Digging into a specific market
A little while ago, I decided to think about processor design as a game. You are given a budget of complexity, which is determined by your process node, power, heat, die size, and so forth, and the objective is to lay out features in the way that suits your goal and workload best. While not the topic of today's post, GPUs are a great example of what I mean. They make the assumption that in a batch of work, nearby tasks are very similar, such as the math behind two neighboring pixels on the screen. This assumption allows GPU manufacturers to save complexity by chaining dozens of cores together into not-quite-independent work groups. The circuit fits the work better, and thus it lets more get done in the same complexity budget.
Carrizo is aiming at a 63 million unit per year market segment.
This article is about Carrizo, though. This is AMD's sixth-generation APU, starting with Llano's release in June 2011. For this launch, Carrizo is targeting the 15W and 35W power envelopes for $400-$700 USD notebook devices. AMD needed to increase efficiency on the same, 28nm process that we have seen in their product stack since Kabini and Temash were released in May of 2013. They tasked their engineers to optimize their APU's design for these constraints, which led to dense architectures and clever features on the same budget of complexity, rather than smaller transistors or a bigger die.
15W was their primary target, and they claim to have exceeded their own expectations.
Backing up for a second. Beep. Beep. Beep. Beep.
When I met with AMD last month, I brought up the Bulldozer architecture with many individuals. I suspected that it was a quite clever design that didn't reach its potential because of external factors. As I started this editorial, processor design is a game and, if you can save complexity by knowing your workload, you can do more with less.
Bulldozer looked like it wanted to take a shortcut by cutting elements that its designers believed would be redundant going forward. First and foremost, two cores share a single floating point (decimal) unit. While you need some floating point capacity, upcoming workloads could use the GPU for a massive increase in performance, which is right there on the same die. As such, the complexity that is dedicated to every second FPU can be cut and used for something else. You can see this trend throughout various elements of the architecture.
Subject: Graphics Cards | June 2, 2015 - 05:56 PM | Tim Verry
Tagged: zotac, water cooling, titan x, gtx titan x, computex 2015, computex, arcticstorm
NVIDIA’s AIB partners are out in full force at Computex 2015 with new graphics cards and new coolers. Among the fray is Zotac with a customized GTX TITAN X card using the ArcticStorm Hybrid cooler which is an air cooler that also features a water block and can be integrated into your custom water cooling loop.
Of course, the TITAN X is NVIDIA’s top end Maxwell (GM200) graphics processor built on a 28nm process. It has 3,072 CUDA cores, 192 texture units, 96 ROPs, and a 250W TDP.
Zotac is factory overclocking this GPU to 1026 MHz base and 1114 MHz boost. The 12GB of GDDR5 memory sits on a 384-bit bus and is also (slightly) factory overclocked at 7010 MHz.
The card itself has the same array of video outputs (three DisplayPort, one HDMI, and one DL-DVI) and the same PCI-E power connectors (6-pin + 8-pin) as the reference card.
The ArcticStorm Hybrid cooler can work as an air cooler or as an air + water cooler similar to ASUS’ Poseidon cards. The Zotac cooler features a copper cold plate paired with heatpipes and a large aluminum fin array cooled by three 90mm shrouded fans.
This cooler should run quieter than the NVIDIA reference card and, especially when connected to your custom liquid cooling loop, and offer lower temperatures. Zotac did not opt for two 8-pin PCI-E so extreme overclocking might be out of the question, but the card should still be heavily overclockable in general should you get a good chip.
Naturally, Zotac is holding off on pricing and availability details of the GTX TITAN X ArcticStorm (ZT-90402-10P) until it is ready to ship which should be soon. Stay tuned to PC Perspective for more details.
