HomeChiplets & UCIeDay 10
DAY 10 · PHASE 2 — ADVANCED PACKAGING

Power Delivery Across Chiplets
TSVs, Backside Power & Active Interposers

By EcrioniX · Updated July 2026

Phase 2 closes where every other challenge in this course ultimately gets paid for: power. Every chiplet needs current delivered to it with minimal resistive loss, through the same TSVs and interposers already covered — and the industry is now attacking the problem from two directions at once: smarter package-level power grids, and moving power delivery to the back of the die itself.

The Same TSVs, Carrying Current Instead of Data

Day 6 introduced TSVs as the vertical interconnect carrying signal through a silicon interposer. The same physical structure also carries power — from the package substrate, up through interposer TSVs, into each chiplet's own on-die power grid. This means the power delivery network (PDN) design decisions made at the interposer level directly compete with signal routing for the same TSV budget, and getting this wrong shows up as IR drop — voltage sag under load that can push a chiplet's supply below the level it needs to operate reliably.

Optimizing the Interposer Power Grid — Small Changes, Real Gains

Published chiplet/interposer power-delivery co-design studies show that IR drop responds strongly to fairly modest design changes:

Design changeMeasured result
+5.52% interposer PDN occupancy, plus extra PDN grids27.17% improvement in overall IR drop
Bridge-chip design, 9 bundled 8µm-diameter TSVsIR drop only ~1% higher than a standalone (non-chiplet) reference
Decoupling capacitors added to bridge-chip/interposerSignificant reduction in high-frequency supply ripple

Figures per published chiplet/interposer power-delivery co-design research.

The takeaway from these numbers: a well-designed chiplet power grid doesn't have to cost you meaningfully more IR drop than a monolithic reference design — but you have to actually design for it, rather than treating the interposer's power grid as an afterthought behind the signal routing.

Active Interposers — Moving the Regulator Closer to the Load

A passive interposer (Day 6) does nothing but carry TSVs and RDL wiring. An active interposer goes further, embedding integrated voltage regulators (IVRs) directly into the interposer itself, physically shortening the distance between the power supply and the power-hungry logic above it. One published study measured a 73.7% reduction in maximum IR drop compared to a passive interposer baseline — a dramatic result that reflects a simple physical truth: the further current has to travel through resistive metal before reaching the load, the more voltage it loses along the way. Put the regulation closer to the load, and that loss shrinks sharply.

Backside Power Delivery — Attacking the Problem at the Die Level

A parallel, complementary industry shift moves power delivery off the frontside of the die entirely. Backside Power Delivery Networks (BSPDN) relocate the entire power grid to the wafer's backside, connecting to transistors through dedicated vias, while freeing the frontside exclusively for denser signal routing — the same "get the two jobs out of each other's way" logic that motivates separating power and signal at the interposer level, just applied one layer down, inside the die itself.

🔵
Intel PowerViaPaired with GAA transistors on the 20A/18A nodes; 18A entered mass production (Panther Lake) in early 2026
🟡
TSMC Super Power RailSkips the N2 (2nm) generation; targeted for the A16 process around Q3 2026; connects directly to transistor source/drain

Intel's own reported results for 18A PowerVia in production: roughly 30% IR-drop reduction, a 6% frequency uplift, and 5–10% better standard cell utilization — utilization improves because power routing no longer competes with signal routing for frontside metal layers. Separately, broader backside-power-delivery research across sub-5nm nodes has reported around 10% IR-drop reduction as a more general figure, underscoring that Intel's specific implementation and results are on the strong end of what backside power delivery can achieve.

Two techniques solving one problem at two scales: active interposers and optimized package-level PDN attack IR drop at the chiplet-to-package boundary. Backside power delivery attacks the same fundamental problem — resistive loss between power source and transistor — at the within-die boundary. A cutting-edge chiplet package increasingly uses both simultaneously.

🎯 Day 10 Key Takeaways

Frequently Asked Questions

How does power reach each chiplet in a package?
Power travels from the package substrate up through through-silicon vias (TSVs) in the interposer, which carry power vertically alongside signal TSVs, before reaching each chiplet's own on-die power grid. The interposer's power delivery network shares the same physical structure covered on Day 6, just carrying current instead of data.
How much can interposer PDN design affect IR drop?
Published optimization studies show meaningful gains from fairly small design changes: one study achieved a 27.17% improvement in overall IR drop by increasing interposer PDN occupancy by only 5.52% and adding extra PDN grids, while a bridge-chip design using nine bundled 8-micron TSVs kept IR drop only about 1% higher than a standalone (non-chiplet) reference case.
What is an active interposer and why does it help power delivery?
An active interposer embeds integrated voltage regulators (IVRs) directly into the interposer itself, rather than leaving the interposer purely passive. This shortens the physical distance between the power supply and the power-demanding logic, and one published study showed a 73.7% reduction in maximum IR drop compared to a passive interposer baseline.
What is backside power delivery (BSPDN)?
Backside power delivery moves a die's entire power delivery network to the wafer's backside, connecting to transistors through dedicated vias while freeing the frontside exclusively for signal routing. Intel's version, PowerVia, entered mass production on the 18A node in early 2026 and delivered roughly 30% IR-drop reduction, a 6% frequency uplift, and 5-10% better standard cell utilization. TSMC's competing Super Power Rail is targeted for the A16 process around Q3 2026.
What is the difference between Intel PowerVia and TSMC Super Power Rail?
Both are backside power delivery implementations, but TSMC's Super Power Rail connects power directly to the transistor's source and drain, a more direct contact scheme than Intel's PowerVia. Intel adopted backside power earlier, pairing PowerVia with its 20A and 18A nodes and GAA transistors, while TSMC is introducing it later, skipping its N2 (2nm) generation in favor of the A16 node.