Subject: General Tech | December 7, 2016 - 01:25 PM | Jeremy Hellstrom
Tagged: qualcomm, centriq, centriq 2400, server
The days when AMD and Intel were the two choices to build a server with are long gone. The ARM architecture has been making serious inroads as various vendors have begun to offer various solutions utilizing ARM designs, up to and including AMD for that matter. Today, Qualcomm have joined these ranks, announcing their first processor family designed to power a server. The Centriq 2400 series is based on a 10nm process node, with up to 48 cores. As The Inquirer points out, this is a rather impressive shot across Intel's bow as Qualcomm will ship a 10nm FinFET before Intel does.
"The Qualcomm Centriq 2400 series, the first in the Centriq product family that Qualcomm has been working on for four years, has up to 48 ARMv8-compliant cores targeting compute-intensive data centre applications that require power efficiency and is built on the 10nm FinFET manufacturing processor."
Here is some more Tech News from around the web:
- Broadcom quietly dismantles its 'Vulcan' ARM server chip project @ The Register
- Sony kills off secret backdoor in 80 internet-connected CCTV models @ The Register
- Mikko Hypponen On The Death Of Antivirus @ Tech ARP
- Christmas 2016 Mega Worldwide Giveaway @ NikKTech
Today Micron initiated the first of a multi-tier launch of a new SATA Enterprise SSD lineup built around their IMFT 32-layer 3D NAND Flash. It may seem odd for a full enterprise line to use IMFT 3D TLC, as that flash has not been known for the high random IOPS demands of the datacenter, but Micron looks to be making it work, and work well.
Above is a performance consistency plot of their MAX model. While this does have the highest OP of all of the models, the consistency is surpassing even NVMe models (using a bus *much* faster than SATA). Sure the results are only using 1-second averages and not our Latency Percentile, but we will be able to pick out any single-IO inconsistencies once we get samples in for detailed review.
Saturated IOPS performance also looks good 'on paper'.
The advantage to operating their flash in TLC mode is that the per die capacity moves from 32GB to 48GB, ultimately driving down the cost/GB of these products and making them an easier sell to enterprise customers. It also enables high capacities - the max capacity of the model with the least overprovisioning (ECO) will reach 8TB in a 2.5" SATA form factor when the last leg of this launch is completed later next year.
The three lines are all using the same controller and base firmware, but with differences in how the dies are laid out with respect to expected performance and endurance.
Below are all of the products being launched. All products use a Marvell 88SS1074 controller at SATA 6Gbit:
- 5100 ECO
- 2.5" 7mm: 480, 960, 1920, 3840, 7680 GB
- M.2 2280: 480, 960, 1920 GB
- Sequential read/write: 540 / 380-520 MB/s
- Random read/write: 93k / 9k-31k IOPS
- Endurance: <=1 DWPD
- Cost / GB: $0.45 - $0.55
- 5100 PRO
- 2.5" 7mm: 240, 480, 960, 1920, 3840 GB
- M.2 2280: 240, 480, 960, 1920 GB
- Sequential read/write: 540 / 380-520 MB/s
- Random read/write: 78 (240GB)-93k / 26k-43k IOPS
- Endurance: 1-3 DWPD
- Cost / GB: $0.55 - $0.65
- 5100 MAX
- 2.5" 7mm: 240, 480, 960, 1920 GB
- M.2 2280: (none)
- Sequential read/write: 540 / 310-520 MB/s
- Random read/write: 93k / 48k-74k IOPS
- Endurance: 5 DWPD
- Cost / GB: $0.65 - $0.75
All models come with Micron 'Flex Capacity', which enables custom *increases* in OverProvisioning. Flex Security enables FIPS 140-2 validated 256-bit AES encryption.
The specs are very good when you consider their performance consistency claims, meaning a 74k IOPS random write rating applies to random writes across the *entire span* of the SSD *at steady state*. Consumer SSD firmware typically chokes with this type of workload, even ones equipped with MLC flash.
We will have more on the 5100 Series from Micron as these products are rolled out and sampled to us for performance review.
Press blast after the break.
Subject: General Tech | December 5, 2016 - 01:50 PM | Jeremy Hellstrom
Tagged: Intel, Puma, latency, lag
Intel's Puma 6 system on a chip is a popular choice in modem provided by ISPs across the western world and if you have recently upgraded your broadband modem you may have noticed an undesirable side effect. There is an issue with the chip which is causing bursts of high latency, ruining video streaming and gaming for those affected by the issue. There is good news, The Register confirmed with Intel that a fix is forthcoming and you should expect your ISP to push out a firmware update soon, hopefully not while you are in the middle of something important.
"Intel's Puma 6 chipset, used in gigabit broadband modems around the world, suffers from latency jitter so bad it ruins online gaming and other real-time connections."