Subject: Graphics Cards | June 2, 2015 - 04:40 PM | Jeremy Hellstrom
Tagged: video, nvidia, maxwell, GTX 980 Ti, gsync, gm200, geforce, gameworks vr, g-sync, dx12, 6Gb
Hopefully by now you have familiarized yourself with Ryan's review of the new GTX980 Ti and perhaps even some of the other reviews below. One review that you should not miss is by Scott over at The Tech Report as they used an X99 system for benchmarking and covered a slightly different suite of games. The games both sites tested show very similar results and in the case of BF4 and Crysis 3, showed that the R9 295 X2 is still a force to be reckoned with, especially when it is on sale at a price similar to the 980 Ti. In testing the Witcher 3 and Project Cars, the 980Ti showed smoother performance with impressive minimum frame times. Overall, The Tech Report gives the nod to the new GTX 980 Ti for more fluid gameplay but does offer the necessary reminder, AMD will be launching their new products very soon and could offer new competition.
"You knew it was coming. When Nvidia introduced the GeForce Titan X, it was only a matter of time before a slightly slower, less expensive version of that graphics card hit the market. That's pretty much how it always happens, and this year is no exception."
Here are some more Graphics Card articles from around the web:
- NVIDIA GeForce GTX 980 Ti @ [H]ard|OCP
- NVIDIA GEFORCE GTX 980 Ti @ NitroWare
- EVGA GeForce GTX 980Ti SC Review @ HiTech Legion
- NVIDIA GeForce GTX 980Ti Review @HiTech Legion
- NVIDIA GeForce GTX 980 Ti Review @ Neoseeker
- NVIDIA GeForce GTX 980 Ti Review @ OCC
- The New King Of High-end: NVIDIA GeForce GTX 980 Ti Review @ Techgage
- Nvidia GeForce GTX 980 Ti Video Card Preview @ Hardware Asylum
- Nvidia GeForce GTX 980 Ti @ Legion Hardware
- The New Nvidia GeForce GTX 980 Ti: Features and Tech Overview @ Bjorn3d
- The NVIDIA GTX 980Ti Performance Review @ Hardware Canucks
- Nvidia GTX980 Ti @ KitGuru
- EVGA GeForce GTX 960 SuperSC Graphics Card Review @ Techgage
- NVIDIA GeForce GTX 980 Ti 6 GB @ techPowerUp
- EVGA GTX 980 HYBRID Review @ Hardware Canucks
- Benchmarking The Latest AMD & NVIDIA Graphics Cards On Ubuntu Linux @ Phoronix
Subject: Graphics Cards | June 1, 2015 - 10:58 AM | Ryan Shrout
Tagged: evga, precisionx, dx12, DirectX 12
Another interesting bit of news surrounding Computex and the new GTX 980 Ti comes from EVGA and its PrecisionX software. This is easily our favorite tool for overclocking and GPU monitoring, so it's great to see the company continuing to push forward with features and capability. EVGA is the first to add full support for DX12 with an overlay.
What does that mean? It means as DX12 applications that find their way out to consumers and media, we will now have a tool that can help measure performance and monitor GPU speeds and feeds via the PrecisionX overlay. Before this release, we were running the dark with DX12 demos, so this is great news!
You can download the latest version over on EVGA's website!
Subject: Graphics Cards | June 1, 2015 - 06:00 AM | Ryan Shrout
Tagged: maxwell, hydro copper, GTX 980 Ti, gm200, evga, computex 2015, computex, classified, acx
With the release of the brand new GeForce GTX 980 Ti from NVIDIA stirring up the week just before Computex in Taipei, you can be sure that all of NVIDIA's partners are going to be out in force showing off their custom graphics card solutions.
EVGA has several lined up and they were able to share some information with us. First up is the standard but custom cooled GTX 980 Ti that uses the ACX 2.0+ cooler. This new version of the ACX 2.0 cooler includes a "memory MOSFET Cooling Plate (MMCP) reduces MOSFET temperatures up to 13%, and optimized Straight Heat Pipes (SHP) additionally reduce GPU temperature by 5C. ACX 2.0+ coolers also feature optimized swept fan blades, double ball bearings and an extreme low power motor, delivering more air flow with less power, unlocking additional power for the GPU." We're looking forward to some hands-on testing with this card when it shows up on Monday morning.
Also due for an update is the EVGA Classified line, often considered one of the best cards you can buy for overclockers and extreme enthusiasts. Though the card is also using the ACX 2.0+ cooler it will include additional power delivery improvements on the PCB that help stretch available performance headroom.
