GCN 1.3 | KitGuru https://www.kitguru.net KitGuru.net - Tech News | Hardware News | Hardware Reviews | IOS | Mobile | Gaming | Graphics Cards Sat, 22 Aug 2015 09:59:01 +0000 en-US hourly 1 https://wordpress.org/?v=6.4.3 https://www.kitguru.net/wp-content/uploads/2021/06/cropped-KITGURU-Light-Background-SQUARE2-32x32.png GCN 1.3 | KitGuru https://www.kitguru.net 32 32 AMD readies three new GPUs: Greenland, Baffin and Ellesmere https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-readies-three-new-gpus-for-2016-greenland-baffin-and-ellesmere/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-readies-three-new-gpus-for-2016-greenland-baffin-and-ellesmere/#comments Thu, 20 Aug 2015 21:27:02 +0000 http://www.kitguru.net/?p=264345 In the recent years, Advanced Micro Devices has reduced the amount of new graphics processors it releases per annum, which lead to massive erosion of its market share and revenue. While the company hopes that its latest product lineup will help it to regain some of the lost share and improve earnings, the firm pins …

The post AMD readies three new GPUs: Greenland, Baffin and Ellesmere first appeared on KitGuru.]]>
In the recent years, Advanced Micro Devices has reduced the amount of new graphics processors it releases per annum, which lead to massive erosion of its market share and revenue. While the company hopes that its latest product lineup will help it to regain some of the lost share and improve earnings, the firm pins considerably more hopes on an all-new family of products that will be released in 2016.

AMD’s code-named “Arctic Islands” family of products will include three brand-new chips – “Greenland”, “Baffin” and “Ellesmere” – a source with knowledge of AMD plans said. The “Greenland” will be the new flagship offering for performance enthusiasts, whereas the “Baffin” and “Ellesmere” will target other market segments, such as high-end and mainstream. It is unclear whether the “Arctic Islands” family will take in any existing products, but it is possible that AMD may address certain markets with previous-gen products.

amd_radeon_artwork_angle_new

“Greenland” will be AMD’s first graphics processing unit based on the all-new micro-architecture, which development began a little more than two years ago. While the architecture is currently known as another iteration of GCN, the new ISA [instruction set architecture] will be so considerably different compared to the existing GCN that it has every right to be called “post-GCN”, the source said. It is likely that the “Greenland” will retain layout of the contemporary AMD Radeon graphics processing units, but there will be significant changes in on the deeper level.

The only official thing currently known about the new architecture, which Mark Papermaster, chief technology officer of AMD, calls the next iteration of GCN, is that it is projected to be two times more energy efficient compared to the current GCN. Essentially, this means means major performance enhancements on the ISA level. Thanks to the fact that the “Greenland” graphics processing unit will be made using either 14nm or 16nm FinFET process technology, expect it to feature considerably larger number of stream processors than “Fiji”.

amd_radeon_fiji_gpu

The “Greenland” graphics processor will rely on the second-generation high-bandwidth memory (HBM), so expect ultra-high-end graphics cards and professional solutions with up to 32GB of DRAM onboard with bandwidth of up to 1TB/s. Consumer-class “Greenland”-based products will likely come with 8GB – 16GB of memory. Due to usage of HBM, expect the “Greenland” chip and upcoming graphics cards on its base to resemble the currently available AMD Radeon R9 Fury-series adapters.

The number of transistors inside the “Greenland” as well as its die size are unknown. Since 14nm/16nm FinFET manufacturing technologies have considerably (up to 90 per cent) higher transistor density than contemporary TSMC’s 28nm fabrication process, it is logical to expect that the new flagship product will feature 15 – 18 billion of elements if it retains around 600mm² die size from the “Fiji”.

It is believed that AMD has already taped-out its “Greenland” graphics processing unit and is about to get the first silicon in the coming weeks.

amd_radeon_shop-home-component

Not a lot of information is known about the “Baffin” and the “Ellesmere”. The source stressed that both GPUs are brand-new and will be designed from scratch. Since the “Baffin” and the “Ellesmere” are named after bigger and smaller islands in Canada, it is likely that the former is a mainstream graphics chip with moderate die size, whereas the former is a small entry-level GPU. AMD began to work on “Ellesmere” about a year ago.

Expect AMD to begin talking about its next-generation graphics architecture in the coming months.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: As it traditionally happens, everything looks very good on paper. If AMD manages to release three brand new chips within a reasonable amount of time in 2016 and the chips will be competitive against Nvidia’s, then it has all the chances to win back market share. However, one should keep in mind that the “next GCN” or the “post-GCN” will not compete against Nvidia’s “Maxwell”, but will have to compete against Nvidia’s “Pascal”, which promises to be very powerful. As a result, expect 2016 is going to be an interesting year for the GPUs…

The post AMD readies three new GPUs: Greenland, Baffin and Ellesmere first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-readies-three-new-gpus-for-2016-greenland-baffin-and-ellesmere/feed/ 87
AMD: We have very strong roadmap for GCN architecture https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-we-have-very-strong-roadmap-for-gcn-architecture/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-we-have-very-strong-roadmap-for-gcn-architecture/#comments Wed, 12 Aug 2015 23:57:59 +0000 http://www.kitguru.net/?p=263320 Despite of ongoing problems and lowering research and development budget, Advanced Micro Devices maintains optimism and claims that it will keep financing development of key products. In the recent months, Advanced Micro Devices has been criticized heavily for re-introducing its previous-generation graphics processing units under new names. The release of one new GPU per year …

The post AMD: We have very strong roadmap for GCN architecture first appeared on KitGuru.]]>
Despite of ongoing problems and lowering research and development budget, Advanced Micro Devices maintains optimism and claims that it will keep financing development of key products.

In the recent months, Advanced Micro Devices has been criticized heavily for re-introducing its previous-generation graphics processing units under new names. The release of one new GPU per year is clearly a result of multiple business decisions, massive layoffs from the company several years ago as well as limited research and development budget. Nonetheless, AMD seems to remain rather optimistic and claims that it has strong APU, CPU and GPU roadmaps. What is particularly interesting is that the company intends to continue improving its GCN [graphics core next] architecture, not introduce something brand new.

“Where we’ve been incredibly protective in maintained investment is in where we are banking the future of the company,” said Mark Papermaster, chief technology officer of AMD, at the at Pacific Crest annual global technology leadership forum, reports Tech Trader Daily. “So it is on that next generation of CPUs starting with ‘Zen’. It is on successive generations of our graphics core next. Huge volume in what we have in not only in discrete graphics and our APU, but the game console wins are all on graphics core next and we have a very strong roadmap for that graphics core next IP going forward.”

amd_graphics_leadership_1

Based on previous comments of Mr. Papermaster made in late-2014 and mid-2015, next year the company intends to release graphics processors that will be based on an architecture that will be considerably different than today’s GCN. In particular, the next iteration of GCN architecture is projected to be two times more energy efficient compared to current GCN and will support new features. Since AMD intends to use 14nm or 16nm FinFET process technologies to make its next-gen GPUs, increased performance and energy efficiency is not surprising.

What is noteworthy is that this year year AMD’s GCN turns four years old. Previously AMD has never used one ISA [instruction set architecture] for over four years. AMD introduced three generations of its TeraScale architectures over four years (in 2006 – 2010), each time bringing major improvements. GCN has also evolved significantly since late 2011 and it looks like AMD wants to continue developing generations of GCN-based GPUs.

amd_graphics_leadership

While AMD’s latest “Fiji” graphics processor based on the third iteration of GCN looks competitive against its rivals, it should be noted that Nvidia has introduced two major architectures (“Kepler” and “Maxwell”) since 2012 and plans to unveil “Pascal” next year.

While architectural innovation may be relatively slow and take time, it should be noted that AMD needs to actually introduce more than one new graphics processor a year, otherwise its lineup will largely consist of outdate GPUs, which will result in further loss of market share.

Discuss on our Facebook page, HERE.

KitGuru Says: It remains to be seen how competitive will AMD’s fourth iteration of GCN be against “Pascal”. Based on AMD’s comments, GCN 1.3 should be rather powerful. But the technology has been on the market for a long time already and nowadays even microprocessor architectures remain on the market only for three to four years.

The post AMD: We have very strong roadmap for GCN architecture first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-we-have-very-strong-roadmap-for-gcn-architecture/feed/ 7
AMD reportedly has priority supply agreement regarding HBM, HBM2 https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-reportedly-has-priority-supply-agreement-regarding-hbm-hbm2/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-reportedly-has-priority-supply-agreement-regarding-hbm-hbm2/#comments Tue, 14 Jul 2015 10:55:38 +0000 http://www.kitguru.net/?p=258850 The first-generation high-bandwidth memory provides extreme performance, but is clearly not perfect for high-end graphics cards due to capacity limitations. A good news is that second-gen high-bandwidth memory is on the way and is due in 2016. Advanced Micro Devices may get it faster and in higher volumes than its arch-rival Nvidia Corp. The only …

The post AMD reportedly has priority supply agreement regarding HBM, HBM2 first appeared on KitGuru.]]>
The first-generation high-bandwidth memory provides extreme performance, but is clearly not perfect for high-end graphics cards due to capacity limitations. A good news is that second-gen high-bandwidth memory is on the way and is due in 2016. Advanced Micro Devices may get it faster and in higher volumes than its arch-rival Nvidia Corp. The only question is when exactly HBM2 is set to be available.

HBM2 to solve HBM's problems

One of the key drawbacks of the first-generation high-bandwidth memory (HBM) is its low capacity. At present, it is impossible to install more than 4GB of HBM on a single-GPU graphics card, which was not a good news for AMD’s Radeon R9 Fury-series adapters. SK Hynix, AMD, JEDEC and a number of other industry players are working on the second-gen high-bandwidth memory (HBM 2), which will solve a lot of problems, including capacity-related. Moreover, Advanced Micro Devices may benefit from priority supply agreement it reportedly has with SK Hynix.

sk_hynix_hbm_dram_2

The first-generation HBM (HBM1) stacks four DRAM dies with two 128-bit channels per die on a base logic die, creating a memory device with a 1024-bit interface. Each channel supports 1Gb capacities (2Gb per die), features 8 banks and can operate at 1Gb/s data-rate (1GHz effective DDR clock-rate). As a result, each HBM 4Hi stack (4 high stack) package can provide 1GB capacity and 128GB/s memory bandwidth. The second-generation HBM (HBM2) utilizes 8Gb dies with two 128-bit channels featuring 16 banks and sporting up to 2Gb/s data-rates (2GHz effective DDR frequency). The architecture of the HBM2 will let manufacturers built not only 4Hi stack (4 high stack) packages, but also 2Hi stack and 8Hi stack devices. As a result, memory producers will be able to assemble HBM2 memory chips with up to 8GB capacity (8Hi stack) and up to 256GB/s bandwidth (2Gb/s data rate, 1024-bit bus). Architectural advantages of HBM2 will allow GPU developers to use it not only for ultra-high-end applications with 4096-bit memory bus, but also for adapters that do not require extreme performance.

The industry needs HBM2

Advanced Micro Devices has already announced that it would use HBM memory going forward for a broad range of its ICs [integrated circuits], including graphics processing units and accelerated processing units. Right now, the company is working on its all-new family of graphics processing units based on the next iteration of GCN architecture with increased power efficiency and performance. AMD’s next high-end GPU code-named “Greenland” will be made using 16nm or 14nm FinFET process technology, which will help AMD to considerably increase transistor and stream processor counts compared to the code-named “Fiji” (AMD Radeon R9 Fury-series). As a result, “Greenland” will require more advanced memory and AMD plans to use HBM2 for it.

nvidia_pascal_module

Nvidia will also produce its code-named “Pascal” chips using TSMC's 16nm FinFET process technology and will also dramatically boost transistor count vs. existing graphics processing unit. It is expected that Nvidia's code-named GP100 chip will also need a high-end memory sub-system, presumably based on HBM2. At least, Nvidia officially revealed plans to use “3D memory” with “Pascal”.

Supply agreement

Since AMD has been a key developer of both HBM and HBM2, there is a contract in place that gives AMD priorities in terms of supply, according to WccfTech. While the terms of the agreement are unknown, typically such agreements mean that SK Hynix has to meet AMD’s requirements first and only then ship its chips to other customers. Theoretically, this could give AMD “an edge against its main rival, Nvidia, going into the next generation of GPUs featuring second-generation HBM technology.”

