- In Japan, single-slot Quadro graphics accelerators with Pascal architecture appeared on sale - Developers of hybrid airliners promise to make flights shorter and cheaper - Google TPU accelerators leave behind Intel CPU and NVIDIA GPU - Xiaomi Mi6 will be presented in the second half of April -

	xtreview is your : Video card - cpu - memory - Hard drive - power supply unit source

POSTER: computer news   ||    IN JAPAN, SINGLE-SLOT QUADRO GRAPHICS ACCELERATORS WITH PASCAL ARCHITECTURE APPEARED ON SALE	DATE:2017-04-06
In Japanese stores professional Quadro accelerators with Pascal architecture  ,  were presented at the beginning of last year  .  By the way, the flagship Quadro GP100 with 16 GB of HBM2 memory among the new products of Japanese retail is not present, the exposition consists entirely of single-slot graphics solutions without additional power connectors. The most expensive accelerators of this family, discovered by Japanese colleagues, Quadro P4000.   The Quadro P4000 combines 1792 stream processors and 8 GB of GDDR5 memory with a 256-bit bus, the power consumption level does not exceed 105 watts.  The rear panel provides four outputs of DisplayPort 1.4, which allow you to output an image with a resolution of 5120 x 2880 pixels. The Quadro P2000 is designed on a shorter PCB, but always occupies one expansion slot.  This professional graphics card combines 1024 stream processors with a 160-bit bus and 5 GB of GDDR5 memory.  Unlike the Quadro P4000, which is based on the GP104, this graphics card uses a GP106 GPU.  The TDP level does not exceed 75 W, on the rear panel four full-size DisplayPort 1.4 outputs are preserved.   In fact, the Quadro P1000 and Quadro P600 are very similar to each other, because they combine a low-profile version with a compact cooling system.  The first offers 640 stream processors, a 128-bit bus and 4 GB of GDDR5 memory, content with a TDP level of not more than 47 watts. The second, Quadro P600, retained only 384 stream processors, although it is also based on the GP107 GPU.  Its 128-bit bus in this case communicates with 2 GB of GDDR5 memory, and the TDP level does not exceed 40 watts. Both video cards are able to offer four outputs of mini-DisplayPort 1.4. Quadro P400 is inferior not only in the number of outputs on the rear panel (there are only three), but also by the number of active stream processors - it does not exceed 256 pieces.  In addition, the video card has a 64-bit bus that connects the GP107 GPU to 2 GB of GDDR5 memory.  The TDP level does not exceed 30 W. Select Rating : Currently 10.00/10 1 2 3 4 5 6 7 8 9 10 48254 Rating: 10.0/10 (5 votes cast) In Japan, single-slot Quadro graphics accelerators with Pascal architecture appeared on sale	Add Comment ( 1 ) IN JAPAN, SINGLE-SLOT QUADRO GRAPHICS ACCELERATORS WITH PASCAL ARCHITECTURE APPEARED ON SALE

POSTER: computer news   ||    DEVELOPERS OF HYBRID AIRLINERS PROMISE TO MAKE FLIGHTS SHORTER AND CHEAPER	DATE:2017-04-06
Many companies are now thinking about the creation of aircraft on electric traction.   A young company Zunum Aero from Washington is developing passenger airliners with a hybrid powerplant: it is believed that gradually such aircraft will reduce the use of fuel, the main part of the route overcoming on electric traction.  At airports where they will land, it is necessary to provide for the possibility of rapid charging or replacement of traction batteries for charged ones. Carriers using hybrid airliners will be able to count on more active use of peripheral airports, and together with lower fuel costs, this will help increase the availability of air travel.  Short routes, as representatives of Zunum Aero explain, form up to 40% of harmful emissions from aviation activities.  The introduction of hybrid airliners will reduce the negative impact of aviation transport on the environment.  In addition, the electric aircraft should make less noise.  "Washington Dreamers" already support the company Boeing and jetBlue.   Select Rating : Currently 10.00/10 1 2 3 4 5 6 7 8 9 10 48253 Rating: 10.0/10 (4 votes cast) Developers of hybrid airliners promise to make flights shorter and cheaper	Add Comment ( 1 ) DEVELOPERS OF HYBRID AIRLINERS PROMISE TO MAKE FLIGHTS SHORTER AND CHEAPER

