Subject: Graphics Cards, Processors | November 12, 2013 - 06:10 PM | Ryan Shrout
Tagged: amd, Kaveri, APU, video, hsa
Yesterday at the AMD APU13 developer conference, the company showed off the upcoming Kaveri APU running Battlefield 4 completely on the integrated graphics. I was able to push the AMD guys along and get a little more personal demo to share with our readers. The Kaveri APU had some of its details revealed this week:
- Quad-core Steamroller x86
- 512 Stream Processor GPU
- 856 GFLOPS of theoretical performance
- 3.7 GHz CPU clock speed, 720 MHz GPU clock speed
AMD wanted to be sure we pointed out in this video that the estimate clock speeds for FLOP performance may not be what the demo system was run at (likely a bit lower). Also, the version of Battlefield 4 here is the standard retail version and with further improvements from the driver team as the upcoming Mantle API implementation will likely introduce even more performance for the APU.
The game was running at 1920x1080 with MOSTLY medium quality settings (lighting set to low) but the results still looked damn impressive and the frame rates were silky and smooth. Considering this is running on a desktop with integrated processor graphics, the game play experience is simply unmatched.
Memory in the system was running at 2133 MHz.
The second demo looks at the image decoding acceleration that AMD is going to enable with Kaveri APUs upon release with a driver. Essentially, as the demonstration shows in the video, AMD is overwriting the integrated Windows JPG decompression algorithm with a new one that utilizes HSA to accelerate on both the x86 and SIMD (GPU) portions of the silicon. For the most strenuous demo that used 22 MP images saw a 100% increase in performance compared to the Kaveri CPU cores alone.
More Details from Lisa Su
The executives at AMD like to break their own NDAs. Then again, they are the ones typically setting these NDA dates, so it isn’t a big deal. It is no secret that Kaveri has been in the pipeline for some time. We knew a lot of the basic details of the product, but there were certainly things that were missing. Lisu Su went up onstage and shared a few new details with us.
Kaveri will be made up of 4 “Steamroller” cores, which are enhanced versions of the previous Bulldozer/Trinity/Vishera families of products. Nearly everything in the processor is doubled. It now has dual decode, more cache, larger TLBs, and a host of other smaller features that all add up to greater single thread performance and better multi-threaded handling and performance. Integer performance will be improved, and the FPU/MMX/SSE unit now features 2 x 128 bit FMAC units which can “fuse” and support AVX 256.
However, there was no mention of the fabled 6 core Kaveri. At this time, it is unlikely that particular product will be launched anytime soon.
Retiring the Workhorses
There is an inevitable shift coming. Honestly, this has been quite obvious for some time, but it has just taken AMD a bit longer to get here than many have expected. Some years back we saw AMD release their new motto, “The Future is Fusion”. While many thought it somewhat interesting and trite, it actually foreshadowed the massive shift from monolithic CPU cores to their APUs. Right now AMD’s APUs are doing “ok” in desktops and are gaining traction in mobile applications. What most people do not realize is that AMD will be going all APU all the time in the very near future.
We can look over the past few years and see that AMD has been headed in this direction for some time, but they simply have not had all the materials in place to make this dramatic shift. To get a better understanding of where AMD is heading, how they plan to address multiple markets, and what kind of pressures they are under, we have to look at the two major non-APU markets that AMD is currently hanging onto by a thread. In some ways, timing has been against AMD, not to mention available process technologies.
Subject: General Tech | August 27, 2013 - 12:30 PM | Jeremy Hellstrom
Tagged: amd, roadmap, 2014, Kaveri, Kabini, carrizo, beema, Excavator, Nolan, 2015, socket sf1b
As is usually the case, AMD will not comment on the accuracy of DigiTimes information but as we have seen in the past their roadmaps have been spot on. Over the next 8 months or so will see the arrival of the Hawaii GPU family and the entrance of Kaveri and Kabini chips, nothing new there but good to have independent confirmation. In the latter part of 2014 and 2015 things are a little more interesting as Beema will replace Kabini with an HSA compliant architecture and use a new socket called FS1B. In 2015 Beema will be replaced by a chip called Nolan and we will finally see the Excavator based Carrizo which are slated to have 45W and 65W versions.
