NVIDIA intros Grace CPU for giant AI and high performance computing workloads

NVIDIA announced its first data center CPU— the NVIDIA Grace. As per NVIDIA, it is an Arm-based processor that delivers 10x the performance of today’s fastest servers.

According to NVIDIA, the NVIDIA Grace is the result of more than 10,000 engineering years of work. The company mentioned that the Grace CPU is designed to address the computing requirements for the world’s most advanced applications, including natural language processing, recommender systems, and AI supercomputing. It combines energy-efficient ARM CPU cores with a low-power memory subsystem that delivers efficient performances.

The NVIDIA Grace CPU, named after Grace Hopper, the U.S computer-programming pioneer, will serve a niche segment of computing.

“Leading-edge AI and data science are pushing today’s computer architecture beyond its limits – processing unthinkable amounts of data,” said Jensen Huang, founder, and CEO of NVIDIA. “Using licensed Arm IP, NVIDIA has designed Grace as a CPU specifically for giant-scale AI and HPC. Coupled with the GPU and DPU, Grace gives us the third foundational technology for computing, and the ability to re-architect the data center to advance AI. NVIDIA is now a three-chip company.”


 

Grace is a specialized processor that targets workloads such as training next-generation NLP models with more than 1 trillion parameters. When paired with NVIDIA GPUs, a Grace CPU-based system will deliver 10x faster performance than NVIDIA DGX based systems which run on x86 CPUs, according to NVIDIA.

The Swiss National Supercomputer Centre (CSCS) and the U.S Department of Energy’s Los Alamos National Laboratory are the first to announce their plans to build Grace-powered supercomputers in support of national scientific research efforts.

Underlying Grace’s performance is fourth-generation NVIDIA NVLink interconnect technology, which provides a 900 GB/s connection between Grace and NVIDIA GPUs that enables 30x higher aggregate bandwidth compared to today’s leading servers.

Moreover, Grace will be using LPDDR5X memory and new architecture that provides unified cache coherence with a single memory address space, combining system and HBM GPU memory that simplifies programmability.

The availability of the NVIDIA Grace CPU is expected in 2023.

Source: NVIDIA

The post NVIDIA intros Grace CPU for giant AI and high performance computing workloads appeared first on YugaTech | Philippines Tech News & Reviews.

Samsung to produce Qualcomm Snapdragon 820

Samsung has just announced that it’s begun mass production of SoCs using the latest 2nd generation 14nm FinFET process technology.

samsung+qualcomm

This new technology will be used with its Sammy’s own and Exynos 8 Octa processor and the upcoming Snapdragon 820 from their major competitor — Qualcomm. This means that the upcoming high-end chip from Qualcomm will use Samsung’s new 14nm LPP process which “delivers up to 15 percent higher speed and 15 percent less power consumption over the previous 14nm LPE process through improvements in transistor structure and process optimization.”

We can expect to see the Snapdragon 820 in multiple flagship devices for 2016, including the Samsung Galaxy S7. Although, Samsung might still go with their own Exynos chipset. We just have to wait and see the official announcement soon.

Source

The post Samsung to produce Qualcomm Snapdragon 820 appeared first on YugaTech | Philippines News & Tech Reviews.

Samsung introduces Exynos 8 Octa 8890 processor

Samsung Electronics has just announced its newest home-baked silicon and a successor to the previous Exynos 7 Octa 7420 which powers Samsung Galaxy S6, S6 Edge, S6 Edge+, and Note 5.

Exynos8

The Samsung Exynos 8 Octa 8890 is built on 14nm FinFET process technology and is a complete package combining the processor and the modem in one. It features the company’s first custom designed CPU based on 64-bit ARMv8 architecture and LTE Rel.12 Cat.12/13 modem. There’s also ARM Mali-T880 to handle graphics performance.

The chipset can provide 30% improvement in performance and 10% more power efficient over its predecessor. It also supports enhanced heterogeneous multi-processing using the four custom and four Cortex-A53 cores. With the advanced LTE modem inside, it can take a maximum download speed of 600Mbps and upload speed of 150Mbps with carrier aggregation.

Samsung’s latest chipset will begin mass production in late 2015. We can expect it to power the upcoming 2016 Galaxy devices.

Source

The post Samsung introduces Exynos 8 Octa 8890 processor appeared first on YugaTech | Philippines News & Tech Reviews.

Intel Core i7 6700K 4.2GHz Skylake lands for Php16,999

Intel’s newest line of processors (Skylake) are already in stores with the Intel Core i7 6700K 4.2GHz coming in at only Php16,999. Announced first week of September, the Intel Skylake chips are made with the 14nm process with TDP ranging from 35W to 91W.

Intel has also highlighted the new features that will be supported by the new Skylake processors. These include support for USB Type-C and Thunderbolt 3 connections, RealSense technology, and Intel Software Guard Extension (Intel SGX) among many others.

Here are the new set of processors and their pricing as indicated by PCHub over at TipidPC

Intel Core i5 6400 3.3GHz – Php9,140
Intel Core i5 6500 3.6GHz – Php9,900
Intel Core i5 6600 3.9GHz – Php10,870
Intel Core i5 6600K 3.9GHz – Php11,850

Intel Core i7 6700 4.0GHz – Php15,710
Intel Core i7 6700K 4.2GHz – Php16,999

The post Intel Core i7 6700K 4.2GHz Skylake lands for Php16,999 appeared first on YugaTech | Philippines News & Tech Reviews.

Intel Launches New Moorefield Mobile Processor

Amidst all the hype for the new Skylake processors, Intel quietly slips its new flagship processor, the Intel Atom Z3590, which is geared for mobile devices like smartphones and tablets.

Intel Atom Z3590 shares a lot in common with its predecessor, the Z3580. Both mobile processors are based on the same manufacturing process (22nm), and the same set of feature set which include support for up to 4GB of RAM, AES encryption, Smart Idle, SpeedStep and Intel Virtualization.

The Z3590 also sports the same quartet of processors based on Silvermont microarchitecture, and the same PowerVR G6430 graphics processing unit. The difference on the new model, however, is that it receives a 7% boost in burst clock speed rated at 2.5GHz, and a notable improvement on the burst frequency on its on-board GPU which tops out at 640MHz.

The new Intel Atom Z3590 has already made its way on some of the devices that were launched at IFA 2015 which include Asus ZenFone Zoom.

The post Intel Launches New Moorefield Mobile Processor appeared first on YugaTech | Philippines News & Tech Reviews.