Mipsology claims FPGA solution beats GPUs and ASICs for ML

November 17, 2020 //By Nick Flaherty
Mipsology takes on GPUs with AI on FPGAs
Mipsology Zebra tool on Xilinx FPGA beats GPUs and ASICs for ML inference engine efficiency

Machine learning software developer Mipsology has released benchmarks for its Zebra FPGA-based AI accelerator on the MLPerf inference benchmarking.

Running on a Xilinx Alveo U250 accelerator card, Zebra achieved more than twice the peak performance efficiency of other commercial accelerators, whether GPs or dedicated AI edge chips.

“We are very proud that our architecture proved to be the most efficient for computing neural networks out of all the existing solutions tested, and in ML Perf’s ‘closed’ category which has the highest requirements,” said Ludovic Larzul, CEO and founder, Mipsology. “We beat behemoths like NVIDIA, Google, AWS, and Alibaba, and extremely well-funded startups like Groq, without having to design a specific chip and by tapping the power of FPGA reprogrammable logic. Perhaps the industry needs to stop over-relying on only increasing peak TOPS. What is the point of huge, expensive silicon with 400+ TOPS if nobody can use the majority of it?”

Peak TOPS have for years been the standard for measuring computation performance potential, so many assume that more TOPS equal higher performance. However, this fails to take into consideration the real efficiency of the architecture, and the fact that at some point there are diminishing returns. This phenomenon, similar to “dark silicon” for power, occurs when the circuitry can simply not be used because of existing limitations. Zebra has proven to scale along with TOPS, maintaining the same high efficiency while peak TOPS are growing.

With a peak TOPS of 38.3 announced by Xilinx, the Zebra-powered Alveo U250 accelerator card significantly outperformed competitors in terms of throughput per TOPS and ranks among the best accelerators available today. It delivers performance similar to an NVIDIA T4, based on the MLPerf v0.7 inference results, while it has 3.5x less TOPS. Zebra on the same number of TOPS as a GPU would deliver 3.5x more throughput or 6.5x higher than a TPU v3. This performance does not come at the cost of changing the neural network.


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.