The International Supercomputer Conference (ISC) kicked off in Hamburg, Germany this week with the release of the TOPP500 list of the fastest supercomputers, with a computer named Frontier taking first place.Deployed at the US Department of Energy’s Oak Ridge National Labs, it is the first exascale machine (1018 floating point operations per second)—an HPE-Cray EX system powered by AMD Epyc CPUs and Instinct MI250 GPUs.Intel had hoped to win the exascale battle with an other DoE computer called Aurora, but AMD beat it to the punch. Frontier also beat out competitors from China and Japan that had hoped to win the exascale race.To read this article in full, please click here
The International Supercomputer Conference (ISC) kicked off in Hamburg, Germany this week with the release of the TOPP500 list of the fastest supercomputers, with a computer named Frontier taking first place.Deployed at the US Department of Energy’s Oak Ridge National Labs, it is the first exascale machine (1018 floating point operations per second)—an HPE-Cray EX system powered by AMD Epyc CPUs and Instinct MI250 GPUs.Intel had hoped to win the exascale battle with another DoE computer called Aurora, but AMD beat it to the punch. Frontier also beat out competitors from China and Japan that had hoped to win the exascale race.To read this article in full, please click here
Cloud services provider Vultr has launched what it claims is the first GPU virtualization platform for smaller and midsize companies that don’t need the much more powerful and much more expensive options offered by the big cloud players.When Nvidia introduced its Ampere A100 processor in 2020, it emphasized that it was the first graphics processor to support Multi-Instance GPU, or MIG. This allows for partitioning the GPU into seven virtual GPUs, in much the same way a hypervisor partitions CPU cores.Now Vultr says it’s the first cloud provider to offer fractional A100 GPU instances to customers through its Vultr Talon platform. The company notes there’s no one size fits all when it comes to customer workloads. Other cloud services providers that offer GPU instances make the full GPU available for a hefty price. Talon is a much smaller instance with a much lower price for customers who just need a snack, not a seven-course meal.To read this article in full, please click here
Nvidia unveiled high-performance computing (HPC) reference designs and new water-cooling technology for its GPUs at the annual Computex tradeshow in Taipei, Taiwan.The reference designs employ Nvidia's forthcoming Grace CPU and Grace Hopper Superchips, due next year. Grace is an Arm-based CPU – Nvidia’s first for the server market. Hopper is Nvidia’s next generation of GPU processors.
Read more: Highflying Nvidia widens its reach into enterprise data centersTo read this article in full, please click here
Nvidia unveiled high-performance computing (HPC) reference designs and new water-cooling technology for its GPUs at the annual Computex tradeshow in Taipei, Taiwan.The reference designs employ Nvidia's forthcoming Grace CPU and Grace Hopper Superchips, due next year. Grace is an Arm-based CPU – Nvidia’s first for the server market. Hopper is Nvidia’s next generation of GPU processors.
Read more: Highflying Nvidia widens its reach into enterprise data centersTo read this article in full, please click here
IBM has added a new member to its Spectrum Scale Enterprise Storage Server (ESS) portfolio that featuers a faster controller CPU and more throughput and that is designed to work with Nvidia’s DGX dense compute servers for AI training.The new ESS 3500 is a 2U design with 24 drive bays and a maximum raw capacity of 368TB. But it can achieve up to 1PB through LZ4 compression, a first for the series that earlier ESS versions do not have. The ESS 3500 can achieve up to 91GB/s of throughput performance, better than the 80GB/s of the older models.To read this article in full, please click here
IBM has added a new member to its Spectrum Scale Enterprise Storage Server (ESS) portfolio that featuers a faster controller CPU and more throughput and that is designed to work with Nvidia’s DGX dense compute servers for AI training.The new ESS 3500 is a 2U design with 24 drive bays and a maximum raw capacity of 368TB. But it can achieve up to 1PB through LZ4 compression, a first for the series that earlier ESS versions do not have. The ESS 3500 can achieve up to 91GB/s of throughput performance, better than the 80GB/s of the older models.To read this article in full, please click here
