ASUS has revealed its upcoming ExpertBook P5 laptop, set to debut alongside Intel's highly anticipated "Lunar Lake" processors. This ultrabook aims to boost AI-capable laptop market, featuring an unspecified Intel Lunar Lake "Core Ultra 200V" CPU at its core. The ExpertBook P5 boasts impressive AI processing capabilities, with over 45 TOPS from its Neural Processing Unit and a combined 100+ TOPS when factoring in the CPU and GPU. The NPU provides efficient processing, with additional power coming from Lunar Lake's GPU with XMX cores, featuring the Xe2 Battlemage architecture. This is more than enough for the Copilot+ certification from Microsoft, making the laptop debut as an "AI PC." The ExpertBook P5 offers up to 32 GB of LPDDR5X memory running at 8333 MT/s, up to 3 TB of PCIe 4.0 SSD storage with two drives, and Wi-Fi 7 support.

The 14-inch anti-glare display features a 2.5K resolution and a smooth 144 Hz refresh rate, ensuring a premium visual experience. Despite its powerful internals, the ExpertBook P5 maintains a solid profile weighing just 1.3 kg. The laptop is housed in an all-metal military-grade aluminium body with a 180-degree lay-flat hinge, making it both portable and versatile. ASUS has also prioritized cooling efficiency with innovative technology that optimizes thermal management, whether the laptop is open or closed. Security hasn't been overlooked either, with the ExpertBook P5 featuring a robust security ecosystem, including Windows 11 secured-core PC framework, NIST-155-ready Commercial-Grade BIOS protection, and biometric login options. While an exact release date hasn't been confirmed, ASUS is preparing ExpertBook P5 and other Lunar Lake-powered laptops to hit the market in the second half of 2024.

Leading provider of advanced AI solutions AAEON (Stock Code: 6579), has released the inaugural offering of its AI Inference Server product line, the MAXER-2100. The MAXER-2100 is a 2U Rackmount AI inference server powered by the Intel Core i9-13900 Processor, designed to meet high-performance computing needs.
The MAXER-2100 is also able to support both 12th and 13th Generation Intel Core LGA 1700 socket-type CPUs, up to 125 W, and features an integrated NVIDIA GeForce RTX 4080 SUPER GPU. While the product's default comes with the NVIDIA GeForce RTX 4080 SUPER, it is also compatible with and an NVIDIA-Certified Edge System for both the NVIDIA L4 Tensor Core and NVIDIA RTX 6000 Ada GPUs.

Given the MAXER-2100 is equipped with both a high-performance CPU and industry-leading GPU, a key feature highlighted by AAEON upon the product's launch is its capacity to execute complex AI algorithms and datasets, process multiple high-definition video streams simultaneously, and utilize machine learning to refine large language models (LLMs) and inferencing models.

ATP Electronics, the global leader in specialized storage and memory solutions, proudly unveils the N651Si Series E1.S solid state drives (SSDs), which offer best in class performance, endurance, and data retention capabilities for the most demanding applications.

Supporting industrial temperature operating range (-40°C to 85°C) along with hardware power loss protection (HW PLP), the new SSDs offer the highest levels of reliability and total cost of ownership value in harsh environments, making them especially beneficial for mission-critical applications running under extreme temperatures, such as automotive, data logger, data centers, and defense/aerospace. Engineered for 1U Edge servers, the EDSFF offering with 9.5 mm symmetrical enclosure is available with up to 8 TB capacity and is constructed with 512 Gb prime NAND die 176-layer 3D triple level cell (TLC).

Samsung has introduced its latest BM1743 SSD, boasting an impressive 61.44 TB of storage capacity. The BM1743 utilizes Samsung's seventh-generation 3D NAND (V-NAND) technology, featuring 176 layers of memory cells. This represents a significant leap from its predecessor, the BM1733, which debuted in 2020 with 96-layer technology and a maximum capacity of 32 TB. Performance-wise, the BM1743 doesn't disappoint. It delivers up to 1.6 million random read IOPS and 110,000 random write IOPS, with sequential read and write speeds of 7.2 GB/s and 2.0 GB/s, respectively. These figures position the drive as a highly capable solution for read-intensive workloads. Samsung claims that the new SSD offers double the sequential read and write speeds of its fifth-generation technology, with random reads quadrupling in performance. This advancement suggests that quad-level cell (QLC) SSDs are now approaching the performance levels of their triple-level cell (TLC) counterparts while offering superior storage density.

