The Next Platform - The Next Platform
The Memory Area Network At The Heart Of IBM’s Power10. About. The Next Platform is part of the Situation Publishing family, which includes the enterprise and business technology publication, The Register. TNP offers in-depth coverage of high-end computing at large enterprises, supercomputing centers, hyperscale data centers, and public clouds.
AMD Turns The Screws With “Turin” Server CPUs
Oct 10, 2024 · With the jump to Turin, the currently top binned Epyc plain vanilla Epyc 9755 has 128 cores running at 2.7 GHz and it delivers a relative performance of 92.93 at a cost of $12,984. That works out to $140 per unit of performance, and so AMD has finally moved the needle here a lot when it comes to bang for the buck.
Accenture Melds Smarts And Wares With Nvidia For Agentic AI Push
Oct 3, 2024 · Lan Guan, chief AI officer at Accenture, said during a briefing with journalists that generative AI demand drove $3 billion in bookings in its last fiscal year, and that agentic AI will help accelerate demand. “The next wave of Agentic AI will be a huge step forward, will be a game changer in how our clients reinvent their business,” Guan said.
With MTIA v2 Chip, Meta Can Do AI Inference, But Not Training
Apr 11, 2024 · Here is what the MTIA v2 chip looks like: And here is the block diagram of its various units, controllers, caches, and interconnects: The MTIA v1 chip was etched in the 7 nanometer processes from Taiwan Semiconductor Manufacturing Co and it had an area of 373 mm 2 (19.34 by 19.1 mm 2); it ran at a mere 800 MHz.With the MTIA v2, the chip is etched using 5 nanometer processes, and Meta cranked ...
AMD Gives Nvidia Some Serious Heat In GPU Compute
Oct 10, 2024 · The MI325X has the same performance as the existing “Antares” MI300X GPU, and in fact, the MI325 is the same compute complex, etched in the same 4 nanometer processes from Taiwan Semiconductor Manufacturing Co, with its power boosted from 750 watts to 1,000 watts to be able to drive more HBM memory capacity and higher bandwidth out of it.
How MCR Memory Can More Than Double HPC And AI Performance
October 4, 2024 Rob Farber. Intel recently demonstrated a new type of DIMM memory technology called Multiplexer Combined Rank (MCR), also referred to as MRDIMMs, that provides up to 2.3X better performance for HPC workloads and up to a 2X better on AI inference workloads in comparison to 5th Gen Intel Xeon processors, based on internal Intel ...
Intel Shoots “Granite Rapids” Xeon 6 Into The Datacenter
September 24, 2024 Timothy Prickett Morgan. UPDATED: Intel has been talking about its “Granite Rapids” Xeon 6 processors for so long that it would be easy to forget that they have not yet been formally announced. But today, the high end of the “Granite Rapids” server CPU lineup makes its debut, several weeks before AMD is widely ...
IBM Power10 Shreds Ice Lake Xeons For Transaction ...
Sep 7, 2022 · Here is a simple algebraic equation that describes the relative computing oomph of two different CPU architectures over the past two decades: If Intel an X86 core is X, then an IBM Power core equals 2X. IBM’s Power family of processors and their resulting hardware systems has never been particularly focused on price/performance or performance per watt, which is something has been driving the ...
IBM Buys HashiCorp To Control The Alternative To Red ...
Apr 25, 2024 · And then on Tuesday, the rumors broke that IBM was going to acquire the upstart, whose Hashi Stack – now formally called HashiCorp Cloud Platform – is an alternative to the OpenStack cloud controller, OpenShift Kubernetes container controller, and Ansible automation tool that are all brought together under IBM’s Red Hat brand.
Copper Wires Have Already Failed Clustered AI Systems
Sep 13, 2024 · Copper has already failed to support the AI workload in an economical manner. Yes, there has been two years of an investor-funded gold rush that that really fueled all of the profits coming into the hardware of players. But copper has already failed in supporting efficient, cost effective, performant systems for the AI workload. The industry is ...