You can expect to see FM1 and AM3 phased out of active production by the end of 2013, with AM3+ and FM2 being the two active sockets until FS1B arrives.
"AMD has recently updated its product roadmap and is set to release its Hawaii-based GPUs at the end of September, Kaveri-based APUs for the high-end segment and Kabini-based APUs for the entry-level segment in the first quarter of 2014, according to sources from the upstream supply chain."
Here is some more Tech News from around the web:
- What Surface RT flop? Nokia said to be readying WinRT slab for September @ The Register
- Java 6 exploit found in the wild @ The Inquirer
- Chlorine has got graphene covered @ Nanotechweb
- Samsung will launch a 55in curved OLED 3D TV in the UK on 5 September @ The Inquirer
- The 20 most bizarre and innovative motherboards: 1999 - 2010 @ Hardware.Info
- NAND flash vendors gearing up for 3D chips @ DigiTimes
- Epic Games’ Tim Sweeney and AMD don’t see eye-to-eye on hUMA @ VR-Zone
- Linksys Smart Wi-Fi Router EA6500 @ Kitguru
- TP-Link TL-PA551KIT AV550+ Gigabit Powerline Kit With AC Passthrough @ eTeknix
- Making S’mores with 50,000 Volts @ Hack a Day
Subject: General Tech | August 12, 2013 - 02:52 PM | Jeremy Hellstrom
Tagged: amd, Kaveri, delay, semantics
The VR-Zone published an article back on the 5th of August which detailed the delay of Kaveri's release until 2014. The information they received put the initial production of the chips in December of this year, with them shipping some time in February of 2014 which they found quite disappointing as initially we were already supposed to be able to buy Kaveri if you go off of the initial announcements. AMD was quick to respond and stated that there is no change to the current release schedule as they had only stated that Kaveri would ship in 2013, not that it would be available for purchase by consumers. This is a frustrating situation for many enthusiast as the tweets and announcement at CES seemed to imply that we would be purchasing these chips already and is even worse for any system builders who had planned to be releasing systems based on Kaveri in time for the holiday season. Maybe gutting the PR department wasn't the best decision AMD has made recently?
"Call it a delay by any other name, but AMD has sent out an official statement saying that Kaveri will be available in 2014 after shipping in 2013.
As a recap: Lisa Su’s Computex 2013 keynote ended with an on-stage demo of Kaveri and an announcement that it would be shipping “towards the end of the year.”"
Here is some more Tech News from around the web:
- The TR Podcast 139: Frame pacing and Carmackulus
- Asus boss flushes down tabs, says 'Windows RT has not been successful' @ The Register
- Sources spill CEO Heins' beans: BlackBerry 'open' to going private @ The Register
- The What Why and How of Wayland and Weston on Linux @ Linux.com
- Camtasia Studio 8 Review @ HiTech Legion
- All Bitcoin Wallets On Android Vulnerable To Theft @ Slashdot
- Raspberry Pi used to make holographic Death Star @ The Inquirer
- Hacking Transcend Wifi SD Cards @ Hack a Day
Subject: Processors | July 31, 2013 - 03:59 AM | Tim Verry
Tagged: Kaveri, fm2, carrizo, APU, amd radeon, amd
Rumors recently surfaced via VR-Zone china that AMD’s Kaveri APU successor will be code-named Carrizo, and it will be compatible with the upcoming FM2+ socket and AMD A88X chipset that Kaveri will use.
AMD’s Carrizo APUs will reportedly be available in TDPs up to 65W and will feature Excavator CPU cores along with a next generation Radeon GPU. Much like Kaveri, Carrizo will be fully HSA compliant. The chips will also include support for DDR4.
Carrizo will allegedly begin sampling in August 2014 with mass production starting around December. That means Carrizo will be available for purchase within the first half of 2015.
FM2+ boards like the ASUS A55BM-A/USB3 are rumored to support AMD's Carrizo APUs (the successor to Kaveri).
The rumors also suggest that Carrizo will be joined by a low power “Beema” System on a Chip (SoC) and a BGA-based Nolan APU for embedded systems. Details on these complementary chips are scarce, however. Perhaps most telling is last bit of the article that suggests that AMD will not be releasing a AM3+ Vishera CPU-only processor successor. It seems AMD is going all in as an APU company after all.
