https://www.phoronix.com/scan.php?page=article&item=arm-24core-developer&num=124-core ARM SoC / micro-ATX board / removable DDR4-2133 UDIMMs / PCI Express x16 slot / Gigabit NIC it certainly sounds very exciting... But this "Developerbox" will set you back about $1200 USD. Additionally, the 24 ARM cores are Cortex-A53 and not the more powerful A57 or newer AArch64 cores. Also, these Cortex-A53 cores top out at 1.0GHz. The price is obviously the biggest setback for this developer box built around the Socionext SC2A11 SoC...
https://www.slideshare.net/linaroor...doeasc-supercomputing-linaro-arm-hpc-workshopPresented by Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE- NA0003525.
https://www.servethehome.com/ampere-emag-is-now-shipping-product-with-lenovo-as-a-major-partner/eMAG Technology & Power
Ampere eMAG Pricing and Availability
- TSMC 16nm FinFET+
- Arm v8.0-A, SBSA Level 3
–EL3, secure memory and secure boot support- Advanced power management
- TDP: 125 W
Here is what we have in terms of pricing and availability for the eMAG:
- 16 cores at up to 3.3Ghz Turbo $550
- 32 cores at up to 3.3Ghz Turbo $850
Today Atos announced a deal to deploy a BullSequana X1310 Arm-based supercomputer to CEA in France.
CEA has been developing large, multi-physics, mission critical codes for over 40 years. This is particularly the case of CEA’s Military Applications Division (CEA/DAM)
...
CEA/DAM ordered an Arm-based BullSequana cluster from Atos, using the new ThunderX2 CPU from Marvell
https://insidehpc.com/2018/11/arm-powers-atos-supercomputer-cea-france/The new model, which will be delivered at the end of 2018 in the Île-de-France CEA/DAM center, located at Bruyères-le-Châtel, includes a BullSequana rack with 92 BullSequana X1310 blades, three compute nodes per blade, dual Marvell ThunderX2 processors of 32 cores @ 2.2 GHz, based on the Armv8-A instruction set, with 256 GB per node and Infiniband EDR interconnect. The new ThunderX2 processor supports up to four threads per core with 8 memory channels delivering the combination of compute and memory bandwidth required for critical scientific workloads.
https://www.hpcwire.com/off-the-wir...fficient-computing-with-cray-marvell-and-arm/Los Alamos National Laboratory is running classified simulation codes in support of the National Nuclear Security Administration’s Stockpile Stewardship Program on the new Cray XC50system with Marvell ThunderX2 processors.
We acquired Annapurna Labs in 2015 after working with them on the first version of the AWS Nitro System. Since then we’ve worked with them to build and release two generations of ASICs (chips, not shoes) that now offload all EC2 system functions to Nitro, allowing 100% of the hardware to be devoted to customer instances. A few years ago the team started to think about building an Amazon-built custom CPU designed for cost-sensitive scale-out workloads.
AWS Graviton Processors
Today we are launching EC2 instances powered by Arm-based AWS Graviton Processors. Built around Arm cores and making extensive use of custom-built silicon, the A1 instances are optimized for performance and cost. They are a great fit for scale-out workloads where you can share the load across a group of smaller instances. This includes containerized microservices, web servers, development environments, and caching fleets.
The A1 instances are available in five sizes, all EBS-Optimized by default, at a significantly lower cost:
processor : 0
BogoMIPS : 166.66
Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 cpuid
CPU implementer : 0x41
CPU architecture: 8
CPU variant : 0x0
CPU part : 0xd08
CPU revision : 3
Architecture: aarch64
Byte Order: Little Endian
CPU(s): 8
On-line CPU(s) list: 0-7
Thread(s) per core: 1
Core(s) per socket: 4 Socket(s): 2
NUMA node(s): 1
Vendor ID: ARM
Model: 3
Model name: Cortex-A72
Stepping: r0p3
BogoMIPS: 166.66
L1d cache: 32K
L1i cache: 48K
L2 cache: 2048K
NUMA node0 CPU(s): 0-7
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 cpuid
Up until early 2015, Amazon and AMD were working together on a 64-bit Arm server-grade processor to deploy in the internet titan's data centers. However, the project fell apart when, according to one well-placed source today, "AMD failed at meeting all the performance milestones Amazon set out."