Supply agreements are usually signed in a bid to ensure priority treatment, high volumes and good prices. For example, Apple usually signs supply agreements to ensure that it gets what it needs from its suppliers and at low costs. AMD's share in the GPU market is pretty low these days and it may simply not need a lot of HBM2 chips for its launch next year.

HBM2 is still not quite there yet

Earlier this year SK Hynix demonstrated a 300mm wafer with HBM2 chips on it, which is an indicator that the company is testing such products internally, but this does not give any idea about when the HBM2 is ready for mass production.

At present SK Hynix uses 29nm manufacturing technology to manufacture HBM memory chips. According to roadmap leaked by SemiAccurate some time ago, the company plans to use its 21nm fabrication process to produce HBM2 sometimes in Q1 or Q2 2016. SK Hynix’s transition to 21nm is generally considered to be slow, which means that actual launch timeframe may be slightly delayed.

sk_hynix_tsv_roadmap_hbm

SK Hynix thoroughly lists all of its products – current, future and even some EOLed – in its catalogue that is updated every quarter. It is well known, which of SK Hynix’s chips are available, which will be available in Q1 or Q2 2016 and which will be sampled in Q1 2016. At present, SK Hynix does not list HBM2 anywhere, which may be a matter of trade secrets. However, back in 2014, the company did list first-gen HBM chips as “sampling” in Q3 and as “available” in Q4. At the present time, nothing is known about availability or sampling of HBM2 chips, which may indicate that their availability timeframe is not exactly clear.

AMD and SK Hynix did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: Without any doubts, HBM may have certain teething problems, but nobody is talking about them publicly because of commercial reasons. Before the problems get solved, it is unlikely that SK Hynix or other producers of memory start to manufacture HBM2 in higher volumes.

The post AMD reportedly has priority supply agreement regarding HBM, HBM2 first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-reportedly-has-priority-supply-agreement-regarding-hbm-hbm2/feed/ 13
AMD officially launches the Radeon R9 Fury X 4GB https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-formally-introduces-radeon-r9-fury-x-4gb/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-formally-introduces-radeon-r9-fury-x-4gb/#comments Wed, 24 Jun 2015 20:54:38 +0000 http://www.kitguru.net/?p=256019 Advanced Micro Devices on Wednesday officially launched its new flagship graphics processing unit as well as a card based on the GPU. The new graphics processor is the first chip in the world to use all-new high-bandwidth memory (HBM), which is a high-profile innovation on its own, to boot, AMD has managed to put together its …

The post AMD officially launches the Radeon R9 Fury X 4GB first appeared on KitGuru.]]>
Advanced Micro Devices on Wednesday officially launched its new flagship graphics processing unit as well as a card based on the GPU. The new graphics processor is the first chip in the world to use all-new high-bandwidth memory (HBM), which is a high-profile innovation on its own, to boot, AMD has managed to put together its fastest GPU yet.

Specifications the Radeon R9 Fury X have been known for a while. The code-named “Fiji” graphics processing unit integrates 4096 stream processors, 256 texture mapping units, 64 raster operations pipelines as well as an all-new memory controller with 4096-bit interface. The new GPU is reportedly based on the GCN 1.2 architecture and supports DirectX 12 (feature_level_11_1), OpenGL 4.5, OpenCL 2.1 and Vulkan application programming interface.

amd_radeon_r9_fury_card

AMD’s “Fiji XT” chip integrates 8.9 billion of transistor and is the most complex graphics processing unit made to date. Peak compute performance of the GPU is 8.6TFLOPS, the highest FP32 rate ever demonstrated by a GPU.

amd_radeon_fiji_gpu

All AMD Radeon R9 Fury and Fury X graphics cards carry 4GB of HBM memory, which operates at 1GHz frequency. While HBM memory on the new flagship graphics cards from AMD has peak bandwidth of 512GB/s, the limited amount of onboard memory has potential to limit gaming at high-resolutions, although we have not yet performed our own tests.

The “Fiji” chip is made using a 28nm process technology at Taiwan Semiconductor Manufacturing Co. Since 4096-bit memory interface is extremely complex, AMD has to use a special interposer (a complex pad made using 65nm process technology at United Microelectronics Corp.) to connect memory to the GPU. The HBM memory is produced by SK Hynix. The final assembly of the chip is performed by Amkor Technologies in South Korea.

amd_radeon_fiji_diagram_gpu

Due to extreme complexity of AMD “Fiji” graphics processing unit, innovative DRAM and rather expensive packaging and assembly, AMD Radeon Fury X is very expensive to manufacture.

The AMD Radeon R9 Fury X is available now starting at $649 in the U.S. and £509 in the U.K. The less advanced AMD Radeon R9 Fury will hit the market next month and will cost $549. Later this year AMD will also release small form-factor Radeon R9 Fury Nano graphics adapter that will cost less than $500.

amd_radeon_r9_fury_x_specifications

Discuss on our Facebook page, HERE.

KitGuru Says: AMD has jumped back in to the high-end GPU market, bringing with it its fastest graphics core yet and HBM, which will play a huge role in high-end GPUs over the next few years. We don't have a review up just yet but we will be running some tests of our own shortly so keep an eye out.

The post AMD officially launches the Radeon R9 Fury X 4GB first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-formally-introduces-radeon-r9-fury-x-4gb/feed/ 35
AMD’s official Radeon R9 Fury X test results: World’s fastest GPU https://www.kitguru.net/components/graphic-cards/anton-shilov/amds-official-radeon-r9-fury-x-performance-results-worlds-fastest-gpu/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amds-official-radeon-r9-fury-x-performance-results-worlds-fastest-gpu/#comments Fri, 19 Jun 2015 01:28:52 +0000 http://www.kitguru.net/?p=255272 Advanced Micro Devices this week officially unwrapped its new flagship single-chip graphics card based on the highly-anticipated “Fiji” graphics processing unit. The new AMD Radeon R9 Fury X graphics adapter has a number of advantages that can make it one of the world’s highest-performing solutions. In fact, according to AMD’s own benchmarks, the new graphics …

The post AMD’s official Radeon R9 Fury X test results: World’s fastest GPU first appeared on KitGuru.]]>
Advanced Micro Devices this week officially unwrapped its new flagship single-chip graphics card based on the highly-anticipated “Fiji” graphics processing unit. The new AMD Radeon R9 Fury X graphics adapter has a number of advantages that can make it one of the world’s highest-performing solutions. In fact, according to AMD’s own benchmarks, the new graphics card has all chances to be the world’s top single-GPU graphics card.

AMD Radeon R9 Fury X graphics card is based on the “Fiji XT” graphics processing unit that contains 8.9 billion of transistors and features 4096 stream processors, 256 texture units as well as 4096-bit memory bus. With 8.6 TFLOPS of compute performance and 512GB/s memory bandwidth, the adapter is the most technologically advanced graphics card ever introduced. The only drawback of the Radeon R9 Fury X is limited amount of high-bandwidth memory (HBM) onboard – 4GB – which may be a problem for a number of games.

amd_radeon_r9_fury_specifications

AMD officially remains silent about performance that can be expected from its Radeon R9 Fury X, but WccfTech web-site has published official performance benchmarks of the graphics board listed in the reviewer’s guide of the adapter. Such guides are written by independent hardware vendors (IHVs) to assist reviewers of their products. The documents are designed to provide reference performance numbers in order to reveal what type of performance to expect from a graphics card or a microprocessor. While the RG papers are not supposed to unveil weak points of solutions, they tend to be rather accurate and faithful.

The benchmark results were obtained on an unknown test system in various games in 3840*2160 resolution with or without antialiasing. AMD’s specialists compared the Radeon R9 Fury X to Nvidia’s GeForce GTX 980 Ti, which costs equal amount of money ($649) and which is only slightly behind the flagship GeForce GTX Titan X in terms of performance.

amd_radeon_fury_x_performance_semi-official

The test results of the Radeon R9 Fury X obtained by AMD show that it is faster than the rival in all cases. In some situations the difference is negligible and the GeForce GTX Titan X would be faster than the Radeon R9 Fury X. However, in other situations the Radeon R9 Fury X’s positions seem to be unbeatable.

amd_radeon_fury_x_performance_semi-official_3dmark

From test results, it is unclear whether 4GB onboard frame-buffer limits performance of the Radeon R9 Fury X anyhow or not, but what is clear is that it can compete against its direct rival with 6GB of memory.

AMD Radeon R9 Fury X graphics board will be available next week for $649. In mid-July AMD will also ship AMD Radeon R9 Fury with basic cooling solution and lower performance for $549.

amd_radeon_fiji_fury_card_render

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: Without any doubts, AMD’s Radeon R9 Fury X is a really fast graphics card. With further driver optimizations it may become the world’s highest-performing graphics adapter. But will it be more successful than Nvidia’s GeForce GTX 980 Ti and Titan X? Only time will tell!

The post AMD’s official Radeon R9 Fury X test results: World’s fastest GPU first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amds-official-radeon-r9-fury-x-performance-results-worlds-fastest-gpu/feed/ 102
Dual-GPU flagship AMD Radeon R9 Fury X2 graphics card pictured https://www.kitguru.net/components/graphic-cards/anton-shilov/dual-gpu-flagship-amd-radeon-r9-fury-x2-graphics-card-pictured/ https://www.kitguru.net/components/graphic-cards/anton-shilov/dual-gpu-flagship-amd-radeon-r9-fury-x2-graphics-card-pictured/#comments Wed, 17 Jun 2015 00:44:27 +0000 http://www.kitguru.net/?p=254864 Even though AMD’s new-generation dual-chip flagship graphics card is only expected to hit the market several months from now, the company already uses such graphics card for demonstrations. The new add-in board does not resemble current-gen dual-chip graphics adapters. The upcoming dual-chip AMD Radeon R9 Fury X graphics card – which may be officially called Radeon R9 …

The post Dual-GPU flagship AMD Radeon R9 Fury X2 graphics card pictured first appeared on KitGuru.]]>
Even though AMD’s new-generation dual-chip flagship graphics card is only expected to hit the market several months from now, the company already uses such graphics card for demonstrations. The new add-in board does not resemble current-gen dual-chip graphics adapters.

The upcoming dual-chip AMD Radeon R9 Fury X graphics card – which may be officially called Radeon R9 Fury X2 or Radeon R9 Fury Maxx – features two code-named “Fiji XT” graphics processing units with 4096 stream processors and 4GB of HBM memory. In total, the graphics solution features 8192 stream processors and 8GB of high-bandwidth memory. The board has two 8-pin PCI Express power connectors, which means that it can consume up to 375W of power, which may indicate that its clock-rates and power consumption are not really high.

amd_radeon_fiji_fury_maxx
Dual-GPU AMD Radeon R9 Fury. Image by Anshel Sag, staff technologist and technical writer at Moor Insights & Strategy.

The graphics card looks big, but not as big as current-generation dual-GPU adapters thanks to usage of HBM memory. The board utilizes a PCI Express bridge from PLX, just like today’s dual-GPU graphics cards from AMD.

The upcoming Radeon R9 Fury X2 graphics adapter will use a dual-slot cooling system, but it is unclear whether the cooler will use liquid, like the one on the Radeon R9 295X2, or not.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: Looks like AMD’s new dual-GPU flagship is ready. Considering the fact that AMD’s single-chip flagship – Radeon R9 Fury X – will cost $649, it is highly likely that the new dual-GPU product will cost between $1000 and $1500.

The post Dual-GPU flagship AMD Radeon R9 Fury X2 graphics card pictured first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/dual-gpu-flagship-amd-radeon-r9-fury-x2-graphics-card-pictured/feed/ 19
AMD Radeon Fury X poses for camera once again https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-radeon-fury-x-poses-for-camera-once-again/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-radeon-fury-x-poses-for-camera-once-again/#comments Fri, 12 Jun 2015 00:13:15 +0000 http://www.kitguru.net/?p=254108 Although Advanced Micro Devices and some of its allies have published a number of teaser photos of AMD’s upcoming Radeon Fury X graphics cards, they have not revealed the actual look of the boards. Fortunately, a Chinese web-site has managed to picture the whole adapter and thus reveal its design. As expected, the AMD Radeon Fury …

The post AMD Radeon Fury X poses for camera once again first appeared on KitGuru.]]>
Although Advanced Micro Devices and some of its allies have published a number of teaser photos of AMD’s upcoming Radeon Fury X graphics cards, they have not revealed the actual look of the boards. Fortunately, a Chinese web-site has managed to picture the whole adapter and thus reveal its design.