Here is some more Tech News from around the web:
- Sh... IoT just got real: Mirai botnet attacks targeting multiple ISPs @ The Register
- Does Windows 10's Data Collection Trade Privacy For Microsoft's Security? @ Slashdot
- Elon Musk uses GTA V to accelerate AI rise of the Terminators @ The Inquirer
- Netflix Keeping Bandwidth Usage Low By Encoding Its Video With VP9 and H.264/AVC Codecs @ Slashdot
- Windows 10 'HomeHub': Microsoft to rival Amazon Echo with no new devices @ The Inquirer
- AK Racing PRO X Gaming Chair Review @ NikKTech
- I made my dumb appliances smarter with the Internet of Things @ The Tech Report
Third annual release
For the past two years, AMD has made a point of releasing one major software update to Radeon users and gamers annually. In 2014 this started with Catalyst Omega, a dramatic jump in performance, compatibility testing and new features were the story. We were told that for the first time in a very long while, and admitting this was the most important aspect to me, AMD was going to focus on building great software with regular and repeated updates. In 2015 we got a rebrand along with the release: Radeon Software Crimson Edition. AMD totally revamped the visual and user experience of the driver software, bringing into the modern world of style and function. New features and added performance were also the hallmarks of this release, with a stronger promise to produce more frequent drivers to address any performance gaps, stability concerns and to include new features.
For December 2016 and into the new year, AMD is launching the Radeon Software Crimson ReLive Edition driver. While the name might seem silly, it will make sense as we dive into the new features.
While you may have seen the slides leak out through some other sites over the past 48 hours, I thought it was worth offering my input on the release.
Not a performance focused story
The first thing that should be noted with the ReLive Edition is that AMD isn’t making any claims of substantially improved performance. Instead, the Radeon Technologies Group software team is dedicated to continued and frequent iterations that improve performance gradually over time.
As you can see in the slide above, AMD is showing modest 4-8% performance gains on the Radeon RX 480 with the Crimson ReLive driver, and even then, its being compared to the launch driver of 16.6.2. That is significantly lower than the claims made in previous major driver releases. Talking with AMD about this concern, it told us that they don’t foresee any dramatic, single large step increases in performance going forward. The major design changes that were delivered over the last several years, starting with a reconstruction of the CrossFire system thanks to our testing, have been settled. All we should expect going forward is a steady trickle of moderate improvements.
(Obviously, an exception may occur here or there, like with a new game release.)
Radeon ReLive Capture and Streaming Feature
So, what is new? The namesake feature for this driver is the Radeon ReLive application that is built in. ReLive is a capture and streaming tool that will draw obvious comparisons to what NVIDIA has done with GeForce Experience. The ReLive integration is clean and efficient, well designed and seems easy to use in my quick time with it. There are several key capabilities it offers.
First, you can record your gameplay with the press of a hotkey; this includes the ability to record and capture the desktop as well. AMD has included a bevy of settings for your captures to adjust quality, resolution, bitrate, FPS and more.
ReLive supports resolutions up to 4K30 with the Radeon R9 series of GPUs and up to 1440p30 with the RX 480/470/460. That includes both AVC H.264 and HEVC H.265.
Along with recording is support for background capture, called Instant Replay. This allows the gamer to always record in the background, up to 20 minutes, so you can be sure you capture amazing moments that happen during your latest gaming session. Hitting a hotkey will save the clip permanently to the system.
Subject: Storage | December 6, 2016 - 03:32 PM | Jeremy Hellstrom
Tagged: kingston, dc400, enterprise ssd
One does not usually think of Kingston when building out a server but perhaps the DC 400 series of SSDs might change that. It uses 15nm MLC NAND and a pair of quad core Phison PS3110-S10 controllers, each with 256GB DDR3L-1600 of cache. You will find enterprise class features such as SmartRefresh, SmartECC and firmware controlled power loss management. Currently there are 480GB and 960GB models, with a 1.6TB model expected soon and all models have over-provisioning which can be modified by the user after purchase. Pop over to Kitguru to see if the drive can meet its advertised speeds.
"Kingston’s DC400 series are the latest additions to the companies Enterprise range of SSDs and have been designed as entry level drives for data centers. The new drives have been built with read-intensive applications in mind for use in a mixed workload environments."
Here are some more Storage reviews from around the web:
- ADATA Premier SP550 480GB Solid-State Drive Review @ Techgage
- Plextor S2C 512GB Entry-Level SATA3 SSD @ eTeknix
- TerraStation F2-220 2-Bay SMB Cloud Storage NAS @ eTeknix
- Seagate Skyhawk 10TB Review @ OCC
Subject: General Tech | December 7, 2016 - 03:04 PM | Jeremy Hellstrom
Tagged: nvidia, amd, gaming, watch dogs 2, GTX 1080, gtx 1070, gtx 1060, rx 480x, rx 470
[H]ard|OCP have spent a lot of with Watch Dogs 2 recently, enough to create three articles covering the game of which two are now published. The first article focuses on performance at ultra settings and finding the highest playable settings that the GPUs they tested were capable of, without installing the high resolution texture pack. As it turns out, the game is much more graphically demanding than many other recent releases, so much so that only the Titan X and GTX 1080 was able to perform at 4k resolutions, the GTX 1070 and 1060, as well as the RX 480 and 470 only feature at lower resolutions.
