Friday, June 5, 2015

Smartphone platforms migrate to 64-bit (AArch64) mode

Recently, most existing and new mobile SoCs have started to become available configured in native 64-bit mode (AArch64) in conjuction with a 64-bit version of Android 5. Although SoCs targeting premium-level devices that are already shipping were the first to support AArch64 (including Tegra K1-64, Exynos 7420 and Snapdragon 810), recent entries in the Geekbench results database show that cost-sensitive platforms are also migrating to native 64-bit mode in upcoming smartphones.

This move involves Cortex-A53-based platforms such as MediaTek's MT6735, MT6752, MT6753 and MT6795, Qualcomm's Snapdragon 615 (MSM8939) as well as a new Snapdragon 410 (MSM8916) platform (which was previously limited to ARMv7), and HiSilicon's Kirin 620 and Kirin 930.

Initial ARMv8 platforms used hybrid AArch32 mode

Several ARMv8 based SoCs have been shipping for some time, but most have been using AArch32 mode, a hybrid mode which takes advantage of some of the architectural improvements in ARMv8 but does not expose native 64-bit mode to applications. Snapdragon 410 did not even take any advantage of ARMv8, running in 100% ARMv7 mode.

One reason why full AArch64 mode has not been adopted right away is that is does come with a performance penalty due to the increased storage requirements for program code and pointers, which puts greater demands on the memory subsystem of the SoC. Cost-sensitive smartphone models are especially sensitive to this due to a lower amount of RAM and smaller on-chip CPU caches. A decrease in the price of RAM chips has allowed the amount of RAM in cost-sensitive models to increase (e.g. more devices shipping with 2GB RAM), making AArch64 mode more appealing.

AArch64 also has benefits, in particular for floating point and data-intensive applications that use NEON vector instructions.

Comparison of CPU benchmark results

The migration to AArch64 mode across the board makes it easier to compare CPU benchmarks of different SoCs, which was previously made more difficult by the fact that some SoCs used AArch64 mode while others were still limited to AArch32.

In the following sections, I will return to Geekbench CPU test results and try to make apples-to-apples comparison for different groups of SoCs.

Quad-core Cortex-A53 SoCs

Quad-core SoCs included are MT6732, MT6735 and Snapdragon 410. Note that the version of Snapdragon 410 tested most likely reflects a newer silicon revision that has not yet widely appeared in end devices, since previous versions of Snapdragon 410 (MSM8916) were always limited to ARMv7 mode (seemingly being unable to run in AArch32 mode).

The following table shows selected integer tests results from Geekbench entries for the mentioned SoCs, running in AArch64 mode.

SoC        Geekbench  Clock  JPEG Compress (int)      Lua (int)
           ref        speed  Single IPC   Multi Par   Single IPC   Multi Par

MT6732     2705430    1.50    783   1.36  3108  3.97   795   1.29  3017  3.79
MT6735     2650175    1.30    646   1.36  2604  4.03   656   1.23  2047  3.12
MSM8916-64 2708213    1.21    626   1.34  2481  3.96   615   1.24  1280  2.08

The table below shows selected floating point and memory results.

SoC        Geekbench  Clock  Mandelbrot (float)       Stream Copy (memory)
           ref        speed  Single IPC   Multi Par   Single Multi

MT6732     2705430    1.50    631   1.23  2490  3.95  1030   1156
MT6735     2650175    1.30    526   1.19  2091  3.98   901    965
MSM8916-64 2708213    1.21    508   1.23  1969  3.88   447    505

The "IPC" value as shown in the tables is an index calculated from a comparison with the performance of common Cortex-A7-based SoCs, normalized to the same clock speed. The parallelism value ("Par") is the performance scaling from single-core to multi-core for the specific Geekbench subtest.

The IPC values are fairly consistent, as would be expected from the same CPU core (Cortex-A53) running the same ISA (instruction set architecture). When scaling to multiple cores, MT6732 does best, as shown by the scaling in the Lua benchmarks. This is not surprising as MT6732 is not an entry-level SoC given its cost structure, being better described as belonging to the mid-range segment. It is likely to have a better memory subsystem (in particular, a larger and faster L2 cache) than the other chips.

MediaTek's new entry-level chip, MT6735, apart from running at a somewhat higher clock speed (1.3 GHz vs 1.2 GHz), outperforms the 64-bit version of Snapdragon 410 when normalized to the same clock speed, which is especially evident in the Lua multi-core test and memory tests. The Lua results could be a reflection of L2 cache size and/or speed. Memory performance (based on the Stream Copy subtest) of both MediaTek chips is roughly double that of Snapdragon 410 (something which was already evident in the respective 32-bit platform results).

Mid-range octa-core Cortex-A53-based SoCs

The octa-core Cortex-A53-based SoCs targeting the mid-range segment include MediaTek's performance-oriented MT6752, the recent cost-reduced MT6753, Qualcomm's Snapdragon 615 (MSM8939), and HiSilicon's Kirin 620 (Hi6210).

These SoCs use different CPU clock speed configurations. MediaTek's MT6752 and MT6753 run all cores at the same maximum clock speed, 1.66 GHz for MT6752 and (at least in the tested device) seemingly only about 1.1 GHz for MT6753, even though Geekbench reports a maximum clock speed of 1.3 GHz. HiSilicon's Kirin 620 can run all cores up to a maximum speed of 1.2 GHz.

Qualcomm's Snapdragon 615 uses a pseudo-big.LITTLE, hierarchical architecture with one performance cluster of four cores running up to 1.65 GHz in the most recent version of the platform (previous versions ran up to 1.5 GHz), with the other power-efficient cluster running at a significantly lower clock speed. MediaTek's annnouncement of the MT6755 (Helio P10) shows that MediaTek is also transitioning to a hierarchical CPU clusters for new chips, similar to Snapdragon 615.

Having one power-optimized CPU cluster helps power efficiency for low CPU demand scenarios such as smartphone standby or light usage. The fact that Snapdragon 615 is not very power efficient, despite the low-clocked cluster, in mostly due to the low-performance 28LP manufacturing process used.

The following table shows selected integer tests results from Geekbench entries for the mentioned SoCs, running in AArch64 mode.

SoC        Geekbench  Clock  JPEG Compress (int)      Lua (int)
           ref        speed  Single IPC   Multi Par   Single IPC   Multi Par

MSM8939    2704276    1.65    837   1.32  4269  5.10   789   1.16   667  0.85
MT6752     2709869    1.69    890   1.37  6719  7.55   907   1.31  6531  7.20
MT6753     2699665    1.10?   572   1.35  4298  7.51   587   1.30  4282  7.29
Hi6210     2704356    1.20    630   1.36  3473  5.51   626   1.27  2156  3.44

The table below shows selected floating point and memory results.

SoC        Geekbench  Clock  Mandelbrot (float)       Stream Copy (memory)
           ref        speed  Single IPC   Multi Par   Single Multi

MSM8939    2704276    1.65    661   1.17  4019  6.08    512   569
MT6752     2709869    1.69    714   1.24  5637  7.89   1024  1158
MT6753     2699665    1.10?   463   1.23  3597  7.77    802   958
Hi6210     2704356    1.20    506   1.24  3419  6.76    833  1030

IPC values are fairly consistent for MT6752, Hi6210 and MT6753 (when a likely clock speed of 1.1 GHz is assumed), but Snapdragon 615 consistently shows somewhat lower IPC, possibly related to the earlier revision (r0p1) of the Cortex-A53 core used. It is also possible that, similar to what seems to be the case for the MT6753 entry used (Meizu M2 note), the actual maximum CPU clock speed is lower than the one advertised and reported to Geekbench.

Multi-core performance scaling approaches 8.0 for the MediaTek chips, which can be expected due to the symmetrical CPU cluster configuration. Multi-core scaling for Kirin 620 is lower than expected for the integer tests, especially Lua, possibly due to L2 cache performance constraints.

Snapdragon 615, due to half the cores being clocked at a lower clock speed, shows a lower scaling factor, however the Lua scaling is particularly low, the benchmark score in fact often being worse than the single-core result, while being only modestly higher in other cases. This could be due to L2 cache constraints for one of the clusters and associated synchronisation issues in the multi-threading implementation used by the Geekbench test.

Looking at memory performance, MT6752 has the highest performance, closely followed by MT6753 and Hi6210. Qualcomm's Snapdragon 615 is well behind, probably due to the older/slower interconnect bus used.

MT6753 benchmark results suggests performance issue

Even though a clock speed of 1.30 GHz is reported to Geekbench by the operating system in the MT6753-equipped Meizu M2 Note, actual Geekbench subtest results are not consistent with a Cortex-A53 core running at that clock speed. There is variability in the results between different runs, which could be caused by thermal throttling. Many of the results seem to correspond to an effective clock speed of approximately 1.10 GHz, although for some runs the score of certain tests (including JPEG Compress) does approach the level expected for a clock speed of 1.3 GHz. Most of the time however, performance is significantly lower than expected, as if the clock speed is throttled to around 1.1 GHz for long periods of time.

The lower than expected performance could be related to the manufacturing process. The MT6753 was designed with cost-reduction in mind, and may use TSMC's 28LP process which has low cost but lower performance. Qualcomm's Snapdragon 410 and 615 also use this process, limiting their performance (and in the case of Snapdragon 615 resulting in heat production). MT6753 was announced as supporting a clock speed up to 1.5 GHz, and the lower-than-expected attainable clock speed may force MediaTek to adjust the specifications for the chip if the issue is not resolved.

Sources: Geekbench browser

Updated 6 June 2015.

Thursday, June 4, 2015

MediaTek announces Helio P10 and MT6753 arrives in shipping devices

MediaTek has announced Helio P10 (MT6755), a performance mid-range smartphone SoC that is the successor of MT6752. Featuring an octa-core Cortex-A53 configuration, Helio P10 improves upon MT6752 by using TSMC's new 28HPC+ manufacturing process, which delivers power efficiency and performance improvements while remaining relatively cost-effective. It can reach a higher maximum CPU clock speed up to 2 GHz and upgrades the GPU to a Mali-T860 MP2. It is expected to be commercially available in end devices by the end of 2015.

Features shared with Helio-X10

The new SoC  incorporates a few features from Helio X10 (MT6795), MediaTek's current high-end offering, including dual ISPs with 21MP camera support and improved capture capability, as well as improved audio quality.

Otherwise, the SoC has significant similarities to MediaTek's MT6752 which it succeeds, most likely including a 32-bit external memory interface, which keeps SoC cost and phone PCB cost down. With MT6752, MediaTek already demonstrated the ability to achieve memory performance adequate for a 1080p device within the constraints of a 32-bit memory interface.

