Raja Koduri Teams with Jim Keller at Tenstorrent to Build the Best Computing Platform for AI and Software 2.0

Image: Intel

SquareBionic has shared a presentation that can confirm Raja Koduri will be joining the board of Tenstorrent, a Toronto-based artificial intelligence and machine learning technology company that specializes in building AI processors for machine learning workloads. Koduri, who left Intel recently after serving as its executive vice president and chief architect, can be seen standing next to Jim Keller in a photo that Keller shared this week, a veteran who has been described by some as being a CPU engineering god for his contributions that include the development of AMD’s Zen architecture. Keller currently serves as the CEO of Tenstorrent, which was founded in February 2018.

From a Tenstorrent FAQ page:

Tenstorrent processors comprise a grid of cores known as Tensix cores. Our processors are capable of executing small and large tensor computations efficiently. Network communication hardware is present in each processor, and they talk with one another directly over networks, instead of through DRAM. Compared to GPUs, our processors are easier to program, scale better, and excel at handling run-time sparsity and conditional computation.

Tenstorrent’s processor cores are known as Tensix cores. Each Tensix core includes 5 RISC processors, an array math unit for tensor operations, a SIMD unit for vector operations, hardware for accelerating network packet operations and compression/decompression, and 1-2 megabytes of SRAM.

As model parameters grow along with a corresponding growth in computational volume, Tenstorrent applies proprietary heuristics to dynamically determine which parts need to be computed (pruning out the rest). This improves inference latency and allows the training to converge quicker.

Join the discussion for this post on our forums...

Recent News