Pure Storage and data-warehouse developer Snowflake have partnered to bring Snowflake’s cloud-based data-warehousing technology on-premises.Under the new relationship, the Snowflake Data Cloud compute engine will be run on Pure Storage’s FlashBlade file- and object-storage array. Pure has another line of storage devices, called FlashArray, but those serve a different purpose, notes Rob Lee, CTO of Pure Storage.“I look at FlashArray as our scale-up platform, and FlashBlade as our scale out platform,” he said. “We tend to see FlashArray applied much more to transactional database-type workloads, like OLTP, trading databases, billing databases, where you have high update rates, and we tend to see FlashBlade applied to data warehouses or analytics types of environments where you don't have a ton of transactional change, but you've got a lot of analysis, a lot of read-type workloads,” he said.To read this article in full, please click here
Pure Storage and data-warehouse developer Snowflake have partnered to bring Snowflake’s cloud-based data-warehousing technology on-premises.Under the new relationship, the Snowflake Data Cloud compute engine will be run on Pure Storage’s FlashBlade file- and object-storage array. Pure has another line of storage devices, called FlashArray, but those serve a different purpose, notes Rob Lee, CTO of Pure Storage.“I look at FlashArray as our scale-up platform, and FlashBlade as our scale out platform,” he said. “We tend to see FlashArray applied much more to transactional database-type workloads, like OLTP, trading databases, billing databases, where you have high update rates, and we tend to see FlashBlade applied to data warehouses or analytics types of environments where you don't have a ton of transactional change, but you've got a lot of analysis, a lot of read-type workloads,” he said.To read this article in full, please click here
Western Digital introduced new high-capacity and high-performance products this week during its What’s Next event in San Francisco.First up, WD announced it is sampling conventional 22TB and shingled 26TB hard disk drives to cloud service providers, with widescale availability expected this summer. The drives, named Ultrastar DC HC570 for the 22TB version and DC HC670 for the 26TB version, are what WD calls UltraSMR disk drives. It's a means of packing greater amounts of data onto a disk platter. Western Digital
WD’s previous high-end drive was the 20TB Ultrastar DC HC560. It packed 2.2TB per platter and came with nine platters. The two new drives managed to pack a tenth platter into a 3.5 drive form factor. All of these drives are helium-filled to reduce friction of the spinning platters and feature Western Digital’s triple-stage actuator (TSA) with multiple independent read/write heads.To read this article in full, please click here
Western Digital introduced new high-capacity and high-performance products this week during its What’s Next event in San Francisco.First up, WD announced it is sampling conventional 22TB and shingled 26TB hard disk drives to cloud service providers, with widescale availability expected this summer. The drives, named Ultrastar DC HC570 for the 22TB version and DC HC670 for the 26TB version, are what WD calls UltraSMR disk drives. It's a means of packing greater amounts of data onto a disk platter. Western Digital
WD’s previous high-end drive was the 20TB Ultrastar DC HC560. It packed 2.2TB per platter and came with nine platters. The two new drives managed to pack a tenth platter into a 3.5 drive form factor. All of these drives are helium-filled to reduce friction of the spinning platters and feature Western Digital’s triple-stage actuator (TSA) with multiple independent read/write heads.To read this article in full, please click here
Cisco is urging customers to replace flawed memory sticks in some of its Unified Computing System (UCS) servers before they fail.The problem is caused by a manufacturing error in 24 dual in-line memory modules (DIMM) that exhibit persistent correctable memory errors that if left in place could knock the servers offline. The problem is found in 16GB, 32GB, and 64GB memory DIMMs.
[ Get regularly scheduled insights by signing up for Network World newsletters. ]
Cisco describes the flaws as manufacturing deviations that affect memory modules used to make up the DIMMs. All of the problem parts were manufactured during the middle-to-end of 2020, according to a Cisco alert.To read this article in full, please click here
Cisco is urging customers to replace flawed memory sticks in some of its Unified Computing System (UCS) servers before they fail.The problem is caused by a manufacturing error in 24 dual in-line memory modules (DIMM) that exhibit persistent correctable memory errors that if left in place could knock the servers offline. The problem is found in 16GB, 32GB, and 64GB memory DIMMs.