As expected, the AMD Radeon Fury X graphics card based on the code-named “Fiji” graphics processing unit uses a hybrid liquid cooling system as well as a short printed circuit board. According to the image published by ChipHell, the new flagship graphics adapter from Advanced Micro Devices is considerably smaller than modern top-of-the-range solutions from AMD or Nvidia. The Radeon Fury resembles ATI Radeon 9000- and ATI Radeon X800-series graphics adapters released more than a decade ago.

amd_radeon_fiji_card_unofficial

AMD does not want to talk about its yet-unreleased Radeon Fury graphics card officially and does not even allow to picture it. Nonetheless, pretty much all specifications of the new flagship graphics card from AMD are already well known. The new GPU has 4096 stream processors, 256 texture mapping units and revamped GCN 1.3 architecture. The flagship graphics board will carry 4GB of high-bandwidth memory with 512GB/s or even 640GB/s bandwidth. Although the card is short, it requires two 8-pin PCI Express power connectors, which means that it is rather power hungry (may consume up to 375W of power).

The only things that are unknown about the AMD Radeon Fury for sure are performance numbers and price-points of the new boards.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: While the cooling system of AMD’s Radeon Fury looks impressive, not all modern PCs have mount locations for 120mm fans. It will be interesting to see whether AMD will allow partners to use their own cooling systems on their products.

The post AMD Radeon Fury X poses for camera once again first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-radeon-fury-x-poses-for-camera-once-again/feed/ 18
AMD Radeon 2015 roadmap leaks: Whole lineup now revealed https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-radeon-2015-roadmap-leaks-whole-lineup-now-revealed/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-radeon-2015-roadmap-leaks-whole-lineup-now-revealed/#comments Tue, 09 Jun 2015 22:29:16 +0000 http://www.kitguru.net/?p=253645 A web-site has published a slide that reveals AMD’s graphics products lineup that will be available later this year. The image does not only unveil the names and positioning of AMD’s upcoming Radeon solutions, but also code-names of the new graphics processing units from the company. If the slide published by VideoCardz is genuine, then …

The post AMD Radeon 2015 roadmap leaks: Whole lineup now revealed first appeared on KitGuru.]]>
A web-site has published a slide that reveals AMD’s graphics products lineup that will be available later this year. The image does not only unveil the names and positioning of AMD’s upcoming Radeon solutions, but also code-names of the new graphics processing units from the company.

If the slide published by VideoCardz is genuine, then AMD’s new lineup of graphics adapters will consist of seven new models based on various graphics processing units. The flagship products based on the code-named “Fiji XT” and “Fiji Pro” graphics processors will not formally belong to the Radeon R9 300-series. Previously it was reported that the new boards will carry the Radeon Fury brand-name. It is noteworthy that the new Radeon Fury graphics cards based on the “Fiji” GPUs will be available a little later than the members of the Radeon R9 300-series, which may indicate that the new flagship products will not hit the market right after formal announcement of the 16th of June.

The high-end Radeon R9 390 and R9 390X will be based on the “Grenada” graphics processing units, which are claimed to be improved versions of the “Hawaii” chips with higher clock-rates and revamped architecture. Both boards will carry 8GB of memory and will cost $329 and $389, respectively, according to WccfTech. Higher clock-rates of GPU and memory will help the new cards to offer performance that will be higher than that of Nvidia’s GeForce GTX 970, but it is unclear how the Radeon R9 390-series will compare against GeForce GTX 980.

amd_radeon_roadmap_2015

AMD also plans to introduce Radeon R9 380 with 4GB of memory based on the code-named “Antigua” chip also known as “Tonga Pro”. The product is expected to cost $235. In addition, AMD wants to offer Radeon R9 380 with 2GB of memory for $195.

AMD also intends to roll-out Radeon R7 370 and Radeon R7 360 based on the “Pitcairn” and “Bonaire” graphics processors, which have been available for years. The outdated GPUs will address $100 – $175 market segment. Keeping in mind that graphics boards based on the “Pitcairn” and “Bonaire” GPUs have been available for years, it is unlikely that the new Radeon R7 will actually get popular. People who wanted them have already bought such boards.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: Although AMD’s Radeon R9 390-series graphics adapters may actually be rather competitive, it is obvious that they are late. AMD needed to respond to Nvidia’s GeForce GTX 970 and 980 last September, but decided to cut prices of existing solutions, not offer anything new.

The post AMD Radeon 2015 roadmap leaks: Whole lineup now revealed first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-radeon-2015-roadmap-leaks-whole-lineup-now-revealed/feed/ 46
Specifications of AMD’s Radeon Fury confirmed by benchmark database https://www.kitguru.net/components/graphic-cards/anton-shilov/specifications-of-amds-radeon-fury-confirmed-by-benchmark-database/ https://www.kitguru.net/components/graphic-cards/anton-shilov/specifications-of-amds-radeon-fury-confirmed-by-benchmark-database/#comments Tue, 09 Jun 2015 16:20:05 +0000 http://www.kitguru.net/?p=253573 Even though Advanced Micro Devices openly demonstrates its next generation graphics processing unit, it has never confirmed specifications of the product. Nonetheless, multiple leaks have already revealed the vast majority of technical details about the upcoming AMD Radeon Fury graphics card and recently specs of the device were confirmed once again. According to database of …

The post Specifications of AMD’s Radeon Fury confirmed by benchmark database first appeared on KitGuru.]]>
Even though Advanced Micro Devices openly demonstrates its next generation graphics processing unit, it has never confirmed specifications of the product. Nonetheless, multiple leaks have already revealed the vast majority of technical details about the upcoming AMD Radeon Fury graphics card and recently specs of the device were confirmed once again.

According to database of CompuBench benchmark, a test suit used to compare parallel compute performance of CPUs, GPUs and accelerators, AMD’s code-named “Fiji” graphics processor has 64 compute units, reports VideoCardz. Since every GCN compute unit has 64 stream processors, the total amount of SPs in the new GPU is 4096, as reported a number of times before. The chip is expected to feature 256 texture mapping units.

AMD’s Radeon Fury will be the first graphics card to use SK Hynix’s stacked high bandwidth memory (HBM). The new type of DRAM is expected to provide unprecedented memory bandwidth of 640GB/s thanks to 4096-bit memory bus and 1.25GT/s transfer rate. The graphics boards will be equipped with 4GB of HBM memory.

amd_radeon_artwork_angle_new

AMD’s upcoming flagship graphics card will use hybrid liquid cooling solution and will be physically shorter than today’s high-end graphics adapters.

Pricing of AMD’s Radeon Fury X remains unknown. It is expected to be formally introduced on the 16th of June, 2016.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: The main intrigue about AMD’s Radeon Fury X remains its actual performance. The graphics card is expected to demonstrate excellent results in high resolutions, but it is completely unclear how it will compare against Nvidia Corp.’s GeForce GTX Titan X. According to CompuBench, the new graphics processor from AMD is considerably faster than the Titan X. However, actual performance in games depends not only on pure compute performance.

The post Specifications of AMD’s Radeon Fury confirmed by benchmark database first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/specifications-of-amds-radeon-fury-confirmed-by-benchmark-database/feed/ 14
AMD teases ‘Fiji’, but refuses to reveal ‘Fury’ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-teases-fiji-but-refuses-to-reveal-fury/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-teases-fiji-but-refuses-to-reveal-fury/#comments Thu, 04 Jun 2015 07:30:34 +0000 http://www.kitguru.net/?p=252659 At a press conference at the Computex trade-show Advanced Micro Devices has officially demonstrated its first graphics processing unit with high bandwidth memory (HBM) code-named “Fiji”, which is set to power AMD’s next-generation flagship graphics card known unofficially as the Radeon Fury X. But while the company did show its “Fiji” chip, it did not …

The post AMD teases ‘Fiji’, but refuses to reveal ‘Fury’ first appeared on KitGuru.]]>
At a press conference at the Computex trade-show Advanced Micro Devices has officially demonstrated its first graphics processing unit with high bandwidth memory (HBM) code-named “Fiji”, which is set to power AMD’s next-generation flagship graphics card known unofficially as the Radeon Fury X. But while the company did show its “Fiji” chip, it did not want to show the “Fury” card, reports Leo Waldock, a KitGuru editor, from Taipei.

amd_radeon_fiji
AMD “Fiji” graphics processing unit is held by Lisa Su, chief executive of AMD. Photo by WccfTech

Leo arrived at Nangang at 9am and was told the floor was closed to the Press until 9:30am. He took the opportunity to head up to Sapphire, who were in a separate room, so he could say hello and grab a chair. At the Sapphire booth, Leo bumped into Ron Myers, Corporate Vice President of Corporate Marketing at AMD. Ron is a big guy in every sense of the word and only slightly intimidating.

Earlier AMD waved a “Fiji” chip around on stage. They refused to give its name but the unnamed chip had four stacks of HBM so it was “Fiji”, no question.

AMD is showing a running and apparently fully working version of “Fiji” to customers but not to the Press, so Leo asked Ron if he might relent. They both knew the other side of the Sapphire NDA door was the card Leo wanted to see, so Leo asked if he could see the card and take photos.

“How about static without performance?” Leo asked.

“No,” said Ron, and that was the end of that.

sapphire_nda_demo
The closed door

While it was impossible to take photos of the AMD Radeon Fury X, Leo tried to discuss some aspects of the flagship graphics card that only features 4GB of memory (compared to 12GB on Nvidia’s GeForce GTX Titan X). His question about the 4*1GB limit was side-stepped so it is unclear whether AMD could install 8GB of HBM if they choose. A natural guess is they cannot. Ron Myers assured that 4GB of high bandwidth memory is plenty for 4K gaming so it is not just a question of the amount of memory, but also the speed and bandwidth. Put it another way, the requirement for 8GB (or whatever) is in combination with the current, slower bandwidth.

Apparently, AMD wants to build the marketing impetus for the 16th of June, when the first reviews hit the Web, or the 24th, when the graphics cards hit the stores. The problem is, many aspects about the graphics board are already known: it has 4GB of memory, it has short printed circuit board, it requires two 8-pin PCI Express power connectors, it is power hungry (may consume up to 375W of power), it uses hybrid liquid cooling system, etc. The main intrigue about the AMD Radeon Fury X graphics board is its performance. Obviously, a static image of the product cannot reveal any performance details. Moreover, an image of the graphics card itself was recently published by Johan Andersson, technical director of Frostbite at Electronic Arts, in a Twitter post.

amd_radeon_fiji_unofficial
Image of AMD Radeon Fury X published by Johan Andersson

Discuss on our Facebook page, HERE.

KitGuru Says: It is hard to understand why AMD is not prepared to show “Fiji” to the Press. During the conversation Leo called the chip both “Fiji” and “Fury” and Ron did not blink, so we know that it is the correct name.

The post AMD teases ‘Fiji’, but refuses to reveal ‘Fury’ first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-teases-fiji-but-refuses-to-reveal-fury/feed/ 31
The name of flagship AMD Radeon revealed: Fury is back https://www.kitguru.net/components/graphic-cards/anton-shilov/the-name-of-flagship-amd-radeon-revealed-fury-is-back/ https://www.kitguru.net/components/graphic-cards/anton-shilov/the-name-of-flagship-amd-radeon-revealed-fury-is-back/#comments Sat, 30 May 2015 00:50:24 +0000 http://www.kitguru.net/?p=251878 AMD’s next next-generation flagship Radeon graphics card will be the world’s first add-in-board to use stacked high-bandwidth memory (HBM) that will ensure unprecedented performance and will open a number of new doors for graphics adapters. It is rather ironic that for a graphics card that shows the future of GPUs, AMD has reportedly decided to …

The post The name of flagship AMD Radeon revealed: Fury is back first appeared on KitGuru.]]>
AMD’s next next-generation flagship Radeon graphics card will be the world’s first add-in-board to use stacked high-bandwidth memory (HBM) that will ensure unprecedented performance and will open a number of new doors for graphics adapters. It is rather ironic that for a graphics card that shows the future of GPUs, AMD has reportedly decided to use a name from the past.