Thus, Amazon went out and bought Arm licensee and system-on-chip designer Annapurna Labs, putting the acquired team to work designing Internet-of-Things gateways and its Nitro chipset, which handles networking and storage tasks for Amazon servers hosting EC2 virtual machines.
Next, as reported on Monday, the Annapurna engineers turned their hands to designing the Graviton, a multi-core Arm processor that powers AWS's A1 EC2 instances. These virtual machines are available now in the US and Europe.
As for AMD, in 2016 it launched what remained of the Arm chip it was working on with Amazon, the Opteron A1100 codenamed Seattle. The clue was in the name, we note. Today, AMD is all in with its much more successful Zen-based x86 processors, Ryzen and Epyc, and no one talks about the A1100.
Around the time the AMD and Amazon partnership was falling apart, and just before the web giant bought Annapurna, AWS veep James Hamilton complained that Arm CPU cores couldn't match rival Intel parts in terms of performance. It wasn't known publicly at the time that AWS was tapping AMD as an Arm processor supplier.
Today, Hamilton said, "I’ve seen the potential for Arm-based server processors for more than a decade, but it takes time for all the right ingredients to come together."
He also spelled out why Amazon decided to go it alone: the ability to license Arm blueprints, via Annapurna, the ability to customize and tweak those designs, and the ability to go to contract manufacturers like TSMC and Global Foundries, and get competitive chips made.
As Intel has lost its edge, rival factories have been able to catch up and fabricate good-enough processors. Also, today's high-end Arm CPU blueprints are much more than smartphone brains, and are capable of running desktop and light server applications.
"Arm does the processor design, but they license the processor to companies that integrate the design in their silicon rather than actually producing the processor themselves," said Hamilton.
"This enables a diverse set of silicon producers, including Amazon, to innovate and specialize chips for different purposes, while taking advantage of the extensive Arm software and tooling ecosystem."
"Most of companies that are producing silicon that license Arm technology are fabless semiconductor companies, which is to say they are in the semiconductor business but outsource the manufacturing of silicon chips in massively expensive facilities to specialized companies like Taiwan Semiconductor Manufacturing Company (TSMC) and Global Foundries."
He added: "When I joined AWS in 2009, I wouldn’t have predicted we would be designing server processors less than a decade later."
The con: it's too damn slow. It does well on the Phoronix Test Suite. It does poorly benchmarking our website fully deployed on it (nginx + php + MediaWiki and everything else involved). This is your "real world" test. All 16 cores can't match even 5 cores of our Xeon E5-2697 v4
https://www.huawei.com/en/press-events/news/2019/1/huawei-unveils-highest-performance-arm-based-cpuKunpeng 920 integrates 64 cores at a frequency of 2.6 GHz. This chipset integrates 8-channel DDR4, and memory bandwidth exceeds incumbent offerings by 46%. System integration is also increased significantly through the two 100G RoCE ports. Kunpeng 920 supports PCIe 4.0 and CCIX interfaces, and provides 640 Gbps total bandwidth. In addition, the single-slot speed is twice that of the incumbent offering, effectively improving the performance of storage and various accelerators.
https://www.zdnet.com/article/huawei-unveils-kunpeng-920-server-arm-chip/At the same time, the company also announced an Arm-based server series called TaiShan.
The series has three models: The TaiShan 2280, a 2U base model that has 2 sockets and support for up to 28 2.5-inch NVMe SSDs; the 4U TaiShan 5280/5290 that can store up to 10 petabytes; and the TaiShan X6000 that is a 2U 4-node server that Huawei says can deliver 10,240 cores per rack.