The BM1743 is available in the traditional U.2 form factor, with an E3.S variant supporting PCIe Gen 5 also in the lineup, thanks to the custom Samsung controller. Samsung has enhanced the durability and data retention capabilities of the BM1743. The new drive boasts an improved endurance rating of 0.26 drive writes per day (DWPD) throughout its warranty period, a notable increase from the BM1733's 0.18 DWPD. Additionally, the BM1743 extends its power-off data retention to three months, tripling the one-month period of its predecessor. In a hint of things to come, Samsung has suggested that a 122.88 TB model may be on the horizon, potentially doubling the capacity of the BM1743. This new offering puts Samsung in direct competition with Solidigm's D5-P5336, which has dominated the high-capacity SSD market for the past year. High-density storage solutions are becoming more important as AI and HPC tasks require and produce massive amounts of data.

Kioxia Corporation, a world leader in memory solutions, today announced that it started sample shipments of 2 Tb (Tera bit) Quad-Level-Cell (QLC) memory devices with its eighth-generation BiCS FLASH 3D flash memory technology. This 2 Tb QLC device has the highest capacity in the industry, elevating storage devices to a new capacity point that will drive growth in multiple application segments including AI.

With its latest BiCS FLASH technology, Kioxia has achieved both vertical and lateral scaling of memory die through proprietary processes and innovative architectures. In addition, the company has implemented the groundbreaking CBA (CMOS directly Bonded to Array) technology, which enables the creation of higher density devices and an industry-leading interface speed of 3.6 Gbps. Together, these advanced technologies are applied in the creation of 2 Tb QLC, resulting in the industry's highest capacity memory device.

South Korean startup Panmnesia has unveiled an interesting solution to address the memory limitations of modern GPUs. The company has developed a low-latency Compute Express Link (CXL) IP that could help expand GPU memory with external add-in card. Current GPU-accelerated applications in AI and HPC are constrained by the set amount of memory built into GPUs. With data sizes growing by 3x yearly, GPU networks must keep getting larger just to fit the application in the local memory, benefiting latency and token generation. Panmnesia's proposed approach to fix this leverages the CXL protocol to expand GPU memory capacity using PCIe-connected DRAM or even SSDs. The company has overcome significant technical hurdles, including the absence of CXL logic fabric in GPUs and the limitations of existing unified virtual memory (UVM) systems.

At the heart of Panmnesia's solution is a CXL 3.1-compliant root complex with multiple root ports and a host bridge featuring a host-managed device memory (HDM) decoder. This sophisticated system effectively tricks the GPU's memory subsystem into treating PCIe-connected memory as native system memory. Extensive testing has demonstrated impressive results. Panmnesia's CXL solution, CXL-Opt, achieved two-digit nanosecond round-trip latency, significantly outperforming both UVM and earlier CXL prototypes. In GPU kernel execution tests, CXL-Opt showed execution times up to 3.22 times faster than UVM. Older CXL memory extenders recorded around 250 nanoseconds round trip latency, with CXL-Opt potentially achieving less than 80 nanoseconds. As with CXL, the problem is usually that the memory pools add up latency and performance degrades, while these CXL extenders tend to add to the cost model as well. However, the Panmnesia CXL-Opt could find a use case, and we are waiting to see if anyone adopts this in their infrastructure.Below are some benchmarks by Panmnesia, as well as the architecture of the CXL-Opt.

TrendForce reports that while the enterprise sector continues to invest in server infrastructure—especially with the rising adoption of AI driving demand for enterprise SSDs—the consumer electronics market remains lackluster. This, combined with NAND suppliers aggressively ramping up production in the second half of the year, is expected to push the NAND Flash sufficiency ratio up to 2.3% in the third quarter, curbing the blended price hike to a modest 5-10%.

This year, NAND Flash prices saw a robust rebound as manufacturers kept production in check during the first half, helping them regain profitability. However, with a noticeable ramp-up in production and sluggish retail demand, wafer spot prices have dropped significantly. Some wafer prices are now over 20% below contract prices, casting doubts on the sustainability of future price hikes.

