News Posts matching #PCI

Return to Keyword Browsing

Alibaba Previews Home-Grown CPUs with 128 Armv9 Cores, DDR5, and PCIe 5.0 Technology

One of the largest cloud providers in China, Alibaba, has today announced a preview for a new instance powered by Yitian 710 processor. The new processor is a collection of Alibaba's efforts to develop a home-grown design capable of powering cloud instances and the infrastructure needed for it and its clients. Without much further ado, the Yitian 710 is based on Armv9 ISA and features 128 cores. Ramping up to 3.2 GHz, these cores are paired with eight-channel DDR5 memory to enable sufficient data transfer. In addition, the CPU supports 96 PCIe 5.0 lanes for IO with storage and accelerators. These are most likely custom designs, and we don't know if they are using a blueprint based on Arm's Neoverse. The CPU is manufactured at TSMC's facilities on 5 nm node and features 60 billion transistors.

Alibaba offers these processors as a part of their Elastic Compute Service (ECS) instance called g8m, where users can select 1/2/4/8/16/32/64/128 vCPUs, where each vCPU is equal to one CPU core physically. Alibaba is running this as a trial option and notes that users should not run production code on these instances, as they will disappear after two months. Only 100 instances are available for now, and they are based in Alibaba's Hangzhou zone in China. The company notes that instances based on Yitian 710 processors offer 100 percent higher efficiency than existing AMD/Intel solutions; however, they don't have any useful data to back it up. The Chinese cloud giant is likely trying to test and see if the home-grown hardware can satisfy the needs of its clients so that they can continue the path to self-sustainability.

Imagination Technologies Releases Open Source Drivers for PowerVR Series 1

If you owned an Apocalypse 3d/3dx or Matrox m3D, you would've been one of many gamers that had bought a PowerVR Series 1 based 3D graphics accelerator and was both excited and underwhelmed at the same time. Released originally in 1996 and the PCX1 manufactured a 500 nm and a core clock speed of whopping 60 MHz, it was the only direct competitor of 3dfx's original Voodoo graphics card, which was technically slower at 50 MHz, but delivered a lot better in terms of 3D quality. Here we are in 2022 and Imagination Technologies, the company behind the PCX1 and the die shrunk PCX2 that was launched a year later, is releasing the drivers for both 3D accelerators as open source. Outside of a big nostalgia trip for those that might still have their card knocking around, there's questionable value in these drivers.

The second generation of PowerVR GPU's ended up powering the Sega Dreamcast with the third generation ending up in PC GPUs that were competitive with the NVIDIA GeForce 256, at least until NVIDIA changed from SDR to DDR memory. The most unique part of the PowerVR Series 1 was that the 3D accelerator could use the main 2D display cards memory as a framebuffer over the PCI bus. Sadly most games didn't support the PowerSGL API at the time and weren't able to take full advantage of the hardware when DirectX 3.0 was used. The open source drivers are provided as is and it seems like some libraries are missing for the Tomb Raider port for the PoverVR Series 1 3D accelerators, but beyond that, there should be no limitations.

NVIDIA Unveils Grace CPU Superchip with 144 Cores and 1 TB/s Bandwidth

NVIDIA has today announced its Grace CPU Superchip, a monstrous design focused on heavy HPC and AI processing workloads. Previously, team green has teased an in-house developed CPU that is supposed to go into servers and create an entirely new segment for the company. Today, we got a more detailed look at the plan with the Grace CPU Superchip. The Superchip package represents a package of two Grace processors, each containing 72 cores. These cores are based on Arm v9 in structure set architecture iteration and two CPUs total for 144 cores in the Superchip module. These cores are surrounded by a now unknown amount of LPDDR5x with ECC memory, running at 1 TB/s total bandwidth.

