Vikram Sekar
@vikramskr.bsky.social
I write a newsletter with easy but detailed explainers on semiconductor technology for busy engineers and investors | Views mine | Sr. Staff Engineer at $QCOM
Pinned
Vikram Sekar
@vikramskr.bsky.social
· Dec 5
Vik's Newsletter | Vikram Sekar | Substack
A weekly column with in-depth articles to better understand semiconductor technology. Click to read Vik's Newsletter, by Vikram Sekar, a Substack publication with thousands of subscribers.
open.substack.com
I write a column on Substack with in-depth technical articles on semiconductor technology.
Subscribe for weekly emails!
open.substack.com/pub/viksnews...
Subscribe for weekly emails!
open.substack.com/pub/viksnews...
HBM is hitting a wall.
Costs are high. Capacity is capped. DRAM scaling is over. Yet AI models keep getting bigger.
Sandisk + SK Hynix think they have the answer.
Costs are high. Capacity is capped. DRAM scaling is over. Yet AI models keep getting bigger.
Sandisk + SK Hynix think they have the answer.
High Bandwidth Flash: NAND’s Bid for AI Memory
Can HBF be a new memory tier for AI workloads? Where its limits will show, and what are use-cases for a high capacity memory thats slower than HBM or GDDR.
open.substack.com
September 22, 2025 at 4:02 PM
HBM is hitting a wall.
Costs are high. Capacity is capped. DRAM scaling is over. Yet AI models keep getting bigger.
Sandisk + SK Hynix think they have the answer.
Costs are high. Capacity is capped. DRAM scaling is over. Yet AI models keep getting bigger.
Sandisk + SK Hynix think they have the answer.
September 19, 2025 at 5:23 PM
Interconnects are the hidden backbone of AI datacenters.
A single rack carries ~2 km of copper. Multiply that across hundreds of racks, and the business opportunity becomes clear.
The choice of interconnect defines performance, power, and cost.
A single rack carries ~2 km of copper. Multiply that across hundreds of racks, and the business opportunity becomes clear.
The choice of interconnect defines performance, power, and cost.
September 8, 2025 at 7:31 AM
Interconnects are the hidden backbone of AI datacenters.
A single rack carries ~2 km of copper. Multiply that across hundreds of racks, and the business opportunity becomes clear.
The choice of interconnect defines performance, power, and cost.
A single rack carries ~2 km of copper. Multiply that across hundreds of racks, and the business opportunity becomes clear.
The choice of interconnect defines performance, power, and cost.
Chip design knowledge is tribal.
AI promises to replace engineering grunt work—but machines need documentation to learn.
Problem? Documentation is the one thing engineers hate doing.
The real challenge: how do we make documentation machine-readable and engineer-friendly?
Read more: 👇🏽
AI promises to replace engineering grunt work—but machines need documentation to learn.
Problem? Documentation is the one thing engineers hate doing.
The real challenge: how do we make documentation machine-readable and engineer-friendly?
Read more: 👇🏽
September 4, 2025 at 4:09 AM
Chip design knowledge is tribal.
AI promises to replace engineering grunt work—but machines need documentation to learn.
Problem? Documentation is the one thing engineers hate doing.
The real challenge: how do we make documentation machine-readable and engineer-friendly?
Read more: 👇🏽
AI promises to replace engineering grunt work—but machines need documentation to learn.
Problem? Documentation is the one thing engineers hate doing.
The real challenge: how do we make documentation machine-readable and engineer-friendly?
Read more: 👇🏽
The memory wall is the real bottleneck in AI hardware.
GPUs today can deliver TFLOPS, but they sit idle waiting for data.
What bridges the gap is High Bandwidth Memory (HBM) — the only memory tech that can keep up with modern AI training.
HBM is so critical that it makes up 50–60% of GPU cost.
GPUs today can deliver TFLOPS, but they sit idle waiting for data.
What bridges the gap is High Bandwidth Memory (HBM) — the only memory tech that can keep up with modern AI training.
HBM is so critical that it makes up 50–60% of GPU cost.
September 1, 2025 at 2:45 AM
The memory wall is the real bottleneck in AI hardware.
GPUs today can deliver TFLOPS, but they sit idle waiting for data.
What bridges the gap is High Bandwidth Memory (HBM) — the only memory tech that can keep up with modern AI training.
HBM is so critical that it makes up 50–60% of GPU cost.
GPUs today can deliver TFLOPS, but they sit idle waiting for data.
What bridges the gap is High Bandwidth Memory (HBM) — the only memory tech that can keep up with modern AI training.
HBM is so critical that it makes up 50–60% of GPU cost.
A jet broke the sound barrier with 50 engineers and 1/10th the usual budget.
Chip design still needs armies of people and billions. Why?
