【2015.07.23】外媒新闻推荐 新谷歌眼镜 R9 Nano Fury X瓶颈解除
本帖最后由 包子侯爵 于 2015-7-23 11:20 编辑新一代谷歌眼镜
http://www.kitguru.net/channel/g ... ture-rugged-design/
R9 Nano开始向合作伙伴供货
http://www.kitguru.net/component ... images-hit-the-web/
R9 Nano部分性能曝光
http://wccftech.com/amd-r9-nano- ... e-heaven-benchmark/
UMC开始批量生产TSV以接触Fury X的瓶颈
http://wccftech.com/umc-begins-volume-production-tsv-hbm/
以上文章将会成为简报或全文翻译，就在本帖会进行分页处理，敬请期待
Title：Google’s next version of Glass to feature ‘rugged’ design
From：http://www.kitguru.net/channel/g ... ture-rugged-design/
We have been hearing more and more about Google’s next version of Glass recently and now it looks like the next iteration of the wearable will go through a bit of a redesign in an effort to make it more rugged and durable for enterprise use. Google is currently working on the Glass Enterprise Edition as it prepares to take the wearable in to a slightly different direction.
我们已经听到越来越多关于下一个版本的谷歌眼镜的消息。现在看起来下一代产品将会有一点重新设计，使其更加的坚固耐用，便于企业用户使用。谷歌目前正在开发谷歌眼镜企业版，产品将准备让可穿戴部分放到稍微不同的方向。
According to 9to5Google, Glass Enterprise Edition won’t be too different from the ‘Explorer Edition’ wearable we are all used to seeing, though it will be re-purposed and designed around use in businesses. The popular rumour and leak site has knowledge of a few Glass prototypes that are nearing completion, making it clear that we won’t be seeing much of a departure from Glass as we know it.
根据9to5Google，企业版眼镜和我们平时看到了预览版没有什么大的不同，但是它为企业重新定义和设计。传的沸沸扬扬的是几件眼镜已经接近完工，但是我们无法一睹真容。
Internally though, Glass Enterprise Edition will feature a few improvements, including a larger prism display and an Intel Atom processor, two things we originally heard about a few weeks ago. Alongside that will be a larger battery and better heat management, something that the original Glass suffered from occasionally.
虽然在内部，谷歌眼镜企业版有一些改进，包括更大的棱镜显示屏和Intel Atom处理器（APU快上{:5_138:} ）。这些将会需要更大容量的电池和更好的热能管理（这都是原版谷歌眼镜遇到过的问题）
Google has a few ‘Glass for Work’ partners, so the Enterprise Edition will likely be sent out to these select workplaces for testing and feedback. The report also notes that we do not currently know anything about pricing or retail availability, although the likelihood of retail availability seems low.
谷歌有一些“Glass for Work”合作伙伴，所以企业版看起来会送到这些选定的工作室来进行测试和反馈。报道也指出，我们现在还不知道价格或者是否零售的消息，虽然零售的可能性微乎其微。
KitGuru Says: Since Google is not currently targeting consumers with Glass as it did in the past, we likely won’t see the new version out in the wild much, if at all. Though it will be interesting to see what Google has in mind for workplace use when it comes to the Glass wearable.
网站点评：由于谷歌眼镜和以前一样没有瞄准消费者群体，所以我们不能过多的看到新版本的内容。但谷歌为工作时使用眼镜的想法（效果）应该挺有趣的。
Title：AMD begins shipments of Radeon R9 Nano to partners, images hit the web
From：http://www.kitguru.net/component ... images-hit-the-web/
A web-site has published the first images of AMD’s third graphics card based on the code-named “Fiji” graphics processing unit – the AMD Radeon R9 Nano. The publication of the picture indicates that AMD had already finalized specifications of the product and recently started to ship it to select partners.
一家网站公布了AMD Fiji家族的第三张显卡AMD Radeon R9 Nano的首张图片。图片的发布表示AMD已经完成了产品规格，最近将会给选定的合作伙伴出货。
Iyd.Kr web-site this week published two images of AMD Radeon R9 Nano, the highest-performing small form-factor graphics card for mini-ITX systems. The graphics board looks exactly like on renders by Advanced Micro Devices: it seems to have a very solid design and its cooling system looks very compact.
本周 Iyd.Kr 网站公布了两张AMD Radeon R9 Nano的图像，为mini-ITX板设计的高性能小尺寸的显卡。显卡看起来很像AMD展示的样子：他似乎有很坚实的设计和非常紧凑的散热系统。
The Radeon R9 Nano is reportedly based on the fully-fledged “Fiji” graphics processing unit with 4096 stream processors, 256 texture units, 64 raster operations pipelines and 4096-bit memory interface. The card is equipped with 4GB of high-bandwidth memory operating at 1GHz, which provides 512GB/s of bandwidth.