NVIDIA Grace CPU Superchip uses the NVLink-C2C cache coherent interconnect, which delivers 900 GB/s bandwidth, seven times more than the PCIe 5.0 protocol. The company targets two-fold performance per Watt improvement over today's CPUs and wants to bring efficiency and performance together. We have some preliminary benchmark information provided by NVIDIA. In the SPECrate2017_int_base integer benchmark, the Grace CPU Superchip scores over 740 points, which is just the simulation for now. This means that the performance target is not finalized yet, teasing a higher number in the future. The company expects to ship the Grace CPU Superchip in the first half of 2023, with an already supported ecosystem of software, including NVIDIA RTX, HPC, NVIDIA AI, and NVIDIA Omniverse software stacks and platforms.
NVIDIA Grace CPU Superchip

Intel Introduces Arctic Sound-M Data Center Graphics Card Based on DG2 Design and AV1 Encoding

At Intel's 2022 investor meeting, the company has presented a technology roadmap update to give its clients an insight into what is to come. Today, team blue announced one of the first discrete data-centric graphics cards in the lineup, codenamed Arctic Sound-M GPU. Based on the DG2 Xe-HPG variation of Intel Xe GPUs, Arctic Sound-M is the company's first design to enter the data center space. The DG2 GPU features 512 Execution Units (EUs), which get passive cooling from the single-slot design of Arctic Sound's heatsink, envisioned for data center enclosures with external airflow.

One of the most significant selling points that Intel advertises is support for hardware-based AV1 encoding standard. This feature allows the card to achieve a 30% greater bandwidth, and it is the main differentiator between consumer-oriented Arc Alchemist GPUs and itself. The card is powered by PCIe power and an 8-pin EPS power connector. Arctic Sound-M is already sampling to select customers and it will become available in the middle of 2022.

Below is Intel's teaser video.

NAND Flash Pricing Set to Spike 5-10% in Q2 Due to Material Contamination at WDC and Kioxia, Says TrendForce

WDC recently stated that certain materials were contaminated in late January at NAND Flash production lines in Yokkaichi and Kitakami, Japan which are joint ventures with Kioxia, according to TrendForce's investigations. Before this incident, TrendForce had forecast that the NAND Flash market will see a slight oversupply the entire year and average price from Q1 to Q2 will face downward pressure. However, the impact of WDC's material contamination issue is significant and Samsung's experience during the previous lockdown of Xi'an due to the pandemic has also retarded the magnitude of the NAND Flash price slump. Therefore, the Q1 price drop will diminish to 5~10%. In addition, according to TrendForce, the combined WDC/Kioxia NAND Flash market share in the 3Q21 was as high as 32.5%. The consequences of this latest incident may push the price of NAND Flash in Q2 to spike 5~10%.

The contaminated products in this incident are concentrated in 3D NAND (BICS) with an initial estimate of 6.5exabytes (approximately 6,500M GB) affected. According to TrendForce, damaged bits account for 13% of the group's output in 1Q22 and approximately 3% of the total output for the year. The normal production schedule for the entire line has yet to be confirmed. It is worth noting that the damages announced by WDC likely do not account for total losses stemming for this event and the number of damaged Kioxia parts has not been aggregated, so the total number of affected bits may increase further.

Phanteks Previews Robotic-Looking Evolv Shift XT Case, Compact PSUs, and White Edition Products

Phanteks debuts a host of new products for the upcoming year at CES 2022 - The brand new Evolv Shift XT Mini-ITX Chassis and Revolt SFX Power Supplies, Matte White Editions for the Evolv X & Eclipse P600S Chassis, white SK PWM D-RGB Fans, white AMP Power Supply and a complete range of Gen4 PCIe Riser Cables and Gen4 Vertical GPU Bracket.

Brand new and unique Evolv Shift XT Mini-ITX Chassis and super compact Revolt SFX Power Supplies
Evolv Shift XT - Compact, Powerful, Futureproof
The Evolv Shift XT brings a unique small form factor that can extend in size to tailor to your cooling performance needs. The Evolv Shift XT has no compromise on performance with support for powerful hardware, whether in Compact, Aircooled, or Liquid Cooled Mode.

congatec launches 10 new COM-HPC and COM Express Computer-on-Modules with 12th Gen Intel Core processors

congatec - a leading vendor of embedded and edge computing technology - introduces the 12th Generation Intel Core mobile and desktop processors (formerly code named Alder Lake) on 10 new COM-HPC and COM Express Computer-on-Modules. Featuring the latest high performance cores from Intel, the new modules in COM-HPC Size A and C as well as COM Express Type 6 form factors offer major performance gains and improvements for the world of embedded and edge computing systems. Most impressive is the fact that engineers can now leverage Intel's innovative performance hybrid architecture. Offering of up to 14 cores/20 threads on BGA and 16 cores/24 threads on desktop variants (LGA mounted), 12th Gen Intel Core processors provide a quantum leap [1] in multitasking and scalability levels. Next-gen IoT and edge applications benefit from up to 6 or 8 (BGA/LGA) optimized Performance-cores (P-cores) plus up to 8 low power Efficient-cores (E-cores) and DDR5 memory support to accelerate multithreaded applications and execute background tasks more efficiently.

