Mirabilis Design unveils the first rapid prototyping platform for Artificial Intelligence Processors and Applications
Architecting new AI/ML processors and designing Data Center and Edge Devices using AI
Sunnyvale, CA., Nov. 14, 2019 – Mirabilis Design announced the immediate release of VisualSim AI Evaluator for quick architecture exploration of Artificial Intelligence (AI) and Machine Learning. This AI evaluator combines analog, digital, power and network modeling to select the right architecture for the accelerator and the right configuration of accelerators and memories for a target application. The modeling effort in VisualSim has demonstrated good insight into the operation, generated alternate processing modes, helped create better memory access schemes, made parallelization effective at a lower cost, and narrowed the list of required parallel accelerators. VisualSim AI Evaluator can be used for the design of data center systems, edge devices and AI processors/ accelerators.
Using VisualSim AI Evaluator, architects and though-leaders can design the custom accelerators, select partitioning, and determine the implementation, topology, system sizing and memory access. The design criteria are based on use-cases and traffic input; and the generated statistics provides insight into deadlocks, system bottlenecks and meeting of the requirements. AI architecture exploration is a new field of study and to help designers come up to speed, Mirabilis Design is conducting a Webinar on November 28th 2019 on the topic "Strategies, trends and exploration of AI architectures" by experts from renowned AI processor companies. To register, visit: https://www.mirabilisdesign.com/sign-up/
This VisualSim AI Evaluator contains four different modeling technologies, 90 million events per second Discrete-Event Simulator, interactive visualization environment and machine-readable documentation output. The modeling technologies include:
- Library of analog components, memories, queues, bus topologies, multi-core, GPUs, FPGAs, ASICs, CPUs, accelerators, and High-Performance Computing (HPC) structures
- Task graph modeling components to emulate the application
- Analysis tools for task tracing, deadline monitors, memory access. Data overload, efficiency analyzer
- Use-case and traffic generators to emulate the environment and input streams.
VisualSim AI Evaluator is fully integrated with the industry-standard VisualSim Architect, a system-level modeling and simulation software that is used to evaluate the timing, throughput, power consumption and functional correctness of the design. Systems designed in VisualSim include x86 processor, GPU, FPGA bus topology, adventure cameras, radars, flight avionics, HPC, automotive electronic control units and aerospace networks.
VisualSim AI Evaluator is available now and is on display at SemIsrael 2019 on November 19, 2019.
The AI Evaluator is an add-on to VisualSim Architect 19.4, which was released in November 2019. This product is used extensively in designing products from aircraft avionics to adventure cameras; and processors to safety critical systems. VisualSim Architect 19.4 is available on Windows, Linux, and MAC OS.
About Mirabilis Design
Mirabilis Design, a Silicon Valley company, designs cutting edge software solutions that identify and eliminate risks in product performance. Its flagship product, VisualSim Architect is a system-level modeling, simulation, and analysis environment that relies on libraries and application templates to vastly improve model construction and time required for analysis. The seamless design framework facilitates designers to work on a design together, cohesively, to meet an intermeshed time and power requirements. It is typically used for maximum results, early in the design stage, parallel to the development of the product's written specification. It precedes implementation stages - RTL, software code, or schematic – rendering greater design flexibility.
|
Related News
- Silicon Valley Company unveils revolutionary Artificial Intelligence (AI) driven Processor Generator
- BittWare selects EdgeCortix's SAKURA-I AI Processors as its Edge Focused Artificial Intelligence Acceleration Solution
- GreenWaves Technologies Unveils GAP8, the Industry's Lowest Power IoT Application Processor, Enabling Groundbreaking Embedded Artificial Intelligence at the Very Edge
- Cadence Advances Pervasive Intelligence at the Edge with Next-Generation Extensible Tensilica Processor Platform
- Tenstorrent Selects SiFive Intelligence X280 for Next-Generation AI Processors
Breaking News
- Frontgrade Gaisler Unveils GR716B, a New Standard in Space-Grade Microcontrollers
- Blueshift Memory launches BlueFive processor, accelerating computation by up to 50 times and saving up to 65% energy
- Eliyan Ports Industry's Highest Performing PHY to Samsung Foundry SF4X Process Node, Achieving up to 40 Gbps Bandwidth at Unprecedented Power Levels with UCIe-Compliant Chiplet Interconnect Technology
- CXL Fabless Startup Panmnesia Secures Over $60M in Series A Funding, Aiming to Lead the CXL Switch Silicon Chip and CXL IP
- Cadence Unveils Arm-Based System Chiplet
Most Popular
- Cadence Unveils Arm-Based System Chiplet
- CXL Fabless Startup Panmnesia Secures Over $60M in Series A Funding, Aiming to Lead the CXL Switch Silicon Chip and CXL IP
- Esperanto Technologies and NEC Cooperate on Initiative to Advance Next Generation RISC-V Chips and Software Solutions for HPC
- Eliyan Ports Industry's Highest Performing PHY to Samsung Foundry SF4X Process Node, Achieving up to 40 Gbps Bandwidth at Unprecedented Power Levels with UCIe-Compliant Chiplet Interconnect Technology
- Arteris Selected by GigaDevice for Development in Next-Generation Automotive SoC With Enhanced FuSa Standards
E-mail This Article | Printer-Friendly Page |