When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works .
Qualcomm's approach to near-memory compute is pretty much straightforward: the company disaggregates the AI accelerator from the system-on-chip (SoC) and puts it under the LPDDR DRAM stack. The HBC accelerator connects to the LPDDR stack using through-silicon vias to provide maximum bandwidth and capacity without using expensive HBM memory and advanced packaging. Qualcomm does not disclose the actual bandwidth HBC provides, though the company claims that it offers 6X higher bandwidth-per-watt compared to HBM and over 200X capacity compared to on-chip SRAM.
"We have separated the AI accelerator from the XPU and placed the XPU directly beneath a DRAM stack," said Tony Pialis, Executive Vice President and General Manager of Data Center Business at Qualcomm. "This is very important because it gives us the performance advantages of SRAM with the density and capacity of stacked memory. In effect, the congestion associated with HBM is gone. The value to the industry is lower power consumption, less heat, and the elimination of the costly silicon interposer used by HBM solutions. We can also deploy multiple HBC stacks within a single compute device using standard packaging, which delivers a significant performance-per-cost advantage."
Putting DRAM on logic or next to logic is nothing new. All DRAM makers have experimented with near-memory compute architectures, but have failed to make them popular. More recently, GUC, a fabless ASIC design service company, proposed its DRAM-on-Logic (DoL) technology that places one to four DRAM layers on top of logic to get around 5 TB/s of memory bandwidth and offer higher performance than some HBM3E memory subsystems without using expensive advanced packaging and HBM3E stacks.
Since Qualcomm does not disclose actual performance numbers, it is hard to compare its HBC to GUC's offering. However, the biggest caveat about HBC is that Qualcomm does not tell us what the HBC accelerator actually does. In theory, it could be everything: a transformer-specific near-memory engine, a more general array of tensor cores, or some kind of preprocessing logic for AI inference or training.
SK hynix unveils 'iHBM' thermal architecture that cools AI memory at the source
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/tech-industry/artificial-intelligence/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/artificial-intelligence/qualcomm-reveals-hbc-near-memory-ai-architecture-ai250-and-ai350-accelerators-touts-6x-higher-bandwidth-per-watt-compared-to-hbm-200x-capacity-compared-to-on-chip-sram#main
- https://www.tomshardware.com/membership
- AI data center boom hits a human bottleneck — critical skilled labor shortages could slow deployment despite billions in funding
- How Businesses Are Building Specialized AI They Can Trust
- Logitech goes off the rails with Prime Day gaming mouse savings of up to 47% – Eight of its top-tier gaming mice with incredible discounts
- Steam Machines will only come with one 16GB stick of RAM — company may change this to two 8GB sticks in the future, but the first batch of consoles is limited t
- Back in stock! Corsair's tiny touchscreen discount returns during Prime Week — Xeneon Edge 14.5-inch LCD touchscreen hits $199.99 agian
Informational only. No financial advice. Do your own research.