Intel's NUC 12 Extreme Edition to Feature Non-Soldered LGA1700 Socket for Alder Lake

For a significant period, Intel's Next Unit of Computing (NUC) series has featured soldered processors on the PC's motherboard. However, according to the latest leaks from Twitter hardware leaker @9550pro, we have a potential Alder Lake-based NUC featuring desktop processor versions and a dedicated LGA1700 socket. As the leaked image shows, it looks like Intel's NUC 12 Extreme edition will feature an LGA1700 socket that features support for desktop-class of Alder Lake processors. If this leak is correct, we could see a compelling NUC solution filled with Intel-only processors, meaning an Alder Lake CPU and Arc Alchemist discrete graphics card.

There is room for PCIe expansion, which means that theoretically, you could connect any GPU to the mainboard. However, it is natural to assume that Intel could force their own GPU SKUs to launch this mini PC. We have to wait and see what Intel presents at tomorrow's CES 2022 event for more information.

NAND Flash ASP Expected to Undergo 10-15% QoQ Decline in 1Q22 as Market Shifts Towards Oversupply, Says TrendForce

Demand for NAND Flash products will undergo a noticeable and cyclical downward correction in 1Q22 as major smartphone brands wind down their procurement activities for the peak season and ODMs prepare for the New Year holidays, according to TrendForce's latest investigations. As such, the NAND Flash market will remain in an oversupply situation, with prices continuing to undergo downward corrections accordingly. However, PC OEMs have been reinstating certain orders for client SSDs since early November in response to improvements in the supply of upstream semiconductor materials. By fulfilling these orders, suppliers are able to keep their inventory level relatively low, meaning they are not under as much pressure as previously expected to reduce inventory by lowering prices. Taking these factors into account, TrendForce expects NAND Flash ASP to undergo a 10-15% QoQ decline in 1Q22, during which NAND Flash prices will experience the most noticeable declines compared to the other quarters in 2022.

Regarding the price trend of NAND Flash products across the whole 2021, TrendForce further indicates that suppliers have actively transitioned their output to higher-layer technologies, resulting in a bit supply growth that noticeably outpaces demand, though the tight supply of components such as controller ICs and PMICs has constrained the production of NAND Flash end-products. Hence, the decline in contract prices of NAND Flash products has not been as severe as previously expected. Moving ahead to 2022, however, the supply of relevant components is expected to gradually improve, so the market for various NAND Flash products will also likely shift towards a noticeable oversupply. As a result, prices of NAND Flash products will steadily decline before the arrival of the peak season in 3Q22.

Sapphire GPRO X080 and X060 Mining GPUs Based on AMD RDNA2 Navi Architecture Surface

Sapphire, along with various other AIB partners from AMD, has been making graphics cards exclusively for cryptocurrency mining. With the arrival of AMD's RDNA2 generation, this has continued as well. However, the company has been doing it more quietly to avoid backslash from its customers already furious about the poor availability of graphics cards in general. Fortunately, El Chapuzas Informatico managed to get ahold of two datasheets from Sapphire that highlight features and use cases of its GPRO X080 and GPRO X060 mining graphics cards, primarily targeting Ethereum coin mining.

According to the source, the company has readied two models based on RDNA2 chipsets. That is GPRO X080 SKU based on Navi 22 with 2304 Streaming Processors, running at 2132 MHz frequency. Paired with Navi 22 GPU, 10 GB of GDDR6 memory runs at 16 Gbps speed on a 160-bit bus. This model has no display outputs, and the only connector is a PCIe 4.0 x16 slot that connects the GPU to the motherboard. Running at the default 165 Watt TGP, the card produces a 38.0 MH/s hash rate, while the optimized form of 41.6 MH/s reduces TGP to just 93 Watts.

