ARM is yet another best chip maker has now introduced its highly-efficient processor in its Cortex-A series, and said that it will be offering significant performance improvements compared to other 64-bit CPUs. Cortex-A35 comes in that category which is specifically designed for wearable devices and embedded applications. However, ARM billed the Cortex-A53 as a replacement for the Cortex-A7 initially, tests showed the A53’s power curve was huge enough that it wasn’t a drop-in replacement for the 32-bit chipset. Now that, ARM has announced a new 64-bit processor, Cortex-A35 – does replace the Cortex-A7, while improving performance and flexibility.
Smartwatch these days are using Qualcomm Snapdragon 400 SoCs based on ARM Cortex-A7. While Cortex-A35 is here, could take the power profile of A7 and its ARM big.LITTLE multi-core capabilities and combines it with the software maturity and 64bit compute experience of the ARMv8-A architecture. But presumably tilts towards the A7’s power efficiency and performance ratio rather than the minimalist Cortex-A5. A5 customers likely don’t have much need for 64-bit in the near future in any case.
The new Cortex-A35 is specifically designed as a successor to the Cortex-A5 and A7 and if you work in environments where the A5’s performance is good enough, it’s probably fine for the foreseeable future. Reports suggests that the A35 is targeting environments where power is below 125mW (ARM claims the A35 can operate at 1GHz while drawing just 90mW) and that’s on a 28nm process. Real power and voltage levels should be even better, since ARM intends for the chip to deploy at the 14/16nm node, allowing for a greater frequency range or even lower power consumption for Internet of Things devices that don’t require much in the way of performance.
The ARM’s new Cortex-A35 has an eight-stage pipeline and limited dual-issue capabilities like the A5 and A7. When compared to the changes to those cores is that ARM has improved memory accesses, branch prediction, and instruction fetch to boost bot power efficiency and overall performance. If you configure this the best, then ARM borrowed heavily from the A53’s memory architecture to improve the A35’s final design, and boost the ache subsystem’s overall capabilities as well.
ARM also said that Cortex-A35 processor consumes 32% less power, has 25% smaller silicon footprint and provides 25% more efficiently when compared to the A53 CPU. The Cortex-A35 can be configured with 8K-64K L1 caches and an L2 cache between 128KB and 1MB. Customers who wish to do so can implement a Cortex-A35 core with an 8K L1, no FPU, Neon, L2 cache, hardware cryptography, or multi-core capability.
What’s this? Two different vendors can build two different Cortex-A35’s with entirely different hardware capabilities, including functions we think of as essential to a modern processor, like the FPU. In typical configurations, ARM is telling users to expect a 6% improvement in integer performance, 16% in browsing performance, 36% in floating point, and 40% in a Geekbench-style MPI test.
The goal is clearly to provide a chip that better suits an evolving IoT ecosystem. By offering low-power devices that include advanced security capabilities like TrustZone, ARM is giving developers some hardware options to help with the goal. Devices-based on the Cortex-A35 are expected to be in-market by the end of this year and also suggested that some companies might apparently choose to use a pair of Cortex-A53 / A35 cores in Big.LITTLE configurations to take full advantage of the efficiency of its low-high-power cores.
ARM in a statement also said that “It will enable ultra-efficient 64-bit compute capabilities for next billion smartphone devices and other rapidly growing markets beyond mobile.” Based on Cortex-A35 chips are purported by late 2016.