Outdated workflows. Clunky tools. Rigid hiring.
Boom Supersonic built its own software platform and leapt ahead.
Who will build the chip industry’s “mkChip”? 👇
Chip design still needs armies of people and billions. Why?
Outdated workflows. Clunky tools. Rigid hiring.
Boom Supersonic built its own software platform and leapt ahead.
Who will build the chip industry’s “mkChip”? 👇
August 22, 2025 at 12:44 AM
A jet broke the sound barrier with 50 engineers and 1/10th the usual budget.
Chip design still needs armies of people and billions. Why?
Outdated workflows. Clunky tools. Rigid hiring.
Boom Supersonic built its own software platform and leapt ahead.
Who will build the chip industry’s “mkChip”? 👇
Chip design still needs armies of people and billions. Why?
Outdated workflows. Clunky tools. Rigid hiring.
Boom Supersonic built its own software platform and leapt ahead.
Who will build the chip industry’s “mkChip”? 👇
Literally the best picture of High Bandwidth Memory (HBM) on Chip-on-Wafer-on-Substrate (CoWoS) packaging I have ever seen.
August 19, 2025 at 10:51 AM
Literally the best picture of High Bandwidth Memory (HBM) on Chip-on-Wafer-on-Substrate (CoWoS) packaging I have ever seen.
Nvidia’s AI chips lean on TSMC’s CoWoS packaging — where GPUs + HBM sit on an interposer mounted to an ABF-based substrate.
ABF is the industry standard but also a major bottleneck — and the U.S. has no domestic source.
ABF is the industry standard but also a major bottleneck — and the U.S. has no domestic source.
August 18, 2025 at 2:03 AM
Nvidia’s AI chips lean on TSMC’s CoWoS packaging — where GPUs + HBM sit on an interposer mounted to an ABF-based substrate.
ABF is the industry standard but also a major bottleneck — and the U.S. has no domestic source.
ABF is the industry standard but also a major bottleneck — and the U.S. has no domestic source.
Chip engineers feel in a rut after almost a decade on the job.
Here's an actionable plan to get out of it. 👇🏽
First, why engineers feel stuck:
→ You do a tiny task in a huge flow
→ When impact is unclear, motivation drops and you feel replaceable
Here's an actionable plan to get out of it. 👇🏽
First, why engineers feel stuck:
→ You do a tiny task in a huge flow
→ When impact is unclear, motivation drops and you feel replaceable
August 14, 2025 at 4:25 AM
Chip engineers feel in a rut after almost a decade on the job.
Here's an actionable plan to get out of it. 👇🏽
First, why engineers feel stuck:
→ You do a tiny task in a huge flow
→ When impact is unclear, motivation drops and you feel replaceable
Here's an actionable plan to get out of it. 👇🏽
First, why engineers feel stuck:
→ You do a tiny task in a huge flow
→ When impact is unclear, motivation drops and you feel replaceable
GPT-5 is here. 🥳 With sloppy graphs, hype and disappointment.
We know it has trillions of parameters, but where does it come from?
Today's deep dive post covers everything you need to know.
You will even make your own GPT-5 estimates at the end of the post.
We know it has trillions of parameters, but where does it come from?
Today's deep dive post covers everything you need to know.
You will even make your own GPT-5 estimates at the end of the post.
August 8, 2025 at 5:43 AM
GPT-5 is here. 🥳 With sloppy graphs, hype and disappointment.
We know it has trillions of parameters, but where does it come from?
Today's deep dive post covers everything you need to know.
You will even make your own GPT-5 estimates at the end of the post.
We know it has trillions of parameters, but where does it come from?
Today's deep dive post covers everything you need to know.
You will even make your own GPT-5 estimates at the end of the post.
7-rules for high impact engineering careers:
That no-one ever tells you...
That no-one ever tells you...
August 7, 2025 at 3:17 PM
7-rules for high impact engineering careers:
That no-one ever tells you...
That no-one ever tells you...
The 2024 Stack Overflow developer survey puts Matlab as the least admired programming language among 50 different ones.
Lower than Cobol, Visual Basic, Prolog and Fortran.
Read full post. 👇🏽
www.viksnewsletter.com/p/the-declin...
Lower than Cobol, Visual Basic, Prolog and Fortran.
Read full post. 👇🏽
www.viksnewsletter.com/p/the-declin...
The Decline of MATLAB: What Engineers Should Learn Instead
A frank look at why Python and Rust is the future of the hardware programming stack.
www.viksnewsletter.com
August 7, 2025 at 1:54 AM
The 2024 Stack Overflow developer survey puts Matlab as the least admired programming language among 50 different ones.
Lower than Cobol, Visual Basic, Prolog and Fortran.