Intel's Sapphire Rapids Xeons to Feature up to 64 GB of HBM2e Memory

During the Supercomputing (SC) 21 event, Intel has disclosed additional information regarding the company's upcoming Xeon server processor lineup, codenamed Sapphire Rapids. One of the central areas of improvement for the new processor generation is the core architecture based on Golden Cove, the same core found in Alder Lake processors for consumers. However, the only difference between the Golden Cove variant found in Alder Lake and Sapphire Rapids is the amount of L2 (level two) cache. With Alder Lake, Intel equipped each core with 1.25 MB of its L2 cache. However, with Sapphire Rapids, each core receives a 2 MB bank.

One of the most exciting things about the processors, confirmed by Intel today, is the inclusion of High-Bandwidth Memory (HBM). These processors operate with eight memory channels carrying DDR5 memory and offer PCIe Gen5 IO expansion. Intel has confirmed that Sapphire Rapids Xeons will feature up to 64 GB of HBM2E memory, including a few operating modes. The first is a simple HBM caching mode, where the HBM memory acts as a buffer for the installed DDR5. This method is transparent to software and allows easy usage. The second method is Flat Mode, which means that both DDR5 and HBM are used as contiguous address spaces. And finally, there exists an HBM-only mode that utilizes the HBM2E modules as the only system memory, and applications fit inside it. This has numerous benefits, primarily drawn from HBM's performance and reduced latency.

XPG Unveils ATOM Series PCIe M.2 2280 Solid State Drives

XPG, a fast-growing provider of systems, components, and peripherals for Gamers, Esports Pros, and Tech Enthusiasts, today announces XPG, a fast-growing provider of systems, components, and Peripherals for Gamers, Esports Pros, and Tech Enthusiasts, today announces a new series of solid state drives (SSD), the XPG ATOM series, geared toward creators of different needs and budgets. They include the XPG ATOM 30, 40, and 50.

The ATOM 30 and 40 utilize PCIe Gen3x4 and NVMe 1.3 to deliver sequential read and write speeds of up to 2,500/2,000 and 3,500/3,000 MB per second, respectively, to give creators the performance they need to create without limitations. Their M.2 2280 specifications support the latest Intel and AMD platforms for creating on the latest PCs, including desktop and laptops. For users seeking a further boost, the ATOM 50 takes advantage of PCIe Gen4 x4 and NVMe 1.4 to offer read and write speeds of up to 5, 000/4,500 MB per second.

ADATA Unveils LEGEND Series PCIe M.2 2280 Solid State Drives

ADATA Technology, a manufacturer of high-performance DRAM modules, NAND Flash products, mobile accessories, gaming products, electric power trains, and industrial solutions today announces a new series of solid state drives (SSD), the ADATA LEGEND series, geared toward creators of different needs and budgets. They include the ADATA LEGEND 740, 750, and 840.

The LEGEND 740 and 750 utilize PCIe Gen3 x4 and NVMe 1.3 to deliver sequential read and write speeds of up to 2,500/2,000 and 3,500/3,000 MB per second, respectively, to give creators the performance they need to create without limitations. Their M.2 2280 specifications support the latest Intel and AMD platforms for creating on the latest PCs, including desktop and laptops. For users seeking a further boost, the LEGEND 840 takes advantage of PCIe Gen4 x4 and NVMe 1.4 to offer read and write speeds of up to 5,000/4,500 MB per second.

Global Ranking of Top 10 SSD Module Makers for 2020 Shows 15% YoY Drop in Annual Shipment, Says TrendForce

The emergence of the COVID-19 pandemic led to severe delays in manufacturing and logistics. In particular, governments worldwide began implementing border restrictions in 2Q20 to combat the ongoing health crisis, leading to a sudden decline in order volumes for channel-market SSDs, according to TrendForce's latest investigations. Annual shipment of SSDs to the channel (retail) market reached 111.5 million units in 2020, a 15% YoY decrease. In terms of market share by shipment, Kingston, ADATA, and Kimtigo once again occupied the top three spots, respectively.