SK hynix announced today that it developed PCB01, an SSD product with the industry's best specifications, for on-device AI PCs. The product marks the first case where the industry adopts the fifth generation of the 8-channel PCIe technology and brings innovation to performance including the data processing speed. The company expects the latest advancement in the NAND solution space to add to its success stories in the high-performance DRAM area led by HBM, enhancing its leadership in the overall AI memory space.

With a validation process with a global PC customer underway, SK hynix plans to mass produce and start shipping the products to both corporate customers and general consumers within this year. PCB01 comes with the capabilities of sequential read and write speeds of 14 GB and 12 GB per second, respectively, bringing the performance of an SSD to the level unseen before. The speeds allow the operation of a large language model or LLM, for AI training and inference, in a second.

In the contemporary digital landscape, Solid State Drives (SSDs) play a pivotal role by providing crucial attributes such as speed, reliability, and efficiency. These attributes facilitate rapid data retrieval, elevate system responsiveness, enable seamless multitasking, and significantly reduce boot times and application launch delays. Among the top contenders in the SSD market, Acer's FA100 M.2 SSD has successfully secured the top place, capturing the discerning consumer's attention with its cutting-edge performance and unwavering reliability. It stands out as the preferred choice for users who demand excellence in their storage solutions.

Acer FA100 NVMe PCIe SSD
The Acer FA100 M.2 SSD is renowned for its exceptional speed and efficiency, boasting read speeds up to 3300 MB/s and write speeds up to 2700 MB/s. It supports ECC error correction technology and the S.M.A.R.T. function, based on 4K LDPC, which enhances error correction capabilities and ensures secure data storage. Additionally, it supports multiple technologies such as modern standby and ultra-low power consumption. Designed to elevate user experience, the Acer FA100 combines high performance with robust durability, making it ideal for gamers, content creators, and professionals alike.

Small, fast, hot—M.2 SSDs. The compact power packs require additional cooling to ensure consistently high performance. ARCTIC offers the right solution with the M2 Pro. M.2 SSDs are true speed miracles. However, they tend to reach high temperatures quickly during intensive use and reduce performance early to avoid overheating. The M2 Pro was specifically designed for 2280 M.2 SSDs. Thanks to its additional mass, it not only keeps the temperature under control, but also ensures that the SSD can cool down more quickly. This enables reliable performance and a long service life. The cooler is extremely compact at 73 x 24.2 x 10.5 mm and comes with two precisely fitting ARCTIC TP-3 Premium Performance thermal pads.

Western Digital has released a new budget friendly SSD that got a serious jump in model number, since the company decided to call it the SN5000. Its predecessor is the SN580 launched just under a year ago and price wise, it's the better option of the two. The new SN5000 uses the same BiCS 5 TLC NAND as the SN580 on the 500 GB to the 2 TB SKU, but according to Anandtech, the 4 TB uses BiCS 6 QLC NAND. The SN5000 is still a PCIe 4.0 x4 NVMe drive, but the overall performance has been significantly improved. If we use the 1 TB SKU for comparison, then the sequential read speeds have gone up by 1 GB/s from 4150 MB/s to 5150 MB/s. The sequential write speed is up 750 MB/s from 4150 MB/s to 4900 MB/s.

As for random performance, the read IOPS are up from 600K IOPS to 730K IOPS and the write IOPS are up slightly from 750K to 770K. The 4 TB QLC SKU is said to deliver even better performance with the exception of the random read IOPS. The 1 TB SKU is said to have a write endurance of 600 TBW, but the 4 TB SKU only offers 1200 TBW. That's 0.33 drive writes per day (DWPD) for the 1 TB SKU vs. 0.16 DWPD for the 4 TB SKU, showing the weakness of the QLC NAND. A new feature for the SN5000 series compared to previous WD Blue NVMe drives is support for TGC Pyrite 2.01 encryption. The WD SN5000-series starts at US$70 for the 500 GB model, going up to US$80 for 1 TB, US$140 for 2 TB and topping out at US$280 for the 4 TB model. WD only seems to have the 500 GB model in stock, with all the others being available in 3-4 weeks time. All SKUs come with a five year warranty.

Samsung Electronics just filed trademark paperwork for two unreleased client SSD models, the SSD 990 EVO Plus, and the SSD 9100 PRO. Having exhausted the three-digit model number sequence with the 990 PRO, Samsung is going with the 9000 series for the next nine generations of its flagship M.2-2280 client SSDs, beginning with the 9100 PRO, which will likely be succeeded in the future by the 9200 PRO, 9300 PRO, and so on. Nothing yet is known about the 9100 PRO, but we predict it to be Samsung's answer to the latest crop of Gen 5 drives that offer over 14 GB/s of sequential read speeds, and over 12 GB/s of sequential writes.

The Samsung 990 EVO Plus could be a whole different drive from the current 990 EVO, designed to compete with the value end of Gen 5 SSDs that are based on the new Phison E31T DRAMless Gen 5 controller with around 11 GB/s of sequential transfer speeds on tap. This is something the current 990 EVO cannot achieve, as its controller has a wacky logic that either uses Gen 4 x4 or Gen 5 x2 (it lowers the lane count upon detecting Gen 5). Samsung will probably remove this limitation with the 990 EVO Plus, allowing Gen 5 x4, and getting its performance in the league of the E31T-powered drives.

Panasonic Connect Canada, Division of Panasonic Corporation of North America, today announced enhancements to the fully rugged and modular TOUGHBOOK 40 laptop. This second generation of the TOUGHBOOK 40, the Mk2, is the company's first PC to feature Intel Core Ultra processors, incorporating the latest CPU, GPU, and NPU technology advancements and up to 16 cores. Its dedicated NPU accelerates artificial intelligence (AI)-driven tasks for customers across law enforcement departments, federal agencies, and utility companies. Compared to the previous generation of Intel processors, these new processors deliver up to 143% faster AI application performance, 73% faster generative AI, and up to 40% lower processor power for AI-enhanced collaboration.

"We are dedicated to developing solutions that not only address the current needs of our customers, but also anticipate their future requirements," said Dominick Passanante, Vice President and GM of Panasonic Connect. "The TOUGHBOOK 40 Mk2, equipped with advanced AI capabilities, is another example of how we're providing the mobile workforce with tools to enhance productivity and efficiency on the job."

SK hynix has returned to Las Vegas to showcase its leading AI memory solutions at HPE Discover 2024, Hewlett Packard Enterprise's (HPE) annual technology conference. Held from June 17-20, HPE Discover 2024 features a packed schedule with more than 150 live demonstrations, as well as technical sessions, exhibitions, and more. This year, attendees can also benefit from three new curated programs on edge computing and networking, hybrid cloud technology, and AI. Under the slogan "Memory, The Power of AI," SK hynix is displaying its latest memory solutions at the event including those supplied to HPE. The company is also taking advantage of the numerous networking opportunities to strengthen its relationship with the host company and its other partners.

The World's Leading Memory Solutions Driving AI
SK hynix's booth at HPE Discover 2024 consists of three product sections and a demonstration zone which showcase the unprecedented capabilities of its AI memory solutions. The first section features the company's groundbreaking memory solutions for AI, including HBM solutions. In particular, the industry-leading HBM3E has emerged as a core product to meet the growing demands of AI systems due to its exceptional processing speed, capacity, and heat dissipation. A key solution from the company's CXL lineup, CXL Memory Module-DDR5 (CMM-DDR5), is also on display in this section. In the AI era where high performance and capacity are vital, CMM-DDR5 has gained attention for its ability to expand system bandwidth by up to 50% and capacity by up to 100% compared to systems only equipped with DDR5 DRAM.

Gigabyte has quietly added a new SSD to its growing lineup and this time around it's something quite different. The drive is part of Gigabyte's new AI TOP (Trillions of Operations per Second) and was announced at Computex with little fanfare. At the show, the company only announced that it would have 150x the TBW compared to regular SSDs and that it was built specifically for AI model training. What that 150x means in reality is that the 2 TB version of the AI TOP 100E SSD will deliver no less than 219,000 TBW (TeraBytes Written), whereas most high-end 2 TB consumer NVMe SSDs end up somewhere around 1,200 TBW. The 1 TB version promises 109,500 TBW and both drives have an MTBF time of 1.6 million hours and a five-year warranty.

Gigabyte didn't reveal the host controller or the exact NAND used, but the drives are said to use 3D NAND flash and both drives have a LPDDR4 DRAM cache of 1 or 2 GB depending on the drive size. However, the pictures of the drive suggest it might be a Phison based reference design. The AI TOP 100E SSDs are standard PCIe 4.0 drives, so the sequential read speed tops out at 7,200 MB/s with the write speed for the 1 TB SKU being up to 6,500 MB/s, with the 2 TB SKU slightly behind at 5,900 MB/s. No other performance figures were provided. The drives are said to draw up to 11 Watts in use, which seems very high for PCIe 4.0 drives. No word on pricing or availability as yet.

Kingston Digital, Inc., the flash memory affiliate of Kingston Technology Company, Inc., a world leader in memory products and technology solutions, today announced the Kingston XS1000 External SSD was named a winner of the 2024 Red Dot Award: Product Design. The Red Dot Design Award, established in 1955, is one of the world's largest and most prestigious design competitions, receiving more than 20,000 annual submissions from approximately 60 countries worldwide.

The award-winning Kingston XS1000 External SSD is a convenient file backup solution to ensure your important documents, cherished memories and media files are always readily accessible. The drive is extremely compact, weighing less than 29 grams, and designed to fit in the palm of your hand, making it perfect for any on-the-go lifestyle. Don't be fooled by its size, XS1000 offers read speeds up to 1,050 MB/s and large capacities up to 2 TB providing ample room for storing countless photos, videos, and files.

GIGABYTE today launched its flagship M.2 NVMe SSD, the AORUS Gen5 14000 series. The drive packs the winning combination of Phison PS5026-E26 Max14um controller, with Micron B58R 232-layer 3D TLC NAND flash memory, along with a fast LPDDR4 DRAM cache. The drive comes in 1 TB, 2 TB, and 4 TB capacity variants. The maximum speeds vary for the three.

The 2 TB model is the fastest of the three, with a sequential read speed of up to 14,500 MB/s, and sequential write speed of up to 12,700 MB/s. The 4 TB model is the second fastest, with up to 14,100 MB/s sequential reads, and up to 12,600 MB/s sequential writes. The 1 TB model is third, with up to 13,600 MB/s sequential reads, and up to 10,200 MB/s sequential writes. All three models come without a heatsink, with just a metal film label on top. GIGABYTE recommends pairing the drive with M.2 SSD cooling solutions included with your motherboard to minimize performance throttling. The company didn't announce pricing.

MSI, the leading brand in gaming products, is proud to announce the launch of the MAG Infinite E1. Equipped with processors up to 14th Gen Intel processor and NVIDIA GeForce RTX 40 Series graphics card, the MAG Infinite E1 is designed to be the ultimate gaming companion, delivering unmatched functionality. Built with the iconic MAG spirit of durability and robust construction, the MAG Infinite E1 showcases a design that conveys a stable and endurance, appealing to gamers seeking both power and reliability.

The MAG Infinite E1 is powered by up to an Intel Core i7 processor, offering significant performance enhancements over its predecessor. When combined with the NVIDIA RTX 40 Series graphics card, the MAG Infinite E1 not only leaps in performance but also in AI-enhanced graphics capabilities. Gamers can immerse themselves in lifelike virtual environments with advanced ray tracing and enjoy ultra-high frame rates with minimal latency. Furthermore, the MAG Infinite E1 is equipped with state-of-the-art transmission capabilities including DDR5 memory and M.2 PCI-e SSD slots, ensuring peak performance and making it the ideal choice for gamers who demand the very best.

Currently, only Phison offers widely available performance PCIe 5.0 NVMe controllers for consumer SSDs, although the competition is heating up and Chinese SSD controller makers MaxioTek and InnoGrit, as well as Taiwanese Silicon Motion either have or will be releasing competing controllers this year. However, it also looks like Taiwanese Realtek will be joining the fray, albeit a tad late, as their upcoming RTS5782 PCIe 5.0 NVMe controller, but the company didn't reveal a release schedule. Although Realtek is known as a more budget friendly chipmaker, regardless of the product segment, the RTS5782 will be an 8-channel controller with support for 3600 MT/s NAND, and it will have a dedicated DRAM cache using either DDR4, LPDDR3, LPDDR4 or LPDDR4x memory. It's said to deliver sequential read speeds of up to 14 GB/s and sequential write speeds of up to 12 GB/s, with random read and write IOPS hitting 2500K.

Realtek is also working on a pair of new DRAM-less models, the PCIe 4.0 RTS5776DL and the PCIe r5.0 RTS5781DL, both having support for 4-channel flash, but still supporting NAND speeds of up to 3600 MT/s. Engineering samples of the RTS5776DL are expected to be available before the end of this year, and it's said to deliver sequential read and write speeds of up to 7400 MB/s and random read and write IOPS of 1200K. The RTS5781DL will enter the engineering sample stage in the beginning of 2025 and will up the sequential read and write performance to 10 GB/s and the random read and write IOPS to 1400K. In addition to the new NVMe controllers, Realtek also had its RTS5736DL on display at Computex, which the company claims is the world's lowest power DRAM-less SATA SSD controller, that also supports size of up to 8 TB. Realtek claims the RTS5736DL is an ideal solution to pair with a USB 3.x bridge chip for external drives.

EK, the leading manufacturer of premium liquid cooling gear, is proud to introduce the EK-Quantum Momentum² ROG Maximus Z790 Extreme D-RGB - Plexi. This top-tier Ultrablock-class product, part of EK's renowned Quantum Line, is engineered for the ASUS ROG Maximus Z790 Extreme motherboard to ensure flawless compatibility.

The EK-Quantum Momentum² ROG Maximus Z790 Extreme D-RGB - Plexi is equipped with the award-winning EK-Quantum Velocity² cooling engine, delivering direct cooling to crucial motherboard components, such as the primary M.2 drive. This monoblock also features:

• Direct connection to Vector² GPU water block and Active Backplate Sets via bypass valves
• Temperature sensors
• Liquid flow meter
• Direct integration with the ROG water-cooling zone
• ILM Replacement Kit

Thermalright brought several new CPU and M.2 SSD coolers to the 2024 Computex. Our tour of the Thermalright Computex booth began with the HR10, a high-performance active cooling solution for M.2-2280 SSDs. Its design involves an aluminium base from which two heatpipes draw heat from the drive, pushing it through an aluminium fin-stack, which is ventilated by a 40 mm fan. The cooler comes in two trims—black and silver/chrome. The Frozen Infinity 360 is the company's flagship AIO liquid CPU cooler. It features a 360 mm radiator, a cube-shaped pump-block which features an infinite-reflection ARGB ornament. Each of the three included 120 mm fans has infinite reflection ARGB diffusers along their sides. The cooler comes in black- and white trims.

The Thermalright Royal Lord is a thick single fin-stack (U-type) CPU cooler. It features a large CPU base that supports HEDT processors, seven 6 mm-thick nickel-plated copper heatpipes, fully soldered construction, and a high static-pressure 120 mm fan with a fluid-dynamic bearing. This cooler supports large CPU sockets such as the Intel Socket E, or AMD sTR5. The Thermalright Burst Assassin 120 EVO, much like the Royal Lord, is a single fin-stack heatsink, but with a narrower fin-stack, a brushed metal 2-tone top-plate, and two 120 mm fans in push-pull configuration, instead of just one. This cooler uses six 6 mm-thick heatpipes, and has dark powder-coating along all its metal bits.

Silicon Motion's SM2508 was first revealed in August last year at the Flash Memory Summit 2023, but after that things went pretty quiet. However, the company was demoing the SM2508 up and running at Computex this past week and it's set to edge out Phison's E26 Max14um in the battle of fastest NVMe SSD controller. We're not talking about any massive gains here, but the reference drive from Silicon Motion was shown running CrystalDiskMark 8.0.4 at the show and if we do a rough comparison to a Phison E26 Max14um, the SM2508 beats Phison by about 800 MB/s in sequential read performance and 500 MB/s in sequential write performance.

This might not seem like a whole lot, but the SM2508 is built on TSMC's N6 node which results in a 3.5 Watt peak power consumption, or 7 Watts for the entire SSD at load. A typical Phison E26 based SSD draws in excess of 11 Watts of power at full load, which is a big difference in a mobile device. This should obviously also lead to lower thermals and we should finally see PCIe 5.0 drives that don't need massive heatsinks or active cooling. In fact, 7 Watts power draw is very similar to Phison's E18 PCIe 4.0 based SSDs. Silicon Motion is still working on fine tuning the firmware for the SM2508, so performance might yet improve to reach the promised 14 GB/s write performance. Currently the random performance is also looking a bit on the weak side compared to Phison. According to Tom's hardware, we should see the first drives with the Silicon Motion SM2508 appear in the market sometime in Q4 this year.

SK hynix presented its leading AI memory solutions at COMPUTEX Taipei 2024 from June 4-7. As one of Asia's premier IT shows, COMPUTEX Taipei 2024 welcomed around 1,500 global participants including tech companies, venture capitalists, and accelerators under the theme "Connecting AI". Making its debut at the event, SK hynix underlined its position as a first mover and leading AI memory provider through its lineup of next-generation products.

"Connecting AI" With the Industry's Finest AI Memory Solutions
Themed "Memory, The Power of AI," SK hynix's booth featured its advanced AI server solutions, groundbreaking technologies for on-device AI PCs, and outstanding consumer SSD products. HBM3E, the fifth generation of HBM1, was among the AI server solutions on display. Offering industry-leading data processing speeds of 1.18 terabytes (TB) per second, vast capacity, and advanced heat dissipation capability, HBM3E is optimized to meet the requirements of AI servers and other applications. Another technology which has become crucial for AI servers is CXL as it can increase system bandwidth and processing capacity. SK hynix highlighted the strength of its CXL portfolio by presenting its CXL Memory Module-DDR5 (CMM-DDR5), which significantly expands system bandwidth and capacity compared to systems only equipped with DDR5. Other AI server solutions on display included the server DRAM products DDR5 RDIMM and MCR DIMM. In particular, SK hynix showcased its tall 128-gigabyte (GB) MCR DIMM for the first time at an exhibition.

Fueling the next wave of AI innovation, Western Digital today introduced a six-stage AI Data Cycle framework that defines the optimal storage mix for AI workloads at scale. This framework will help customers plan and develop advanced storage infrastructures to maximize their AI investments, improve efficiency, and reduce the total cost of ownership (TCO) of their AI workflows. AI models operate in a continuous loop of data consumption and generation - processing text, images, audio and video among other data types while simultaneously producing new unique data. As AI technologies become more advanced, data storage systems must deliver the capacity and performance to support the computational loads and speeds required for large, sophisticated models while managing immense volumes of data. Western Digital has strategically aligned its Flash and HDD product and technology roadmaps to the storage requirements of each critical stage of the cycle, and today introduced a new industry-leading, high-performance PCIe Gen 5 SSD to support AI training and inference; a high-capacity 64 TB SSD for fast AI data lakes; and the world's highest capacity ePMR, UltraSMR 32 TB HDD for cost-effective storage at scale.

"There's no doubt that Generative AI is the next transformational technology, and storage is a critical enabler. The implications for storage are expected to be significant as the role of storage, and access to data, influences the speed, efficiency and accuracy of AI Models, especially as larger and higher-quality data sets become more prevalent," said Ed Burns, Research Director at IDC. "As a leader in Flash and HDD, Western Digital has an opportunity to benefit in this growing AI landscape with its strong market position and broad portfolio, which meets a variety of needs within the different AI data cycle stages."

KLEVV by Essencore had a formidable lineup of high-end gaming PC memory and SSDs at Computex 2024. We were greeted at the booth with an Essencore-branded LPCAMM2 module with 32 GB density, and LPDDR5-8533 speeds on tap. The Genuine G560 (it's named Genuine) is a modern M.2 NVMe Gen 5 SSD with a fanless heatsink. It comes in capacities of 1 TB, 2 TB, and 4 TB; with sequential speeds ranging between 13 GB/s to 14 GB/s reads, and 9.5 GB/s to 12 GB/s writes; and depending on the capacity, the endurance is between 700 TBW to 3000 TBW. The CRAS C930 is a premium M.2 Gen 4 SSD, with 1 TB and 2 TB models available, sequential read speeds of up to 7.4 GB/s, and sequential write speeds between 6.4 GB/s to 6.8 GB/s. Endurance ranges between 750 TBW for the 1 TB model, and 1500 TBW for the 2 TB.

At the value end of KLEVV's SSD lineup is the CRAS C925, which offers mostly similar performance numbers to the C930, but with slightly different endurance ratings. It ranges between 500 GB and 2 TB; with the same 7.4 GB/s maximum read speeds, but slightly lower maximum write speeds of 6.2 GB/s for the 500 GB model, 6.3 GB/s for the 1 TB, and 6.5 GB/s for the 2 TB model; and endurance rated at 600 TBW, 1200 TBW, and 2400 TBW, respectively.