The 28HPC+ process is an upgrade of the existing 28HPC (high-performance compact) process (which is also relatively new, used by Allwinner's A83T and other SoCs), which improves performance and cost relative to the established 28HPM (high-performance mobile) process. Existing MediaTek chips like MT6752 and MT6795 most likely use 28HPM, which is established and has also been used for previous-generation SoCs such as MT6592 and Snapdragon 801/805.

MediaTek migrating to big.LITTLE CPU configurations in new SoCs

A significant departure from existing octa-core MediaTek SoCs such as MT6752 and Helio X10 (MT6795) is the pseudo-big.LITTLE CPU configuration, whereby one cluster of four Cortex-A53 cores is clocked at a higher frequency (up to 2 GHz in this case), while the second of cluster Cortex-A53 cores is optimized for lower frequencies, being clocked at a lower maximum frequency (1.1 GHz according to AnandTech).

Together with the previously announced high-end Helio X20 (MT6797) and tablet/Chromebook-oriented chips such as MT8173, Helio P10 marks a migration to (pseudo-)big.LITTLE, hierarchical CPU designs at MediaTek. While symmetrical octa-core designs such as MT6752 and MT6795 reach very high multi-core processing power by allowing all cores to run at the maximum frequency, there are signs that this configuration impacts power efficiency for tasks that require less CPU power, which can be run on power-optimized low-frequency cores.

In practice, this may be reflected in somewhat mediocre standby battery life for smartphones using MT6752 or MT6795, even though power efficiency for demanding tasks that utilize all cores is likely to be pretty good.

Budget mid-range MT6753 reaches end-market

Meanwhile, MediaTek's previously announced MT6753, which is a cost-effective budget mid-range SoC, has arrived in commercially shipping device in the form of Meizu M2 Note. Despite the name chosen by Meizu, the new model actually has lower performance than the existing Meizu M1 Note, because the MT6753  is a less costly, lower end chip when compared to to the MT6752 inside the M1 Note, with considerably slower maximum CPU speeds for the eight CPU cores, as well as a lower performance GPU. There are also signs that the memory interface and the actual memory frequency used by the M2 Note is slower. The lower cost of the MT6753 platform is reflected in the low selling price of the Meizu M2 Note.

MT6753 implements several cost-reducing features, including a lower maximum clock speed (reported to be 1.3 GHz for the M2 Note), most likely associated with a cheaper manufacturing process (either 28LP or 28HPC) than the 28HPM process of the MT6752. A significant factor for lower performance is likely to be a reduced size of the L2 CPU cache inside the MT6753. MT6753 is likely to become a significant volume driver in MediaTek's 4G product line.

However, early Geekbench entries for the Meizu M2 Note suggest that the CPU cores of the MT6753 SoC used in this model are mostly unable to reach the planned clock frequency. The Geekbench results are mostly consistent with an average maximum CPU clock speed of about 1.1 GHz, significantly lower than the 1.3 GHz reported by the OS and the 1.5 GHz mentioned when the MT6753 was originally announced a few months ago. My following blog article about the use of AArch64 provides more details on this subject.

MT6753 has lower-performance GPU than MT6752

MT6753 also has a significantly lower-performance and smaller GPU (Mali-T720 MP3), compared to the Mali-T760 MP2 inside MT6752. MT6753 marks the first Mali implementation with three pixel processing cores; previous Mali GPUs either had one, two, four, six or eight pixel processing cores, Most likely, Mali-T720 does not have the memory bandwidth usage optimization that are present in Mali-T760, which together with the more limited pixel processing throughput means that devices with a 1080p display such as the Meizu M2 Note may be impacted in terms of 1080p game performance and power efficiency for graphics-intensive operations.

World modem support in new MediaTek platforms

All new MediaTek SoCs (including Helio P10 (MT6755), MT6753, the low-end quad-core MT6735 and the announced high-end Helio X20 (MT6797)) have world-modem support, facilitating compatibility with more cellular networks used worldwide, including legacy CDMA networks in the US and other countries. This makes MediaTek SoCs more attractive to smartphone manufacturers targeting multiple or worldwide markets.

Sources: MediaTek (Helio P10 announcement), AnandTech (Helio P10 article)

Updated 6 June 2015.

Thursday, May 21, 2015

Battery performance based on Geekbench battery test results

A while ago, Primate Labs added a battery performance test to the Geekbench benchmark suite, which has been frequently used on this blog and elsewhere to analyze CPU processing peformance. The battery performance test gives the opportunity to better gauge the power efficiency of different CPU architectures, especially for the type of workload that the Geekbench battery test represents.

Battery test overview

The battery test is intended to be run starting from a fully loaded battery until the battery is completely run down. It appears to target a certain fixed level of CPU processing that is sustained throughout the test. In the test results, a duty cycle parameter is given for several time points, which more or less represents CPU utilization. Slower CPU cores (such as quad-core Cortex-A7-based SoCs) have a higher duty cycle percentage, while high-performance "big" cores such as Cortex-A57 and Krait-400 show a lower percentage.

In practice, most battery test results in the Geekbench database were terminated early in the benchmark process and do not give useful information. The test runs that completed a full run-down from 100% to close to 0% battery do give a usable indication of battery efficiency. The benchmark expresses battery performance as a number, similar to Geekbench CPU performance scores. This score is correlated with the duration and duty cycle using a certain formula, reflecting the amount of CPU work done and the battery running time. The score is heavily influenced by the actual capacity of the battery used in the device.

Overview of results for common SoCs

The following table shows Geekbench approximate battery test scores for common SoCs used in smartphone models for which a battery capacity specification is available. The table is ordered by SoC model name.

Device                    SoC              Score      Capacity  Duration    Score /
                                           (Range)    (mAh)     (hrs:min)   mAh

Apple iPhone 5S           Apple A7         1220-2090  1560      2:00-3:30   0.78-1.34
Apple iPhone 6            Apple A8         1550-2360  1810      2:35-4:00   0.86-1.30
Apple iPhone 6 Plus       Apple A8         2580-3250  2915      4:20-5:25   0.89-1.11
Meizu MX Pro              Exynos 5430      2080-2730  3350      7:45-10:10  0.62-0.81
Samsung Galaxy Alpha      Exynos 5430      1850-2710  1860      4:30-5:00   0.99-1.46
Samsung Galaxy Note 4     Exynos 5433      3190-3650  3220      5:20-6:00   0.99-1.13
Samsung Galaxy S6 Edge    Exynos 7420      4100-4600  2600      7:00-7:45   1.58-1.77
Huawei Honor 6            Kirin 920        1580-2080  3100      2:40-3:30   0.51-0.67
Huawei Mate 7 (MT7-L09)   Kirin 925        2470-2820  4100      4:05-4:20   0.60-0.69
Huawei P8 (GRA-L09)       Kirin 930        3270-4150  2680      5:30-7:00   1.22-1.55
Lenovo A5000              MT6582           3740       4000      14:00       0.94
Xiaomi Redmi Note         MT6592           2850-3560  3200      7:30-9:00   0.89-1.11
Huawei G750-U10           MT6592           2960-3430  3000      7:45-9:00   0.99-1.14
Meizu MX4                 MT6595           2540-2780  3100      6:20-6:55   0.82-0.90
Lenovo A7000-A            MT6752M          4550-4950  2900      8:16-8:50   1.57-1.71
Meizu M1 Note             MT6752           4900-6310  3140      8:10-10:30  1.56-2.01
HTC Desire 820s           MT6752           3580-3730  2600      6:15-6:30   1.38-1.43
HTC One E9+               MT6795           3370       2800      6:00        1.20
Moto G                    MSM8226 (SD400)  1600-2000  2070      6:00-7:30   0.77-0.97
Xiaomi Redmi 1S           MSM8226 (SD400T) 1485       2000      5:30        0.74
Lenovo A6000              MSM8916 (SD410)  2700       2300      6:50        1.17
HTC Desire 826            MSM8939 (SD615)  1800       2600      4:25        0.69
Xiaomi Mi 4i              MSM8939          2520-2810  3120      5:50-7:30   0.81-0.90
HTC One M8                MSM8974 (SD801)  2500-3300  2600      4:20-5:50   0.96-1.27
Xiaomi Mi 4               MSM8974          3150       3080      7:45        1.02
Samsung Galaxy Note 4     APQ8084 (SD805)  2500-3550  3220      4:10-6:15   0.78-1.10
LG G4                     MSM8992 (SD808)  2500-3260  3000      4:15-5:30   0.89-1.09
HTC One M9                MSM8994 (SD810)  1400-2580  2840      2:20-4:20   0.49-0.91

Devices with low processing power but long battery life may be penalized by having to power the screen and wireless connectivity for a longer period during the test.

The ratio of the battery score and the battery capacity (in mAh) gives a very rough indication of the efficiency of a particular CPU architecture, although the comparison may be skewed by several factors.

Results by SoC type

The previous generation of Cortex-A7-based SoCs such as Snapdragon 400 and MT6582 shows long running time due the effiency of the Cortex-A7 core, but the battery score appears to be affected by the limited CPU power. Snapdragon 410 does relatively well despite (or perhaps thanks to) being limited to ARMv7 mode.

SoCs with previous generation Cortex-A15 cores for performance in a big.LITTLE configuration, such as Kirin 920/925, show relatively low efficiency, as is to be expected given the relatively high power consumption Cortex-A15 is known for. Exynos 5430, which is manufactured on a relatively advanced 20 nm process, generally does better.

Octa-core mid-range: MediaTek does well

Among octa-core mid-range SoCs such as the Cortex-A53-based MT6752 and Qualcomm's Snapdragon 615 and MediaTek's previous-generation Cortex-A7-based MT6592, both the MT6752 and MT6592 make a strong showing, with MT6752 getting particularly high scores.

MT6752 has an optimized memory architecture with a 32-bit memory interface and is manufactured on TSMC's 28HPM process, which helps performance relative to Snapdragon 615. Although not tested by Geekbench, reports indicate that wireless standby power efficiency is not as great as the CPU efficiency for this SoC. It is possible that due to the CPU cores being optimized for relatively heavy CPU loads (not big.LITTLE so no cores optimized for low power consumption at low frequencies), which includes the Geekbench battery test, a low load scenario (such as reflected in standby time) produces less optimal power consumption.

Qualcomm's Snapdragon 615 (MSM8939) does relatively poorly, which can largely be explained by the assymmetric CPU configuration and lower-performance 28LP manufacturing process.

Performance segment SoCs

The poor performance of Snapdragon 810 (as illustrated by the HTC One M9) is apparent, with significant worse battery efficiency than the previous generation Snapdragon 801 and 805. Snapdragon 808, which uses a later revision Cortex-A57 core and is used inside the LG G4, does somewhat better.