Following in the footsteps of the recently released Titan X Hybrid comes the GTX 980 Ti version. This card will use a standard blower cooler for the memory and power delivery while attaching a self-contained water cooler for the GPU itself. This should keep the GPU temperature down quite a bit though the benefit to real-world overclocking is debatable with the voltage lock that NVIDIA has kept in place. If only they were to change that...
Finally, for the water cooling fans among us we have the GTX 980 Ti Hydro Copper, using a water block from EK.
Interested in clock speeds?
- EVGA 980 Ti ACX 2.0
- Base: 1000 MHz
- Boost: 1076 MHz
- Memory: 7010 MHz
- EVGA 980 Ti Classified
- Base: 1152 MHz
- Boost: 1241 MHz
- Memory: 7010 MHz
- EVGA 980 Ti Hybrid
- Base: 1140 MHz
- Boost: 1228 MHz
- Memory: 7010 MHz
I am still waiting for pricing and availability information which we will pass on as soon as we get it!
Subject: Graphics Cards | June 1, 2015 - 02:00 AM | Sebastian Peak
Tagged: computex, Poseidon GTX 980 Ti, GTX 980 Ti, gpu, ASUS ROG, computex 2015
ASUS has already announced a Poseidon version of the new NVIDIA GeForce GTX 980 Ti graphics card, which is part of the company's Republic of Gamers (ROG) lineup.
No photo of the GTX 980 Ti available yet, so here's the GTX 980 version for reference
"ROG Poseidon GTX 980 Ti incorporates the DirectCU H2O hybrid cooling solution with a combined vapor chamber and water channels to give users cooler temperatures along with improved noise reduction for 3x quieter performance. ASUS graphics cards are produced via exclusive Auto-Extreme technology, an industry-first 100% automated process, and feature aerospace-grade Super Alloy Power II components for unsurpassed quality and reliability. ROG Poseidon GTX 980Ti also features GPU Tweak II with XSplit Gamecaster for intuitive performance tweaks and gameplay streaming."
We'll keep you posted on pricing and availability (and actual product photos) once they're available!
When NVIDIA launched the GeForce GTX Titan X card only back in March of this year, I knew immediately that the GTX 980 Ti would be close behind. The Titan X was so different from the GTX 980 when it came to pricing and memory capacity (12GB, really??) that NVIDIA had set up the perfect gap with which to place the newly minted GTX 980 Ti. Today we get to take the wraps off of that new graphics card and I think you'll be impressed with what you find, especially when you compare its value to the Titan X.
Based on the same Maxwell architecture and GM200 GPU, with some minor changes to GPU core count, memory size and boost speeds, the GTX 980 Ti finds itself in a unique spot in the GeForce lineup. Performance-wise it's basically identical in real-world game testing to the GTX Titan X, yet is priced $350 less that that 12GB behemoth. Couple that with a modest $50 price drop in the GTX 980 cards and you have all markers of an enthusiast graphics card that will sell as well as any we have seen in recent generations.
The devil is in all the other details, of course. AMD has its own plans for this summer but the Radeon R9 290X is still sitting there at a measly $320, undercutting the GTX 980 Ti by more than half. NVIDIA seems to be pricing its own GPUs as if it isn't even concerned with what AMD and the Radeon brand are doing. That could be dangerous if it goes on too long, but for today, can the R9 290X put up enough fight with the aging Hawaii XT GPU to make its value case to gamers on the fence?
Will the GeForce GTX 980 Ti be the next high-end GPU to make a splash in the market, or will it make a thud at the bottom of the GPU gene pool? Let's dive into it, shall we?
Subject: Graphics Cards | May 29, 2015 - 11:26 AM | Ryan Shrout
Tagged: catalyst, amd, 15.5 beta
Last night AMD released a new Catalyst driver, 15.5 Beta, that targets performance improvements in both Project Cars and The Witcher 3: Wild Hunt. You can pick up the new driver for both 32-bit and 64-bit versions of Windows 7 and Windows 8.1 right here. The full display driver version is 14.502.1014.1001.
