The announcement of the ARM®Cortex®-A35 processor today marks the beginning of a new family of ultra high efficiency application processors from ARM. So, what are the key features of Cortex-A35 and what benefits does it provide compared to previous processors in its category?
Before we go into the details of Cortex-A35 processor, a brief background on the existing Cortex-A5 and Cortex-A7 processors from ARM will be useful.
The launch of the Cortex-A5 processor in 2009 ushered in a new era of high efficiency mobile computing by implementing the ARMv7-A architecture in extremely low power and area profiles. The industry leading efficiency benefits offered by Cortex-A5 enabled the rapid proliferation of ultra affordable entry smartphones. The Cortex-A7 provided further performance and efficiency improvements along with support for ARMv7-A extensions. Additionally, the Cortex-A15 and Cortex-A7 processors formed the first big.LITTLE™ CPU pair thereby redefining efficiency across all mobile markets.
Both the Cortex-A5 and Cortex-A7 processors have been tremendously successful not just in mobile but in other diverse markets like embedded, wearable computing and offload processing in enterprise applications. Focusing on the success of these processors in the mobile market alone, Cortex-A5 and Cortex-A7 have shipped in over 2Bn entry smartphones to date.
Looking into future, it is estimated that more than 1Bn entry smartphones will be shipped in 2020. This implies an 8% compounded annual growth rate, making entry level mobile the most rapidly expanding mobile market segment.
This rapid growth in entry smartphones sets the context for Cortex-A35. The requirements for next generation entry mobile solutions converge in three key requirements – deliver more performance, consume lower power (thereby improve efficiency), and provide premium features at an affordable cost point. The Cortex-A35 processor delivers on all three: it brings the modern 64-bit compute capabilities for the next billion smartphone users while delivering efficiency improvements compared to the previous generation of processors targeting entry markets.
So, what benefits does the Cortex-A35 offer compared to previous generation cores for powering the next billion smartphones?
The Cortex-A35 processor has several key feature enhancements compared to Cortex-A7. I will focus on three:
The Cortex-A35 uses a combination of power reduction and performance enhancements to deliver efficiency improvements compared to Cortex-A7. The Cortex-A35 consumes 10% lower active power when compared to Cortex-A7 for an iso-frequency implementation on 28nm. In addition, the Cortex-A35 is an ARMv8-A architecture based processor and supports both 64-bit and 32-bit compute capabilities, whereas the Cortex-A7 is an ARMv7-A based processor and hence only supports 32-bit.
Additionally, we can compare Cortex-A35 with Cortex-A53 (the first efficiency-maximizing ARMv8-A processor). The Cortex-A35 core is 25% smaller compared to the Cortex-A53 core for a typical configuration that includes 32k L1 caches, NEON, and crypto blocks. The Cortex-A35 consumes an impressive 32% lower power per core and is 25% more efficient compared to Cortex-A53. This makes Cortex-A35 the smallest, lowest power and most efficient ARMv8-A processor we have built.
So, how does the Cortex-A35 processor reduce power consumption while simultaneously improving performance in the entry mobile power envelope?
The Cortex-A35 processor has a redesigned in-order 8 stage pipeline that delivers significant efficiency improvements while providing full ARMv8-A support (capability to execute both A32/T32 and A64 instruction sets).
Here are some key micro architectural improvements in Cortex-A35 compared to Cortex-A7,
The graph below depicts the relative performance improvements delivered by the Cortex-A35 pipeline compared to Cortex-A7 across some of the popular benchmarks. To ensure like-for-like performance comparison, the graph below compares only 32-bit code on Cortex-A35 and Cortex-A7, using the same processor configurations, and running at the same clock frequency.
The Cortex-A35 processor delivers overall 6% faster integer performance compared to Cortex-A7. The Cortex-A35 delivers 16% faster browsing performance compared to Cortex-A7. It also delivers an impressive 36% overall improvement for floating point operations, which can translate into improved performance of apps, like gaming, that use floating point operations extensively.
If we look at the GeekBench single core benchmark, which includes the aggregate performance scores of integer, float and memory streaming tests, the Cortex-A35 processor delivers a 40% performance improvement compared to Cortex-A7.
To summarize the first key benefit: the Cortex-A35 delivers higher performance while consuming lower power, thereby providing a leap in efficiency improvements compared to the Cortex-A7.
Saving each mW of power is extremely important for entry smartphones where the overarching goal is to maximize the battery life.
The Cortex-A35 supports new power management capabilities that enable further power savings while making it easier for designers to integrate these features in their next generation entry mobile SoC platforms. Highlighting three new power management features available in Cortex-A35:
The combination of power management and efficiency improvements in Cortex-A35 translates into uncompromised performance at new levels of efficiency for next generation entry-level mobile solutions.
The third benefit of Cortex-A35 is full support of the modern ARMv8-A architecture at unprecedented levels of efficiency. This enables Cortex-A35 based mobile devices to deliver affordable 64-bit compute and leverage the investments in ARMv8-A 64-bit software ecosystems. The Cortex-A35 is fully compatible with the vast ARMv7-A software ecosystem, and it simultaneously delivers improved 32-bit performance.
Cortex-A35 executes the A64 instruction set in the AArch64 execution state. This means that future entry mobile platforms can realise higher performance via
In the AArch32 execution state, the Cortex-A35 runs the A32/T32 instruction sets and seamlessly executes the existing software written for ARMv7-A architecture. In addition, new crypto and floating-point instructions are also added to the AArch32 state thereby providing efficient acceleration of algorithms that use these instructions.
We discussed three benefits of the Cortex-A35 processor so far. But, how will Cortex-A35 be used in future entry mobile platforms? The Cortex-A5 and Cortex-A7 have been shipping in several entry smartphone platforms using different core configurations ranging from single core to octa core. The scalability and configurability of Cortex-A35 opens up new possibilities for ARM partners to continue innovating and differentiating for future mobile solutions while delivering the full ARMv8-A features. Cortex-A35 can be configured from an ultra low power, very small single core to four cores in a single CPU cluster. Being architecturally compatible with existing ARMv8-A processors, Cortex-A35 can also be connected as a LITTLE CPU in a big.LITTLE system.
There are many possible configurations of next generation 64-bit capable entry mobile compute subsystems, the diagram below shows one example. The example uses a quad core Cortex-A35 cluster with other energy efficient IP from ARM and is capable of delivering efficiency improvements while incorporating the premium features in affordable cost points for the next billion smartphone users.
The introduction of the Cortex-A35 processor truly begins a new era of ultra affordable, ultra efficient 64-bit compute, not just for next generation entry mobile but also for many other rapidly growing markets beyond mobile.
Efficiency is a cool thing!