In a bid to emphasize that its next-generation flagship Radeon graphics adapter based on the code-named “Fiji” graphics processing unit is a very special product, Advanced Micro Devices plans to assign a special name to it, not a model number. The new top-of-the-range graphics board from the company will reportedly be called AMD Radeon Fury, which should imply how furiously fast the new GPU is.

AMD’s flagship Radeon Fury “Fiji XT” graphics processing unit is reportedly based on the revamped GCN 1.3 architecture and integrates 4096 stream processors (64 compute units), 256 texture units as well as all-new memory controller to support vertically stacked high bandwidth memory (HBM) chips with 1024-bit input/output interface. The top-of-the-line Radeon graphics adapter is expected to carry 4GB or 8GB of HBM memory with up to 640GB/s of bandwidth (thanks to 4096-bit memory bus and 1.25GT/s transfer rate). The Radeon Fury graphics card will feature a hybrid liquid cooling system and will require two 8-pin PCI Express power connectors.

amd_radeon_artwork_angle_new

The AMD Radeon Fury reminds of ATI Rage Fury, a popular graphics card for gamers from ATI Technologies in 1998. The add-in board was among the first graphics adapters to feature 32MB of SDRAM, but it was not nearly as popular as 3dfx Voodoo or Nvidia Riva TNT. While it did demonstrate great performance in 32-bit colour mode, it was not a dream graphics solution and certainly was not a legend.

It is interesting to note that the dual-chip Radeon Fury Maxx launched in 1999 introduced the alternate frame rendering multi-GPU technique to the consumer market, but received a bad reputation for poor drivers and lag issues. Nowadays all multi-GPU sub-systems use AFR method of multi-GPU rendering.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: The Radeon Fury is definitely a nice name. Moreover, many experienced gamers will clearly remember good-old days of 1998 – 1999 as well as the ATI Rage Fury and the ATI Rage Fury Pro graphics cards (which were actually manufactured by ATI in Canada back then!). But the key to success of AMD’s new flagship is not nostalgia. They keys to success are actual performance in video games, price and availability. Will AMD Radeon Fury deliver? Let’s wait and see! In the meantime, let's think, what variations of AMD Radeon Fury we can expect from Advanced Micro Devices. The dual-chip could be called Radeon Fury Maxx, whereas a slightly slower version could carry the name Radeon Fury Pro…

The post The name of flagship AMD Radeon revealed: Fury is back first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/the-name-of-flagship-amd-radeon-revealed-fury-is-back/feed/ 28
AMD’s new flagship Radeon ‘Fiji XT’ pictured: moderate size, LCS https://www.kitguru.net/components/graphic-cards/anton-shilov/amds-next-gen-flagship-radeon-fiji-xt-pictured-moderate-size-hybrid-cooler/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amds-next-gen-flagship-radeon-fiji-xt-pictured-moderate-size-hybrid-cooler/#comments Sat, 23 May 2015 01:16:56 +0000 http://www.kitguru.net/?p=250824 Johan Andersson, technical director of Frostbite at Electronic Arts, has published a picture of AMD’s next-generation flagship graphics card code-named “Fiji XT” in a Twitter post. The new top-of-the-range AMD Radeon graphics solution does not look like graphics cards available today. As it appears, the new enthusiast-class AMD Radeon “Fiji XT” graphics adapter will use a closed-loop …

The post AMD’s new flagship Radeon ‘Fiji XT’ pictured: moderate size, LCS first appeared on KitGuru.]]>
Johan Andersson, technical director of Frostbite at Electronic Arts, has published a picture of AMD’s next-generation flagship graphics card code-named “Fiji XT” in a Twitter post. The new top-of-the-range AMD Radeon graphics solution does not look like graphics cards available today.

As it appears, the new enthusiast-class AMD Radeon “Fiji XT” graphics adapter will use a closed-loop hybrid liquid cooling solution that is supposed to ensure quiet operation and maximum efficiency. The board will no longer support DVI connectors and will only feature DisplayPort and HDMI outputs.

The new top-of-the-range Radeon graphics adapter will not be very long, like today’s high-end graphics cards from AMD or Nvidia Corp. In fact, the length of the graphics card seems to be comparable to the length of ATI Technologies’ advanced graphics adapters that were available a decade ago. Therefore, it will be possible to build a very high-performance small form-factor gaming PC using a “Fiji XT” with liquid cooler.

amd_radeon_fiji_unofficial

AMD’s flagship Radeon “Fiji XT” graphics processing unit is reportedly based on the revamped GCN 1.3 architecture and integrates 4096 stream processors (64 compute units), 256 texture units as well as all-new memory controller to support vertically stacked high bandwidth memory (HBM) chips with 1024-bit input/output interface. The top-of-the-range Radeon graphics adapter is expected to carry 4GB or 8GB of HBM memory with up to 640GB/s of bandwidth (thanks to 4096-bit memory bus and 1.25GT/s transfer rate).

Mr. Andersson did not reveal any additional information regarding the upcoming flagship graphics card from AMD,

“This new island is one seriously impressive and sweet GPU,” said the game programmer.

Discuss on our Facebook page, HERE.

KitGuru Says: Tweets like the one made by Johan Andersson are clearly sanctioned by AMD and are intended to attract attention to the product. In fact, the amount of teases – both official and unofficial – that AMD and its partners have made regarding “Fiji XT” is quite overwhelming. Let’s just hope that performance of the product will be a breakthrough.

The post AMD’s new flagship Radeon ‘Fiji XT’ pictured: moderate size, LCS first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amds-next-gen-flagship-radeon-fiji-xt-pictured-moderate-size-hybrid-cooler/feed/ 4
AMD’s flagship ‘Fiji XT’ to use new branding and cost $849 – rumours https://www.kitguru.net/components/graphic-cards/anton-shilov/amds-flagship-fiji-xt-to-use-new-branding-and-cost-849-rumours/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amds-flagship-fiji-xt-to-use-new-branding-and-cost-849-rumours/#comments Tue, 19 May 2015 22:59:14 +0000 http://www.kitguru.net/?p=250180 The next-generation top-of-the-range AMD Radeon graphics card may no longer carry a model number, but will introduce a new brand akin to Nvidia Corp.’s GeForce Titan, according to a media report. The highest-performing single-chip graphics adapter is also rumoured to cost unprecedented amount of money for an AMD single-GPU solution. In a bid to emphasize …

The post AMD’s flagship ‘Fiji XT’ to use new branding and cost $849 – rumours first appeared on KitGuru.]]>
The next-generation top-of-the-range AMD Radeon graphics card may no longer carry a model number, but will introduce a new brand akin to Nvidia Corp.’s GeForce Titan, according to a media report. The highest-performing single-chip graphics adapter is also rumoured to cost unprecedented amount of money for an AMD single-GPU solution.

In a bid to emphasize extreme performance of its next-generation flagship graphics solution based on the code-named “Fiji” graphics processing unit and 8GB of high-bandwidth memory (HBM), AMD will not call it the “Radeon R9 390X,” but will introduce a separate branding akin to Intel’s Extreme Edition or Nvidia’s Titan, reports SweClockers. Back in the days ATI Technologies offered Radeon X800 XT Platinum Edition, which featured improved performance compared to the Radeon X800 XT, but had the same GPU configuration.

At present it is unclear how many “Fiji”-based graphics card models AMD intends to release, but previously it was reported about three solutions with different GPU configurations, cooling systems, performance and prices.

amd_radeon_artwork_angle_new

Fudzilla reports AMD’s new top-of-the-range graphics card will cost $849. If AMD releases three “Fiji”-based graphics adapters, then it can sell the highest-performing product in the lineup for $849. However, if the number of solutions in the lineup will be limited to two, then it will be rather hard to successfully position them while selling one for $849.

AMD’s “Fiji XT” GPU is reportedly based on the revamped GCN 1.3 architecture and integrates 4096 stream processors (64 compute units), 256 texture units as well as all-new memory controller to support vertically stacked high bandwidth memory (HBM) chips with 1024-bit input/output interface. The top-of-the-range Radeon is projected to feature 8GB of HBM memory with up to 640GB/s of bandwidth (thanks to 4096-bit memory bus and 1.25GT/s transfer rate).

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: While it makes some sense to introduce a rival for Nvidia’s GeForce GTX Titan X with a loud name, in a bid to actually re-capture market share, AMD will still need both Radeon R9 390X and Radeon R9 390 that do not cost nearly $850. Therefore, we are likely to see three graphic cards based on AMD’s code-named “Fiji” GPU.

The post AMD’s flagship ‘Fiji XT’ to use new branding and cost $849 – rumours first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amds-flagship-fiji-xt-to-use-new-branding-and-cost-849-rumours/feed/ 26
AMD to start actual sales of Radeon R9 300-series in mid- and late-June https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-to-start-actual-sales-of-next-gen-radeon-r9-300-series-in-mid-and-late-june/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-to-start-actual-sales-of-next-gen-radeon-r9-300-series-in-mid-and-late-june/#comments Wed, 13 May 2015 02:11:26 +0000 http://www.kitguru.net/?p=249187 Advanced Micro Devices plans to formally unveil its new family of graphics adapters at the Computex Taipei 2015 trade-show in early June, but the actual sales of its new graphics adapters are expected to start later next month. AMD’s partners will begin to sell Radeon R9 380, R9 370 and R7 360 graphics cards as …

The post AMD to start actual sales of Radeon R9 300-series in mid- and late-June first appeared on KitGuru.]]>
Advanced Micro Devices plans to formally unveil its new family of graphics adapters at the Computex Taipei 2015 trade-show in early June, but the actual sales of its new graphics adapters are expected to start later next month.

AMD’s partners will begin to sell Radeon R9 380, R9 370 and R7 360 graphics cards as well as their derivatives on the 18th of June, 2015. The flagship products – the AMD Radeon R9 390-series – will hit the market on the 24th of June, 2015, reports BenchLife web-site citing undisclosed sources.

Developers of graphics cards often begin selling their latest products a couple of weeks after official announcements. A slight delay with the Radeon R9 390-series introduction will hardly harm its sales.

amd_radeon_artwork_angle_new

As reported, the new flagship graphics solutions from AMD – the Radeon R9 390-series graphics cards – are based on the code-named “Fiji” graphics processing unit. The GPU reportedly features revamped GCN 1.3 architecture and integrates 4096 stream processors (64 compute units), 256 texture units as well as all-new memory controller to support vertically stacked high bandwidth memory (HBM) chips with 1024-bit input/output interface. The top-of-the-range Radeon R9 390X is expected to feature 8GB of HBM memory with up to 640GB/s of bandwidth (thanks to 4096-bit memory bus and 1.25GT/s transfer rate).

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: It has taken AMD quite a long time to prepare the world’s first graphics card with HBM memory, but it looks like the company is on the home straight now.

The post AMD to start actual sales of Radeon R9 300-series in mid- and late-June first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-to-start-actual-sales-of-next-gen-radeon-r9-300-series-in-mid-and-late-june/feed/ 5
AMD: Installed base of GCN GPUs is over 100 million units https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-installed-base-of-gcn-gpus-is-over-100-million-units/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-installed-base-of-gcn-gpus-is-over-100-million-units/#comments Fri, 08 May 2015 01:49:13 +0000 http://www.kitguru.net/?p=248503 Advanced Micro Devices has been using its latest GCN [graphics core next] architecture for its graphics processing units for over three years now and will release at least two new GCN-based product families. Without any doubts, GCN is one of the most successful GPU technologies ever. Apparently, it is one of the most widely used …

The post AMD: Installed base of GCN GPUs is over 100 million units first appeared on KitGuru.]]>
Advanced Micro Devices has been using its latest GCN [graphics core next] architecture for its graphics processing units for over three years now and will release at least two new GCN-based product families. Without any doubts, GCN is one of the most successful GPU technologies ever. Apparently, it is one of the most widely used graphics processing architectures too. According to AMD, more than 100 million GPUs worldwide are GCN-based.

“With graphics core next, we provided an architecture to make it easier […] for programmers to unlock the value of our graphics both for visualization and compute,” said Mark Papermaster, chief technology officer at AMD at the company’s financial analyst day. “Really a ground-breaking architecture!

Different incarnations of AMD’s GCN architecture power Radeon graphics cards, accelerated processing units, various embedded application processors as well as high-performance system-on-chips for Microsoft Xbox One and Sony PlayStation 4 game consoles. In fact, game consoles alone account for well over 30 million of GCN-based graphics processors.