Read full post. 👇🏽
www.viksnewsletter.com/p/the-declin...
Lower than Cobol, Visual Basic, Prolog and Fortran.
Read full post. 👇🏽
www.viksnewsletter.com/p/the-declin...
The safest path in engineering can also be the most crowded.
Early in my career, I focused on RF while most went into digital design. It wasn’t the obvious choice—but it gave me a differentiator when wireless took off in the early 2010s.
Early in my career, I focused on RF while most went into digital design. It wasn’t the obvious choice—but it gave me a differentiator when wireless took off in the early 2010s.
August 5, 2025 at 3:23 PM
The safest path in engineering can also be the most crowded.
Early in my career, I focused on RF while most went into digital design. It wasn’t the obvious choice—but it gave me a differentiator when wireless took off in the early 2010s.
Early in my career, I focused on RF while most went into digital design. It wasn’t the obvious choice—but it gave me a differentiator when wireless took off in the early 2010s.
Solid-State PAs vs. Traveling Wave Tube Amplifiers
Pros and Cons. 👇🏽
Tube amplifiers have been the mainstay of power generation in SATCOM.
The efficiency and output power of tubes was unmatched by solid state technology.
Until GaN arrived.
Read more here:
www.viksnewsletter.com/p/why-the-fu...
Pros and Cons. 👇🏽
Tube amplifiers have been the mainstay of power generation in SATCOM.
The efficiency and output power of tubes was unmatched by solid state technology.
Until GaN arrived.
Read more here:
www.viksnewsletter.com/p/why-the-fu...
August 5, 2025 at 4:37 AM
Solid-State PAs vs. Traveling Wave Tube Amplifiers
Pros and Cons. 👇🏽
Tube amplifiers have been the mainstay of power generation in SATCOM.
The efficiency and output power of tubes was unmatched by solid state technology.
Until GaN arrived.
Read more here:
www.viksnewsletter.com/p/why-the-fu...
Pros and Cons. 👇🏽
Tube amplifiers have been the mainstay of power generation in SATCOM.
The efficiency and output power of tubes was unmatched by solid state technology.
Until GaN arrived.
Read more here:
www.viksnewsletter.com/p/why-the-fu...
Here are the answers (with questions) to yesterday's pub quiz on my newsletter, along with short explanations 🥂
www.viksnewsletter.com/p/semi-pub-q...
www.viksnewsletter.com/p/semi-pub-q...
🍻 Semi Pub Quiz #1 Answers
With short explanations and further reading materials.
www.viksnewsletter.com
August 1, 2025 at 1:25 AM
Here are the answers (with questions) to yesterday's pub quiz on my newsletter, along with short explanations 🥂
www.viksnewsletter.com/p/semi-pub-q...
www.viksnewsletter.com/p/semi-pub-q...
This week's post is a semiconductor pub quiz! 🍻
How many can you answer?👇🏽
Answers will be published, along with a short explanation and references tomorrow.
So make sure you subscribe to the newsletter to get it in your email.
Good luck!
www.viksnewsletter.com/p/semi-pub-q...
How many can you answer?👇🏽
Answers will be published, along with a short explanation and references tomorrow.
So make sure you subscribe to the newsletter to get it in your email.
Good luck!
www.viksnewsletter.com/p/semi-pub-q...
🍻 Semi Pub Quiz #1
It's hump day, and who says you can't have an online pub quiz.
www.viksnewsletter.com
July 31, 2025 at 2:16 AM
This week's post is a semiconductor pub quiz! 🍻
How many can you answer?👇🏽
Answers will be published, along with a short explanation and references tomorrow.
So make sure you subscribe to the newsletter to get it in your email.
Good luck!
www.viksnewsletter.com/p/semi-pub-q...
How many can you answer?👇🏽
Answers will be published, along with a short explanation and references tomorrow.
So make sure you subscribe to the newsletter to get it in your email.
Good luck!
www.viksnewsletter.com/p/semi-pub-q...
SATCOM is leaving vacuum tubes behind.
For decades, traveling-wave tubes were the only way to generate >100W RF output.
Enter GaN.
GaN-based SSPAs are now rivaling TWTs — delivering high power, efficiency, and reliability.
Read it here:
www.viksnewsletter.com/p/why-the-fu...
For decades, traveling-wave tubes were the only way to generate >100W RF output.
Enter GaN.
GaN-based SSPAs are now rivaling TWTs — delivering high power, efficiency, and reliability.
Read it here:
www.viksnewsletter.com/p/why-the-fu...
July 28, 2025 at 12:46 AM
SATCOM is leaving vacuum tubes behind.
For decades, traveling-wave tubes were the only way to generate >100W RF output.
Enter GaN.
GaN-based SSPAs are now rivaling TWTs — delivering high power, efficiency, and reliability.
