TSMC confirms 'unexploded ordnance' removed from wafer fab construction site Probably a relic of a Japanese WWII naval site TSMC has confirmed that workers were evacuated from one of its construction sites in Taiwan after discovery of an unexploded bomb. "Regarding the suspected unexploded…

Washington, United States — More than a dozen US-based employees of Taiwanese chipmaking giant TSMC have sued the company for apparent discrimination against non-Asian workers, according to a recent lawsuit. The suit alleges that the world’s largest contract manufacturer of chips — used in everything from Apple iPhones to Nvidia’s AI hardware — unfairly favors […]...

Keep on reading: Taiwan chip giant TSMC sued for alleged discrimination

Starting November 11, TSMC plans to stop supplying 7 nm and smaller chips to Chinese companies working on AI processors and GPUs. "The move is reportedly to ensure it remains compliant with US export restrictions," reports The Register. From the report: This will not affect Chinese customers wanting 7 nm chips from TSMC for other applications such as mobile and communications, according to Nikkei, which said the overall impact on the chipmaker's revenue is likely to be minimal. TrendForce further cites another China-based source who claims the move was at the behest of the US Department of Commerce, which informed TSMC that any such shipments should not proceed unless approved and licensed by its BIS (Bureau of Industry and Security). We asked the agency for confirmation. Any moves by the silicon supremo is likely to be out of caution to pre-empt accusations from Washington that it isn't doing enough to prevent advanced technology from getting into the hands of Chinese entities that have been sanctioned. As TrendForce notes, it "highlights the foundry giant's delicate position in the global semiconductor supply chain amid the heating chip war between the world's two superpowers."

Read more of this story at Slashdot.

US probing whether TSMC helped Huawei make AI chips.

Министерство торговли США направило TSMC уведомление о запрете с 11 ноября на поставки в Китай чипов для искусственного интеллекта, сообщает источник CNBC. Речь идет о чипах с техпроцессом 7 нм и меньше, предназначенных для ускорителей ИИ и графических процессоров. Запрет был введен спустя несколько недель после того, как TSMC уведомила Министерство торговли о том, что...

Oct. 16, 2024 — Xsight Labs, a leading fabless semiconductor company providing end-to-end connectivity solutions for next-generation hyperscale, edge, and AI data center networks, has announced the tape-out of the […]

The post Xsight Labs Launches E1 SoC Built on TSMC’s 5nm Tech for AI Workloads appeared first on HPCwire.

PITTSBURGH, Sept. 24, 2024 — Ansys and TSMC today announced a successful pilot with Microsoft that significantly speeds-up the simulation and analysis of silicon photonic components. Together, the companies achieved […]

The post TSMC Collaborates with Ansys and Microsoft to Accelerate Photonic Simulations appeared first on HPCwire.

LONDON and TORONTO, Sept. 30, 2024 — Alphawave Semi, a global leader in high-speed connectivity and compute silicon for the world’s technology infrastructure, has unveiled the availability of the industry’s […]

The post Alphawave Semi and TSMC Collaborate on 3nm UCIe Die-to-Die Subsystem for AI and HPC appeared first on HPCwire.

HSINCHU, Taiwan, Nov. 8, 2024 – TSMC (TWSE: 2330, NYSE: TSM) today announced its net revenue for October 2024. On a consolidated basis, revenue for October 2024 was approximately NT$314.24 […]

The post TSMC Releases October 2024 Revenue Report appeared first on HPCwire.

A US order to TSMC to cut AI chip supplies to China over Huawei sanctions won't cause problems for Apple. However, Taiwan's prohibition of TSMC producing 2-nanometer chips elsewhere could make an impact.

U.S. sanctions against Huawei has caused problems for TSMC over attempts by intermediaries to order certain AI-based chip designs on Huawei's behalf. From Monday, TSMC is suspending shipments of the AI-focused chips to China, on the orders of the United States.

The Department of Commerce imposed export restrictions of select chip designs that were intended to be shipped to China, an unnamed source of Reuters claims. The shipment ban, which kicks in from Monday, affects certain types of chips made with 7-nanometer processes or advanced designs, intended for AI or graphics processing.


Continue Reading on AppleInsider | Discuss on our Forums

The US order, which is being reported for the first time, comes just weeks after TSMC notified the Commerce Department that one of its chips had been found in a Huawei AI processor, as Reuters reported last month.

Staying ahead of the curve is essential to meeting customer needs. Cadence has consistently demonstrated its commitment to innovation, and its latest IP portfolio available on TSMC's 3nm (N3) process is no exception. Today, rapid advancements in AI/ML, hyperscale computing (HPC), and the automotive industry are driving significant changes in technology. Let's explore the impressive array of IP that Cadence offers on this advanced node.