Largely due to the relatively advanced manufacturing process (14 nm FinFET for Exynos 7420), Samsung's latest SoCs do well, particularly Exynos 7420 used inside the Galaxy S6. Even Samsung's previous generation Exynos 5433 appears to be well ahead of Snapdragon 810 in terms of efficiency.

A limited number of results is available for two Cortex-A53-based performance SoCs (characterized by a wide memory interface and more powerful GPU than mid-range solutions), MediaTek's MT6795 (Helio-X10) and HiSilicon's Kirin 930. Kirin 930 shows relatively good efficiency in this benchmark, possibly ahead of MediaTek's MT6795. Kirin 930 has a two-level hierarchy in which one cluster of Cortex-A53 cores is optimized for a higher and the other for a lower frequency, while in MT6795 all cores can reach the maximum frequency.

Source: Geekbench Browser (Battery search)

Updated 28 May 2015.

Thursday, May 7, 2015

Smartphone and tablet processor market share in 2014

Strategy Analytics has published its yearly report detailing global smartphone application processor market share in 2014. The total market had sales of about $21 billion with robust growth of 21%. The report shows that Qualcomm continued to lead the market in terms of revenue share with 52%, followed by Apple with 18% and MediaTek with 14%. The Apple number most likely reflects an estimate because Apple does not sell its chips to third parties. In fourth and fifth place were Speadtrum and Samsung LSI. The report mentions that HiSilicon, Intel and MediaTek had bigger growth than Qualcomm in 2014.

Qualcomm's strength based on Snapdragon 800 series wins in higher-tier phones

According to the report, Qualcomm's leadership was largely based on design wins for its Snapdragon 801 and Snapdragon 805 SoCs in the higher-tier market. Examples of this include the Samsung Galaxy S5 and LG G3. However, as I have previously reported Samsung has increased its use of in-house application processors starting from the second half of 2014, culminating in the exclusive use of Exynos 7420 in the Galaxy S6 in 2015, putting pressure on Qualcomm.

Baseband share in 2014

Strategy Analytics has also published a report with details about baseband (modem) market share in smartphones. According to the report, LTE (4G) basebands accounted for 50% of cellular baseband share in 2014, and the figure is likely to increase significantly in 2015. Qualcomm led in LTE basebands, but HiSilicon, Intel, Marvell, MediaTek and Samsung also increased LTE baseband shipments.

In terms of revenues in the overall baseband market, Qualcomm, MediaTek, Speadtrum, Marvell and Intel had the top positions in 2104. Qualcomm had 66% revenue share, followed by MediaTek with 17% and Speadtrum with 5% sare. Given the product lines of the respective companies in 2014, Qualcomm's revenues are based on both integrated SoC and separate modems, while Intel's sales were mostly separate modem chips, while the other players mostly shipped a mix of integrated SoCs and modem chips.

Comparison with 2013

Comparing with the reports that Strategy Analytics issued for 2013, Qualcomm saws it baseband revenue share remain relatively stable at 66% compared to 64% in 2013. MediaTek saw its AP market share increase from 10% in 2013 to 14% in 2014, and its baseband share increased.

Tablet processor market in 2014

According to another report issued by Strategy Analytics, the market for tablet processors grew 18% in 2014 to $4.2 billion. The top-five revenue share positions were occupied by Apple, Intel, Qualcomm, MediaTek and Samsung LSI. Apple led with 27% share (which must be an estimate), followed by Intel with 17% and Qualcomm with 16% share.

Notable is the absence among the top five of traditional leaders in the Chinese white-box market such as Rockchip and Allwinner. This most likely reflects in increase in brand name tablet shipments at the expense of the white-box tablet market, the low selling prices of white-box tablet processor and the encroachment of MediaTek and Intel into that segment.

Source: Strategy Analytics (Smartphone AP market share), Strategy Analytics (cellular baseband market share), Strategy Analytics (Tablet processor market share)

Thursday, April 30, 2015

More details emerge about Cortex-A72 CPU core

Recently, more details have become available about the performance improvements implemented in ARM's Cortex-A72 core, which is a replacement for the high-performance Cortex-A57 core. Apart from the gains from using a more advanced process such as 14/16 nm FinFET, Cortex-A72 also implements fairly significant micro-architectural improvements affecting performance per cycle and power efficiency. AnandTech has published a detailed overview of these improvements.

Cortex-A57 based on Cortex-A15 and not fully optimized for power-efficiency

The Cortex-A57 CPU core, which was announced in 2012, has significant similarities to Cortex-A15, ARM's long-standing high-performance 32-bit CPU core, which has been known for relatively high power consumption. As such, it is not unexpected that improvements on the Cortex-A57 architecture (in the form of the Cortex-A72) have proven to be possible. Cortex-A57-based SoCs  such as Snapdragon 810 have been known to throttle, being forced to reduce the clock speed due to excessive heat production and power use, resulting in reduced sustained performance. Apple's A7 and A8 processors use CPU cores that most likely have strong similarities with Cortex-A57, but which exhibit little throttling due to a lower maxium clock speed, a lower number of cores and other factors related to the the chip design.

Increased level of sustained performance

ARM has made available a number of slides detailing the improvements in sustained performance and power efficiency in Cortex-A72 over Cortex-A57. On a 28 nm process and similar clock speed, ARM's charts indicate a roughly 20% improvement in power reduction. 

Sustained performance is expected to be higher than Cortex-A57, implementations of which (such as Snapdragon 810 and Exynos 5433, and to a lesser degree Exynos 7420) have suffered from an inability to maintain high clock speeds and throttle back to a relatively low speed due to heat production and associated power consumption. ARM gives a figure of sustained 750 mW operation per core on a 16FF+ process with a clock speed around 2.5 GHz.

In terms of IPC (instructions per cycle), ARM's information shows improvements in all instruction-level performance segments, with a 1.16x improvement for "analytics", 1.38x for cryptography, 1.50x for memory, 1.26x for floating point and 1.16 for integer compute. The increase in memory performance appears to be significant.

Improved single-core performance evident in early Geekbench results

Early Geekbench results for the MT8173 SoC from MediaTek, which includes two Cortex-A72 cores, give an indication of practical peformance of the Cortex-A72 core, although the exact clock speed the Cortex-A72 cores are running at is hard to determine. The following table shows single-core performance from a recent MT8173 Geekbench entry, comparing it to Exynos 7420 as used in the Samsung Galaxy S6. Both use 64-bit AArch64 mode.

SoC                        JPEG   Dijkstra  Lua   Mandelb. Stream SGEMM SFFT
                           Compr.                          Copy
28nm? MT8173 (Cortex-A72)  1429    1287     1675  1750     2217    979  1345
14nm Exynos 7420           1475    1082     1409  1147     1993    954  1379
The MT8173 easily matches the single-core performance of Exynos 7420, while showing significant improvements in the Mandelbrot floating point subtest and the memory-intensive Dijkstra subtest, and also the Lua subtest. Memory subtest (Stream Copy) performance is also better than Exynos 7420, despite the likely much wider memory interface of the latter, providing clear evidence of the improved memory performance (largely due to smarter prefetching) in Cortex-A72. Overall, since the MT8173 results reflects a SoC using 28 mn or perhaps 20 nm process technology, while Exynos 7420 uses Samsung's leading-edge 14 nm FinFET process, the ability of the MT8173 to beat Exynos 7420 in single-core performance while using a less advanced process is impressive and illustrates the performance improvements in the Cortex-A72 core.

Reduced silicon area results in lower cost

Cortex-A72 has a silicon area that is 10% smaller than Cortex-A57 on an equivalent process, while delivering improvements in performance and power efficiency. Already SoCs have been announced or described that utilize Cortex-A72 cores, such as MediaTek's MT8173 for tablets, Qualcomm's Snapdragon 618 and 620 for smartphones, and MediaTek's MT6797 (Helio-X20) for smartphones.

There seems to be a clear trend of using just two Cortex-A72 cores (instead of the four cores used in many Cortex-A57 implementations), reducing cost and maximum power consumption. These are cores are augmented by low-power, small-area Cortex-A53 cores running at a lower frequency. MT8173, Snapdragon 618 and Helio-X20 all use such as configuration.

Use of Cortex-A72 may be more effective than high-clocked Cortex-A53 cores

There are indications that Cortex-A53 cores running at a high frequency (such as implemented in MediaTek's MT6752 and MT6795 (Helio-X10), HiSilicon's Kirin 930 and to a lesser degree in Snapdragon 615 and the announced Snapdragon 415 and 420) run into a power efficiency bottleneck at higher clock speed, due the relatively steep increase in power consumption as the clock speed of the Cortex-A53 core increases above 1.3-1.5 GHz. Solutions that combine a small number of Cortex-A72 with lower-clocked, power efficient Cortex-A53 cores may prove to be a sweet spot in terms of practical performance and power efficiency for mid-range SoCs.

Source: AnandTech (Cortex-A72 Architecture Details article), Geekbench Browser

Tuesday, April 28, 2015

Spreadtrum takes market share in Chinese smartphone market in Q1 2015

DigiTimes Research recently posted a report about smartphone AP (application processor) shipments in China in Q1 2015, indicating that Chinese fabless semiconductor company Spreadtrum gained market share in Q1, mainly based on strength for low-end 3G solutions. According to the report, Spreadtrum's market share reached 17.4% in Q1 2015, while MediaTek continues to lead the Chinese market with 46.8% share, followed by Qualcomm, which increased its share to 23.6%.

In terms of overall shipments, according to DigiTimes unit sales of smartphones by Chinese manufacturers declined significantly by about 30% in Q1 2015 compared to Q4 2014, with manufacturers focusing on export sales suffering the largest declines. Huawei, which is moving towards a strategy of using mainly in-house chip solutions from its HiSilicon division, was relatively unaffected and took market share in the quarter.

Spreadtrum's product line

Spreadtrum's increase in 3G smartphone solution shipments most likely reflects the 28 nm SoC it announced in June 2014, the SC883XG. This SoC features a quad-core Cortex-A7 CPU running up to 1.4 GHz, an ARM Mali-400 MP2 GPU, modem support for TD-SCDMA/HSPA(+) and GSM/GPRS/EDGE with dual-SIM capability, and integration of Spreadtrum's Wi-Fi/Bluetooth/GPS/FM chip technology.

The features of the SoC are extremely similar to MediaTek's successful MT6582 platform, which has been on the market for more than one and a half years. The combination of quad-core Cortex-A7 CPU, Mali-400 MP2 GPU and a high level of integration of other functionality on a 28 nm process appears to deliver good performance and very good power efficiency for cost-sensitive devices.

Spreadtrum also recently announced volume shipments of the SC7731G with 3G modem and the SC9830A with LTE modem. Rather than using Cortex-A53 CPU cores, the new chips continue to use efficient Cortex-A7 cores with Mali-400 MP2 GPU with support for Android 5.