I have been looking forward to the launh of AMD's Kaveri since AFDS 2012, and Carrizo appears to be a refinement of that chip. It should be more power efficient and faster thanks to architecture tweaks and process shrinks. I think that AMDs architecture and HSA approach has potential, and I'm excited to see what these upcoming chips can do with regards to performance.
Subject: Motherboards | July 28, 2013 - 07:40 PM | Tim Verry
Tagged: hUMA, Kaveri, hsa, fm2, asus, APU, A88X, A55, PCI-E 3.0, mATX
ASUS recently announced two new socket FM2+ motherboards that are compatible with AMD’s upcoming “Kaveri” Accelerated Processing Units (APUs). The new boards are the A88XMA and A55BM-A/USB3 and use the A88X and A55 AMD chipsets respectively. Pricing and availability have not yet been released, but the new boards confirm that users will need new motherboards in order to take advantage of AMD’s next generation APUs (though the new FM2+ boards are backwards compatible with the existing APUs, it will not work the other way around). Both motherboards should be available around the time of the Kaveri processor launch (2H 2013).
The AMD A88XMA FM2+ Motherboard.
Both the ASUS A88XMA and A55BM-A/USB3 motherboards come in the mATX form factor. The boards both have FM2+ processor sockets and expansion slots including a single PCI-E 3.0 x16 slot, one PCI-E 2.0 x1 slot, and one legacy PCI slot. The support for PCI-E 3.0 is new for AMD motherboards, and the extra bandwidth may prove useful for as graphics cards get faster and AMD works on its hUMA and HSA architectures to create a layer of virtual memory that can be simultaneously addressed by CPUs and GPUs. There will still be latency to deal with over the PCI-E bus, but more data can be moved back and forth in the same amount of time.
The two ASUS FM2+ motherboards also share the same rear IO options, which include:
- 2 x PS/2
3 x Video outputs:
- 1 x HDMI
- 1 x DVI
- 1 x VGA
- 2 x USB 3.0
- 2 x USB 2.0
- 1 x Gigabit Ethernet
- 3 x Analog audio jacks
The RJ45 jacks are backed by a Realtek 8111G Gigabit Ethernet controller and the audio jacks are handled by a Realtek ALC887-VD chipset. Finally, they also have UEFI BIOSes in common, but from there the two boards diverge in hardware capabilities.
The ASUS A88XMA is the higher-end of the two boards, and features a FM2+ socket, four DDR3 DIMM slots, and six SATA 3 6Gbps ports. It utilizes the AMD A88X chipset which is aimed at enthusiast platforms.
ASUS' A55BM-A/USB3 budget motherboard.
On the other hand, the A55BM-A/USB3 motherboard uses the cheaper A55 chipset. That motherboard features an FM2+ socket, two DDR3 DIMM slots, and six right angle SATA 2 3Gpbs ports. The A55Bm-A/USB3 should be significantly cheaper as a result of the A55 chipset and resulting hardware reductions. In most other respects, ASUS has managed to make the two baords remarkably similar, including aesthetics and basic board layout.
According to Bit-Tech, the two boards are are part of a larger family of boards with the new FM2+ sockets. As such, we should see additional ASUS boards that fill in the gaps between the two models closer to AMD's Kaveri launch. As noted above, ASUS has not provided official pricing or release date information yet.
Subject: General Tech | May 23, 2013 - 01:00 PM | Ken Addison
Tagged: z87, Y500, xbox one, xbox, video, Temash, Richland, podcast, pcper, msi, Lenovo, Kaveri, Kabini, Jaguar, Intel, hgst, gtx 650m, Giagbyte, ECS, asus, APU, amd
PC Perspective Podcast #252 - 05/23/2013
Join us this week as we discuss Z87 Motherboards, Xbox One, Lenovo Y500 Gaming notebook and more!
The URL for the podcast is: http://pcper.com/podcast - Share with your friends!