Read it here:
www.viksnewsletter.com/p/why-the-fu...
For decades, traveling-wave tubes were the only way to generate >100W RF output.
Enter GaN.
GaN-based SSPAs are now rivaling TWTs — delivering high power, efficiency, and reliability.
Read it here:
www.viksnewsletter.com/p/why-the-fu...
Turns out that you can now put TSVs in EMIBs.
Whoever created this image impresses me more than putting a TSV through a piece of silicon.
Check it more on IEEE Spectrum.
https://spectrum.ieee.org/intel-advanced-packaging-for-ai
Whoever created this image impresses me more than putting a TSV through a piece of silicon.
Check it more on IEEE Spectrum.
https://spectrum.ieee.org/intel-advanced-packaging-for-ai
June 12, 2025 at 1:35 PM
Turns out that you can now put TSVs in EMIBs.
Whoever created this image impresses me more than putting a TSV through a piece of silicon.
Check it more on IEEE Spectrum.
https://spectrum.ieee.org/intel-advanced-packaging-for-ai
Whoever created this image impresses me more than putting a TSV through a piece of silicon.
Check it more on IEEE Spectrum.
https://spectrum.ieee.org/intel-advanced-packaging-for-ai
I'm in SF attending the International Microwave Symposium.
If you'll be attending too, let me know. We'll chat at the conference.
If you're in the area and want to grab a beverage, hit me up.
If you'll be attending too, let me know. We'll chat at the conference.
If you're in the area and want to grab a beverage, hit me up.
June 12, 2025 at 2:35 AM
I'm in SF attending the International Microwave Symposium.
If you'll be attending too, let me know. We'll chat at the conference.
If you're in the area and want to grab a beverage, hit me up.
If you'll be attending too, let me know. We'll chat at the conference.
If you're in the area and want to grab a beverage, hit me up.
I'm contemplating a deep-dive post on the role of GaN/SiC for AI data center power.
Along the lines of what Navitas is working on.
Good idea? Or is power not such a big deal at the moment?
Along the lines of what Navitas is working on.
Good idea? Or is power not such a big deal at the moment?
June 11, 2025 at 1:35 PM
I'm contemplating a deep-dive post on the role of GaN/SiC for AI data center power.
Along the lines of what Navitas is working on.
Good idea? Or is power not such a big deal at the moment?
Along the lines of what Navitas is working on.
Good idea? Or is power not such a big deal at the moment?
I was reading a paper on use of glass substrates for 6G in the latest IEEE Microwave Magazine
The first chart is how we will need 10-100 Gbps (!) for immersive AR/VR experience!!
The first chart is how we will need 10-100 Gbps (!) for immersive AR/VR experience!!
June 11, 2025 at 2:35 AM
I was reading a paper on use of glass substrates for 6G in the latest IEEE Microwave Magazine
The first chart is how we will need 10-100 Gbps (!) for immersive AR/VR experience!!
The first chart is how we will need 10-100 Gbps (!) for immersive AR/VR experience!!
After I posted my article on the use of AI for RFIC design, a founder of a startup just out of stealth contacted me to say how their product does exactly that for MMIC design.
I'll be meeting them at IMS next week to see their demo. Exciting!
If you missed my post on AI for RFIC, link in comments.
I'll be meeting them at IMS next week to see their demo. Exciting!
If you missed my post on AI for RFIC, link in comments.
June 10, 2025 at 1:35 PM
After I posted my article on the use of AI for RFIC design, a founder of a startup just out of stealth contacted me to say how their product does exactly that for MMIC design.
I'll be meeting them at IMS next week to see their demo. Exciting!
If you missed my post on AI for RFIC, link in comments.
I'll be meeting them at IMS next week to see their demo. Exciting!
If you missed my post on AI for RFIC, link in comments.
Turns out hooking up chiplets in a honeycomb-ish pattern in an SoC gives the best throughput somehow
June 10, 2025 at 2:35 AM
Turns out hooking up chiplets in a honeycomb-ish pattern in an SoC gives the best throughput somehow
Time to upgrade to USB sticks.
June 9, 2025 at 1:35 PM
Time to upgrade to USB sticks.
7 unwritten rules for a high-impact engineering career in the chip industry (or anywhere) 👇🏽
Stuff I learnt the hard way over 15 years in the industry.
Link in comment. 👇🏽
Stuff I learnt the hard way over 15 years in the industry.
Link in comment. 👇🏽
June 9, 2025 at 2:35 AM
7 unwritten rules for a high-impact engineering career in the chip industry (or anywhere) 👇🏽
Stuff I learnt the hard way over 15 years in the industry.
Link in comment. 👇🏽
Stuff I learnt the hard way over 15 years in the industry.
Link in comment. 👇🏽