MediaTek's 3G market share impacted by Spreadtrum

The DigiTimes report attributes MediaTek's loss of market share in China in Q1 2015 mainly to Spreadtrum's gains for 3G smartphone SoCs, where MediaTek has had a strong position. However, Qualcomm is likely to be a significant factor as well, with indications from new model announcement by companies such as TCL (Alcatel), ZTE, Lenovo/Motorola and others that MediaTek's late introduction of low-cost 4G solution has hurt the company. The resolution of the Chinese monopoly investigation into Qualcomm is also likely to be a factor.

Additionally, a trend has been noticed whereby second and third-tier Chinese smartphone manufacturers have lost share to the largest first-tier manufacturers in China. Since MediaTek's share among second and third-tier manufacturers has been the strongest, this has hurt MediaTek's shipments.

Projections for Q2 2015

For Q2 2015, DigiTimes expects overall AP shipments in China to increase 17.6% sequentially from the low base set in Q1 2015, although that still amounts to an increase of 18% over the same quarter last year (Q2 2014). DigiTimes expects MediaTek to recover some share to reach 48.4%, with Qualcomm seeing a small decline to 21.3% and Spreadtrum's share declining to 15.2%. DigiTimes attributes Spreadtrum's loss of momentum to pressure from MediaTek's 3G solutions, which probably reflects price reductions implemented by MediaTek after it saw shipments decrease and inventories build.

Sources: DigiTimes Research (smartphone AP shipments in China in Q1 2015), (DigiTimes Research (Chinese smartphone shipments in Q1 2015), Spreadtrum (2014 smartphone chip announcement), Spreadtrum (2015 smartphone chips announcement)

Thursday, April 23, 2015

Details surface about MediaTek's upcoming Helio-X20 SoC

Recently, details surfaced about MediaTek's upcoming Helio-X20 SoC, a high performance offering in the series of Helio-branded SoCs, of which the MT6795 (Helio-X10) is the first member. The deca-core Helio-X20, which has the model number MT6797, has a total of ten CPU cores and is the first mobile SoC with a hierarchy of three clusters of progressively less performance-oriented CPU cores: two ARM-Cortex-A72 cores, four high clocked ARM-Cortex-A53 cores and four lower clocked ARM-Cortex-A53 cores.

Three-cluster hierarchy extends the big.LITTLE principle

The SoC's ten CPU cores are organized as follows:
  • Two Cortex-A72 cores clocked up to 2.5 GHz to provide "extreme performance".
  • Four Cortex-A53 cores clocked up to 2.0 GHz for "best performance/power balance".
  • Four Cortex-A53 cores clocked up to 1.4 GHz for "best power efficiency".
The different clusters and their separate L2 caches are linked together using MediaTek's MCSI interconnect technology. MediaTek claims higher efficiency than big.LITTLE based designs, which have just two levels of cluster hierarchy.

The triple-level hierarchical design is a significant departure from the symmetric CPU configuration on current MediaTek smartphone SoCs such as MT6795 (Helio-X10) and MT6752, which have eight "equal" Cortex-A53 cores, although MediaTek does have experience with big.LITTLE, for example in the 32-bit MT6595 and some tablet processors.

Reports suggest the chip is manufactured using a 20 nm process at TSMC and will be in mass production as soon as July 2015. This marks MediaTek's first known product manufactured using a geometry below 28 nm.

Other features: ARM Mali-T880 MP4 GPU, dual-channel LPDDR3, world modem

Based on a recent report from that gives more details about the specifications of the chip, other features include an ARM Mali-T880 MP4 GPU at 700 MHz and a dual-channel 32-bit LPDDR3 memory interface at 933 MHz. The maximum display resolution supported is 2560x1600. The integrated LTE modem has Cat. 6 capability. and also supports CDMA2000/EVDO Rev. A (world modem support). The video processor supports decoding and encoding of the H.265 format up to 4K resolution.

The report suggests the SoC will start shipping to manufacturers this summer with end products reaching stores by late autumn.

Execution issues at Qualcomm may help MediaTek's chances of success in high-end

Execution issues at Qualcomm regarding their high-end product roadmap may increase the chances of success of MediaTek's high-end product line. Qualcomm's Snapdragon 810 has some performance issues and has not been a great success, giving MediaTek the opportunity to capture more of the performance-oriented, premium level segment. MediaTek already has Helio-X10 (MT6795) in the market, which has gained design wins, but for which some key characteristics such as power efficiency are still unknown.

Meanwhile, MediaTek has come under pressure in the cost-sensitive smartphone SoC market, previously the bread-and-butter of the company, on which Qualcomm is encroaching by gaining market share for low-end devices in China. This is mainly the result of MediaTek's delayed introduction of cost-sensitive 4G SoC solutions.

MediaTek's sales performance under pressure

While MediaTek has made some progress penetrating the performance-oriented smartphone market with SoCs such as MT6752 and MT6795, it has lost ground in the cost-senstive smartphone segment among Chinese manufacturers, which it previously dominated. Although MediaTek's March 2015 sales rebounded from the low level of February, for the second quarter its sales performance is not expected to reach the level of previous quarters (such Q3 and Q4 of 2014). Indeed, the forecast given by MediaTek during its quarterly results presentation for Q1 2015 on April 30 sets sequential growth between -5% and +3% for Q2 2015, which represents a lower level of sales than the level MediaTek was accustomed to in 2014.

Due to a product mix with a significantly lower volume of cost-senstive SoCs, offset by some traction for performance-oriented SoCs, MediaTek's product mix has changed, with overall unit shipments and unit market share for MediaTek declining when compared to the previous year, despite likely higher performance-oriented chip shipments.

Update: MediaTek has officially announced Helio-X20

On 12 May, MediaTek officially announced Helio-X20. Most of the previously known details are confirmed in the announcement. The chip utilizes MediaTek's new CorePilot 3.0 heterogeneous computing scheduling algorithm, with together with the tri-cluster architecture should provide up to 30% reduction in power consumption. The chip has advanced camera features and has an ARM Cortex-M4-based sensor hub processor for better battery efficiency.

According to AnandTech, quoting MediaTek, the GPU used is not the Mali-T880 but an as yet unannounced Mali-T8xx series GPU, similar to Mali-T880. Compared to Helio-X10's PowerVR G6200, MediaTek sees a 40% performance improvement with a 40% drop in power.

Sources: CNXSoftware (Helio-X20 article), DigiTimes (MediaTek Q2 sales projection), DigiTimes (MediaTek Q2 2015 quarterly results), (Comparison of MT6797 with Snapdragon 810), MediaTek (Helio-X20 announcement), AnandTech (Helio-X20 article)

Updated 21 May 2015.

Thursday, April 16, 2015

HiSilicon introduces Kirin 930/935, a performance-oriented Cortex-A53-based SoC

Huawei has introduced the Huawei P8 and P8max smartphones, featuring the Kirin 930 and Kirin 935 SoCs from Huawei's  HiSilicon semiconductor division. The octa-core Kirin 930 SoC is a performance-oriented SoC featuring only Cortex-A53 CPU cores. With a maximum clock frequency in excess of 2.0 GHz, it bears similarities to MediaTek's MT6795, but the use of a pseudo big.LITTLE configuration (four Cortex-A53 cores clocked up to 2.0 GHz and four Cortex-A53 cores clocked up to 1.5 GHz, for a total of eight cores) is reminiscent of Qualcomm's midrange Snapdragon 615 SoC, which runs at lower clock frequencies.

Huawei also introduced high-end models of both the P8 and P8max with larger storage capacity featuring the Kirin 935 SoC, which is a higher-clocked version of Kirin 930. The Huawei P8max is a smartphone with an unusually large 6.8" display.

SoC is targeted at performance-oriented devices

The Huawei P8 models are higher-priced performance-oriented smartphones, and the characteristics of the SoC match this segment. Apart from the high maximum clock speed of the Cortex-A53 cores, the external RAM interface is likely to be a dual-channel 32-bit configuration like previous performance-oriented SoCs from HiSilicon. Presentation materials from Huawei describe the Cortex-A53 cores in the faster cluster of four CPUs as being of a special, performance-enhanced type, which probably reflects the application of ARM's PoP core-hardening technology whereby the core is optimized for running at a specific frequency and a particular power profile, trading performance against die size. The process technology used is likely to be TSMC's proven 28HPM process.

The SoC is reminiscent of MediaTek's recently introduced MT6795 (Helio-X), which also targets the performance segment with an octa-core Cortex-A53 CPU configuration. MediaTek's SoC has been reported to have been adopted by competitors of Huawei such as HTC and Xiaomi.

Previous generation Mali-T628 MP4 GPU used

Rather than using an updated current-generation GPU like Mali-T760, the specs sheet for the P8max indicates the Kirin 930/935 SoCs continue to use the Mali-T628 MP4 GPU that was previously used in the Kirin 920 SoC. This GPU core is not known for great power efficiency, although there are suggestions that the more efficient Mali-T760 (which features memory bandwidth optimizations) has a relatively high silicon area and cost.

HiSilicon's new SoC line-up uses only Cortex-A53 CPU cores

Apart from Kirin 930, HiSilicon has also introduced the Kirin 620 SoC, which is an octa-core Cortex-A53 based SoC for the cost-sensitive segment, clocked up to 1.2 GHz and with a single-channel memory interface. This means Huawei now has in-house Cortex-A53-based SoCs suitable for most of its smartphone product range.

Thursday, April 9, 2015

Cortex-A53 based SoCs: MT6735 shows up, power efficiency of MT6752 in question

More and more devices with Cortex-A53-based SoCs, mainly targeting the entry-level and mid-range segments, are coming into the market. Qualcomm's original Snapdragon 410 (MSM8916) has already shipped in large volume, and devices using Qualcomm's Snapdragon 615 (MSM8939), as well as MediaTek's MT6732 and MT6752, have also ramped up. Meanwhile, Huawei is introducing devices using its in-house HiSilicon Kirin 620 SoC.

In the Geekbench database, results for new SoCs that are not yet shipping in end products are showing up, including MediaTek's delayed performance-oriented MT6795 (Helio-X) and the appearance of a result for the MT6735, MediaTek's new offering for the cost-sensitive segment.

In this post, I will be examining updated benchmark results for these SoCs, as well as taking a look at battery life benchmarks. Power efficiency of Cortex-A53-based products does not appear to be as good as hoped, with significant variability present (for MT6752-based devices, for example).

Snapdragon 410 smartphone platform appears to be slightly updated

Qualcomm's Snapdragon 410 (MSM8916) smartphone platform, which has performance flaws probably associated with the use of an early-revision Cortex-A53 core, seems to have been slightly updated in some recent models and reference designs, with a minor performance improvement due to a slightly higher clock speed (1.21 GHz vs 1.19 GHz) and what appears to be somewhat improved memory performance, while still being limited to 32-bit ARMv7 mode.