Looking at the channel market for SSDs as a whole, NAND Flash suppliers (among which Samsung possessed the largest market share) accounted for around 35% of the total shipments in 2020, while SSD module makers accounted for the other 65%. The top 10 module makers accounted for 71% of channel-market SSD shipments from all SSD module makers. Taken together, these figures show that the market remained relatively oligopolistic in 2020. However, it should be noted that TrendForce's ranking of SSD module makers for 2020 takes account of only products bound for the channel market and under brands owned by the module makers themselves; NAND Flash suppliers were therefore excluded from the top 10 ranking.

PCIe Gen5 "12VHPWR" Connector to Deliver Up to 600 Watts of Power for Next-Generation Graphics Cards

The upcoming graphics cards based on PCIe Gen5 standard will utilize the latest PCIe connector with double bandwidth of the previous Gen4 that we use today and bring a new power connector that the next generation of GPUs brings. According to the information exclusive to Igor's Lab, the new connector will be called the 12VHPWR and will carry as many as 16 pins with it. The reason it is called 12VHPWR is that it features 12 pins for power, while the remaining four are signal transmission connectors to coordinate the delivery. This power connector is supposed to carry as much as 600 Watts of power with its 16 pins.

The new 12VHPWR connector should work exclusively with PCIe Gen5 graphics cards and not be backward compatible with anything else. It is said to replace three standard 8-pin power connectors found on some high-end graphics cards and will likely result in power supply manufacturers adopting the new standard. The official PCI-SIG specification defines each pin capable of sustaining up to 9.2 Amps, translating to a total of 55.2 Amps at 12 Volts. Theoretically, this translates to 662 Watts; however, Igor's Lab notes that the connector is limited to 600 Watts. Additionally, the 12VHPWR connector power pins have a 3.00 mm pitch, while the contacts in a legacy 2×3 (6-pin) and 2×4 (8-pin) connector lie on a larger 4.20 mm pitch.

Intel Z690 Alder Lake Chipset Pictured

Today, we got ahold of the first picture showing Intel's upcoming Z690 chipset, the highest-end chipset offering for the Alder Lake lineup of processors. From previous leaks, we have concluded that Intel has enabled the Z690 chipset to be a very powerful offering. Featuring support for running either DDR4 or DDR5 memory, the Z690 chipset will allow motherboard AIBs to offer motherboards with both the new and current DDR standards, easing the transition to the new DDR5 memory. As far as PCIe connectivity, this high-end chipset produces 12 PCIe Gen5 lanes, along with 16 PCIe Gen3 lanes. This is, of course, just an addition to the 16 PCIe Gen5 lanes that the Alder Lake processor provides, enabling a wide portfolio of PCIe lanes for connecting SSDs and graphics cards.

Below, you can see the Z690 chipset image (热心市民描边怪 image), compared to the Z590 (AnandTech image) chipset, where there is a clear difference in size. The new Z690 chipset seems quite a lot bigger, and that is really not a surprise given the new technology stack that it brings.

Penetration Rate of Ice Lake CPUs in Server Market Expected to Surpass 30% by Year's End as x86 Architecture Remains Dominant, Says TrendForce

While the server industry transitions to the latest generation of processors based on the x86 platform, the Intel Ice Lake and AMD Milan CPUs entered mass production earlier this year and were shipped to certain customers, such as North American CSPs and telecommunication companies, at a low volume in 1Q21, according to TrendForce's latest investigations. These processors are expected to begin seeing widespread adoption in the server market in 3Q21. TrendForce believes that Ice Lake represents a step-up in computing performance from the previous generation due to its higher scalability and support for more memory channels. On the other hand, the new normal that emerged in the post-pandemic era is expected to drive clients in the server sector to partially migrate to the Ice Lake platform, whose share in the server market is expected to surpass 30% in 4Q21.

ATP SATA SSDs Qualify for Compatibility and Interoperability with Microchip's New Tri-Mode Storage Adapters

ATP Electronics, a global leader in specialized storage and memory solutions, has announced that its A600Sc Series serial ATA solid state drives (SATA SSDs) have been successfully qualified for compatibility and interoperability with Adaptec Smart Storage PCIe Gen 4 Tri-Mode SmartRAID 3200, SmartHBA 2200, and HBA 1200 Smart Storage adapters.