“And you can see the adoptions. It is, of course, our discrete graphics business, but it is much more than that,” added Mr. Papermaster. “It is in the game consoles, you see it in the Mac Pro, the iMac 5K, leading workstation designs, server installations. It is scalable, from mobile applications to high-performance computing applications. It has got the installed base of over 100 million for developers to leverage. This has been a very successful architecture!”

amd_radeon_hd_7000_artwork

So far, AMD has released three iterations of its GCN architecture. Next month the company intends to unveil its new GPUs based on the fourth-generation graphics core next – GCN 1.3 – design. Sometimes next year AMD plans to introduce graphics processing units based on the GCN 1.4 architecture, which are projected to deliver two times higher performance-per-watt efficiency compared to today’s GPUs.

Discuss on our Facebook page, HERE.

KitGuru Says: 100 million graphics processing units is clearly a lot. Imagine how many GCN GPUs AMD would have sold if its accelerated processing units were more competitive in general purpose workloads that rely on x86 performance…

The post AMD: Installed base of GCN GPUs is over 100 million units first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-installed-base-of-gcn-gpus-is-over-100-million-units/feed/ 21
Supply of AMD Radeon R9 390-series may be constrained – report https://www.kitguru.net/components/graphic-cards/anton-shilov/supply-of-amd-radeon-r9-390-series-may-be-constrained-report/ https://www.kitguru.net/components/graphic-cards/anton-shilov/supply-of-amd-radeon-r9-390-series-may-be-constrained-report/#comments Wed, 22 Apr 2015 09:02:55 +0000 http://www.kitguru.net/?p=246173 Supply of next-generation AMD Radeon R9 390-series graphics cards is expected to be very short initially. A media report suggests that the main reason behind supply constraints is limited availability of high-bandwidth memory made by SK Hynix. Even though Advanced Micro Devices taped out its code-named “Fiji” graphics processor that powers the Radeon R9 390-series …

The post Supply of AMD Radeon R9 390-series may be constrained – report first appeared on KitGuru.]]>
Supply of next-generation AMD Radeon R9 390-series graphics cards is expected to be very short initially. A media report suggests that the main reason behind supply constraints is limited availability of high-bandwidth memory made by SK Hynix.

Even though Advanced Micro Devices taped out its code-named “Fiji” graphics processor that powers the Radeon R9 390-series graphics cards in the middle of 2014 and currently its yields should be high, there is a major problem, which could hamper availability of such adapters: yields of high-bandwidth memory at SK Hynix. According to a report from TweakTown, there will not be enough memory available to fulfill AMD’s needs in the coming months.

amd_radeon_r9_295x2_295_x2_1

The first-generation HBM (HBM1) stacks four DRAM dies with two 128-bit channels per die on a base logic die using through silicon vias (TSV), which results into a memory device with a 1024-bit interface. The first-gen HBM stacks are made using proven 29nm (which SK Hynix calls “2xnm”) process technology. High-bandwidth memory comes in HBM 4Hi stack (4 high stack) packages, which are tested by SK Hynix before shipments. Each HBM 4Hi stack is placed on an interposer next to the graphics processing unit, a process that has not been used for graphics cards before.

It is unclear whether yields of HBM memory is the only problem that affects availability of AMD’s Radeon R9 390-series graphics cards, or there is a combination of problems that involves HBM, usage of interposer, testing procedure of multi-die devices and so on.

sk_hynix_hbm_dram_1

AMD Radeon R9 390-series graphics adapters will be the first add-in-boards to utilize HBM memory. The new graphics processing unit from AMD reportedly packs 4096 stream processors/64 compute units, 256 texture mapping units and has a 4096-bit memory interface. The Radeon R9 390’s memory bus operates at up to 1.25Gb/s data-rate (1.25GHz effective DDR frequency) and delivers massive 640GB/s memory bandwidth.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: If AMD really has problems with production of its Radeon R9 390-series graphics cards, then it explains why the company wants to release the whole lineup of next-gen adapters at once. On the other hand, the company itself expects its GPU market share to increase after it releases its new graphics solution. If AMD cannot ship enough graphics cards, then its market share will drop, not increase.

The post Supply of AMD Radeon R9 390-series may be constrained – report first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/supply-of-amd-radeon-r9-390-series-may-be-constrained-report/feed/ 16
AMD reiterates plans to introduce new Radeon R9 300 GPUs in June https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-reiterates-plans-to-introduce-new-radeon-r9-300-series-gpus-in-june/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-reiterates-plans-to-introduce-new-radeon-r9-300-series-gpus-in-june/#comments Sat, 18 Apr 2015 10:28:04 +0000 http://www.kitguru.net/?p=245701 Advanced Micro Devices has reiterated plans to start high volume shipments of new graphics products and accelerated processing units later in this quarter with meaningful revenue contribution starting in the second half of the year. As reported, AMD is set to officially release its new lineup of GPUs in June. Because of weak demand for …

The post AMD reiterates plans to introduce new Radeon R9 300 GPUs in June first appeared on KitGuru.]]>
Advanced Micro Devices has reiterated plans to start high volume shipments of new graphics products and accelerated processing units later in this quarter with meaningful revenue contribution starting in the second half of the year. As reported, AMD is set to officially release its new lineup of GPUs in June.

Because of weak demand for personal computers, AMD’s issues with channel inventory as well as competitive positions of its products, shipments of AMD microprocessors and graphics processing units have been dropping for about a year now. Moreover, AMD’s CPU and GPU market shares have been decreasing for many quarters in a row as well. As a result, the primary tasks for AMD’s management is to boost sales and improve positions on the market. According to the chief exec of the company, this is exactly what AMD plans to do in the second half of the year after launching “Carizzo” accelerated processing units, Godavari (Kaveri Refresh) APUs and all-new Radeon graphics processors in the late second quarter.

“As we go into the second half of the year, we would like to see some regain of share in both the desktop and the notebook business,” said Lisa Su, chief executive officer of AMD, in the company’s quarterly conference call with investors and financial analysts. “I talked about Carrizo being a strong product for us, I talked about some of our graphics launches that we will talk about later this quarter.”

amd_radeon_artwork_angle_new

As reported, AMD plans to officially introduce its new Radeon 9 300-series graphics processors in June, around the Computex Taipei 2015 trade-show. According to sources with knowledge of AMD plans, this time the company will take a rather untraditional approach to introduction. Instead of unveiling numerous new graphics cards one after another, the company is going to reveal the whole family at once. As reported, the new series will contain both new and old graphics processing units.

Based on media reports and sources with knowledge of AMD’s plans, it is expected that the Radeon R9 300-series family will contain three all new graphics processors: Fiji, Grenada (improved Hawaii) and Trinidad. In addition, some forecast that AMD to finally use Tonga XT chip with all compute units/stream processors activated.

Here is the compilation of what we do know about the Radeon R9 300-series range so far (please keep in mind that not all model numbers and specifications may be accurate):

  • AMD Radeon R9 390/390X – Fiji Pro/Fiji XT graphics processing units featuring GCN 1.3 architecture with up to 4096 stream processors and 4096-bit interface to HBM memory. Price range: $649 and upwards.
  • AMD Radeon R9 380/380X – Grenada Pro/Grenada XT graphics processing units featuring GCN 1.2 or GCN 1.3 architecture with up to 2816 stream processors and 512-bit interface to GDDR5 memory. Price range: $249 – $299 – $329. Since “Grenada” GPU is basically a revamped “Hawaii”, it is possible that instead of making a new GPU, AMD will simply use the old one under a new moniker.
  • AMD Radeon R9 375X – Tonga XT graphics processing units featuring GCN 1.2 architecture with up to 2048 stream processors and 384-bit interface to GDDR5 memory. Price range: around $229.
  • AMD Radeon R9 375 – Tonga Pro graphics processing units featuring GCN 1.2 architecture with up to 1792 stream processors and 256-bit interface to GDDR5 memory. Price range: around $199.
  • AMD Radeon R9 370/370X – Trinidad Pro/Trinidad XT graphics processing units featuring GCN 1.3 architecture with up to 1536 stream processors and 256-bit interface to GDDR5 memory. Price range: $119 – $149.

The situation with the upcoming Radeon R7 300-series look less clear. On the one hand, AMD could continue offering its code-named “Curacao” graphics processing units for Radeon R7 360-series graphics cards, but the company could also introduce something powered by the GCN 1.2 or the GCN 1.3 for the price range of around $100.

amd_radeon_graphics_artwork

If the compiled information about the new Radeon R9 lineup is correct, then AMD’s positions in the second half of this year will be somewhat better than today. Still, given that the market is very competitive, a lot depends on Nvidia’s GeForce GTX 900-series refresh plans. Nonetheless, AMD remains optimistic about its future products.

“I think from the standpoint of being able to capture more of the market and increase more to where our normal shares are in graphics, I think that something that we believe we can make progress towards,” said Ms. Su.

AMD did not comment on the potential Radeon R9 300-series lineup.

Discuss on our Facebook page, HERE.

KitGuru Says: It will be interesting to see how successful will the new Radeon R9 300-series family be. Releasing one new graphics card after another ensures that every GPU receives a lot of attention from the media. When AMD launches the whole lineup at once, the press concentrates on the flagship product and hardly covers mainstream offerings. As a consequence, some customers may never learn about AMD’s new offerings in the $100 – $200 range.

The post AMD reiterates plans to introduce new Radeon R9 300 GPUs in June first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-reiterates-plans-to-introduce-new-radeon-r9-300-series-gpus-in-june/feed/ 134
First images of alleged XFX AMD Radeon R9 380 hit the web https://www.kitguru.net/components/graphic-cards/anton-shilov/first-image-of-alleged-xfx-amd-radeon-r9-380-hits-the-web/ https://www.kitguru.net/components/graphic-cards/anton-shilov/first-image-of-alleged-xfx-amd-radeon-r9-380-hits-the-web/#comments Thu, 09 Apr 2015 22:59:10 +0000 http://www.kitguru.net/?p=244329 A web-site has published what it claims to be the first photos of the upcoming AMD Radeon R9 380-series graphics card. If the images depict what they claim to, then it confirms that AMD’s upcoming Radeon R9 300-series lineup will at least partly consist of rebranded current-generation products. The XFX Radeon R9 380 Double Dissipation …

The post First images of alleged XFX AMD Radeon R9 380 hit the web first appeared on KitGuru.]]>
A web-site has published what it claims to be the first photos of the upcoming AMD Radeon R9 380-series graphics card. If the images depict what they claim to, then it confirms that AMD’s upcoming Radeon R9 300-series lineup will at least partly consist of rebranded current-generation products.

The XFX Radeon R9 380 Double Dissipation graphics card looks almost exactly the same as the company's currently available brother, the XFX Radeon R9 290 Double Dissipation: it lacks AMD CrossFire multi-GPU connectors, it uses two auxiliary PCIe power connectors (6-pin and 8-pin), it has a long “Double Dissipation” cooling system and uses reference design printed circuit board. The only difference between the existing graphics adapter and the upcoming one is the marking: the latter carries the “R9 380” label.

xfx_radeon_r9_390

Images of the graphics card were published by Wccftech on Thursday. The web-site claimed that they were found on a Chinese forum.

xfx_radeon_r9_390_1

Previously it was reported that AMD intends to re-introduce current-generation products under new names in its R9 300-series lineup. The Radeon R9 380-series graphics cards were supposed to be based either on the code-named “Hawaii” graphics processing unit or the “Grenada” GPU that features the same configuration, but is allegedly powered by the GCN 1.3 architecture. It is unknown which chip does the XFX Radeon R9 380 graphics card use.

If AMD’s partners already have the “new” Radeon R9 380-series graphics processing solutions at hand, it means that the launch is nearing. Unfortunately, the status of the flagship AMD Radeon R9 390-series graphics solutions based on the code-named “Fiji” GPU is unclear.