The specific changes?
Highlights of AMD Catalyst™ 15.5 Beta Windows Driver
Crossfire Profile Update for:
- The Witcher 3 - Wild Hunt
Performance Improvements for the following :
- The Witcher 3 - Wild Hunt : Up to 10% performance increase on single GPU Radeon R9 and R7 Series graphics products
- Project Cars - Up to 17% performance increase on single GPU Radeon R9 and R7 Series graphics products
Users of the Radeon R9 295X2 will be glad to see support for their hardware added for The Witcher 3 and just about everyone will be glad to see some dramatic performance improvements in Project Cars and Witcher 3. We know from testing internally as well as widely reported issues that AMD Radeon graphics cards had issues with Project Cars, resulting in performance well behind comparable NVIDIA GeForce hardware. With as much as 17% improvement for Radeon R9 and R7 hardware though, hopefully that frame rate increases quite a bit.
We'll be doing some testing with this new driver here today, and if anything jumps out at us, we'll be sure to let you know!
Subject: Graphics Cards | May 29, 2015 - 11:05 AM | Sebastian Peak
Tagged: rumors, radeon, hbm, graphics, gpu, Fury, Fiji, amd
Another rumor has emerged about an upcoming GPU from AMD, and this time it's a possible name for the HBM-powered Fiji card a lot of us have been speculating about.
The rumor from VideoCardz via Expreview (have to love the multiple layers of reporting here) states the the new card will be named Radeon Fury:
"Radeon Fury would be AMD’s response to growing popularity of TITAN series. It is yet unclear how AMD is planning to adopt Fury naming schema. Are we going to see Fury XT or Fury PRO? Well, let’s just wait and see. This rumor also means that Radeon R9 390X will be a direct rebrand of R9 290X with 8GB memory."
Of course this is completely unsubstantiated, and Fury is a branding scheme from the ATI days, but who knows? I can only hope that if true, AMD will adopt all caps: TITAN! FURY! Feel the excitement. What do you think of this possible name for the upcoming AMD flagship GPU?
Big Things, Small Packages
Sapphire isn’t a brand we have covered in a while, so it is nice to see a new and interesting product drop on our door. Sapphire was a relative unknown until around the release of the Radeon 9700 Pro days. This was around the time when ATI decided that they did not want to be so vertically integrated, so allowed other companies to start buying their chips and making their own cards. This was done to provide a bit of stability for ATI pricing, as they didn’t have to worry about a volatile component market that could cause their margins to plummet. By selling just the chips to partners, ATI could more adequately control margins on their own product while allowing their partners to make their own deals and component choices for the finished card.
ATI had very limited graphics card production of their own, so they often would farm out production to second sources. One of these sources ended up turning into Sapphire. When ATI finally allowed other partners to produce and brand their own ATI based products, Sapphire already had a leg up on the competition by being a large producer already of ATI products. They soon controlled a good portion of the marketplace by their contacts, pricing, and close relationship with ATI.
Since this time ATI has been bought up by AMD and they no longer produce any ATI branded cards. Going vertical when it come to producing their own chips and video cards was obviously a bad idea, we can look back at 3dfx and their attempt at vertical integration and how that ended for the company. AMD obviously produces an initial reference version of their cards and coolers, but allows their partners to sell the “sticker” version and then develop their own designs. This has worked very well for both NVIDIA and AMD, and it has allowed their partners to further differentiate their product from the competition.
Sapphire usually does a bang up job on packaging the graphics card. Oh look, a mousepad!
Sapphire is not as big of a player as they used to be, but they are still one of the primary partners of AMD. It would not surprise me in the least if they still produced the reference designs for AMD and then distributed those products to other partners. Sapphire is known for building a very good quality card and their cooling solutions have been well received as well. The company does have some stiff competition from the likes of Asus, MSI, and others for this particular market. Unlike those two particular companies, Sapphire obviously does not make any NVIDIA based boards. This has been a blessing and a curse, depending on what the cycle is looking like between AMD and NVIDIA and who has dominance in any particular marketplace.