[ Get regularly scheduled insights by signing up for Network World newsletters. ]
Cisco describes the flaws as manufacturing deviations that affect memory modules used to make up the DIMMs. All of the problem parts were manufactured during the middle-to-end of 2020, according to a Cisco alert.To read this article in full, please click here
AMD is looking to quickly integrate Xilinx technology into its CPU business, but perhaps more significantly it’s developing software to enable a broad portfolio of applications for its hardware.On a recent earnings call, AMD CEO Lisa Su said the company sees opportunities to deliver stronger products as a result of technology it gained when it merged with Xilinx in February.
[ Get regularly scheduled insights by signing up for Network World newsletters. ]
“As one example, we are integrating Xilinx’s differentiated AI engine across our CPU product portfolio to enable industry-leading inference capabilities, with the first products expected in 2023,” Su said.To read this article in full, please click here
AMD is looking to quickly integrate Xilinx technology into its CPU business, but perhaps more significantly it’s developing software to enable a broad portfolio of applications for its hardware.On a recent earnings call, AMD CEO Lisa Su said the company sees opportunities to deliver stronger products as a result of technology it gained when it merged with Xilinx in February.
[ Get regularly scheduled insights by signing up for Network World newsletters. ]
“As one example, we are integrating Xilinx’s differentiated AI engine across our CPU product portfolio to enable industry-leading inference capabilities, with the first products expected in 2023,” Su said.To read this article in full, please click here
Intel CEO Pat Gelsinger expects chip shortages will continue into 2024 due to a lack of manufacturing equipment and tools to make the chips. Gelsinger made the comments during an interview with CNBC's TechCheck about Intel’s first quarter earnings. While the company did well in Q1, the outlook for Q2 is not as positive, and Intel stock took a hit for it.Semiconductor manufacturers have faced a number of challenges to meet demand, most notably production shutdowns due to the Covid pandemic. However, Gelsinger specifically linked the shortages to a lack of manufacturing equipment and difficulty building new semiconductor fabrication plants, or fabs.To read this article in full, please click here
The modern graphics processing unit (GPU) started out as an accelerator for Windows video games, but over the last 20 years has morphed into an enterprise server processor for high-performance computing and artificial-intelligence applications.Now GPUs are at the tip of the performance spear used in supercomputing, AI training and inference, drug research, financial modeling, and medical imaging. They have also been applied to more mainstream tasks for situations when CPUs just aren’t fast enough, as in GPU-powered relational databases.
[ Get regularly scheduled insights by signing up for Network World newsletters. ]To read this article in full, please click here
Intel CEO Pat Gelsinger expects chip shortages will continue into 2024 due to a lack of manufacturing equipment and tools to make the chips. Gelsinger made the comments during an interview with CNBC's TechCheck about Intel’s first quarter earnings. While the company did well in Q1, the outlook for Q2 is not as positive, and Intel stock took a hit for it.Semiconductor manufacturers have faced a number of challenges to meet demand, most notably production shutdowns due to the Covid pandemic. However, Gelsinger specifically linked the shortages to a lack of manufacturing equipment and difficulty building new semiconductor fabrication plants, or fabs.To read this article in full, please click here
The modern graphics processing unit (GPU) started out as an accelerator for Windows video games, but over the last 20 years has morphed into an enterprise server processor for high-performance computing and artificial-intelligence applications.Now GPUs are at the tip of the performance spear used in supercomputing, AI training and inference, drug research, financial modeling, and medical imaging. They have also been applied to more mainstream tasks for situations when CPUs just aren’t fast enough, as in GPU-powered relational databases.
[ Get regularly scheduled insights by signing up for Network World newsletters. ]To read this article in full, please click here
IBM will launch the first major update to its i operating system for Power CPU-based servers in three years. The enhancements are largely hardware-oriented, supporting both the older Power9 and the newer Power10, which has been available since last September.IBM's i OS 7.5, not to be confused with iOS from Apple or IOS from Cisco, will be the first upgrade since version 7.4 appeared in April 2019. Power Systems, formerly known as the mid-range system AS/400, also have the option of running IBM’s own UNIX variant, called AIX, as well as Red Hat Linux.
[ Get regularly scheduled insights by signing up for Network World newsletters. ]To read this article in full, please click here
Andy Patrizio