DEV Community

gxqwb profile picture

gxqwb

Research notes on quantum computing, AI infrastructure, blockchain systems and high-performance computing — and what they change in everyday life.

Joined Joined on 
Wavelength Multiplexing vs Parallel Optics: The Fiber-Count Versus Wavelength Trade

Wavelength Multiplexing vs Parallel Optics: The Fiber-Count Versus Wavelength Trade

Comments
5 min read
Rear-Door Cooling vs In-Row Units: The Air Path That Wins at 100kW per Rack

Rear-Door Cooling vs In-Row Units: The Air Path That Wins at 100kW per Rack

Comments
6 min read
App-Chain vs Shared Rollup: The Throughput Independence Tax

App-Chain vs Shared Rollup: The Throughput Independence Tax

Comments
5 min read
Test-Time Compute vs More Parameters: Where the Inference Budget Actually Goes

Test-Time Compute vs More Parameters: Where the Inference Budget Actually Goes

Comments
5 min read
Topological Qubits vs Transmon Logical Spins: The Error Budget That Decides Scale

Topological Qubits vs Transmon Logical Spins: The Error Budget That Decides Scale

Comments
5 min read
Immersion Versus Direct-to-Chip: The Heat Flux Economics of Liquid Cooling

Immersion Versus Direct-to-Chip: The Heat Flux Economics of Liquid Cooling

Comments
5 min read
Free-Space Optical Links vs Fibre Trays: The Alignment Budget at the Rack Boundary

Free-Space Optical Links vs Fibre Trays: The Alignment Budget at the Rack Boundary

Comments
6 min read
Absorption Chillers vs Electric Chillers: Cooling Paid for With a Heat Bill

Absorption Chillers vs Electric Chillers: Cooling Paid for With a Heat Bill

Comments
6 min read
Preconfirmations vs L1 Finality: What a Fast Receipt Actually Costs

Preconfirmations vs L1 Finality: What a Fast Receipt Actually Costs

Comments
6 min read
Prefix Caching vs Recomputed Prompts: The Hit-Rate Break-Even

Prefix Caching vs Recomputed Prompts: The Hit-Rate Break-Even

Comments
6 min read
Lattice Surgery vs Braided Defects: The Spacetime Bill for a Logical Gate

Lattice Surgery vs Braided Defects: The Spacetime Bill for a Logical Gate

Comments
6 min read
Polymer Waveguides vs Fiber Pigtails: Where the Optical Link Actually Costs

Polymer Waveguides vs Fiber Pigtails: Where the Optical Link Actually Costs

Comments
5 min read
Flywheel vs Lithium-Ion UPS: The Ride-Through Seconds Nobody Budgets

Flywheel vs Lithium-Ion UPS: The Ride-Through Seconds Nobody Budgets

Comments
5 min read
Intent Solvers vs AMM Routing: Price Improvement Is Not Free

Intent Solvers vs AMM Routing: Price Improvement Is Not Free

Comments
5 min read
Mixture-of-Depths vs Uniform Compute: The Routing Tax on Every Token

Mixture-of-Depths vs Uniform Compute: The Routing Tax on Every Token

Comments
5 min read
Erasure Conversion vs Standard Decoding: Who Pays for the Threshold

Erasure Conversion vs Standard Decoding: Who Pays for the Threshold

Comments
6 min read
Linear-Drive vs DSP-Retimed Optics: The Watts Inside the Pluggable

Linear-Drive vs DSP-Retimed Optics: The Watts Inside the Pluggable

Comments
5 min read
Phase-Change Buffer vs Chilled-Water Tank: Shaving a Compute Peak

Phase-Change Buffer vs Chilled-Water Tank: Shaving a Compute Peak

Comments
5 min read
Trusted Setup vs Transparent Proofs: Who Pays for On-Chain Verification

