Hot Chips 2026: d-Matrix stacks AI accelerator directly on custom DRAM for 100 TB/s per card — TSMC 4nm compute die bonded face-to-face at a 36-micron pitch on top of a custom-designed die
Tom's Hardware
Published
Read the full story at Tom's HardwareOriginal
d-Matrix presented Raptor, which it calls the first 3D DRAM accelerator for generative inference, showing a TSMC 4nm compute die bonded face-to-face at a 36-micron pitch on top of a custom-designed DRAM die.
Have a take on this story? Discuss it on Gab — no account needed to read, free to join to post.
Discuss on GabWant a second read? Ask Gab AI to analyze this story — private, no account needed to start.
Ask Gab AIReading the article
💡 AI analysis provides alternative perspectives on current events