AMD and XFX did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: If the images are legitimate, then AMD decided to simply rebrand existing graphics cards without changing their PCB design or improving them anyhow. Perhaps, the company will boost clock-rates of the “Hawaii” GPU on the Radeon R9 380-series graphics cards compared to the Radeon R9 290-series adapters. Still, it will not make the “new” solutions significantly better…

The post First images of alleged XFX AMD Radeon R9 380 hit the web first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/first-image-of-alleged-xfx-amd-radeon-r9-380-hits-the-web/feed/ 20
AMD readies ‘Greenland’ graphics processor https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-readies-greenland-graphics-processor/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-readies-greenland-graphics-processor/#comments Tue, 31 Mar 2015 02:19:34 +0000 http://www.kitguru.net/?p=242839 Advanced Micro Devices is working on a new graphics processing unit code-named “Greenland”, which will be released next year. The new graphics chip will replace code-named “Fiji” GPU and will be AMD’s flagship graphics solution in 2016. Nothing particular is known about the forthcoming Radeon graphics processor, except its code-name. Fudzilla reports that the graphics …

The post AMD readies ‘Greenland’ graphics processor first appeared on KitGuru.]]>
Advanced Micro Devices is working on a new graphics processing unit code-named “Greenland”, which will be released next year. The new graphics chip will replace code-named “Fiji” GPU and will be AMD’s flagship graphics solution in 2016.

Nothing particular is known about the forthcoming Radeon graphics processor, except its code-name. Fudzilla reports that the graphics processing unit will support second-generation high-bandwidth memory (HBM). It is also likely that the new GPU will support DirectX 12 tier 3 implementation, OpenGL 4.5 or better as well as Vulkan application programming interfaces. The GPU will belong to the “Arctic Islands” family of products.

At present it is unknown whether the “Greenland” GPU will be based on the GCN [graphics core next] or post-GCN architecture. Previously AMD implied that in 2016 it will offer a radically new GPU design.

amd_radeon_artwork_angle_new

Given the availability timeframe of AMD Radeon “Greenland” graphics processor, it is logical to expect that it will be made using 14nm process technology at GlobalFoundries or 16nm manufacturing technology at Taiwan Semiconductor Manufacturing Co.

The code-named “Greenland” graphics processor will compete against Nvidia Corp.’s code-named “Pascal” GPUs, such as GP104 or GP100.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: Full DirectX 12 implementation, HBM2 memory and 14nm fabrication process… This GPU promises to be a great performer! Unfortunately, we have no idea whether it will be made available early in 2016 or towards the end of the year.

The post AMD readies ‘Greenland’ graphics processor first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-readies-greenland-graphics-processor/feed/ 3
SK Hynix demos HBM2 memory ICs, opens way for 32GB graphics cards https://www.kitguru.net/components/graphic-cards/anton-shilov/sk-hynix-demos-hbm2-memory-chips-opens-way-for-32gb-graphics-cards/ https://www.kitguru.net/components/graphic-cards/anton-shilov/sk-hynix-demos-hbm2-memory-chips-opens-way-for-32gb-graphics-cards/#comments Thu, 19 Mar 2015 13:36:30 +0000 http://www.kitguru.net/?p=240939 SK Hynix has demonstrated a wafer with second-generation high-bandwidth memory (HBM) at the CeBIT trade-show in Hannover, Germany. The new memory chips will emerge on the market sometimes next year and will increase memory bandwidth and memory capacities for graphics cards and other applications. The first-generation HBM (HBM1) stacks four DRAM dies with two 128-bit …

The post SK Hynix demos HBM2 memory ICs, opens way for 32GB graphics cards first appeared on KitGuru.]]>
SK Hynix has demonstrated a wafer with second-generation high-bandwidth memory (HBM) at the CeBIT trade-show in Hannover, Germany. The new memory chips will emerge on the market sometimes next year and will increase memory bandwidth and memory capacities for graphics cards and other applications.

The first-generation HBM (HBM1) stacks four DRAM dies with two 128-bit channels per die on a base logic die, which results into a memory device with a 1024-bit interface. Each channel supports 1Gb capacities (2Gb per die), features 8 banks and can operate at 1Gb/s – 1.25Gb/s data-rates (1GHz – 1.25GHz effective DDR frequency). As a result, each HBM 4Hi stack (4 high stack) package can provide 1GB capacity and 128GB/s – 160GB/s memory bandwidth. The first-gen HBM stacks are made using 29nm (which SK Hynix calls “2xnm”) process technology. While even the first-generation HBM can enable graphics cards with up to 8GB (with the help of dual-link interposing) of memory and 640GB/s of bandwidth, it will not be enough for the future.

sk_hynix_hbm_dram_2

The second-generation HBM (HBM2) greatly expands capabilities of the high-bandwidth memory in general and will evolve in the coming years. The HBM2 uses 8Gb dies with two 128-bit channels featuring 16 banks. Data-rates of the second-generation HBM will increase up to 2Gb/s (2GHz effective DDR frequency). The architecture of the HBM2 will let manufacturers built not only 4Hi stack (4 high stack) packages, but also 2Hi stack and 8Hi stack devices.

sk_hynix_hbm_dram_1

In the best-case scenario HBM2 memory chips will feature 8GB capacity (8Hi stack) with 256GB/s bandwidth (2Gb/s data rate, 1024-bit bus). Such HBM2 devices will let developers of graphics processing units to build graphics adapters with 32GB of onboard memory and incredible 1TB/s peak bandwidth. Nvidia Corp. has already announced that its next-generation code-named “Pascal” graphics processing architecture will support up to 32GB of HBM2. Mainstream HBM2 ICs will likely sport 2GB (2Hi stack) or 4GB (4Hi stack) capacities with 1.6Gb/s data rate (204.8GB/s bandwidth per chip), which should be more than enough for high-performance graphics cards in 2016.

sk_hynix_hbm_2_hbm2_wafer_fudzilla

Fudzilla reports that SK Hynix demonstrates a wafer with HBM2 memory ICs [integrated circuits] at CeBIT. Typically, manufacturers of memory can show off future DRAM products years before mass production. According to a roadmap leaked by SemiAccurate some time ago, SK Hynix plans to start production of HBM 2 in early 2016. It is expected that second-gen HBM stacks will be manufactured using 20nm fabrication process (which SK Hynix calls “2znm”).

sk_hynix_tsv_roadmap_hbm

Going forward the JESD235 standard that powers HBM memory will evolve in terms of clock-rates, die densities (do not expect 16Gb dies any time soon, though) and other ways to improve performance. Extreme memory bandwidth will be required by high-end graphics cards in the coming years as the world transits to ultra-high-definition displays with 4K (3840*2160, 4096*2160) and 5K (5120*2880) resolutions. Even more memory bandwidth will be needed towards the end of the decade when the first displays with 8K (7680*4320) resolutions emerge.

The first graphics cards to use HBM memory will be AMD’s next-generation Radeon R9 390X. The new graphics processing unit from AMD reportedly features 4096 stream processors/64 compute units, 256 texture mapping units and 4096-bit memory bus. The Radeon R9 390X’s memory interface operates at 1.25Gb/s data-rate (1.25GHz effective DDR frequency) and delivers whopping 640GB/s memory bandwidth.

Discuss on our Facebook page, HERE.

KitGuru Says: The HBM looks incredibly good on paper. It provides nice scaling both in terms of bandwidth and capacity for devices like graphics cards. Nonetheless, it is obvious that HBM is not cheap and will never become a standard for system memory.

The post SK Hynix demos HBM2 memory ICs, opens way for 32GB graphics cards first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/sk-hynix-demos-hbm2-memory-chips-opens-way-for-32gb-graphics-cards/feed/ 6
AMD Radeon R9 390X to cost more than $700 – report https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-radeon-r9-390x-to-cost-more-than-700-report/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-radeon-r9-390x-to-cost-more-than-700-report/#comments Tue, 17 Mar 2015 02:56:31 +0000 http://www.kitguru.net/?p=240402 Although the Radeon R9 390X will offer significantly higher performance than existing graphics cards from Advanced Micro Devices, it will also cost considerably more than current graphics adapters from the company. In fact, the new flagship graphics solutions from AMD will be more expensive than all single-chip Radeon graphics boards ever introduced. Heise.de reports citing sources …

The post AMD Radeon R9 390X to cost more than $700 – report first appeared on KitGuru.]]>
Although the Radeon R9 390X will offer significantly higher performance than existing graphics cards from Advanced Micro Devices, it will also cost considerably more than current graphics adapters from the company. In fact, the new flagship graphics solutions from AMD will be more expensive than all single-chip Radeon graphics boards ever introduced.

Heise.de reports citing sources with knowledge of AMD’s plans that the AMD Radeon R9 390 graphics adapter will cost around $700, whereas more advanced AMD Radeon R9 390X will be priced at over $700. The price of the AMD Radeon R9 390X WCE [water-cooled edition] is unknown, but it will naturally be very high. The Radeon R9 380X will carry $400 price-tag, whereas the Radeon R9 380 will be available for around $330.

Previously the most expensive single-chip Radeon graphics cards cost no more than $649, but, apparently, the company wants to increase pricing of its flagship products going forward.

amd_radeon_artwork_angle_new

The Radeon R9 390-series graphics cards will be the first add-in-boards to use high-bandwidth memory (HBM) from SK Hynix in the world. Extreme performance in ultra-high-definition resolutions that the new cards will provide will justify their high prices.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: It is noteworthy that AMD wants to position its upcoming Radeon R9 390X above the GeForce GTX 980, but clearly below the GeForce GTX Titan X, which is expected to cost between $999 and $1349. For some reason AMD does not want to compete against Nvidia’s graphics cards at the same price-points.

The post AMD Radeon R9 390X to cost more than $700 – report first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-radeon-r9-390x-to-cost-more-than-700-report/feed/ 177
AMD Radeon R9 390X to feature 8.6TFLOPS performance, 8GB HBM memory https://www.kitguru.net/components/graphic-cards/anton-shilov/amdradeon-r9-390x-to-feature-8-6tflops-performance-8gb-hbm-memory/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amdradeon-r9-390x-to-feature-8-6tflops-performance-8gb-hbm-memory/#comments Tue, 17 Mar 2015 00:20:37 +0000 http://www.kitguru.net/?p=240343 A web-site has published excerpts from an alleged AMD presentation that describes the company’s upcoming Radeon R9 390X graphics card. As expected, the new top-of-the-range graphics from Advanced Micro Devices will feature unprecedented performance thanks to massive amount of compute horsepower and high-bandwidth memory. The slides from an AMD presentation for its partners, which were …

The post AMD Radeon R9 390X to feature 8.6TFLOPS performance, 8GB HBM memory first appeared on KitGuru.]]>
A web-site has published excerpts from an alleged AMD presentation that describes the company’s upcoming Radeon R9 390X graphics card. As expected, the new top-of-the-range graphics from Advanced Micro Devices will feature unprecedented performance thanks to massive amount of compute horsepower and high-bandwidth memory.

amd_radeon_shop-home-component

The slides from an AMD presentation for its partners, which were published by Videocardz web-site, reveal a number of previously unknown details about the Radeon R9 390X. As expected, the code-named Fiji XT graphics processing unit has 4096 stream processor and 4096-bit HBM memory bus. However, unlike previously suggested, the graphics card carries 8GB of memory, not 4GB of HBM DRAM.

AMD-Radeon-R9-390X-Specifications

The forthcoming Radeon R9 390X GPU will feature improved GCN 1.3 architecture with full DirectX 12 implementation. According to AMD, the new chip will support new dual-GPU modes as well as specialized render modes for VR gaming. The processor will also support new H.265/HEVC decoder.

In a bid to install 8GB of memory, AMD used multi-layer 1GB chips from SK Hynix on dual-link interposer. Previously it was believed that AMD would only equip its new graphics card with 4GB of memory. Peak memory bandwidth of the Radeon R9 390X will be 640GB/s.

amd_hbm

The Radeon R9 390X will have peak compute performance of 8.6TFLOPS, which is even higher than that of the GeForce GTX Titan X.

AMD-Radeon-R9-390X-4k-and-VR

In addition to traditional version, AMD plans to introduce Radeon R9 390X WCE [water-cooled edition] with improved performance that will be designed specifically for enthusiasts. The typical version of the R9 390X will require one 6-pin and one 8-pin auxiliary PCIe power connectors, whereas the WCE will use two 8-pin connectors to deliver more power to the graphics adapter and improve its overclocking potential. It is unclear whether AMD plans to release Radeon R9 390 in addition to the R9 390X and the R9 390X WCE.

AMD-Radeon-R9-390X-vs-290X-performance

According to AMD’s own performance estimates, the Radeon R9 390X will be 55 – 65 per cent faster than the Radeon R9 290X.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: Since AMD is already showcasing Radeon R9 390X in action, it is not surprising that its specifications show up on the web. Still, we have no idea whether these specs are final.