Trusted Setup vs Transparent Proofs: Who Pays for On-Chain Verification

Comments
5 min read
Pipeline vs Tensor Parallelism: The Bubble Is a Budget Line

Pipeline vs Tensor Parallelism: The Bubble Is a Budget Line

Comments
5 min read
Transmon Qubits vs Neutral Atoms: The Connectivity Bill Behind Error Correction

Transmon Qubits vs Neutral Atoms: The Connectivity Bill Behind Error Correction

Comments
5 min read
Private 5G vs Wi-Fi 7 on the Factory Floor: The Handover Tax

Private 5G vs Wi-Fi 7 on the Factory Floor: The Handover Tax

Comments
4 min read
NVMe-oF vs Local SSD for Checkpoints: The Restart Bill

NVMe-oF vs Local SSD for Checkpoints: The Restart Bill

Comments
5 min read
Optimistic vs ZK Finality: The Seven Days Are Working Capital

Optimistic vs ZK Finality: The Seven Days Are Working Capital

Comments
5 min read
Sparse MoE vs Dense Scaling: The Routing Tax Nobody Budgets

Sparse MoE vs Dense Scaling: The Routing Tax Nobody Budgets

Comments
5 min read
MRAM vs SRAM Last-Level Cache: The Refresh Bill Nobody Quotes

MRAM vs SRAM Last-Level Cache: The Refresh Bill Nobody Quotes

Comments
5 min read
Hydrogen Fuel Cells vs Battery Electric Trucks: The Payload Tax

Hydrogen Fuel Cells vs Battery Electric Trucks: The Payload Tax

1
Comments
5 min read
KV-Cache Offload to NVMe vs Recompute: The TTFT Bill Comes Due

KV-Cache Offload to NVMe vs Recompute: The TTFT Bill Comes Due

Comments
5 min read
3D DRAM vs 4F Scaling: The Capacitor Is the Ceiling

3D DRAM vs 4F Scaling: The Capacitor Is the Ceiling

Comments
5 min read
Co-Packaged Optics vs Pluggable 1.6T: Who Pays When the Laser Dies

Co-Packaged Optics vs Pluggable 1.6T: Who Pays When the Laser Dies

Comments
5 min read
High-NA EUV vs Multi-Patterning: The 2nm Decision Nobody Wants to Price

High-NA EUV vs Multi-Patterning: The 2nm Decision Nobody Wants to Price

Comments
6 min read
TSN vs Plain Ethernet for Robot Cells: The 1 Millisecond Nobody Can Bill For

TSN vs Plain Ethernet for Robot Cells: The 1 Millisecond Nobody Can Bill For

Comments
4 min read
Cryo-CMOS vs Room-Temperature Control: The Wiring Tax on Quantum Computers

Cryo-CMOS vs Room-Temperature Control: The Wiring Tax on Quantum Computers

Comments
5 min read
GDDR7 vs HBM3E for Inference: Bandwidth per Dollar Stops Being the Question

GDDR7 vs HBM3E for Inference: Bandwidth per Dollar Stops Being the Question

Comments
6 min read
DPU Offload vs Host Cores: When the 100G NIC Stops Being Free

DPU Offload vs Host Cores: When the 100G NIC Stops Being Free

Comments
5 min read
InfiniBand vs Ethernet for AI Fabrics: The Congestion Bill Arrives Later

InfiniBand vs Ethernet for AI Fabrics: The Congestion Bill Arrives Later

Comments
5 min read
Confidential Computing's Real Tax: SEV-SNP vs TDX vs H100 Confidential Mode

Confidential Computing's Real Tax: SEV-SNP vs TDX vs H100 Confidential Mode

Comments
4 min read
Spot vs Reserved GPUs: The Utilisation Number That Decides Everything

Spot vs Reserved GPUs: The Utilisation Number That Decides Everything

Comments
4 min read
HNSW vs IVF-PQ: You Are Paying for Recall in RAM

HNSW vs IVF-PQ: You Are Paying for Recall in RAM

Comments
4 min read
MicroVM vs Container for Agent Sandboxes: The Cold-Start Bill Nobody Budgets

