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
High Bandwidth Flash (HBF). A NAND-based memory tier promising 8–16x the density of HBM.
If it works, GPUs could ship with terabytes of memory instead of hundreds of GB. First samples land 2026.
The real question: does HBF complement HBM—or disrupt it?
If it works, GPUs could ship with terabytes of memory instead of hundreds of GB. First samples land 2026.
The real question: does HBF complement HBM—or disrupt it?
September 22, 2025 at 4:02 PM
High Bandwidth Flash (HBF). A NAND-based memory tier promising 8–16x the density of HBM.
If it works, GPUs could ship with terabytes of memory instead of hundreds of GB. First samples land 2026.
The real question: does HBF complement HBM—or disrupt it?
If it works, GPUs could ship with terabytes of memory instead of hundreds of GB. First samples land 2026.
The real question: does HBF complement HBM—or disrupt it?
This week’s deep dive:
how GPUs, racks, and entire datacenters are wired together — and why copper vs. optics is the next big frontier.
www.viksnewsletter.com/p/a-beginner...
how GPUs, racks, and entire datacenters are wired together — and why copper vs. optics is the next big frontier.
www.viksnewsletter.com/p/a-beginner...
A Beginner’s Guide to Interconnects in AI Datacenters
Understanding performance and trade-offs shaping interconnect choices in AI datacenters.
www.viksnewsletter.com
September 8, 2025 at 7:31 AM
This week’s deep dive:
how GPUs, racks, and entire datacenters are wired together — and why copper vs. optics is the next big frontier.
www.viksnewsletter.com/p/a-beginner...
how GPUs, racks, and entire datacenters are wired together — and why copper vs. optics is the next big frontier.
www.viksnewsletter.com/p/a-beginner...
Only three companies make it: SK Hynix, Samsung, and Micron.
And a Chinese competitor: CXMT.
This week, I break down why HBM is so hard to manufacture — from fundamentals to cutting-edge bonding. 👇🏽
www.viksnewsletter.com/p/why-is-hbm...
And a Chinese competitor: CXMT.
This week, I break down why HBM is so hard to manufacture — from fundamentals to cutting-edge bonding. 👇🏽
www.viksnewsletter.com/p/why-is-hbm...
Why is HBM so Hard to Manufacture?
An in-depth look into the incredible engineering behind the memory used in GPUs for AI accelerators.
www.viksnewsletter.com
September 1, 2025 at 2:45 AM
Only three companies make it: SK Hynix, Samsung, and Micron.
And a Chinese competitor: CXMT.
This week, I break down why HBM is so hard to manufacture — from fundamentals to cutting-edge bonding. 👇🏽
www.viksnewsletter.com/p/why-is-hbm...
And a Chinese competitor: CXMT.
This week, I break down why HBM is so hard to manufacture — from fundamentals to cutting-edge bonding. 👇🏽
www.viksnewsletter.com/p/why-is-hbm...
Only a few companies dominate the EDA tool market- hard to disrupt the space
August 22, 2025 at 2:15 AM
Only a few companies dominate the EDA tool market- hard to disrupt the space
That’s why Nvidia’s exploration of CoWoP is interesting. By mounting interposers directly to PCB platforms, CoWoP could bypass ABF entirely.
But the question remains: can PCB makers hit the density, yield, and reliability that AI accelerators demand?
But the question remains: can PCB makers hit the density, yield, and reliability that AI accelerators demand?
August 18, 2025 at 2:03 AM
That’s why Nvidia’s exploration of CoWoP is interesting. By mounting interposers directly to PCB platforms, CoWoP could bypass ABF entirely.
But the question remains: can PCB makers hit the density, yield, and reliability that AI accelerators demand?
But the question remains: can PCB makers hit the density, yield, and reliability that AI accelerators demand?
How you benefit:
→ You build a rare skill mix, restore meaning, and open doors
→ All without risky job-hopping
Read for the complete blueprint:👇🏽
www.viksnewsletter.com/p/how-to-esc...
→ You build a rare skill mix, restore meaning, and open doors
→ All without risky job-hopping
Read for the complete blueprint:👇🏽
www.viksnewsletter.com/p/how-to-esc...
How to Escape the Corporate Rut for Midcareer Chip Engineers
Simple ideas to keep your paycheck, grow skills, and enjoy the work again.
www.viksnewsletter.com
August 14, 2025 at 4:25 AM
How you benefit:
→ You build a rare skill mix, restore meaning, and open doors
→ All without risky job-hopping
Read for the complete blueprint:👇🏽
www.viksnewsletter.com/p/how-to-esc...
→ You build a rare skill mix, restore meaning, and open doors
→ All without risky job-hopping
Read for the complete blueprint:👇🏽
www.viksnewsletter.com/p/how-to-esc...
How to learn effectively?