The post AMD Radeon R9 390X to feature 8.6TFLOPS performance, 8GB HBM memory first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amdradeon-r9-390x-to-feature-8-6tflops-performance-8gb-hbm-memory/feed/ 31
First details about AMD Radeon R9 370 ‘Trinidad Pro’ surface https://www.kitguru.net/components/graphic-cards/anton-shilov/first-details-about-amd-radeon-r9-370-trinidad-pro-surface/ https://www.kitguru.net/components/graphic-cards/anton-shilov/first-details-about-amd-radeon-r9-370-trinidad-pro-surface/#comments Thu, 12 Mar 2015 09:45:15 +0000 http://www.kitguru.net/?p=239583 Advanced Micro Devices and its partners have already started to prepare for the arrival of the next-generation graphics processing units, according to a media report. XFX, one of leading suppliers of Radeon graphics adapters, already has AMD Radeon R9 370 “Trinidad Pro” graphics cards in its catalogue. VideoCardz has published an excerpt from XFX’s list …

The post First details about AMD Radeon R9 370 ‘Trinidad Pro’ surface first appeared on KitGuru.]]>
Advanced Micro Devices and its partners have already started to prepare for the arrival of the next-generation graphics processing units, according to a media report. XFX, one of leading suppliers of Radeon graphics adapters, already has AMD Radeon R9 370 “Trinidad Pro” graphics cards in its catalogue.

VideoCardz has published an excerpt from XFX’s list of upcoming products, which claims that the company is working on two Radeon R9 370 graphics cards: one with 2GB, whereas another with 4GB of GDDR5 memory onboard. The new adapters are projected to arrive in early April, which contradicts the information that AMD wants to roll out the whole Radeon R9 300-series family at once.

amd_radeon_graphics_artwork

Both Radeon R9 370 graphics cards carry “Trinidad Pro” graphics processors and feature 256-bit memory bus. The graphics boards are built on relatively short six-layer printed circuit boards (of around 167mm in length) with one 6-pin auxiliary PCI Express power connector, which indicates that they are relatively affordable. It is likely that the Radeon R9 370 will cost considerably less than $199.

It is expected that the “Trinidad” graphics processing units are based on the GCN 1.2 or GCN 1.3 architecture, but their exact configurations are unknown. It is likely that the fully-fledged “Trinidad XT” will feature 1536 or 1664 stream processors (24 or 26 GCN compute units), but the configuration of the “Trinidad Pro” is completely unclear.

xfx_unofficial_amd_radeon_r9_370_database

If the information about the launch schedule of the Radeon R9 370 “Trinidad Pro” is correct and AMD plans to roll out these products in early April, then the company has probably changed its plans considerably. While in the past AMD did introduce new mainstream GPUs separately from high-end offerings, this did not make a lot of sense. Such graphics chips never attract a lot of attention no matter how innovative they are and therefore their introductions do not receive a lot of coverage.

AMD and XFX did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: While Radeon R9 370 “Trinidad Pro” does not seem to be a very expensive solution from costs point of view, it is still likely more expensive to manufacture than Nvidia’s GeForce GTX 960 due to 256-bit memory bus. While the GeForce GTX 960 is positioned for higher-end market segment, Nvidia can easily lower it price or introduce its cheaper version if the Radeon R9 370 harms its positions in the lower-end segments.

The post First details about AMD Radeon R9 370 ‘Trinidad Pro’ surface first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/first-details-about-amd-radeon-r9-370-trinidad-pro-surface/feed/ 3
AMD to license Radeon graphics technology to MediaTek – report https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-to-license-radeon-graphics-technology-to-mediatek-report/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-to-license-radeon-graphics-technology-to-mediatek-report/#comments Tue, 10 Mar 2015 01:14:19 +0000 http://www.kitguru.net/?p=239325 In a bid to monetize its graphics processing technologies, Advanced Micro Devices plans to license its Radeon cores to MediaTek, a rapidly growing designer of application processors for smartphones and tablets. The move will bring additional revenues to AMD, whereas MediaTek will be able to differentiate itself from competitors. AMD is not interested in making …

The post AMD to license Radeon graphics technology to MediaTek – report first appeared on KitGuru.]]>
In a bid to monetize its graphics processing technologies, Advanced Micro Devices plans to license its Radeon cores to MediaTek, a rapidly growing designer of application processors for smartphones and tablets. The move will bring additional revenues to AMD, whereas MediaTek will be able to differentiate itself from competitors.

AMD is not interested in making chips for smartphones and tablets: the market is highly competitive and many of mobile system-on-chip designers are not profitable. Licensing graphics cores – like ARM and Imagination Technologies do – brings guaranteed profit to owners of intellectual property. It makes a great sense for AMD to license low-power Radeon cores to other companies interested in high-performance graphics.

Fudzilla reports that MediaTek will be AMD’s first customer to license Radeon graphics technology. No details are known at the moment, but it is logical to expect mobile SoC designer to use Radeon graphics for its high-end application processors. MediaTek has been trying to enter the market of premium mobile APs for some time now and with Radeon graphics it will finally be able to offer truly advanced mobile processors.

mediatek_chip_soc_app_processor

AMD sold off its Imageon division, which designed mobile SoCs with low-power graphics, to Qualcomm in 2009 for $65 million. Since then the company did not offer anything truly low-power and its Fusion hybrid processors for tablets have failed to win designs with device makers.

It is rather ironic that Nvidia, which announced plans to license its graphics processing technologies to third parties in mid-2013, still has not signed a single licensing contract. AMD implied that it could license its graphics cores to others, but did not officially unveiled such plans.

AMD and MediaTek did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: If AMD enters graphics IP licensing business, it will probably offer Radeon not only to MediaTek, but also to other developers of application processors. Moreover, the company could develop semi-custom mobile SoCs itself in case a large smartphone vendor wants it to.

The post AMD to license Radeon graphics technology to MediaTek – report first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-to-license-radeon-graphics-technology-to-mediatek-report/feed/ 24
AMD to introduce its Radeon R9 300-series lineup at Computex https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-to-introduce-its-radeon-r9-300-series-lineup-at-computex/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-to-introduce-its-radeon-r9-300-series-lineup-at-computex/#comments Thu, 05 Mar 2015 11:05:20 +0000 http://www.kitguru.net/?p=238767 Sources with knowledge of Advanced Micro Devices’ roadmap have revealed that the company plans to introduce its new family of Radeon R9 300-series graphics cards closer to Computex than CeBIT, as originally planned. AMD had hoped to push out one or two new cards in March and then re-brand many others to refresh the range. …

The post AMD to introduce its Radeon R9 300-series lineup at Computex first appeared on KitGuru.]]>
Sources with knowledge of Advanced Micro Devices’ roadmap have revealed that the company plans to introduce its new family of Radeon R9 300-series graphics cards closer to Computex than CeBIT, as originally planned. AMD had hoped to push out one or two new cards in March and then re-brand many others to refresh the range. That is no longer the plan.

The challenge for Advanced Micro Devices is that it needs to achieve two rather different (and sometimes opposing) tasks in the first half of this year. It must significantly reduce inventory in the channel and it has to try and boost its dropping market share. If AMD does not ship anything new, its own sales and market share will decline. However, if AMD ships brand-new offerings, older hardware stalls in the channel, impacts prices and makes it difficult to sell new products.

FOLLOW UP: AMD demonstrates unannounced flagship Radeon R9 at GDC.

amd_radeon_artwork_angle_new

According to sources from the Far East, AMD originally wanted to unleash at least one of its all-new Radeon R9 300-series graphics card at the CeBIT trade-show in early March. These new cards would feature the company’s latest high-end GPU and high-bandwidth memory (HBM). If AMD’s engineers have done a good job, then this Radeon R9 290-series replacement would be the company’s fastest card ever, especially with the latest games running ultra-high-definition resolutions like 4K or 5K. If that happens, then the launch would significantly disrupt sales of all other Radeon R9 series products, so the company decided not to unveil its new top-of-the-range graphics boards this month.

Once AMD has a new Radeon R9-class product ready, it could change the schedule again, but it seems that the company does not want to launch its new product as soon as possible. In the wake of the GeForce GTX 970 memory allocation issue for Nvidia, a new launch might have helped AMD capture market share, but it now seems to be taking other factors into account.

The sources with knowledge of AMD plans revealed to KitGuru that Computex has been targeted as the launch timeframe for AMD’s upcoming graphics adapters and a “full line up” was demanded from senior management and engineers. Instead of launching just one new graphics solution and a load of re-brands, AMD intends to roll-out a whole new range of graphics cards at Computex in early June. At present details about the lineup are not clear, but expect several all-new graphics solutions to be unveiled, whereas some re-branded products will likely show up in the following months.

amd_radeon_shop-home-component

While AMD does not comment on reports about product plans and launch schedules, the company indirectly confirmed that its new graphics processing units will be out rather later than sooner during the Morgan Stanley Technology, media and telecom conference this week. Apparently, AMD considers second half of this year as a time when it will try to regain lost market share from Nvidia.

“We are confident that as we get into the second half of 2015 with the launch of that [new graphics] product, we will gain back the market share which is low from my standpoint and historically,” said Devinder Kumar, chief financial officer of AMD. “We need to be significantly higher than where we are right now.”

Discuss on our Facebook page, HERE.

KitGuru Says: The reason why AMD prefers to delay introduction of new graphics processing units seems could be rather simple: sales dynamics of Radeon R9 280- and 290-series is not very good in the first quarter and AMD’s partners need additional time to get rid of them. Still, while AMD’s plan regarding launch timeframe seems to be clear now, the details about the exact lineup will probably remain in doubt until the last moment. KitGuru will continue to investigate AMD’s intentions in the coming weeks.

The post AMD to introduce its Radeon R9 300-series lineup at Computex first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-to-introduce-its-radeon-r9-300-series-lineup-at-computex/feed/ 148
AMD to unify platforms for high-end FX chips, mainstream APUs https://www.kitguru.net/components/cpu/anton-shilov/amd-to-unify-platforms-for-high-end-fx-chips-mainstream-apus/ https://www.kitguru.net/components/cpu/anton-shilov/amd-to-unify-platforms-for-high-end-fx-chips-mainstream-apus/#comments Thu, 29 Jan 2015 04:03:12 +0000 http://www.kitguru.net/?p=233089 At present Advanced Micro Devices, just like Intel Corp., has two desktop platforms: socket FM2+ for mainstream accelerated processing units and socket AM3+ for high-end FX central processing units. When AMD introduces its new chips in 2016, the company will unify the two platforms, a media report claims. AMD’s forthcoming code-named “Bristol Ridge” and “Summit …

The post AMD to unify platforms for high-end FX chips, mainstream APUs first appeared on KitGuru.]]>
At present Advanced Micro Devices, just like Intel Corp., has two desktop platforms: socket FM2+ for mainstream accelerated processing units and socket AM3+ for high-end FX central processing units. When AMD introduces its new chips in 2016, the company will unify the two platforms, a media report claims.

AMD’s forthcoming code-named “Bristol Ridge” and “Summit Ridge” products will use socket FM3 platforms, according to SweClockers. Mainboards with the FM3 sockets will utilize DDR4 memory, but will sport an unknown number of channels. Other peculiarities of the platform remain unknown, but given the fact that they will support both FX-series and A-series processors, expect their feature-set to be flexible.

amd_kaveri_fx_mobile

AMD’s “Bristol Ridge” APUs will feature four code-named “Excavator” cores, a Radeon graphics engine based on the GCN 1.2 or more advanced architecture and 95W thermal design power. The chip will be similar to this year’s “Carrizo”, but will be optimized for operation at high clock-rates. The APUs will be made using 28nm fabrication process.

By contrast, AMD’s “Summit Ridge” central processing units will sport up to eight next-generation “Zen” high-performance x86 cores, L3 cache and up to 95W thermal design power. The CPUs will be manufactured using 14nm manufacturing technology.