Designed for storage platforms in next-generation data centers, the Adaptec PCIe Gen 4 SAS/SATA/NVMe HBA and RAID tri-mode adapters deliver significantly higher performance through PCIe Gen 4 x16 CPU interfaces as well as SAS and SATA storage. The new offerings simplify integration and provide flexibility to aggregate diverse storage devices with Microchip's proven security and manageability features for the most demanding server storage applications.

SiFive Performance P550 Core Sets New Standard as Highest Performance RISC-V Processor IP

SiFive, Inc., the industry leader in RISC-V processors and silicon solutions, today announced launched the new SiFive Performance family of processors. The SiFive Performance family debuts with two new processor cores, the P270, SiFive's first Linux capable processor with full support for the RISC-V vector extension v1.0 rc, and the SiFive Performance P550 core, SiFive's highest performance processor to date. The new SiFive Performance P550 delivers a SPECInt 2006 score of 8.65/GHz, making it the highest performance RISC-V processor available today, and comparable to existing proprietary solutions in the application processor space.

"SiFive Performance is a significant milestone in our commitment to deliver a complete, scalable portfolio of RISC-V cores to customers in all markets who are at the vanguard of SOC design and are dissatisfied with the status quo," said Dr. Yunsup Lee, Co-Founder and CTO of SiFive. "These two new products cover new performance points and a wide range of application areas, from efficient vector processors that easily displace yesterday's SIMD architectures, to the bleeding edge that the P550 represents. SiFive is proud to set the standard for RISC-V processing and is ready to deliver these products to customers today."

ASUSTOR Launches AS-T10G2 10 Gigabit Ethernet Card

The all-new AS-T10G2 is here, bringing increased efficiency and speeds to the much beloved AS-T10G. The AS-T10G2 uses the AQC-107 controller, which offers increased performance, and lower power requirements. Using the Lockerstor 16R Pro, transfer rates were found to be up to 1127 MB/s when reading and 1124 MB/s when writing. The AS-T10G2 also supports IP, TCP, UDP checksum offload to reduce CPU usage for a more efficient experience.

The AS-T10G2 is equipped with a 10 Gbps 8p8c RJ-45 Ethernet port. The AS-T10G2 supports automatic switching between all major Ethernet speeds and is compatible with four lanes of PCI Express 3.0. Pop it into an ASUSTOR NAS running ADM 4.0 or a PC to upgrade network speeds to 10-Gigabit Ethernet. The AS-T10G2 is compatible with both full-height and half-height computers, making it compatible with almost any device featuring a PCI Express slot, ensuring affordable, yet high speed networking for both homes and businesses.

GIGABYTE Unleashes the AORUS Gen 4 7000s Prem. SSD

GIGABYTE Technology, one of the top global manufacturers of motherboards, graphics cards, and hardware solutions, announces today the latest AORUS Gen4 7000s Prem. SSD with up to 7 GB/s read speed while optimizing passive thermal dissipation, which promises no throttling under long-lasting operation. Through the SSD Tool Box application, users can have an instant control on overall operation of SSD.

AORUS Gen4 7000s Prem. SSD adopts the PCIe 4.0 NVMe M.2 interface and it equips the latest Phison E18 selected 8-channel controller, which provides users with ultimate random access rate, as well as the high speed 3D-TLC NAND Flash and SLC cache design that brings the PCIe 4.0 into full play. With the read speed up to 7 GB/s and write speed up to 6.85 GB/s, AORUS Gen4 7000s Prem. SSD can power up content creators, gamers, and users eager for extreme performance.

Xilinx Revolutionizes the Modern Data Center with Software-Defined, Hardware Accelerated Alveo SmartNICs

Addressing the demands of the modern data center, Xilinx, Inc. (NASDAQ: XLNX) today announced a range of new data center products and solutions, including a new family of Alveo SmartNICs, smart world AI video analytics applications, an accelerated algorithmic trading reference design for sub-microsecond trading, and the Xilinx App Store.