→ Pick one adjacent skill
→ Use what companies offer: tools, experts, tuition support → Run a 6-week sprint: 3 hours/week, one mentor chat/week, one demo
→ Request a 10–20% trial assignment to apply the skill
→ Ship proof: a design note, a small block, or a script
→ Pick one adjacent skill
→ Use what companies offer: tools, experts, tuition support → Run a 6-week sprint: 3 hours/week, one mentor chat/week, one demo
→ Request a 10–20% trial assignment to apply the skill
→ Ship proof: a design note, a small block, or a script
August 14, 2025 at 4:25 AM
How to learn effectively?
→ Pick one adjacent skill
→ Use what companies offer: tools, experts, tuition support → Run a 6-week sprint: 3 hours/week, one mentor chat/week, one demo
→ Request a 10–20% trial assignment to apply the skill
→ Ship proof: a design note, a small block, or a script
→ Pick one adjacent skill
→ Use what companies offer: tools, experts, tuition support → Run a 6-week sprint: 3 hours/week, one mentor chat/week, one demo
→ Request a 10–20% trial assignment to apply the skill
→ Ship proof: a design note, a small block, or a script
The cycle is common:
→ Early excitement, then sameness, then burnout risk.
→ Promotions rarely solve the core issue
Apply a three-step plan:
→ Identify your career phase
→ Identify your personal engineer archetype
→ Run focused learning sprints
→ Early excitement, then sameness, then burnout risk.
→ Promotions rarely solve the core issue
Apply a three-step plan:
→ Identify your career phase
→ Identify your personal engineer archetype
→ Run focused learning sprints
August 14, 2025 at 4:25 AM
The cycle is common:
→ Early excitement, then sameness, then burnout risk.
→ Promotions rarely solve the core issue
Apply a three-step plan:
→ Identify your career phase
→ Identify your personal engineer archetype
→ Run focused learning sprints
→ Early excitement, then sameness, then burnout risk.
→ Promotions rarely solve the core issue
Apply a three-step plan:
→ Identify your career phase
→ Identify your personal engineer archetype
→ Run focused learning sprints
For paid subscribers:
→ Parameter counting using Google’s BERT-Base
→ Detailed look at GPT2/GPT3
→ An educated guess at GPT4
→ Speculating on GPT5
→ References
Downloadable Google Sheet you can use to make your own parameter estimates and speculate on GPT-5!
See comment 👇🏽
→ Parameter counting using Google’s BERT-Base
→ Detailed look at GPT2/GPT3
→ An educated guess at GPT4
→ Speculating on GPT5
→ References
Downloadable Google Sheet you can use to make your own parameter estimates and speculate on GPT-5!
See comment 👇🏽
August 8, 2025 at 5:43 AM
For paid subscribers:
→ Parameter counting using Google’s BERT-Base
→ Detailed look at GPT2/GPT3
→ An educated guess at GPT4
→ Speculating on GPT5
→ References
Downloadable Google Sheet you can use to make your own parameter estimates and speculate on GPT-5!
See comment 👇🏽
→ Parameter counting using Google’s BERT-Base
→ Detailed look at GPT2/GPT3
→ An educated guess at GPT4
→ Speculating on GPT5
→ References
Downloadable Google Sheet you can use to make your own parameter estimates and speculate on GPT-5!
See comment 👇🏽
For free subscribers:
→ Birth of the Transformer
→ Tokens, Embeddings and Vocabulary
→ QKV, Context Window, and Batch Sizes
→ Attention Calculation Methods
→ Decoder Transformer Architecture
→ Birth of the Transformer
→ Tokens, Embeddings and Vocabulary
→ QKV, Context Window, and Batch Sizes
→ Attention Calculation Methods
→ Decoder Transformer Architecture
August 8, 2025 at 5:43 AM
For free subscribers:
→ Birth of the Transformer
→ Tokens, Embeddings and Vocabulary
→ QKV, Context Window, and Batch Sizes
→ Attention Calculation Methods
→ Decoder Transformer Architecture
→ Birth of the Transformer
→ Tokens, Embeddings and Vocabulary
→ QKV, Context Window, and Batch Sizes
→ Attention Calculation Methods
→ Decoder Transformer Architecture
5. Your visibility is your own responsibility
6. Cross boundaries without stepping on toes
7. Spot CYA but don’t get sucked in
Read more here:
www.viksnewsletter.com/p/7-unwritte...
6. Cross boundaries without stepping on toes
7. Spot CYA but don’t get sucked in
Read more here:
www.viksnewsletter.com/p/7-unwritte...
7 Unwritten Rules for High-Impact Engineering Careers
What they don’t teach you about thriving in technical organizations, but will define your success.
www.viksnewsletter.com
August 7, 2025 at 3:17 PM
5. Your visibility is your own responsibility
6. Cross boundaries without stepping on toes
7. Spot CYA but don’t get sucked in
Read more here:
www.viksnewsletter.com/p/7-unwritte...
6. Cross boundaries without stepping on toes
7. Spot CYA but don’t get sucked in
Read more here:
www.viksnewsletter.com/p/7-unwritte...