Enterprise infrastructure since 1998. Storage, servers, networking, AI. Independent reviews, lab benchmarks, breaking news from the data center.
Joined November 2011
- Tweets 11,311
- Following 249
- Followers 14,493
- Likes 5,639
5,375 Photos and videos
Jun 12
160 years of fluid chemistry, aimed at AI data centers. Valvoline's new Beyond platform covers cooling fluids for HPC and utility-scale battery storage. Where fluid makers fit in the immersion ecosystem: storagereview.com/news/valvo…
#BeyondByValvoline #LiquidCooling #AI @Valvoline
3
288
Jun 12
Our full hands-on report of HPE's B10000 cyber resilience architecture, tested against simulated ransomware in the lab and mapped to NIST CSF 2.0: storagereview.com/review/hpe…
@HPE @HPE_Storage
3
229
Jun 10
ASUS ExpertCenter Pro ET900N G3: NVIDIA GB300 Grace Blackwell Ultra, 748GB coherent memory, up to 20 PFLOPS, 4x M.2, 10GbE, single 1600W PSU on a full liquid loop. The deskside DGX Station unit, and Jensen signed this one. #Computex2026 #GB300 #AIworkstation @ASUS
4
851
Jun 10
Veeam added three agentic AI agents to its DataAI Command Platform for privacy and AI governance. The Data Subject Request Agent cuts DSR form launch time by ~50%. Consent Agent ships now; the other two in Q3. storagereview.com/news/veeam… #PrivacyOps #AIgovernance #Veeam @Veeam
1
2
443
ASUS fit 12 U.2 NVMe bays into 1U at Computex: 8 up front, 4 tucked inside, single-socket Turin, built for partners like Weka and IBM. Also on the bench: an 80-bay vibration-damped JBOD and the all-NVMe VS320D-RS26N. #Computex2026 #NVMe #ASUS @ASUS
6
39
2,723
Our full breakdown of Synology's COMPUTEX 2026 data protection lineup, APM 2.0 and 1.2, the DP5200, and what is shipping versus forthcoming: storagereview.com/news/synol… @Synology
1
554
56% of enterprises now run or plan production AI inference on private cloud. Public cloud's share dropped 15 points to 41% in a year, and cost just overtook security as the top public cloud concern. storagereview.com/news/broad… #EnterpriseAI #Broadcom @Broadcom
2
243
Cisco Cloud Control collapses networking, security, compute, observability, and collaboration into one login, the foundation of its AgenticOps model where humans and AI agents work from the same telemetry.
storagereview.com/news/cisco…
@ciscoDC #ai #cisco #datacenter
1
5
480
Intel VROC isn't dead. Graid Technology now owns it, and CPU-based NVMe RAID is back in active development: a 24-month roadmap, Intel Xeon 6 support, no-cost upgrades, and SupremeRAID coexistence. Ships Q3 2026. storagereview.com/news/vroc-… #VROC #NVMe #RAID @GraidTechnology
1
9
670
MSI's slot-loaded RTX PRO 6000 seats like a blade: align the liquid quick-disconnects, the power blade, and the PCIe slot, push, done. The liquid-cooled card is single-width, 600W, no extra GPU cabling, up to 8 in the 6U CG681-S6093. #Computex2026 #MSI #LiquidCooling @msitweets @NVIDIAAI
7
23
203
30,546
Four NVIDIA DGX Spark nodes in one tower at the MSI booth. Each EdgeXpert brings 128GB unified memory, so the cluster pools 512GB over an NVIDIA switch below, though any 200GbE works. A nearby demo meshed three Sparks back to back, no switch. #Computex2026 #MSI #DGXSpark @msitweets @nvidia
9
35
4,608
288 E-cores on Intel 18A. Xeon 6 is Intel's first data center CPU on the node, with claims of 2.5x prior-gen performance. Full rundown covers the E835 200GbE Ethernet line and Crescent Island's 480GB inference GPU. storagereview.com/news/intel… #Xeon6 #Computex2026 #Intel @intel
1
6
349
160GB/s reads at 1,024 GPUs, scaling linearly from 32: Nutanix Unified Storage is now NVIDIA-Certified at the enterprise level. We cover the 10-node all-NVMe reference architecture, Spectrum-X fabric, and supported GPU platforms: storagereview.com/news/nutan… #Nutanix #NVIDIA #AIStorage @nutanix
4
337
Full workload guide, including all four FIO tables and the I/O-intensive database results: storagereview.com/review/fro… @Dell @AMDServer
1
392
Synology's flagship PAS7700 at Computex 2026: active-active dual controllers, 48 U.3 NVMe bays in 4U, NVMe-oF over TCP, FC, and RoCE. Failover in about 5 seconds, up to 2M IOPS and 30GB/s. Built for VDI, virtualization, and AI storage. #Synology #NVMe #Computex2026 @Synology
7
652