps, get a functional timeline of Intel releases. Seriously, I think I need to sit down and draw a flowchart some day.

Source: China DIY

VR-Zone Has, Well, A Haswell-E First Look

Subject: General Tech | December 14, 2013 - 02:01 AM |
Tagged: Intel, Haswell-E

Here's the short version: X99 chipset, quad-channel DDR4 (2133 MHz), 6 or 8 cores with Hyper-Threading, up to 3 GHz, up to 140W TDP.

Haswell-E, the replacement for recently launched Ivy Bridge-E, will hit in Q3 2014. VR-Zone China has already got their hands on an engineering sample but has yet to do any form of benchmarking. I went enthusiast and all I got is this lousy picture.

Intel-Haswell-E-HEDT-Features-635x435.jpg

Image Credit: VR-Zone

Well, they also got the slide embedded above. Apart from the specifications that were highlighted above, the slide also claims that both the X and K series will be unlocked for overclockers. Especially given how resilient modern processors are, it makes sense to allow all enthusiast-branded parts to be pushed over stock settings.

Of course Haswell-E should also bring the long-awaited boost to single-threaded performance without compromising on the core count. It is expected to launch Q3 2014.

Source: VR-Zone

A Few More Haswell Refresh (2014) Details

Subject: General Tech, Processors | December 13, 2013 - 08:49 PM |
Tagged: Intel, haswell

Intel will begin to refresh their Haswell line of processors, according to VR-Zone, starting in Q2 and continue into Q3. This will be accompanied by their 9-series of motherboard chipsets. The Intel Core i7-4770 and Core i7-4771 will be replaced, not just surpassed, by the Core i7-4790. That said, the only difference is a 100MHz bump to both the base and turbo CPU frequencies.

Intel-Haswell-01.jpg

The K-series processors will come in Q3 and are said to be based on Haswell-E with DDR4 memory. I find this quite confusing because of previous reports that Broadwell-K would appear at roughly the same time. I am unsure what this means for Broadwell-K and I am definitely unsure why some Haswell-E components would be considered part of the Haswell refresh instead of the Haswell-E launch.

My gut instinct believes that VR-Zone is simply confused or that Microsoft and Google Translate are both terrible at understanding this article.

Source: VR-Zone

The 25W, four core Xeon E3 1230Lv3

Subject: Processors | December 9, 2013 - 06:23 PM |
Tagged: xeon e3, Intel, haswell, 1230Lv3

Server chips with low power consumption are in style an the Xeon E3-1230Lv3 certainly qualifies at a tiny 25W TDP.  It is a Haswell chip running at a peak speed of 1.8GHz which would be great for a small business or for a home server.  eTeknix compared the performance of this chip to the i7-4770K with a TDP more than three times that of the Xeon which is perhaps a little unfair to the E3 but is a familiar chip to most enthusiasts.  That said the Xeon doesn't fall too far behind in many tests and at $250 it is less expensive to slap into a Z87 motherboard and it will reduce your power bill somewhat.

index.jpg

"Intel’s Xeon E3-1230Lv3 CPU has been a hotly anticipated processor for a wide variety of target audiences – home users, office users, small business users and enterprise users. Today we’ve got an opportunity to put Intel’s enterprise Xeon E3-1230Lv3 CPU to the test in a professional home user or “prosumer” type of environment, by pairing it up with SuperMicro’s server-grade C7Z87-OCE motherboard. The Intel Xeon E3-1230Lv3 is an important CPU because it offers four cores, eight threads, a 1.8GHz base frequency, a 2.8GHz Turbo frequency and 8MB of cache all for a tiny TDP of just 25W."

Here are some more Processor articles from around the web:

Processors

Source: eTeknix

Leaked Intel Slides Show Possible 2TB SSDs in Q2 2014?

Subject: General Tech, Storage | December 5, 2013 - 10:23 PM |
Tagged: Intel, ssd

Computer storage website, Myce, got a hold of a few slides from Intel's SSD division. The semiconductor giant is expected to have (at least) nine active product lines with new SKUs apparently coexisting with certain older models. Two of the PCIe-based product lines, the P3700 series and the P3500 series, are expected to be available in capacities of up to 2TB. They will apparently be available in 2.5" form factor as well.

myce-intel-ssd-temple-star-4.png

Image Credit: Myce

Intel has not produced the most mindblowing components over the last 3-4 years but, to my knowledge, they have been effective at wooing the enterprise customers. 2.8 GB/s reads and 1.7 GB/s writes at 450,000 IOPS for reading (150,000 IOPS for writes) seem pretty good, though. Combined with Intel's 5-year warranty and it will probably find its way into a few servers.

myce-intel-ssd-temple-star-2.png

Each of the new products will be fabricated on the 20nm process (the older 910 Series and DC S3700 Series, both from 2012, will remain 25nm). Of course Intel has access to smaller processes at this point but, since these are enterprise products, it makes sense for them to use the more tried and true methods for the time being.

If you are interested in enterprise SSDs, keep an eye out in a couple of quarters. Maybe we will even see some stuff coming out of CES in a month.

Also check out Myce for the rest of the leaked slides.

Source: Myce