Nvidia has resolved an issue with its latest Blackwell chip and anticipates resuming production in the fourth quarter, as stated by its CEO during a recent earnings call.
Earlier reports of the glitch raised concerns among enterprise IT leaders.
“We made a modification to the Blackwell GPU mask to enhance our production yields,” Nvidia’s CEO Jensen Huang explained. “The production ramp for Blackwell is set to kick off in the fourth quarter and will extend into fiscal year 2026. We anticipate Blackwell revenue to reach several billion dollars in Q4. Additionally, Hopper shipments are projected to grow in the latter half of fiscal 2025.” Nvidia’s fiscal 2025 started on January 29, 2024.
“The adjustment to the mask is finalized,” he continued. “No functional modifications were required. Consequently, we are currently distributing functional samples of Blackwell, Grace Blackwell, and various system configurations. Approximately 100 different Blackwell-based systems have been constructed and were showcased at Computex. We are now preparing our ecosystem to begin sampling these systems. The functionality of Blackwell remains unchanged, and we plan to initiate production in the fourth quarter.”
The CEO added: “Blackwell will start shipping out in billions of dollars at the end of this year.”
Huang did not discuss the nature of the problem nor of the fix.
Technology analyst Jeff Kagan said he doubts the delay will have any meaningful impact on enterprise IT operations.
“We have learned to always expect these kinds of glitches. Fortunately, they don’t stop progress and growth, although they can slow things down from time to time,” Kagan said. “In the end, this is not a long-term problem (as much as) one of many short-term issues that will be resolved.”
In the analyst call, Huang shared his insights on the future of enterprise computing and the extensive impact AI will have on hardware and computing operations.
“We have reduced the cost of training complex language models and deep learning significantly, enabling the creation of massive scale models with multitrillion parameters. These can be pretrained on almost the entire corpus of world knowledge, allowing the model to learn human language representation, encode knowledge into its neural networks, and develop reasoning. This has propelled the generative AI revolution,” stated Huang.
The CEO further discussed that the economic foundations of IT infrastructures are evolving swiftly.
“With every doubling of a model’s size, the dataset for training it needs to more than double, leading to a quadratic increase in the computational power required to build the model. Consequently, it is foreseeable that future models will require up to 40 times more computing power than previous versions. We must continually enhance performance significantly to reduce the energy used and the costs involved,” he explained.
Welcome to DediRock, your trusted partner in high-performance hosting solutions. At DediRock, we specialize in providing dedicated servers, VPS hosting, and cloud services tailored to meet the unique needs of businesses and individuals alike. Our mission is to deliver reliable, scalable, and secure hosting solutions that empower our clients to achieve their digital goals. With a commitment to exceptional customer support, cutting-edge technology, and robust infrastructure, DediRock stands out as a leader in the hosting industry. Join us and experience the difference that dedicated service and unwavering reliability can make for your online presence. Launch our website.