In the first part of our series on ARM, we mentioned that with every major microprocess design ARM tries to choose 3 licensees to get early access to technology. It's very clear that Samsung was among the early three to get ahold of Cortex A15 IP. Samsung was first on the mobile market with a Cortex A15 based SoC: the Exynos 5250 (aka Exynos 5 Dual). Featuring two cores running at up to 1.7GHz paired with an ARM Mali-T604 GPU, we first met the Exynos 5250 in Samsung's own Chromebook XE303 last October.

The next logical step would be a quad-core version, which we sort of got with the Exynos 5410 - or as it's more commonly known: Exynos 5 Octa. This part features four ARM Cortex A15 cores running at up to 1.6GHz and four ARM Cortex A7 cores running at up to 1.2GHz in a configuration ARM calls big.LITTLE. The specific implementation of big.LITTLE on Exynos 5410 is known as Cluster Migration; either the four Cortex A15 cores or four Cortex A7 cores can be active, but not both and not an arbitrary combination of cores from each island. They're either all on or all off. This is by far the easiest to implement from a software perspective, but is obviously the less interesting option from a heterogeneous SMP perspective. I'll  be talking more about this in an upcoming ARM piece.

On the graphics front, Samsung moved to Imagination Technologies for the Exynos 5410 - implementing a PowerVR SGX 544MP3 setup. The Exynos 5410 saw limited use, appearing in some international versions of the Galaxy S 4 and nothing else. Part of the problem with the design was a broken implementation of the CCI-400 coherent bus interface that connect the two CPU islands to the rest of the SoC. In the case of the 5410, the bus was functional but coherency was broken and manually disabled on the Galaxy S 4. The implications are serious from a power consumption (and performance) standpoint. With all caches being flushed out to main memory upon a switch between CPU islands. Neither ARM nor Samsung LSI will talk about the bug publicly, and Samsung didn't fess up to the problem at first either - leaving end users to discover it on their own. 

Last week Samsung teased a new, improved Exynos 5 Octa - the Exynos 5420. Today we got the first details of the new SoC. The base CPU architecture remains unchanged. Samsung outfitted the Exynos 5420 with four A15s and four A7s, presumably in the same Cluster Migration big.LITTLE configuration. Clock speeds on both clusters are a bit higher now, 1.8GHz is the top speed for the Cortex A15 cores while 1.3GHz is where the A7s top out. Note that on the Cortex A15 side this exceeds where even ARM recommends clocking Cortex A15 for smartphones as far as power efficiency is concerned, but it should be fine for tablets. There's no word on whether or not the CCI-400 bug has been fixed, but I can only assume that it has been otherwise it'd be senseless to do another Exynos 5 Octa release this close to the original. Update: It looks like the CCI bug has been fixed.

Exynos 5 Comparison
SoC 5250 5410 5420
Max Number of Active Cores 2 4 4 (?)
CPU Configuration 2 x Cortex A15 4 x Cortex A15 + 4 x Cortex A7 4 x Cortex A15 + 4 x Cortex A7
A15 Max Clock 1.7 GHz 1.6GHz 1.8GHz
A7 Max Clock - 1.2GHz 1.3GHz
GPU ARM Mali-T604 MP4 Imagination PowerVR SGX544MP3 ARM Mali-T628 MP6
Memory Interface 2 x 32-bit LPDDR3-1600 2 x 32-bit LPDDR3-1600 2 x 32-bit LPDDR3-1866
Process 32nm HK+MG 28nm HK+MG 28nm HK+MG(?)
 

For the GPU Samsung switches back to ARM, this time using the Mali-T628 GPU in a 6-core configuration. Mali-T628 is actually a second generation implementation of ARM's Midgard GPU architecture first demonstrated with the T604. The second generation brings higher IPC and higher clocks in the same physical area as the first-gen cores, the combination of the two results in up to a 50% increase in performance. The T604 was a four-core implementation, so we should see another 50% on top of that with the move to 6-cores in the 5420. A six-core configuration is a bit odd in that we've never seen one before, but the T628 is scalable from 4 - 8 cores so it's a valid config.

On the memory interface front the Exynos 5420 retains a dual-channel LPDDR3 interface (2 x 32-bit) with support for up to 1866MHz memory, resulting in peak theoretical memory bandwidth of 14.9GBps. 