The second article looks at performance with the texture pack installed, which did not have much effect on overall performance but significantly increased VRAM usage. Even the mighty Titan X struggled with this game, we will need a new generation of GPUs to utilize all the available graphics features available in this game. The last review will be up soon and will focus on what effect each of the graphical settings have on the visual appearance of the game.
"Watch Dogs 2 has been released on the PC. We will have a three part evaluation of performance and image quality starting today with performance comparisons. We will also find the highest playable settings for each graphics card and the gameplay experience delivered. Finally, a graphically demanding game."
Here is some more Tech News from around the web:
- Ubisoft Giving Away Yet Another Free Game @ [H]ard|OCP
- Dishonored 2 update 1.3 brings performance boosts @ Rock, Paper, SHOTGUN
- Tobii Tech 4C eye tracker for gaming @ Kitguru
- Wot I Think: Tyranny @ Rock, Paper, SHOTGUN
- Gears of War 4 DirectX 12 Graphics Performance @ eTeknix
- Sniper Ghost Warrior 3 is an off-brand Far Cry game @ Rock, Paper, SHOTGUN
- The Last Guardian Is Finally Here—and Yes, It Was Worth the Wait @ Wired
- Dead Rising 4 shambles onto Windows 10 @ Rock, Paper, SHOTGUN
- Nvidia launches GeForce GTX 1050 and 1060 Indie Bundle @ HEXUS
- Deus Ex: Mankind Divided Graphics Performance Analysis @ eTeknix
- Mugs and mayhem: eight minutes of Prey @ Rock, Paper, SHOTGUN
- Tenebra is a free horror game inspired by silent films @ Rock, Paper, SHOTGUN
Subject: Processors | December 8, 2016 - 09:00 AM | Josh Walrath
Tagged: Xilinx, TSMC, standard cells, layout, FinFET, EDA, custom cell, arm, 7nm
Today ARM is announcing their partnership with Xilinx to deliver design solutions for their products on TSMC’s upcoming 7nm process node. ARM has previously partnered with Xilinx on other nodes including 28, 20, and 16nm. Their partnership extends into design considerations to improve the time to market of complex parts and to rapidly synthesize new designs for cutting edge process nodes.
Xilinx is licensing out the latest ARM Artisan Physical IP platform for TSMC’s 7nm. Artisan Physical IP is a set of tools to help rapidly roll out complex designs as compared to what previous generations of products faced. ARM has specialized libraries and tools to help implement these designs on a variety of processes and receive good results even on the shortest possible design times.
Design relies on two basic methodologies. There is custom cell and then standard cell designs. Custom cell design allows for a tremendous amount of flexibility in layout and electrical characteristics, but it requires a lot of man-hours to complete even the simplest logic. Custom cell designs typically draw less power and provide higher clockspeeds than standard cell design. Standard cells are like Legos in that the cells can be quickly laid out to create complex logic. Software called EDA (Electronic Design Automation) can quickly place and route these cells. GPUs lean heavily on standard cells and EDA software to get highly complex products out to market quickly.
These two basic methods have netted good results over the years, but during that time we have seen implementations of standard cells become more custom in how they behave. While not achieving full custom performance, we have seen semi-custom type endeavors achieve appreciable gains without requiring the man hours to achieve fully custom.
In this particular case ARM is achieving a solid performance in power and speed through automated design that improves upon standard cells, but without the downsides of a fully custom part. This provides positive power and speed benefits without the extra power draw of a traditional standard cell. ARM further improves upon this with the ARM Artisan Power Grid Architect (PGA) which simplifies the development of a complex power grid that services a large and complex chip.
We have seen these types of advancements in the GPU world that NVIDIA and AMD enjoy talking about. A better power grid allows the ASIC to perform at lower power envelopes due to less impedence. The GPU guys have also utilized High Density Libraries to pack in the transistors as tight as possible to utilize less space and increase spatial efficiency. A smaller chip, which requires less power is always a positive development over a larger chip of the same capabilities that requires more power. ARM looks to be doing their own version of these technologies and are applying them to TSMC’s upcoming 7nm FinFET process.
TSMC is not releasing this process to mass production until at least 2018. In 1H 2017 we will see some initial test and early production runs for a handful of partners. Full blown production of 7nm will be in 2018. Early runs and production are increasingly being used for companies working with low power devices. We can look back at 20/16/14 nm processes and see that they were initially used by designs that do not require a lot of power and will run at moderate clockspeeds. We have seen a shift in who uses these new processes with the introduction of sub-28nm process nodes. The complexity of the design, process steps, materials, and libraries have pushed the higher performance and power hungry parts to a secondary position as the foundries attempt to get these next generation nodes up to speed. It isn’t until after some many months of these low power parts are pushed through that we see adjustments and improvements in these next generation nodes to handle the higher power and clockspeed needs of products like desktop CPUs and GPUs.
ARM is certainly being much more aggressive in addressing next generation nodes and pushing their cutting edge products on them to allow for far more powerful mobile products that also exhibit improved battery life. This step with 7nm and Xilinx will provide a lot of data to ARM and its partners downstream when the time comes to implement new designs. Artisan will continue to evolve to allow partners to quickly and efficiently introduce new products on new nodes to the market at an accelerated rate as compared to years past.
- 2 of 2