POSTER: computer news   ||    GOOGLE TPU ACCELERATORS LEAVE BEHIND INTEL CPU AND NVIDIA GPU	DATE:2017-04-06
Nearly a year ago, at a Google IO home conference, the company told that since 2015 its accelerators Tensor Processing Units (TPU) are working in its data center.  The project itself started in 2013.  It took 15 months to develop the first ASIC, which was the base of TPU accelerators.  A detailed report on the work of the TPU, architecture and platforms based on accelerators will be made this summer at an industry conference, and for now the company offers a 17-page abstract on the topic. TPU accelerators are designed to accelerate the work of self-learning computing systems based on deep machine learning.  Neural networks with deep training, for example, have already made it possible to make a giant leap in speech recognition - the largest in the last 20 years.  So, if you compare the work of Google TPU with traditional platforms for recognition, errors in recognizing words became 30% less.  Also, errors in pattern recognition have been reduced.  With respect to the ImageNet environment, the number of errors since 2011 has decreased from 26% to 3.5%.  Without accelerators TPU, recognized in Google, the capacity of branded data centers would have to be doubled if users of the company's services began to use the voice to enter teams at least three minutes a day. Earlier in the company reported that the accelerator TPU demonstrates a 10-fold advantage in solving similar problems in front of x86-compatible processors and modern graphics processors.  A recent report points to a more significant advantage of Google's solution.  When compared with the Intel Haswell E5-2699 v3 processor (22 nm, 18 cores, 2.3 GHz, 145 W) and 180-watt NVIDIA K80 accelerator at 875 MHz, Google TPU accelerators are 30-80 times faster than competitors in terms of performance per watt. It should be noted that in terms of energy efficiency, Google's development is still behind Haswell and K80, but Google blames the short terms for which it was necessary to create a solution.  So, at a load of 10%, the Google TPU accelerator consumes 88% of the maximum level, while Intel Haswell consumes 56% of the maximum on the same level of load, and NVIDIA K80 - 66%.  Also in Google recognize the existence of faster solutions competitors - 14-nm Intel CPU and 16-nm GPU NVIDIA, which will look better than models two years ago.  But even here the developers have a stock.  For example, Google TPU works with DDR3 memory, and the transition to GDDR5 will open new horizons for performance. The current accelerators of Google TPU consume up to 40 watts and are created using a 28-nm process technology.  The clock frequency of the solution reaches 700 MHz.  The solution accelerates the work of algorithms of the company's proprietary software - TensorFlow.  With the same support, NVIDIA accelerators work.  The basic logic of the TPU is 65 536 8-bit blocks operating with multiply-accumulate units.  The amount of cache in the TPU is 24 MB.  The memory block is the largest in the chip and occupies 29% of crystal area of .  Another large block (24% of the area) is an array for controlling media access (MAC).  The internal data bus is 256-bit.  Together, this allows  to perform 92 ter-operations per second. Select Rating : Currently 10.00/10 1 2 3 4 5 6 7 8 9 10 48252 Rating: 10.0/10 (4 votes cast) Google TPU accelerators leave behind Intel CPU and NVIDIA GPU	Add Comment ( 1 ) GOOGLE TPU ACCELERATORS LEAVE BEHIND INTEL CPU AND NVIDIA GPU

POSTER: computer news   ||   XIAOMI MI6 WILL BE PRESENTED IN THE SECOND HALF OF APRIL	DATE:2017-04-06
Recently, Xiaomi CEO Lei Jun confirmed that the new Mi6 flagship will be introduced in April , but he did not mention the exact date of its official announcement.  And now the Chinese source said that Xiaomi Mi6 will make its debut in the second half of this month. According to the source, which refers to the publication GizmoChina , the announcement of Xiaomi Mi6 will be held in the second half of April.  They also hinted that at the launch (during the first week) Xiaomi Mi6 will be released in circulation of 50 thousand units, after which Xiaomi will increase the supply volumes of the new flagship. Also, the source said that the cost of Xiaomi Mi6 will be above $ 300. As expected, along with Xiaomi Mi6 in April, its Plus version will debut, which will receive a dual main camera, a 5.7-inch display with narrow frames around the edges and a dual camera.  The exact price of Xiaomi Mi6 is still unknown. Select Rating : Currently 10.00/10 1 2 3 4 5 6 7 8 9 10 48251 Rating: 10.0/10 (5 votes cast) Xiaomi Mi6 will be presented in the second half of April	Add Comment ( 1 ) XIAOMI MI6 WILL BE PRESENTED IN THE SECOND HALF OF APRIL

	xtreview is your : Video card - cpu - memory - Hard drive - power supply unit source

computer news computer parts review OLD Forum Downloads New Forum Login Join Articles terms Hardware blog Sitemap myspace proxy Get Freebies