This improvement could be the result of a new revision of the SoC with a few hardware tweaks and an associated reference design, although it does not appear to be a radical redesign that would, for example, upgrade the Cortex-A53 core to allow use of the ARMv8 instruction set. Qualcomm's modem-less stand-alone version of Snapdragon 410, APQ8016, does appear to be a new design that does not have the restrictions of the smartphone SoC and can run in full 64-bit mode (it targets development boards and tablets).

MediaTek's MT6735 shows up in Geekbench

A single result for MediaTek's MT6735  SoC has appeared in the Geekbench database. The MT6735 is MediaTek's much-needed offering for the entry-level market with integrated LTE modem with world-mode support. It has been described as a cost-down version of the MT6732, which is a quad-core Cortex-A53-based SoC with a Mali-760 MP2 GPU. The MT6735 downgrades the GPU to a Mali-720 (probably Mali-720 MP4) which appear to be associated with lower manufacturing cost.

The MT6735 has an upgraded r0p3 revision of the Cortex-A53 core which, according to Linux kernel commits by ARM, fixes a few hardware errata which might improve performance and efficiency over previous revisions. The Geekbench entry shows the MT6735 running at a maximum clock speed of 1.3 GHz, which is lower than the 1.5 GHz of the MT6732. This could be due to the use of the cheaper 28LP process at TSMC, instead of the higher-performance 28HPM.

Notably, the device is running in full AArch64 mode, which has pros and cons for performance, but is unusual for a cost-sensitive platform because those platforms are usually sensitive to the higher demands on the memory subsystem from the increased addressing size and addressing space in AArch64 mode. Those platforms until recently only used AArch32, the 32-bit variant of the ARMv8 instruction set. The use of AArch64 makes comparisons a little difficult because it affects different benchmarks (including different Geekbench subtests) in different ways. The Android version (5.0) is also different from most existing entries for comparable SoCs, which use Android 4.4.4.

MT6752's power efficiency average, with high variability

According to most reviews that have appeared for MT6752-based devices such as the Meizu M1 Note and other devices, power-efficiency and battery life is generally average, with significant variability between devices. The Cortex-A53 core, although delivering higher performance, clearly seems to be associated with reduced power efficiency as compared with Cortex-A7 in SoC such as MediaTek's MT6582 and Qualcomm's Snapdragon 400, which generally have excellent battery life.

The variability in MT6752 performance could reflect variable performance yields in the manufacturing process, with some chips performing better (with lower voltage and power at a given frequency) than others. Frequently, chips are separated into speed bins and lower-performing ones may be sold as a cost-reduced variant running at a lower maximum clock speed. Indeed, a review of the Acer Liquid Jade S containing the MT6752M, which is likely from the poorest-performing speed bin of the MT6752, reports relatively poor battery life and some heat production. This suggests the variability may be quite large.

Update (21 May 2015): Recent information suggests that CPU power efficiency for this SoC is relatively high when CPU power is demanded, but standby efficiency (including wireless network standby) may be less impressive.

Overview of Geekbench results for Cortex-A53-based SoCs

The following tables show Geekbench results for a recent, representative entry for each Cortex-A53-based SoC. The first table below gives an overview of the devices, with SoC, CPU configuration, device model, Geekbench reference number, Android version and the instruction set architecture tested.

SoC                       CPU configuration                  Device               Geekbench Android Arch
                                                                                  reference version
Snapdragon 410 (MSM8916)  4 x 1.19 GHz Cortex-A53r0p0        Samsung SM-G360F     2275416  4.4.4   ARMv7
Snapdragon 410 (MSM8916)  4 x 1.21 GHz Cortex-A53r0p0        Xiaomi 2014817       2181099  4.4.4   ARMv7
Snapdragon 410 (MSM8916)  4 x 1.21 GHz Cortex-A53r0p0        Motorola Moto-E2     2275732  5.0.2   ARMv7
Snapdragon 615 (MSM8939)  4/4 x 1.50/1.0 GHz Cortex-A53r0p1  Samsung SM-A700FD    2274606  4.4.4   AArch32
MT6732                    4 x 1.50 GHz Cortex-A53r0p2        Elephone P6000 O2    2265175  4.4.4   AArch32
MT6735                    4 x 1.30 GHz Cortex-A53r0p3        "bq DENDE"           2268728  5.0     AArch64
MT6752                    8 x 1.69 GHz Cortex-A53r0p2        Lenovo P70-A         2276814  4.4.4   AArch32
MT8752                    8 x 1.69 GHz Cortex-A53r0p2        CUBE T7 (tablet)     2078854  4.4.4   AArch32
MT6795                    8 x 1.95 GHz Cortex-A53r0p2        Alps k6795v1_64_op01 2076054  5.0     AArch64
MT6795T                   8 x 2.16 GHz Cortex-A53r0p2        Unknown              2188071  5.0     AArch64
Kirin 620 (Hi6210)        8 x 1.20 GHz Cortex-A53r0p3        HUAWEI Che2-L11      2269931  4.4.2   AArch32
The Geekbench version used in the entries is 3.3.2 or 3.3.1.

Snapdragon 410-based devices are still limited to ARMv7 compatibility mode. Unusually for a cost-sensitive platform, the MT6735 test device uses AArch64 mode instead of AArch32 mode. Both the MT6735 and HiSilicon's Kirin 620 use a more recent version of the Cortex-A53 core, revision r0p3.

Integer subtest results

The following table shows results for integer subtests from Geekbench.

           CPU          JPEG Compress            Dijkstra                 Lua
                        Single IPC   Multi Par.  Single IPC   Multi Par.  Single IPC   Multi Par.
MSM8916    4 x 1.19      591   1.29  2379  4.03   816   1.09  2122  2.60   614   1.26  2229  3.63
MSM8916    4 x 1.21      602   1.29  2416  4.01   830   1.09  2182  2.63   632   1.27  2267  3.59
MSM8916    4 x 1.21      599   1.29  2404  4.01   739   0.97  2159  2.92   592   1.19  2168  3.66
MSM8939    4 x 1.50 + 4  832   1.44  4962  5.96   942   1.00  3469  3.68   744   1.21  2360  3.17
MT6732     4 x 1.50      842   1.46  3357  3.99  1035   1.10  3049  2.94   740   1.20  3049  4.12
MT6735     4 x 1.30      650   1.30  2563  3.94   712   0.87  1856  2.61   642   1.20  1902  2.96
MT6752     8 x 1.69      954   1.47  5810  6.09  1153   1.08  4817  4.18   850   1.22  2244  2.64
MT8752     8 x 1.69      952   1.46  7527  7.91  1200   1.13  4168  3.47   829   1.19  2294  2.77
MT6795     8 x 1.95     1026   1.37  8071  7.87   992   0.81  3886  3.92  1051   1.31  8075  7.68
MT6795T    8 x 2.16     1128   1.36  8991  7.97  1054   0.78  4159  3.95  1112   1.25  4159  3.74
AArch64 mode as used for the MT6735 and MT6795/MT6795T results has a significant influence, with the IPC (throughout per CPU cycle) for the JPEG Compress and Dijkstra tests being reduced when compared to AArch32 mode, while the IPC of the Lua test appears to be better in AArch64 mode, at least for the MT6795.

The MT6735 scores lower than the MT6732 in the Lua subtest, especially multi-core, even when correcting for the lower clock speed, which is probably the result of a smaller or slower L2 CPU cache inside the MT6735, which is targeted at the entry-level segment. The Dijkstra results are also lower, but that is probably mainly due to the use of AArch64 mode, which imposes a significant penalty on the results of this test.

Finally, while earlier results for the MT6795 showed very impressive Lua multi-core throughout, the result for the recent MT6795T entry is significantly lower (although still respectable). This is possibly due to a smaller L2 cache size in the latest revision of the MT6795T, although other reasons cannot be ruled out.

Memory and floating point subtest results

           CPU           Stream Copy  SGEMM        SFFT         Mandelbrot
                         Single Multi Single Multi Single Multi Single IPC   Multi
MSM8916    4 x 1.19      551    655    258   536   316    1264    450  1.11  1796
MSM8916    4 x 1.21      505    615    267   515   322    1292    456  1.11  1819
MSM8916    4 x 1.21      424    518    247   517   320    1277    451  1.09  1810
MSM8939    4 x 1.50 + 4  581    651    255   678   425    2510    583  1.14  3442
MT6732     4 x 1.50     1000   1187    343   697   430    1728    586  1.15  2329
MT6735     4 x 1.30      944   1034    322   636   403    1574    526  1.19  2102
MT6752     8 x 1.69     1007   1115    375  1123   485    3894    662  1.15  5279
MT8752     8 x 1.69      891   1045    387  1162   486    3902    662  1.15  5280
MT6795     8 x 1.95     1296   2070    484  1536   629    5021    824  1.24  6350
MT6795T    8 x 2.16     1380   2129    543  1847   687    5565    912  1.24  7171
Hi6210     8 x 1.20      575    996    262   819   343    2098    468  1.14  2842
The results show the memory performance advantage of MediaTek's Cortex-A53-based SoCs remains, scoring significantly higher than Qualcomm's existing SoCs, probably due to the use of a faster internal interconnect bus.

The first entry for Snapdragon 410 (MSM8916) running at 1.19 GHz is a Samsung SM-G360F, which appears to use relatively high-clocked memory, increasing memory performance over standard configurations (not listed). The two devices with a 1.21 GHz configuration have different memory performance, with the Moto G2 4G scoring lower than the Xiaomi device, probably due to the use of slower RAM. An impact from the use of Android 5 on the Moto G2 cannot be ruled out.

Sources: Geekbench browser, GSMArena (Acer Liquid Jade S review)

Updated 16 April 2015.

Tuesday, March 24, 2015

TSMC's 16 nm FinFET sees adoption by Qualcomm and Apple, competes with Samsung

TSMC will receive majority of Apple A9 business

According to reports, TSMC will receive the majority of Apple A9 SoC orders, which includes the A9 for next-generation iPhones and A9X for iPads. According to sources quoted by EE Times, Apple had originally planned to give Samsung a majority of the Apple A9 orders, but has recently shifted orders to TSMC, most likely using a 16 nm FinFET process.

Because ramping up production of a similar chip from a second source with different foundry technology is challenging and complicated, I believe it is likely that A9 production will be overwhelmingly (and perhaps exclusively) concentrated at TSMC. A parallel can be drawn with various reports from last year, which for a long time continued to echo incorrect projections that Samsung would serve a significant portion of the production of Apple's A8 generation SoCs, which has not turned out not to be the case.

