Samsung Electronics is reportedly seeking 2027 prices for its next-generation high-bandwidth memory (HBM) that are more than three times the price of its current HBM3E product, industry...
As the number of AI computing transistors integrated within a single CoWoS package rises rapidly, DIGITIMES observes that moving massive volumes of data to compute chips fast...
Nanya Technology is stepping up investment in new factory capacity to expand packaging and testing as some customers move into trial production for specification-based designs. The...
Micron Technology's revenue and profit for the fourth quarter of fiscal 2026 both beat expectations, and the company expects capacity supply to be even tighter in 2027 and 2028 than...
AI-driven memory demand is surging, and Micron has recently accelerated capacity expansion across multiple regions worldwide, including Taiwan, the US, Japan, Singapore, and India...
Micron is using an externally manufactured base die in NVHBM, a custom high-bandwidth memory (HBM) product it is co-developing with Nvidia, as the company bets that customization can...
Micron Technology has sharply raised 2027 prices for high-bandwidth memory (HBM), the stacked DRAM packaged with AI accelerators. The increase comes after a year in which fixed contract...
Applied Materials announced that Kioxia will join its Equipment and Process Innovation and Commercialization (EPIC) Center in Silicon Valley, California. The two companies will collaborate...
Micron Technology's fiscal fourth quarter showed a memory maker whose growth now comes mainly from price rather than volume, with customers committing cash years in advance to secure...
Samsung Electronics' HBM4 ramp is giving its foundry business a timely boost, as rising demand for the memory product translates into more work for the company's 4nm logic lines.
Netlist has begun legal proceedings against Micron and downstream customers Nvidia, Broadcom, and Google to stop them from allegedly using the company's patented high-bandwidth memory...
As HBM approaches half the cost of a GPU-HBM CoWoS package, can memory still be viewed as merely a passive component of AI computing? The answer goes back to the "memory wall," a challenge...