Radeon R9 Nano据报道也是基于完整的fiji核心，拥有4096个流处理器，256个纹理单元，64个光栅单元和HBM显存，该卡拥有能在1GHz工作的4GBHBM显存（能提供512GB/s的传输性能）。
Peak thermal design power of the graphics adapter is 175W, but its final GPU clock-rate is unknown. Unofficial estimates point to 830MHz – 900MHz frequency, but AMD keeps the final specifications under wraps.
官方设计功率是175W，但是最终的GPU主频未知，非官方说法是830MHz~900MHz，而AMD仍然对最终规格保密。
Pricing of AMD Radeon R9 Nano is yet to be discovered. AMD plans to officially unveil the product in August.
AMD Radeon R9 Nano的价格目前为止，AMD打算在八月正式发布该产品。
AMD did not comment on the news-story.
AMD未就此报道发表评论。
KitGuru Says: Keeping in mind that AMD has started to ship samples of the product to its partners, it is now a matter of time before the final specs and performance numbers of the AMD Radeon R9 Nano leak.
网站点评：要寄出AMD已经向合作伙伴供货了，现在要知道泄露的最后规格和性能数据只是时间问题
Title：AMD’s Radeon R9 Nano Smiles For The Camera – Benchmarked At 26.6 Frames Per Second On Unigine Heaven 4K Benchmark
From：http://wccftech.com/amd-r9-nano- ... e-heaven-benchmark/
It has been almost 2 months since we first heard about the existence of the R9 Nano in a rumour. Very little was known about the card then except the its name. Now however, we have pretty much all the relevant info on the Nano sized Fiji offering. We have another nano sized update today from DGLee over at IYD.KR. The pictures of the surprisingly tiny but very powerful GPU are here for everyone to see – as well as performance numbers (official).
近两个月来我们第一次听到R9 Nano的谣言，很少人知道该卡（除了名字）。但是现在我们有几乎所有的R9 Nano尺寸信息。我们在IYF.KR的DGLee发布的内容上得到了尺寸。这些图片展示了小巧但强大的GPU以及性能参数（官方）
A slide from the AMD Press Deck. @AMD Public Domain（来自AMD）
Pictures of the AMD R9 Nano surface – official performance and efficiency numbers revealed
AMD R9 Nano外表 –官方性能和耗能
static/image/hrline/1.gif
The R9Fury X is tiny, at around 19 centimetres but the R9 Nano is well, nano, measuring in at only 15 centimetres. Its small form factor design would enable it to be fitted in the tiniest mini-iTX casings out there and its impressive efficiency would enable it to be remarkably powerful at the same time. The card rocks an allegedly full sized Fiji core with 4096 SPs. It is touted as being an efficiency monster with the same performance as the Radeon R9 290X but half the power draw. This is a remarkable card in any way you consider it and here is a good luck at the the shape of the card itself.
R9Fury X是很小的，在大约19厘米。不过 R9 Nano更厉害，经测量只有15厘米，小巧的外形使它能够被安放在最小的Mini-ITX机箱里，同时又有令人印象深刻的效率。该卡有完整的Fiji核心，有4096个流处理器，号称能与Radeon R9 290X有相似的性能但是只需要一半的电能。这是一款了不起的显卡，以下是外形。
Pictures courtesy of DGLee @IYD.KR（来自IYD.KR的DGLee）
The card features a tiny heatsink (by GPU standards) and a lone single axial cooler. If the chip is indeed the full Fiji die then I would assume it is going to be clocked low for it to be efficient enough (and not overwhelm the modest heat dissipation equipment). Now that I have mentioned that, I cant help but wonder what would happen if someone were to mod onto it an after-market heatsink with double or tipple the heat dissipation capacity. Ofcourse, AMD has probably used cherry picked chips in the Fury Nano, so I wouldn’t be surprised if its actually priced higher or near the Fury X (caution: opinion).
该卡拥有一个小型的散热片（由GPU为标准）和一个风扇。如果芯片确实是完整Fiji核心，那主频将会降低。（此处略去N个字）AMD可能在Fury Nano上会使用cherry picked chips，如果价格接近或高于Fury X也不是什么奇怪的事。
Its time for the benchmark and efficiency numbers provided by AMD. The benchmarking by AMD was conducted at rig rocking an i7-5960X (no CPU bottlenecking of any sort) and X99 setup with ample ram. The program used was the Unigine Heaven Benchmark at its 4K settings (3840×2160 resolution, Extreme present, 0xAA). Now we know the Fury Nano has a TDP of 175W and AMD has obligingly given the efficiency numbers for both cards.
