Hot Chips 2026: Micron warns HBM wafer penalty is widening with every generation
At Hot Chips, Samsung’s Sangwook Han laid out a three-phase HBM roadmap that ends in zHBM , which is DRAM stacked directly on top of the processor rather than beside it on an interposer. Samsung projects about 70% less I/O power usage than HBM5 with roughly 2.3x the bandwidth of a four-stack HBM4E system, with zHBM’s stacks limited to about four-high due to heat, at around 100W less. This would require wafer-on-wafer hybrid copper bonding and tight co-design between DRAM and SoC teams. SK hynix’s Jaesik Lee, VP of package engineering, said on Aug. 23 that hybrid bonding won’t be ready for HBM4E, leaving HBM5 as the earliest point. Counterpoint Research expects full-scale HBM production with the technique around 2029–2030.
PieceMakers offers a different version. Instead of the GPU-plus-HBM 2.5D layout, it bonds the DRAM stack directly onto the processor, wafer-on-wafer, with hybrid bonding instead of microbumps. This fits far more connections with the finer pitch, improving bandwidth, and the shorter path reduces both latency and power consumption. The company puts its wafer-on-wafer product at more than 2 TB/s per layer with latency under 20ns, the company figures, but the target is more capacity than SRAM at a lower cost and power than HBM. PieceMakers is not doing the TSV or hybrid bonding itself, as this is handled by the customer’s logic wafer foundry, Ting added. This custom service promises a 2027 date against Samsung's undated roadmap end and SK hynix's HBM5-at-the-earliest timing. Nvidia and Samsung have each, in their own way, settled the architecture question, with the open question being the customer.
Lee also said that yield is the biggest hurdle to wafer-on-wafer mass production. The repair architecture has to be designed in, with testing before bonding, after bonding, and then after logic integration. Lee’s own example was 80% yield per layer, at which four layers come out at about 41% and eight at 17%. Our recently-published hybrid bonding state of play covers the process side in more detail.
This better puts into perspective why the company sells repair and known-good-die IP as much as it does bandwidth. It’s also why an IP-and-royalty model fits the strategy — yield IP is portable across customers while a bandwidth number is not.
For PieceMakers, AI revenue remains primarily NRE until there is a first named customer, with the first volume program expected in 2027 at the earliest. Ting said that Nanya’s Q3 2026 results, which come in late October, will gauge the PieceMakers gain and reveal further financial information. SK hynix’s hybrid-bonding timing, which targets HBM5 at the earliest, is the current benchmark, although its 16- and 20-layer memory stacks are a separate problem from a few DRAM layers on a logic wafer. Qualcomm may also describe its relationship with PieceMakers more formally.
PieceMakers is likely to end up as an IP licensor with a small number of accelerator customers and turnkey volume through Nanya and Formosa Advanced Technologies. The technology risk is the foundry’s and the customer’s, which is why PieceMakers’ design-fee model works. PieceMakers is expected to benefit from a 2027–2028 ramp, later than Ting’s 2027. If the largest HBM maker won’t bond its own memory this way before HBM5, PieceMakers’ own 2027 date is the one it must meet.
Shane Downing Social Links Navigation Freelance Reviewer Shane Downing is a Freelance Reviewer for Tom’s Hardware US, covering consumer storage hardware.
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/semiconductors/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/semiconductors/piecemakers-bets-edge-ai-devices-will-diverge-from-reliance-on-hbm-custom-designed-memory-fuses-dram-stack-directly-to-the-processor-using-hybrid-bonding#main
- https://www.tomshardware.com/my-account
- AI-induced memory shortage is changing how devices are built, Fairphone says memory now 60% of materials cost — smaller laptop and phone makers are redesigning
- Denuvo sues anonymous game cracker ‘voices38’ over alleged DRM circumvention — seeks damages after Anti-Tamper protections bypassed in 26 games
- Solo dev enables running CUDA on AMD hardware in Windows, getting multiple CUDA libraries running on a gaming Radeon RX 9060 XT GPU in Windows — CUDA-exclusive
- Devastated father says his 9-year-old son spent $118,000 on YouTube ad campaigns for his Minecraft channel using a company credit card — bill racked up in just
- Minecraft Legacy gets rewritten in C++ for PS2 and Wii ports — code is tuned so it works well even on the PS2’s meager 32MB of RAM
Informational only. No financial advice. Do your own research.