In the mean time, TSMC's revenues continue to be a relatively high level despite Q1usually being seasonally down, with strong demand for 20 nm production, most likely reflecting continuing demand from Apple, which is offsetting weakness from Qualcomm for leading-edge processes. There have been rumours about an upcoming iPhone 6S and a lower cost iPhone 6C model which may involve substantial unit volumes. Apple's iPhone unit shipments have also been boosted by strong demand in China.

Low yield at Samsung and Exynos ramp contribute to TSMC orders

According to a source quoting sources in South Korea, TSMC's yield rate for its 16 nm FinFET process is better than that of Samsung's 14 nm process. Moreover, Samsung is seeing strong upcoming demand for it flagship Galaxy S6 smartphone, which uses the Exynos 7420 SoC produced on its 14 nm FinFET process, and most likely needs all capacity it can get to ramp up production of this SoC. Samsung also increasingly uses Exynos 7420 and other internally-developed SoCs for other product lines, such as other smartphone models as well as tablets.

Qualcomm said to have limited-time exclusive use of TSMC's 16FF+ technology

According a report by EETimes from a semiconductor industry conference in January, Qualcomm is likely to have locked up exclusive use of TSMC's 16FF+ process technology for about six months. The article appears to quote sources affiliated with Qualcomm that state that Qualcomm feels competitors such as MediaTek took advantage of previous-generation process technology (28HPM) that Qualcomm helped develop at TSMC, without having made the development investment that Qualcomm made.

However, this policy would be contrary to the principles based on which TSMC has operated for a long time, although the initial ramp of 20 nm at TSMC last year also seemed to be locked-up by another company (Apple). Its seems corporate pressure from these giant companies, backed by billions of dollars of cash, is forcing TSMC into these kinds of commitments.

The article mentions that the later access to 16FF+ won't affect MediaTek's mainstream products serving the mid-range to entry-level segments, because 28 nm technologies will continue to be used for such products in the market.

Leaked power consumption graphs suggest increased power efficiency

Power consumption graphs of current and upcoming high-end Qualcomm SoCs running a 3D game at high detail settings suggest power consumption and heat production of Qualcomm's unannounced Snapdragon 815 processor will be considerably lower than that of the Snapdragon 801 and Snapdragon 810, with Snapdragon 810 showing particularly unfavourable characteristics, as confirmed by widespread reports and reviews of Snapdragon 810-based devices.

Snapdragon 815 is unannounced and few details are known about it, with some reports suggesting the use of a next-generation Krait CPU core. Use of ARM Cortex-A72 processor cores appears to be not unlikely, since this core seems to be close to actual production. Most likely, the decreased heat production, which is likely to be associated with lower power consumption, is made possible by the use of the next-generation 16 nm FinFET process at TSMC.

Similar improvements in power consumption were observed for Snapdragon 620, which uses Cortex-A72 cores, when compared to the mid-range Snapdragon 615 SoC, which is reported to also have heating issues. Snapdragon 620, which has been announced, is also likely to have significantly higher CPU performance than Snapdragon 615 due to the use of Cortex-A72 cores, versus Cortex-A53 for Snapdragon 615, while also likely being produced on a much more efficient process (possibly  TSMC's 16FF+), since Snapdragon 615 is manufactured on a low-efficiency 28LP process.

Sources: EE Times (ISS 2015 conference report), EE Times (Apple A9 orders article), STJS Gadgets Portal (Snapdragon heat production graphs)

Updated 25 March 2015 (Add comments about 20 nm Apple production at TSMC).

Thursday, March 19, 2015

Qualcomm releases new variant of Snapdragon 410 that supports ARMv8, targeting tablets and other applications

Qualcomm recently made announcements of products and reference designs based on the APQ8016 SoC, a new modem-less quad-core Cortex-A53-based SoC branded as Snapdragon 410. The chip is targeted at IoT applications, development boards and probably also Wi-Fi-only tablets, supporting Linux, Android and Windows 10. Although branded as Snapdragon 410, the chip is a new design that is likely to fix most of the performance deficiencies of the first-generation MSM8916 Snapdragon 410 SoC that has been targeted at smartphones. For example, the original Snapdragon 410 SoC appears not to support ARMv8 at all, while the new chip is clearly targeted at 64-bit platforms.

Development board released

Qualcomm recently announced the DragonBoard 410c, a development board with support for Linux and Android. It features a quad-core 1.2 GHz Cortex-A53 processor with Adreno 306 GPU, 533 MHZ LPDDR2/LPDDR3 SDRAM, HDMI output and several I/O interfaces. The HDMI output is limited to 30fps at 1080p.

The board is designed to compatible with the 96Boards initiative from Linaro, the non-profit engineering organization developing open source software for the ARM architecture.

With 64-bit support and a maximum clock speed of 1.2 GHz, the APQ8016 SoC that is used on the board most likely uses a more recent version of the Cortex-A53 core than the original Snapdragon 410 processor for smartphones, while being manufactured using the same 28LP process at TSMC.

New SoC probably targets tablets as volume driver

There are indications that the new chip will be used in Wi-Fi-only tablets, such as recently announced Samsung Galaxy Tab A series. There have also been indications that Qualcomm is stepping up its efforts to target Chinese tablet manufacturers.

Qualcomm and MediaTek support mainline Linux kernel with open-source drivers for selected SoCs

Whereas in the past major smartphone SoC companies kept their closed-source drivers separate from the open-source Linux community, more recently companies such as Qualcomm and MediaTek have started releasing open source contributions for the Linux kernel to support selected SoC products. Both companies have also recently joined Linaro, the engineering organization developing open source software for the ARM architecture.

For both companies, the SoCs supported in the mainline Linux kernel are applications processors without an integrated modem. Qualcomm is supporting the APQ8016 mentioned above while MediaTek has contributed code for the MT8173 tablet processor.

Sources: Qualcomm (Dragonboard announcement), Qualcomm (Windows 10 IoT platform announcement), CNXSoft (DragonBoard 410c article)

Tuesday, March 10, 2015

Qualcomm's Snapdragon 808 fixes flaws of Snapdragon 810

Snapdragon 808 (MSM8992) is a performance-oriented SoC that Qualcomm announced last year together with Snapdragon 810. It has similarities to Snapdragon 810 (MSM8994), including the use of ARM Cortex-A57 CPU cores and Cortex-A53 cores in a big.LITTLE configuration. Snapdragon 808 appears to fix some of the performance flaws that are apparent in Snapdragon 810, especially the memory subsystem, while being significantly less costly.

Snapdragon 808 features

Features and differences with Snapdragon 810 include:

  • Snapdragon 808 has only two Cortex-A57 cores (revision r1p2) compared to four Cortex-A57 cores (revision rp1p1) for Snapdragon 810. Both contain four Cortex-A53 cores.
  • Snapdagon 808 has a more economical dual-channel LPDDR3 memory interface, compared to the LPDDR4 interface of Snapdragon 810.
  • Snapdragon 808 has an Adreno 418 GPU, compared to Adreno 420 in Snapdragon 810, presumably with somewhat lower performance.
  • Manufactured on TSMC's 20 nm process, the same as Snapdragon 810.
  • 4K resolution video playback (H.264/H.265), on-device display resolution up to 2560x1600 (Snapdragon 810 theoretically supports 4K on-device display resolution, but all currently announced smartphones using Snapdragon 810 are limited to a resolution of 1920x1080).


Early benchmark results suggest Snapdragon 808 fixes performance flaws of Snapdragon 810

Early benchmarks for Snapdragon 808 have already appeared on the Geekbench Browser. We can compare Snapdragon 808's single-core performance with Snapdragon 810 and Exynos 7420, all of which run in AArch64 mode in the published benchmark results.

To reduce the impact of thermal throttling, the best Geekbench subtest results for a given device have been collected and combined in the table below. I have made an attempt to estimate the actual maximum clock speed of the Cortex-A57 cores during the benchmarks, partly based on the maximum frequency reported by Geekbench when it appears to apply to the "big" cores and not the "LITTLE" cores.

SoC          "big" CPU                    Arch     JPEG (int)  Lua (int)   Mandelb. (float)
                                                   Comp. IPC         IPC         IPC

MSM8992      2 x 1.69? GHz Cortex-A57r1p2 AArch64  1257  1.96  1385  1.99  1031  1.79
MSM8994      4 x 1.8? GHz Cortex-A57r1p1  AArch64  1358  1.96  1283  1.73  1100  1.79
Exynos 7420  4 x 1.97 GHz Cortex-A57r1p0  AArch64  1486  1.96  1409  1.74  1198  1.78

MT6795       8 x 1.95 GHz Cortex-A53r0p2  AArch64  1026  1.37  1053  1.31   823  1.24
MT6795T      8 x 2.16 GHz Cortex-A53r0p2  AArch64  1128  1.36  1173  1.32   912  1.24

The IPC figures are calibrated on the Cortex-A7 core, whose IPC is fixed at 1.00. Fixing the maximum cock speed to 1.8 GHz for the MSM8994 (Snapdragon 810) results (based on HTC One M9 entries) and at 1.69 GHz for the MSM8992 (Snapdragon 808) produces similar IPC figures for the JPEG Compress integer test and the Mandelbrot floating point test, making them reasonably plausible. The best Lua subtest result for the MSM8992 shows a higher IPC, which may reflect improved L2 cache performance in the MSM8992, which uses a later revision of the Cortex-A57 core.

The single-core CPU performance results show no suprises, with Snapdragon 808 showing good performance that is slightly lower than Snapdragon 810, proportional to the lower maximum clock frequency in the tested devices. However, the Lua test shows higher performance with Snapdragon 808, which is especially true for the multi-core test (results not shown), where Snapdragon 810 seems to be limited to a score of about 1200 with little gain when compared to single-core performance, while Snapdragon 808 consistently scores in the region of 4000.

Memory subsystem performs much better than Snapdragon 810

The following table lists Geekbench scores for some memory-dependent tests. 

SoC          "big" CPU                    Arch     Stream Copy  SGEMM SFFT  SGEMM SFFT
                                                   Single Multi             Multi Multi
MSM8992      2 x 1.69? GHz Cortex-A57r1p2 AArch64  1527   1733   767  1126  1678  2946
MSM8994      4 x 1.8? GHz Cortex-A57r1p1  AArch64  1428   1838   741  1009  1870  3649
Exynos 7420  4 x 1.97 GHz Cortex-A57r1p0  AArch64  2003   2622   957  1363  2888  5014

MT6795       8 x 1.95 GHz Cortex-A53r0p2  AArch64  1356   2068   484   618  1542  4764
MT6795T      8 x 2.16 GHz Cortex-A53r0p2  AArch64  1350   2140   529   694  1659  5333

Notably, Snapdragon 808 delivers memory performance similar to Snapdragon 810 at much lower cost, despite using only a regular LPDDR3 memory interface, as compared to the Snapdragon 810's LPDDR4 memory interface which in theory delivers almost twice the bandwidth. This provides clear evidence that the Snapdragon 810's memory interface is still flawed, while that of Snapdragon 808 is much more optimized. Snapdragon 808 even beats Snapdragon 810 in the single-core SGEMM and SFFT test, despite running at a lower clock speed, which probably also reflects a more optimized and functional memory controller. Even in the multi-core SGEMM and SFFT tests, Snapdragon 808 is not much behind Snapdragon 810 despite having only half the number of CPU cores.

