Recent #DRAM news in the semiconductor industry

12 months ago
➀ A new 3D imaging technique reveals key details of the magnetic skyrmion, a nanoscale object with potential for new microelectronic devices with high data storage capacity and low power consumption. ➁ Researchers at Lawrence Berkeley National Laboratory have created 3D X-ray images to characterize the spin orientations within skyrmions, which could lead to more efficient quantum computing and data storage devices. ➂ The study demonstrates the importance of understanding the 3D spin texture of skyrmions for the development of advanced spintronic devices.
3D ICDRAMData StorageNVIDIAQuantum Computing
about 1 year ago
➀ Researchers from Queen Mary University of London have developed new nanocomposite films from starch, offering a sustainable alternative to petroleum-based materials; ➁ The films are made from abundant natural polymer starch and highly conductive MXene, with potential applications in electronics and sensing; ➂ The nanocomposites can be tailored for various uses, including wearable technology and healthcare, and are biodegradable.
2nm3D IC3nmAIAI ChipAI PCAMDArmAsusChipletCoolingDRAMDellEDAEMIBEUVGDDRGPUGaNHBMHPCInfineonLaptopLinuxMicrochipNPUNVIDIAPCIePrivacyRaspberry PiSSDSoftwareSwitchTIautomotivecpucybersecuritygamingiosmemorymonitorsemiconductor
about 1 year ago
➀ The story is about an ambitious startup that entered the DRAM, SRAM, E2PROM, and microprocessor markets; ➁ The company built two fabs and produced successful memories and a unique microprocessor that was not adopted by major applications; ➂ Despite spawning many startups that adopted its approach, the company could not survive independently and was taken over. The moral is that uniqueness can be a negative.
DRAMSRAMStartupsemiconductor
about 1 year ago
➀ The UK has developed the world's first computer-controlled gas cutting machine, marking a significant step towards automation in shipyards; ➁ The machine, built by British Oxygen-Ferranti, can reduce steel plate cutting time by at least 50% compared to conventional methods; ➂ The technology is applicable to structural engineering, locomotive building, and atomic reactor construction.
3D ICDRAMEDAHPCNVIDIASK Hynix
about 1 year ago
➀ Google is rumored to switch to TSMC's N3E process for Tensor G5; ➁ The report also clarifies that Google has chosen not to use 2nm technology for Tensor G6; ➂ The move could impact the competition in the AI and smartphone chip markets.
2nm3D IC3nmAIAI PCAI chipAMDASUSArmCPUChipletDRAMDellEDAGDDRGPUGaNHBMHPCInfineonLinuxNPUNVIDIAPCIePrivacyRaspberry PiSEMICONDUCTORSK hynixSSDSwitchTITSMCautomotivecoolingcybersecuritygamingiOSlaptopmemorymicrochipmonitorsoftware
about 1 year ago
➀ Korea’s September semiconductor exports reached a record high of $13.63 billion, up 36.3% year-on-year. Memory exports grew 60.7% year-on-year and 20% month-on-month to $8.72 billion. SoC exports rose 5.2% year-on-year to $4.37 billion. ➁ The overall Information and Communication Technology exports in September 2024 increased by 24% year-on-year to $22.36 billion. ➂ HBM had a significant impact on DRAM export values, and TrendForce forecasts that memory price growth will slow in Q4.
DRAMEUVHBMICKoreaSoCmemorysemiconductor
about 1 year ago
➀ Arm is exploring the feasibility of running LLMs on mobile devices; ➁ Arm's optimization techniques for LLMs on mobile; ➂ The importance of practical use cases for LLMs in mobile devices
2nm3D IC3nmAIAI PCAI chipAMDASUSArmCPUChipletDRAMDellEDAEMIBEUVGDDRGPUGaNHBMHPCInfineonLinuxMobileNPUNVIDIAPCIePrivacyRaspberry PiSEMICONDUCTORSK hynixSSDSwitchTIautomotivecoolingcybersecuritygamingiOSlaptopmemorymicrochipmonitorsoftware
about 1 year ago
➀ China's DRAM manufacturer Changxin Memory Technologies is expected to have 11% of the global DRAM capacity this year; ➁ Changxin's capacity has increased from 120k wpm at the end of 2023 to 160k wpm in Q1 2024, aiming for 200k wpm by the end of the year; ➂ This rapid expansion could lead to oversupply and a decrease in ASPs for older DRAM types.
DRAM
about 1 year ago
➀ The research on hybrid memory combines the density of DRAM with the speed of SRAM, receiving funding from CHIPS and the Science Act. The hybrid gain cell (HGC) memory research is one of the projects of the California-Pacific-Northwest AI Hardware Center, which will receive $16.3 million in funding from the U.S. Department of Defense. ➁ The team at Stanford University is developing an alternative memory design that combines the advantages of SRAM and DRAM. DRAM can store a large amount of data in a relatively small space, but its read speed is relatively slow. SRAM can read data faster, but its units are relatively large. The gain cell memory developed by the Stanford team combines the small space of DRAM and the almost as fast speed of SRAM. ➂ The mixed gain cell storage device overcomes limitations by combining silicon read transistors with indium tin oxide write transistors, achieving a bit retention time of over 5000 seconds and about 50 times faster than similar oxide-oxide gain cells.
DRAMSRAM
about 1 year ago
Hynix has started mass production of a 36GB 12-layer HBM3E memory, marking the largest capacity HBM to date. The company achieved this by stacking 12 layers of 3GB DRAM chips, making each chip 40% thinner than before and using TSV4 technology. The new product offers improved heat dissipation performance and stability compared to the previous generation, and is designed to excel in speed, capacity, and stability, crucial for AI memory.
AIDRAMHBMSK Hynixmemorytechnology
about 1 year ago
➀ A new research project led by Professor Matthias Jung aims to address the bottleneck caused by memory in computer applications, particularly in AI. ➁ The project involves developing the DRAMSys simulation tool to make it ready for the latest DRAM semiconductor memory standards like HBM4, DDR6, and CXL. ➂ The tool will help developers simulate new applications early in the development stage, identifying potential bottlenecks and optimizing memory usage.
DRAMSimulationresearch