- iTunes - Subscribe to the podcast directly through the Store
- RSS - Subscribe through your regular RSS reader
- MP3 - Direct download link to the MP3 file
Hosts: Ryan Shrout, Josh Walrath, Allyn Malventano, and Morry Teitelman
Program length: 1:17:01
Week in Review:
News items of interest:
1:04:30 Hardware/Software Picks of the Week:
1-888-38-PCPER or firstname.lastname@example.org
Subject: General Tech | April 30, 2013 - 01:23 PM | Jeremy Hellstrom
Tagged: Steamroller, piledriver, Kaveri, Kabini, hUMA, hsa, GCN, bulldozer, APU, amd
AMD may have united GPU and CPU into the APU but one hurdle had remained until now, the the non-uniformity of memory access between the two processors. Today we learned about one of the first successful HAS projects called Heterogeneous Uniform Memory Access, aka hUMA, which will appear in the upcoming Kaveri chip family. The use of this new technology will allow the on-die CPU and GPU to access the same memory pool, both physical and virtual and any data passed between the two processors will remain coherent. As The Tech Report mentions in their overview hUMA will not provide as much of a benefit to discrete GPUs, while they will be able to share address space the widely differing clock speeds between GDDR5 and DDR3 prevent unification to the level of an APU.
Make sure to read Josh's take as well so you can keep up with him on the Podcast.
"At the Fusion Developer Summit last June, AMD CTO Mark Papermaster teased Kaveri, AMD's next-generation APU due later this year. Among other things, Papermaster revealed that Kaveri will be based on the Steamroller architecture and that it will be the first AMD APU with fully shared memory.
Last week, AMD shed some more light on Kaveri's uniform memory architecture, which now has a snazzy marketing name: heterogeneous uniform memory access, or hUMA for short."
Here is some more Tech News from around the web:
- AMD’s new heterogeneous Uniform Memory Access
- hUMA; AMD’s Heterogeneous Unified Memory Architecture @ Hardware Canucks
- Compro TN50W Cloud Network Camera @ Tweaktown
- Wifi Pineapple project uses updated hardware for man-in-the-middle attacks @ Hack a Day
- New OpenWRT Drops Support For Linux 2.4, Low-Mem Devices @ Slashdot
- HP mashes up ProLiant, Integrity, BladeSystem, and Moonshot server @ The Register
- Acer selling tablet using Intel Y series processor @ The Register
- CERN Celebrates 20 Years of an Open Web (and Rebuilds 1st Web Page) @ Slashdot
- BitFenix 5K YouTube Subscriber Giveaway @ eTeknix
heterogeneous Uniform Memory Access
Several years back we first heard AMD’s plans on creating a uniform memory architecture which will allow the CPU to share address spaces with the GPU. The promise here is to create a very efficient architecture that will provide excellent performance in a mixed environment of serial and parallel programming loads. When GPU computing came on the scene it was full of great promise. The idea of a heavily parallel processing unit that will accelerate both integer and floating point workloads could be a potential gold mine in wide variety of applications. Alas, the promise of the technology did not meet expectations when we have viewed the results so far. There are many problems with combining serial and parallel workloads between CPUs and GPUs, and a lot of this has to do with very basic programming and the communication of data between two separate memory pools.
CPUs and GPUs do not share common memory pools. Instead of using pointers in programming to tell each individual unit where data is stored in memory, the current implementation of GPU computing requires the CPU to write the contents of that address to the standalone memory pool of the GPU. This is time consuming and wastes cycles. It also increases programming complexity to be able to adjust to such situations. Typically only very advanced programmers with a lot of expertise in this subject could program effective operations to take these limitations into consideration. The lack of unified memory between CPU and GPU has hindered the adoption of the technology for a lot of applications which could potentially use the massively parallel processing capabilities of a GPU.
The idea for GPU compute has been around for a long time (comparatively). I still remember getting very excited about the idea of using a high end video card along with a card like the old GeForce 6600 GT to be a coprocessor which would handle heavy math operations and PhysX. That particular plan never quite came to fruition, but the idea was planted years before the actual introduction of modern DX9/10/11 hardware. It seems as if this step with hUMA could actually provide a great amount of impetus to implement a wide range of applications which can actively utilize the GPU portion of an APU.
Get notified when we go live!