The “Bristol Ridge”, “Summit Ridge” processors as well as the FM3 mainboards will become available in the third quarter of 2016, more than 1.5 years from now. The new platforms will use I/O controllers code-named “Promontory”, which are rumoured to be developed by Asmedia.

amd_fusion_kaveri_steamroller_piledriver_excavator

The unification of the platforms has both pros and cons. On the one hand, it means that mainboard makers will not have to support two types of motherboards for AMD processors. On the other hand, it means that AMD will be unable to incorporate any exclusive features into its high-end platforms. For example, Intel’s high-end desktop (HEDT) processors integrate quad-channel memory controller and feature up to 140W of thermal design power, which allows the company to offer CPUs with unprecedented performance. Moreover, Intel's X99 platform offers considerably better I/O feature configuration than Intel's Z97 chipset.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: Looks like either AMD is extremely confident of its Zen architecture and it believes that it will be able to address all markets with 95W parts and mainstream platform capabilities, or it simply has no plans to address the market of high-end PCs even with its next-gen offerings.

The post AMD to unify platforms for high-end FX chips, mainstream APUs first appeared on KitGuru.]]>
https://www.kitguru.net/components/cpu/anton-shilov/amd-to-unify-platforms-for-high-end-fx-chips-mainstream-apus/feed/ 48
AMD develops ‘Arctic Islands’ family of graphics processing units https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-develops-arctic-islands-family-of-graphics-processing-units/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-develops-arctic-islands-family-of-graphics-processing-units/#comments Tue, 27 Jan 2015 23:59:13 +0000 http://www.kitguru.net/?p=232810 Advanced Micro Devices yet has to reveal its new families of graphics processing units this year, but already now the code-name of AMD’s 2016 graphics products lineup is known. Apparently, the company will continue to use names of islands to call its next-generation chips. AMD’s next-generation family of Radeon GPUs will be called “Arctic Islands”, …

The post AMD develops ‘Arctic Islands’ family of graphics processing units first appeared on KitGuru.]]>
Advanced Micro Devices yet has to reveal its new families of graphics processing units this year, but already now the code-name of AMD’s 2016 graphics products lineup is known. Apparently, the company will continue to use names of islands to call its next-generation chips.

AMD’s next-generation family of Radeon GPUs will be called “Arctic Islands”, reports SweClockers. Therefore, expect code-names like Greenland, Svalbard, Ellesmere, Wrangel and others. At present nothing particular is known about the new family, except of the fact that it will traditionally cover every market segment from top to bottom. It is likely that the new graphics chips will be made using 14nm or 16nm FinFET process technologies.

AMD’s product families like “Southern Islands”, “Sea Islands” or “Volcanic Islands” may, or may not, be based on the same architecture. Traditionally, families contain chips that may belong to different generations and may have different feature-sets.

amd_radeon_artwork_angle_new

It is anticipated that AMD will reveal its all-new family of graphics processing units next year. The lineup will be based on a post-GCN architecture and will therefore bring-in new levels of performance and new functionality. Unfortunately, it is unknown whether the new GPUs will carry “Artic Islands” code-names.

It is expected that the “Arctic Islands” products will be sold under AMD Radeon R* 400-series brand names.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: A good news is that AMD seems to have a roadmap for 2016 and will have products to sell next year. Unfortunately, we have no idea how competitive will those products be and what levels of performance should we expect from them. In many cases AMD’s new product families are not all-new, but contain loads of previous-generation offerings.

The post AMD develops ‘Arctic Islands’ family of graphics processing units first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-develops-arctic-islands-family-of-graphics-processing-units/feed/ 2
AMD preps ‘Bristol Ridge’ APUs: ‘Carrizo’ for desktops https://www.kitguru.net/components/cpu/anton-shilov/amd-preps-bristol-ridge-apus-carrizo-for-desktops/ https://www.kitguru.net/components/cpu/anton-shilov/amd-preps-bristol-ridge-apus-carrizo-for-desktops/#comments Tue, 27 Jan 2015 21:41:53 +0000 http://www.kitguru.net/?p=232802 Although Advanced Micro Devices does not have plans to bring the code-named “Carrizo” accelerated processing units to the market of traditional desktop computers, it is expected that a similar chip will actually make it into desktops. Unfortunately, this will happen only next year and it is unlikely that it will offer very high performance. Later …

The post AMD preps ‘Bristol Ridge’ APUs: ‘Carrizo’ for desktops first appeared on KitGuru.]]>
Although Advanced Micro Devices does not have plans to bring the code-named “Carrizo” accelerated processing units to the market of traditional desktop computers, it is expected that a similar chip will actually make it into desktops. Unfortunately, this will happen only next year and it is unlikely that it will offer very high performance.

Later this year AMD intends to refresh its desktop product lineup with faster “Kaveri” APUs code-named “Godavari”. The new accelerated processing units will be barely faster than existing A-series chips from AMD, therefore, do not expect the company to improve its positions against Intel using the upcoming desktop products. Moreover, according to a report by SweClockers web-site, AMD’s next-generation APUs are pretty far away and when they hit the market, they will hardly be strong competitors.

AMD is developing is code-named “Bristol Ridge” APU, which will sport four “Excavator” cores (two dual-core modules), AMD Radeon graphics processing unit with 512 stream processors (based on the GCN 1.2 or more advanced architecture), DDR4 memory controller and heterogeneous system architecture features. The chip is set to be made using 28nm fabrication process and will have up to 95W TDP. The accelerated processing unit is, basically, a new version of AMD’s “Carrizo” optimized for operation at high clock-rates.

amd_fusion_kaveri_steamroller_piledriver_excavator

The “Bristol Ridge” APUs will offer considerably higher performance than “Carrizo” thanks to higher frequencies, improved memory bandwidth and other optimizations. Unfortunately, the new chips will become available only in the third quarter of 2016. By then Intel will have a full-range of “Skylake” processors and will be gearing up to start manufacturing of its first central processing units using 10nm fabrication technology.

Since the “Bristol Ridge” APUs will use proven x86 cores, graphics engine and design, it is likely that AMD will try to release it rather sooner than later in order to offer desktop PCs something better than “Kaveri”.

AMD did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: If AMD rolls-out “Excavator”-based APUs for desktops in 2016, then it looks like its new micro-architecture code-named “Zen” will only be used for mainstream accelerated processing units in 2017, two years from now. Quite naturally this will negatively affect financial performance of AMD.

The post AMD preps ‘Bristol Ridge’ APUs: ‘Carrizo’ for desktops first appeared on KitGuru.]]>
https://www.kitguru.net/components/cpu/anton-shilov/amd-preps-bristol-ridge-apus-carrizo-for-desktops/feed/ 13
AMD: We have great GPU products in the pipeline, we will gain market share https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-we-have-great-gpu-products-in-the-pipeline-we-will-gain-market-share/ https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-we-have-great-gpu-products-in-the-pipeline-we-will-gain-market-share/#comments Sat, 10 Jan 2015 04:33:04 +0000 http://www.kitguru.net/?p=229988 Lisa Su, chief executive officer of Advanced Micro Devices, said at the Consumer Electronics Show that the company has a number of “great” graphics products in the pipeline that will help it to fight back market share from Nvidia Corp. The year 2014 was a mixed a bag for Advanced Micro Devices when it comes …

The post AMD: We have great GPU products in the pipeline, we will gain market share first appeared on KitGuru.]]>
Lisa Su, chief executive officer of Advanced Micro Devices, said at the Consumer Electronics Show that the company has a number of “great” graphics products in the pipeline that will help it to fight back market share from Nvidia Corp.

The year 2014 was a mixed a bag for Advanced Micro Devices when it comes to graphics processing unit (GPU) business. On the one hand, AMD managed to introduce the world’s highest-performing graphics card, the Radeon R9 295X2, which carries two code-named “Hawaii” GPUs. On the other hand, the company released no new GPUs, except the code-named “Tonga” chip, which hardly increases performance compared to previous-generation Radeon R9 280-series “Tahiti” in modern titles. By contrast, its rival Nvidia released two new graphics processors and four new graphics solutions only on the desktop market, addressing different market segments and winning multiple awards for exceptional performance. As a consequence, AMD lost market share to Nvidia in the second half of 2014. Nonetheless, the company remains optimistic and plans to fight the lost share back.

“As I look into 2015, we have some very good products in the pipeline, we will talk more about them as we go through the year,” said Lisa Su at the J.P. Morgan 13th annual tech forum at International CES. “I absolutely view it as a share gain opportunity over that period of time.”

amd_radeon_artwork

Quite naturally, the head of AMD does not reveal any particular details about the company’s plans. From unofficial sources it is known that the company readies at least one new Radeon R9-series enthusiast-class high-end graphics processor that will not only significantly improve performance compared to existing graphics adapters, but will also be the first GPU in the industry to take advantage of the stacked high-bandwidth memory (HBM).

A good news is that Ms. Su confirmed that the company has multiple products in the pipeline, which means that the company is on-track to release not one, but a number of new graphics processing units.

“You will see, obviously, new graphics products from us this year, we usually keep that quite tight until we are ready to launch those,” said Ms. Su.

amd_radeon_r9_290_2

Given the fact that many graphics chips in AMD’s product lineups for desktop and laptop computers are more than two years old, it is about time for the company to introduce new GPUs. Unfortunately, it is completely unclear how many new graphics processing units and how many new products on their base AMD plans to bring to the market in the coming quarters.

Keeping in mind that AMD plans to introduce its post-GCN graphics processors only sometimes in 2016, the 2015 GPUs from AMD will continue to use the current graphics core next (GCN) technology. Expect AMD’s new Radeon graphics products to feature GCN 1.2 architecture, a couple of new graphics-related enhancements, hardware decoders/encoders for 4K/UHD video (H.265/HEVC, VP9, H.264 for 4K, etc.), video playback quality improvements and some other things.

Discuss on our Facebook page, HERE.

KitGuru Says: A good news for AMD is that it already knows what to expect from Nvidia in 2015 and that the next-generation products from its arch-rival based on the code-named “Pascal” architecture are at least a year away. Obviously, Nvidia could refresh its product lineup later in 2015 using its chips based on the Maxwell architecture, which could bring a number of surprises. Nonetheless, AMD still has better understanding what to expect from its rival than it did last year.

The post AMD: We have great GPU products in the pipeline, we will gain market share first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/amd-we-have-great-gpu-products-in-the-pipeline-we-will-gain-market-share/feed/ 11
Sapphire Technology teases NFC brand https://www.kitguru.net/components/graphic-cards/anton-shilov/sapphire-technology-teases-nfc-graphics-cards/ https://www.kitguru.net/components/graphic-cards/anton-shilov/sapphire-technology-teases-nfc-graphics-cards/#comments Wed, 24 Dec 2014 00:12:07 +0000 http://www.kitguru.net/?p=228000 Sapphire Technology on Wednesday uploaded a teaser video to its account on YouTube, teasing, possibly, new graphics cards featuring mysterious NFC technology. Like with many viral videos, Sapphire’s video does not explain what exactly it advertises. “Passion is hard,” says the voice in the video. “Sometimes it hurts. People tell you to go, they tell …

The post Sapphire Technology teases NFC brand first appeared on KitGuru.]]>
Sapphire Technology on Wednesday uploaded a teaser video to its account on YouTube, teasing, possibly, new graphics cards featuring mysterious NFC technology. Like with many viral videos, Sapphire’s video does not explain what exactly it advertises.

sapphire_nfc

“Passion is hard,” says the voice in the video. “Sometimes it hurts. People tell you to go, they tell you to stop. Sometimes you tell yourself to stop, but you cannot. Only when it is not from concentrate, they you can stop. Because then it is done.”

[yframe url='http://www.youtube.com/watch?v=0CyUUj9eLFo']

While we have no idea what does the NFC abbreviate mean in Sapphire’s case, we do know that the company sells graphics cards for gamers. Nowadays graphics cards supplier can develop its own printed circuit boards and cooling systems for its products. Therefore, NFC could be a new series of graphics adapters featuring Sapphire’s own PCB and cooling solution tailored for enthusiasts.

The NFC products could potentially be vastly different from everything else on the market. Since it is “not from concentrate”, it may mean that it is not based on AMD’s reference designs that power the majority of graphics adapters featuring Radeon graphics processing units. However, unique PCBs and cooling systems are not usually a reason to start a new series of products, unless, of course, you are going to expand this series with other offerings. Perhaps, Sapphire wants to enter the market of hardware for gamers with a new brand that could eventually compete against, for example, Asustek Computer's ROG.

Sapphire will reveal more about NFC in January.

Sapphire did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: While we do not have many ideas regarding Sapphire’s NFC, maybe you do. Share your thoughts on Facebook or in the comments below!

The post Sapphire Technology teases NFC brand first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/sapphire-technology-teases-nfc-graphics-cards/feed/ 1