The biggest question about the new Exynos 5420 is whether or not the cache coherency issues have been worked out. The solution remains a bit on the large side for most price sensitive tablets, but it could make for an interesting use case in a higher-end tablet. In smartphones I'm still not sold on the idea of having four Cortex A15s running at up to 1.8GHz. Although big.LITTLE is one answer to the problem of getting the best of both worlds (low power and high performance), Qualcomm seems to have a pretty good solution with its Krait 300/400 cores. If Samsung were to enable one of the more interesting big.LITTLE scheduling models in its products however (e.g. big.LITTLE MP, all cores visible at once, intelligent scheduling based on perf needs) I'd be more interested.

Source: Samsung

POST A COMMENT

43 Comments

View All Comments

  • Krysto - Tuesday, July 23, 2013 - link

    "Samsung's new Exynos 5 Octa (product code : Exynos 5420), based on ARM Mali™-T628 MP6 cores, boosts 3D graphic processing capabilities that are over two times greater than the Exynos 5 Octa predecessor"

    The GPU seems to be 2x faster than the PowerVR one in Octa. Also could it be that the CCI bug came from the fact that Mali is more optimized to work with that than the old PowerVR chips are? So we might not see the same bug again.
    Reply
  • alex3run - Tuesday, July 23, 2013 - link

    The new Mali T628 has twice the count of ALUs inside and the clock speed is supposed to be a bit higher. Don't forget that SGX 544 is an old GPU, which is not blazing fast. Reply
  • darkich - Tuesday, July 23, 2013 - link

    Can't wait for this to show up in Note 3, with the performance and battery life to scream in Anand's face.

    How he fails to see the amazing big.LITTLE potential is beyond me.
    He's not even interested in this top of the shelf ARM SoC!

    While Bay Trail with its FAR inferior(likely) GPU and tripple the price gets him all excited.
    Get a grip, mister.
    Reply
  • flyingpants1 - Tuesday, July 23, 2013 - link

    Anand likes Intel a lot. Reply
  • ancientarcher - Tuesday, July 23, 2013 - link

    I wonder why...
    Anand, do you have a commercial relationship with Intel?
    Reply
  • krumme - Tuesday, July 23, 2013 - link

    Obviously the prior A15 version was not working. Performance a few percent over s600, and bad battery life as shown by gsmarena benchmarks. I doubt the memory bug is the only reason for it? The process needs maturement or perhaps 20nm, and the software side needs to mature too?

    But besides that, this concept have great potential in reducing fab cost and helping battery life, moving complexity from production to design. Never in history have that been more important. And in perspective ARM and Samsung is working to fix the bug, while Intel is in the process of positioning Bay Trail against A12 while fixing benchmarks the usual Intel way; Look we came here first, and look we are way faster. Its a total disaster and and its a pain to watch. My eyes bleed watching this old style spin machine. Deliver the results or shut up.

    This time, Intel is not the gorilla, but a tiny unimportant player, still working to get its old monopoly, with a proven record of failures on the mobile side. Intel better used their ressources on building the business side, and on the cloud and server side instead of this old battling AMD habbits.
    Reply
  • Ortanon - Tuesday, July 23, 2013 - link

    Let's not get crazy; Exynos 5 Octa has a higher IPC than Snapdragon 600, but the Snapdragon has higher battery life. Since Snapdragon isn't weak in CPU, having better battery life makes it a better phone part. After throwing so many CPU cores at the Battery Problem and still coming up short, it really isn't all that difficult to imagine someone being disappointed in the 5 Octa. Reply
  • lmcd - Wednesday, July 31, 2013 - link

    The new Octa should fix that. That's the point. It'll be able to switch CPU clusters quickly and aggressively and save more power. Reply
  • Krysto - Tuesday, July 23, 2013 - link

    I see people making this mistake a lot, but - Bay Trail is NOT A SMARTPHONE CHIP. It's a tablet chip. Merrifield is the one that will be in smartphones, and it won't be until Q2 2014 most likely.

    And I agree the GPU will be much weaker than ARM competition, too, even though it will use SNB GPU architecture (but not as many cores, or as high clock speed).
    Reply
  • Krysto - Tuesday, July 23, 2013 - link

    Mali cores usually came in 2x numbers compared to PowerVR anyway. The cores are no equivalent, so that's not where the "2x" performance comes from. It most likely comes from the increase in Mali T628's architecture performance, and also because of the higher clock speed.

    Oh, and I think the GPU was at least as fast as the one in iPhone 5 and as Adreno 320, so I disagree that it wasn't fast.
    Reply

Log in

Don't have an account? Sign up now