Comparison with MT6795

In the marketplace, Snapdragon 808 may compete with MediaTek's MT6795 (Helios X10), which is a cost-effective performance-segment SoC that only uses Cortex-A53 cores. Comparing Geekbench subtest results, MT6795 scores signficantly lower than Cortex-A57-based SoCs such as Snapdragon 808 in single-core benchmarks, although the gap is not very large except in the SFFT benchmark. The MT6795 does relatively well in multi-core benchmarks, where it beats the Cortex-A57-based Snapdragon 808 and Snapdragon 810 in most cases by a considerable margin, especially in the JPEG Compress, Lua and Mandelbrot tests which are sensitive to the number of CPU cores (multi-core scores have not been listed for these tests in the tables above). As an example, MT6795 scores 8167 in the multi-core JPEG Compress test, twice the score of Snapdragon 808 and almost 40% higher than Snapdragon 810.


Snapdragon 808 appears to be a much more optimized, less flawed SoC product than Snapdragon 810 that may perform similarly or even better than Snapdragon 810 in practical use cases due to the performance flaws present in Snapdragon 810. At the same time, Snapdragon 808 is likely be considerably cheaper. The only caveat is the question of whether excessive heat production makes thermal throttling necessary to the same degree as Snapdragon 810. With only two Cortex-A57 cores, the SoC should be less problematic in this regard.

Source: Geekbench Browser (MSM8992 results), Geekbench Browser (MSM8994 results), Qualcomm (MSM8992 specifications)

Updated 15 March 2015.

Early benchmarks appear for Cortex-A72-based SoC

ARM recently announced the new Cortex-A72 processor core, which is an improved version of the existing high-performance Cortex-A57 processor core.

Alongside the Cortex-A72 CPU core, ARM also announced the CCI-500 interconnect technology as well as the high-end Mali-T880 GPU. Devices incorporating the combination of these technologies are expected to become available in 2016.

However, SoCs using the Cortex-A72 CPU are likely to become available earlier. Qualcomm and MediaTek have both announced SoCs using the Cortex-A72 core with commercial availability in the second half of 2015, suggesting that the CPU core itself is at an advanced stage of introduction. Already, early benchmarks for MediaTek's MT8173 tablet SoC that incorporates the Cortex-A72 have become available.

Cortex-A72 appears to be enhanced version Cortex-A57 optimized for next-generation processes

In its announcement press release from 3 February 2015, ARM claims that more than ten partners have already licensed Cortex-A72, including HiSilicon, MediaTek and Rockchip. Cortex-A72 is based on ARM's ARMv8-A instruction set architecture, and can be combined with the existing Cortex-A53 in a big.LITTLE configuration. Cortex-A72 seems to be positioned as a replacement for Cortex-A57. The similarities with Cortex-A57 are very apparent, for example in the identically sized L1 instruction and data caches, and a feature set that is otherwise very similar.

On a 16 nm FinFET process, the core can sustain operation at speeds up to 2.5 GHz within the constraints of a mobile power envelope (e.g. smartphones), with scalability to higher speeds for larger form-factor devices. However, the first announced devices, such as MediaTek's MT8173, appear to use older processes such as the tried-and-trusted 28 nm HPM process at TSMC, so they are likely to have a lower maximum clock speed.

ARM claims increased performance and power efficiency, although these claims seem to be based on implementation on next-generation processes such as 16 nm FinFET that deliver a significant intrinsic improvement in these metrics. ARM mentions micro-architectural improvements that result in enhancements in floating point, integer and memory performance. When implemented on a 16 nm FinFET process, ARM expects Cortex-A57 to provide 85% higher performance when compared to the Cortex-A57 core on a 20 nm process within a similar smartphone power budget.

Overall, the differences with Cortex-A57 appear to be relatively minor, so that Cortex-A72 is best viewed as an enhanced version of Cortex-A57 that is optimized for next-generation processes such as 16 nm FinFET. Nevertheless, the first SoCs to use the Cortex-A72 core will be manufactured using a less advanced process.

Benchmarks appear for MediaTek's MT8173

MediaTek's MT8173 is a mid-range tablet processor mainly targeting Wi-Fi-only tablets, since it does not have an integrated modem. It has two Cortex-A72 cores and two Cortex-A53 cores in a big.LITTLE configuration. Probably manufactured using the established 28HPM process at TSMC, the maximum clock speed of the Cortex-A57 cores is likely to be lower that the target for 16 nm FinFET, although MediaTek claims a clock speed up to 2.4 GHz, while a much lower frequency is apparent in early benchmarks results.

The chip also features a PowerVR GX6250 GPU, which delivers higher performance than the G6200 GPU used inside MediaTek's existing MT8135 and MT6795.

Recently, early benchmarks for a MT8173 development board have appeared both in the Geekbench Browser and in the results database of GFXBench. The first Geekbench results already appeared in December 2014. The latest set of Geekbench results date from the end of February 2015, although they do show a certain amount variation that may reflect thermal throttling.

Single-core performance good, but not spectacular

As expected, the Geekbench results show good single-core performance, albeit not spectacular. As shown in the following table, singe-core performance is in line with Cortex-A57-based SoCs such as Exynos 5433 and Exynos 7420. It should be noted that the MT8173 test SoC is most likely manufactured at 28 nm with a corresponding relatively low maximum CPU clock speed, while Exynos 5433 and 7420 are manufactured using smaller leading edge processes at Samsung.

SoC          "big" CPU                    Arch     JPEG (int)  Lua (int)   Mandelb. (fp)
                                                   Comp. IPC         IPC         IPC
MT8173       2 x 1.6? GHz Cortex-A72      AArch32  1310  2.13  1380  2.10  1064  1.95
Exynos 5433  4 x 1.80 GHz Cortex-A57r1p0  AArch32  1456  2.10  1397  1.89  1174  1.91
Exynos 7420  4 x 1.97 GHz Cortex-A57r1p0  AArch64  1481  1.97  1409  1.74  1198  1.92

In this table, to determine the IPC index I have made an educated guess about the actual clock speed of MT8173 when running the benchmarks. Geekbench reports a 1.40 GHz clock speed (which probably applies to the Cortex-A53 cores), 1.6 GHz seems to be a good match, providing just a little better IPC than Cortex-A57. Note that Exynos 7420 runs in AArch64 mode, which skews direct IPC comparisons.

Practical implications unclear

Without knowing the exact clock speed of the Cortex-A72 cores, it is hard to draw conclusions about the actual IPC improvement over Cortex-A57. If the MT8173 uses a 28 nm process, the ability to approach the single-core performance of Samsung's Exynos 7420 manufactured using 14 nm FinFET process is impressive. However, although MediaTek demonstrated the MT8173 in an actual tablet at MWC, it is unclear what kind of device the Alps development board in the benchmark entries actually represents, so it remains to be seen whether the benchmarks actually reflect the power budget of a tablet.

The multi-core performance reported is not very impressive, as expected because of the relatively small number of CPU cores. The JPEG Compress multi-core score shows CPU scaling factor of 2.72, which is good and implies utilization of the Cortex-A53 cores. The Mandelbrot floating point benchmark shows similar scaling.

However, the Lua integer benchmark has a very low multi-core scaling factor of 1.41, which is lower than expected, even when allowing for the limited number of cores. For example, MediaTek's MT6795 achieves multi-core scaling of 7.5 in this benchmark, and the Exynos chips range from 3.9 to 5.0. Other chips with a low multi-core scaling factor for Geekbench's Lua subtest include Snapdragon 810 (Cortex-A57-based), MediaTek's MT6595 (Cortex-A17-based) and NVIDIA's Denver-based Tegra-K1 SoC. There are indications that this benchmark test heavily depends on on-chip cache (primarily L2 cache) size and speed.

GPU performance of MT8173's PowerVR GX6250 GPU improves on G6200

The MT8173 test device's GPU performance as shown in GFXBench results database is not overly impressive, but suitable for a mid-range chip and an improvement over the PowerVR G6200 GPU used in other MediaTek SoCs such as MT6595 and MT6795. In the T-Rex Offscreen benchmark, the MT8173 registers a score of 1487, higher than the 1311 of the MT6595 (G6200)-equipped Meizu MX4. In the GFXBench 3.0 low-level tests, alpha blending scores higher than the MT6595 while the other low-level scores are comparable.

Sources: ARM (Cortex-A57 announcement press release), AnandTech (MediaTek MT8173 article), MediaTek (MT8173 announcement), Geekbench Browser (MT8173 test device results), GFXBench (MT8173 test device result)

Updated 10 March 2015.

Friday, March 6, 2015

MediaTek sales collapse, loses market share in China to Qualcomm

Mediatek has reported revenues for the month of February 2015 that show a steep decline, both sequentially and year-over-year.  Revenues came in at only NT$9.671 billion, a decline of 45% from January 2015 and a year-over-year decline of 39%. Since the merger with MStar became effective in February 2014, the year-over-year decline is factual and reflects a steep actual decline in the sales level of the combined businesses.

Although MediaTek has attributed the sales decline to a transition to new products in the smartphone segment, seasonal factors and fewer working days due to Chinese New Year, the main reason is likely to be a dramatic loss of market share in the entry-level segment of the Chinese smartphone market due to changes in the competitive landscape and a lack of a low-cost 4G solutions in MediaTek's product line.

Qualcomm's agreement with regulatory authorities in China has hurt MediaTek

On February 9, Qualcomm announced the resolution of the investigation by Chinese regulatory authorities into alleged monopolistic practices by Qualcomm because of the high royalty rates it imposes on all 3G and 4G-connected devices and its ability to combine royalty agreements with chip sales, effectively shutting out competitors. As part of the resolution, Qualcomm agreed to pay almost US$1 billion and agreed to a lower royalty rate of 65% in China.

However, the agreement may have increased Qualcomm's ability to enforce patent royalties and enhanced its bargaining position with Chinese smartphone manufacturers, leading to a larger proportion of Qualcomm chips being used, mainly at the expense of MediaTek's solutions. Previously, a large number of smartphones, most with MediaTek chips, were produced and sold in a grey market that avoided payment of royalties to Qualcomm. This grey market may quickly have become much smaller, contributing to the decline in MediaTek's shipments.

