Author's Latest Posts


GPU Or ASIC For LLM Scale-Up?


The CEOs of OpenAI, Anthropic, and xAI share a strikingly similar vision — AI's progress is exponential, it will change humanity, and its impact will be greater than most people expect. This is more than just speculation. The market for AI, and its value, are real today: A human developer with GitHub CoPilot codes 55% faster with AI. GPT-4 scores 88th percentile on the LSAT vs. 50t... » read more

Chiplets: A Technology, Not A Market


Chiplets are big business, and that business is growing. The total chiplet market today is roughly $40 billion annually. Chiplets account for roughly 15% of TSMC's revenues, and they account for about 25% of all DRAMs. All of the major AI/HPC semiconductor companies (NVIDIA, AMD, Marvell, Broadcom) and the major hyper scalers (Amazon, Google, etc) are looking to chiplets to build superior... » read more

eFPGA Gives You FPGA Speed And Density At Much Less Cost And Power


FPGAs are everywhere in all types of systems for their flexibility and quick time to market. As your volumes grow and you consider an ASIC to cut cost and power, you can now incorporate an embedded FPGA to continue to give you flexibility for the parts of your chip that need to adapt for changing standards, improving algorithms and customer optimizations. If you are an SoC designer, you c... » read more

eFPGA Architectural Improvements That Lower Test Cost And Increase Quality


More than 40 chips have been licensed to use EFLX eFPGA and >20 chips are working in silicon. Big customers like Renesas are planning high volume families of chips using embedded FPGA. As a result, we have gained extensive experience and knowledge in almost 10 years of doing eFPGA especially in production test for cost reduction and reliability improvement. eFPGA DFT and MBIST for high q... » read more

Use Cases And Value Proposition Of eFPGA


Flex Logix EFLX eFPGA is the first eFPGA that enables a customer to match the performance of FPGAs from AMD/Xilinx and Intel (in the same process node) with the same density (LUTs/mm2). EFLX eFPGA has been in use with customers now for more than 5 years, hardware and software. More than 40 chips have been licensed to use EFLX eFPGA and more than 20 chips are working in silicon. Big customers... » read more

The Next Generation Of Embedded FPGA


EFLX eFPGA has been in use in SoCs for more than 5 years, hardware and software. More than 40 chips have been licensed to use EFLX eFPGA and more than 20 chips are working in silicon. Big customers like Renesas are planning high volumes and families of chips using eFPGA. As we have worked with customers our architecture has evolved from EFLX Gen 1.0 to Gen 2.0, 2.1, 2.2, 2.3 and now in 2023 ... » read more

Connect To Any Chip With Programmable GPIO


Your MCU/SoC today may have several options for GPIO connections: UART, SPI, I2C. But there are dozens of variations and kinds of GPIO interface protocols: you don’t have enough pins to provide all of them as hardwired options. As a result, a significant number of your customers either can’t use your chip because they need to connect to another with a GPIO interface you don’t support, ... » read more

The Importance Of Metal Stack Compatibility For Semi IP


Every foundry and every node is different, but for every foundry/node there are multiple supported metal stacks. Some chips use a lot more metal layers than others. A common rule of thumb is each metal layer increases wafer cost 10%. So, a chip with 5 more metal layers than another will cost 50%+ more. The most complex, high performance chips, including performance FPGAs, typically use AL... » read more

Micro FPGAs And Embedded FPGAs


When people hear “FPGA” they think “big, expensive, power hungry.”  But it doesn’t need to be that way. Renesas has announced their Forge FPGA family. Details are at their website and in one of the many articles that covered their press release. Forge FPGAs show that FPGAs don’t have to be big, power hungry, and expensive. Forge FPGAs are tiny, draw standby current measure... » read more

Integrating 16nm FPGA Into 28/22nm SoC Without Losing Speed Or Flexibility


Systems companies like FPGA because it gives parallel processing performance that can outdo processors for many workloads and because it can be reconfigured when standards, algorithms, protocols or customer requirements change. But FPGAs are big, burn a lot of power and are expensive. Customers would like to integrate them into their adjacent SoC if possible. Dozens of customers are now u... » read more

← Older posts