Ljubisa Bajic and Jim Keller: Tenstorrent | Ian Interviews #6
With all the money flowing into AI processor startups right now, trying to tell them apart can be tricky. Most are aiming for inference, others for training, and some are in the middle, all looking for that edge to put them above the rest. Tenstorrent believes it has the solution for both inference, training, and can be scaled from 16 chips to 16 million.
Ljubisa Bajic is a veteran of the semiconductor industry, working extensively in VLSI design and debug coupled with extensive accelerator architecture and software experience. Ljubisa spent a decade inside AMD as an ASIC architect working on power management and DSP design, before a spell at NVIDIA as a senior architect, and then back to AMD for a couple of years working with Jim on the hardware that powers AMD’s balance sheet today. He left AMD to start Tenstorrent with two other co-founders in 2016, has raised $240m in three rounds of funding, and created three generations of processors, the latest of which is shipping this year. At least two more generations are on the way.
Jim Keller is a bum who hits electric rocks with spanners.
Written version of the interview on AnandTech: https://www.anandtech.com/show/16709/an-interview-with-tenstorrent-ceo-ljubisa-bajic-and-cto-jim-keller
1:10 Q1: What is Tenstorrent?
1:52 Q2: What made Jim invest?
3:14 Q3: Basement in Toronto?
4:38 Q4: Just co-founders to start?
5:30 Q5: Why start a startup?
7:14 Q6: First impression of Ljubisa
9:19 Q7: First impression of Jim
13:18 Q8: Jim’s way or the highway?
15:25 Q9: Comic Sans in talks
16:30 Q10: Confidence in Ljubisa in 2016
19:46 Q11: Proof-of-Concept
24:00 Q12: Inference vs Training
25:49 Q13: Tenstorrent’s Unique Value
28:45 Q14: Adding flexibility in models
29:37 Q15: Customer interest in Greyskull
31:28 Q16: Most Promising Architecture?
35:33 Q17: Multi-chip for software
36:44 Q18: Off-chip vs on-chip
37:56 Q19: 75W per chip vs 300W?
40:05 Q20: Low hanging fruit
40:55 Q21: Is a 2D-mesh still relevant?
46:25 Q22: Roadmap for AI to move 3D?
47:05 Q23: Wormhole’s limits as AI grows
48:26 Q24: Roadmap direction
50:01 Q25: Si-Five Vector Units
51:00 Q26: Die area hit with X280?
51:39 Q27: Mix Generations of Hardware
52:52 Q28: Foundry relationships
53:23 Q29: Tenstorrent Funding
56:56 Q30: The Jim Keller Effect
59:40 Q31: Assisting customers with engineers
1:04:45 Q32: Ljubisa’s now the boss
1:06:51 Q33: Jim in sales
1:10:12 Q34: Jim in the Nuts and Bolts
1:12:55 Q35: Rockstar status
1:14:21 Q36: Staying at Tenstorrent?
1:15:28 Q37: Will Jim Ever Retire?
1:16:35 Q38: Tenstorrent is Hiring
1:18:22 Q39: Locations and Places to work
1:19:10 Q40: Cost of Cables and networking
1:21:22 Q41: Silicon Photonics?
Welcome to the TechTechPotato (c) Dr. Ian Cutress
Ramblings about things related to Technology from an analyst
Patreon helps support this channel: https://www.patreon.com/TechTechPotato
Also available through Patreon is special 1-on-1 consulting for the financial services industry!
Many thanks to the Patrons!
Support the channel by hitting that subscribe button, or using our Amazon affiliate link. Please note that TTP may receive a commission if you purchase anything through these links
Intel Core i7-11700K (8C/16T): https://geni.us/SreZM
Intel Core i5-11600K (6C/12T): https://geni.us/T4WG
Intel Core i5-11400F (6C/12T): https://geni.us/6UISblx
AMD Ryzen 9 5950X (16C/32T): https://geni.us/5950X
AMD Ryzen 9 5900X (12C/24T): https://geni.us/5900X
AMD Ryzen 7 5800X (8C/16T): https://geni.us/5800X
AMD Ryzen 5 5600X (6C/12T): https://geni.us/5600X
Intel Core i9-10900K (10C/20T): https://geni.us/Bench2020-10900k
Intel Core i7-10700K (8C/16T): https://geni.us/Bench2020-10700K
AMD Ryzen 9 3950X (16C/32T): https://geni.us/Bench2020-3950x
AMD Ryzen 7 3700X (8C/16T): https://geni.us/Bench2020-3700x
AMD Ryzen 5 3600 (6C/12T): https://geni.us/d08ThJ4
Follow Ian on Twitter at http://twitter.com/IanCutress
Follow TechTechPotato on Twitter at http://twitter.com/TechTechPotato
#techtechpotato #tenstorrent #jimkeller