FPGA
Field-Programmable Gate Array; a chip whose logic and wiring can be reconfigured in the field via programmable muxes and lookup tables.
As defined in Dwarkesh Patel Podcast - Reiner Pope – Chip design from the bottom up
Where it comes up · 8
- Dwarkesh Patel Podcast - Reiner Pope – Chip design from the bottom up3 claims
- Etched - Building AI Hardware to Make Inference Faster and Cheaper - [Invest Like the Best, EP.480]3 claims
- Intel: Cyclical Recovery or Secular Demise?1 claim
- AMD: How Chips Are Changing1 claim
- Early Stage Investing1 claim
- Dylan Patel - The Infinite Demand for Tokens, Claude Mythos, and Supply Constraints - [Invest Like the Best, EP.469]1 claim
- Sarah Guo - The Power of Conviction - [Invest Like the Best, EP.383]1 claim
- David Kirtley1 claim
Most important claims · 10 of 12Search all claims for “FPGA” →
- 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
- 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
- An FPGA emulates the ASIC programming model in fixed hardware using registers for storage, lookup tables (LUTs) that act as programmable gates, and a large set of muxes in front of every component that select inputs from elsewhere; programming the FPGA 'in the field' amounts to configuring the control bits of every mux to superimpose a particular wiring through the LUTs and registers.Dwarkesh Patel Podcast - Reiner Pope – Chip design from the bottom up
- Because fusion particles move at roughly a million miles per hour (about a meter per microsecond), the entire fusion process plays out in microseconds, requiring the system to be measured and reacted to at microsecond timescales using gigahertz computing, programmable logic (FPGAs), and fiber optics rather than slow wires—because human operators cannot respond at this speed.David Kirtley
- Challenger AI chips face high barriers because their failure modes in large-scale training often appear only at multi-thousand-node scale, which cannot be fully simulated or tested on FPGAs, so buyers need a patient-zero workload at scale to know whether they work.Sarah Guo - The Power of Conviction - [Invest Like the Best, EP.383]
- Many traditional semiconductor funds missed the AI chip companies, and coding experts missed the coding companies, because they could not see that the constraints had changed, since EDA tools and FPGA validation have improved in ways that veterans underweight.Etched - Building AI Hardware to Make Inference Faster and Cheaper - [Invest Like the Best, EP.480]
- Intel's programmable solutions business, the former Altera, and its EUV mask-writing unit, which raised outside capital at roughly a $4 billion valuation for a 20 percent stake, could be monetized or spun out to unlock value.Intel: Cyclical Recovery or Secular Demise?
- Etched parallelized the entire schedule by building software, racks, production lines, and FPGA-based chip emulation before silicon returned, so that bring-up took 40 days, compared with 10 months for another well-known AI chip company to go from silicon to running inference in a rack.Etched - Building AI Hardware to Make Inference Faster and Cheaper - [Invest Like the Best, EP.480]
- AMD bought Pensando for about $2 billion and Xilinx for about $49 billion in 2021 to add special-purpose and FPGA capabilities, preparing for heterogeneous compute, though Jay notes the Xilinx price was high for a company with about $800 million in revenue.AMD: How Chips Are Changing