Today's most demanding and complex applications, from networking and AI analytics to financial trading, require low-latency and real-time performance. Achieving this level of performance has been limited to expensive and lengthy hardware development. With these new products and solutions, Xilinx is eliminating the barriers for software developers to quickly create and deploy software-defined, hardware accelerated applications on Alveo accelerator cards.

Microchip Announces World's First PCI Express 5.0 Switches

Applications such as data analytics, autonomous-driving and medical diagnostics are driving extraordinary demands for machine learning and hyperscale compute infrastructure. To meet these demands, Microchip Technology Inc. today announced the world's first PCI Express (PCIe) 5.0 switch solutions—the Switchtec PFX PCIe 5.0 family—doubling the interconnect performance for dense compute, high speed networking and NVM Express (NVMe ) storage. Together with the XpressConnect retimers, Microchip is the industry's only supplier of both PCIe Gen 5 switches and PCIe Gen 5 retimer products, delivering a complete portfolio of PCIe Gen 5 infrastructure solutions with proven interoperability.

"Accelerators, graphic processing units (GPUs), central processing units (CPUs) and high-speed network adapters continue to drive the need for higher performance PCIe infrastructure. Microchip's introduction of the world's first PCIe 5.0 switch doubles the PCIe Gen 4 interconnect link rates to 32 GT/s to support the most demanding next-generation machine learning platforms," said Andrew Dieckmann, associate vice president of marketing and applications engineering for Microchip's data center solutions business unit. "Coupled with our XpressConnect family of PCIe 5.0 and Compute Express Link (CXL ) 1.1/2.0 retimers, Microchip offers the industry's broadest portfolio of PCIe Gen 5 infrastructure solutions with the lowest latency and end-to-end interoperability."

Intel Confirms HBM is Supported on Sapphire Rapids Xeons

Intel has just released its "Architecture Instruction Set Extensions and Future Features Programming Reference" manual, which serves the purpose of providing the developers' information about Intel's upcoming hardware additions which developers can utilize later on. Today, thanks to the @InstLatX64 on Twitter we have information that Intel is bringing on-package High Bandwidth Memory (HBM) solution to its next-generation Sapphire Rapids Xeon processors. Specifically, there are two instructions mentioned: 0220H - HBM command/address parity error and 0221H - HBM data parity error. Both instructions are there to address data errors in HBM so the CPU operates with correct data.

The addition of HBM is just one of the many new technologies Sapphire Rapids brings. The platform is supposedly going to bring many new technologies like an eight-channel DDR5 memory controller enriched with Intel's Data Streaming Accelerator (DSA). To connect to all of the external accelerators, the platform uses PCIe 5.0 protocol paired with CXL 1.1 standard to enable cache coherency in the system. And as a reminder, this would not be the first time we see a server CPU use HBM. Fujitsu has developed an A64FX processor with 48 cores and HBM memory, and it is powering today's most powerful supercomputer - Fugaku. That is showing how much can a processor get improved by adding a faster memory on-board. We are waiting to see how Intel manages to play it out and what we end up seeing on the market when Sapphire Rapids is delivered.

BittWare Launches IA-840F with Intel Agilex FPGA and Support for oneAPI

BittWare, a Molex company, today unveiled the IA-840F, the company's first Intel Agilex -based FPGA card designed to deliver significant performance-per-watt improvements for next-generation data center, networking and edge compute workloads. Agilex FPGAs deliver up to 40% higher performance or up to 40% lower power, depending on application requirements. BittWare maximized I/O features using the Agilex chip's unique tiling architecture with dual QSFP-DDs (4× 100G), PCIe Gen4 x16, and three MCIO expansion ports for diverse applications. BittWare also announced support for Intel oneAPI, which enables an abstracted development flow for dramatically simplified code re-use across multiple architectures.

"Modern data center workloads are incredibly diverse, requiring customers to implement a mix of scalar, vector, matrix and spatial architectures," said Craig Petrie, vice president of marketing for BittWare. "The IA-840F ensures that customers can quickly and easily exploit the advanced features of the Intel Agilex FPGA. For those customers who prefer to develop FPGA applications at an abstracted level, we are including support for oneAPI. This new unified software programming environment allows customers to program the Agilex FPGA from a single code base with native high-level language performance across architectures."
Return to Keyword Browsing
May 16th, 2022 10:34 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts