logo
#

Latest news with #PCIe5.0

KIOXIA Broadens 8th Generation BiCS FLASH SSD Portfolio with High-Performance Data Center NVMe SSDs to Maximize GPU Utilization in AI and HPC Workloads
KIOXIA Broadens 8th Generation BiCS FLASH SSD Portfolio with High-Performance Data Center NVMe SSDs to Maximize GPU Utilization in AI and HPC Workloads

Yahoo

time3 days ago

  • Business
  • Yahoo

KIOXIA Broadens 8th Generation BiCS FLASH SSD Portfolio with High-Performance Data Center NVMe SSDs to Maximize GPU Utilization in AI and HPC Workloads

KIOXIA CD9P Series PCIe 5.0 SSDs Feature Advanced CBA Architecture and TLC Flash, Delivering Breakthrough Performance, Efficiency, and Capacity SAN JOSE, Calif., June 19, 2025--(BUSINESS WIRE)--KIOXIA America, Inc. today announced the development and prototype demonstration of its new KIOXIA CD9P Series PCIe® 5.0 NVMe™ SSDs. These next-generation drives are the latest SSDs built with KIOXIA's 8th generation BiCS FLASH™ TLC–based 3D flash memory. KIOXIA BiCS FLASH features CBA (CMOS directly Bonded to Array) technology, a breakthrough architecture that significantly boosts power efficiency, performance, and storage density, while doubling the capacity available1 per SSD compared with the previous generation model. As GPU-accelerated AI servers drive up the demands on storage infrastructure, maintaining high throughput, low latency, and consistent performance is critical - including keeping valuable GPUs highly utilized. The KIOXIA CD9P Series is purpose-built for these next-generation environments, delivering the speed and responsiveness required by AI, machine learning, and high-performance computing (HPC) workloads to ensure GPUs stay fed with data and operating at maximum efficiency. The CD9P Series leverages KIOXIA's most advanced 3D flash memory to date, featuring a CBA-based architecture that reduces heat generation, enhances thermal management, and delivers greater overall value through improved performance, power metrics and total cost of ownership. With an increased focus on power and performance efficiency (performance per watt), the CD9P Series 15.36 TB model delivers approximately 60% and 45% improvements in sequential read and write speeds per watt, respectively, compared to the previous generation SSD. It also achieves gains of approximately 55% and 100% in random read and write performance per watt, measured in thousands of IOPS (KIOPS), respectively. KIOXIA CD9P Series drives deliver 4-corner performance improvements of up to approximately 125% in random write, 30% in random read, 20% in sequential read, and 25% in sequential write speeds compared to the previous generation. KIOXIA CD9P Series SSD highlights include: PCIe 5.0, NVMe 2.0, NVMe-MI™ 1.2c compliant Open Compute Project® Datacenter NVMe SSD specification v2.5 support (not all requirements) Form factors: 2.5-inch 15 mm thickness, EDSFF E3.S Read-intensive (1 DWPD) and mixed-use (3 DWPD) endurances Sequential performance (128 kibibytes (KiB)@QD32) – 14.8 gigabytes per second (GB/s) read and 7 GB/s write Random performance (4KiB@QD512) – 2,600 KIOPS read and 750 KIOPS (4KiB@QD32) write 2.5-inch capacities up to 61.44 terabytes (TB) and E3.S capacities up to 30.72 TB CNSA 2.0 signing algorithm support2 (Prepared for the threat posed by Quantum Computers) "The CD9P Series extends our NAND flash leadership with a solution engineered for today's most demanding AI and accelerated computing environments," said Neville Ichhaporia, senior vice president and general manager of the SSD business unit at KIOXIA America, Inc. "By combining our CBA-based architecture with PCIe 5.0 performance, the CD9P Series helps keep GPUs consistently fed with data - significantly improving utilization while driving greater efficiency, responsiveness, and scalability across AI-driven data center workloads." KIOXIA CD9P Series SSDs are now sampling to select customers and will be showcased at HPE® Discover Las Vegas 2025, taking place June 23–26. For more information, please visit and follow the company on X, formerly known as Twitter and LinkedIn®. About KIOXIA America, Inc. KIOXIA America, Inc. is the U.S.-based subsidiary of KIOXIA Corporation, a leading worldwide supplier of flash memory and solid-state drives (SSDs). From the invention of flash memory to today's breakthrough BiCS FLASH™ 3D technology, KIOXIA continues to pioneer innovative memory, SSD and software solutions that enrich people's lives and expand society's horizons. The company's innovative 3D flash memory technology, BiCS FLASH, is shaping the future of storage in high-density applications, including advanced smartphones, PCs, automotive systems, data centers and generative AI systems. For more information, please visit © 2025 KIOXIA America, Inc. All rights reserved. Information in this press release, including product pricing and specifications, content of services, and contact information is current and believed to be accurate on the date of the announcement, but is subject to change without prior notice. Technical and application information contained here is subject to the most recent applicable KIOXIA product specifications. Notes: 1: Compared to the previous generation, 15.36 TB model. 2: CD9P supports Leighton-Micali Signature (LMS) algorithm acknowledged by Commercial National Security Algorithm Suite 2.0 (CNSA) as a digital signature algorithm to prevent firmware tampering in preparation for threats to conventional cryptographic algorithms posed by quantum computers. Advanced Encryption Standard (AES-256) with a key length of 256 bits, which is the data encryption algorithm used in CD9P, is also acknowledged by CNSA 2.0. Read and write speed may vary depending on various factors such as host devices, software (drivers, OS etc.), and read/write conditions. Performance based on KIOXIA testing compared to the previous generation, 15.36 TB model. Performance is preliminary and subject to change without notice. Definition of capacity: KIOXIA Corporation defines a kilobyte (KB) as 1,000 bytes, a megabyte (MB) as 1,000,000 bytes, a gigabyte (GB) as 1,000,000,000 bytes, a terabyte (TB) as 1,000,000,000,000 bytes, and a kibibyte (KiB) is 1,024 bytes. A computer operating system, however, reports storage capacity using powers of 2 for the definition of 1GB = 2^30 bytes = 1,073,741,824 bytes and 1TB = 2^40 bytes = 1,099,511,627,776 bytes and therefore shows less storage capacity. Available storage capacity (including examples of various media files) will vary based on file size, formatting, settings, software and operating system, and/or pre-installed software applications, or media content. Actual formatted capacity may vary. IOPS: Input Output Per Second (or the number of I/O operations per second) DWPD: Drive Write(s) Per Day. One full drive write per day means the drive can be written and re-written to full capacity once a day every day under the specified workload for the specified lifetime. Actual results may vary due to system configuration, usage and other factors. 2.5-inch indicates the form factor of the SSD and not its physical size. NVMe and NVMe-MI are registered or unregistered trademarks of NVM Express, Inc. in the United States and other countries. PCIe is a registered trademark of PCI-SIG. The OCP and OPEN COMPUTE PROJECT marks are owned by and used with permission of the Open Compute Project Foundation. HPE is a registered trademark of Hewlett Packard Enterprise Company and/or its affiliates. LinkedIn is a trademark of LinkedIn Corporation and its affiliates in the United States and/or other countries. Other company names, product names and service names may be trademarks of third-party companies. View source version on Contacts Media Contact: Dena JacobsonLages & AssociatesTel: (949) 453-8080dena@ Company Contact: Mia CoolKIOXIA America, (408) Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data

NVIDIA RTX 5080 vs AMD Radeon RX 9060 XT: Which 16 GB GPU deserves a spot in your rig?
NVIDIA RTX 5080 vs AMD Radeon RX 9060 XT: Which 16 GB GPU deserves a spot in your rig?

Hindustan Times

time11-06-2025

  • Hindustan Times

NVIDIA RTX 5080 vs AMD Radeon RX 9060 XT: Which 16 GB GPU deserves a spot in your rig?

Choosing your next GPU is more than just grabbing the newest model, it's about understanding what you're really getting for your money. With the NVIDIA RTX 5080 and AMD Radeon RX 9060 XT, both sporting 16 GB VRAM, buyers are staring at two radically different approaches to power, performance, and practicality. So which one should you actually buy? Let's break it down where it matters. On paper, the RTX 5080 immediately takes the lead with its technical muscle. Built on NVIDIA's Blackwell architecture, it packs 10,752 CUDA cores, a blazing-fast 16 GB GDDR7 memory (30 Gbps), and supports PCIe 5.0, drawing 360W at full load. On the contrary, AMD's RX 9060 XT is a leaner card. 2,048 stream processors, 16 GB GDDR6 memory (20 Gbps), and a power draw of just 170W, based on a more efficient 4 nm RDNA 4 architecture. Both are high-bandwidth, PCIe 5.0 cards. But the RTX 5080 leans into raw strength, while the Radeon plays a smarter efficiency game. One's a tank; the other's a hybrid. This is where the differences stop being subtle. Across popular AAA titles like Battlefield V, Cyberpunk 2077, and Hogwarts Legacy, the RTX 5080 consistently delivers 120–150 FPS at 1440p Ultra, sometimes doubling the RX 9060 XT's 60–70 FPS range. At 4K, NVIDIA still holds its ground with frame rates in the 80–100 FPS range, while AMD struggles to stay above 50–55 FPS without scaling down settings. Ray tracing? It's not even a contest. The RTX 5080 continues NVIDIA's dominance, especially with DLSS 4 frame generation boosting frame rates by another 30–40% in supported titles. AMD's ray tracing capabilities have improved but still feel like they're playing catch-up. This is most noticeable in real-time lighting heavy scenes. That said, Radeon's efficiency is impressive. Drawing almost half the power of the 5080 and producing far less heat, it's a smarter fit for smaller builds or users who value silence and low thermals over raw power. If you're planning to build a system today, your choice likely hinges on two things: budget and performance needs. The RTX 5080 will almost certainly sit in the ₹1.2–1.4 lakh range, while the RX 9060 XT is expected around ₹55,000– ₹60,000. So here's the catch: if you're not gaming at 4K with ray tracing enabled, or if your games lean more on rasterization, the RX 9060 XT still holds its own. It's quiet, efficient, and affordable, making it a solid option for 1080p or light 1440p gamers. But if you're chasing top-tier performance with headroom for future titles and want the best AI upscaling, ray tracing, and raw frame rates, the RTX 5080 is the no-compromise option, assuming your PSU and wallet can handle it. The RTX 5080 is a monster. It outperforms, outpaces, and outshines the RX 9060 XT in almost every way. If you're gaming on high refresh-rate QHD or 4K monitors, this is the GPU that justifies its cost. But the RX 9060 XT isn't a failure. It's a value-driven, efficient performer that makes a lot of sense for gamers who play lighter titles or don't care much about ray tracing. Buy the RTX 5080 if you want top-of-the-line now and for the next 3–5 years. Buy the RX 9060 XT if you want reliable 1440p performance and a GPU that won't turn your case into a space heater.

Astera Labs Leads in PCIe 6.0 & AI Connectivity: More Upside Ahead?
Astera Labs Leads in PCIe 6.0 & AI Connectivity: More Upside Ahead?

Yahoo

time06-06-2025

  • Business
  • Yahoo

Astera Labs Leads in PCIe 6.0 & AI Connectivity: More Upside Ahead?

Astera Labs ALAB is emerging as a key player in next-gen data center connectivity with a full-stack portfolio spanning PCIe 6.0, UA Link, and CXL 3.0. It is the first to market with a complete PCIe 6.0 solution set, including retimers, gearboxes, smart fabric switches, and optical modules. The Aries 6 Smart Gearbox acts as a bridge between PCIe 5.0 and 6.0, addressing speed mismatches in complex hyperscale systems. Meanwhile, Scorpio P- and X-Series Smart Fabric Switches, now in preproduction, support both scale-up and modular scale-out AI topologies. Combined with Aries Retimers and the COSMOS software suite, the fabric switches deliver telemetry, diagnostics, and system-level optimizations for high-performance, low-latency AI infrastructure. Astera Labs is advancing next-gen data center infrastructure through strategic OEM collaborations and a broad standards-based product lineup. Its work with Wistron on NVIDIA's NVDA Blackwell-based MGX systems showcases its role in enabling full PCIe 6.0 support for AI servers. As a key contributor to the UA Link Consortium, Astera is gaining early momentum with the UA Link 1.0 standard. Beyond AI, it's expanding into general-purpose compute with design wins in SSDs, NICs and CPUs. Adoption of its Leo CXL controllers and Taurus Ethernet modules reflects growing demand for CXL 3.0 and 400G/800G Ethernet. Astera Labs leads with a full PCIe 6.0 portfolio comprising retimers, gearboxes, fabric switches, and optical modules tailored for hyperscaler AI clusters. Its Aries 6 Smart Gearbox bridges PCIe 5.0 and 6.0, while involvement in the UA Link Consortium strengthens its role in high-speed AI interconnects. In comparison, Broadcom AVGO has launched its PCIe Gen 6 portfolio, featuring high-port switches and retimers tested for interoperability with partners like Micron and Teledyne LeCroy. Broadcom's Interop Development Platform (IDP) offers advanced telemetry and diagnostics, facilitating system design for AI infrastructure. Broadcom's in-house SerDes technology and collaboration with ecosystem partners aim to support scalable AI clusters. Marvell Technology MRVL has expanded its connectivity offerings with the Alaska P PCIe retimer product line, built on 5nm PAM4 technology. These retimers, available in 8- and 16-lane configurations, are designed to scale connections between AI accelerators, GPUs and CPUs within servers. Marvell's focus on low power consumption and compatibility with PCIe Gen 6 and CXL standards addresses the needs of both AI and general-purpose server systems. Astera Labs has rallied 46.4% in a year compared with the industry's 37.4% growth and the sector's 11.7% rise. The S&P 500 index, meanwhile, has improved 12.5% during the said period. Image Source: Zacks Investment Research Astera Labs is presently trading at a forward 12-month price-to-sales of 18.93X, which is below its 1-year median of 20.01X. However, it remains overvalued compared to the industry. Image Source: Zacks Investment Research ALAB currently carries a Zacks Rank #2 (Buy). You can see the complete list of today's Zacks #1 Rank (Strong Buy) stocks here. Want the latest recommendations from Zacks Investment Research? Today, you can download 7 Best Stocks for the Next 30 Days. Click to get this free report NVIDIA Corporation (NVDA) : Free Stock Analysis Report Marvell Technology, Inc. (MRVL) : Free Stock Analysis Report Broadcom Inc. (AVGO) : Free Stock Analysis Report Astera Labs, Inc. (ALAB) : Free Stock Analysis Report This article originally published on Zacks Investment Research ( Zacks Investment Research

TWSC Debuts at COMPUTEX 2025: Empowering AI with Full-Stack Storage Solutions
TWSC Debuts at COMPUTEX 2025: Empowering AI with Full-Stack Storage Solutions

Korea Herald

time23-05-2025

  • Business
  • Korea Herald

TWSC Debuts at COMPUTEX 2025: Empowering AI with Full-Stack Storage Solutions

TAIPEI, May 23, 2025 TWSC made its debut at COMPUTEX 2025, one of the world's leading technology exhibitions, under the theme "Transcending Intelligence, Ascending Full-Stack Solutions." The company showcased a full range of storage products and solutions designed to support next-generation AI and computing applications. As AI adoption accelerates, storage technology is becoming more scenario-driven. TWSC provides tailored "One Solution for One Scenario" services based on its full-chain capabilities in chips, algorithms, and application scenarios, accurately addressing the diverse needs of smart terminals, industrial control, servers, and other fields. Full-Stack Storage Matrix Unleashes Efficiency TWSC highlighted high-throughput, low-latency solutions at the event, including PCIe 5.0 SSDs, DDR5, eMMC, UFS, and LPDDR series. Combining performance and efficiency, these products enable AI inference and edge computing applications. According to TWSC's 2024 annual report, the company reported revenue of RMB 4.773 billion, a 168.74% increase year-over-year. Embedded storage sales reached RMB 843 million, rising by 1730.6%, while high-speed PCIe SSD sales grew 979%, becoming a major growth driver. The company now offers scenario-based solutions across enterprise, embedded, consumer, and industrial applications, building a strong foundation for global growth through advanced storage modules. Full-Stack Self-Developed Capabilities Build Competitive Edge To enhance control over the industrial chain, TWSC has developed an integrated "wafer-to-product" scenario-based service capability, enabling differentiation through media analysis, chip design, firmware optimization, and packaging control. TWSC uses its "5+1+N" global supply chain network to ensure smooth coordination across R&D, production, and delivery. With a robust validation system and adaptive quality control, the company aligns product quality closely with customer needs. From chips to scenarios, and data to value — TWSC's participation highlights the shift of storage technology from basic functions to intelligent services. By integrating industrial resources and expanding application scenarios, the company is building an open and collaborative innovation ecosystem for smart storage. About TWSC: Shenzhen Techwinsemi Technology Co., Ltd. (Stock Code: was established in 2008 and specializes in integrated circuit solutions for storage controllers and modules. The product line covers four major series: SSD, embedded storage, DDR, and portable storage — offering reliable storage solutions for high-value applications such as smart terminals, data centers.

TWSC Debuts at COMPUTEX 2025: Empowering AI with Full-Stack Storage Solutions
TWSC Debuts at COMPUTEX 2025: Empowering AI with Full-Stack Storage Solutions

Yahoo

time23-05-2025

  • Business
  • Yahoo

TWSC Debuts at COMPUTEX 2025: Empowering AI with Full-Stack Storage Solutions

TAIPEI, May 23, 2025 /PRNewswire/ -- From May 20 to 23, 2025, TWSC made its debut at COMPUTEX 2025, one of the world's leading technology exhibitions, under the theme "Transcending Intelligence, Ascending Full-Stack Solutions." The company showcased a full range of storage products and solutions designed to support next-generation AI and computing applications. As AI adoption accelerates, storage technology is becoming more scenario-driven. TWSC provides tailored "One Solution for One Scenario" services based on its full-chain capabilities in chips, algorithms, and application scenarios, accurately addressing the diverse needs of smart terminals, industrial control, servers, and other fields. Full-Stack Storage Matrix Unleashes Efficiency TWSC highlighted high-throughput, low-latency solutions at the event, including PCIe 5.0 SSDs, DDR5, eMMC, UFS, and LPDDR series. Combining performance and efficiency, these products enable AI inference and edge computing applications. According to TWSC's 2024 annual report, the company reported revenue of RMB 4.773 billion, a 168.74% increase year-over-year. Embedded storage sales reached RMB 843 million, rising by 1730.6%, while high-speed PCIe SSD sales grew 979%, becoming a major growth driver. The company now offers scenario-based solutions across enterprise, embedded, consumer, and industrial applications, building a strong foundation for global growth through advanced storage modules. Full-Stack Self-Developed Capabilities Build Competitive Edge To enhance control over the industrial chain, TWSC has developed an integrated "wafer-to-product" scenario-based service capability, enabling differentiation through media analysis, chip design, firmware optimization, and packaging control. TWSC uses its "5+1+N" global supply chain network to ensure smooth coordination across R&D, production, and delivery. With a robust validation system and adaptive quality control, the company aligns product quality closely with customer needs. From chips to scenarios, and data to value — TWSC's participation highlights the shift of storage technology from basic functions to intelligent services. By integrating industrial resources and expanding application scenarios, the company is building an open and collaborative innovation ecosystem for smart storage. About TWSC: Shenzhen Techwinsemi Technology Co., Ltd. (Stock Code: was established in 2008 and specializes in integrated circuit solutions for storage controllers and modules. The product line covers four major series: SSD, embedded storage, DDR, and portable storage — offering reliable storage solutions for high-value applications such as smart terminals, data centers. For more information please visit and follow TWSC on Facebook and Linkedin. View original content to download multimedia: SOURCE TWSC Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into a world of global content with local flavor? Download Daily8 app today from your preferred app store and start exploring.
app-storeplay-store