MicroVM vs Container for Agent Sandboxes: The Cold-Start Bill Nobody Budgets

Comments
4 min read
Processing In Memory vs Wider Buses: Where the Memory Wall Actually Breaks

Processing In Memory vs Wider Buses: Where the Memory Wall Actually Breaks

Comments
5 min read
Stop Address Poisoning: A Free, Local-Only Tool to Catch Look-Alike Crypto Wallets

Stop Address Poisoning: A Free, Local-Only Tool to Catch Look-Alike Crypto Wallets

1
Comments
2 min read
Layers vs Bits per Cell: Where NAND Density Actually Runs Out

Layers vs Bits per Cell: Where NAND Density Actually Runs Out

Comments 1
4 min read
Speculative Decoding vs Distillation: Two Ways to Buy Latency, One of Them Charges Quality

Speculative Decoding vs Distillation: Two Ways to Buy Latency, One of Them Charges Quality

Comments 1
4 min read
1.58 Bits vs FP8: What Ternary Weights Actually Buy, and What They Break

1.58 Bits vs FP8: What Ternary Weights Actually Buy, and What They Break

Comments
4 min read
Pooled Memory vs Local DIMMs: Why Half Your Rack's RAM Is Stranded

Pooled Memory vs Local DIMMs: Why Half Your Rack's RAM Is Stranded

Comments
4 min read
Compressed Cache vs Bigger Context: The Memory Bill Behind Long Conversations

Compressed Cache vs Bigger Context: The Memory Bill Behind Long Conversations

Comments
4 min read
FlapJax treasury FLAPJAX outflows, 2026-10-28 COT — a chain-only audit

FlapJax treasury FLAPJAX outflows, 2026-10-28 COT — a chain-only audit

Comments
7 min read
Heat From Below: Geothermal vs SMR for Datacenter Baseload

Heat From Below: Geothermal vs SMR for Datacenter Baseload

Comments
4 min read
The Reconfigurable Fabric: Optical Circuit Switching vs Electrical Packet in AI Clusters

The Reconfigurable Fabric: Optical Circuit Switching vs Electrical Packet in AI Clusters

Comments
4 min read
Spikes vs Attention: Where Neuromorphic Chips Actually Save Energy

Spikes vs Attention: Where Neuromorphic Chips Actually Save Energy

Comments
4 min read
The Data Wall: Why Synthetic Data Buys Time but Not Accuracy

The Data Wall: Why Synthetic Data Buys Time but Not Accuracy

Comments
4 min read
Trusted Nodes vs Pure Math: Why Quantum Key Distribution Loses to Post-Quantum Cryptography

Trusted Nodes vs Pure Math: Why Quantum Key Distribution Loses to Post-Quantum Cryptography

Comments
5 min read
Analog In-Memory Computing Versus the Digital NPU: The Energy Per MAC Argument

Analog In-Memory Computing Versus the Digital NPU: The Energy Per MAC Argument

Comments
5 min read
The Reticle Wall: Why Packaging Became the Real Fab Constraint

The Reticle Wall: Why Packaging Became the Real Fab Constraint

Comments
5 min read
800 Volts Versus 48: Why the Rack Power Standard Is Breaking

800 Volts Versus 48: Why the Rack Power Standard Is Breaking

Comments
5 min read
LPDDR6 Versus HBM: The Memory Fight Moves to the Edge

LPDDR6 Versus HBM: The Memory Fight Moves to the Edge

Comments
5 min read
Six Years in the Queue: Why Datacenters Are Building Their Own Power Plants

Six Years in the Queue: Why Datacenters Are Building Their Own Power Plants

Comments
5 min read
The Migration Nobody Budgeted For: Post-Quantum Cryptography in Production

The Migration Nobody Budgeted For: Post-Quantum Cryptography in Production

Comments
5 min read
Twenty Millijoules: What Event-Driven Sensing Changes About Always-On Devices

Twenty Millijoules: What Event-Driven Sensing Changes About Always-On Devices

Comments
5 min read
loading...