ASIC
Application-specific integrated circuit; specialized hardware built to solve the mining hash puzzle millions of times faster than general-purpose computers.
As defined in ms_13
Where it comes up · 18
- Nvidia v. Google, Scaling Laws, and the Economics of AI7 claims
- AMD: How Chips Are Changing6 claims
- Gavin Uberti - Real-Time AI & The Future of AI Hardware - [Invest Like the Best, EP.356]5 claims
- Andrew Homan & Chris Miller - Redefining Semiconductor Progress - [Invest Like the Best, EP.396]4 claims
- Full Tilt Investing3 claims
- Dwarkesh Patel Podcast - Jensen Huang – TPU competition, why we should sell chips to China, & Nvidia’s supply chain moat3 claims
- How to Identify Interesting Markets2 claims
- Early Stage Investing2 claims
and 10 more
Most important claims · 10 of 45Search all claims for “ASIC” →
- Modern AI and ML can take unstructured data such as vision, natural language, and speech and make it usable in typical program logic, which previously was impossible, pushing software into the physical world and driving different hardware and software designs including ASICs.Martin Casado - The Past, Present, and Future of Digital Infrastructure - [Invest Like the Best, EP.280]
- The largest internet companies, the Super 7 including Google, Facebook, Amazon, Microsoft, Baidu, Alibaba and Tencent, are designing their own chips, and along with a few others they consume about 70 percent of server CPU output, which makes customers into competitors.AMD: How Chips Are Changing
- Anything expressible in an FPGA can be expressed in an ASIC at roughly an order of magnitude lower cost and better energy efficiency, but the first FPGA costs ~$10,000 while the first ASIC costs ~$30 million due to tape-out; so FPGAs make business sense when you need deterministic latency, fast runtime, and high parallelism but will change the workload frequently (e.g. monthly) and don't want to repay the tape-out cost.Dwarkesh Patel Podcast - Reiner Pope – Chip design from the bottom up
- The roughly 10x cost penalty of an FPGA versus an ASIC comes from the LUT: a four-way AND that takes three AND gates in an ASIC requires a 32-gate LUT (a 16-input, 1-bit mux) to implement, because a truth table lists every input combination whereas placing actual gates and wires is far more concise.Dwarkesh Patel Podcast - Reiner Pope – Chip design from the bottom up
- GPU mining hardware can be redeployed to rendering or AI workloads if crypto markets change, reducing hardware investment risk, whereas ASIC hardware only mines one coin and can become nearly worthless.Full Tilt Investing
- Hyperscalers are building custom chips purpose-built for specific workloads such as search or social media feeds because this can significantly lower their cost to serve, as their NVIDIA GPU spend grows toward ever-larger totals.Andrew Homan & Chris Miller - Redefining Semiconductor Progress - [Invest Like the Best, EP.396]
- Compute hardware has swung from general-purpose CPUs to GPUs to specialized ASICs and back toward specialized hardware, as Bitcoin mining acted as a petri dish for extreme demand for efficient compute that now resembles machine learning demand.Early Stage Investing
- ML accelerators are fundamentally a software problem, not a hardware problem; companies like Graphcore, Cerebras, TensTorrent and Groq built good chips but terrible software, and if you can't write a Torch-level performance stack on Nvidia GPUs down to the driver, you certainly can't write one for your more specialized chip.George Hotz #3
- It takes at least three generations to produce a competitive custom chip; TPU v1 was an achievement just to ship, and TPUs only became vaguely competitive around TPU v3 or v4.Nvidia v. Google, Scaling Laws, and the Economics of AI
- Bitcoin mining moved from laptop CPUs to GPUs, which are orders of magnitude better at parallel hashing, and then to ASICs built only to compute SHA-256, which are orders of magnitude better again. This escalating arms race pushed mining into large farms next to power plants.Hash Power – Part 1