Additionally,  being a Taiwanese company, MediaTek is a foreign company within China, while policies in China tend to favour Chinese companies. As such, the agreement with Qualcomm and related policies may have been designed to favour upcoming Chinese chip designers such as Huawei's HiSilicon technology and the smartphone manufacturers themselves, rather than supporting MediaTek, which is not fully in the Chinese government's interest.

Lack of entry-level 4G SoC has left gap in MediaTek's product line

Because the MT6732, which is the lowest cost 4G solution that MediaTek currently has in the market, is too costly for the entry-level 4G smartphone segment, MediaTek currently has no cost-effective product offering for this segment. As entry-level smartphones transition to 4G, Qualcomm is taking market share with with its 4G-enabled Snapdragon 400, 410 and 210 SoCs, which are already in production targeting the entry-level market. This comes mainly at the expense of MediaTek's existing 3G solution shipments which previously occupied entry-level models in the product lines of most Chinese manufacturers.

Even for existing 3G models, MediaTek may be seeing market share loss as Qualcomm's cost-reduced 3G SoCs may be favoured by certain manufacturers given the changed environment regarding patent royalties.

MediaTek's loss of market share is evident among the current and new product line ups of smartphone manufacturers that previously used a lot of MediaTek solutions, such as TCL (including the Alcatel brand), ZTE, and Xiaomi, as well as other manufacturers.

However, MediaTek is close to bringing the MT6735 to market, which is a lower-cost 4G solution with a WorldMode modem with which it intends to target the entry-level 4G segment. A cost-reduced octa-core smartphone SoC, the MT6753, has also been introduced. It remains to be seen to what extent and when MediaTek will be able to recover market share in the entry level segment. Although its smartphone product line will soon be in good order and complete, it may be affected by factors beyond its control.

Many companies shipping Snapdragon 615 despite technological superiority of MT6752

Adoption of Qualcomm's mid-range Snapdragon 615 SoC by Chinese manufacturers has been strong, even as MediaTek's MT6752 SoC has ramped into production. According to most reports, the MT6752 SoC has a superior cost structure as well as delivering higher performance when compared to Qualcomm's solution, which also dominates new mid-range models from brand-name smartphone manufacturer outside of China. For the reasons explained in the previous section, Chinese smartphone manufacturers may have a strong impetus to ship models with a Qualcomm SoC in order to better deal with patent royalties, despite the technological superiority of MediaTek's chip.

Previous delay of MediaTek's MT6795/Helios X10

MediaTek's main product for the performance segment of the smartphone market, MT6795 (rebranded to Helios X10 last week at MWC), was originally announced in July 2014 with availablity to end users expected before the end of 2014. However, the chip was delayed and it is likely to come to market in the near future, several months after the planned introduction. This has also hurt MediaTek, although given the patent royalty environment it remains to be seen to what extent MediaTek will be able to gain traction with a high-end product, since patent royalties claimed by Qualcomm are significant for high-end devices with a high selling price.

Update (11 March 2015)

On 10 March, DigTimes reported that industry sources expect MediaTek's sales to rebound significantly in March to a revenue level of about NT$20 billion due a pick-up in demand from Chinese manufacturers. The sources attributed the previous decline in MediaTek's smartphone chip shipments to an inventory correction among Chinese manufacturers. According to the sources, there are signs of a pick-up in demand as vendors gear up for the launch of 4G devices in Q2 2015.

However, it is likely some orders from February 2015 where shifted into March. For the months of February and March combined, MediaTek is still likely to be seeing a disappointing year-over-year decline in revenues. Because of the competitive pressures mentioned above, it remains to be seen at what level MediaTek will be able to maintain revenues in the second quarter of 2015.

MediaTek's 4G smartphone chip product line is becoming more complete as the low-end MT6735 (especially) and MT6753 and the high-end MT6795 reach the market. Additionally, some details have surfaced about the new entry-level MT6570 and MT6580 SoCs, which appears to be developments of the popular MT6572 (dual-core Cortex-A7) and MT6582 (quad-core Cortex-A7) platforms with added support for 4G, comparable to Qualcomm's Snapdragon 210 platform, targeting the entry-level 4G segment. Given these new chips, MediaTek's smartphone performance has potential to improve.

Sources: DigiTimes (MediaTek February 2015 sales)

Updated 23 March 2015 (Mention MT6570 and MT6580).

China tablet processor market declines in Q1

According to a recent article published by DigiTimes Research, tablet applications processor unit shipments to Chinese manufacturers grew by 4.7% in Q4 2014 to reach 34.7 million units. However, shipments are estimated to decline by 24% in Q1 2015 when compared to Q4 2104. Year-over-year, shipments are expected to drop by about 8%, which marks the first time quarterly tablet processor shipments in China experience a year-over-year decline. Excess inventory from Q4 2014 is given as a cause for the decline in shipments.

MediaTek leads Chinese tablet market in Q1 2015

Based on information published by DigiTimes Research, MediaTek, Rockchip, Allwinner and Intel were the top four providers of tablet processors in China, in that order, in Q4 2014. For Q1 2015, MediaTek is estimated to expand it market share by about 1% to reach 28.5%, although absolute shipments will decline significantly due to the overall market decline.

Rockchip, who was the market share leader for most of 2014, is estimated to see its market share remain stable in Q1 2015, registering a 0.6% increase according to DigiTimes Research, who did not supply a market share figure for Rockchip, although it is probably in the region of 25%. DigiTimes mentioned that Rockchip's new chips launched at the end of 2014 (which includes the Cortex-A7-based RK3126 and RK3128) have not yet reached strong shipments.

Meanwhile, Allwinner continues the trend of a steady decline a market share, being expected to have a share of 15.6% compared to 17.6% in Q4 2014. This allows it to be passed by Intel in terms of market share, with Intel's market share estimated to rise from 15% to 16.3% in Q1 2015.

Intel's global market share has increased and is significant, especially revenue share

It should be noted that in terms of global market share, Intel has a stronger position than what would be inferred just from the Chinese market due to a strong position at brand-name tablet manufacturers outside of China, such as Asus and Acer. The other chip players in the Chinese tablet processor market, especially Rockchip and Allwinner, have a weak position outside of China. Due to the higher-end nature of Intel's product mix, Intel also has a higher revenue share, whereas the sales of companies such as Allwinner are mostly concentrated in low-end processors. It has been reported that Intel is abandoning its "contra-revenue" strategy of subsidizing tablet processor sales, which it probably can afford to do because its chip solutions are fairly competitive on their own.

Global brand names gain share, use different chip suppliers

In the global tablet marker, brand name manufacturers are gaining share and dominate the dollar value of the market, also for semiconductor content. Apple and Samsung, who lead the global tablet market, use a lot of in-house chip solutions (100% in the case of Apple). Samsung also uses suppliers like Qualcomm and Marvell, who otherwise do not have a strong position in the Chinese tablet market.

MediaTek used to have strong market share among Taiwanese tablet manufacturers such as Asus and Acer. However, its market share their seems to have been eroded significantly by strong adoption of Intel's Atom SoCs at these manufacturers (who have strong ties with Intel through PC manufacturing).

Popular tablet SoCs as of Q1 2015

By analyzing the tablet models offered on Chinese e-commerce portals, one can get some idea of what SoCs are currently used the most in tablets from China. I took a look at the tablet offerings on

Rockchip's RK3188 (which probably means the RK3188T variant in most cases) is still widely used. Originally a mid-range performance segment SoC, there are indications that Rockchip built a significant inventory of this SoC (which is not particularly cheap in terms of manufactuing cost) last year, and the chip has been used in cheaper models as well. Rockchip's RK3126, which is more cost-effective than RK3188, is slowly starting to appear in new tablet models.

Meanwhile, Rockchip's high-end RK3288 is used in several models from Pipo, Teclast and FNF, and these seem to be reasonably popular for a high-end product. I have some concerns about power consumption and battery life regarding these products due to the processor cores used in the SoC.

The most popular MediaTek chips used in tablets are SoCs with 3G connectivity such as the low-end dual-core MT8312 and quad-core MT8382 (the equivalent of the MT6572 and MT6582 smartphone SoCs), as well as the more performance oriented octa-core MT6592/MT8392, which provides good performance and battery-life and has moved down to lower-priced tablet models. Additionally, the new 64-bit MT8752 with 4G (equivalent to the MT6752 smartphone SoC) is starting to appear in new models (Cube, Teclast). For WiFi-only tablets, the MT8127 (which has a relatively powerful GPU for a cheap SoC) is used in some low-to-mid-range tablets.

Allwinner's A31s, which was released in 2013 but perhaps its last successful product introduction, appears to be still used for production. Low-end tablets are available with the A23 and A33 SoCs, although the A33 does not seem to have been very successful and has been affected by weakness in the low-end segment of the tablet market.

Allwinner's new octa-core A83T has started to appear in a few new models, and is probably replacing the high-end A80 Octa which is likely to have had low profit margins.

Finally, Intel's Z3735F, Z3735G and Z3736F Atom SoCs are widely used in tablets, although most prominently in higher-prices models that come equipped with Microsoft Windows.

Update (15 March): 3G smartphone chip inventory unloaded onto Chinese tablet market

In an article published on 13 March 2015, DigiTimes Research reported that due to a high inventory level of 3G smartphone solutions in China, such chips will be unloaded onto the Chinese tablet market by players such as MediaTek, Qualcomm and Spreadtrum.

3G-enabled chip solutions for tablets are usually very similar to similar solutions for smartphones. For example, MediaTek's smartphone solutions have commonly been used in tablets, while MediaTek's official 3G-enabled tablet solutions most likely consist of a chip virtually identical to the smartphone version, with the main difference being a different model number (e.g. MT6582 vs MT8382). That MediaTek would target any excess inventory of 3G smartphone chipsets at the tablet market is not surprising.

However, I am little sceptical about the volume that may be involved. The Chinese tablet market is clearly contracting in the near term, and the volumes in the tablet market are considerably smaller than the smartphone market, even the declining 3G part of the smartphone SoC market. To put things into perspective, MediaTek's quarterly 3G smartphone chip shipments were on the order of 70 million in Q4 2014, while its 3G tablet chip shipments were probably in the range of 5 to 10 million.

The article also mentions Qualcomm, which in the past has not been a major player in the Chinese white-box tablet market. It mentions rumours that Qualcomm may form a partnership with Allwinner (which has been consistently losing market share) to penetrate the tablet market in China. The article also states that while Intel has introduced 3G tablet solutions, Intel's solutions are unlikely to be widely adopted until Intel introduces the 4G version of its Atom x3 (formerly SoFIA) platform.

Sources: DigiTimes (Q1 2015 China tablet AP market article)DigiTimes Research (smartphone chips inventory unloaded to tablet market)

Updated 15 March 2015.