Cutting CapEx, Not Capacity

‘The cloud’ has been an industry buzz word for some time now, and while the initial focus was on data storage and sharing – and spawned the likes of Dropbox – ‘cloud computing’ is currently the latest trend.

For instance, Amazon’s cloud platform, Amazon Web Services (AWS), gives users access to servers and a range of applications. Storage is available as before but so too now are dedicated relational databases; which in Amazon’s case is provided through a different service.

Enterprise businesses are taking advantage of cloud computing platforms for a number reasons. These include pay-as-you-go (as opposed to investing considerable CapEx), speed and flexibility (resources and storage can be made available quickly), and one is spared the headache of maintaining a mass of IT hardware and keeping on top of software license renewals.

Earlier this year, Amazon announced EC2 (Elastic Compute Cloud) F1, a compute instance with FPGAs that users can program to perform hardware accelerations. The F1 instance includes an FPGA developer Amazon Machine Image (AMI) which includes a development environment with scripts and tools for code compilation and design simulation.

It is expected the primary users of EC2 F1 will be software developers, working on complex and compute-intensive algorithms for which FPGAs lend themselves particularly well. For instance, High Performance Computing will increasingly exploit FPGA technology.

But let’s not forget one of the most important roles that FPGAs have been playing in our industry – EDA. For a number of decades they have served as hardware accelerators for ASIC prototyping purposes.

The big shift
As designs grow in size and complexity, verification emphasis shifts from simulation to emulation. With FPGAs already making their way onto the cloud for other hardware acceleration tasks – provided as pay-as-you-use services – it is logical for these versatile devices to be available for ASIC emulation too. The idea is to remotely access leased equipment for the emulation of hardware and/or the design verification of pre-silicon software. That could include simulation optimization algorithms to achieve high performance in VHDL, Verilog, SystemVerilog, SystemC and mixed-language simulations, along with support the latest verification libraries, including UVM.

Aldec’s plan is to use Amazon’s AWS, giving users access to Aldec’s hardware emulation platform cloud. They will be able to login using the Secure SSH protocol using either a terminal or a graphical desktop. It will then be possible to use the AMI to prepare a design for emulation. When that is done the user will then be able to connect via a secure VPN to the HES Server based in Aldec’s facility, which will comprise a number of HES boards on which the emulations will run.

While Amazon’s FPGA Developer AMI is undoubtedly geared for hardware acceleration – within a variety of emerging markets – HES Cloud effectively provides remote access to a high performance emulation platform and a functional verification tool which are both geared for the highly specialized task of ASIC and SoC emulation.