Memory Solutions: High-Speed and Power-Efficient

Cadence's DDR5 12.8G MRDIMM IP supports the highest speed grade Gen2 MRDIMMs and features a fully hardened PHY optimized to the customer's floorplan. The LPDDR5X IP is silicon-proven at 9.6Gbps and is ideal for power-sensitive applications, offering a fully integrated memory subsystem.

GDDR7: Leading the Way in Graphics Memory

Cadence has achieved a significant milestone with the world's first silicon-proven GDDR7 IP, supporting data rates up to 32Gbps. This IP offers the best price/performance ratio for AI interfaces, making it a game-changer in the graphics memory domain.

PCIe and CXL Solutions: Robust and Reliable

Cadence's PCIe 3.0 IP is a mature and production-proven solution available across a wide range of process nodes from 28nm to 3nm. It offers a versatile multi-link architecture for optimum SoC configurability and flexible use cases. The PCIe 6.0 and CXL 3.x solutions are silicon-proven, power-optimized, and highly robust, with jitter-tolerant capabilities. These IP are the only subsystem proven with eight lanes of controller and PHY in silicon, ensuring interoperability with leading test vendors and OEMs.

UCIe PHY: Setting New Standards

The UCIe PHY IP from Cadence are set to be generally available after successful silicon characterization in both standard and advanced package options on the TSMC N3 (3nm) process. These IP demonstrate significantly better power, performance, and area (PPA) metrics than the specifications, with a bit error rate (BER) better than 1E-27 compared to the spec of 1E-15. The power consumption is also notably lower than the spec limit, ensuring a simpler integration with a best-in-class power profile.

112G PHY IP: Pushing the Boundaries of Performance

Cadence's 112G PHY IP are designed to meet the demands of high-speed data transmission. The 112G-ULR PHY IP, characterized in the 3nm process, showcases exceptional performance with support for insertion loss over 45dB at data rates ranging from 1.25Gbps to 112.5Gbps. This IP is optimized for both power and area, making it a versatile choice for various applications. The 112G-VSR/MR PHY IP also stands out with its excellent power and performance metrics, making it ideal for short-reach applications and optical interconnects. Additionally, the 112G PAM4 PHY solutions cater to hyperscale, AI, HPC, and optics applications, featuring a mature DSP-based SerDes architecture with advanced techniques such as reflection cancellation.

Cadence's IP portfolio on TSMC N3 shows innovation and expertise to solve today's design challenges. From high-speed PHY IP to robust PCIe and CXL solutions and advanced memory IP, Cadence continues to lead the way in semiconductor IP development. These solutions not only meet but exceed industry standards, ensuring that customers can confidently achieve their design goals. Stay tuned for more updates on Cadence's groundbreaking advancements in semiconductor technology.

Learn more about Cadence IP and other silicon solutions.

US restrictions on semiconductor tech are spurring the move.

After a chip manufactured by Taiwan Semiconductor Manufacturing Company (TSMC) was found inside a Huawei processor, the U.S. Department of Commerce has ordered the company to halt shipments of advanced chips to Chinese customers, according to a report in Reuters. Huawei faces significant trade restrictions from the U.S., so the pause on shipments is supposed […]

© 2024 TechCrunch. All rights reserved. For personal use only.

OpenAI is working with Broadcom and TSMC to build its first in-house chip designed to support its artificial intelligence systems, per sources

Taiwan Semiconductor Manufacturing Co, whose customers include Apple and Nvidia, has been at the forefront of the march towards AI that has helped it weather the tapering off of pandemic-led demand

The U.S. curbed the export of advanced artificial intelligence chips to China two years ago, citing the need to limit the Chinese military's capabilities

Reports say TSMC notified Chinese chip design companies it would suspend 7 nanometer or below chips for AI and GPU customers beginning Nov. 11

Long-time Slashdot reader UnknowingFool writes: As NVidia and AMD battle it out with their GPUs in consumer gaming, behind the scenes both manufacturers were competing against each for manufacturing capacity with TSMC's lines. It appears that early on in the 7nm line, NVidia lost out as it is rumored their strategy was to use Samsung more only to go back to TSMC when that failed By then TSMC had sold out their capacity to AMD. For their next generation GPUs it appears both NVidia is securing both 5nm early while grabbing as much 7nm as possible.

Read more of this story at Slashdot.

Earning calls sure are interesting! Below is an excerpt from the TSMC Q209 call (transcript from seekingalpha). The discussion revolves around the 40nm yield issues and TSMC's ramp to improving the yield. Dr. Liu really hits on a key element of DFM...(read more)

Dear All,
When I want to start simulation with spectre the error says:
Fatal error: Illegal library definition found in netlist
I set the model file correctly, but I don't know why it errors!
I opened the ADE>>Setup>>Model library
and I tried to modify the path of models file (SCS files)
It gives me "Illegal library definition found in netlist"
Thanks.