https://open-source-silicon.dev logo
Channels
aa
abcc
activity
adiabatonauts
analog-design
announce
announcements
b2aws
b2aws-tutorial
bag
basebands
beagleboard
bluetooth
board-respin
cadence-genus
cadence-innovus
cadence-spectre
cadence-virtuoso
caravan
caravel
caravel-board
chilechipmakers
chip-yard
chipignite
chipignite2206q_stanford_bringup
chisel
coalition-for-digital-environmental-sustainability
community_denmark_dtu
containers
courses
design-review
design-services
dffram
digital-design
digital-electronics-learners
discord-mods
dynamic-power-estimation
efabless
electric
events
fasoc
fault
foss-asic-tools
fossee-iitb-esim
fossee-iitb-google-sky130
fpga
funding
fuserisc
general
generative-ai-silicon-challenge
genius-vlsi
gf180
gf180mcu
hardware-beginners
help-
ieee-sscs-cac-23
ieee-sscs-dc-21q3
ieee-sscs-dc-22
ieee-sscs-dc-23
ihp-sg13g2
images
infiniband
j-core
japan-region
junk
klayout
latam_vlsi
layouteditor
lvs
lvs-analysis
magic
magical
maker-projects
maker-zone
microwatt
mpw-2-silicon
mpw-one-clean-short
mpw-one-silicon
neuro-mem
nydesign
open_pdks
open-pdk
openadiabaticlogic
openfpga
openhighqualityresonators
openlane
openlane_cloudrunner
openlane-development
openocd
openpositarithmetic
openpower
openram
openroad
opentitan
osu
pa-test-chip
paracells
pd-openlane-and-sky130
picosoc
pll
popy_neel
power
private-shuttle
rad-lab-silicon
radio
rdircd
reram
researchers
rf-mmw-design
rios
riscv
sdram
serdes
shuttle
shuttle-precheck
shuttle-status
silicon-photonics
silicon-validation
silicon-validation-private
sky130
sky130-ci
sky130-pv-workshop
sky65
sky90
skywater
sram
stdcelllib
strive
swerv
system-verilog-learners
tapeout-job
tapeout-pakistan
team-awesome
timing-closure
toysram
travis-ci
uvm-learners
vendor-synopsys
venn
verification-be
verification-fe
verilog-learners
vh2v
vhdl
vhdl-learners
vliw
vlsi_verilog_using_opensource_eda
vlsi_verilog_using_opensoure_eda
vlsi-learners-group
vlsi101
waveform-viewers
xls
xschem
xyce
zettascale
Powered by
Title
k

Kunal

01/28/2023, 3:40 PM
Limitations of GPT-like Models in IC Design Process and need of opensource PDKs/VSD-HDP ChatGPT, as a language model, may not be able to replace VLSI physical design engineers, STA engineers, analogue designers, and physical verification engineers for several reasons. One reason is that the IC design process is highly complex, which is quite evident from past VSD-HDP participants and requires a deep understanding of the underlying technology, and process nodes, as well as the ability to make decisions based on trade-offs between different design constraints. GPT-like models can assist in automating certain tasks, but they are not yet able to replicate the level of expertise and decision-making capabilities of human engineers. Another reason is that the PDKs (Process Design Kits) used in the IC design process are often proprietary and not available to the public. This makes it difficult for GPT-like models to access the necessary information to perform the tasks required in IC design. This is where there is a need for opensource PDKs like SKY130 and there is a huge demand for people who understand production-grade PDKs, which is a core topic in VSD-HDP Additionally, VLSI design is an iterative process, and it can take multiple rounds of design, simulation, and verification to arrive at the final product. GPT-like models are not able to perform these tasks as well as human engineers, as they cannot use their intuition and experience to make design decisions that can save time and resources in the process. This is the exact point where we need open-source EDA tools and even more users who understand open-source and proprietary EDA tools usage. VSD-HDP currently focuses on the open-source EDA toolchain, which is the best place to start and is completely under your control. Furthermore, physical design engineers, STA engineers, analogue designers, and physical verification engineers are responsible for ensuring that the IC design meets the required specifications and constraints. This requires a deep understanding of the underlying technology, as well as the ability to use specialized software and tools to verify the design. GPT-like models may not have the same level of expertise and understanding of the technology and tools used in the IC design process. This is where we need a lot of open-source IPs, which again is a core area of focus in VSD-HDP. Finally, it is worth mentioning that the use of GPT-like models in VLSI physical design and STA tasks is a rapidly evolving field, and it is possible that in the future, these models may become more advanced and capable of taking on a greater role in the IC design process. However, it is unlikely that they will fully replace human engineers shortly. Learn more in the upcoming VSD-HDP and embrace AI as it's going to be the next cutting-edge solution which would help VLSI engineers. Here's the registration link https://www.vlsisystemdesign.com/hdp/ Your best bet to remain irreplaceable in the VLSI job market - Learn and innovate as much as you can using opensource All the best and happy learning
🌍 1