寄存测试和效率由AMD提供。AMD的基准测试在i7-5960X和X99平台上进行，用Unigine Heaven Benchmark（4K下 3840×2160分辨率，特高设置 0xAA）。现在我们知道Fury Nano的TDP是175W，AMD也给出了两张卡的效率。
Pictures courtesy of DGLee @IYD.KR
The R9 Fury Nano has an efficiency of 0.152 fps/Watt at the above settings in this 4K benchmark, whileas the R9 290X has an efficiency of 0.076 fps. Simply multiplying the efficiency by the TDP we arrive at the actual score of the R9 Nano: 26.6 frames per second at a 4K benchmark – not bad at all. Ofcourse its worth noting that running a benchmark in 4K fully exploits the HBM capability of the Nano, so the efficiency difference might not be as high at lower resolutions where the HBM factor does not come into play. These are after all the official numbers, so it would be exceedingly unwise to take them without a grain of salt.
简翻：R9 Fury Nano的效率是0.152 fps/瓦，R9 290X是0.076 fps/瓦。
It is also worth noting that while the bandwidth of the R9 290X is 320GB/s it only has 2816 stream processors so the Bandwidth Per SP of the R9 290x is 0.1136 GB/s. On the other hand the Nano (if the rumors are true) has 4096 SPs with 512 GB/s bandwidth – the effective Bandwidth Per SP becomes 0.1250 GB/s. So when you take a look at the full picture, it isn’t actually that huge of a difference as one might think at first glance. In a way the Fiji Core is not benefiting as much as it could from the HBM due to the fact that it has such a large number of cores. Needless to say, HBM2 should be quite a step up from the HBM1 used here.
简翻：但是R9 290X只有320GB/s的传输带宽和2816个流处理器，效率0.1136 GB/s；而Nano 4096流处理器，512GB/s的传输带宽，效率0.1250 GB/s。
Radeon R9 Nano Specifications
Title：UMC Begins Volume Production of TSVs for AMD’s HBM Powered Graphic Cards – Fury X Supply Bottleneck Removed
From：http://wccftech.com/umc-begins-volume-production-tsv-hbm/
UMC, short for United Microelectronics Corporation, has entered into volume production of the TSVs (Through Silicon Vias) used in the production of the HBM technology made popular in the Fiji products from AMD. The short quantity of this particular piece of technology can very well have proven to be a bottleneck in the consistent supply of Radeon R9 Fury Series GPUs.This report by PRNewsWire however, should allay any fears of a constant shortage scenario.
UMC，联华电子公司的简称们已经进入批量生产TSV（硅通孔）来给HBM技术的AMD Fiji产品使用。这一特殊的技术将弥补Radeon R9 Fury系列GPU的生产短板。这份由PRNewsWire的报道，将会缓和产品短缺的担忧。
A slide showcasing the finer features of the 2.5D stacking tech used in the Fury Series. @AMD Public Domain（Fury系列的2.5D技术，来自AMD）
UMC starts volume production of TSVs, bottleneck in the AMD R9 Fury series eliminated
联华电子公司开始批量生产TSV产品来打破AMD R9 Fury系列瓶颈
static/image/hrline/1.gif
Let me give a short overview of the HBM technology first. The interposer is made by UMC as well, and employs the TSV (the standard tech for coupling stacked dies) process for stacking DRAM dies. A CMOS redistribution layer is used to place micro bumps to make the dies communicate with the interposer while TSVs are drilled through. All this is done in the 300mm Fab 12 foundry (UMC) in Singapore. Here is the thing however, UMC hadn’t entered into volume production of Through Silicon Vias until very recently (20th July 2015) and this meant that there was a very big bottleneck in the Radeon R9 Fury X supply chain. Here is what UMC had to say on the occasion:
简翻：
“AMD has a successful history of delivering cutting-edge GPU products to market,” said S.C. Chien, vice president of Corporate Marketing and co-chair of the TSV committee at UMC. “This volume production milestone is the culmination of UMC’s close TSV collaboration with AMD, and we are happy to bring the performance benefits of this technology to help power their new generation of GPU products. We look forward to continuing this fruitful partnership with AMD for years to come.”
AMD has previously confirmed that they are having supply problems (too much demand) with the R9 Fury Series (released so far); and with the R9 Nano releasing next month, it was only going to get worst. The good news (or brilliant news rather) is that UMC has ramped up its production significantly – so all HBM1 equipped products should have no supply issues (far as HBM/TSV/Interposer tech is concerned) and all AIBs can have their fill of the coveted memory standard. The only issue now would be the dies itself, which shouldn’t probably pose too much of a problem seeing AMD must have been expecting this level of demand.
The R9 Fury X, Fury and Nano GPUs use a 2.5D interposer schematic where the GPU and the HBM is placed on an interposer. This tactic increases the yield significantly and is far cheaper than a pure 3D stack, not to mention makes heat dissipation a alot easier. AMD has been at the bleeding edge of memory technology and while it has faced down a few hurdles, it looks like things are finally starting to look up for AMD. If the demand for the Fiji powered graphic cards holds then it (and AIBs) should now be able to radically increase its supply to meat the demand.
页:
[1]